From 5867557ec651bc0a53588af7c75c0b6858cdf36c Mon Sep 17 00:00:00 2001
From: "roger@hammerdirt.ch" <roger@hammerdirt.ch>
Date: Thu, 21 Mar 2024 12:47:13 +0100
Subject: [PATCH] new build

---
 _build/.doctrees/environment.pickle           |  Bin 62007 -> 61892 bytes
 _build/.doctrees/grids_2023.doctree           |  Bin 182532 -> 153003 bytes
 .../.doctrees/plastic_shotgun_wadding.doctree |  Bin 52539 -> 53968 bytes
 ...6e5accfa2c51ba007dd2cfe381a0658d975cc4.png |  Bin 0 -> 20187 bytes
 ...d41307ef7514e245c37c044cb00987aa2adae3.png |  Bin 0 -> 23142 bytes
 _build/jupyter_execute/grids_2023.glue.json   |    2 +-
 _build/jupyter_execute/grids_2023.ipynb       | 1200 +++++++------
 .../plastic_shotgun_wadding.glue.json         |    2 +-
 .../plastic_shotgun_wadding.ipynb             |  173 +-
 ...6e5accfa2c51ba007dd2cfe381a0658d975cc4.png |  Bin 0 -> 20187 bytes
 ...d41307ef7514e245c37c044cb00987aa2adae3.png |  Bin 0 -> 23142 bytes
 ...f3c7abb0bd6ee7496fb1c9f71718a65c2dfa91.png |  Bin 19985 -> 0 bytes
 ...065aff20d9460441e62fe8c1e0623ccdeb4808.png |  Bin 23131 -> 0 bytes
 docs/_sources/grids_2023.ipynb                | 1212 +++++++------
 docs/_sources/plastic_shotgun_wadding.ipynb   |  189 +-
 docs/grids_2023.html                          | 1549 +++++++----------
 docs/plastic_shotgun_wadding.html             |  422 ++---
 docs/searchindex.js                           |    2 +-
 grids_2023.ipynb                              | 1212 +++++++------
 plastic_shotgun_wadding.ipynb                 |  189 +-
 20 files changed, 3098 insertions(+), 3054 deletions(-)
 create mode 100644 _build/jupyter_execute/3b10867ba4b3bf65b1dee903696e5accfa2c51ba007dd2cfe381a0658d975cc4.png
 create mode 100644 _build/jupyter_execute/44661da8d7b6632d7323190eded41307ef7514e245c37c044cb00987aa2adae3.png
 create mode 100644 docs/_images/3b10867ba4b3bf65b1dee903696e5accfa2c51ba007dd2cfe381a0658d975cc4.png
 create mode 100644 docs/_images/44661da8d7b6632d7323190eded41307ef7514e245c37c044cb00987aa2adae3.png
 delete mode 100644 docs/_images/5f56302bedbd28c12ef38d5cf2f3c7abb0bd6ee7496fb1c9f71718a65c2dfa91.png
 delete mode 100644 docs/_images/a17b221991c8fe26eb7f6c3320065aff20d9460441e62fe8c1e0623ccdeb4808.png

diff --git a/_build/.doctrees/environment.pickle b/_build/.doctrees/environment.pickle
index d0d06697594c73abf465812e8a9e52197e63307c..1b4b120eb1b4c3cf9bfb02478ac4eac4b93c4ebd 100644
GIT binary patch
literal 61892
zcmdVD3zQt^bsk7O2bjU&{o+e%5+pGo(KGezswPF55J8dDkRU`*4@;z4_4sS58~tKe
zH-Hg@MB2m>a8f5?HmwtHoMRt3Qer!?*N(k$e2yJIwRY@X=Qyz)Tf0#ld2MUgIX=ny
z#2c@Doc-?qsH&ds0j7Hac^5qFsrn!HzyH1WzxV$4f7EAoeeoy$(|!D3dN}FE_4c)8
z*1l5jb=ob~?hn(0?;F&c;R}VNzdbzj+2M`hQo6(Ic83?z`LGl8dyIwk-Z0fy;!caL
z^g3&-w-T}|D@mtW56f4*q|eHI=CxL8J^@@=mbH>$x;yCwymIMIl~Fe6w4?gkFkO_$
zs`uT`i;N7ry`3wp*Q<vt;mGdquCGy#l3LPVZ!&6?_jZ`h$Ng5b){j{WsfR>r&F^$B
ztF*&;fm)~AuXox4<dH$bYGLPUyV>zVbgSR*w1>CS{XN$0B=vr$w_Y3cn!~gb_xs)C
z>6MkWdOsfc%R#5L5__!{>!H{Eve)*S>q&o%Qb2|ps3*yQB?|n_^cW=;nvm_@O!u*C
z{hn8gI-NcPCmwoF_r3F_QYmk#WN3yt|DF}34+rUS-m9cD=mo4<Z(pt@gD9$B8>aVx
zHtj)+sC*Oj7<9WmmL#>SUawtmuO-8`hUvZ*5C#WZULCaX6bb8nBJ9CS#PSknd5KsK
zc;28NcYxH6b4?IrZ_w$k_v&jg<ZCC8GLXcvX?E5+!?=_lWY>b`AY`?!*GFg2##@lL
zqfb7$T<@;8{aO&S;BvQ92Rl)9`TV8YC6F6!?|ma4wESc_^wFr0v>{6$0%ZWj1D88N
zO~Gz~vgi;xxsNv<c~|O?CTd?K_+G+@fk-$2o(buZ@<#GMAFp>ikej5QfbH|(KkIqz
z00MUl<Rvz>2F*SMA*g|#KI@6rjuY`}tnK+t24woIop6z&E-nO}W~W_?7{EX>!%nm5
z^;%v(9;S1|q<XXt>L&v~0o(zJ;xOIQ_ma!adeTQv4|3Q*x|V=OEucbBcY{yOeh0)R
zNgSrTxIm)#{h%eg#sUth<~5t0t2GRoPLDctbR@IhuJu`~i}Zs??+p6gK_5dYL~+1P
z;?C9Kh8q2Pi=o_b^<C+S5m12#+=#U?k@nC?UaJ$L<2yQ01PLC=k!&kSM7po(_1QI$
za;@G*tv%f^;weKhNE(CgI#|MovPi#~9uZOxbZfZ~-b(j0z4qF`TLYBs3^YA7A~77*
z^vs>K(+Y{#@_MU@(X}gK{Q=jG8#sJKDwuv}ZLP`V;LX$y;iS^$I4|3f<bARyTq_a(
zx#lAE<OAUY@>PlGFjZ|7J26a;i*n0IUB<{^J@KBY(i&7{eGT$|EIlbfj#H4ukH)78
z<cdEOAC8a2N8@Ah@%Tji?zj{`ax;EBej+{{FU4o#C*!A(bQV$=FUKpf7VGKW*Izhy
z{?!+jTj4N$09GJbsR=EVtU#!ntP3{q%wwU~_iEi<2SbWRsu=vk^j)Ks)}Z8*8tFDw
z;EC}9HQ1_N=UN?O34=xzd}_2{w+S;<4{DI+{@S1ol^2GEb{`)toeWwn4?5n^beo#j
zB~%t0H)9jMw(!3lSK{i;`04nW_+0$H`2Dxy7jMNc#V^MnSbbN#iUP01uf`YR*W!!m
z+%+boG=BYNeCbyF;rJuzf{<`&oE9WM-Us6Z8EyC?mj)k+9(3VOt_RZntUG{~gw~Gg
zO|Ase{ao-zk`{SVqfls3Fd{Prq>h>_5GF5Oc&&%w&cgHcpg)A2eI2T0=W-8<Cp`!g
z(eDj{{s8$HlStaZdB}yhOhUX{k|+M`AYByp1-6Qm8@JDMiD(B}?~-^bJx;y>%n)Eg
z{k^}ww#<`u^+|JLxW7SvdD46UwNdt)od9&1e+9Y_Y@?h(VI;#OLnC|8e<!4P7sto4
z*R7+KODOaz%4BZDE?9U_mh}DJOgxA2-%R(M?*s$xBV}dhP_*sAjflUP?tzjfuZT1-
zO3%H~3EseK0Wex>as5od-VZ*#j0EJ9&D|hb!|xb=b{Ky-JxsDbD#|KrJ|6}u>BJ`T
z%=1|~7kJ#6feW`gu7@G?-pzDR%exk`E>!ae{ww~adxYg;A?5WLT&e`muy&jlNvGXh
zAKo1JUb>4X3@;4)N%+TqNBE5K-;MuS{9T~Pk5j=(-6@p($-HE-cZCu^lb6`EvxVZn
zkQIl5uJzz34dd^`Q;YRIa5&w^hl`TRbgto-$#@Kb>U@hl*d7T3arXe(<c4?6gcafb
zC~D8;zF~S$YOR;xT0Rf00!h{|EDTgp3hmPp#K`-nrD64Y%o`?2dXx{*F2gV(^PkkX
zhmvkP1+^~*KM>+lC?pATM;I@otzrCxaJS-aA1>PND_#?Rq!??!u7N>@;dOBxju{Nz
z4mkb83!fiywf*n#kRFnS3U(6K8Xg4f8x<to{<~Cgj)a0d5oj}BbFRml48BvAu&dt*
zz4h#MFMq8?t^V)=uMsnt5ngoxL)e2`1jm><1gD3;!^af)CxtqwDRa#k#)n*b{5mo8
z#`1NQcjG$7_l=>bSXyIn&#v{QlM@X-^{Mq5+~sxxGIICpRyrrk@b3N3@fStSJp@+r
zou|a>@ePr6K&nf4YaKEa@IMFrsO*+uM@75w**Fqq_k}F-;0{9Upu9xC(~~eTwP?`h
z8WtW=4-*vllVH<LQR^TTfKN04O{kk$#>4$yy~Ta~Hr##82O?-@IE}TW>%n!rB^%|Y
zK{(%V>3AZy*PL;OW4Pc=a>Fxvg5nZSNw-6JnOwXD@crZuk`N}smm^Q}deKM1#0H}y
z^vo3qSF#d#ZA_5hgwy1u*I#MY{S`Q95I=Ldx<cBy4BRin`X?(=L37uQ8^0CtJDv`&
zr`u`M#BP}W)w|Sscb$74vaw?OlX8j}{H6AviSc+q@ulX&TEL~fAkr5vGuF+gaZ(!K
z&IxuNhnUsdA^d4_BryrWw2$V4P}W>p=3(e-tXsz%O^Gj0f|@8K9p-Wgr3A6)*Wiw0
z!YE~Ve-|Q44wINS!qe_TC-7mvuZ{2lX69l>e&GVCm4hOUY_yyp-5BzWeJ!s|K4QXW
z*K#E7Y1jMRdT@Dtc#9X>FW+nMXlZ8nmZ*DlG#R3}22Ck4$#Lb_9Fg7$JQ6&?Ehclg
zx{YVXe=Yv&q7*j)a$-kXMUA;bq}OZgZBS2H5{csi&k?{CQRe&2qy_~_6Fb@b0wrON
z#CnivS#=(>$zBbeMo30MOF+#2+XD>$jKqfvX*G{)6{z;N&qEdSo*gab%L$eAZIssJ
zYIl3XgUQ&#BQ;R&AP}NGAUhmP?%c6~fVar~OqwSPx997EK|EDig%_XOBjZauDV>yS
zI?qe+fi-M=Y}<YJ@gK@LoaYo`Em^j#$O8@W*R$jWUP}fU;-xHI;HSDaj6am+2oD+f
zz+sLNE-6%!&T|%`h@Z@A9pLRCrqu4&qdG-d<_7J{ZG?bCH>d{!7cu=FHk!rG?cvo2
z^-!b>8j3Cj6s;PbDJHF<AX7;a-yX|6dQnthgm@DMn{@SgMx4a`3~fPF755k^mkJVL
z_8`T4hkz@3LCKiKO2N#ECYYwOVPg?}D`Ej{QNsww$W&wDDDN;_N|9c>S`TR`$y%aM
z+(aQ_LC$`?4KD|fNhFAtq6CkEk!Bj+%yJHL$e6JPy}IyXM@cR6VSb>GFrh~5X*B;3
zuYa{yr<np-SWGD95u&Pp3RS#jh6112a{YIJyJB2smA&JNk<WXn1fTWtq6c|Vbgb8}
z3AY&YVWC7t4v#<zwan+oygE%8`NJT-A|9^B*F-f5un$)yP>nC8{#`P6%FY!c5}1<n
z#)j!9?`|V`fFp0><9D|Su*hdQ^iSMf=qk#RH}Jk<1Gfu#6Yo(?1aCyJMUh#VZY~}$
zd5Gikpp!Db$9M*XCu)N(oD&AOk-N`as>DP-fx7TLXlwYqJXutt7zTN`aJ;zH%(6u&
zOc>)DEPtIMmp4UKkw?yFKKDR;PvE|+?7}i(g>Vz~f`XZF?0U71&!-lAQY?Upky8L9
z8i{{B{tZz;#3l;ETqH}W?>6gw!VlyBRxyJ_Nk)zo+G4uIHHvV}Y0@M!d2EW)MRbmu
zgBoim%<Badi7dh<9jT%q(tQ%x5Wo!?0vvCYP!e%%iRnqsH-Qju2X*<}USXW6imS@|
zksJ^qXi{Jh2R>^%o{t@xGq$==E|iB^*@NR*^+Y%~6tR7zkWDjoKBZGINaKR<>HUR5
zJ=TIfk|ij!*Z`HQ!S(O2*Hqmn3Uw)sX2npf13tAvwBGB%86hiMN*^v1h2f<IlmISP
zv);l4fR{L0D8bE1ExCf}R4F}D$Vf273`nh~hr;@m<!qKxg4c>rXQ8BsG4WZ}@S~re
zzwbUZ-zvd)cwP27TYKSJcM0JuSb{U9>$GN4>LGgDYnMdgGUU1me{5;x<I7Jz^=+Sc
z?D~zRGoSwWn{U1O=36UkXG^EweDkp<PM>+Ew6aoq?1@r~VOCj!7AjqhG1n`>>qERd
zl)&b1%+Iep`Q&`*$<phb%1KEY<`9b|*ZQRhtSxz^3ouE`C`ARI!_3fYm9A6TjZ)w1
zVWP?ll=__#L=}XiqFFhC_6-HN^!%kuB}K4OCn~i82N-r#0a01>IVoK~|JtjUI5lpR
z-pDZeq-ge&rK?!P5||1p390tVd`4A)4^><eRnDqr6mcOONxu|ep@Ws4mEBq9uhhXM
z#1R>YNz@c&JdP{oxh0ySMC+Wk&H5Eq0;Zf@^{BKYsi+zuE&_tUQDG2@uJbxnfWu#Y
zd%$|@m!v>pfhq&F4B2@Bixo>mu+p>d<+ULVG&q*doOy=Bxlt4t0kGa~vmR048P4sM
z(({-f_?X*5B3K*DCGjkYIDe_001eDsSh!sJNWIxC`K;7M#0U~YGQ^wi$6lWn)KtlN
z^bAU6(Bx&>rL~^t^U_>`ymp9wbCE4|>kMk0n9j2}AW^e@x=&3(4Thz9yCecn1vc`~
z?DIfWuoAs_o|I9$f0m;!u)oOl5S2KKj$kOUYhCa(@|p=dTOwUU5Jah0NYN0(!QZoz
zF(M~VCBnQws%5k==@e>Rsg&oTQ2^=DN6(f>hn(*O=ShR`Bqab>P=rtKx`I#i&WGYN
z^PFQK;rUMKDl75D#1dFtqGr&!ydC68)s>Wps*k?(!s{=Tvyj`P-^L*kWRQ_iCM1Ey
zBackNxLEilfi^E&>_UcHfCylp$sW*HrD!c8;ZSg-`Z+p~L@dBksGFMO;Atc%Mkq><
zqzg)*xi-5B#luzJ=}#=3E<H7on@B!=W@-7!GpEmRu+Syos8o)3fH$I6iJ==s<;)m#
z(Q8m1dO-*x5tGE?<8S5M6Fq-_X8=w}8Ot-*I{g9zxB!l1<^(U~i57`?FLwGu77J~X
zNG#<=)F2`rV;C$a<d`g-ezSf0Op(%D#sGz&F7uZqL3}|;A|5eG6#Mk2OGU)Rt3<U3
zlxmH3U%*_ZFv}7(l|!epBVAhV4w87OP<^y4VIy>!pg>Z3;)!Bo8}T6c1ttmTygMH^
z-WmlxCN@-;{*Bci?}E^)qIhY9N|Ls$9VQ=vG2-1PrWCcqnbH%*G0BBk!J-ax?$q0S
zmqD^r9D%Z?V!}vGf&hNyvh+y)mKBtprdA%ApaD0M^A4maK--`k!6n`cinuMEDLwn_
zv!&Cgr-d#?ccyh-Cg*^IO{AfR2@;Y6RSE4A@zDpv)Gjp!7_HEICCr+!0Pi(LJq}Tk
zI2%^W3AP0-T_GciAE3&ud=Xo+PjYBs^c1Pmz(x--&cuj@2Stp40)L&GVi;6RnCc+L
z8mTuT3MowQN(b9e5ESZ^dxJJtlid8mxYDFQ!?VyZwmwOjdi2fqqa(w*PzvZ3-j)+s
zZ?>eJEtPd4{UaVhp(LCE1h{gIsCJ@YDRY^SZg&s^SrD6qY9K6}+r#<p9kov=F9I8n
zJsk&=4Lht5Hjyw?2rk`8b^-wo1)FvyVOP_}T}eQMym7fRV<09(VooLafvpy5rDGRg
z>5wx`u|tXi;qdb@D@YKzl=B!d2^FDKY=Kd8r*!*rNmiDVHZeWQVs&!XB_~%Rv#<ie
zCvu`$F@eK|7sPpK0>NXDa(5FgCWSKi1QKU+K}${d9^w-;T0Z8h$9zTuK43;mo5UJ_
zgF;+|wxH%>%&RaNrM6@wmQU5J8U>S(C})0%Qu7r;LCy3TMeQJLFE<jJ@LcIFw^@Is
z-EFPNvd>|qB(YZ@GUZmQSq=y{6qa;SYmSAus6cJMYD$LBC|bMy%_Rib-#jx^kp)#I
ztix_$F-{cvI2C$J70Lj?=+X8s$ph7}LDRZCJ^t1BUkU^csKqrY0pR`rMd7=HDxFsG
zC<dW2_Nj~k1w(I%(uY+d4OzK&OGX|a$g=WahL~JXY+A%1PpC3HN}`tbIv7OvzyCw8
zyi&Sw?$sAc?|I?Xb1%R0+`04TUw`4!rS}d+%g6GnViyo5*0gQy=qu+gy!fGWFQVQn
zuRPbRFL!!tvQB(4Zj+$JzZw4<E^zZ=IhOBWlM5Ik1shKwFFd#+7a<-L85rSMcLTG<
zHZg3q7__i|kVBJ;yHw;FLLXQg;K}!k^8HS?iKTdK^1>V#WQ8`v@&-}-s3@>8s8fW=
zgApR$y1m^I%OXcaHJ(L5BCK5?hRbX17g?Ac@%?XzL|~s4eA5=~!T9KRVtjB#N(%Y$
z(j_nj9$W;IAxf06nh4FtXBZ-QR4(i(Ds$MS$1@0}H_>Cc2>9_=ATsT<FJjZg<+rX6
z$P*7}C7mU?XHY19ebC0*ICg=MpywqX$NU%+Tr2T7EO+5x(Gb_p+I$mHu72lDxfud0
z8Edp8aQ#h;a(0!XeQ^A*zX{1Fr!S#(jvLpdol0)x4ZVrYfV4RRyS}bxu!$<zl%}-i
zvn1JPM{}VHDBPDN<`5q*y#Pmdc47__&cNe>frT)jS^%KzxD$7IF)0GD>@A9mi8XP#
z;&xDg5P32#SriT!4bB<}2Twjos+LcyHY~qAm}jWfh-@+?SK-n^8NMMA`Wt(S>OF`$
zg*IioSp&4_qpIGYgYPlS>JcrCnFn2+RXkKI0mliEuhnfFWFbdwTogm9ka4xsyG+1V
zcWtbKZJ&tt!|3shlX)vLBd0^U{S%K2JznggyjTx<0JaA)Ff15|ZIdrP*ZUd1aK_8-
zg&4~CEi^ZFpzIb)=U9OfTR2Lj2$#IoZP@I=Yb;WYe6Wkr`~W4kyvqn~3e`b7EqEYJ
zEu0>qopwzo;+86+-1sM%9XteuRc}WfirbBBJW&Y6U&mV7XSd&XU;6IX;E17*3|b&t
zrx5}zx1TJ&T2HY17)BpEMU$aI{jh3dTz4K+Sp|i}yL((^Ow@fD);U4aJ+xDrc25YI
zI;H@$(Kl=esyCtV22u;2RGC4qgI#smb_>OEf{*R6f~KUZ;K|KB`E2>GJo?lprF~lD
zMWla<?43|p*rX#?oOvFF+cQUr94MYgcyZ8TC)TI~#Y@az!~S(>+<re>Lp~7HXrovk
zB97TNq+D6a!{pvUwN1)9NPDAc>ESY4hp2~Q-FFT<kJj2Ab%;N8urqfjHfF$uoFjYR
zL|i`IOMzO<0eaY;yoVOtDSS#hOU05EsqG%N8|~}IFbrXh@9Kfq!O`Cz$W1xuLhXvF
z)(%ewe6K<cI}wx~kOd@RP6XYqSQi-IvA_Wz;sqv>;V5O@h7ibwM>tpmrk%@J0lfvc
z66W;?RTCLpkZ6OS%DbPUuH71Kq4g+GQ=@<%b{8eF>d_-&$dYSc8?@gZfSg!F4r_f_
z4!OHW?%O#A!N(Y6%`W_)b|^Rh4CAk-d$SzAkbWe4RR!TsU1<CZ3_tD;<k?u5q6GnR
z!qQ!=UB+<Bik-}h$>y?|!!|uHwm&b%x1mjJ=dw@B1|hbBW~!;2gE*LjKtbAEKM@Fp
zBcKpR^H1b;#Xc3KbZ=!Hxj!$`;v3d`ty&Wn9VQ}gr$Dm=o|KSuYz<IEE8r-0pV7Vn
zm3bg<L9Fbi3sV2S1a9RWeK0RaUI|GBMkMVUz#z?WDNsHuCN|BymBTuo!{QysEK2N1
zKd>@LdMkdty%N{4g&(Wd3e5toGPt77p{$O|$ZM7IhA>UY&L_x|6CEtk=cGOeff53m
z@BX08V?2?|<{`2nqearaVhF%?&_s<K)~wKkCAU12ETz(XYF6?#{1F-;dHZ5Ea!_XQ
z{c?OaoUE}=W^g|Sqo9pN(JN{aTFfi>KLX^j;%<HDXtnnA@UqA_TUz!)?3v;Vt;=Dr
z)1_lU67->w$~a+#k+JwZh5RW>L3%_MJU&*ihJCqM&dN*kcY)IbBc*92lT;=4SOLD6
zdpCZYthQL!Y<vyRVrts>U+^eP{IB`rzs(=Njz?AR-xZ#Jr||sm@!a?ZCD8P^@q6_8
z`|344R)}(lH9Q$q5V#-ZM;pkw#xXOmcNv&tAF)(^i#&5JYK^3Bc4`J2>$$Q&!fPq9
zP1doCgYRAAnJ0KA%m~fzv5OXFj-LloO^zR%!Crk{Q{>QIF5y>XJF)~wX_ILv)p!6Q
zx3r><TuESazH~%YgCdihQ+Qi7rO0GFL3CARCQX<jT3u7&hW)%V+(DBYmj$XPdAf3H
z#O78mkeMgJ3vhi$%lb8_NcaZB)n5|z5A*Ee*&@D`pg>*Z<x9122)13v|2Kx8lU|HK
zfGCVbI-pEjY&pFZ0)l2C&CsODZ+bo!7F53Icrjn>W>p5CBUsE15qRXGCXS?NU*v}!
zZ0*9~IkBNgN|uljv4H|!FptluwgpF2ltj)nhw;A_w4p;v0pgt<+H*^17IM-YKo;?V
zZyAN>gl$ZOCyqRbs&tHseB9AOjgRiY(BWt=qJRh~k>dqls$3pmS3<vBmJp7i0OlQS
zO!#|i*Fd>CR9=q2gacGKQ^G;tuMQ50LtgMQU{+~UEsXzL83MOCoh30;VED<cV%6Ip
z(ZaD7fkuADOiuft4QK?8pfP&hOihDuOoqe2i7a(aO=T6jFj_Y|t2S0u<rJ#k?hKr$
ze>`uRd!p)yTmi^~U{PKQ!D!lC(iR1?F+Wm9_>aEIEObxh6u{GwI~*5X!?X=9r-x%B
zQlcqC%1#%00zuxwt~`<(v9JRN845~liBVOLZ^#u9-VE{)Wb;}g`p;*Q!}QoCm@BLp
zVmX{-x^$g<SL`?9EZSH_7_Vb5!G>*Cg^*D58h#R$2VgTK9zb>r^I<Y;SY^PDll)Nc
z8PVwYX+#{Z;^>e}NZRlz6ecPN&!&56be6G2qh1(ZvK&AA2#-+|#933?o!(a?nZ}7M
zC~R6DCJ`;3%nQhK3L8t1ut^YP_sC07n}kywVp8@{Vn%%f64*6~0A*4`B=`nGyYDZA
zk{bzaoEXr##~$Mci#;4Mp{@1F3WY#0xkmtb#aK3%tt<h0pQ6eHYcCxH#K|EzrKy?3
zo?%zY=a})~Ppw$&V)*i)^0D=oSL~0yn0$NNf2yT@p!r&B^<tx6`RK>0ANauKbI)Qi
zg3pM>5)g>%!Kqqr(PVy*zFt6dJm&qJR4QfJy%n-(h~Bj+{`j1}tSwhoV9xt13`b|f
zveya~(kDsPsyL#mUPfSjm_B^lCWnphhtg~O0DcB?2lL^aAxg#y`i)NFku1>>J}y(3
zz+!Wuih~mc7rf?GZ#}_8(W7%wdvfP+-!d<Jc9}*B7G+cpj1tbyVqZ3<vvhh>dXw@@
zEymcg7>aNzx!n+NL$Msg4-}HeMaKgLZa8fyh9B`#9_plXZe0ostFd{am?;k6@^BMk
zS#oMyETA;(1(Ek~F;BW!6qSo;^pnSv&fz5R)8y65b2>*8Y*56|@vbsj_!Dt%rFrgG
z2N(Id`Fd*&!BtE+Y4Jpo`|Y?V`jiz_;aPH}FmH$b70%KCXR{W?vIO5t3Bg<4Mmxo5
zp+csJs0IjIS~{)5j>-U?J_CD=SUQ~_xsc95*@=Tu`{h>0EMe}V%*sytscQ@3y>udo
zFP(`aI$wZTOgO`b<+tplDwf|S9OX;*a(9s;@HnK1WtvH+QHSrK%h{PL62XHKSLvZH
z2gB9v>Iknoq`!=yR2w_98O~#GQwJdP%sRzs5E?+9x&<PGhD#n+cV~M)RkGNSiSqYv
zXuaWG@kF$b(2z%wvzExgqV!`MY6(?4T-`C&KAkT`g^g%I;E){qIG1r`)g7cqWypg3
zX>eccdBuP{Jd%zDN(?$2^-|tEEoXozv>+@r;(osRgy0!QC%+D1J0dFSqEPrGur#XZ
zoGlg;aZds1Cb3wEV+0`XElhn->M}M+B7#^$NRKX0z#zdb16>@yq1mdq6#`pB#ri9f
zlV#C=T3}j%s-TjE7~_R>UoQ#@b)QgmNfRPshuven<vQy}900~4SEdAs>Wx6!&$Um!
zkQ@I+x*rw9JmnfWw?s6GWYPgvI%rW-sfSd|7%D5`o;`}r#~u!~@#QG!lJq#A#^Y89
zjAsaxyyk#Tj~*$WJyFN{pgQ&m8gc@|@Qag(@s9LPC*0CSwN}ji6a;B-FrJRY)YO@n
zLAr;geCQo#ZQ~oz`!AmR?Y}yA`tN<_=Ntb%d;8KKf3@+yWpDrBwXZdPCwu#$ul-!(
zceA%2`*mlK;v^rf=wVTZmJi}jr3>=N92WWLT(meh1Bt>6X$K9szl{U8I4jNDC*AOI
zvADUSylUY%vK7y*R)fgUY(vBUhHF+#JqW5%z?iP<%yTTg>PLa*g?80vrsMmDV@K7%
zWYwx~Ro&$-iRNa|9ZfTJyJ|;PRJB~+4Gmwbm`2qID}KeST9I4v^`L4yj&4Mu=^9$K
zT5+S$U=`DJBk%UmbuZK+-*a@waH7!FbgyEYRXgylAgCCY8)z)_JwLQP-}XZmYKE;v
zh8sjx(~Ddyx;^xO1(j;Wx2sII8EOD%HFO*&a$VhY9ow>W&9bzJRa_R@wyqnl?ddEG
zEZeFE)ynOm+ir!0t{H@u7Mjf03@30sGt?aqbgmi^bD58B8M<McmL7#(SPcxr^xP;4
zB1gAx58aROACLl?AS!V3Gz%Pz!oZCz%ZW_0s<Qz7s0N{nHg#4BY)!93PPJ;{_4d#`
zLwAGF_8F)XSQXn1QQOgMyIRpIk?B=66T)Ff3_OM)xt8rQ&8&o0MT<gBtKJ?uk-%|v
z#@s51f_n~vz^_z{imNfr4=cdlf-FVMFhl1026MDPuR4&az}3KxkVAim54GC~zT^28
zvyF;l+rI9H0Ako)WN8K@L$A1g7(uYK5G{qK6-AN5%t+HC2!rcJzUkk-6Q-|gZpHCE
z3q_*}ng|&KT_91+_JSbtjKJ1?Pt%+*G=hkkuI_0>%Bq77TLSu7=y5(nNmhh!pR8a{
zcp1y$SWydTY9eA8%Z)C(%_y|2N<|MnH*`Qq(+C~YF!d@12MaCT)EpK$wr(-QvI7$o
zx2(Vimt4p53`7{1dHb$f1`ZiR)F4nGmsxQ`+pJg+4TwTu=r-isfb$nt3=gB*#E^ta
zFs%?|sT#f^yZXd<SCc{S3d62{I3%#(4E8FFhVO8#c{|2Nq2<}0p?P{}hfE7K$a9Ep
zyRK{N&;y1Y>Y;1+0hB;hhvI>RRXoEAF`ykQxI=FvunTpW7kN?OJ6;uRw5kz<hI2?6
zI6-7XMtz3C6$FNDvx;W8k*!B04N~^s;mZDYov=0Av#Pod{SfJ)V?gpT>cbE+>oSco
zUx(m_T4-1hW6L&N%W)xQQRvvrLr-tdvOsq$x>L1`K!YlFpdT3Yo8?uj;Gknw+=?6E
zpRZSR(=-jQ3gY+}l#D^a>Yj6Z=&o)#CR7RuwdEq%=0^~;s;O&6SoJ+@P0%4H5i;Cr
z7{D5sFeG*u__l$PniPo5ObS-Qs)6GWdX5)Vbl-&DcYMQkZQBV!fB-`_0BJPcs(?kz
z_ch1YJ--?mzV6;(+<FGopJ#%po@X0QHDDy(S{3pU*_smoY1<FbEoNJq2HobmmC$iR
zGm0v@$L?TKpbY{)#8C50=t@Q=&e1GW$cFD!JZ77K?gb|F8c-pT^bI!*(Lku%cToBj
z$8=4YD41!Zihp+1i8RY5nXy4`%XKxF5+B9`VinnLP;qqEcB-BSz3l0CQ2LPJidQvl
z*RsOE_E0UVfL{UAnc)RCEP17>X%(ndo0<3zW-NjvGMIYJb;3KCL!$~?h)(OMLzdh2
zfvgsQr@m%E3&G_uEyK4$-FJ1e`xe+*!8nBALPYOCcT#G8=m!Dpitj)n1fV}5=9?G@
z9!Tw)z6qBEx*lB7briE;LN!=7sL4BwriyREQ-JP-n1m7RkmXvC7r$aubx;h#2{mtq
z_-9utP831&Rw8&fk?lLCRk;)0Js6z|aQ1v?63e#jif?HU<cL`yxan0)kO!TDvV$$Q
z4ZZ3)UZkP4i~imLcRPaqgXIp)Dyu>Vl5WQTq31!9gR@2i@r1E3NcX@>z+G@5UV#C1
z1pn_2qp8Xq=wiqWq!G>^=wOAB<yL)iX$-5vV2L1AP{x++RG0>(?HCXOU$;V#ig7*j
z4qR%vX&PskkM2Y;<ph4ny-gRfBa+tkMLcBq1^B@#EG~;4L(z1n^pbOzn5MAvBEFq;
zS-|5``w(TIZHjzZ9IJ#Ec_gl6;&4NEU6jSdy>M%n+I^Dl<R{TFljk)|grV|z0_|Jj
z;BlQ>$Xa!}=}esc1rCi@3B5TP^g~EPt%0xZ7^M68w1$?A_+12W>@j1b9wInNK@fDG
zVvH--%5owrpk-Jg%p`*x2u9HD7Zi!ia`U?hW$1B_#KIgl-XN@Y<A#i7-9cye((+A!
zP1xd0;4ZOx{pyF0rgLIB2l0;w1_SPLQKw!+bt3RxBxvI`33DP9>vxrk99l-F*{RqW
zp<<&ZdeHFj_tgWt8$SN7?g80o8u*t&w$BoRcTM;>w7WpI&l6Ue@Qsq~r?v^QZ3o$C
zzWkR$w*T&~l8r;V3uODAoNSfhV3cg;E<v_Akc|QhH-@A63zDqc2FW1Z%>yub^n!<K
zXs1WA%+GM*9<3}Kxwq$C6*ClUtw{F-F>YDKQUjv1jsKqT+4%+(6on@q!vVW`ua2$p
zrT2O3EO{Eo2kD?h@q)aB-w{SE{ZZ5fyxn}WRDam`5xmoVU-N~{Wu#zs;1WI_306y|
z2<_|=@lZVN!8H>33+;?TP>Pq|o9%c*?bYqxAf4-b*g{3OsQviB=ZdWH!)R1oASUr?
z{1{TuvmeKw^yC{fFToyPx&x559+Qbd@M&Ww8b68BjsFQh=s@GA@RvIH)A$QWKP&$H
zy!i7~@#h!CpMSystnTmzjbFhd$BQ(@9q@YiqKM$q9uK-t5PxaSOx`NEfx-g0uL1mQ
z$n7j5N8|Ah$Q^l|CAf|%0nv23R3_T#6H)r+%qVRuqC~QO2b3Oo16#9`!sW3rmADy)
zuC<zo*`G{}S<b&fI*;?mYa7NFmu?|)BqrP(G>9i$!!?K$e9$&{)3^+$7+Ms=Y{4Jk
z%0zJp2BU4F)bjDTmyXHQaAbt;{F_v4N!{#;y+xrI?&%@gaY<)vFdRLc`t8P>R2InW
z%|gGM72^YF7L6d}_5NMc$}2gLwDgZVR&J)df#0B4AM(&BR0`ikEyjMSL8Gqm%lHvo
zYn(t^qSd2Qw<<v#&Oq$vAR2q{XCmzzi<{&$j%=23a<dFh<HHzl{1j7(Z%p4*J-L7~
zod(z<Mbjgv5ZB=-lyej~mERgJt!`i4#>NP3PmRnNp^aHV>_bJt?iCK=u5;x0MY@%O
z+d<m*h=<LM#+y_3Vyj#^ajL7(D372~;LP@M&V2jS2#s;(!?S|8=bTx1o=$>e7Y(h-
z($%NABO)Z?GgG6!Rd(z<g?U=mc7X>w#(8jKYAnWh@Tplr+<P9Jr;}TJ|KMaEe0gfr
zx6T88YD~6W;K9yu9(-wPEXH{7-LrzY_dGa<yZ>?7!=}dKm!?L2>pZ}jjjZhg4|a|7
z;Hy((F~)<Rn-#>Cd9XCA;nrw&QKE(Rv;3GjKS)lm{0a_n+ZDfHh5I!qJ5gi(hp9Wb
zRZeNAupZMd6GmmOGcgkqZ#cMEmiU!BQ8~k}z|Gy`-2C6C#&nFEzt2H@3!SS&G;>g$
z=e(N8gvH(W%C|av3VXdq$&X_d@Lh##wR@6tH9s{rV}zcY6+}L4c5)DR-ML!i98n`@
zA~*D@k>Bc&*e|%DhQ%l+COA{eQ)4p5iKk`-anCt%f;h2NHT9vXyRlWCoa8*YlR8?R
z;AXu(HBMvPd2Ln@_nbTLx+Lxc#El}bGIYn(oz>X-)V<j%liqzwUQdWmHStZ-;q7$V
z1b6Jp)ToW|Dw!3;MqaTgLVOa7IT$W6!w@EH1`s(GcbK-$?2yd8%CIdR(bh>bqwk-Z
zdRvu^J*TkL#oH|ywz+Zt;U7$m!I%jAeGcMV=sz5Oks{#diV^UM)cxhD`?gi;9yvup
zc!~hzU#ThDt+`1a#4k>b&KRkGVO9{iod2xg*4+-6oj?#k-CRpoP+|8Vu6V*hg-K%n
zM^krWtBg5G0Re?axrj$`7_3h4D*kY4oW{8G%~?TgnL9IUp?PvE_>qapis<m%z4Eme
zxF;c-9$~@+=i$KAXpAvo9|!TR)J8;F+N;oO;pQCP(TPHDPTjYy3jGmIVub>v9;dHH
zwb71A`be7^p)q2YX9bZ<{F8!TcUvDFC9dGkjyv<^BUATbt9&`e`H~|snKKh~(Hm2v
zG{%_^&I;n5bEZU`!L7^Kq>Ax^Qvo4vw_v5h0`(-5aeeCkY?Vuoa4so?aLJWGs9Zp3
zRBcU~^<0}8y)ljrW(Bd4V>7tHxhE~u=L{fnEQE(K1Be_8;Zn{3BFExh`SaOI{42PZ
zsq`YQ9lPR9)b~F=H9xm1u}5iXkahz=STD0OJ~Kl&6ohooxS#)HQ)4qGpg+Pvd<!k>
zsf+l8T^*-W`AnO(7vNfY+|15*x8pVreEDOtH}hLlcXq3!e+=t?0w<hF4$BIsvcRb<
zaVoN6lI8u4sqq_Q#=n{sL_R|PrQqjgmUm`f^O@VSO^PmEEVk7!*Pl<_*R8ViJ-274
z8fFN`-ysyXXVR47Pp8IvjLm-{c=WB?`0&^ZYM3cTMcBGRmr0UyD|Sdt9&``m!%_EU
zE5zfcvT>$3k|R~lkQy0v6E{daFg1!}3^_3?h<w}~<sj~Q4FB;l&e08*^d%X(Bwwu#
zPBc~LrtZ{M2iOzitW#K(i&$;o-2|Wby;I{j#=B=`1#!=Lx2)pI(27ddm7P=L@J{{)
zo4R*fW#UQ}XNDqF=qZz@M&xF$2(~IsnCSacBRj^;+N>Zpa&rbZGxt=5f}R0Hj)kzp
zGl0mk5U$w_AaX43;4ja*9zTB`cZLq|L2z7GFlk=*rK!2NRjFM#g;Oc2>4JXQJMJ8R
z_tZ#?N#l3T3S!F~nAsnr{aN^O0<mDS<^Jl_xNnsQe1BHfc7X}=<4pLusj(Pi!cTJ$
zo6b<~y2+itfKB@NQWUO)m?+%8KXsS3O4x-{Z8TjLO&94pX}a;dQ=>6P+25HJL@wU{
zc2*F%niKrJ3u<l#5IGiNGx7`|a$4-2b=MAIp^jN>HYwOt%xBgh(;eA(YVX~d2+)-u
z6L*>a_M~0rOH;QxCghKE5SyxxrMpkqY0pr6VCqgzRw!enO&{b@P=1`Fj8B*0>)zz(
z$>SWEf|<CE@Z!`+jZyymtdyVCEh)X`<IbBaVh=eFFY*0$2=0ihl_u-+%TxDstK@&=
zRHuLtk1cIPsK|s#T0Wi{xiL1dSwZBQ%@>^9ET}Xqzn(Zpi#a$5!Pk~?jR)tMrxGEz
zIA^zsi}{7Ad$m=roj&E^@=rpGFEs-#&bcfxLu-V06DGIm)F_Ve?$)dz?m6$uuQOaQ
zPAC3CoWJHLvT-SDfBk8E?4vC{o7ln^u@R-93l%3iQa?I%=eEkiGGgfhyYeV@WkRmp
z$39U)4#5hJ+z2Bl%xiymYDC8v`Gd29xaW+#9~<0pJsNQmbSbg+m3j|1LL)Xfk!k;C
z>W*xcX%C#DPZV%WIERXujBseep0{708mlo5{o1S`?m34JUc&caV7z;zCi&Hfljhui
zHZ}fRWz3;di9~=DB1d3^9}|uv{FkYb8RN%)o)yGKe$3$0=hFh=!^{98$Ko9C$fj=Q
ztj6=fLUd6rU*Qv@d<k*l$bAamUA`Nk{Bbw)p<*ae;Zjz(6l7(BkzAS@t1(G=d{z)!
z=F!Y^tUP=#*Edz%_YxhfD_t5iyZ9>EM0UM4b+5KMo(ti7xx%T!y$NB37_h*qz_<xU
z@s+9Z8)Mwd9K;M$vsuSX8H<>7F#%S+u6Rv+oC@F0B*TX<sTXf!z(y9@Wjm2A-Ko31
zRkkeCvZcVTEU?2C8ahanVORF)u86Y4uE?HAQ-{{nn2s^1F)N6CWUUDv-|eZxgD<FS
z@WjX3=|19mQ15!19akMr-IcBK?V(dJ&f-eGGJQC{Jc7#zmnP`Hzcn>pV_f>1vx3;j
zr5VgzZYjlJo&iLT#XYi=XD^ApB}(_c7W6y#3~I?fD{d>fvo8LHsVTfw;W-P_N!L0m
zYgxuMz=T}cF4Ija<xMs61Sj}sr^a$jl>YgwApU>A#BWaBx2-a9=c#%~-{_KO4R@?g
z@Q8nJ>ek1Y^Nm?S+;irfeqH#TPnVQh4$sQZRMT;)%&twesQVV~m0$Wqwxv#K=&;N`
zp3MU~IaUSEO*o9ZcWV5`IJbLN5ciyOcUsBSrpA1$gJ$wd?vB+7$C=7gBQeH-Cuaq*
zWe&_dN4Vok?i*9%zEvJ<vXZ-Fb;4fL4^EB67!xjV5S#k@cYTU{r<L5n)Lq&tVJENT
zg07Ps_1@HIj8V2TD~MdYo3nz*T|mL#d+7qsJjiyPYh!JFqW$^G)E(cd6zo3b@m34=
zWx_s{@145+G4_8C2l1^NSkKaF4_w<mz_m&1>Vw|Wp3;UCoSZ@^3SX?o3w>bmYV7rK
z=UyUwf{9%CAE&0mR=MzAz6h$YrCT^C{$Icrw{pP!7T995cbTxI<x=4*6#crrlZNll
zPmTE)|9)mx5c%-^saZkf!&gYrT^PPIfXJ~B>-95$$Z7HDtf6DV0vj>-y^`O$jTkfB
zQMs`1?)c2q(}}w={$SE>j6GAgIwtA6IEYO()#ke~W)1o2&*MwrxML2x9uTDo#Ho|3
ztiBfaNpU3}zMf4X!0d$a<V^xkPTlp%>S>JNsc|Y8#gI=<1cs!n6o$03TAYEVuSUzM
z=FUk9>GagNj<M;nSwZB3@Dai3yB+vD_&Wc9Huk^EaLz<)a$#!xx5}<Vm{ZahyuGFh
z*%Y}kA;7mfH7aA=cxhG;_naGtUd2uc3cKE(9lfbLuvK;(KGjkfOyb9cb&Jl_xQy|m
zIV*^b{FuSY<%UwI(iuSHSZtrQBhpavJC46~hB7;)d8hl5|IyU_nk;YBzlrAYKTk4`
z-#2xuW0Lh14q^uLIP=8lp$~h#x^UFtwBzEVBreehUQ6`-$%(r4m#6OL7KxiaeCmoq
zhJ134Oqq}=b7V5Bw{4Qu`^Blz8l(O%%u4-Pos&nt9d`i>a<9{qy!i>6&%qJyu1w^>
zA5PuXt#aVeQ-p`0Ie(HEVNZI7QIQRk81c=iu^VH=@68G#S8d-Ayu91)$5FYK#LomP
zeobW3fyKMyqL1mI^q5*R;z(e*zJ*UNuIFwDhR39XtNW%#XpAp=X9aQ3`SQeukrWJC
z1DeraVc4IDyM*ih=37b4se856;dFZAaLUob#>4_zBV%fU)1pm{;u!DBvx2ziynF0<
zx=<hUGX#r#*1yUa3=slMVr3Lx#^?+-Ig0a<sr$55&OMGRrxa3Ui4>0;$>my!)Ck`u
zEXlqxHG*S&`{1k~Hu7x-Pce5kg=w4tM2^MJ-d-cm?7<u(@#!S|s_HwqE}x&8mRpsV
z<6K@O7L$FJ33J20J~cjL;_+DyVpEUtuCJ+_nn>-^o%c|D-_(8GD(xSeO#99DPQW-$
za$CMKHGX5f_}*DT<b&jUW(AQCRUr}o-yEu!@U4{+ePOO1)q~qcaDHoQLTpuBj-P_A
zU}c5Hc-Uauq_ge6F*QD8;_<IIh)sv;-H&~qz{ii)-~h4F;raALfAvqN?%-Alj?Zfl
z9_0{3pS-~o6rVIC|72>E#%TV>vx3Nn<bM=w+iWH=v)wv;(dz|ZPExv9$7dV+xbAl%
zV;<gruO<>lPQmR8z?Y=l%}^+~G&?3uBOaI<oiV1I;2<^~2zT9PoxpVk*%W{;S9ZF%
zU3v1Ur1wtUzpajglXQ1Mh6i7Wlz5ENe9};OW@@a)sP4`RA|DF&tRQmhBzXV-$~uVw
zIRl6s3!#c<0Fl!|xU(~W$gvR7z8OH|SbXoSkrKiJOP&0aaNoKJ?zBgvzc97HO&*NY
z%?*KEIX?0)nx#{>H8#X<aS)p-w!3fP=PnL<nEOl))c(-a9oi!C(mkiTvfVK%{-dcI
z9i!s+%?ctP7GDvJ*vw|n8m~S2{(2i9$g5+y3#vS5b`TAiO#5G(x({2W{jpOx!zz%V
z7?MI_j1j*&H3nmh_?1~fj4|R6v<*Hgip}jk#y0y7;?}<gntuwF59~P{R>h?T^exk+
z3+W*l5UtTF5q|JZ&Cd-lq=)Hp_uA;??vy@H=?RrHdASqv>baWyVrWf$EA(?imhO{Z
z-lk7c^X3|V4jMK7f`0BhfS>L7VfZGscP(VyemwlZf5pFaF7Wslq^LQ3B38ZOo31<8
znjL?5E8QK}!w??H&2&*VAro$;d)k8*P6V)U`05|*Naw}pGCS?&`tYXY*dL+!bhrHQ
zY+7E4J1w@->#VWfO31FP6z_lNGq1J6L3H7gFSo*Bx)b{!*l=~5_~?QdIWyR#+^h*L
zI0J}WY(6)u<O#DjNDn~PY9L%qi3WYX?i;WIs}J&Ti>@BwyL?u6@~?`n?&F4#e`TC1
zX5Yi*pZ%RAQ2-a0R=0h}u<<omU<BN^eQwzJGx@l>?eoLNyD@E`^wsTnd0xHjz{{F?
z*@>6GBVM+n`ahG8y!toA%MPUP1u*~zQzVoxs}}-$0WV8D3n7g@K21JJ$OWp~f$B>b
zg%tb%%%*sxX5SHy)Y6ZM$DMfmE%CSukAE&6cjNJ4T!s$__?8k{Kc`*@6{cROhqu%V
z_3$Ue%N(kIO+NDKf1zHe`lGlK6M*MdsrvJHp|4@$jk?uXE4**V``;+M@4)*nipqP?
z!Z+n3Z($!UCjuB;;|ZW;ybw^laiAY8yc5tt;hli~h^V|5Kz~C#&g1b<<Rihy_iGEf
zLy&m~$ow&EKO@Xh{JMPP=zNcQA#{FTy-<h$K)n#X7I4gis;}<C%QNDI_*4^*#HY{5
zM-KMO>V?4mx_BWD{ul8`9DE3y0|Ama_?&noZiM2I$o3ubkpui6#0&NOH|3+~?xw0y
z^nEA#{xl5%>`Fr2Pl!iC{l5{9Kz%Ss_tOZA>T5!+-DZTvp9kD@ABw`tmi2OSmDCi$
z&Jqokh*q*hoSG6P(O#BlsYH+_OSDxYh?MS^4cRz*B>{k7S=ow81nIJ}mAov-n3Z)@
zS<o;`bX6kcC|y*&(p2g~p=ebl?kg6}D6m*e%}B5x)J-;sB#|&Z*z|%jt}*f2<p5D~
z7%m~5__$zt5X>N(T$5IZ*uiz-ThN!2Y+I5Z<i@Yo@6>wCAK(k;{L`RR_6w*(2KgOs
z5c4;(jQJax$n0&9E|LWVG>%3x{K7Cjqzqm$RYFeZ!%ho9q!6FlqjuA60sphm>va0H
zWWD8gnix;y?(e=N-m)({)2GKTr2CS(Pdon3`Pf+igRI`)$C{n1c;8ir9q!{{A!PWD
zdXMjo7+#3~?uEudV16MzP)}ZG#k^bT-df>P@9ARAYj@hu=O2F``01RyYM99Tdt`?0
z8>D-K*lVxhd%%6(g*o|JEV2g-69}NMvLfoqL}FIDsNTR1e9rv_)Y6Wi+a-{VF9YGm
z|AFQjU%}HTAsXLLy=nXa@6%r1>DPL%b<y$t_#QT#pgu!@%4;P=Bb9Qlw}$t|Kc-3<
zMH)Yd*ISJr!Y@AJ{=@tax-7puU+C~I@C}>r3th=PH%cS(3;=Y$0RGTUN&KPZZ~P&#
zdW*Ej_6FA&jemk>(EGVoCmfJ3b|a_j&Xxzyiy+EEi?Nr~*xLh6Nl~5Jy2+cm#ap_?
z8@k2Yxi!dGw7t7t0Mz(R-e{J)qlYg|=I!L^NuLjjbOHBetaaqaLxG{hXLr-{8E!d8
z)pQRodKYAA{2`#jC0tCpalL(Qx!DQ4Cc|*3z0vd9iP)ch5uYYnhXcLT_zx(Z9;h|F
zPp#LmQ-&8H*BXu>uMgVL9r8VV<U8H<GADc=pYd({N7QTlC;It6>F1B}^LaSF{^y5q
zTRWk^1(>hniX8bCml}VBVoMw9ru$yy#4l|Q{m%-}cZ&~S4;$MKQa>kyT)4!)j$OJ4
z?{qi`-|eWZ@Et*NBg*NKi|aVW-!6?HiC*p_-9fu)`?zdTh}(v=^tN|v0K~$`hgnIM
zMw8M7T&k0OxfK<TOuT8FSDcuYZu-SQ03&@~<NCZN^*I;h33@(Vx~MMOmy7A@3^W~7
zFBLBzCc-G2#H|k>5F66cZKYwMpfEk71x4D1g2Ez?78Ge43JNPdT2Q2IC@4(yXhD%C
z3ue~5RxFyOO1mu!FNF0dDyubpzT;*jDc#x@g#u}Ww=jyINZWv4Wg>pcuh`IQ;a7}8
z6=@p^3SVQiph%MiH~1f-<c7ozFojbx3R9$Qgee@A4KPLG#-c?L%9=0A5S(nXrn$!C
zYEtS-xR!rPO6>o}Ph7$qsTQeU@V1BE_Hu25w|(?R#-*`{CnOxC1R8^lLn7g5mT*iY
zoTLO^<$jUy5G9a&G#(ZSr7YnQk?>fS@VH1=$`a0qgtJ*fStMv#f-VxQEWs8DZkA9L
z3Gc}go)rntWeMj*!uc%W1(EPlmhiGjcqL1CRU}-@5<Vyr-pCR@#1oWVOn2cp1sntN
zHFn}FB~3gD<F_rLh{k{w5(epRT#f-Z2WnGVHf+U$Q9Ag31X0>vi+u=}?VZQ1EFvzn
z)Oa`iG;$D$HSeV7ZMVWg*9<~S3r*&0h7-7+8S0K_SN*CHF_-y{;TXDMo0cAhURVtb
z!}Q!J3L;0hm%HsX7`VoRqhLL^S`8vYvkeXZ8?IR~^&qH50b{zZGtaT~sviZK7or(v
zI=*i>c2o^aR;~J0)m3008U^cUnyK4WJF=px<@#=D_*%s@szzAxD`wS-+={OURoiiN
zBMME|(5lsn8-)g|n5G+f3T$Z<tRLaO(6(L2MjaLgo@N2FC=A@lvYf~?t2zr@-K++o
z3)1MU64;tviJWTH#H#}P=qOksqT}j}xmA!A@v<QBD;1;SYE1LP3IJQ^MZ^p<WUg;8
zM+@|-gWd$LW@%BVz&<hx)-!ZB2yLHLd^@lzwi^N)N3-o}MXN-nSJg}q(T*5M0)o4i
z?J>=)gjNMGHLa?^zH1b0z=BE@AgfHbS=IC`@GEp2CvwqoP{y)!%>r7i;xf=m*A3SO
zCBne6t!hxMD6kKYg4MlHi+s<~Aw^N>YPwgk&8i*vfL}2zH_%v!FCT`s=i7eBLd~$X
z$Z&%QC`7ImDX>pSu%s~FNgv2&U1X)#;i!?%x7_G5E{%_k6h7~GzQt^#;@GyY`yt3|
z*j{951{%;St{+CgPYc0|(6pi`a+n!udIUnaZseQ3!eMC?tYxssgVaDaP}!`wp>0+y
zkPuu54Bf`aG6F9MD~1O-G|^88uW5yTRH+)iVJWbWkAgLQU2`jr?^$R%ssQDXF)$U}
zVKz=$MxGJay6<V46QY5LnXc|>BnMRoB9?(YJqp&cDiuBS+|Yp#nnviDhN)LUeHL1}
zsW~iiY~5mpWd|mt)v^K~!s0rfXLzB<Ooi=J5-d$2pg^L~@@&u0JUz5SriB{DLkRe;
z>)JXvYS^J3x`rQsomCy<62qY48CD2+a;zW&dv+t(&_E^TMP3y6j#ovOt!l(D@*NUF
zCx~o}AfG`vgTSzDR?!SMvh|24mkaqb5-gb&U|VGl&^2wSrz+G3N?KuLxmBN(n_*QL
zsA5+<;A`1Vg=y%QV;D^Lbt|k?9Hxk1jDqzHr~%Iej-F>5PBma88(J0pjBL#bAf2`!
zxR%RoOVcnWUAGcCZfHhPMfX@H<jbRAZO!(qs;)yjM|$WO&>GOWVF+n<nZ}r}LurIs
zXjl+%%QjrgaUn2K=-A9d8wy)z6fAMq5B(s3a`GK8EHG_Sp_*^HgpLP&?VHf37!J%d
zbsfbls7MXk2J(`D)keX(y5*SA2qch}i!S>SM5}7*nh{ogFT{AlD2b5aR>J^V+k~dK
z!@#!<l+-f0bw|Ngd=rWZLJ4w)5tO6lTA-_6F{-);B|+@g%n<)<a43o((v=7bKeBzt
zv?`f$etHzF9YGYKGy}8Bst`vSoA^KUJd9+W8AfE8ItGYA^v1}5=69KC1O`|D6P4+N
zl~J&P4iY+5%Lp`()PZ_rP^FevtwKdOR>iHj0si@VMK?{;@TwRHKCA>|P>Z_fD3(=5
z!5UTAXqX5+f^0%*+P<rqTHr#VX%@yOY^P~KXhYq1byB&O56g)0gVxbbCScYm*otGi
zCbT?Euz?X#wX05~SvCon4Nh4uTCpG_I`u!Y-Js&=uI*Gk54Ob9GuoP?V4=AJKZG*z
zAXpWMkQ+G~$jQg1?^HZM$8dn$p-UJ$qzin*4MU8GP`5LuLLUViGQS!)4v`NsThV<J
z*2M7*8)R@oNIgU&3NRit-Ks!qFwns9b<eLxhOfIB%c`SbT@R|hf??qK&>@y>+ZEr^
zP(ET-6{6);Ob{631o{o;);9F2=XjBZ(k_NjHXQ5?V4<KOpSEjRVPJb8T2z6c2MogH
z1vXrj3ZPeDn{0+*#^4Bnxh|uD=sKaYrvq}<K1aUd7wG4^=;t%^^ON-R-SqQi`uPF+
z`9b>mYxHxAe*Pi-{2KlIH2wUy^z$q9^Go#eo%C~qetwjGeu93!L_fbuKR-u5DgFFY
z`uQsTe35>B7(eeI<`y=^I$h%$64J%<ovZC;#|z2tOoX%9I3p<{Y_=Uma8=+E>82NG
zj%$GIP6akIfaKen!B)gHx~A?EN|w7}1m`kI4|jU?H7v|FYuwwd4SIDr!RcO#oYiEs
zGF?E3uBIXn$X#fyCw)r5%zK!g;BVNHg-gtrMdC8WIuUMuHAE~9$<K?TDw3BTz%F%M
zuZ;5_muq}U5X*&YQA<4^f`9EdSq*^>aYb`7jGsyOW7(J|C+qFLcWu~s0+uH|>@}M;
z1V%3-REFX`bOq~@3xi&>mIN_f06UD|Cwd@4uoM_P7ULjwlMYj(7a^<p2wGiEhBwp0
zB8EGX+E}4>4)E1S3LnSJ3t1119H1wJWDz$F;!ckMA5uw4bFfy62JHZed*gnqS;O^*
z_%5PLu#QBC`nEfLCL&;b3pg4-c(v2Rk}ht#ueIv!K_ANozl5;bz{ioQK0gP7Bh=qU
z0QMuX7P4l&g)O0IxN)9?B{I~bb+r2_MAtY`s81mU7HgnW=c;t)kb0<?nshx}=eeP1
z2*KzRQI3eBVP`;0skZ@`q5Jy>T?h!P5%dQ5aWg$2A8QCe)1An}_+KNSx=8ZT_A_}o
z!sVsyLsoiB3JhfBf<IYS_T#fT{Z6Y!-!%4s59DvY2g2779K|~Dt#ltzmPEC7nc+Cm
zM~M`N0tT^|ka74jM1(bKy|rtgNZlhW8=vGfW!G51sa!(@kqzTl)1!G3yv>-^x)h;J
zD|cL}uJHwimF32uyAB4`cx|j+qMi7)Mi+lp-__{j&#lHa`b|&fE%m&5!Y~qQtk=V*
zlW#Tt3NNwPV!bt1!$v$Tg(v9tVviv@+N*UTX&7vc#ck;K;T~&YeL%>sTv@-B9x0}F
z2L0{;bi9=w<g$-gZ>x(nh#1QVjaz7IG#%^tY}iOC{fHbK0xroHhzI)f&H@vf6c6Ly
zg+jm?%o_jlGtD6ABqa7KpzN7+QM8V30QKH5emOlPyFpP+L<g^7WHr7>t)VNtf1C^|
z=Q}CqsLT->OU0=h-$i-HWS)o#*0Rj+rp)6qlk`pqttw?|*!U9VF4nv2SL@*#>nAlt
z>l<I@i4x(c)1*P4I$PzvV!dE2;^Fhy!+{>vf`rD@{!BKZQKHuH76!^8{*?t0Y>*-Y
zVLw((t+%gWm8XMabI5tHm_x)5F*pnP_e)S9J(ex0VXXJi(hZH8gBX!*b`?sK1wzr^
zN)IUwTBEJz7}(um{I}8tlvLOb8%JSz8qeeBJBF{zU<XhU(UZ5ZFt9))kst0WzYW`f
z-NAiQkqGtIv0$(U3~)_*XP6!x%LzN{LmAOlX9Lp*$4cc#(V#P6Mtr(((!%AkAtE*V
zctTeD5Pt;+o1M;OUT&Bk=V|g99Z-zlQvumb7YA)oM#5U4_YBm@HTudUHXN(FZu5#q
zWY%aq`?^69vw6H`z>eZ&0-ys(9tCo+$GXk+GQQ~mDt6js1B)H}+jhOT%^^#8j1Ms^
z?GUXpVa>TfdvloHKTbSO{2IU<AIk&zDPw;I1BWvy;a$pUP?r#9nDeVXhv^cc(AekG
z4)B>4pa~_-HYo~>X>MD<_!x{`0Ey<*OllGH`m{AIJ>o%WAo|9QVV1gI++hL3j_+a9
zXoO=zms->qeCT0%K)$^Vr9)em^As8yB88S6*K1gJx(s1Vh=w$OEnu|h<D=V`G5o~N
zr;RHKYOz7adey636;Q7-_OD)Lgg=Yo%h-7aTSnMbzKX49`7&0nz{!ZXdX>TKEDSA{
U=JTa`8Ntr-1?sr@a^NrjKXtMd^Z)<=

literal 62007
zcmdVD36va1dLBre4K&a|;|A{{K@trPs=D&dB!?q{0LkGr3Bm;D62U3u5!qRVx>#8S
zpa+Cb&j^sx9zLnOlI686S$?*6_pL3-_DJ(AuVi~H&04m+l17p>yW>N$o@DRa_q^*}
zuWfmy{r-r^qq?fmU9|x1<-BQBMnwMc$A85ifBX^ooxA?j+5h7K{$Fx9?nd?YjS6dD
ztM@wX7Hjv1$>K|cdNX*rQ1pYtGv775HC#$|xZUpXVlp3e{C<zIpxzrM%5v0cvE^Q8
zmGzbbc5ONCH0we6x*PXdxzF6za?K-v%N6-nJWO`SJ)gf^+U#Yt^*imbzB)`6B(mxA
z?(?D|!)|Zq8te7y0gE}Z2fAykG@`f`_t%<?dgY@XCi79h)vWa+)<WqaQCjmlovUft
z;k-eu)9u$gZ2|JgAZE3obG_Z{xB-UM?|0h6JIR3_>vrOLztdZ*4SLOCVn+RbH-2t;
zd9~h;242PQw3Z{c)nYx2x?gtNZgVZ}k5LN9PzUum9<VqCe>*uwg@rC;zqgb9>_)%m
z*1}Gw&%lXCKHB}*e5q8*dn&0_Rh$3lGRlX8<TxKy+!^$I)~vU$*5W}J)^7}x2SA(l
zphZ-^4SEc^-5!hM+I6?ruD4g?;k(0Re+vkMgDtlXTDU0*>wO~Z;$>oaiL<;!EC)Py
z(2qJmYR9=I2(s7jbk}<I)d=#n6G*8j;@C7htDRv~N*37-zc~n4t?TwN81(Tj<n8FQ
z&sOT)wYFFDBj#W2cIsd!UaefXT)PZ%qwl?MM}w9ZR{{^63P~HX<PlH?P+V}i<JVHy
zEl?H%!XWqa&O`TF9nwVoivrJ$88HwA2f;HTJyPCC{^z5$ZU=G`*JH4K9{guLx9vmV
z?tr|+rq-a@hamVh(9>f*(c5t%UX8U~ugQQ+pS5EyQZ&SUey7=K*Fpv`kj$XdY`VRc
z+mD9H95JaLu7UdTz>5KQK%zKI_VnHOYO@~qG15g28%Wn;(5MAe2<mR|soC#<*d&R=
zWEU4mG=C7ZWH*@4A=TVwvva)$rRnr&Ku1R^>+M>fwYn%@M0sb>?+*G<r2x$VH;y{j
zhwI+x*INwjhAWRHCq_W|E^s5(Mnu{}BXzA#fPwGmgdrq&q(-u>AQ8#_rrT#XK+4s6
z8*lCD1|csQ3MFX_x@%wwS7lLtJ2@hx9_ZF`A-t39X}ayzfx8MQ+ZkwjXhdQ-s>zwn
ztkW`yS7oi$gm&$US%1K-<2nu>kp`yUSzT>1sl1ulA)L~(InK*ABzeCa3Aakbe{Q+R
zJb6I)pnOb4beN=l6bCU(j*E5`lvbcQtS6o`Q(A+mtgk};k0mE1$Z-m?=*j3*fn3oi
zqr=gW=xB5-Iv$;f9*;`V6St$Mqi3Si(Nc6KdN%q9iq1j`qe`?KRU;+Y`_{|nF1+z_
zr4<a5hcFAo%Qazz;$;YRlXbxcUU@8V`);k<>p-PQQ-$&mlgCD1T7{91Yh>Hf2G5K)
zs9~<^b#Bz5OHi7$;nSlH<3X$C!fLBk#UOx+Y{w$?cBEk(I{t4&X5`$Co{OH3&P6Xp
zuiS}Vy%T*rdM*0I%45+A8oVC85nYVlj4mZ}H<*yS=&jq)<vY=*qE9FLgv`q6W}l?+
zOPFpTbq!C{k~)zv!Mg3_nw=bA-2v<#>~L6ba<xtla8Vv9THr;ELZbyi+RV6<foU>d
zOk&BtH+xWE7F?+N{UK(~w_q%GR(dcc$s&w?zc=vv1JpyyP_%<{g^OjG#B#SJPxPIG
zWI@arn0?4x@fmk67X84ET^7GePt$CVi3KoW&|aypR(R2_KG{Mj@Z0n+FPisZ2+Cfw
z<AW~qufw`Q0H|hA&`nITu(2*I+6gJJMTxJt-8y=?j7D#uP39Qv!ki7tk_F$J3EVLH
z6Um+n9e=>Ro~-R0nzmgy1~9;TV0OvRA)AWUb8mP2xA9m2jGkKD;u5e|z^B(xfO?um
z*Gbm!3&ZakMn9e$Cg~j&&a`Si7woj?M7Ie?s_xeyApO-r8<TPn(5ynxSTg6k+&zI)
zwmYf^0W8_=WKYYz5wI?d?I->S|0R3GT*LyZ>oGV<F@9tI;<Si6?dIC>_P}$KUA$m;
zao|nDKl-nP7a0BN=%=F}0Y$z{4JQq!(DHBPEsLWowD`Ha#fF0|H2-^9bC}#(53bKJ
z`XT&kvAzoqC;Pd&q*9s8HM}xS2ScDb-y)y1N5VkdJxH@`!@Z$lUf>=k-k!_7y<}0^
zp^w8^JP$5FlB-Y)6|bZw>U{}f<oSI$Rk}Uq4&yjE%2l+>pe8h-$2IPAB->5_1)=;v
zh)bc6B*-0MTtQ#M=o#Taf%$N{c3*Rw@C=2n0lNm24C-}h4XzfZupMyYhZnzh$PMv7
z#gF8WY*d)}F#p0Qz>Gx=$y)z5HJl@%Am0MkjK4Y8V@(EcC@a|2?*#5z_PCcn*1}eQ
zc#*#mF-#2n)qPN57mf~GT^bPF82${eQPiIl=Af2Nz?@-R<&xt!iJ`YDH`BUXH=*CR
zhT_H2Ducsyqc7c-aPaxhuhrlHw_}izJ5+a)IoXB}?;pb5;3(}Ou#)e*B)Sp3FRBho
za|!>e!xbypJLrdHyNsDpyd9m5LeX}Az(N-e9>fmDON=`?35BeMgEqIY@Ns%ra==3b
zn{JD@7O4TeoB?P;!^|ok?f2>}?!C9+z{A52VVU6u*5a-UXYh{flur%9oraUf3;7Jp
z8Fx5>Q{5!TI-@5jF7cG3Ka{u0#ajSBKpq|mVJy5e@*Qs$y&f!8pdEp$Ekn5CW#4UM
z$pg2VmLt9Xa<lF&!{vhbX%%OgtaBN-U&VYLFG~Z>oiRT7EsMY7<?v&=oi;7ihRJu_
zqu#q~+?SA@75kr5Q^epu>-d?_$Ac+fY93|_IH?y!`NCDky7|IPN&_4;!Or6lvwAy#
zhfJ;^mK9jY(Fza7noG+(Ci)ud*0JhJ#g`YsOcaU^bGd|3f>`uxaImoil(KxF3y~#<
zNvs6nJ9l9dxQ^{_BOrjawpe3dyhvtcQIydfEtfpEhP+~b%Wad_7xVS9)TBM_dcRxu
zudWU6@J0vZa}7Q!t@Yj&?;ag3hA6JWQi@7)ML9M{q;~?31i#?u(sa18jaNqB9es~z
z#iszdR3odB>f9l+>oxWssF%(p632bKMgUKVGT(2;H5gD@s>$y6Q4v->tOuEvug+tA
z*sEdC2(qNmVi2?c-T>;Kk@#?-tmbm70@ME91(;$!vZKX%xkQq_O=>l{+1=i7F=g!G
zu@@M35D4)bkR1*tckb9gz+2#cCarvh+w)DqAYPiz3a`GnM@EcxQaKsdWS+O+iZyI}
zcH09F@IO>@IIk&0PqJ$HA`cxz-^_~l@wa5yAX>`G1%Bz!hS4Xp8sQ-WA2`er0w9H#
zr1P8w9inHmw+`}t5G88&>tUVZCUb-K)i#1UVi+_6fs0sB4;xpDgWJPjAJhX;E@&u*
z<Wu}<c&1piiiRvLlKA#m=Fy9$0wY9_pls6B=M_;eiZiqYQPW7qNV`Ok2&)Gv<~syj
zF$yZix>O2g)-=Y#lMNgDF}5NWuog9FI5acWg`<4Ha4AK3?Rq^RRg!OsG4Ux1F$i+@
z>uq>BfJ`Dmv=l9PT#GEz@OD<S$RT45>i6oxiybAksK@jJdxRx2qDiCmhxq%~dv#hV
z&<u+O#XN#e_0QuKx0#{9*Q(t99ptVUm)Uf_<A#y1WT^#T$MU9&yeS6O>(_)^j1{gh
zqN0Y!6opylD_;IOEgAU_g#E;iYteP_ngrN~tKz4fFD2eRn(oqht`K9uBAa(MOup^j
zc9MrI@-E)Fw_Sim9?PMB?%qOA<0g3rFBLnuTM(OgkJm&vMubmNGN)5F7Y|H%h|KaZ
zQabq_;}x`=s|~tvP8i%q?mly=5)1hl=E8Gft>N?XV(}8K`N+eC<HcvqtXc%O#AIB<
z%wMNi<Zbb)s3YeyUwa^8CvdN%^FoENLI8<ILE%X_cD-81<4X&^C>Fqk<`e*lPNH9n
zzAhSw*hE3iMX{9nZnNGe{Gk7LiWMYEG8UAgEtX5%q6pWV7EQ8}N1HfZ#Nenqn6Y-u
z+@4Rd#UgC7k!ch}x=#Wd0=TYXa*$9!JIVPb5aRvdUB0$YG0sfI_0;>391uZeGGGt~
zzG^$3>kh3MTU{6zs>7=6;qj_^ESwvP!9G!_rWHG1(xouS;)3tVgM~&t*1~)wTTo@O
z18P@;>)&6irSCpdc$dm(RSd&A;7cpS-`yUZ5t?O7$)km)n0RSR#D|O3thcZL;4O|8
zTJY(l7GJ}1s+1flRK!?f`efFVLqYvoC0nJG;I$%nS!gL@Onj9!{LK6F4?K{rw@R2i
z+%9{It-gGtyM*u+W`Z-No3sm3>LDK6YnMb}1#;blKen{|PUYE;e9Pyax_N8q%=_<L
zdH2edcb8YsmQG)}^3*e@&pcmRUM@ZLOsU1Nsw}|@m99rv>y_a3A%Y!9VDq=;=a-*-
zcE0p%=`Bv>xFjd$0NWoo`lS%8ExDzOn35`JMGarX%Fu0<Zc^E;Qs3=ip~@SS`kfL)
z6@;UvSv!IDtrT$S{N>A~lwhS!SZV_fFzloa#LHsLap~rTH{ZC-sd20Hc81ZniEh8G
zbRFAL0#hL+0lmFEpHWrdLoY6gSI(y0q{M}A#Ql<wtqWFqK@O+FA8CL~h$Au(lc*`$
zxExokb4#>D3D-DnoAqm~1WY-*>S1X~QZem>xCjUW#}tD=44uD24LJPDdjr;6yDS9?
zTTU6M3S{SHY(Fd!!AdWDjK2+OAmvy(bLM#t=T=c*1i*T`&3Z(E=Q+2ROXsmZ@UXUp
zM6foPOX67)k^53T1{zqou%J@<biLUud92h$#0U~YGQ_*?M{b|C$kLYc7#WPppvl{`
zORGKC<E^;_x$OYs<|13_))~w?F`ZX&K;q5z={|J@GZ>WW?UD#Q71+o_v*&@RU?oO#
zo{Ukuf0m;!u)oCZ5Vbgqfk2hmjV^c^y3LrKEs?Du2%^>NWN3)t;O|+<7*Ug#5@B8@
z(=ytaYzp<Bnw0afD1h|jlV?k0LoRgu3uHlfQ7Qn}(1b7Vx`I#i%vJIEdCoDA@It3_
zot60ZU<s@)Q8yS|-Vf@e>55B4)h9px@>?&Lvyj`9-@+jgWRQ_iCM1Ey6HiRSxY+pP
z0&U*5ID`y09}&PllOrHqrD!c8;V^Jy`Z+p~L~N;2sGGXu;7JowMx>M=Nf(qrcWrhZ
zhKHNH)1O;9UHZsGZld_~nWf6JXHK8tU|~zZQE41Efj44SiJ|L7<;)m#F=|jAc0mXt
z5tGE?op*EYiIKn38GsW~#`4P5PQSnaE`TGIIl&8cqDLa$tDU}(#X_GX5=(iLREdbk
zP=iWLj>*#LEA7)~ij?Lu1}Frz!XK6d@dYJ`c*G>p?EUvkMa0FUM70Q%-WnagfLWn1
z%Mx{!L#MVQL#lKKakNx;eY7oMBW#+WKwNs}nPO+_@gVpGCJE?#IPa+Mj)EQ&8+w=i
z8+(6z2*R$4=A{uTN!qe@5Puqz5g$G=rDz?_l%6T-Bp2co77dtlr{3my1MyN(1Ld13
z6Gq-72;f&POHbraSwlH!>g9<E7H~Z|Hz7p<+B)M1F7Z)N#BJ$J>4g_wD4jk%Ep(yX
znbmoXoC6LvmJ>auAR#$0m9Rb`*FH>4?NVa^ZH3({VbzQ+b+;+r;}BC4XKGc6k?6B@
zjV4k20jhkKFJepclT<BePmwAOq;3d36B-Q<iWmU{{uZB#F`;6?R0lCu$-EI!$Y8qH
zI!G)*P^eSx4cgpH^63|oD=qpnJPREonMumjlULeLj;M8^70@d@RbtHEY^i#-R91xa
zk9Y)ymT(3T;L0sxnp=WRn+hS_?jQ!TPo(|SKv+1phx2@#H1j8Kf;k>p8jJC|oGFA&
zB#bl!m+Yi@0s)Q`Hsu*1PicLg5fCA7T;^JcAcWk468u2&M7q<li|=&Em8QsfqChzO
ze5?v$L@wnzMl3=_C>2R9>DnpTUMb0!<)Te2kFr>uTy@FCm8dN2K=6f}=vFM?kivpE
zFD)Q=3{vJR(PmO0gHIrFwieXW<=!KFfkxZMeD|2IXut=oXesTh@qHBHD)a?27hzq6
z#VGY9Be8s`rq?K#ghIJSMU<NF5DIE0&!^P(gLb76(}L$(uhM4y<#xBVEZe?_os!sC
zhRBp#t!CLL+|XFkDcy4{#6<;a2hy%&_>7{p+pjDkz<%Y-FpVsvZGt-HEo{b#M(<Fg
zchg20AWV9c&?R}0cC6B}E-#P%QS{3KfrIJhnv?+W{@+pfZZR#VT|A0Gq!s(qiU9>f
z?}*li(?U{NnT;hQj}K*4c`!pPE+{rFVvr}&Hatp_ZtZoTL=V35$=6>mT|D>3%cYOL
z{KmQ0UVri2g$r-JeEIUnhN9<V`KuzY2McRTL_7NWxr?uU^4zO<@AcPTY}PBC-l}{j
zx)ilY(4t?DeuE3#yx5NAIcahOLzEzu1oFazD{>R!VNn4M$G#hwEfT+wYB6XbBalOr
zo4eHH20|a$8{owciuV0Zw~4KIq-|jh46?$SVS9rpepEDAAJi$r<iQ9LZ{6PRh;5N0
z;x%4HK_cv3Aco7|Iv}dBI^r2^h(sWB3chKJaxgyg!_W_INXZ~SUAhdWz=I1hWr!9f
z>?Xpp@fC&$9+eAOLS+uS^mGQHbOj@pn}F}U4v}e}eHBR)SKqxkAWz(<opcuGo<X7c
z%|RP`<H!ObLC;$}jrB1oxLV?ISnk4MMnhaX>+=etT>Z`!nGAuQj8)naxOoLy&aP9m
z503xME0BD0`eNGWxOG#`Q}M05qbo@7qvQzWaox;d6IGCAmRijhNV3n4*1{A}xGyWr
zAwFGt8IJDk#2m()fyV^{3t_-?1AwZdcGTg`qzGVUZ&6%K?1{@Aw?zR$)XBJHQ8+MZ
zaMnOLc<~~cTE47WxBd2TUXkubWQ!@e3zrny@DxMXZ{!r!dk}RBZOVSL4rtRSef7Z{
ze2-yOk7#McT-fUD#Y4pwaGVhNTG_@y7HZN|M4?iJitC-;RRXrMYyB%o<V3U|lOC@)
znfD?qaylg2KljAY<;@<+oAqD^F!vw^h7ALe2>I%Zy`SeBXT0rRh@p(%!g3=6Ww+Qm
z#}1T8;V6+ITyj^oA=!h!u|RL+$}Y6|Au4RSR}tJ4rh_sqcpxp^I6XqSb4@1VmT5$}
z@srs+cnAio-VQqyw;M@3NfC;^iM_P%-2T7=$>VRr5yKc6tU$I;BLrHepDeslkC9J|
zNguhN@i0aGaN5VX?OaT&3I>S}_jp<{(e`Cn=LAXiQ0_BjPY9VhmI7#FY)A;IH(~Gw
z(h8nTEB#&vS#?>uMapr4j|5jiQ!-WX<mR4zq5SPne&pNa{ItNENdFYoJ7KVpq$75m
zc^!q@Ge?OWC|*Z+anK?YYt(__E#_|^BOMmE-_Q1t5BfDq6zfC8vHFITr?cc?a_?Z;
zCe<xcwli%#TxDwz^+4?V&LQ(?we8Y?_^%FfZFeFu11{to&G${j<&(V>sKpwfhlJxj
zwBb(SQ_2+;TUKPYdq_9h-;Xdc1T~)31FwUlf54YXIT%9inwIVzp7eRHLJgS+sU46F
zBw<eY-LBXd7|&SXfDiEo6UlIts_sGv)WRbitOC={RqTM?fm?~`^$5KtD!3p~f?rzq
zAVpofHA;$gDNs|RfFH7p;wT-_6GCOlwXY4@?+rjsY$6A>K4uP?-6QjMjzRFDgRI$w
zAJh(H^3O2(X0kV{;T!2kvd6R`{HcqLuR;B|JCIjnV~REe$O%h!v342imNh$>H<R6E
zD~D}L-t0i$jHjVZ?B}XS+XewrK{L}-&Ot2ZAkdJ~<tGB6a0CqEX#I)&U6H4f8r?hD
zKpxDSw0H`7uT^VeM#mJ9_fw!*3{Of(I#L5tq7`ry*=LkDkX9bddk{Oj$v$a+KMro?
z1ARDeM_vg@1vHZK2B4%lE(OYG%|z17yE&}mIV?VKtfEAY`N8Eu+*|hQ?d7PBq<rjJ
zr)U;vmBAJ79LnBFEAqEWc}G|#WG4>fS%?m{=yOspLZF0z=Gh;VJjM&TY#yRHWVA`L
zSEvBy4qB*@!<sdku;rFl(oC6JzI0Xc9{dqfki37f8d;PTJYSAy!^t=H%L?wtKnvQ~
z6up)%LW^|;|3`p4R?NSLjZXKT9<7Lqv!#j~AZLniv{r&%r%MNYB<MpUFXPM<G-KgB
zh5RW>L3TtoJU-U2hP+&CXXUN=v%u-0k=C@6Nv0AxR)8<o-i?1kv$ojRZ2T5}i=}Df
z8~7<({LlH%|0VzVP5eyX`=^E9|E%!)pW}DqUr+%pj~oAz9)CA|OpX<z9AXbo1{DPE
zNBLm|a;|Z3%<WwT=Ex(K#&3aFu7<6V(v8l+AhDhs`y>3VRBYolWO4A^HC}mwS7I8W
z^*yp^G0pK4K53WZ2Vsz_&)*a^l*=XjiYy~bfRuAGsZxyx5b~K;jFB4&B<D*<H0@AS
zl5+}gtCkuv8BY*HO)KLjrXkv0OT!HZ_+Yq$CKHzhswa7Q>ePtjRxXg4C&3$Vdq>;)
zHJC{F2E&!FiT4ll>f&i3o=Q-lF6#2FS~vvTZsPy9hF_Fkj6i@Wj7>VAOewaU-YEit
zW&y3x<dolZJ!~wb^<v<~dXdeVPWT+bVs(JPBM&ukBt`$CKIkB|3&-I^LXng#AtNGz
z0$wnW&!l||j-*i%xzZd)zba@$$Bul&J3EwfOJ^2x(i}t;@qwp|!gGRaPI%(TgLst=
zMv;#@+NkmA9Z(&P_5vD+kP<mw@TJP-0kRVM<+6lu3=OdEXk)?OTfG6w)nW2-1STAb
z!kH2d`oZ)lkT|vlF9XvmCDmf`zmg$vm-AK<!xRiZi&cE}?uV{$tVN)apBj_PK3D_N
zz!5Y?Pmra{ARLq7FmT2yJ$aT^6^1bSZg%=??A5fU@ao-8wTbtS=UsD8G(GfI0P-+c
zl(#}KnvzS}qG6`<BW;BL=%tl~;iWYN@N|d{2S8V`Y=g_`;@F6kXsVF1(}kTtkhhSP
zM{*-JcHkhxK#7!?^ws0*YDI)MgM0+l{4Ejv=PSu!a_lmuE9@9zJDg;?bd!8n<Qs7o
zt$#&KUdKL;Ic%d>2#IuE!_SuT0BnZDL#S?HJxtRYb{UXyk{{DOBRU;FUx>q1937Gg
zNgKX|!a@b%*<>$iXBjCP^@4iIcKkFWJVwzFr$;F}y`O3_>4|J8=CnLaB6>WTH<0HP
z*0&&GlOSl`BQGIM5>9Z4DV+}`W;8Y+fviacDB~I;!M70FeWegeZp4&0F`$!-J;sj;
zyEtM(srB(Pg+Q>lM*w+Qt!NcJD}ddns4~IYOGo=~atKaoqQ#M`8fN(%Q$O|jWu09L
zUK^O-y7t<#@vX1MpKW^|X;nYbe6zK3snIt-^R3P&K5_Nj3)qa{D`K$)1me1Is@7Vx
zm>(o>6%ZYddA}%)N?8tXnPxOZ@7ff9d{L=XE9Nq$^Zqi!Vc4MTwt^JtlVobsIAZ#G
z8G-d-^5|W=95((6j9%lv!JmQ5U_P8PB$cs(eWR0jBujLJkINJmut+XU<KRTWeQxu*
zyB1@i=+e2UJ-KtZzrq`zt&pZ*Qzos!q=eJ3$jioZmd;~JZ&IF;g^pE(D#EGc^M-gD
z%A8O-P)HsZ9S;<^;k2PpKjNi4rb*}Ax)c^pb@N2AQXHw};U>hg<kGg-Ahoa;Mct#t
zI_Y9jR4yd#CyytY!`a^F$g7v<bdJVIP=xBZ*BNd6i8yy^c^*s;F7lJ`_0}qat5|T-
z=7}VCH+oNuDQlXBXUUbqx*hYcaFzx*o3$XeC3r3+1aD;<Ws1>8g)9+K4J<g4-H4jg
zNs)`m9L$<H0(C$pHD(2Kmt<9Tt}nfEAlgf3fA}VuIE?cp2*8BXddXhy_E97q`)m`=
z>?IqXR>K}$c0hIb0S1?yt|DPul(<S?wBip}wx`E$(*yPugrC~T!Dcv1y)8ZJm{-;*
zB7-0R>e3q=GHAG<VP$ug<(U?X)JwE~a9!^W_nIr>dW42NMx6CTt`wCYTlbbQs>78X
zWBt=fQoOJpEr=G1BM&Dqj;z>&<fsfzkmn3Oi|kgY-r<pQY(+x7aHuQw+iBwhM4_!;
zVfzm7eI|s-pojb_gYAf&Bn!f{lW3Cu(1}`X8{&=uvO;285C;Z8+&ft0pw(5RLLydJ
zL-39+K7cylhJY>(+R(aG+~|NLP_fgB;<zHlPg_aLFbdSN5KX+8?C*ts;oWD_cgf}<
zHita1UZu|ZAqN1B<7Sf}(R(A14sbh@Z`nrwPjUb+h!x2Va$|{T6tkqGs&u5HmX;n$
zqr)&xA@||YbUt!%e2s5B!D=MO`GOrcIzV$FQ1XfbIwyLhc*-O_zy~9-U(k>f7*o7B
za~SPNHap9fETp@_+#^9a28Y_|@JlT{{W3`Q(BclG6Re%2bFZHJt?$@z>WQEH<q;JV
zrBDB{o0IfdR94iVDk`)nRDSH&8~+0H2!DF%Kizm>kl=(L?et-@hqe`>wPc?>N{7uq
zIxj8G(?I^Pa@s-a`GYu!i!;=X#hnj4K$hekvFW*-dfURGWXpzavcT5-K(7WG^Qx-l
z+pZQUmTNekqlV08o~2r<q8gg6gn=74zN%`j9fp2rDMqDBg1ixQFU0=>!>}zwvsD)O
zZdG>!BMf{y)O9P=G)G~+t!R!P*yvMXrf*agGqfB>!{gnd`^+~T(=!~V7|hXJ-S?fq
zvaHYsM0Ba^N>$gZAv0|TBosxp4RjIsx}iJ1W8NJ)k-)MQ#%u>f!8v^2_e@hY?JBE!
zfeGw&N4G<!Y5}u7m049^aV*tQeY=WIgS$hws#Q%f93#|2K=JHA^{S?Zw*%8NHAfF^
z(^GuMuq;Il0}!w3IHny2Dl;|B4&A#$cWuY<L$zwCRs3JIHB(bSoX}@XQ55D{y5e}D
zUj;85k7<_Ysg@BszQ!EK(;a&g=&EA-f#EUG-q%gT4!||5Y8Z}LHABsHsv5u;A;U<}
zrL7w-t7>MTn;=WI>f9Z=;s({wb1em87Y24!aZN*W4BrELO;xx3DhoUpQssJv7qFnJ
z8r4v>{SXom+Iq;Lf6zFznc#<psZ~`NUN6AgipoOG4h&E&)O^eJJYq6qmhPA#aRS0_
zDK>EN)gW}8O+?dGEKgMx$59~ZOf{iIq3LTH_+c7u2-XA+$N>puCMlV(u&SwQK2Az`
zx?PnFcm`IVuUz6~;q&A0>Y#UxAw?c(MwkQ{On!hpla2IG$EaMWAC#;b=$eTEYNigh
zfla=u7|?wc4qITVF62uCEg+Pd9(bYYsGh3dol~Ha&J5MG48v2r0P?S5Y<g7%8x+&_
zKqpH<zYtqZ55v%6T3A&=Xsd09p5_VYXU7MLg!nRY0<fLv)4EIqaw?53TOEGTIJ^mC
zZAG^<sCmdVTelGd@<JBqj;2)A!0}w{m@6Pfhzi>Ye5jlTi8lh@GgP#!ZZc*E65$$}
z0R?lQwH^#w5bCz$k#$sclUW+pIj*gGx?!2Ds#aY~Rhi-`dSIFsyE{c~7vwRkmg{<E
zRn-l{Fg?Ah*g#BoU@=@%gUVV}%Lo`0&wzxvmK#>l+V(Ab6TLM(4F=QjwW<R$z)<P7
z?y9<Hs*d79dn}Bmss;GZ0IFf=RGAsV;Dm-}X}Y<Y$g8l}uI3wx>l&)%_>80vU8#C#
zR4pF_H#{FKVTN9<!YtUf8CZ6pg`ugqOz7=~lI-f9?*)p^Tn%Q1kqxw}x~7CCu=Xs|
zWrhamuCKuqyRgYnEl;(B038I1vB^AT!x(@9hOO&?Z@8A@h9;!JX9`nY-+(bTL4Feg
zZ!iu2gVhXO+h(xVRoe<SnMt72j&E5$CJ@W@O~un-)L<VB+c2yk3@k7r^n+?pRdh4-
zA+cW7@)Xx|Le&HF?=CZ@rP&(hJ=k#-Lg^Te6;^d4Al-zR>$Y8mY<ifh6+Z|K+c#my
z3=GkQId+vzxT-pE4nR@`<0a#3cmP-Rfw@=JRhr8kO^2`tif1cix^*CLdYEW5SJSjj
zxN3xos$k;qHHSGW><-Ki{vWt5j1_3FhG4O#II0o^o<#!y(KVG!u!V_g6Ut!L*1f><
zp&1xIw91F<5X(HxCXsV7F?t&2Ti7Q^l%k-S4v(dZNez?CCfejH0Ae}1>Q@2Of?I(h
z>$>YWFnN}4+NKST`<`MdAcX2VdZ2soC>X<h2L9ijt47subw|O7^-u{c6|)g$AW%Vv
zM^<Ib!-Qo)WK<nSST|H#x9re_XJr`-k|}Wipz+V(Mt*6?y~(?IfngA+DwyVmF67U0
z9cZ!cgbdz^MGlnZLqT+i7#u6#R}BM3N`=x0_1kPl4+EG?7nV>7V7DOV@azIOJ3!L_
zzXR0>lmHgf#{}+Rmc_*6n=l)s!<O!AoKhda50^RBIO2R9lR)D^{2?zlSwO-hZT*XI
z$?!{XhtsIJY<dDslbzC8&OKvV_s)y(cid$@4_oa=5Q4H8`K~!O5ijvTT}i{)hwhqa
zdj=h(%Z5U>%uaq#9m{|IhK49rzPO;Y77iZww*{<Kr>o7x(O}@vxJ2m9$(SG_9_beO
z%8o&DfUkvUSBYO$0RJA#JQ^WlmlPwx@F@hje4{K^zXDpCGLs+*C1W6nRnX-a6sXK<
z^UDZjWO9$hLK`+dO<3*51sWB_!eI8&?v9TfZE<99m)P8X<5NeIIkDS=@W?}h0r$LU
zP@ll-MBsZ!(8gO5=0qws?<o~Iw2V%(Q?WNf#fB$F&<ODF8wYnc82(+^1G14{^Ph!m
ze;gg(JK^Kd?g81pkFXNLXATFWWYcyDvdw{PM>yF=>-TLF_1gw9H+>|9|0SsTpTDP+
z=Fsi|rT<b+>AR@;Pi!lw`S!tJknHAh9Uc_nVFn%nqEwN%!ViJsBCagTxwq$Dms>;#
zmG1E)T)c|C3WRqXKTX~5d>bZ=;uufigkHT@M{a%TC3lU*&*A(bowO+4nHTd*#z<HG
z7T%@ME6=v-4;x>>GhG-qU&u})=I_A0d_0t#?!6*nv`d6p@oNw6p~xR7wF<E=-hOYE
zGKaTUw!4F5uJ0lTi|%KYmy!)UZtxmEgRaFrWD={!&!Pn5`#JoRoP3*BY)BQR%K<5a
znWiE{w$=}&@l~{L{5t+%7>&P=e`%P%h<^d;e-!`xlKAHziGTjF_~%#nKPx-jLF3o(
zv+;HO0cvDaHbL#kTP()iQ87?cj8d5}RMrt#VD&p3<SbZiTZa|t>?T+}^fpqd<HGf=
zn7eS34P8Su5xM_;YUD-<Me(*xP<r$dW&hWGN~@tO@9-~eQx-42%VkoK><>q=x<_)j
zQ<5|K^1vG;^Em6gx=t0jA_%!8SrTGE{Nv`bLB!&QvB43<#XB;%$@N%h<UVhJ>lwv?
z8z|;P(dMeVmyYDra6E<X7o5~=DZLjIc}#(@49OwN?xgcP&|DWMjJweWFAHS$LLuSe
z5%VYaA+&53;~^Nev};<8BX5+_3~-;z?PNFb8}#Z!VF%|$&J8ycQK><y+4xob5fYaa
z1|vE@HFf6_(gZ3Bh>voJjT881B1amJY*5p9a-)jV8&z=ob{Iy4pQ9@A)c6f8+iQR_
zon_l1os%P{5J%!Dlyej~?cW_Pt!!V}#-zgAKtWLHm8p@DAigC7aehV+NkMA_GB0vS
z_na}uFVXcFd_JWFO#Ik*+G$Tcn5{DB#HntIMtKB{0)w`XGwABn2#ql)nia$<Uc9fI
z*>|3fq$8b&HjU}l)b*3c4@`~vR@t%t6jp>;-vu7*80W#4rp9872g$4;?mrJM&=E48
z$T*n?U!EHEt@D5%Uz2?oc(8Mv2Y-EPEXH{76SIQ2|2#N{&kEqyi4EtBZ%mE))_H)#
zBU#@C9_$+D!Ea8D#TXC1J}ZbV^I&P#`MXN%lM>|toaN`;`H6OV<adFHYq$7KFWl)t
z+ldzI52qgBRykEYg}ttRnJ_AIn~AlQc)|(Fvc#|43CkIN1#a#h=jI<wjp-OS|2+rs
zA^KQ{Xi1a~p7UxV6CU4vzg(=tr;v0uO8#My%#(bqN2bPRjL;9x3L;mV;~d02cdiyV
zM^eq1$c^(;BfnLZI3T!@s>LWLCOA_sPL0VJCtjEp#C_+)3F5?7&D84D!`LcMPI8`X
zW{y@SxLLu}IE`_~ofX7==gwo7#l?iU+61!<U3Rs(8T<aJN3&HXJ$_2wlZdZC@oeqj
zZZ>U#J9c|&)W&%Ag;_zY=M|eGNGPyKMj|_6i6iE+>0vc;bT(PP&g_}Yy}^(ukMQlJ
zCDPAMO~$PX$(~c#UE}>0X1KX=N8&3}V=yKQU*;e_L`UNAs}xc{R}867r0zGT9@|!_
zd*l>F^(hpPe+j2Jfz3^FCB88=I%A~%%~?U@a{hI}t$Q6nJAr6GdY3L;iiM;WTsnoL
z6O+V#+uZ$f@lH}?AjP9x#G|MND-+y{Kb)1cc`)q{W(Bcj?#yh3=E=X{hd3r1qNnd0
zNA_`-LUujEgb7~6lT)KHrXr7X5Fe&BBGOWNM6ZRreE2{o3jHfnk8SJLsE>6`iUOn_
z=fOs;(T+*>=={_OjS>6BSwZ9y|AOGxy|zb3i7U88WOKeWrXIsq`ErblevZUs&P=dH
zt5c&i#+hJN5ci!kCE^V3fkq}U^aW{10q)yirNWN)q$%T1PCcHja_I@qr4%7tyCo1R
z7Z4gXTa%VQ-#;~aV;s9ZD~R<Ro52nKYnZu&CoRn93?OnWgoiN$h#U*yQqBM($KrnZ
z^I5vV>$oYZ^eQewyXH=`_y1sOer{D_kJ45lr941bud*^ed_y=CgmllipZ|+fV>2e8
zU*#Y^#F_QfC45w`j`Om7$xR6qxF{cY#q%QsxE}=HBAM*X{I63FcB`a+3LAj}C!CTF
z$|+7|fm2!HRAj}ZnfLdn#&3)nzdI|4Ttj|a@N=V?cV=Jn`Ma`BiY{Gsw$*soL3||X
z{%pE`^zQ6T)eLd@O=4nuCM_xUPmT8&oA+`MAEM4Z^>V6aDWgIpxX|^M<lKq`qRC2E
zoqDueRl287WqOu!BuA>8AvL0P6B8!NQ=>S>kY{HFk?Y-Q!PAZOt}$Z@%hO|=qdPb0
z+ctD<f4WULajJTI>OpOlb<d2mF2$-`#A+SyCiujEY-$|Gcz1DD5ci#Tl{CN%tC-4q
zI?ttgxS79kW9rdum5Iw)z!`=xMK7K5QjOfm6+!CKgoXZKYGlW_*_#!_dT!3(X6Bx%
zFwirA$gvRf@C+bwEQD(|1Be`pP5k9qt<wAj++sSwN5^rk!lZTG-<X<<Tb0^<r*IG^
z?YdxJ_KrKpKRGoLW77CnX9clk4$SP2QKA;U<v=W$Jahk(sd3*b4|t+h)^~vk^W#kT
z^{KHKW5Ta;5F2_+_k90+{vxve@$D*HT`^I(|HITn+A3l9oob`&vgo=<*GbEbe>XK6
zW0d{3vx3OQ``^q8A~$n_zxTk*%>W|DLL?{803xTw$yw8P2#fT@#zxuE8;beN7G%29
zA0OL$Z<cF^kaCWbF#PuLkzDlO&T`Qkc{23#Q};S1<TeMfq4`+4_k^AHl*qeN4|1|W
z86$1-Fpq-r11n{GOby=~Cr3{nSjh~`#C?Qsof@ez%71!R%FpVSl-~4kH_tVZOwPkg
zJn;^}9dQNJWPASYQ;&43<bUE+r+^TTEv-kW$b?B&{^r!kjj`dztRQmBHV~Y=*NfX{
z&e3KL4o2|3W!$a7dFG~tkXszw+rY*A3saA3t6V#M%Efi0gcjdw23nkRSz(6O2=68=
zZvXt$D30;&zn&Guedk^IEru)4>F{8HBj5ZGIId~!uRVv)k5DQVZ3p2S-H1}q6^|1g
zsb83Sa9d?z8L@PMU3nC{G9g!{ja5Pp!3vJt2qPz~YyaNVh>kJx=Vt|R-x>KJGTm{F
z8*!4D#@g5FJ={@^*x*E_{p+a*vQ?%%bc#Njz%k(*Dq=Fip$W-vzc)2jV;uUIvx2zq
z99q1LFVtZ2?va_~S2#{ub05Hme(yy*ecX#UbSjnzkU``KjPPT^xrBXFBQwU2J+p#X
z&yN{=`g~a+e3%(P<XF7T1#3e$b5>{P;X-sV-M+#{Px%(&M9ux!)CAqC<~~vkC8oHP
zQ(OwNGGUT@erl}7B*mT;#Flw9^BOA;-^=~YH12zuPS}+$51L(kCv76Tys1aERdyA^
z_i~3b4fn=`6=J{ws{-RDOp3Ls@f%~@6%JyCrP-`HQ^qDH-En|juWN1-pUcA6JZa*?
zx7~}^J0OvTvTP@^<$I<c_Ey<ap>0cnU0Gm<6dF2Flwnu)=<<oO#IDGmNlS<CoEp<H
z2Hlz!M6Ow%7d*b#ONWPFPVX8NpO2>-lIwoG>uz*z^)F97l&$jZkyDtQ#l44R`jmZn
z1eXymO|XA|acaEAxb$PQf>_U`8K${>rWDFN1Be`p`!rLYy)1G|Qrr8c-|yhVtR>^D
zxcFpqTl||-Q+TVwa~4x4-JO}vmStR5OvsguGF{42-q0dXaDu-+HI`$d^eeN1`2PVD
z|6uB|ZIy{TPt^l_HH@y*plcm=tW5BT|NYdxk1^-}nia%-XU^%jgx~pGDK*Q%S^42?
zI#-p=YZGVG$M@Z@h08NpN?mH9gEIe|HxKCKSQR)o;Z*J;Q{y+rxd&$jao;(&*-q~H
zsWIQG(oEjT-LW#^IMa($BQeH-7iI;qWe&`|M%Z*GcXevqx5|SJc5-*DOvp72rp987
z2`&e*p}&96m&lv#<ldfoNLwZB<egm5b&{k0g{jdPqwIIj3L+Qp@0b-t?g9$_-cJ{B
zW+mHou8qC*iSy6TOg-?eO2O_^F7LH4zf8ze`I}SsKgRx_;vhae#d?8Gd$_(o!2L;U
z=_khJd`bx^I5~w-6uzO22m0jW^~mkxO1fD11QWUNTT@eEt6caP-vmvurRz8-{$Icr
zhpga!3v7|>T_$X4yHxlJMZa$EB=!A`sWBhp->=OIB3Ix4X;u)q`U)w!2kJWmh#U*C
zUq1tgoEFBcp?tz3y`S>KOT@?ypKNy5<zxHrji*faZ%)j?_&1YsFdm+|*D?7%$w6#r
zpYB5r#v`9{dv#%dV2g0ELmZXpOL`^x(APu*^upA`oNR!`h?_im>RO5nnHr8vnUE=S
zWU|>|+a&Aq+|+1|QQw-C`i&Wr)}Qz+t~?avUZY>~W((xhfg^NT>EuL=&rLnlt#aVW
zQ-p`0IsYXwLaJScQIQRk81c^3*o`sbGqZxoP1`30FYk3Y^{5Py@uN;Dzb2~5cTYWr
ztupCY8Vch`U>Bl=FJ7(X(=XIx(s`Wkm>QumzPvvxi2Kf$XVz(wKWGieQMtyDc7eMR
z>)ys0GJk36QEin|r`M}fju!GQ3TTb!)Py~xAD<e<G2Z>?tRU_?@18nOw+Z*^IIUCi
zSpPa>n26vvi-0d~5bq2&$T0o~Q;%t@oO>EKX{1P%B~siSmQiSl)Ck`uM4EqbY6Qpl
z_SIQItmoSdo?`B7im7o15IGh)AIOHWi<wuf$4GoSF~5p)6W8TGPEE_L%FA&sFA|H%
zKFfqXt^a#!e8$A%{}fc6+6kZ4WjQsG+NI66h8|wHPd<6_)MVOkv?YYeagy6|a%%j>
zcyVl25V?{Zo)tu{szM_E%T(3N^*-!6PO{fS+{7>U87I0=D^n9<>#7P{!OAHX>4sv_
zf0{4@e|&0u#>C@g4q}GI-K@HL0-rosg#*M!)$_TD1aD3~z^xJ-*M}1x<p4yVoHw%#
zTY(d9c&|^5(iqLdSwZ9~=?k`Pw33*4-a35A?fGC%T)I@p*Ae=-&Tt}QKA3t4TV>3V
zQ*gU{@FgyHGZYFg&5lXSh(9qkI%7=vK0(nBZO%G@Q<&KjfJb3FUECfyIobLrryk!{
z$$gTJWM+8q_^QNXl;)FE;jd1O)fm<PyIDcxs_<841(DBAg7^QQW+$PLGl0mk5T<wr
z5IHS`J39l2919Wcn*l_Q#j#mENWuaUT>dSesTFZ%n>X!=uk8o!jnhcOTo=fd`jH=@
z`=eQfJHG<)KXDKr;tW4`Y0$&kXL6wSiTg#oWY4Lt?01Zck4@d_n4x-jRuH*boa7)j
zTx-tiP#t}x-o}Z{IxZD~DfgQlL<1(%{=(E_m^_P&32t)i6prQyBq)ZIA~D8@b5mn5
z#)yy23Sx{AC7k%h$Jdav*JB%g1ZwNwOUpkQ$LTYNGdMV_N#A^1x|kf20nr-m65$WN
zhxWzc#pE#ESz8;uvzE%|sXV538gF+(-l$WP-wCUwUkLl+kR|)&H%#fHp1iw82Q+HD
zM}K1aGr%8)uY0;T0@m$E!%zGX{!8Y3mwzFHy2GdR(kFcTZs%&V;|=d5yQ6v#z$3Yx
zEXXco!JTAJd(c9nBMXLa{N9daUVJO8({8Q}Zwrp)giUtKuk<D5<*3tQ%e~Gj>n#WD
z+H&!1YoEETWe%qczr4~4hRM!mz0HOz+r%|^LVaeKnDV(zn8F!A<g)W0W;MuiZsQ+?
z`|#$r89p%gqmY*3QKa2a6MQLfkN9U^{Ig&DbAbOd*-Fqz*G+GYMYL}m!XK&D&(Jgf
zKH;C8x>pI}i44S#a1bBjM5mmO@ToZ*NI;mF_Qm)C*z2sm8uiJckKGo&j)emX+5N|p
z*HS+>_0YFS@I*c3k7CGECk2M&>Zcgey-(tX<{00b13@Vfc4zML=WP1fsc{`+(^qB%
z@o>iJFAGj@wECTOCS81sts>_I6Y1T8K)*9J{##|&A!NJ?1oHS#&W$Won{(rzPmRhL
zH@-P5i2KfsLvP?5HysMOJ3HnM-Y0XF96r@bF_^@UEFPEhW9QVkjPYaJtRU9&BcJ7V
zbA`T}0hd@D&lF6U(iuSHSp3kef<;)+M@SFCGpoVPsHKh+eavnVYo?Wl`DaL1j__}g
zuI%UQ#g!fW>!T|>@pW^0G5g9c|CsP3{|n%v(#p0k3>$A?y^8JWZC@NV+Vbbhw(lJ_
zejt6=j)yO&4?FPijr3tB9_HZ^(C#)~|A_p_Uw=nD>_GYZ@+U9<(e#19{vA9l;cbMq
zR<`x=N%ToBp+I#zQ2i{3LoEUG+r>}n_AiK^)YC7BpF8pMUyGl+@bdr`)_83<elE+O
z9F@!I1EF#~eV`Hkne>51_z%Uy9A5w5<WK(kAzW7quyZT)x{*H6>z~2{eIj#?f~fe4
z^5+ZB+wuJ83eP+6{0;H)9`x`B@+a@%aokV@Fu2PTKwrcI0mTys8Wf%h=<UKY0sX3Y
zc`tzezW6zhpL>yC1_1K}AD_A{c-n%@J3!_ZwE^a6{wL*6j?Pb|4}{Kdqz^RU|Cl}y
zy&l6^4|;uN7alH(2jWvt{3Jg8p!~_f{&f04V1G|M5C``mEf8>sgUjM4aqzPEN!++D
zeiGS!SpMVyza}1N<o`<k6vN$cAtA=T6J!6!P+Xe)@$SDBKMC~{uuCWf>iA4I*RZg@
zDi#5E(Xi-?fSc?`Q>;nLN;$qx{yf3X3e~g_y<~+rIwe}7zpPMC3qhK!&`1kGq~w6?
z$iM+C2>=Ak+L~!0NSC!W^R^&k*49eff`(b4ofblll7)0s)wFb9p{bJ=?k_gYD6mj0
z%}8(n)Q#7PB#|&#Y`T6KcbT~DvX4DwEc1kP;!}gkqFlk&<Qk3G!A;`3u$Plof^o9Q
zmx{H1r`BWM0N+jL9}1<mU&1@IeEongAM+<#N9Iqopv;~I$pWnx0gW%D<KdTv$)R+4
zSS*#0llh?2!j?;b5ARXG$u^(=v#;0b^lR~2%j-0Ujo+o!!|u!CDf>V(Efp>%`{TMt
zj`cYYd3ad9rq3_2X6HJdch#|K?c>M3fZ^-xJ)TK8ycqrIi;X`H%r7Pf>+xHxSa&Dc
zTPu7(K3S-_?N0lA{z>_Pm(0oghKant1MF5F7$ke)U$<BBk>EZb!km08HrWG)2?Q`!
z`6Awvg~Y66A$<Zn@R9giFiSi9ZkIqdeg=Bi_<j14_*d|2ln{--jiQT<|AGD{d-<T>
z?7i8=zz^Wl*$5f*8MbrWR!lTXOV0IH@!a@%dMTqw<L}_{PUG+5FP3^=<^LcM`%55q
zVYIuzG^F7d#*qa%sEp=jyiHe7;2+AQ#6KiV_=gsQ?~>`*-r(k<@eAk!L!WDPf&qms
zZskPX*>Vx2Ac(TjLgdCZ_TGS#QM^ul-R520;XU2q9o^ym+!<v2+1_0%0BZaz-f335
zqlb@9=KbX5ai42MvJW?AtajvgM1i5iXLr-}816a8tH~Z*^)ATL_(MQP^kgCKM)mfM
zO0(m;O$J@4z1?%$vB*%rgpU)g;e+E#jXy%`<Y2AoetxZnq*C61qEHBz@b^I*x<$T+
zkAWw<UgL!C<BPtH9gC2Ko%ClH{n?E_--{TL_q{_zcshZ=1(>hlk{tPj4~B0;v!!+K
zCi~yu#4l|O{XhZwZt*GXVdE$YHv+luGXGw7=@Mc%!%6raD?l7Uay`n)kxOeh$KNiE
zAc;}#8~MO03BqVmvJZFSWM5##3r8ki6wY6qSe0z}<v#%1PiBkO%Y9t-D1?1oS#sCA
zJph7?d5s(Mnl$EIkS7@VWa(0R-M-8_OHV=5QT0;s`e8yXosjs{!_{J4S+cD(EHo7J
z&S*nfrf@c8uZ#J3w52Rt*HTQ<qb+6Gx|U*!9&IVhWXo(iuNB*7rE=nK$kzLUdKi||
z95|lHJyMixEv2tOAK@>IVkpbjVQ5aoFm)|b3{wUP-(nQ5EL%q-;c$$$lx4EzIxj>t
zU0=8ks_;!lp~|xLP=&*?4yr6%-?k`D83rTr1b3U})!ck?n<)(^oXq`@y2b)GFL)w5
zBaIE79;T;9(z?g#iBz~z!Y@>x$_kzm1*fTi=Ay=uDELTLa8?v7Qvu0IqbdrttUwn9
zW>#Q{0w*hYP857JD|kT^d`njFq9}MND>yF-Udakx6$P(l1)mTFuV)2sh=Mn>f=i;{
zt*qd(DEMSn@F`L7nXKTmqTrpZ;0iBDC&^?N;+Jp{$m`gNkCrs?OU#7ZV%iB9utLEg
z*^Rq0;PAi<%V`cN%$T7TU%}=B-3a<g+`V@Jm$YCeJM&$b<{kxo$yFp?eUMx*Y?B4H
z<_CH;(3n?ME#G#vK(SoI@f<Z|HuEgiQWe$EbR`Vj!0}a8bL}wnLrXC#-S#SGyT+5F
zU|rjB{7|hLY8C%iZOzma-*-ZvF-1|BYw3#Pg?`ly&<)cp&r>ZUbbO6Dj;A|z3igRn
zuvWFIDTZT&dg$o3X9ucRH8s^y1Jg4#M-Oe&Q+&s;EJY0i%~q?9W7=V$GE>v+&`rTU
zHVW1Y@xQ<@Y|FqqEb!f`4$Q*9w?kdGLQQiN=G%(q_<;@5D9rSYs$zzg<7jwH!InnB
z5)mz1Va#?wR_rtRzGs@MX;)d*3rqmkF^Z6>TEJ{iWmeT!91ElI?W$f4gB0wkQLwJ6
z*nVJm%=8RjHw`-gHdfUz9J6YMn(I_G5YY%3NCJY}y5X{_W(K+mnANJ2f_;1xtj~PY
z0Z4}_26Hr52fqT#vO*gJ2W50!sp>$BnKlEh6h*ZSP$KYkLw9_~Ou;@i3RZE0YUsI^
z0x1duyQ;XRp*e={0lul~wqIodK7<$;u4i}w3#zJ74OQC@fkJ5OVG8ym5-eGe50Zzn
z^%qUqYw+600jxB-j7#IQBaJUuuBS6YH7&#N6fXdoRl^PSs)`O2)AoW8_*Db&BGB|O
z3@xUGRV4%=Y&-NcFU8@^C|F%(p$n;jY~W?hv;#vkb&wET@KwctW~sjG2d3&m4mFGu
z!mH_l7n+Xhsd@_bnNhGtXqZ}6_0T>5Ar$nY0W{PJU@;VrgoiOpcg&Ea9cpMPHpuF$
z7>JWe<LObbu3~wrsyL1Usb;DPy$(%Z)1aXyr~zdS9Eb?m%uLdIUtv{K)qFo-o^Dq&
zm8?jxWT;_493bKvngNA(ppYI^CkS=h@yJ}Ly2&g}HB8r5J>9TOR#mI6rK(Kv6g@Ca
zi={+RM!~u&6wB3oLvdY0wH%)jwX2S+>Y-7!eDK@wd|S7fp;xPra@#fo%MP?KG!>U+
zV)NW6SfgsVx}zwtccBtkDo6?P1p(y4W>v;KP}>TsfvQ7fbVIdu%MMLg0?S}7`be?0
zN5Mk7buaLIAL{N|Rm=4?gN#zu(`-V=g$499*eD1X(=<gvGaW{!3jKxrXJE^tU~NUW
zH0W5!G>jBO_Cgluj;2)A!13Gw5(>EsQDHlQ4?C#Ab{c{287f*<GXblPf;Bx2s&4oi
z$Qgt%H@dBZuAZqniVL-~z{IK+;6DQ#3PY#L%n&9tG(1bw%}l_oQLsj+s0z%GuQ|+7
zA?A>F{6BDA=!U{nHPkglQyi7(Z5iN!Z8J?JskLDAGc9vQ!TJhFXgRv-S3yz>28Y2o
z>8|5I=`7u}P20zRo?<E*q}g@!K=)vG8H1rwTq|XnISN*FFzdnSDj{SOX2|gDs#f)F
zn24&blJ$2q9YPx@o~@7()1i2#hY3t`(N88|#wb|R(rgWO6O)<>jc^Rd3ah$70%m|y
zx{Y3R$cRGY4-MNlp}U6VxGt=-t7NoQN5Q(f=X-&oGZ%toLWJzls)C%M31)eg=>j^`
z0dj{SL3aYEv8UQW0F4L~Bb%o6QLs>L$G0pZA7s{4JPr04X2Jj&tN>CE(FlF$Lsiku
z(1!qeRm)Rc&k0peu``w}kAk&b7*7*w;Cg0N)eXZiJ-v$dA=4d*mTPJtF!aO-7$z_S
zR>`&8u!`0;R47viZ5>z`M#!gO>w4fDE{GPI5OkkGxLn`B<ZlAH2@`2Bs2PK60p{9_
z6w$VVY=-)n1WPdxSg<gF0drxOlmPf(teDXQcok500}>plMxX?+Up^)z2c{O5-8Z2x
zL}N?$wN$`fSPwQ(@e*@G7nHMH2ewRiLI&T(qG{CfF&rI&g6Y-wRl@+qR68^TPqS%y
zK+f8i$XEO#{rOY$=kL>>@1Z|;=+CdvpM?JWMf&rz^yi1^&tIoMzeIn2ng0AH{rPX{
z&tIlLKSzK5d;0Se^yka;=j-(62k6h&=+9T^&!3||KSqE44E_1L`11jxZ$VS!w=}*T
z1<AsN&h>V);|An+#=_ZbEJ=!pIok+BxGHdo6wURkmaRfaEE9944?Q)iDq9w7>RNie
zP+aK-A)L!NIo#>hSCP=vtZ{F*Ht5yi1SfkbhE|ht%VZydb+t4QfZBbnwYX0OScVUi
z6Z{FO%(&CMA_^-M^+e$LjQ~+O6rUGO)0kdz5U0Cv+cM5gUaj#|8l>5*hOPAXA^6u`
zlhqJ+5H~i*!|3_s0Me~^alF><yElf7ry*s@VYk_=Aw+r=aWgdUVJOJw**EAlYq1~E
zeXzsmB{2dKjHM9au?U$9P0C)tC<0dV5W%_{4{s-jMKpJ$v{9jc4)TN@3M5C&4OkDI
z9Hd_e&LV>9N1Yx4K9m;4&B1Cd9JGBD?v47bW(~I?;xmaB!8#Hm{@d>KnFxpRqf_X7
z@p`9+R4810Uu)IdgFZG8zJ?gvz(dMKpP!#Z&ceqCzyTE20@kdz>KHOg&vURuhI+V$
zem{>;8z%~lDWE804Rq>Um+l-&4;4$}u8Z3}*EJ0w7=0qj5z#d042UW9HUKjW|G=ON
z0bw<Q-T*&tCkN%v8bZ-@Me;EERYa2)NIu$LCND?0ytF;YN{>l_fvjBgCd<kJd_||<
zY1QZx$1d=J{LS}3_!=UmNS(Tq>?g{SsMfAB9K-!Ik>ZfgAQlrU4qt_cux72ddIJ=x
zyM$$<#%aoKFrQPohHxSqMsFlX^CEbg5vz46T$`AiCU@2NR>N|oG3c&=K{fvNuyGar
zL~k}a_-Ey@MvQ;%G_KR%<YeAc&#lJ{nowiC9=@b}r*Vt7SZJ}{Dyt!Z9ob_shP}{Z
z2$l9~T}T>~t+9U_#(lWQTG%NN@+*_k?j%QwrJX^)I{+Q;B#T`35%_I&u^SO#L!ogS
zeT|kQ4~`8R-%sU7q;d$jBwrvN=+6fWOvGn0ej5e>cNf(7hoET%K{p5>#}94KBnzT<
z3<Ie5hS6)uAvp{RG9pxX1De$sQg0XvA0H<}TJu9xb5zy{i<Jhg8$UvI$7G!d5Z1EF
zKTDOzWhL3209IAX)UffRRJ%~`u3fJOtE?Z_5V~*tI4_h4hn*%VePV5u_bKZIV-Xym
zNA4p=RP$rfsRNm8!lHz&;T<T-A^y<?5p0km17SZ_EUmY%VZWz?<L0P&xL8BP51^cd
z`UfQ_kRBVD)G>B`XcLFDW)T|MX4hdfnJ*0eo#aqzL2GnG3yR$xMjs^m&@#n#*f@@v
zr|}B@d|~*O40a%jauYMvyVxVxM|#MQ#FyX0%z!gBeKL@U`q!~{u!{b1XM1Ou9386(
zI%`82UQSQcCl8Oc$`5eEVqg;S==Mn+H_Zl!)9mL3+1rQsBly?sbguGt!{j(GlXvQX
zUOX)fl9?<F+M<nwwU3@NP$yUElaDy2lU{tAzj#DejrOy@>lZPb$72TUC>|yNI*8&?
zAd5ZLZLXE^fd^2r(=Myn_uwD8>%FH9S<FLz1=@>vJ#|w?ee&Qq@i_5o0CRk-4&<kb
z0~!Btr2!Q@mbwh-jf5HI{NB%DvV>SPvSZsmzS#maVWQavO@T43Yzr7Kc=+D+RfxLC
z&dp-*BI=qwiok02D5CM%qX@ZYk0O4a?RgtAT%Fa6sCHJLhO@JJ5uMH+MF={36tUy=
z8{+x1#C%;$7$YZ-7%D5GjHD^YFwOhWWiCl^Eo5$=lG&3ZF3ct3j@%8%N)L#1Ik+_V
xFgV#ExMY++S7TV~43mTM={=ZRI^>j>kWmmNwDr1H!}i-%C}Irx84SG2{|n=%2=4#@

diff --git a/_build/.doctrees/grids_2023.doctree b/_build/.doctrees/grids_2023.doctree
index 7446ce6c783aec81a36f0f04d296e25361909d53..bdf10308437fe0d81476baed56789b751e8c8b2e 100644
GIT binary patch
delta 21426
zcmeG^d0f?1_TIz(;DM-#JD>=P3XkQnlmXVXsEL}Xm}x%XAwCtsCB;&4NpqpJFM6tR
zLo>BfK`YlRCYx%q(#FP_921*KtEr^PrZSh`x!d=BQO7?0KEHo{Gx+)VIQQOj&vKV@
z@45Hf?}8_TUw9$NuflKT_`q7fZo~bY&a|QeqwM_M3aUSyprCKhCn_j>%3T`o`(+Zs
zZ`ZO`yN>4tGgVUEkZ82Nzr9MirVUVd6+f~>WB2`$D)}BIciBc3sA|}-fr<}LZ>Q?L
z{(wtCgJ)!^Dzi7T7^8BOLczL?EY`R*qm3#pYoKIKc@LG0zD)GimA6$?UM(M{3LYE^
zF-Gs1CY8&qt5Kno#=4n`+p5h(?&O1-+y_;VX!IVV$=yFjiHCLX5Z;+FN(y8B*%%|v
zrL`z~M9Y59LoCjyam6cfPPue5_sqXv2{v~Ip`4r*A(N}#BV{|z)(o2$C`!ic*@IPu
zvN0?Xcl3jBqozDi5ssddr%J=~Al4`^)PmK`(W2DuAc?P-1s&X)o?|xef(p&@HMbfR
zxcn(<vg{(=WUtRA(YDRiN>&$X$_+b7gW$1BNnAbx9EN9Xn-DRy9-QEQ$UPy+=rcCb
zs2JmCoSc`cB(433s@*zYDUMP16SrCOHTkk)t@)|>TGI7%s5dglwQWo}e4M1bZGl5k
zo-=^j;N&<xL>m4~f_L(0JxVKx(XvN1qY95AZ?J{BcXAib(9JoQkk2jD$f1jFRRz`i
zsX6;kXk(LFPM$P9!-#gbHgYET8IMg!Qdp-~lf++7(9^;`QFqgzfkgN5iCU(zHI%&g
zm}b*3Q7b=su~t50EhHKHN;IjDOGXBptdkrV{y0ReS_gi{1Cu&Q=Ej^!eH7HNB*%)(
z1;s0C!Qbdvsw6ckm#P_SoLYLns+P4ZN9l2R9kuA}GQ}Lj*HiM`GA(Xs<v^?-2mwas
zWHry53`&zhX)-8H21RTxezif_6<Rr%*$UDMQrv}(l=LEWjD{pjde^g$w}{3`8E}u$
z<)Fi-xXWY4kb}MOTn1UC#Rp?$iT|OP@OZyw%@$L!rw0MEsyw|gsfx9fh=qp~;@{rB
zF=Em?3bFLa4H4nf&d55lR>rX-4+lO%42zRJ<wniXRz99tei+pq;*IR1&8;Pyq1q4U
zra^*lvS+OyvObU#xLQ_xnpXtR8tfAX9Spxe-U53~)K{*9Y8?4vry!Jdt3-LU@p_A}
zAkULp5XUhGd&+PfYsnPR701rB_=!rVOe;?C{L@#+`;{La?hgHolYa_;FZ_(8pIaFX
zAC>tA`ZsHaeMUiq5&6|kLH?8?-F*CU?sihDbZARs=2v#Y$LJo=o7ZKZ87p3mFlsK|
z#2U+bs*zepk9+)_nMFyda=8$Y*nbL0>^}u0_MZ}u?>{-T>*!y)(jHP|RyW+IAlI}+
z!}G&EG9~wx!#?Y#3J1@KHMV}%#+O$@)(*NFUw+n0p^9x||1)taNt?y4#_BV)f#3|V
z?lNs4PM)Dnp-9S2;n@zl^c^Zq_=FZiA<g=;v|<bBlq=Eb`guo%M*F-NWBlg|P3-fw
zf3ErSJ)IHuMOTGOo46Qb)E5dDnTz%s1M4+^+OQ=VHT7K-ve>2#{8A%}ZCdu}fl3Im
zvlrqtwJdez|3S-kH%3*4`ev&s(I0xNdC>glHe&2&8jhb^Lx4X<pJK^mwepJ!i_(%@
z4q?S2y=g~Q)uUB&t7cVoEA}h)rwKLUdb4cURkJLU=&D%;PJd)s5WjK(y9sl$pqDlt
zVwQ1>5U4D|U*)uGH2r_~^*BFgs-rMNPCfyNAtE3#`2-{;pTy&nPe66&PAEvsJ&|Y5
zJ)V+t@5>)z724n#F-GQ(G@nEvd30Tkhkqo8K_u1Wvl)N;k+zQ_OL%KNe$o}h1f1{_
zO#o3UCg8h2(F71l^2K6|hzm3yc~bad4_xRWcccT(E0X`2T4wq_ZH~iL<~WRG##LjG
zR?>pZ<RX_IgF1c97~FNeF<4_AgIDZe$T1l7eP7@U!4q;A!ZP|xOIVOv!WR1*wMSc;
zYgo>uPg|TP>el7vtiN1tW?v3qf9E2z06fwg+8fz_YK2#NLu&#$GiDt9IZ>}Vm#>oL
z?~P@tSF)VEo-Ef)36b%!ULk44MMolZ4h6m<PM6tJ#RAqDyD}CXG@0im_WNgFzR<^r
zeFlEnj@@uufEn$X+(2M$hhIRw(m|ts9QO;T-MX=Tup|Kg-i_5jRRC6Z0Y_N!8R`&6
zaT0aPihyR#j6NMY;}6~06xbvYaCJNjh7AE&=Y*EK55%(o2D<|I7Q|ss^VZ!Eup4?Z
zJFq%x`Id&`2|GFxSTCw*lpSg-)xN9WjRmydo9d%wA%;oYAOkDDV3D{bmqq$zx{@48
zG$s4`5MZ1-ov3oYJ@4=pMcnErr0*+5mN;?3<nip7Dxec5JhzUuQ%SNvc<XxB)|Xeq
zIX|+#5;{zfM8TYi>}~}fsWZVRs@dHFb=3u3XTSy4U)ElIflXCa_)!&lCb2e(A?+t{
z8zm)T?a!<$eltmnBaW%?p;BF3+CYaLdl!XZ^WiMSCNz7H&I}xQbTn&?4To4Te%zpu
zU%kk(r9_ul9A=kkme_m~rKgv&2qn_#H)*_ZCMq30oDG)ZL|tYM96On{RVCb@;?~Km
zoh*Kxj=%8C00_l|msp5WXx+?MY`sepqm!^WW8b1+A+e%z^evVp2^_wnL|hpLarm!1
zE&9^)teaKBfm>+n^84|sk;1<xw*He@FGY_Va&%8Kr6fxphg)W_2*Jcycb0^FSU0Ir
z_DC$ozNh6wezt}YyUfOTf~Q|9H`Cz{uq<y&C*$B^YH7!G7J@g=WD(X9R~eN=jbwf-
z-KZPi(OPtRgf7a!dxk?tCHN=PSuCVw7`3kMs_|&EhXpfCO=!0li^+$yu(aKaWvNEA
zNA;Z1ydW08dsY|I>0TVxj5bBDEN5AY(~)x0>W4hDsBRk(&Ya2Gc%@81p+L=pEW~(g
zyhXDV6yi6$PdeW_9Q3I9>r4_R9jo`Tc*TUapL$}@28o8)e3KvTJ>!h@0$rD%BC=GB
z{!Swp9o%s^=@Dy#rpiHGe}o40L-Vzc`2HhA>5lB?#`;kKif{NVt>>y*QnToYriw?8
zs`m4$nTn@p^3HgK`2}Qlj>>W*NFC%@Ir>F1t}ig_^G&gjBOwiIpEdJnXG~+UOwZry
zqF5uoLQfrjh>2%MnaFj2Bt=s!isIopgmKH;CPr9=79Ll)N!l}`OjWaABGdyFCTjDK
zSd33nLbA2Z>6kPTN6j@y3>}AZ9NMB*m_5bMM0uWN;FJ{$O2&$bdMKTmAB&!OChx>o
zNS1K2C9;iI9VfER1gEtj?DGj_@Nm$&51LQnM!ah6!!$W`9OGzGWZ?S;m>&7FcMEzB
zqxSQb*n9zN*<z)=C2Pk26$gx}Djt&eayz5!v_fw(@l7Va$;68tO_PalGV%XEO?)(b
z8-TMOB`3S)LMnU{fRzi_ZSao(Ji370Cy!+dk~5td!ny1qj%`Ky8t2l6k37nX$j7T2
zz@l*dc4)(?bX>@C;qw6F+ox!8-vK>w$3k*aK9d;@`ydA|FZ=~xBY&jT*AULlghgx;
zqw`eZ+@O82^n2PZX6S3WM#mSkfiNOa_)hkDTTL3n0;PjAV+nhj!B|NnWPt?%tNXFG
zSdsw)@ZgFY3m5X_5iem&y(`8q)Z6gG)%9uuARBwHVNt&MMd>baqTvz{Kev$(Kev$(
z_n;(HM&~vH;x5#?vaWKT+RK#ko!W^M(v|()ssdftYfv~(k_<UdeI+XSP6}cdOw8O1
zte>jC<^r3dKysh%lHB;!z9d8kLD`ZJ-RdidU+81}v#f0pSFN#=6eE!jUZnj>_M7B$
za1>;hsK$v`$n_IRa*`A&a*q^5j!_Km+r$zi3O{ke_Rnbo!Z{lG9Fwgfj(c&fPEu?@
z?8-FSD+!UwD^euM7gErBS4f;~n-#T{%^?=gZPwC+Y|&`s3aJWF@34ENAmjkusoH{k
zA6d)~u<)6!N*dwyoZ70%UEHdPWIwMVa&+Qw>+`IQ*<#AssehiuSn^Ca2fMw%A}s}`
zlY`@_KuY%b3ra?Vdp2EH(VkTHnec3ezNiEu$3{ubJ(?3bTR1e4+jIkyKSOQuo>oHm
zG;y`Mlw6u@QyQ-`6O8fOEu+Be%&1Yo-59Ld&U#9LMOZ}G4o#HDLExzmG)sPjj_&7m
zlH3?2Hg{jz*I3%l>%AyG<hSVYO8!bLrft%?*XkZ1Z^f&D#ZSTKYFV-rk4ITx@J=lr
z_fN3@PCewfYl6#nD#8Z2CivEVEiAbvQdlIXL_xwCSwqgcq)xsFX}e3;5dKKbF`XoL
zL{%e4M2$S*e*E@nvs=miP&nM_z$Gu6<F7alkG!lH8K>sQVGr_KC0p_}WF_)4RBiGt
zV(>4oXvN62h{aC3E&XWmEO6v*J>1BxP=ZmAhn^CVdo)!F;ZXE>^aj4OM@v`XiN(;p
z7V_!B`80AK^~3&qHT9Ccx_T`^=2%M?j<djRwa+pm(xvlL|FLEIP#$@o0{5AHs#7Uq
zBoVLd)2$Isu_BngU#mWPzh+9YB3`Cum<akFu<*=~PV<q!T6j|49L{rsA1)zW+2-30
zXtE6^RCm(KKuJoqR=vvZ6SbPwil((fERIcU1>Z3=trbmc1)aV(trZ!K){0*IW*c4z
zMAs)Q54MQE9qIa~Eq=ft1U3cYl~1I{=g7<`%ukjcUq|xzRQei^?~tGogCCq?eOR5v
z?;~3M>sc<_fZ@5U4KDYA9(b~z1+#TLBLaor*Yos^T_l`&n%p|_))t+nJFXQ0yDy$*
z?HSmEghz*c|3;;@AnD6};|Jpzv=5S(U5D=Q)t6I*pf9Jg{PI(rsYPP3ln{5UB*Yyn
z3310t;gMq{AbB^H_yem|CFb3fMAUav3R^f>vZ8RXBq$s#35we(3G&-1RZX~9GFP}*
z5)>|$1jP;2taB_@Nx^TZ-akht!LpbKQe#*H-KWSj`CM_>;Ub+<%QSgjSvCPS_PXTN
zltLokOEnYsyEG^+rp8|~Nr{W8ZI?{e!vFf_68FETg)w|6IB?Kq)?Fq?Q@9PD_$OUX
ziPGw!bOjOhovzFsFpR&VlUVVc$#%sQ(%?jc$(B4ZB@uaHTDE29btZn`1?#7>n3b2H
zy9g7&qVMTaQmEe4`Tr%Ij{_nh9h^a!%^(kw#b1lDOANx34EXUD#qSiRq+~e7@fI07
zoxaA{<q8_Y*xkJ93%XnHkKy$!1Bg_2AIOECLEba22|f@E-DQTbbv9qPVHkn^!wD9X
zwcG6r=?s=DOZUDXQLAiZ>DEe1hf4!wk=MpK(w%OH80He<Hcmp^#t8`fc<4@C;*pJ$
zdHlr(3L7V}O&ceZrj3)>!p2EZ*f<H2jq5AuqA+nXQ<yjj3KJ(mVd5kxOq>M0CQhUc
z)5OVQuZfdsuZfdsVd4aM-BB))go%@&FmV#}nmC#EnmCy@O`K{jI%CRHpg3RR_D!WJ
zoGD9!UfU*#2-_w>uWgfQVcP^KY@5s!woQV<wn^|hwoMc?b^3KeE>xfVM|8ThX?ue3
zNE8K-^3(d4gRnjlZnNzSl95aMd~wC|aE~-=8BV9Gz+%=!`Wmx#RFHGC_oX%48HA<L
zWX*P%)~r{^KGQV4XfbK-&fw-&>2PO=g(X3FzB5GmFC#(vGjx?gC(P&qW1+c?@78Vs
zyG?G?zU=}l8FaGAjhgSLCTY9P8+{ZX3+_m}jdWtgKGX6&Qz$U2yEm4SE}}g%c&syc
zBd>!)3wc<V3e3LU#)H$kd5mi-K6P!Dh?u?uMhKyJwDvGtqfoaYA}J!SZ5|bKImnu)
zqOc`b@SNbXwfc9AI^YN0;OWAY{3J(4T6(@KH9sZ4D9xFlROohRI#SXy)7;c=1x2pp
z0%uab%i%~bEKDvaa;IcalxdnXqcAhwSx}IgP+Bs!%F~Rrp~!cjKOUq8vxeU-vGMS`
z!LZ0ik={4S*t@a5&l1)(!QR!Rx(fEj;XS}kb$A@=?J%Fzq!?7FXxt*RtlFy<nJL=*
zCeOdudqhuo3O=^s@@!~}A-&)W_*9IJp5bp$*j-nLpWd{8Y%_9(MPPj&2sRqN3WVd0
zxgYzt+(n$ciujYg!9)Jyf>g9$4pqDjI(P3w(Q~fi2#RNDOaI%Cs^UXOMgMj7ia|qi
zZfeWj2NPipK<i+6*HoEID=v-ZXOiJ*h?kl6l;NiAaly0==!NT22rVWUD^ls8`ok1(
zLLWsSGnGoR1eQJ3TTkMSgFJ=S-brXfC7RQUrkf_jxOG#am9v~;2Vtt9z^9ydMs-Q2
z$!g6wcU1;OZXL*g5%KwlO-+8~1hiWxU>&aL0j+-31dPFdWkNI@7t$yABzul=8hv!s
z^HHAaEMGk!4R;EHeBY9#rl92e%TsX7EwHgLH8m|QsnC^Cn4X`OmXchUo|2rBl<9C6
zx(id2QXJ{-qI73csyjK=S&))m;7Cm^$ajz{obGZZy9!<IlxwHpO(Bh^U|@)dfDM}Z
z9kpt*$1lV>6FU>~H8U|X#GHv?Jk&F>pIKK#h6k!7!?F~54>RbvAG_SBoqo17ifX4H
zc~+|%&CK&z@C@XI?53IN&tOalx7j_L^I18KOD<zh^U&plE@DCs4QXT`?-fb)B&88k
zYY49F8!;gRr^_BZD1?po+-O2h_DVn_TyJzEapP@3!QW|4SGw5vNJxaZi#!qHE+7%&
zF7bGXJBOr4Uo#j!R}`un67b!7VWKL&bqI`B;QAr3P=S1RO0St);En=DPjdxH3Vp{l
z_W?c65Ol>3wf;V!mmea{uOjKeayYL4v#x@)U!?b+qL{Xdu@rzcxF1loyvUKSPsW5>
zcp&SmD~QX()Q>2_Qee~NU5*t|T;AFH(QT$E=3$9As2@;Zy`U}5Md@iVJ>3&&x<u20
zhzqotc_ylQHQY!HajDgQgsH0txO2|a)alBJ9@q-PblVh*uic~N;E#Xl)r=_Ok9={{
z{iY1`m{-dn9`d#vt#xAy9k^_y$xU3peBe!gGZJDMz4Vz)VUChCe~pWY1A$%&2v+n6
zSCi%saDCGgQs{Q(d`~<(uxaEpjhtUOa&T}Yq}bMz%_gfjubn@x0D8Jdn{eA2Z(cQn
zn{Cf{(`qwb;3!B-&&+p=&3IRSpeobXY{vImssaoPB0hZGcttD<=~l`~K5$EjD3-<<
z`Fao`B5bVLRWh5OLC{%Rt1&RbZmDG15KvrqJ(c3bF>-rzrwjf9cDoFo*-%VkNIo{Z
z*b|lI!;k=IZ<pKnXRj%5?SZ{M&|Q^3XD!Fj61WpK6l3&ciUyij0*P>&;<Lqzmu;8+
zg3lyq%V3Zs6!yFoLA`*OQwqJnr6|1UMHnq9;N?=d3nnQ^wl^wYPzHC}Emer=@iMp@
zwg}+{!g4!C=achNX~!LtVK-DOF28%lY>%~e?~(+c$=FzDfxD<sE=mFti;{rEq9h=(
zC`mlNC~*jDr@?j!8vOKS;R<fb1P(ua`O^xBQHcDj8<_AU&{IfJkrt*q6((PgzIl>c
zO;IA&qpTTbnodk&FlZfLpF}xdpLnPYeWpRAugn1Y1cCtjltZ=z=@=shS62ajIz*I+
zuoemO$61)QlACj0B-W>jm6{zzw^+G(V@(u?RVK6L51Y)I7sTK{R+-H7WuBIhKk>s#
zG&$DIp(8oe9FamlVlZ-+SzQNa=<2kHX$ARHN-UqNt5R47y`d;KYkET{q_jMO8&5o~
z8H+DkV8>_7>J++-W1caqi$DiilL8&+WWK^%^S69q5=}|*4zx0grc==dT2NZ=bn}NU
ziopr1H6x^WgBaYg+U!GG_f+pA|Lz11TBFAe(z>UKG)!!y9er=&?qI=~AC+0YFo6%R
zg-%MOIg?^74TKHzVTdZJT$+Rv)=_wgls#)%EN)+CDoEdxpifH(1?gK7^n6!<p7n6I
z&CAkooh29VQRrgL8~lmL^T&?WS_;gm)@<>q>P956?l4^@g)V|F7FANPc0O6cuth*I
zA{$I9B^yjCzu&-jDnh2H#~|BMH&xbkY^1v78_l|_H=0U(ztOBaaB-u$6ob$C)+}zM
z5!UV`5qB&GfBgDcNLFl<mY7t^HbJ(f1(1y;{7;sU@91r+G@QGLNS|6lVs&^9=%XG&
z_y?DoRMtJGI~p67LXL%?(Z>^kSDqvO{WhC5D>j=o-`foI9TC|Wl|Ua7;h-238Ir4G
z3vr#f#gx5vi&^*b7CL+KRxoNOMqtU~K<}Idy`@`WP>YqVZx+u7^!tG(8_5Fzn`|Us
z@S1F-m?up(^1s?fj<)T$3$Nlsde&@u6??pS!mD`Mn>LU53yKO0oTgWiUnJAlcooMi
zRRM+vo)k{SQQ8u3hjg2TFgX>yLwKp&>+iIiH=1^mO=s_r*}|vjiSNEhK82-JZiwg6
zE5ety!Efl#Pun1pzF_d>R*C|kK#`k+KJ^XYPECtY!JmckqE1*-3$b=lB$<bVdYN0Y
zgJib2RQ<z?5QYbLK!0mJ$$uD5sDbV*6IazhR%E8FaB6v}`{t-|B~#N<ulg>-uuyEb
zolZxGNO@pTDDK-%Hy{H{0n(wLh3k$T#1(f!e+;T2U&-PCgk#1oC<hG1@B~I0b%j7X
zxk<X+szUM1E+~dgp*ZLz7z*1Yo>BU>uMyhKKeV3(mvBzLL=PzF?+-7*z3`f%`Fc)c
znp95b^w;H8`!d`Xv?5fDEEs~zpQnT9&aZ$w=o2$9dOHjc5?qr#C#3o|vj)BDCLhzP
zz~g3%^t5I#wKUFSJE?Jc?V&EQD6`g12hmPgwh<5PfqUa8y2h2*Y^AP}Lf4ci`ge0w
za)Kiv#a1$HVre<gpd5Nl>7)mhaeE=wW~-7<5C50-+uE+`@U~&1O<K%E(!T@Vz7Mhk
zTg((=vNa~{R9-Yr*bTw-H6h9vj-B?9TG{(aErBRUDD^z<hZk|#0kHXa$VVJ>0D9wn
zCD3B`+5<3@vDLfJzY6y-m=(7Bw%6c-59|-)BcnCm_Xb2p@8x0;rD^%g!lzG~Tv#w^
zTFKO26UUWIo9doY<=Gd8Rd3ME+PkXGhi}l~_}(!5{tZZNzlZ8xx7HuR@HdAbJs^(|
zJVU~8-XX}&Tte3!o^|vIAkShBE#yCK_>Iv`{3n2}>^#2wXGkFZ4B|gm_|L^ayl@Co
zas$YGczpR!Z~l|Xf0po{Mf_(T|Cz&oayifb{O3;ob36S^TNYH}n&{?}ZwmhuiYG4&
zAAS?M4dWs`CdA1VqC6(V$Q2^w3ii34&xk;-hjY&roO1=&T){C{aLW~(a;FuCbK0ct
zPjA8<bA*01TwS5xISvW^_{$)v-v$m{<Vp_XKMT3`HvSVxw_~14(IQ+Wegz^Gw(+D;
zIGaO4;n5rt3RiN7E9{{`@#^p4JS+{vU2nk)5ZqiC1955|DBwuk{5B+me{($XHgx|V
D9+CFZ

literal 182532
zcmeFaeUxO$RUbIg%=Apx=o1h^l98XPndz)iRaR!!cd4uKjHGGJjAk@UH)z<RNxjT`
zRr#{>OZhUpsx&mVWsoJ4YkWirI9_9$FY~?2*8;Y8@frcfu;8_9pFM~D;8+KP(OJYE
z$sGT&yT|*xHzHm{ypMb@yK2NpdUK?%s`v4G5jSq!xN+}|d;i+~pSbs)SKLGYO<x-f
z+kXGJ?6z9{LCXtHrw_IU%}LMek59knbm_03-Z?EzFOJ-!U@#dqz0>JEc%s?%yRDJe
zKfQ^Yuc7D1em5vffQ!vRf9(2wZxkZ5?{8mdKXCJOy5Nq-Bfl{j<4c5muipxQGJT-g
zb%OvG3Gu$B*X^E8UpICS>m#o>xb3a@{o!PM>P_$OyFGpi&72JN9}Ty8Yvdg;)<VBg
z_qrZ;VS16U>P>VFALrlwe#<*Pefpm1f_LmSachFEKK+X6tNCuv8@nxc>~iZK^jiMd
zZFIfUk4_&Lo;2I;sD~TV`{={?ap~cQ7fyre#h~khbnU?r-CW?m>f@84ciO%XOz%TC
zxLvQZ`r=L|(+6;iq1p@6`?{dm=`&w(d3r&Sy1LpP^t{#4;Lsbbw!GV`!2lmxIdX%s
zw=(wJ-s<59^sCn@wY9Q8Jn1)1rx%7U24;NPzPJ5~_Pvuv`ynxgY6RM^1=-uLzj@mJ
zN|3t!h9oMt--z39!vEhwBW6&u{Z^ZXudr$O$^;s=FMYKAb$3qNk0@%jOZe+i5T^Zh
zpvP#^F1HujtIsSx+pe^$?ONE4i_-@JuQ~Py{TNe~+83wykNq)*NpWoZ{^{4;@Pe`5
zKXiyX&TxdG<ky2!Vnn=h-wp4Wczni_-+9XX&$O$xpCyX6E6=u9pPe*Zi;yP8Cg{R@
z(S_PXcHv1m67R7`qSSsyU6{W4M%#0EbR8aD$2%T+Bj4*|#&L76&wRvgr#oLe*Ht^e
zRkriu^dgwZJsi2iwn5Ps{s1E5M%xb@{BKO{^=^aH+RlmRj&Q*p^VRFbqt5$@N1Yqs
zQRiSZ=<%I*Klj9Yo#vq1#W*?*&uzAyu0I}oBPVcs!>$*UohSSJWX~P>W54G)UjMc~
z8uV!@J40`Phn%*1+r!&l-|2a7Fd5MhTVMx+k<;>;E@oue0bNHPHQ056vD<ICqZW8!
zFdm>CPHF$z#BaGEvNPyA&kXwhc))ni;QM{gd9P@l-*?_U84ZS>+jp+xn>S1C@pu^Q
zuC5LzjjrExi7SJ0XVffv_#Zv$;>YU98x8`3JXvky(_L@%spsFhy|%Nxv9#n+D~X8j
z{zeBA)^+dz{vMGO>9(BPZg=7Z{LtZG&@$=Zc12I9-=+P>O)`e>8%^vroAH+QAe~8|
zl!qr@|Lop+^^y1Ot#7O^EtQ$sO6}{@-}}-U=u>-!e9)XB5Cs>pbbwE2wiyy+<F2?v
z&DXnp+ivKKW<%3O&h!F0fT?gg{VQi>%~KLzClFtoN-Qw3u#jAzzUREycII$=D3pqC
zOyO=t;?(;#5x+Yh5!)Y|t|{uxF>7WK?3I{Nc3UjY^JcCg19K3RY#u7&yzu9*yyqT>
z%j-w}_(R^POY-9gGI{Kd#$L<mX<-J5GV(~daK<AyXgd&RwMunk+40A;*f{;c*cmi#
z`-2I@`T%bR^mpKmZhND^DS5|DZ#ZUA^xSB0;JkOzI`R*foTK&$1QsM~&p&LFJa=%@
z??aqp-7P!s8607G7%e-E6Z+hy5_XVvUH?O9Aukw4GezSLx`QJuFnwp_^XI8sUH2Ab
zVQD}1aQK*($cY1|6xv`FE!nE9Ro2$mY8&NY>i~i{Y`*KTs6BGgFCqi4299bFE|It%
zG_eX`U3skA<-d=h342)7`a~~Y2>f7-)dtOO_=E1?kpJX0YvlR?`i*Cs-l&gf8iR>g
zGNGIVBz%a1L+HU{zbPPEe$Vd*(9f~N`GXdd#2=sVvWCyA)dB>ElIjO-z=Pa!S;5dW
zT>2u`Ho7##n%4Ab38l}ButGv>AM|&fI^At!T(FjV2M1W4@pY`4lm4y#;Hb}x0<hs|
z(xP=3lz=idL33Hp$65{+Z0m*}wXrs1<qLc$&h?jYjr!9sEB22Fk{>sPT3gG^H>b}M
zB{pY0VoR%^H9wNR{6KPU&6J$!6EKvX+iJPtj?r@S!hO&;i}|_h%pCcP(+9oYu<ZtZ
zVCpXWFX5b4eDsoj!)C<a$j6AJyL=MMW}KO(uXIW?>8NK=s#YO4VyXA-CjYPbntWER
zBdMz~t-}%)*;+@4skDw6J6Gp@tSX2-5U+cz17Lj_i))HovLCeR_xXJEQ@ib5B|rXe
zdJpnLYf6tpjyz`X5wUN)?VX5yVGAwAB93)Z_k@;6nn53&xP4d_PQ>;M79F}VXmogu
zWDVws_Lm2+A+;R20p`spEzwvrO-TF+9UZ8&Jw1Rv7B1Gj)g_eyi$9iC=w*XubAm-y
zEcD%h*kY<iS-V}?lP312P{FY0ZNj_;=srw%BkWDP-4kaLkOtvm<sJ@rS5McSo;&1j
z1+Xz;Deqz7aA0bKDhU<BYqtCT2WbxqCF>imJ$YSh4Iz~aYMu)<EoSe$0xX)J-)U!X
zC7s_Z*csda^ZI=l8G1YmokN!x4}1|?V|e(%yD;^D-vqnE7}|%$lgt@)@IM$@F%;QP
z#GDDa5sX3a`prq#9hIH;liHWSnnIT(4H-64Y60HECZUJP!5{Tu{()T;H?(P(b~41#
zlfZMpkta^zlYz)&OK72(L!?fRu)C4sr{Rr{$TCDzS9e8BUR-i}Wb5Vc@=l1SZP|GO
zrWo&-O;F3`m#@R(1NuQ#AG!ToXrS>e{0>#wZ^A^!8u14we)ATl8u|!<aX?!LbFP_P
zV~bQU^qP2G%MuTLL7!Yq{2mB8_CQh3IfAJQ?e0S#2cba$v1#zfyABlVXUXt}#viyN
zy#s2yJ<R-;KN_#NeYbmp&DbII^GT!Z4_0ZL2%@gCwRGqndgb=G*EJ14n|H@K_S)Kc
zZG@lOzpnPJFd&CKrj`ctl07fp7{N)`LDkZKRnCjB39L%~5O4~Hez`Mr787Y5?IDBp
z6&G38Y&KfT%|=ki-l4WKcQKQ~?MxyYPGk0<kV}<YAzL|9$Ze_U=r^XOx)EUZx8OE|
zs5Nvkm%KjYtgxSD2^oJ@x`1eEUBi+Ss#rPH!bcv1`G6D%vbMtx(Bn_I>LOenY<y5-
zm-lgdSf9x~tV&D#D@r;%C114^#UIDT8_GsTYl!K7fch3TU-pUp6^9-iolvK+WRbbV
zfftYjwonqWAVRZ(79|`VyN(A@3<VIX)^IX{kpv1Q{{^|vOUJTub2MQngXoW}WV|NB
zjDwqam2bke0G*L<;Ip)hU|sF{Fyoxif+5>+<ilX)-G)<y-x5wH*nmjk!}5w%!t0ft
z=RM(i6l*s2mEFM!);+9CaDDa<#k&m;<}9C@4KtGP$&l_!{qmr2K=0^*K5){^Y+k%|
zP+#34-W>VpIF{0uA2i{v@mkAHz0~*6j?hZKR2S+fJQXi|q8PN7=b%NT`F>=w8Y;o-
zqQk4iLi~m;0GbiZZ1v!AB>+@&NIjUoB4VcRsJr>aatNF#S^k`ulodZRtO~aw{HLSa
zeiOn$OkUgovy(efPC4NzrLCLa=a~TuZe(g;ujut)j<y^nLQxlUnC74~=F|KMCf!ik
zZ~3tGveOGvO6$$S0xXqtDH(VdC^o0s`YV06a_$?-wY-6;OjcrSVxPpOLVSxqP7;#4
zEFUB%gnF37A+=ffcE$EH{4f?W@;IZ@yfK#IhMf?Gq=qc!P?CVX#t_@&{lGS!gf4ar
z{%yZC!869z90Y`}O&gBxU~r4X-C#u9ez;<#0iQbA7{Gzd=6v$q$_)c{F?|;Kcqv>!
z(F1&zqDX|8f|M#4;LDW(Y>D;aToQ{m`tMQ_%MdIV5l7WxL%$slGyNO&`ul0yPW(#K
ztT#cB1&JJ*Q@5dXK_4WqUe~`xODvd{Hql>SuP-?K-$I?uR^VQqgyafr5Bl&g0WpB7
z3zvZ&8k@*TXP6Y2<LfNE&ES?dJ%+$8HkuHqF;jPyoS*T8O}_62`LbhgC~|1^nI|Ug
zTIaj?1#JwRZr?41WVf!jFW61`0r7>42-_MXROQgL!mr=WU?`&8-OG04{!uo)IzNJE
zK(6;FK9e0v>8RdrsI7#G6eAs*7&Zio(f*z1#a)K(@YtCdR?+($kZj`r^K9a?x8f;9
z`TsG;3q;}Y1wmnZNT!#xXjs86foI+dX5NZ1^G@AJ#9HTL#09mE5;7dRMsvv8ApLK6
z=tii<tgUTYtEjLoZf;@~g%U$XL?JFh8zN1AZT-Ps5C%cS5%`c%TWiaeN=2wM*h)cS
z37a}rS9+_uzHzGuJ0Z3gD;&yzy~leI7T{dN?(4Qo{&=j`lfyQihVa7w27Smk7%h9S
zfWsRN^BJIo#gPLF1lV%;Je=-$P{sggL!pdJBcmn2{9_U9MzMJVQf%P+9!wCgMW%PC
zIAjZDb0C{0U39ibk#yMqA}|9U5p)zyXb#}w=U%w|6L`zfS+a?un@58Yz*xq@qbGiW
z0TLTD5g<p;anv0*L#r)hC*`+D0<%<y;nzXHt}__=ecAIP65ZIPihu`hAxQGR=6KM+
zFl>z5p|Vm8^OyE8+hXc}r<tESvX$h|GfH47X)$SZ{uWR|8}I)q)oBVX!d|}XoD3#f
z9|5Nm%Y%LE_4m;<4K)>djI<S7Jt=GTgx6D=DQZJO?lQ!=82gv;(SV|$urI<^fklDq
zAjG{p2nP5;jxRDSOdu8qeKz25L=s$laJ%*3`odI(JA#cKJ(4g1t5Eb3qKP?zSlJ$Q
z`0fn-MLLaVJYkQ<XF<oj8qWJj!}$!qU}!kcoj387<}<yV6FIW;|9`oKogXzh<l$Tc
zua@SVPurBd4{opwN-Evw8x%u}rnY0ckGO6xw2>8*b)OI@HYy)^8L=)b9xs>X*hBV~
z>>*<^UsvNL$ZU_xxhg>Kg94=Cr;oTR!mPalg9Vwj*~%VX49(iw&i+W$Xq;jQcTF{#
ztnJEF-OgccUwNJa^2kzzh(QmY)&V?!2wT_{K2j2x9M&nk{AyOs`IbFY@4!&yUp44F
z#QW8tZOd0J)$%z=hZ~`4S*vY_BA)h}WA6}lVVHxUKFRP4w%O2P!Dbh1QLz(+dX%8$
zsLilkRiFa#j#xU7ZDSH{b`f-mWeYS5;9rHxMy4Gyvk4W8l~b}rQNSz~FX{31#pj`7
zbzz$yI~$dUmAa|yagROwuGRNFui7urs3qaj0-JdWFY~@!Ig*#i)P*Gu4gzvsi!%XR
z>kLk+tqMjlT0~}jvYUtcTtVA03>D{0TYEY@IoEU`CF+|Kro&5lR_k8-tk%8fcUJ51
zzb6hlb&QGqQugFNyC?UZUr(O@WM)rFu>*A%r>};rB_CkDft~Ly(*U#(1j8~yt6QZd
zC3Ve9HV^&HjMZ=YAi_5eCy3g>5lkHS!;ZJVb~?Ry-0SWJLqv|@GQ<E!?vo?B^PR+$
z!Wh>03{=Grhl1C3l!S-+=!~Uh8L&?OO<xzDrL4;%ie&Sl<9dMS<9eOH8h#>1rwB_V
z5%OM~Gd0Nf!e4#xo_nsqVt;kvN-#d5U33%2uv%ByT3M#e?!gErF`aQ^(1O$?^W-jV
z{8t7CD|G(Sd6Aza(<c0!h@f%1D_9s05%k{kTR4&R4!(b9VFus~48-`P0??qNImX*#
z95+;7AJLf!_3o8b?i@PFXHDT~fb<^iEmjvDJ{7yS81{6Lx_$*~lPigE1)b)%_ZH*$
z{4{kQZ(O~yihm?I=x?xU9k^cfdeEI5Mz1xYOGK|7;oVW4POsLJUP*#(4Pq$IjRq7<
z83m{Fy3uRHX0Y0eUQ_{^`Z|6aF_q9?Nv12zAENUhm`R1&&e~2*zf7cRT`gUP)uy=u
zyVc6j_Yhx(LyE!WW#=*-WLc?JR;p{4m++Dt1MyPAE73=;<JjGJ<@%&Mgxk+4ebc*Q
zAc+55fmZ4Eqp#{O$L?%zMK2+S0al+r4Wre>Yt`tLO1V;rUDFrvo1|6(+17B^;HWQU
zvc+jst`OH))HNQONw@VcBf1$h5woOH-rBia!fkvR5$;@P>gJab;o{RWpNIpANQuBA
zyvnOE{X&|DRND$wq)<gjlM=dAp^C5)gsEb!fVDyux%yITa0x4Fp^C_f*}9sp`6lSO
zg(|{y<1Nn&!WF7W$X;^^xP)nWMpeW%7yS&GT9oM}>gXy>FCe=B*>k2B$uLl-b3Uh@
z>9d+%5XZxi$BJ)uz7K$%@5eu6JNhX?uXTQW)<-O~i#@m=MAj?u$yG)b7NT0`M{S^}
zb*S?Z+*khN7cSn1<2pJ1Q#Op)qhyhAoNrm+?LCf4<=N0Xbet`^>jyG}tepqQ`gwqC
zoCnC}SwW;BDMEO%6CtOFWf)SAkU_|CU;@GgY4vds3WEa)dYs}068UzxsyduZMA%^P
z`}UUODA7faUaR6CHDG5&yH>3zG>qIC(Et{rVF=HT7WNcld3LlK^;8WitGA9m{46L+
zkC43xKg56dO_7>z(0%&`sD>L`JL<Zl-T(oTq0pDu4YdO+ghIM_DujYE%oaj{=j4~X
zP_T8O-?p_2+r3rl{0eSQ7g!I%VG_R|QG^V?+QlA@!Xc<5@K0@hDC$f57l4c^U8(vI
ze|lAXIz=JUK_=0-YTF0*5UW`Y#Lgn!Wz7BdLqrG8e_@kg`VhPBq)M32#U~$*eM7tW
zB5i&{I&L&^=>4_}_x`vGH}=^X&gF<_F{)d}JdK^72AM)-^Dn;zPDbHgB%h&hq^&lC
z0PeF(H|nj5>o(w9+(oL(6;6CxqEkpq?AfEVvxg(f{;`6Dl7rE%GdgUzrRv(wva^Z*
zSMh%=joVA_Sh$k{HfXh?Si8=pC!TmB@(O?N0GV}H0_0EIMM(7Um^_F>WbTEp2N!B|
z!Te0yXmd6C5!GPvDF<<yG54f_)pUm(LH#1Wn9vAuiCnb1h?RkhwMk8rFQLILT*vvT
z@t{Z7%};f`19pTW<>#T_Ux7;%J*kMEL>;4kYj05wh;W3;4_v*$A=cGhgvzKBuN*3*
zLWB6Yn1jTj$ZCq?cjQRK(N&dqlylp09!(KUBc47$QWzwDfYOTS8;S-BLvB<sHb-33
z9eKtUXY>#-#Bo67E32w)=x@YfYxp0PgSP?C{;fsl>LdL|Fnot?u5VipA-w3e*R7;J
zYtX1J9z{|QdS2RZ@kgEfq7*D9?n4P@yd<M0qMJgJ8*th)oeYQjSL2>pCPWHiEu(?B
ze>EJDD1DL}xt0Nm`&W5P$2i#6)tLA#(dnruhyzpJF+0BXSS0wX(;g?<2!_$06qJ!8
z#Jr#eB?m)b2naLZlSIdSPZD{ePb$(-%QJoJNh3WP9BEd>A5m5m_pe^7RwGV%q^*o{
zVzoXSt?EcL96z1l_=S(q?;(QGJp|E}`jZhB(10B9rVrct3cYSm9*V<YR5d)6a+REG
zrWHI9LQfbAg2t`3xt$9_&kzfO2DDPHMcrPBt<W>Vf}oM6{hRIxeoLMLu|cTNAn4xV
zkAxwmZeFWVn1Vs;v=N;F#v@8#@AMBLXc3ix_|`704S@}fKv08OsDa7DSXIMVEi=E(
z8b*fDZBqnf2x?MwbA4l5Q;=qKax>!N$QWWAx5>wy*^Kx&GK3h%ssRD8dB#yUEqNTN
zjn~%51Ce7KXMpiI64(=z+xiH3#<3U&@1S#~t&?RZ=tHZ@8q!+wkk-_YR>~U`XfcbH
z3=tnvhM*zc+}ezW)<hYLA#_g_S1<&1uu{&P+zb&PQHGE+(~u8yj;O{>9#Q(hwY8kG
zb_N)aD1qG=oFG;ir;lMvg)Q*Fy*<dBoomTMxu%D*V(@h0%wmZ6P%;D$WyPRjIzoIT
z89|KXde-#jMra}_W?%@S4P>n0OPO;d*F$Y4c_eZF>NV!q9CLF97>^`@8LK7|3wu;b
z!Jhar@wT2kj_Z0HS$52tk_-_aM~0wrTwB}78c2qS4<ti~f!xTN)eI3INQRIDNx^Tj
zBXbVqM#ezm{?%(+Ifd*DFdj$(yWSp*4<~&{*AbMU)}farS~rr%aYK(|C2J}$M0^|>
zg2u6mB;1;Ui4&3`;^W8=IVU7T#K(~#&O9MEGsY43uU^}xV7D9-at0WWBY{09GJ|6j
z`p{-4d=ybs3$ecuo0pr(<GHEFvzoP3GDLhl8G^@ihdFlE)MkkIcrt{XmxgpqWC@0d
zk0(RO@w|H_b}M5%asTSIok$E~ni4w$jK`C}-bwZlq|BVOR)Zs$m?-UgrrNWWJeFH}
zEZ3s(l~J9AA>w1n5HyzSTU%KIk|E+_$q-^Jx3V~jA>w1n5OORHh&g5KcE(uZKE{$(
zk{ok$1{jYefn7&tAXHvBA!}UVtPYWG=mZDJkQpvOIAL!{xe!Pzf~Ly_W3rW^?c{;p
z)&pHJ=#w~I7$QE<3_%0Ewq>kh=?L+0W&|<LwJdJqM#RUNA>=q4E5V%Oypu7`xPSE;
z3~`YaFKyP&fa8%SI3<P2nu!A`sC5(pkBQ%%<dNLbBe|9(_!uHSk_^EkxwDZqlnfCc
zN`??axt+yN3=tnnhB)(-t!CMU=z*)(4hC-Y42UJ)*rdspp;>@Dnhf~vW6V{Yl|+gV
zN|k$pd}xt_C$aIYrWl0~Eg&taRm+%?II{#ud`JZdjcFCZ4Ox64P~xL1P~@=Y1Bs8T
z01*Rgnn&iGqgCC><edvWfPsZ+J~ETirs*t1F|vgC1OO=o1dXk%sbb6f_`s%_i3~f@
zTGk|~rWuN~rD$tCb_T-YVUS6nBn+%!E85AL@&Y7bU`=b0v7J%_i=UBDcol+CxXR#_
zv;9}{BwyhwD_muU%~^ZiwDc=nW$b1wTxApvXP>9E#J}VntO8jo5o<(+t4zfNus@KL
z?fAOMs+rJ-3RjuA>5VHv$-5Op1u}KPWZjk^wA@p6aIF9pt}=uaiEs+us%U<VX~?Y4
z65|%GvcXZ|Dl1%N(w|L&Ct-ic;RrLlTNR4lC|qSEeuxmsi)G;|D_mtV(5Y~halBXI
zDpUFj3)mUnEf%nat4u_VlZ-7~Wg<$J71_d7Hp@d^xXKDwnTpq(rQgo-Y_a?;TxAKd
zx9qjkJMGXaVVH)t3s+g;Dnsokk#Lc=iq-jDW%j|uhwh~$4Nr|;{|e5;89gy5jwW{g
zG0vkU=Vs{qDsI^)5oKnE2WKOvoki^YCIHnL#QUQd(W7%#T83%u3OUQ&0F`9RB6mbk
z=7V$P>vZ&ML=~_r$6K2Ro0ZynZL6_SQR%bp>Q$SPUl(nweZo;v^54ZMsSkH{em_P_
zeX3IoQLXbfd?q?dskHp`ELuiRN22JaO7U%-=<IwZ1krqg%p0$y{w5sd?0go_r=PU!
zd_EcOzu<BbT&ewr>FdVsVSVKFP_z*hLn&#9&5R5EM%_bNN_f*xqbE5p*e5wJ#7}aT
z+Lu1s{<=G-?MJ5fU3&Q8h0~y2!e5WJF9hwkqY~+>tS`G0dGa%yGoXb&`>BaKUB*#6
zPI|s#Cp}-G(k5K+hH{?cm?Kp-M_OA|`E*6SmoHg*EHS&vW1c55JIX$!)V@;bfM+~m
z^M6b7gDOdAv%krrL_j25f9k{ALg;{iZpchVp@?fQzH4yQ?+)D7oe!wr_@pDvZRg4=
zQVFAk3<?yk9{7hSM<1+;Oy+eYTlY~{+zZOX*1^>eh_2i-{fd@^124(Sf<`jm>9t+;
zk==9n+{NhwGV8MOjn0RtpATTBU7x;QeJ$)#q%6g^<Jss;FHP?|M&pr4S@p%93LtIg
z+vpp$&T+!)<|s@r0H`%+o=z7I5q2HaYn2*hYv!vxI)vW7Fns`j(V^qh&c^^ZeF%Sg
z#}p#yk550!caPjr|MX-08UhRtJtXwGoO5K*3mlK~C`Iq-bmQP)yS3?VY*p9XW@T%;
zRz2{xHd`BO&5gC{My2K@4lbvWzD*tGG}2Ff2eDMGGomXAvdQc}aUt@Yi&sQ)=tM63
z5jwMbIKbgNDyujiv|OAZ@s69`sOh7u5mNdS;rI~l00lB}+N+1SO0F4mM5Se@%8^Qb
zkN2oFlZT49RI-x!c!J2w2F|iG8*qB;K9`Tgsa{H}uS(0Ko&#P&O&T-@Ir%9sKPpgB
za%FEAgoWz9I2vmUjvtnTl}~WckbNXka9o_e*6UADTOKpNRqvu6jxqDv7iij*+83u6
z=}w&rCd6)Q+4I7KDEDw342_CZJ`DLN{4;Wz6Qo*3oldR`h7vxg)rmvOvSyd8x3P>E
zyFOPjrGwY3#EbDla4iovm0s30ueh=h70?0-pYW!35l_+EA=d=RKutxmsQi#o9Se_9
z(w-ji93Lm=`ePK;TXvq%B|t^v#e1ke*1rXY#ik-WqKJ~rsBa4G2w?a&@tmwgA<B$}
zWf}^aP|3C)mAQ!4<Nc>|^YBMC5C4jMIV$WU(yH@I^xW!G#+$zozS;R@{Hjt$2xiyZ
zJbm#SWi@VaDay+t<WTZr%Rvb&PjHA@HCfJC%qVgO+$uZIK}_*fAel{-Wr<BgDEdR(
zIN%!%0#V%a7uyC~;(SVyEx*M1m>#Wv71DgBhNDKycr)*4J^q+j3}mfzBCD)KEc6>O
zW?V>yB!VbJh*8iIBqaKIK-skWleua4w>0hkXg=B*Z))0U4O?l<;kM;LlK-r(OfOJb
zLm$e`1xV2Y|Cp4S3&8{>5RXr(oHi*+KS!;x=2M~q@WYQCK)^CbOZuY-57(;~<rDFT
ztXwEY0_Awr1zGbE&l_T!&RIzDj%wNz|0~NmPQn_rJ*1uM;vp)Ch&qd;azP=(lPN1h
zINo0rZM7NdLF7^-T`m7)oN9*B1E$$x`X*6c8;f&7Sy8pi(hu=q*tJLB1P%QyH#vO~
zN?jQnl{|Z@*Ima>6lxi%eOx?3ZKdKjY)ZUsE=tf2>ThdGyj8wz6|H()6s<y`D7!^Y
z$v<FiqS+n{Xla1vN=2lWc==~-6gvaxQm8Tx6-RI@>z|~kOoq^F)OBW6d3dNv8Y<l&
zy@#uhq9&B6KI&p+7_nxC8Yv?W8Ze4bm7VJYXfM!7=o?`6K63ns(xD<diJE4tQ3<66
zQwj|}Y7bZiRta>()S%C<1WnejsZhH*%|yCWi_+2zhSVi0G8&de6_ZXBt66rQUv{pc
zxE4*($ND(tKY%$&O|BOTYVz5zvr^M$`qjCZp0xkJGn?tBPhB5+O&_&xQGN{BK8>*!
znW#`Pb9CD~abPe&HCz-d8x4A3KPbK@NRPzQR_@WlZPj@~+TGuqyZawc>VD_vv6k8D
zUum{V_|-R{R)i$LWZ|Prfs$2ex9!${!`!X^9^Lw9Ly473kuu(VI(&0>A35FD$P=TC
zF5+w)(rY23>vNy{31a2G>TULecE8(m_xn`$+Y4KttKY_(y5D-Wo1p}C?!%W11*mfY
ze|H|hKZf>WkTr1$`C2R??-?9HdXAPIxoWhLsSFDStQ;<j`cURV+>aogL2C2K07Bld
ze25)&nrx2jad}>1&&*{9<$5aC3f90d#Ro^clF<?d3o#u%r<`bFnFwy7Xtr3KxDi-+
zuyWl-7GScY@XANa&aFN`Xe$m7Dpeg@0>nDRC8@bV$n-UWY@tSlt3yF3td%nfWzV7S
zkkcT)-uJzF4jHU^ae6@-9>3>QNx<o=SQWtXO{x6EEPw4Cn15am#ZGE~;jZC++90%G
z=eORWDe`e@;_6c$uZMPO{arl+r>|4$6%}2jYGH;kKfD(zgHe0Ep~NZe(!hQ*bgvbZ
zZS`9#*a?ii6>UK@zCuqq{FF$zV9Yi=Woxs~tjofV?I(qawEZ4MHf1E!g`?kcebPhb
zL$*(a<|w&pDB(Ht8GFosVXiSJ4flIA?SEFjY-+gEudUbLOI5J1;au!(7)!YhJ?1eo
z<^}aSH?b5im;BEo?XYV<zbO?_b$P}Uc87l}@}b!h|3@He(dSR-KC6bJ&#{`%>Yl8i
zXjcM`a=Eg08`z2T{12oSF!^K}O0p|Z9ao_=u}%6A#Y+3M6%}q5r^@=W{G$e?o(BP9
zm-o%jpk_HN<ah`sYch_){zL|)z(Wcqi0UpfYOzpd%VXa=g2nq-)VJr+q|E^t&5?<V
z+CrS(#fX=YSRKDoZQ7CFn6Q0Rnqn;`pdC%vU{SxYreyZ?%cQq9PyWF?JjpJS@6!xv
zFbxE+81tANoy_d_!vlvxpoUB?JtvD2Co15^oXe2c_fAIsDS20;-oG#jf1UFD*Sl`R
z>jve{&^v^Wi*mR5knmn`dIuJuM^8Kd1#}2V%zusuQtSK~{Sa=XfAo=8!1ab+JRq~A
zo}nMtr};Z>57hnl#~pxCoAAAO#%Q$chE)^%bs=3=Ko=CLHWm)Lhl4&S=twjZ_w;hn
z`BNgv>Qh7xAgi&b?}0iQS&gmGj2C|F0uj5{qmrJkv*$D$tukt*o|Kjr7Q*ZMi==%~
zzT)BHO*|Cdz@sg%+;fMeuG?!s%{bmAMXk<{26cb`_+|v>&<3!O%cOgr7*KAb0oJTD
zB145A-q*j`ZQFA$KL@W1)iD<ypC0EQzI;<ORTN=I=ZyD>`M6cXR(U+&+NN+*d!^VT
z%WP72$9szpfAh-2y_JVsi`2VT{n(-jcfN5_+Fw*<Mi!SHD#hy2PnrVs^EsiC@U6kg
z;>~5p1;Hpq?A{YtBfX`vdw5uSagnp@F77&)(Htrzs?y_L-sLNI&=oYG9t^1s_-&v5
zDbrV+JrE;a;Q^%hLbq^XJUTQ<q(`qT$v|ygY<O5mV3L&!(;|%-bK)3v(G9Lkd0i}P
z32%=M>rJd>@Gdq1gSIev%6-KQd@pj1nq2S7*ShLGDi0HV&%Va*eNcSugYs)?$jTVP
z(vtX^eQjZZre7VB8R>u~*a+`A`^XpII4{PCvP%s^yA~te-R1t>S)TP8^(XPYZgcjF
z=uqN&AH2h#Te!KfAjDKX@Mx&Wm0QBErTs@ka%*Zoilz#3t7|uxmKOTN{ZiTygx4==
zOw2PW@p0?mGHDoaDKucqg>KRE4>)XO>|nxSAE}ZiiPuBzgh*U=o+ZDU%D@e7Bkku!
z^V@d}ydE0Z^oPhxK86FBLIX(WDqoi4#S(%>8It2&Ku78j$PIfau{q~Sy}$Tu*kI8x
zn)>=$*mSylgY;yX9z0mQ30Z(}xuI9O47=*(CBZD=$N78WFBw&bX@oGFlK26G_uk@*
zyUTYLm&zEDI_p|>4!;XZ;*Tx`h}0<;yLd#Bx+H%>#88-C3mrATmGTwjVVyMap*;}g
zN$UD_m~_1T{mWLTE<@n$VsSX^PP`J=sa~NjtbA|{{TH8GCM6OMmJ=xurIKGPS^Hu!
zp_RB;vR<M^wOF#?VuCpild@Q{mYrhB;$29wWX-u`*&D~VWo#U$M$Gy5BJSFb-#22;
zfBt89<M&qDWF~}DcK+V%Q12f!LcJMEgjv2N1+G0ufu03Btown4u<q$ar1|I~xuVxX
zfa(LC37ov%h<5+45v7BIdfRWcJcO?XcKml3;%ziqZGPw7`2Ho(;1XNV$Z|z`jng=x
zpWXs4)OU8q?K;d`O>(s(U*n$BAC`sE-o@6CHd>c?YliLAZ5K*Ru<Vp~c9s@~v>B|T
zX4AMlYCZ=`S})kYEbKAm*3iFv({V02L;o0YB+w@PezWZb3%HN{AH7NML4O){2jifG
z%T%*xue4dIJUTpH-ryh5l^23OPEbJC1>xvX);ag6Rm;xt-eu|q_KGKavWd&?@t%uY
zp!)#IU~7P6&Z7nzjrr_$hi!MSQr=u<yUgAqEDuiilRp8|19rEm-@%46`BUm6WM%4)
zU3@{}n#S_6=l1B^)GYMIJ!Z}Hr0e%eD^+Ze;sdZm4|P3Ywn|Wy_ZBCV`yac6gE5*Z
z0gm}orA1s3dL?vr3W%t~_vH8Kmu7o3=nv{Oe4J@+YnTf}{bm>br_z$rHVZx}_$0a$
zvG~Lm@z0)@i2t>J%Od{i6q!7ah-WAv;@^`3H;;&a$QJPrCW!dX<M__UaDJ!rPW*D`
zwDWHIJ0i`k(>$SQHyV4lqWuTpu8D|t91b8$0R@ue6}C=pX*)Qvgsl*3FO9T~eo9L8
zIfQLqSxcq@B~RZas7DJWQBaB3%Q5kaD!ug@h>=sa76Y}IzAC;f2Fez0AHpo26%3zS
zfBn?|!@}(dcxTmL8A=GZaSGf#!tGVIaJ!f)+-6C(P?#BwyIW!Q|3Obx^9+h+U|RW2
z<9Wm!d^4(^!k{5_AVPtrshtHTOw0x!!&wkWb)^gwmZ=+C-+?U;K}O=)U<u_+VT4b8
zQ7UWHzQ}vJ@ro2=ETs4cvggZwsarDoyQKaWc;RF6Ppc(RISEBKZOJe<FW!LM8^ENA
z=){(T*P-mI;6#{`<>%SgE<efJiL&!N{CA^Up|Kg|D_I*An+>?X2YtjU)oNTzkX-pB
zUuh#kF;KXT|24d(ORhHrOOl<MUyz~Z2mT0N5faC=u+ed}Was=Mxw?eWH;Gu1j;w#j
z&A#eQd1~9XD3>b-cc4e7SbMc)Te$s$6pJqgk=60Al~H9&DdNRMzyvBL!k6(xuovSW
zIj_a|(~Ga9D1skMSv}|3X)u&njQ@TL+&qi%tL?>j;cSbs(Kur<Mnnud!Hh@}c}$N2
z7}--EyG3y{4?y(}5YQgG*-i~;d=Rf3`K@vL^ywPKw|t67RO|dJNhujF@<SZs()l;I
zYRCVb4={xQVWDwb@rGZV-iy>FvFjW)1Y6GNBzDU<%J}*x_^iJJ^UV#es$7$Tdzx^^
z=H&kz65!eP>a(*HOc5<t>-?wijdm4rFoI-u4Bzx2t`<%9I~W(OycZl>L<op2N&@P9
z9#<o@AF98nuNU20TXtlRbw}fO?2f(`!8Y?8sj78e6~6IObX3Q)CWIw+{#20YGf5<}
zX&nuI`j6txM8;<RqcRaOW-4_)8>4$^_E;>wNOr#6J0DQGp3=rbL!V4C5s8V4S9bqA
zBC6C7%lV%=k42!{e!VgAyRB7ezpi`7UUM?`R=3>7y0=l=+}hY^R2!{Ivs&A557sNS
zgYEU|=60iX;BHkbt@Z7L*4p~P!NHcdc2Gf5h3dxk_CaH<Q6BaWPdoR36tJ7T5<fcc
z;}|U+5cfDS1xeY}r)O`+F7^<|R2K&?FLK=9DuL51T9DG_KRwC9|LXynU_pln^!s#h
z-59Lt+pb8)C)>0G)ATVcCF1Zv)p_jL3&P|*Ii9p9$hUGcZ01T!&_lEMTZj_1&NnB#
zX7c3JBm_1g$79&%q3@?tB7J70<>2A*cuJD<9n`J_$Bfx1CCj$uvzGX`Nsv#LZ6pEB
zo<CpB^XJY7XxG8<7p#rvoijg;t*M$bFI>BL&plT-aKj;n+goHZH-ljD>cXWP^>z24
zRmEm$w?A&LG~1XsB^+JpFF7wFf~bMIy|mII{SF(ncAe2-!!1?Uc9xw@{J)C-qX_Eu
z(mNKoUP=Pkpw)_E?K+p9cmj1-tXKGZ6zQ@;+`H>k*N4Ycng#XOC~E{R)aZiwPTOd6
zHTn_NVDYK+5-+03Du#(VozMtziDGSbap)6KM@?#)d<hM1;X2h18}#TpuWxwhu)oWG
z5W0p9=b_(U84rf&Nk#PJ$|?`b)rBjp=*XH8+#rk%5(df-T>YZn=U!P=-JmY9hC`jB
z->uZ&P1JNkqP9lYMZyhHG6PxiqXp~DG>S|qk##>(!3)e9ty+#tR9z!tMzIS>sr=(n
zU|sqk8JMb5*=8P%Yt&#O<&MWyR%1#af+%xteIJ@%p0XiFo`2ZJL0md{AdVC0HW1NN
zT?m0qpviS1!kTB5@>WVwSQ|nUhlCa7*kcHyiCxBCQ6e_-$(`1?fQ*hNF3|^Kwv3EE
zr_}=^-zafMZ8N0=SJ>sWVqk<oEix-G&e>s|$}+jbxPSE-ujRY_j9zk81<f;RShxT=
z^>VGeo>C7q>?T9#5wIYro3(PyV2(LEstcGUcNF)pK8E9ya8zgXG^={TX1SU*pjm~+
z*UB}cR{5Mg%~QCbwt;j>I-nt=$DH9mKDM0UpT@RY-Y_cWCQf{Yh>tBp(Ae4&f6gAy
zs9(*QY^i?r)?7W#Dqg)=-b^W38gg@1@#^)mS+G;}7(Y|0<`pW{%&K`zccmSr>2-xl
zb@#4=LZxEOkwj&oQY9+Wg-XSBEee&&>+-T&s8qb=OxK4Bm1=OrwSh>9{6eZ!ww>`4
z2?oP6q*VWS0-R~;v+R!-*)Y}~_qs{u$M0sS=o#M5O<Y!{wmEX5Z@87lPOEu0>D2YB
zHtGJmgudo5(f)M8YpEp4FwqJcozX=5U1(5V6YWRkvoDQ_HoYTc;+9^RT2d3{cbL3E
zIZQ%}FHYRumA#j&%`@!1JJrq2jq|eiCV*wxd(|sx`+_8UuYBiR?7af(Wn}N=2F2~Y
z{qRugnNQKKRkKgdzI0m(?%zvcrHuk>lg1auN^5-|mMpD8B%8HpWz_~tanzW$FhYSh
zRTF_skQp}GT1tHz8$c6A+3`XPZPhTHD7#0BeKy)%jhftDG9~HmhNq}AdYomUT{p~*
zi6qN1(AErt;G8|qvzxHaQfKrv%TBwowY+IIH?hB2mfGt2@>V6G&uCkUb*orFW?Hv+
z9=x2aTil>x0ikrYq4O%2o6nMH!ha*3ki`N*S|U}u<P}JZ`eFgOYD(l{0XaeR!YYR^
zTwREi<M}geM4~Z+XV}aCUkPxj8`YG({GW@Usy|_<^V-W-YPFrU^_{!f%j;L|z5K-o
zQb`x9hh~IZT}XH>l|*TKd5cErTj1H@RubetfY5pO@}HK^o_R0-2T4G)!>!&b!>wY`
zihOP^?>7AWLKW9*-hsQZv0e3=2uNJp+(uca&GpU3#^%9VvsT^M^jfv1+iY#t+{(_*
zn%8Qe<kQ-Et8uWoQ)|@L<DrUAfi=wBeS7#@Q2OkligK`bnfqqXsvLobvf5XUC+#`&
z{siXFVgI_3@Y>zZ89{+F&Y4XbnVcbtYw}rp&V1r4Ux9<R_|FPV&ljthIC;{0lw}B;
z{bq$`YD%1a`kT}Hpq>S%Prs5r{<|Wg`M2o@*ThH<$9@f7<0$`N#hr`?@zC?%B9PUm
zK1Yj$I4fZsM~DO}$JqQMX3XXCtM0j{<sHaKtWljZ=GS{jtM2y)J>Tt?`bY%kwUDS`
z<n|A}Wv4G=ww89;Pr?7lQWJcL50AA5y)rOepwvhGL!?Ti_%WF)PaO4=S=$7-ypIpn
zjfcb|t2h^kb6q8QLp&;qu^`hVm$)dK&BfV)Asx@#BWMMO6K0eHBWyai=YX=zF%o~k
zJ@$jWiolm$#Qpu7;#o?2PU#gVT)``>MOHc(OFB>wkr<tyKqA75pblN7{}kZcfmjic
zbQw8JJ^MlQ2$|00dB`IwFD3_ovKvYo?EA<dL$9m<2%TP$<PaDo35D;;?o-?1FLqH%
z5z)+)6hjR0KEvS?{Ed+}o{ajc0~mfWEcnHu@4*=P?7&8d4nj8H`q1~#ixLW{jmFCk
zuyG;}A$O8im-v{XDo}vKh~jZBRK^w0INu)Spr_oR;+!N-Cvr+SPSyt~ZX7T@WIPOR
zq4S)-Bur~|6^B#l<4evXkvmuRs6B!XvbFRjk(X{iL==NG#H~7VwBWXWwu}q)o=n+d
zQAs^+(c)GeGos$-_UUPaSm8RrWnQ{n0mJW8XZHDN2fa8(Iz7st#UweVd@o{@jP{|-
zm+{V(8Lu$Wh)c!CHS1j>-bIK4r^v^lQRL;r!BNCWQVwQ)mXw|VcX%Q9Aw@#qVEXxE
zWL>3f&h!LVnDa3;Th5~>s3&V74#5~Br&K9#EKv~wLN8U9tC}H2=j;7CYAjBIy6DpJ
z+cBXjk0Y~>v*O@_K@0JYpoKk|lF=eqDM&Q0xQo`{LJ(1zo0F1&MiNf@3JpW-;w{}D
zOekZ9aQ|<aLX>ASe^$;pe&o?xnnD6VmMW|d2PnwX=z>3qvh~nxiR8Ea7Eb)4uPT)#
zB-dD^()N~ixp({>j5?AlB015)2@hPDJG2yFj08i3FVY27k|#X6EMdYA5q}a3sB(%l
zYIH%SWNjcbE2U>e?o5<Q?4ybNJQz*_dB-BjI}R(;nPqjNS#=e$=`y>iU{U&1*uYp@
z^ptkPWVWznpWG~~_Lk)`BxT*DnfOu;$wSr(f)jdDJB&P^C)||YfRZ7HEv^p^>S0@P
zLyi))Wj_SFxgS1qGi+QWbEoVlBKgJ0g)b9X#|{_ppa#)I)zqQPRAF2AxVPd6##0p5
zY^0mGFPmz%%||V$5_-6Fv&^|k#Z0+`sxwr{nRy`6E;@WJxx)|;2a`V6zZ8wI8JXnZ
zv6g!YO@z=oriyt49DWXoWQoP)BnmG>FHjT4yk>uLK}@k8lF;KY7LI13gj=cGu8$|f
zF1S_9H2H^+!*T{=F{9=RNkkJj*pq)CQ`ZRdCK*M{ZIZS=^??NnsaYiwdGZ5>g29Ql
z@ExNaPzFqmf<EoXpQwt45nX}_m-50hs$UU^e&km5rt|j5vtqgu8hn3LlocJ=6KTNk
zto#Cx0zCspg(}&PJSAHCcBdachtV|PVmg#@&#8tlArU-8%$`_J!bg^!lEOE8nb4J`
zrE<@6`%*`x=F*D+<q;>9h~c#aR)fg{vCNM`EtDN5<w#Nkze3~D{niLpC$YX859#HY
znh|25bH+m}y6f~*NC(BOcshJ@)p##_5S*$yr`{2*lM^Of)bOCWoH1FJ9F<C;*f;cB
z#lE4~H)th8>_iN`yx2FW95hND358IxZ_qo5V&BjYmFQyMfb+M-zCjjX;QdUoZ%EjE
z6#Ir^-w<x9zBu*`whQbBvwT^3)0n^VgPeTi@29w;=E*$8P{Nz?-=x6JlX>d3cIK&v
z&X#$~Xxv@8dZu5CN?^jKK$}FeX0oZFg5(%5!>UwE8Bf{6_&et{j9>BnJdD4ULic%w
zk)gye{zeMiJj3`pdl+AJwqZ0HcbCKX!tWr>5b{$t>fK2l^}R5bsNjO)w<vrR+%7F*
z+m1@T@V=~)@pW~AxLomU6Nb4FiuRyFJKS=p^Ee91cmtVu7l4FJ@S;4AdK}Q@p?@2R
z;o*#&^!iA60h26}HHz$&dyC=?ToA>H7O998>H{61EN|Z}!IMU?+T;lLly3BF<nW~o
z@P^;-b4j7x$l{Gzu$Rc5SjUD1=4Tl6F2f$(Ml~oTB);q-?+m4BzU&<%B^ZMEj_D8d
z8umT<t>>ZZR9>9^2#_0SyaM-0i!RcY@nCX@w4ax6F2G2HT1lZ565pYcd0Yf6G)Uvh
zMBLc__V6xSUBmXl_R2`5aQODa--K1REX=f#&n>|rNJ;PEf5Irzs4Y7qO35K>$K4oB
zVC%#%b4|s)MWpdRsiUeL4EA^uwUqZ3QDniR9L@{WOsfE&X!9grRX_Q*DCif1%C6<d
zuf*QtqIJ*Zso*DGC7)kX@jmlza^1erSWm(4G)IVK43o7U4t3wOSnn@h^F{-&+XYn@
zua7B9D-n3{y8JQe4G-k4*7!q|J&*o+0)DQ=n>QDZ2BTXkpQVOl07Q$<?~4R0hj-un
zdRSwRzdQ2!RKZLMjj;M4RUxeR7VnU}K<2Ebw?}*yt~-TT3uR^@)(WvU*%#7>yr7&w
zlmt}X!ldHWLagNzq%V<JvlZn(KQBdj@t?7x{J9j(b{<8Up@gFRXDM*=D9W$573Ei-
zO;I))rxj%#X;+%Q1z|CizI|nIu%gP>uR!@l&{=TW`3F#vJ(ZDEKTM8q^)Nid;^FD5
zNK-}@KBRd)9-n$`T_w4F4N-QwPJR1HirkyNNjT2xBadr_HoaE8aZ;yc4;837fB8Y=
z+dRehgXtR+AM{)F7`0G5hNPMAQ3ta{-q2F}8FgX$@VliS8g52pk3Uh(Mk#h^n9lV{
zcZi5FwR_9?w9TALXt4-M%#%F#y&y^LkHWyiN94=1d$EE7;Vqxs=_>pE1Q7&>j@KLd
zBOiMY=W+K0K6HeCwFfQLn>pXId$l`vuhw<1wsfy_+TNoZ6z9P$1Q!huPk`>gZQpFW
zL+HcK_-H`aTN7{uhd>;lNZH_s`<XI`<obVKb3C9jv>VG#tx{V<%!WO-yNVotVc)k2
z`<}T7I{>?ECK0w{=Kh@i*_F4gtT^9BK5dm0xf<qyu2vm!OJql`*22We)f&G+w->%`
zcO~V&-Sk`Z#_qQ*e49Gd9t6V`>~6Y)!L1dH#`*_<Y~G`5D+q`UJ`j0HilgZBkT!zv
z>l9XrV9O7Do3pZl6DTrx{L8N2HZOe>cqw}F#)@gbAW8(Ec77F6%XTrtpTZRxPX73-
z@1^i;W7f_U1pUIRVN&68=T2g|a}+ODfvng7E!Ha4jg@M3rMf{IGH^t7rLwWIR$W|R
zQ%IfdYIqRAj$~YeDI_$z8FsfvjfW9KGWLdh<q8aODq<3=3P&0ND2&P2=a5Mq6D4pd
zR(IhL%TYj)FuV(sRnNnV;ul@D{W7c%T&A8Z6Qn6#UcOAG0Q!?CK|f_p7rulzTq?ei
zSYMth1lD`9m^|K7b;)&kdGYlY1zew{A$Q+^g-eK`IY1I>7Rwwy1sjNe%j=3bRZ;-B
z`igNaw9hO+&_ldakY(!tU9c*33*(mz)mo6Voy&*sIWOK>SRet<QOp$kHt>b5p8epL
z_`0yU09C~G5beWD6@E?|8Teaxw8q!@pE0VuzzV?S-Wg9{4d25X;qS^~pkw*O*F@NY
zKob+8Iq-vh-5l`%ql@S>CYc(~{gND4(G*nFQSDlKB)mnqZv%hgr@pES2gS<NFNtp=
zfa~tQh5ZtLO9lj9aySl^ViCfj6)~NbCdI`;h|&~Y>3c2iGTNZu;mA2^Qp9A(Plh3o
zFq(zm5t+^V0}lFJp*<bF&d-m$L&+_$i6Hj`jBS|6d~N^RW0%AiV`e}(+i598Os{CV
z2<a72X6&x&kN&Xwocw8g!|XP!jV{;54C7M6{*L_-tf81cD3Ay8j+CaVNk+^Mx{EIu
z{dT(+U860LALRa`E%G*6V%thZzY)I%+p7vbMGQ2D5X)LiRNn}ZyR%wEQLc524Raes
z>xR+J81PA5SY<d|SG2=yd&pwh+!de_6Iz0}c?Dy%ik#g;B$t+Khl3IWCR|p`x7120
zQXkwM={rE>P{B?<#9u8@Xv&%hM?P}927b@)q8d~Jf?_Moh_YZI9bBFxuof~Xs}CHv
zo;Uyy)yDiop)C?Fp-2<HaBh>3OvqnOhFD6FF8;f$CD!F#{rkTD)!=z?F=P}N%QX(G
z0hf2h(Guf2B1LhPj=AV(#gcG&SNt??80$NK3vU{iL~t>~+~I#O!T#f8#D>^e9HRik
z7~+EFGjSTf&ri`a;vj&CN>#s$-ry913SMp<;5TugMXYEz;4$(W6M_v&k3K41AQGB%
z4Hv*TZ80<?%r5WBUyPp4CKoAAwUug(6er`QNgorBls=DWnoJoQ*30TC(N#Pf_SK-?
zOcI9cIzOfGmW_`pVloFxvW2vuvoVTvM7i)rgnHt*lP+0DN9=g`!h&$&Y9PA6j}i+*
z?^Cap@O5a3W+gnL0)14L#)~|U;YfZ(l7zmA<&O>t@Z6{KTyXh(2+~0sM)*Pg0INM5
z6fbW<5h{tcwhrKF7@m|6Dy#`8Jdk^fPs)MhW<pmM*X#5t+#J@aJapKL<d0DQh-Wn;
zD44y)Z<J??&}3?6^aJ164?iILEVp1{)epx@1W`lw)oF7FGK$9%&O%CJ?2ESRs@-yq
z^FbvLeTf3*5x_5o0JXNMkA$B%u<FC&pk8!<`CUOIv6G~ETAmCsd|v6rP|e!a@OLy#
zmD0K&K6i6ZjnabHtf0I5mtWj1S027|S(WHJHqJ#E9Cwq|Tippu4>mMk<q>9eH7tT%
z?6HbHR<XxI$raui6?-fW8!7f!v`84rX0gY@{sQ#aSDPbEoMMl~r+q_aQ5t=C0ZVzY
z$0AkBxvaItaCcx_D)v~#9xG85Pu?)G)}Q!%vBxU*STBn`mhDu#mE}~+8(jbVI=j`{
zp)=gBDLGHD2}6ls6E6jBo?w%&vV%=tbGBd;qjBjj#CXA1E0IzQiL3^V4pIhi6zJl$
zYPCl0!E3cG{;^gOKg7jNadAsr++j!JwVh3V1R1{r{sq>VL&SPUx81M<$W8dZ{NT+6
zl_ebBN#P@3-(_3y&ica?lF)D)K9aPYK<S1j3pR0OK~ycal6$~qWw}IzSs4a76m%2e
z8xB%-z*OF1Po%I!vYVTX6N_eh%Um~785Uq9Xu_C}xZ@hq+8_*_(=j3@9px&6lK2Dm
zX9P!6%_Z@O>{&_v4DAU8y%A3Hg`l@BTRw4KvZb-lvgP9`!eAcR!caoCe0K;JO?wvo
zJ3gJwc$63Z`!~<5O;GVRHyh_wn;-!!t2TjpWuDpu@||<3O(3w8)FD^PUvMp2Zcrq(
zG}n;-ixY$|U7-T*?3{%PXg#vCysH|rQ8b-H8A1Hfa;CUM>GH9v<pa~1=##;yROq#}
zN<J`Mjx!mIYDZmL%h^p`@iG|<_pe^t%-Ky{Ofngaib-DE%Gu4$MQ3JqZ`{9nZHH=o
z8WkDRMsq6z4EF)HnGb9`0}S`CUV~H!^1<z7z~TPYYpexnJp49yNj;0hDOGs*-Q<E0
zRR3b_Vf{_BoPoen`NlO8`_t$$!f?1kFM_{lyt$4t86|XKV;e$GHw%JhSzZV|$t(z(
zTX`Y$)UqIGM&*Uj6Uu_1d6XAIPa_M0W=~!SJ$Wn$nlpJJ^pvq6Xr|<a&=bXip!ty(
zLQf70g64z`p=JcJm{q4-lva!~zvj1O<|oFhZDetOR`nCRiHY2wRsSR}M4bDpGzW8X
zKer;z{R|<wKc#d{IE@)1&ixD_xjz>~ockFfC--wJ;@r;=Ik}%9;@r;=lKXRYB+mT|
zA-Ufu@siFLaqee`GjqRYmSpZHu36vC;{L39IAGnZUS?Ipsg&1K%43Io#}K+hN=$I|
zbiw^;HN|a+IQKJz<o@-HMT}b!=YEC|++WQF5$Aq}$jSZOia7T(gy4QwGH0#E3=!vk
zhLGH!QqsvLXPo;PLU2DT;hC+7b3a1}?qADa<y|za%LQksMv5NkWbUUS->779e^xDf
zaDNt|vTE6b`;A^EiV22@bN`x_{h8d)5Sk`x0x?8R?q`TN_cMg#e$uUHjW|QZxt}3&
zaz8`Fxt}2<_h$(chKO@NLrCs7DzK%GNSyl_LUMnWB;Z!Wxt}2f_pci((43l&9;RgO
zr}5gTWpV#H#n8v~{&lVQSF`kfhR}ML;yZ>AdjEPB(=bGw`xzpq>}QBL_cKIJ?q>*1
zR;weD`)LC`i~AWO&i&kqoZQb4aqedb$^BV;#}IMuXNa8K&k%9$XNa8K&k%9$X9&Ul
z8wP95$^Dwf$=pxG-pbVbH<GzOEXa)f?pd^Eh&cB%gy8<oEbeEBIQKJz;QqAgi{Vnu
z5OMBj2+94qS`p`dh7jDpW(cc9k;$#lBcmn|LrCt=Mb0?)Glby&jV#&Et%!3!LkRBA
zR9hG#&ixD_xZkWsmQIT}_cMgx{%xZpb8^2XP%`%urFOQmWdCL|_irlMUoEd?Es_io
z=YEDD?yr_>xgg@)&k%z9ce417TM_4eh7jCe%>@zXeug0Kua&p6_CVZ<IQKJz<o;Z=
z(1WWc5JS+IR<o^e+=@8&Glby&n!$I8tjiE_?q>+W{ifQI4iV>mh9K^*mA4FySaCmo
zrqo6)99T1Jqw+fNa;lBW4JsU1$?g*}$QKSQ@;Mt`KP`KciAF-WaA4Uq(=s}lW+bc&
z2Ug+0qQh}e6xo?a^C*Weg6j{*l^KSR%8apjOVj}vBCgCZ1SvClTM<`g7(ysB`Mi>P
zq9~P$A%rrM4<fG2FoaO$O$epT5KRgP7V#bXI)o~35-O2t3I|p_+|(BitRv!@!hyx^
z5^2WCGN2R=EIomk7IE2MIIxiaVsG(=CKNj=;$|FnR0tzx;lLuRSWeBSaA4)peDsbl
z*@#J+YT>|QcS%m!&mI>|R;BAQgwXq|g#!!ISm^zkfgFVcOUVAhfn~`4Ed7gJNAX>6
z;lR??K8Slwpk&!k_JP8I#qN^AfyKtFFIESZec<dD=|tD+Q|gRYG+At^^DC4X_8;RP
zZ?43#wa(AYMz+u{_WYh#AD;}p)6Q?=Ta$LVy?~6f|7{c_dd#e29ul3_t_+c!59NjZ
zfjko#$P<#+=?vtEaz9s&w>A$png<6P8#~p?Rh20CZeF!1`Mc4!+NXIXCI4NFlE!J_
z-zQpsAN_-RO+<vwcjBi^!Yfbo{Wd-m9i>!Sep<jJ(^98<SDD;ZYWC?uzft#)EfZNf
zPdlFpK{TIWY<`ORi+t_T#&kZ5=UuBw7To8P;q=kMNW0#Uj@5qabfJlKk0QzH>C<np
zk1fCUY{!<>oUk(=>wM)u^}L77>RqH90$a&by0`togi=p(>ie|xr&Lm%kM|<|B&B^*
zFH<IK&Ohe7uiw?_O~dk?TykDyZV^f4kd-V<D9L$Gkt%)UA`Scqx$}IaA*6(t^rf<5
z^DnA4+w<$cNPcTq@}$wHyy&A3;|#1gxT?>cYwns-VFQspd`09j1r3o+ekIJBztW(r
z`N&7kS@T^rO^g@Q((Ut$D&4-T<`s!GDtTaJ!q1oA|1Iyvcp^C^QuuRvL!=qS`1+7`
zsKy{uozHy6Cgs;$6jL`JDXAjChkqg@<s0P7s7Rpa!vFNx0j217#mTzS04W%ezp)8=
zBAq5BOhpP?-#b$0;z4*ZQ%*d0q~}Wsi884`m^mSI!o($U+2}fE4^lJZ)VwFjL-?qm
zh3iO`iz#{Hh!PQ$=oR^?TXf%Zn>frj_ImV(N<te>kT3p@*hBruTtiK><~tIHdai`;
zZ-IzMhQ`A&l4K%n()vz$ZDB!;5fZ67d;6Soalc&ML<aXVRUANIBmSwNN<(=KY26Xy
zPQUHYZ**e~)d~>)wJ!6;?&G~RT*i+w?v(jmx`4OvH}K4d>2|fu(BgS~62DaFAG%7P
z$0N0ybdYcXnXr(}oFy{_^#`S}<;#vt=&&RbjniGq@F+5AQ!a8`0Z)be*wV#A=?=2y
zN`QU;=B^`3nfc4d{7Qd<x=fUI5>GCP<h0Zr`UaJ1L;733!-PXJ=E<nf_b3PY1gVvY
z(EI4b20FFH6aW<|KR(ey{HSei-c(Qb=<(y#aFnR=+zyEbA`E?Rgb$59rUIT9DM~Gh
z)Q6fT`UN~|XRox7!W<I?n@F)$un8r~E!hmWbZSeoT}ZO1u4!qRh9dpF5J0Jl^vC}f
zPK~h@u4A^MK2K^4h7uaadJ5b;X?MQH)?Z(DHvQFToUvxlBgm)!m6QfvcRuOjbu;CQ
zQd?fiPuL99IxhzLq5sSb<fe@HJPgE8f`Ps@1#TV&dXvpSuRj|D8I4P4pm?Geb4&ih
zr|yO2K#95fxJ7()*0sM}rA2#VYq?xoUnWI?)CT@P)CsKY<tnKIwVKiugjPZN1TFLx
z`iBvOVnLTk5vTza(c$4sz*z$<p2TTWdWb&CPga!HA=(kXQNg+^k@;Ev8lYL7p(cs9
zsUcP4JKPyu<B#w^>K#U*e+a2|lQa{#V2@jS)y?vTTKolFsiM;+J_e-;F!-giT*WWA
zO8;){sKtNWqS>jd-h^rZU?O_JxJA`(#{MB{8>8^nty!wTxMk=9`jx0Mpzkmk;91B-
zAKMqA2W_R|u&m+qP@x9S60Vl46tRVap4X+iXRLD2?<Ia(7E-R?#{OcDuc(r(OX`*V
zMUgO_i_<RhGm9v>i!#cnWFrAlwXW%oOZ&Rf$P22p8IVS$=m`^pZHUBRA<H{%4~-v_
zhKKZrtJq3nn?ywBZHVXvb}Gt(U~X>2)&(t*o0sxp*f<oVru<%<0=#4vd|h^0sGKHi
zzpAdhbXmfR*<H+TTh-SSrI_7cw6ojRoBsBB=}kZX*88Z8+;^oYI`imF3?=lYkA`qj
z=RoxDxT<31r2DWlGbf$f-1gSaD<@q7SXNFt^~yXs>Et`-l9NtgsRi$4kduxZlys!$
zrCftwx~y~D9pn6oJ_Db8mSXmyohX`)rAtPmz>3tYb5SsTI5HWGf@D*(&PBoCPM(>L
zjoi(tS?8i)I@Tz;WfXLjdT1vKrcWCrgHiBZYSy_Zm<}*V2BQFj)U0z+Fnt0c8H|o1
zq-LFqg6VkFWH1U&nsI0+3a8H{B*W1Gh4aWdXMGn|QaxYrM>MaZxPO&Sh!{!zP+pkB
zP6ZS_lY9V~4_458tH59lh=ha-HiVvSD&&nJXp)h&I}e1OV-^HWt@I=Sb}RJEvLI+e
z;i!vo+|@kzU_<EnWI>47y|k1+HiVu<7KDskP03_qL+H6<LC}<`q#g;kA@q!~Amo{y
zlo%=-LeCQmLd5Q+r6RB)^xUu@XiAX3Lh}WFlSg$D&+G_Pop?y|TQcu6;{kIP@AKgf
zJ&9BU`K*lO{VbMY2;CM7f|>xvO$ql5$;1$G-ZxI{)C@8uGA={Jd7mL9?`LrxL&SNX
zAq4MdP9KJd^FBjJ-p@tOIPWur;QdT##I1<)K0^rJPs^rbk4T*N8A9-WTHLA)5$An|
zAl|RQSa;XFubCy8_eo+B`Yhh(a~W~o=W`i?_cO<vA>zEx5Q6u&Q_d%bWMT;29W{Lz
zf_ecm<${RwK0`>}Hz=JreYh2I-e(BG`_(MQWr#TMGlb;*tVzreao%SLDfe^HBF_5^
zA?1Eb5)OMr;=Iogg7<5=Xc6aqh7fY!9Mn1Gz8>jh-lrj_EFrUapU;NGd7qEkNV%Uy
z>Fm=wW>URGu49Ne?{g~z?`LuyLuiVq>BA6`_fs;agyYQ+ao%T$oN}Kb;=IoglJ~Q?
zjv?Z_&k%z5D_L47L&SNXA#%!nhKTb%LrA%w#rq5q=Y56{a(|A5TVjy3&ZCDZnfGbD
zNXpFOeLheT=Y2k(BISOT!om=7xz7+n?q@PCL&SNXAq4Mdu09MA=Y58dyq_ia8A20P
zO&^Akyr0Fm3=!vjhLF6UB}y0~&if1@c|U9EV2C*HGel0g&k%9mX9&UjX(>2EQNj>$
z-e(BG`{q7yPPwmXoXq<~Y?_?2c%RRO#Cf03g-E%dHNP1m&if1@c;B4giE^JI;=Iog
zg7-6bnG6x<eTK*>_ZcG2`wWqj_ZdQui<&+Rk(2isBF_5^A$dR7h{SoHAtdkTf{61z
zLkQkC6_)ftjq^T32;Mg#=Hz`%pk&@BO40H-i}yL9Se*CyNQdP8tQD3a;=Iog#QQny
zJPZ-%eTERcpO)+~lrjtv=Y58dyq`7R3=!vjh7i1;IRhCY&if1@c|U8%%@BHM)%0Nq
z!TV{c|7=>sd7mL9?`JI?+=@8wGlby%Ogj%l#Ce|~i1*KA=h3}O=6&iWDJ-*ie=FI>
zxuudUZl<R63n|SIao%SL;{COp5OLmT2*LZCS*ilJBF_5^A$UL2w!si_-e(BG`|G({
z5$An|ki4I@>)=+zd7mK!?`N707(#Q0nm!CcOp%_a(H_(|?=uAPel6#q#(AG1&dmF|
zY011#Z6ql(i}$yad4F5+KJubxjW<KYd7mMK+|Sf`7$VO53?X<wQ{pm2oc9?bC+{;v
zoc9@mcpnQ`E?UHSpCKggXKfj{6>;8Y2*LaL$QkE-h9KV0VK(DdXa-Z$harfs^72KT
z_ZfnC-=027=fTgE1fxYX!psDtEVf=w2}Zd=MKppffK}BrvB*f<4cx+7ekS{fNst!N
z2#7Z_;z6{WO{N(M+#(tw%4u36CsU0?a}kY@8PE{dRyd$RXe*h!R1T|%Yby*Pw3SQ)
zCqu-w6^0O+dZy0A5PBA=MV=v~wvx3=Wr(=8!Vp4R$=szfL|j{82%)W1vUaHq5!Y52
zLTD?QyHtkIbHkzqO^Gw@QnhqX*3?-|wik+6Bn~^S;}#lr8RxW4GK6l6>LWu?6N+dA
zkqA}tewLkx$r<N;Ca2*2A{t>p`9WngV>0iP#4Mr_uog?XpXHS*q7mvsr2#uJE#h*&
zh(@r3IN9qQm;3B>7IMFcMlkZnWm#yLoN>9&<P>thh(;J3Y1K4Y?vsvML?h&v`|Li~
zL{-WgyU&HbU&&%zhKTF?3?X%%ECVM)#Ce|~B=2V_>kJXs_ZdR!`?)$2m-`GM^!*|l
z0ke+X=W)5uUT3NAXN@;QXcbOz9Yct{ZssnNA>w;ohLAc>mOqFg;=IogIeDKU;=Iog
zIeDKU;=IoglJ~Q=3=9$HeTI;{p9><+`wSs?-wY)vq7k}o5bP}~#$~TF@qQ7FaKyBb
zyq{&~DWVb7@e`U+iB^0FTs^asbsn1HMKnUF^JKbHi)aMB*JWD7<$e*3VDEL=aUIur
z*y}9hem?hkT<2kkoH`G;BChi=gwT01d7mNTIuApT&QnAq95F3~&XX@nC2rqm2(s_z
zjz+LkLHrEmT3CHbWnYM<V>?5(=%1X8Y$bY2%NG4(QH*E;h`Y`fU0rK#Z&mIpTXguU
zP08Pkw$)BTcjj!-GS|i@@tNo-rP9*O79FFd&YP>!;Hs>)>Di(cpCIYSk5GTlm@V3X
z(@8%f?V2N7^qcKuX<u=+WNAj@bh0$vxanI|N~mCkQuwY|DSUNmVf|P_rr%g1VIwWC
zP9$u6^kJ1lY9*MAZhI#yGBfo`;3D%aE_R20(>v9l4_|P^3t=j2egPNN3var4+J4K;
zQ<c%U_D8Rjsg~PMieYZQXX&q>-Z?F`?{8nA48^7PGwQ;0`8u~I1b<(1JZK;<7E+zn
zDz!D|I<?NZE<Yyo8_)NWJ=-2ym^b0^ue}?&YD9vW2j$CF!sDM136DALHz)1lT+A@5
z_J&>L_(IaIwnursdcm?JW#AlnNXLzgVo0P$PjJq!k>@!L$_0kh&PV>ZjXYuWX44-d
z0XWioj{{0mY!Rd^(u0Q|;B;c+qk+bu?}!w!M(Xb`q88hO_olf9k5U-_dg9<kGGE5C
z0a=L)f9w_a+#{3SpfZ`;=z7kk$n6%H85kZK3Yn13Oe*al_jQ!DDG!|QH8I*lFg&M&
zTa-C@kuZDMbx)AVPUWi`o|KTSj+5WXo8|7HxsS|#i_9}3a~-GLTA}QGE8=RxE64$8
zz5?OXTxlV-d6>&Ch_s@t^UKK>myyE`?Q43RUCv50XE%|v(v|zj=!&j9JLr3n_5@Um
zLDpv|ArpAhr!3)nwI%-Mm`GjcXM&RWqw9_iz52nRKNgS3VJXR<VLstv$W%(em;aF2
zQ+x$ee5RU`H@EMnx}0L{(NJXDYSla`#u!Sh0GC6!s74w6J1$hL6l4GNp_wVhYL)Fq
z^}JGyC4gn67*nszlVVK1b1o^y1lG$a#TYjzDX8})S_)pe>|)##Bbro)Rwc(pQjFEL
zDj!ib4pb;hU=&STAd=C@6p<Rw8wJz0h-5G_N~C5Ni-KvZL^2qeCsMPEMZvUvA{mSf
z6{*?9qF~xPlMF_t>eP7ND46!sB!iK|CN;ZQ6inN7lflTYo0?rL3Z`v%$zWvAn2}v9
z3a4!v$#7)cIFEQ<>$@;->-myw>!$e<Rm74*90f8#CLc!PFiwK2ls8k757-cT@+r3u
zL(rUCD{rRwr)>y5<tzwc{@Y0L(b*7sqFE5q{FmZzu_5&IvLI+yAzxXF@79LUlgfgS
zZl7EbdMa5E!sWTOgF#J*mbP1=Cy)g}^9CJBIazE&=xJj?2=iYx7diD*u^?!MR4e6e
zV^q<nS=q)!%XH=q&2Y(cfjBQ=hmkQIvLk-eq8viXWkvkr6l99;-G+!y2aa+T(;+R}
zl?@S}4h$itLt2El4H2IX43Tp>FfHQKfgy5EhwO;ov|Ma<N8;0gTOp@IN(8745uXkW
zA*MsVR>Y?RL(p{Cu#SDI*?^xZXY&d*e&*Rc9=ey)**tDgp~iFF4b!17=GZwM%Zq|(
zA)2hIku)vTcx?EMU76NBl4(|`@!(<7BRrRtuq#qRQ=zoPM5z{27HWL9>KfNucr#I`
z@m%wnX;G;0hDAsn+!GTGGptbK>ozS4HNHxvV3;pnCTcu6A3pJ~|HVE0pYl=HI`1Vj
z|LRl9@E>(ZoFTg9$=S%M5gET3*2=DRo`_;ZeGhjZ-Lkp1vD3P{=oa;=?a%R|ZMEGn
zXO3=>Zk`4{6CI^gTAI-<F<R=FiTu$micb*T@=ogS8KYYaIPGtWv}=y&mcL|2w|wQ<
zqFao{>2L_$xar#?@g)Nh(Xq0zLIE9V;U*M8G+mDR(<8wk(Z~}c>O===h^Uk4!pJ*7
z@I$}pwN9UY1p+o+PC+O?ESV&K)$LDzPZ)&q4?_+!s&0P~g>=Xuo-d*n+Y;^P<{CT-
zLixkQ!HWc;L}hsN@3Z-n*Eg%R_4D#4CxB)7lhrHp_><*3=i*NmST7@gGB@Z;!Vtwh
zF)SC_KbCB{Act1EKRJq~Jq*cc<Y7qlCr81~WQdA_>HTqX%V?vV>Q9b>>8(LB7@7K0
z{mD@<ZR<}4Bcp$+KRF6^CPP#dOxypHTSgn|RDW_5Om88Q!N?^r!=D_5(_VpOIC2l1
zhd<f+?ztMG1TsP1wLjU0(38*d8`7Lh_b1yBddgW4Wb#GU9mDfTW;<m<up#tBvmj<0
zqHG8~y(|ctRq6g@8$wSi3u3kd&4$oZ$$}tLZl#>&PqrcS1hODz8=`CoJ#8!qnk^`5
zmf}ygA@o$SAZUin=T8=}FOfevZ1de4qHKuxbYQ<BO^0-UvJDZR4h$itLz+L?hKNrG
zh7i*s&7W*T#HRy8<eUyn&iHg-h@8`bA>z}4A;fe@^W@qciBAWHkkcW>pKL?KrvpQX
z>5#7#@#(-2G#$>_pUh1!)OdF|Mx1!sUV_5IS2%2Z*YU@0*KfW9z9OmnuLOR}+jSa)
z@p#aq>tpYDyn=@g`@2rpI~dco9>UE1{>peT+;ysz;qf~b?krqcWyq@wS2z@1){Eo;
zDb#q-OgP?DSg4p|=j2b0f@vX|tf`SSP4y>7!L&F{1|zvzsPV8K7+X9oc9UsF^0!dq
z{r({&%5AS(afF(mGb~haXradAuvOirMO<%TH*8M5g?B}9y@eri>MaZr*IO8(P~(}`
z*~6ES`jRx}++m?13lwU+o(@cl_;g^sGv{<D)c6QF&qIy3T?M~Gu7cI4KKD<A^Cs$`
zJcAqgw`L=!x;{-e@^3^jqArKKb|Y83YICQ0S8n9+RhyE37;Wo0yODW_YMp<N&qPNl
zm6oO(IYvwE5zX&LR(t|C@~=^U&*(-r;Qm<(T&ewr>FdVsVSVKF2DiNxoa>#8Pd%&4
z3;jmj>v}z}KR#{0b-K{>y4^aT>^*%Ne|pDW6XwPV?mqoh39jY#rH{71?#^lZk?DPx
z9)5V?G-#Lb*Q4zVLHq6S`M%2fvOA$P0t?2R0WGw{QxkQ1uivWbYz5>#?)(5c>6)ns
zw9`~Lg**QMPh>fRFF)@gx4}5rb>1C}{ho{S`OD%Mw&V6&4o)ezd^)s$D*c$bpSKzM
z63&0p0OxlBzw*<e3)qn_TX_h6^~tg04u_sQ3UCY^DFv{{ZS#S2Gr<IRf=;RT1}(4a
zO!_T&$yG=BX}3p%NvGFw#v6B<NI&5o((ngm=XtN`cDn+fP%LQ9YH;Y^_GIRQNpI41
z$M`!;?|?K2^o<}qB){y4-E_6A==sIo4SSfYa}6^&i|<Pu=BTsywG^xLdSu@CO3J5k
zwn^;RllTqiH;KRE;{7UhhGyB$zr6pRdsG4tkrAZxd$CKU&cBIWYn#2cWYmM$haUN@
zar^Y?79>dLQ+OAW<C{Y2x2quS4}IhnknWv7i2-*$8^84V*d-&};=w2U!wFJrtSPS5
z7wqxxhAnuuz548|rG*6F0B!ceH;gvhtKIY=Hd-|?CA|@Z;2XgQItxqZbE5MH*+9`Z
z|5Uu$od3=LDBesac=bYbz)N#e{PK&3-HEq*=L4azTH#z1E1^K<_@WPp0f|hPc<jXI
z?~67mow@FvjQrE-e!VgAyRFsEWOxFy*J<6GjJ?&3gN@C#O0D6w8m-!Pvs&{G*0x(4
z&4b#(T64>7G%AhOrsr*~?`$44pcWl$Rky0!?&e0b);e%^s^ww-@U(Le=y&I|^Gf{a
z{3OU95Ep+AjRZ&h01XGFA6R`lw{kMQh^6b$TP1L@q%y!$Usu75tabh_AhCEv$ke%M
z4Ak^(S0s}M{)dq9WW92{zFpzWG)~od?AQygD(27eq&+KsnLlqcby_4K5#n3WF0}d=
z6J9e}cxt2rn=a5CS;Z3O_tPn$6^guCnnlL%rIAU{(#%GwdHp@|Suv7Q7TF}oH?RLr
zHc;gI9XYT6>!dg5o{3{6`*xlB4X6Nynlxwx9+FETp^>R6MOXi%1UbugVxwrXoI0~w
zseOIApuc`<Gu5Aly%VCg{p)IxnYO=B?Nl@33->{r27ex*fz4kLwrGD6YvRKs5JYYh
zMZifTeOf4P{!I9xGp<s9oDCFd_DpV`+44?B$dSZVD*esreb6ofiXw$5`dzWmUC(ZI
z=ldR@{YYeS{w;cc^{GWocC8s{1>=RUN6sl?+HiGqZo63j0+9+1Dzwz!S>+~;yxARK
z?vY|Hl<(M!jT6@HO@&=4-&<wpNxU_Hugs}#t=1|IVbMI6N#dLX?D@>3WILM=qiKVN
z+wi-TpA1Rb@B&`fpOxR^ZN{?0s8N)SN;1l_^H{&{9q-D$!8X#I*_pNagK@MqVGBST
zC}w`JE9YWC%5xy4EoGKoC6>K>dso`j)ZQOT8O`pUpT9S%gq1qK9J{7x#q`n>awiJb
zl$%o|)hqEvSHzA7Dg{`+XYGFN&E2mx-LGBwa)yrI`6YA^6fxf13g4XF``5hFKXj4I
zZ|pf<zZIypCVJWK(~Y_Nw66Q~4Pnb>E+nc?#+!Nj^oARQlR&5o$enoN9Jsd!qp)i!
zckLeDn!AS^x`*xgdT6|<dpKj|c+l%ldgGI!ciOoR%KY>K<l}*VeA>Ryxq!br58xkK
zRemnU6ndH%{Qu+=$QSAyh`r}JvPdGTq3;Ap9N8Wmi6uY?d10hNjD(;qtru$FgexO2
zw6>fhqCF~qbM8^u(xYN@KC(rzc4=odd|a{(A76cbhL6X;Jwe_@w_E4hm#?$?^2YP)
z%kw|_h3?BEc3-~c{Q5G2RYz*On#aC?2C07=&I&_qK2L+xx>^;KL25m+OZrUMg1iQ)
zKMvn8+H9`}`8KY9m<<%wmgUCv-_QT1G)N^A{5%X&Rb`NB`SPIIiW0G{mx*c0t!_1H
zwd&4JwYh!Z)i%Ax*1=|TZLL<RY;L#*2enFTXMMA>zFze<YX=^TS6*eaw$^O6yasGN
z+i}xW>D9Jr>Mi*Dyi8Ny@#YI;<oOyv{so$*Hu&>4d*?7s)e>GanK_qf%A&vwt-|!k
zbv_dw3>Ky-3G!7mGC56Cub0oB*);W<Y#@^;r1{7h{!r4JbDO4aOXJYGG);{L*eJ@Z
z%)tjIP<&brrmLK<$dWxi^5Cor%~s(AwhdTw8>jI7h}gXq_Ah3f>d-#_3)51yID8>L
zX{&`ngbwyZi!cWpsJ@fLf-q1iBIYqrwZjjcan<s&fg;VG$<yi6nr4GEP$jNf>2D?(
zsQz{Kk~z~r^<hnRttrJc*r;|M`8)1+v2q}9gS1yTs@kDF(%vGQ?3+P=fa*&(>TYFy
z4R)W=ZhzcfX|~~fDIvnFzr=Ch4Yzsga6}2wS74nRjCP&TVZ$v|*LIejP5i%#|Kn)S
z_7cTzCxd03SykUpi!&d(trlWD5h7j_A>#To=W=FMeE(&1W|bS16zskw(&4+eJ=kZw
zBoTW=0SQMg?3XlTVGx26xLn$RcB!U$lAj7+)Rx6bK#{e)r|k{>k&lQ3=W+K0#!)2E
zZx328UFu{efDs3s<ESf{j!_U|Z?U#`RnkXizf}1JV=1d-;c$+!sdN5(4kV_y$zU)U
zH9d_%@2aSKqkWNJNi?HQsj|YDWR4W1qqurK{I#E_wNecU$T&8#`=otBpNUHT1T{JO
ziEt?OCln><O5TiKMsF(=b*e`Lf7rbZBe3HKkJXt&ftDlc8b`fSlJVLQnljcQIU-1<
zTr;xAs=mj#z!w$1NDL~bL;EytayRJ%u@lj;UPkysH8Et1T6rzy_*B?ShS06CAgB@5
z^7h^LQlIfi?q%W`k616cPP*m`)kLn7PRw5^ucejTWvb)b3=!`oLr^a<mIlO}W2q0H
zB=<7$@JXzfT$elEORmc;dRaA^Xdbi;$1=N8y2<o&_EN_wC-;&9mScz8W4+|^$?;xt
z?PJl)T1r0Uu$K%GA4`T1V_7vI=Io_DS&-aII${tzbsy^`7s`$IlB?W`UZy234tvQE
z@m?~7=%txKd(K|!!w<>5q*D;F^zyM@a#huMFS#(Q=;cP1^kIm2FT*;wn3sl_p0k(w
zfKzfW6Aw7WddZb5<Gtj{m7<r`lmqbLSTaPsmkc4t(twz=m-^^yaxdu&Y(fHsSU<U9
zW4xbSVo>xmb7p2$uY@Xp_oJx;`;+@g2X&*F9TKJFPI6v_9hCCwQb)JTnSz!f;seSM
zG@x7MEkjnT0maXh1k}YIYGwjzo=EEKZ`wxg3wdCe8&vF}^vPf?H)0zIK2}Hfi#=4a
zhjPa{@2*(+iak{1(7n(a<kZ4aSL~ta;B~Qw5|&glkraC<p^p}Or~_h$Vh>g9p>kRs
zza;liwr}zm$kVs_)W;ta4##L9=NV3G|LkmJ(|>3N3UtiV+CLM;h&to$`m{DuBv-xK
zU7gkrU$rUuKS$eYyLr>%DW*nk*WX82L+AVGpYIm|4xR7BPZ^=WLsaYhOME6eN~yFo
zPix0$Im5S_5^SOQ1TiZ=N&QU-w&;8oZMKd8Of9(2i>~p3XT^4a`>_<bv&K7??6|r&
zonKs?(fAqOV)OXsS^KhN_vOv!*Own^hXDt=FPcH756eRlv2ZUOdeWy6_1X04W%<Ic
z_N^tKD0huhob786Mf%9MIKVzTjrqd6{Gd4rsD!o(^e`{kQ`C8lVA*^z{O?6$e*U{d
zx_qsC**t&#!rw&<GeTK#_<|3mjN4SuUPk3(3*Q@dJw8iM_306bgR><EU5`%E<Mar7
zb4T8AFdCPgXFVTIKt3ogyu9J@ba6D@I0Pfy#qh6=;XxK}L~_V;TM#rq8TIicdHx)*
z{-`Azhtnl}2gTHJQXM(v$gONSp&1}Re0AUPj$P_S=&VjC^j>yA0;lWud}@(6wIW-D
zKD&Z6EyRFRYv`05eNR3>?(ycJkMix3C_#@-_E40=5J&F`Sbb4=(PeYF)Vn|qJhYus
z7BDtvWx(%vPW4Z~AO&83>>t2$&V81YQ*PR^FE1a2C;tJW&Ra0@!NBbW7{MM+R|f3w
z_nSzX!1V2VM-~O?lYW2`IW*3w0nay`*2Ke!Bkn%>9E?Xmk|gs{E}lpuyN4_W#0=tD
zRGq)YUh3naH}WaHf7yA)?c;0{-U=L!7V!H%y3p;O=yV7J#Cib}=?+xaskXd>n)gi*
zRcAV&aC)~np77gv1)atcM-6vz;0jC&*ENdNQ{4U7I~<Ho#CceZY%u6EWYZgssVgUf
z(vledxakWnZ4Decz0^i50C%3+O`Rhmplu^ZbayzwJm$kyKJnYg34E{~dW1Gi`tA|^
zl<YMa`AAlX7>Eg_RS+!akG&qX`hz$!MnfE^fd68aQnm{*HpMK(ksDt!W-&|M(aT_#
z+KY5~u0@&-+Wlh2BK^BKSIY9zTH_!&#7YG5cH19Ja7O6xaO55GN)lO6A*)n~5DPF5
zl9(4PaX?k_ks%RDwnJE+(1B5`ZTOOUU*@Ud6&9gmC+Y-~5cOe{kXj$58YRCFOb!nL
zBr(E<M_Mb+N8v21gT)oX9T8Qu>Or8ADiF3^LeoRt0fNi$lNM&R+_JQ8P^hq4KG2Ki
zV1&hBOhOrp70d5njCB<kq(U=9`kb=!&E6R59v$2gscyEAl$KV*W*4b?@EHWg$*zj?
zT9E9#)VR&&geZqa4Ig%?!O#a}j2i*asD*O97}zhhfwe`!mAOU1FC~crV;{57(%S`B
zrN5ZkS9Mky-jC=lK%V``L+>2)n_Wa}LjO=366>1X!*86chqNR472U(<6LuuizsAQU
zq3Z`c(}ljsrzW{!Ez-a+`)H<zl0Y7_ry0!p+`0pe4LcJ^2+VDgVL0>-)sdC%6&!xY
z!FLDhbO4<bnwp&Xke%qYnw&3#hS;QT&P8fkSN=&Nsb|#GT6h-eR~!h$VL0~YCA&T2
zx!OZR|3B#Vd@yO~-}sDs3#Vdz1SF3TI!+<NoQXj3Vd{OmVIQ8WVMM53O=_4q>u?&M
zvXc{Cj9EulCADH!0Hd#(%?-$hu=a%WOk+kaN2ao#J9(z^{hW|N5l{YQlj?`(A{C9{
zul-VJQ22*>3}^7v9&Lfeve-OPTOD)l#Oxb+UAd7Th}~cqbgo)|Mijf(zc_cVKlOiv
zz5Y4f>&U^0sBJg;cgDerKYsJfgB5F=+Xs#FI#`hamUXZ~y^<D>lXS2`zH=@ID+Jcd
z=wJmmC@Cmtd)Ik?8;2UCH7q=+#;a5;D~p^8Y_JgdSYEoL5Zq)Hl`g{H<e`PsFrKSI
zoklEM!nuMdo(_>q#v{kw5$uGR@|29`J@0xlAFhsxNXDhOa*0dnX)IhL8ZY-D1*>0h
zx$1By{E>1<p<;JM#ajv}!blE7RN+#px*FF-7iAfeAvBFuU_3(*X>W`sbjBnTLX*>i
zASyoLb^`-L5iiBx7^RbLTQZ%fkrXItuu`m(S!W!?DT!Hq%sS!_>7yAm8jcoY#OcH*
zEzV9S4V+9T`T~Vg&!SV-DG5<aV-}sV4oT!-Cx+0yQS8L$EY41*JO?e-GRTy5%tBNN
znMJ0oQx<vHi811I;=>+ir&FGz8tWN!$_g?PM?GfIDeIg@4t8RQIGOmU$Jxo0=d1_C
z<<FXRStmWjS&>;}$~x$ggG>w&Clj9)IXjv192TJiH?zo;byP$gHkn1HtSF}(WMYUo
znfS2D*~ygWv<aPlm_??nvnHY(&nz-!9W}{8CWeTUiBGE#nQRF3Xmph;M_p0B&;qJX
znnpE(Jf~Htdf_Z8Wt~(}r(I^zDeI_;-N{6ifFa^^;sY~hrc<6sEjpJui%wYwUBc5c
zvj~-S)Fsbq#~5)+@o^cVR0LyAma1lH<MhDQEOoq^qK{YSQOE^|)_RrxBS3Ph<N_p4
zE&+08&Z_F>B`cfsK(<z%rk00ik8|kdX^J^x<fT@cW`0hpc~uWY3b|-RvXt{`igsQN
z4>4z}=K@2IUdUYGDdrqPOMvJ;*&t_Ut}GS3N`d@YI(julNw0>7p|iDgfssHh#>mTD
zDSEnS$l0ltrKnfwP<583UQJQetKp&QY+YSoBv30nRh@^oQq*<P5Te!@1$~ynUZvC7
zSsHsaMP;vsr?azlc7c&VuJCwv9&)9q?V=&)K&~vsy-LTtvo!Z=it1hsk9lY7?gAr$
zT;VzIJmgAI-$g^tJ{Pm}_bMG1&r;y4DH?n=JT9KC!V8Q9YK7;;^H3{Aix&+!JGHX(
z_$nPc&r;;8DVlsWJanE%l@}-p^kNiTkL*|ym3aXIx=8zXxGsk3{266emO@{p^Xpj}
zeKkd;uZD-$bLsQ~CV^t%0rp5|lS!7M){Dl>kYCX6Q_jH`F0YyA;CVCsaykdk4Juq-
z4a0?|XH~LmisVt@@^XV<Z&AtEd3M;mOV>2EAc(X%mPUq%OL}g_45>vjP+Gd^*E9o{
zZd=NB5sfTdUipr-XYHy}Hq~?NsSB4E*fD!EUAVl+gqXdJE?izjrY*9y&ax>NE-xa}
zj*;^#QNb=;UQ8w<nO`EA3YQm{32|^i#;hw`UZ4|ILCzvn;qt;k7*2&J6Yb8D<%P?u
zTDZKhABxBArD*4c%PWyuh0CkU`MnF5S7=Rw0f9VP(juK=PAFVn%J@d)DqLQ3#A1<0
zYc_KgE-#&jkvv+nsa3eV4lLPKxV#({%9h~rvX7ws9-Sgved_<O?&?Aux32KaWd7`(
z@$5`G&9<{YW+BUDySB&P%<eFxeP~LP%_d6eLZFmgRkmbH8d-9rtL(Uthd#9I!iAPp
zeP|(RQ+5di3VqCDDG3zP_My<n_8}Dd*0gylg+jk`WZ9C(p4p5i4-Mq3ban5!=Nz4L
z?vcj&?nko=439Moh&2Ih*@uU79t*XVhAsQuFpuF+*^Uicwsqa8Rh!3xE$a`>TJrD1
zvYs$(8Q-Fs{WnZAe3!=BG7VdHz?OrLK$Gvc69lO&&e&j&xPhMlXY2#gcS6{*#O=WD
zw`15%3iVaWLVazV9Mo4z_~U<zdALJAll_YweU7zN-r34$zcGuOuWsjc+6Zg6*mOKi
zT<dS<IT@3zlW(qYy7=Tvho*}^1DVdqIOU^a^D*O^{UoM2mXlvRT)vD<88E%HlPB82
zD=!eg37tH}?(7(LlR9}h>*Qxo&dF24e^yR@?VyuauZ?i=;`PMAfsi$D@8b^7I<^%%
z&djaP$g!Dm&2D0vV>x!?aQPn1u@mj!*xwoBiJt~^GR5xp7<Q97b|vfB=T6SCQ^FtL
zu@8JnznR)^{W2rh1r6Woh+^2mPX_R9b*)<2x>~7i)t)A_kFQ#WbEWv~^9j1Zrx}v<
z-*=C2EbI?y62ipVcVh>K3%tWaQUdRM^yY()-}_-vRT&Ad>xBegf?X5+uC8@=Rke6o
z15{i$5Jdo=m|DAS_`2nb%Pjt;c}p(zI1KGy`X0|@KLmW#Q{RhTk2cLYxju4^#1Lby
zW_A9}(K_1?FlScnSQrR9J-p3o@5=iF8AqzymvQvftc-s;T1MWeG<9EMF~(PCV{hg7
zA!%G-xy&17wl#lG2QFnq?DBAj2aq&nsS&#<{{YK+-!_+?x$%uIHcWKOfU+{mfCB>D
zVYmEJk8KbA>MMz{9<_VcdjA@h>4a-)wtCI}#}PLvZ9Y3)Qy;L|A-7;`xskf{Z<D?g
zmK!N{Z;fF$X;$9KX65rImz7h(KYCWqJ_J5|4hU(42D@7{h3Evkl}Zax4`CgS+O7<;
zR;d@hmB4c>y#%BeVU&cSwae(9&l8uruel8qo5KRv&bXV;1B6otxEuc4E!N7|{x9Fw
zM91-jW7T(ySIgJS)qG%Rb<cOX&sMowE7$UF*zR;`6oysHwQV%zleqXlkv1EaS59-P
zxcK&A#gd!{b|1_c9q&ninb+*6XsQV#B9RkG?$Q``lSV`}8xa>yE+SIG4<cfaX5^QF
z?@~%&jY?j#MCU13qmt#85?G^>@Jh7olCzf>1vrHwMT{oEM>+sJm4Yf705qippVM66
zR;2{!Hw=MI4UnD^u&ET6GlK9S-Bt-D)z!4#G2=~Hz-m{swSCoUxmc(oSwPI1sRnjW
zneZtRpERT*_+;gIsTRgNikpwcjyaI#z<ZSWc)#7qtkNnwEeil;^nnDY_SzM>l(aYi
zb&eFd7#M=|2_m_wdyP<7PEZE^qYH3IJ(BaUXbw<$qaR1Th4@89=30geq%y!#VtkIu
z%s>EY8YidXX;kpu!)d;E8u|{-mW9_)X(Md98btOdb5m1tt%*(V0WoZ(uH2lK%K@+|
zk;c@0!jX*7Qb2H99YD#T2n6&p_-({3hGTGxN>6nvzqp3Hn65X#!B23xVJSxJj{k}h
z-JFqmQ*%UeIwx0+eG7&Xnh1kI>zr=X!xs1zfMV>zQ0T!~2C4%pv|*4&(LGtP+)gM|
zU_5)YZE+-Xp=g$NN`Zyrv)PNP;rpJin#k^s;ls!zYC}YF#S2B2%N%ow<hh|MLoDnc
zA<xJ{%y%F|GWu-x!q8xOnsf+YD1e|dhIAyC9nEcp*d7}e*Wtu7h8xMpfgtMnx~dx;
zI0vQyh9E364@9>n)PzMWT}3KrTKkbXFAG{IJay0{XDoQsvX0eB?Ry;z%MEzMHhdKO
z#BhaMU|lz$+dpXP1V*TP>VBL2=`>Ify}(e@BiTzDLVe8w!Xf+Tii%2+Fc6_gPs)WP
z8qBI(f-)4(jKT({%e`)D(*ksQbQ|H@F*+)A0#rQkyGfQMYN>0OnjBl6NmhL{2jxy&
zqk4X;63KPyNt~#s3Y2SDSHPN!XfHjv^)$>;@SBYx_S7<9e<@*4KLIC?+cW&KWr${(
z=0M0+Owo2QSq>182m)Q0(alA94ldPJ`_a``K*j#v4I{cQKhJUj5FHTUK!1eil9hD0
z@+n`t+doC<oesLLKteOEmg(SsIO;6n&PH+xnD4$&Ukwq!0Y*N~=kcjZAnrXIo@<x@
zdI#>V9|soh8KobUo(aMZgegD|VF?&24*2_U6R%;pP2B7x1FTU_2*UbMKdVh%iZ_sP
z*v)e8fpfI$hK^Y6LIl$=1SVN;px2&CFz}A5={i6%DKp%YtHhaX5Eu^juBPO5UoOQQ
zn0<ir#|-ziND1q5G0r0hT=*a%^b)SFDm1@kATPmVRv{#ON+6elC*bn~dIXg#cM&@b
za$lk&08QrP6T@8@4IVop^z-eUoULweSCjHBKFL-`e?;t$ddG8c#`Mx+|DH;dEvyuE
zxjGQ7ZMh-cO#2VG+<*9*-bn<&QFivfj+=c1(=qdhaxG&A+CqMe&Fl{`-AH-=LUPc}
zX(q$vJf$KS`t`{E`Rvrx?Z}Ssj~2)U>JneswD&O3ZW8$wuG;Ssc@9tU_ScAP;~CVh
z5xIjMBkXSz*`O|Gh&&|nOClE*L1-5HJRNNiIfE6>UMDh_2bm$VmIGNK@?RqV0g+dR
zV4x8TUL7EM+gIZ1ARvf-;7U6k3!$snU&Nm->?er4Oyor(ZxZ<#k)IHGgNQ~--68TV
zBCmjiGDo`8dwaGpYp<~83Tv&f#tLhzu%-%Ysj!CkSUZI^yT@87tdYXnDE7ZGMJ%7f
zvMDT=!ZIl=kHWGjp}C5fV6&Sy*yiRPHn{oE*xE0U@!8rtWPG-^M#g7rpC?1JwSP@V
zY;8VbYky2_Z0$>Q8`#>{>4>atuM_zx-HSyc8>c{iK}T#++C(L`C~X@OTa<82V~f5@
zM{H3lG1;OvRmq`TPN!NjEh=&g37b*?+%RsT1u^Ltr;2n-+z$x^3AbJMoPPG^uAduf
z?Dx)PIOdXBdC*#hKWZCaP%*VW%&T{0O6IX##~X2=E&(R1Lz|vJ2b6~k&w3#((#TB+
zsJC#ZZ%zl_kG@Guq~>EaM9>Dv#qq@b)jQpcj8_QoI?re)t*Jz3&YKIjqrvOJ-uW$A
zdmi5EQ(6YfF=g2ze^FJ!f=+LiE)u#p?NZTS<A5`s%~9u9M`y@%rS0KqZR3c3a*lr{
zK_;A~5W+%uL;3p4RKa<nkJv;-K?{%(z3_%QJ%t+F{zA-Bp6VNf7mmD6rBtu#h|Bu&
F{{TfV=BWSx

diff --git a/_build/.doctrees/plastic_shotgun_wadding.doctree b/_build/.doctrees/plastic_shotgun_wadding.doctree
index 4a30b7aec541472189115c3844efc0e13006bc77..05f0a6241c92dd4779b338dd99d54a424f983c0b 100644
GIT binary patch
delta 5856
zcmeHKYiv{J8O{X<;wFJmkw7SkQ%)}A<_k{Z3}a$gTS$CM0kNu3*RdU)c(I-N(qLAS
zm?UMY%u4basiGs7mK4UV8BT$&KpN2YBc<v^)ugTiiS5U_iqb?#lcv#Z-*?XU9!y20
zP211>IeFgO^S<Bldmepx|7iLr<LR<q*^%FU_8ZxY<uX-+yP*z--`UF0L|qL-g%gDg
z87H1$=+H!rp|96nWN1WZW@t`lVaV65gngAo%o?t2W=PeH8OExYnQy-NX+&cjRBTwq
zEaRITbV$}<^+x88Mmd<3{5g8`+w?Y;ao3EDvwA)AsW&2;vT$%rxl;5G^>c7bi7oFd
zk<6g7vcg+dB)h3Xiit@MHf&-PU{|AmR6@7adb#jw?E!z62Igw>;BZSOY-+4zwEjk<
zoz_U@?{ZLNL|VNOhv_zA#uTEV%{brgaV5N}&1bYDn=y56oP)<|k*s(NlHJ(B!7nBM
z(w!W9ELnGI1B_>3A%yQ@VIfTLu`>rY{rDTXL*uO1wK-JvZJ<A*PBIfedx}ewshzED
z8bL@zM1@2|R7gZbgk%v#5PkU&a}{j6&d`WX3BiUUX3Y`H)%1jz?(J5=WD~LsS1KW+
zxr8NBNnz|&N;u#A46~@Li2nJpQt+ErViu8=2~z>H2CF%^XDSfe^hV1-XU4=FJqHmp
zCfbN~*<8)asKSWkv&6s0f?4W~9E?iVl*J$t|EsSI%B@IzU&%qc6-x{%4$fGs#YD$|
z3bJkajN3a|3RWAIQPDXp#q4ShKCvOmsJaB6I<rb7nSP}lo@>dM3j-$W&w9p7wMU$O
zTEjv8vl0u@pM8?0H*#=Avbv4j&~{8L+HMdDhBkAs?qCiyH{$PxawPJPka*b+ETfX-
zk*wk^9GsP`8#@>!EZvFdPAvy7?X<F4sU(T43#$bStMxyxR^n~v<Ed1}oLZH$L8C!c
zV`gIBbvRGfplz#n3#uj}x_Tm_swN_OJrWVU9*OAj{TCRbvi9A6%%!qs?Ji(3U-wpq
zsHT10y^2|?W+l}3pk*Yw*59)#S75exxL<O2sO(OEM;#cOir}N3HLU8}o=%45Nj>xy
zp+&A$U-qtM7QI##MR5YEe{d45Xw<;6sQ7&)Wl`~~Jb+nE2Qcf<ffkm3*Q|u)eRxVL
ziqG{u!D3Vthx@R4%2En{>02qrhWe3;isFNYR1{D37s$mUlPi=OtOxR7nL!4B>&Grx
z1K9nRRSAOwc;1_&_=^ENFO|(TuV8m7n=eWhmCd)K_?~Z*7#ZO~Q}N!WIJh?1Mdvu&
zA_M+lVX`}SKy;rzxSbuF>Xo<*3rpjMg{Ar7rAe%g=c5wo>UFJ2N<_^>*O6B<Wepmw
zRwpWvfP|$Ikf1~Y5|l_lM2RwliYLKVK|T|~Nu?-jjC>e^MWyKZv8S13I8XLg@XwEt
zZ&E<UH?0iO&wF=*2#w&UpSS!i@<|ESbi%?A{R~gPRl+RqB=Ss5Vurs_2}h5YVkNnK
z{6pdyeHXj!9yhZLD)OES*lBJYGj3jJVi{Ezv5WsAMk`P3V$q^Y2DvaLy$036peYab
zU(&K*;Ykxi{*y^*^+MW5C)cy!vG*|T?t9ov{afty&97S?bZ7we#XNZ7)LQKDKBoQg
z6#fXR(~T^eec8s)%xTOkJcH4HUdD=+E2al6)Noss4_B{ntkilI(>7kkxAxjqB+;M4
z7K7(Zk4bMrtrZ5HKZh(+QzjVMxfu4nLqt^gRR#4D(88h#uVG=){tt_mn3~!qC|$iu
z*H)*gMWthA!aRLH6>LX~p)+eK*nXbdQ_eT7i^liI%XwL>Vh7(IR0N%Y_Rf$Z-05<J
z+%APityHa7YE&AnqTQ$1-0tqEQf%28=NIpZ^M?PbWFXEO@fp0@b4r$y5^jZ(@RL2u
zUr$TnmAs00PYB+mnRI_XcKq8*uPN;IF5VGRMEqfe%da3;v_Qn=i2TTIS5!EBj*dt$
zq#$A5;q|%$uJ%BvLYT0ejJTLF#2@Z|N$j+JUDU*mzv7V{@T5NweVFtE85ENPJ<HcL
zB^`>jGQ?69j~*g3w#4o2<Q>8GU>xGo@3G>MCzA$xbd(H~EgndC&7aeWidT3(Bgg&z
zR50i+gx<YNvXf>#AtT-*nC;3^WQW{)LrSkB@Kcw+%NGyx)x4biM8}Z{u70q#r&Pbq
z776iwUyairaM!rngPk3YNR63QDg3P-w=-nGq5sqLhhOVGY$@(ZxYfZgr7N4e2ktmC
zVf08YeD}thOyL-6&#VkS?W)N0^wMAW`$G?1(`O|ecMJxv<%9iNX|i*eICm{u7L&X8
zx}D@7fv_(WZ_WgJS>Ec{;?9VZcLcoT6~`9&99}p1v$mu}9uGp!_0qKEuP5rRE7H^K
z8Hu0#{>$`2Z7rTWT}$x8$2tZrGj*wNz%OPBQ-1{~X3A2}63<Hb>x_bUmwZ^e=x9bt
z3JlJyNIe6)KCI|zAf`u4ANSJ8W0pR?SVSIwpbsStRFOwGmPscIMLOL<x(XgzXAx>F
rLcT@FwS@Ux8l{B1R$$}55~==9nJJa$PlP!f%Wm`gL%#DjHl+R=@6m>&

delta 4969
zcmeHJT}%{b6y?Xoh>B7ZkX2ZzBcMok23c6@va(vO!u}R%(^QM=f<XeTRnce*xco?B
zum$e=Vj@3Ul!`xF7e%W=NMD*(<C;EM0}1I%YsE@@YO193eRJ=?OP|`uec7CIzjM!>
znZ0u|q5kN*XQMSIG-t$z-)i<`XgtzBj|kn@w<8MVzJn+wkb=k(cpuT}Ks%ymYlji_
z7;T8Ajdnz}4SG19sYBMCS&T?5CWU4F7g(Dq-bScTfOQ*_kXg<PP_44gtOBh2d;+{w
z>v1NkJ55ehys(kuOOpv}QURe+y8!3(%awXpivSaP8u?mJW@gcWjS~(s8yCqUFeJdn
zO=tmS64iTEG%1;4`J*j6=slVZ(}o1-a4mpMg_&sUEhO8qY_<KS06GiVnk;lN4Hi<2
z66)Ga*SD)*52tbx(Y9wZNvHb-SZE-#)GcK8V5b0Is`VwM0z6XLbHhRO2`>bHFTx99
zg-4z^*!131tT8{g++)l$dfZ?-Bh8_~&$bFt8jqMSxs@Q{hzAKrJV-d=LBbIa5{|Sx
zzQ^7kqaF_B%b~&R(=sbBT8WGW%21IUNc^ljQx7r4Ymo6!;dRS;J=`dk!-_K=EDGvN
z1Fuzn7ZjBoECH()S!b32uT<vqrGe2#$~cn%$84l@%Iuyk3;TG;aKD#weYc%dQh@-y
zDjT(%6@6Dr8e}-g__bbu{SIm|ivnD6kTDM&Zd@~z1`a3nu+Zsn$}c)UE0Y8WImw|{
zS_50J$T7yxCgrmaUD{aA<_6FP6!7rj(y?p-@;*>)<N!LZGLuDs`zmX&2wf#4)RoX}
zZ5Ci{TO1S@(*LIB5%=$r&(n8O8_T3Bm8EVG;Ht_V>_kggQcCE#L4YHra?)`xo=F^q
zcZ<Di;obU=yA{0XSr(}TnLAhXNVB=dX>g{zBSDj!E$+?cxuzhtdkSK?rXZGU3SzmY
zpk?*9<}n15J4AR>Pf`|Zjs`7?Y8$pAVv+W&AxUY`7mJYBn1n|x)mj>p;<;~Gb;Xg2
zYO&1Yt<D8Ykq#a<CZq1p#sf<G8@U}$=&(E^e^os_v4YIx@YDHdJ_|n>&?;^5wsg4U
zTaH4OeZQ$fmVKE`)K=7FM%C#im(o0C6XC69x=R*`A2+W=5sSp`W}Gr&PlsQdmn&V7
zj=3XQD$b5%sd%|X8>`&5{23*IqbUKFnl<oy3k_P-iu1=EB6POWJ&()1Pg?1oS#l<y
zq>E?CxkqIzIWPL~xl67L_`{btJ5u>_Th+FDZi!t*hf4#MZ7Flh@vTaEu&o5|n+2A#
z4B@58hVat-`_cqg_!D^&x%cgL8;nLuBBa5iXHG59<Qd%M5>Fxpv87TFOCklaBvO!^
zL@^w_4bF8gEV56mMSUxfu`K$eZyPf6jS@sNeP%?K^A1EWY<k!gOh(4u@7N1kWMe@)
zq6vo{1~05ZRx?CCfgw_O3-xgJ>on?=KR^CbeR^-wv|ar+RIm?-s#`Q^x}Ox|w~A1)
zewe0shv_u)(nolzyKRo;kAZy$<wB=50qSq(;9<&u6_Iyfjx3MM9u924!*h2?_TmoB
zlD?x^Q{T8|C**@PoB*F*UQHA3lI)ku^e2deg?PI7o)giJgQQEjLZ^S<qYl@7>+A>#
zCdEV;xi4U=<0{DtM(C-1H9{t)Yc!(snsuT2B%~aEp)=RWWpvaEJ*D&E_;nrnvh-3`
zDZFU>%?mHu|FCGm(a{~4bmfM;eL1s9$7#?u_Bt{+@x$WisGl{#sh^%k>o#QjE9dX_
zSDM?Sb7b7=_xbDn8I_vKm`bTCJ_b_j65!1vUE~r-4y8mc1yd+JDpe_e9!izV=RyW;
zTueknd;C%F!E%qcuJ&+N&HmcD!xe}8Rjc56Xx;p)nuv(10SzQSPJH(Q!@crPUHgJs
ucTL6NV+UlRJhF<Z>{YL#*zc2h?3Zcnb(Qh#RBo?*oDkKk37&jh6!{NEbZ-6t

diff --git a/_build/jupyter_execute/3b10867ba4b3bf65b1dee903696e5accfa2c51ba007dd2cfe381a0658d975cc4.png b/_build/jupyter_execute/3b10867ba4b3bf65b1dee903696e5accfa2c51ba007dd2cfe381a0658d975cc4.png
new file mode 100644
index 0000000000000000000000000000000000000000..604743772dcdb124e526c53ff536d2c99428151a
GIT binary patch
literal 20187
zcmeIaXH-<(vNqa)2qF>$BuG$_f=Fs42T_!$D2Nz{0*wfga|T7CAW53k7>JT2NX{ro
zRuPb#bB;~s)^hK2_Bnfu^NsJ`al@bcqu<7UyVsg)&YD$ERXxuPymMRe6d4m43WYkQ
ztfZiULJ^`-D1t=N<M7FJ)><vRN!Z_bV6SO~v3D}GH9_4nw70gfvbQjMa?a7j*3Qhz
z63s8hFT{85slC0mouq)k^Z)z;zm=`2KtCC&KV0O5wbDa76pGRic@d<`rJ12nx0RF?
z<nK8rEDpLj)7}_sSY4(%M`Fx9s)V9BN2>DX>|0G@V)mTOl8a<5A1*e2`aa1!qfYBU
zOiM>)b(O+_?wH><-LQb54+Ck<w@4X?eXn8(t`Tx>?ioe+2%VU~%}yLhtK)uj$;fD_
zsZS-&%{_}3YB<Nv&i>>sox3gpH8pkkhdWq!qgK`Y-+s%SnJ0@XY;9GeU>3jn^yx*>
z__m%d<WlZ}4c22{Pt5(!xb8<rzwE}dZa7urL!_XnxL3vmH`O3jR#sNHaYNTWUYHGY
z?fP{Byw|HiOT5i<1qB68IURobpFe-%I#z?>hunL=BL*$CkwN8Q_sOY$q70BfMf@25
z%Uhwa9EMviL?}VZDKsR6TwnV}kn+{5D7s7ce@||+vrk?vr9_*yCyb8NzDQ0@-7VwQ
zXuWprTDoqzX!IrREe9<Hh2&$=^MaAFvC2=LuoDmv{LawyZ;rk+AMeg+5Hi{ti{3xn
zTju2E{*`|Bqw4JvPImTgt(<!J-1K{EE2pGn+?zL4`r3*?cde}jqj|NS9337cNZ7r4
z_wJm&wz7hPN<dYPZ`GHWyRN!76q-p6zR<%g5!$5sTpBEIjb7r%6aRgjrecnaALaxV
z`CIPqY*Okst}Lx_$d=%48s0=Ph+Cg49&*jh&AfZ=epW$1K(s{X$d=z5XJ(9rJxN>v
z<I*{_U1a(GmS4*7b<G?SRE*-@)*=Tt_p4j+qCfLZRMmG{1gb-XQokm7jnw!s%Xubn
zslJWcwhIhUTFvi$=N2MW;w|;Vz3i-~jE!eJ>#2eMXl_47f|^n5?J_cU_Oa;&AHffm
zd&9jxQ+4Oig;&U}riXGwW<@k@ln5MA=H7`9Tew;o>L;2a&3?QisI9FneEQS(M(~-^
z%*cpqFdZ2W3%KD^k!QaHB<!Y8R5Ub1S2OQtf9|!gU+km%?$VrU-jhSlCYx~g<4tN-
z*4xI$oM=qz2rR^aU5CueSFdb$CS%rnO_N+$Bg4aM-^srS2n;+gE{?sFTM-eX@7Y^$
zn30BiGF0KRKP`7uizzTH=zUP-E`h2(*gESp<Z@wjbo5@XUZP&5Yo67xY_5mg#*gbS
z{rv7$x;iw3FlzG3D8o~>v631|UB8#^<Z|y~$n3pc`Qx;hApR3GC%+Q1csD$3QRdn!
z9B+7S)Se(wvD$FfVz4aw=SRhLeDzVHRrSH!3pi)r=lw;iFw8uUJ;x#E@l(%!rxVol
zeK99^P-MYKLdiNY9wyhmE-}>>ulSnj%7b#p%k}=0(_md`>PfQpbH4*$pB1yMKP4t;
zP=o4NXo`)Eg^jX0>d%({yk8XOzNUP*d~_H_DYsAM?a$_km0Bu!fs=8wT^W(5V3k%%
zyPc?X>(*r1e9p&bU7y_XgHG;82l#v0kD`$;O|>$j^jv4TFdewIeyi#>{IFL?o>Ak2
z3TGSTL;BzVC4QaRm3_(~8Q~E<T!rwo*6oy9O!Icn<Cqq|`q7$M`zOWymE9>RDdAYG
zlA4;@D7ThsEsM^W-9vhkR+74tRsE_G4s*0up8Xz~&#g{1Y7E7#)xIE!jEie-ioB3<
z_v7&b(~kDlKNStF`!;;4Jvq8f-@hAt3!?KbH~l(l{iEE;YRF}p1x3Lksj%4h<>8lS
zbS#qg-@oM4zdFSsA<^4u9@USH?JY1xyQ~=(Sq(46`s~0SgjLKlZaO_SHkPiLM!}&N
zYP|3#4~6&wES90K&@6I#JD$C|3YM2^?^DWxrrO9-I8UJFE&9FvLypZ>+8e^9B#imZ
zk*ZT>#n1b1K6=C?<GS$<<`0(yhU5S8<*}veBhRUhB=wfJml@F*@=Mw|e81O4tcC{G
zm%Y7FpR{vt7hu|?O~S*&QOvULe>AtI;;nuaJ%9YHJ4?CilUA&R9e4HqTFZ?jQ+Sev
z-U9z0KkleM{-l+O-0Z}O6XJ=tVfAL{26*phDfJgUKiS1kP0hn>WbkloXYzfv;m)97
za@S720KTmF(k&*G4sAPojzBVaUeqC&o=vYwj7#=Oa&p8G9qi%PtB(%COj_Rl%ziBP
z>eShWV1cR!@1`^EWkmGkw_(<KTb6D#<#d4ce4qLG(PcIzX68>G$NTs1D^}`GW<4yJ
zidZ!3Og(i3m$u8wd{}_-nd4(;=W3)r7Q9;`P`&iCW{^meXJr4~h)LkmW~jyzxi*$3
zNL3eg?;1Vn6|-M2Yih1~?o85`+0RDIi(WDBHU@`7&Mf}MJg4-PBCE?wdVTkwb|kYQ
zAt6t4dxGdL&HT=wp_E?nPUAa&zScY*{O+{#Qg`;_0)tvYh!$%LDp}yEGqrQ4`pk2Q
z2hw6iE&g1c@6HY`rDJEe6}ob5M9!&9pt@Z)I?5xubHy=*&G@Qe>Qi=`u-8rIt!l<i
z($66}!IlyHs2IkLMn`7mRx!o2e1jWhJo>^5^IvGz`6@G~ENElH{%~*j==9mMC$B0f
z90Pylez-FY8<3io_MSzIiI~NoH;73HRBii$Z4G(gbzz*-rM_hEJP&r=SHICO43tLB
zb!CoQi_Z*K%L!Dh5LUWwj>Ved&hzpH>3i<@g~=Uakx58Tzj!m0xe0um;>Vk>175#2
zX^!Fnw_NdH?lL<&apYrz)o)sAy&{;@i*-H^OJ212jpaA18mw3qc^%B_OYclXs>O)}
z{`vF3vSjqQ?9K$ulP6EobxMW9WVRUE;>D(6s<_Ub^WIsXCR)nl?o3mk&MqGMa63_Q
z1BUl!&VJYf{}cAxQpNi1zGABm@M4v&W~f)>jCIl4db5n$>-Cg!RHskZISqR#4wgC0
z4wj4M<>d{yEmtPUdh~T_u6KAHMwTy?1^W<@xZXBA*v$31TvQeu5a2NTEOo4;kBb;@
zpnqXWQ#Cy5>6`HVpIvH5%zTp>Yaf>({_^7rEbJJEWE(_M_P42m9RJ&IMt2(+UQw{9
ze0kOdvBP4hqSw@6w(rX&n8dZ-b?{+3smkkobL$;)rb`2*eEL-h$4@cc`FQix-$4BJ
z0{HXqu~Qz?cTn1r44U~)6t|R=-Z?Jzf$PnfzybdFN(dt)4Nbn5OT5zj$jO@kzdUO`
zFsZ1aI^{w_!Tfz?v>qanKHU6wu6`0&%*_x6c`z1vd3ha=&91D+#qI0ZQoHHXXU<H0
zNrE72P|z#gqAs&Zd--wE#Gun~3YdyGGsW)KVoM;+1?m0-Nrxb0BEcPKlsi5L2b~gO
zmK+eEB+JuE8-YG$sZSc%XxMPm>77LUD1|UuthB{Se`YABq!L_;^m;2A?9&GPKUiWT
zR>)|3=3^LE%!>7_m}RnI{i^}%`cuqOj#*dtZYwDnG(~XjgU6Tz4<Rt@xp%ok2A^Ph
zz!4^0CpPR}KlUv+Ff7b;XKm8r&*%3g@fX?IBdo~Ke#Qmzc<g!$TJ&0v%hI{XY(*lx
z<F~d^Ybqut6@Xc=6zrUwFU5wOU(oA0`<%6^2<N^PCuldN=KJD>%idz~$--suRa5PW
zs-3B~N~hw?83YYb`W~Bfs0-@2iN)gKsc-c9$%<jDBIey8F6&d^NAK>xrlqECx{&lL
zcDZUVG~TKzR?=Y(rt(3)abS<D5jirU4s*W|1dyX!p6@V!fB4=OB?3}p$juz87JAlA
zjTrivUKOvis%mPSK7Cr;ZHq5a%4sV~>(jkJSa1l?TZD_5uowU?T;BrvXdA8fm+7#B
zC@JZ<F!NA9`_Yx0inV6;BJc&tEAC7f*gb$~E<0~_Y1`?_K@3V&i>(7^(p=^+pRSd8
z2ExV)Q~jvw)>Vdn#t+vjTRvVhR7?AHLU@G2!@FlYW?^k1pNx*zxv0f)YoV8U@6$hB
zG6x#nIqw3tw;!lp-}+i?=zBqjtm^VmrCk=fLGXE>2&>n=jVpfX7EE6(ENw<cM#a(L
zo^1N_+d1~mha}6ajMf6`dM=)Ktd-6Gd_E7Lc4}|A8XuJ?<MwuQzJ~_!XKis;By7fx
z0YX@_(EL$q#w2Q?l%f*-pwjhA8Xp&zpKiG$T{Z#i!y6;TMwrtyG!phRR5ms?xP0*E
z;LGd4U9P+9xVlR6$F$6+aT@D?u^(lKJ?Zu|pM*H(=DQ4y6fyu5a$(YIq)A?f5)j6W
zzP~vScw6}Ck8>z+GU`f7q(^wKqej3Y&HzhdrJO8%aA^=|$(cj~5T}@1wHpM#jRl{g
z@!ofs^(N#B6x)kwKi*&WM+Jn0Z19G`f3jNIl9eN^#hGzQGcz-%Gm?Zp^R4c${pkL@
zZ@DZaqQB%|rOkwMTavIWUlct~&Va-U01cG-?yJOr0=?ZVTELAprX_i*K-k_Mc|qws
zmyt%cFO9hC9zD0q#RIk{2g{wN=Q49s0X}~lU;?<lU%)8GNQ$7!3TGjJ;+IeW1Cs5g
z+nL3!y#e646`d6}MiLt&WRxylkdaB;*jOJt&mR*!GxIdz_65iCLG%8?LJ^qSK!C0n
z(?`$)EXof0o`WB2cWSG8Wkg#}8{TD0r`8x5R1xBto4>@)UNvr83J+T9>3I}B+>X-8
zynnf7@VcELR>FPTI&>)RB=Pa%rx_kda#)$atnpgfz!8Y=@urO~syH4;(j=Sp{!TR^
zA)()&w1Ney_kU?Rf^k<JY(1`ys~e_{TK~l5_Rcp1T#ebPSw|~iG?=C^QwbrVa0nrq
zVE=R7*)5RrV8w0N0j+)jY_66d9uCRQ;Z||=&gX8#i>t%V=+4#eaOlyUe&{*#-XB%6
zw^R;`%Wu>WGP*I_DZNrdl$@OWqsqf=Y<#?u+kpnAbFIzlI4UM8_|&;ysGs?_a&sYa
z&>5pX4~NFWz^R)k|679huXL|8d3SRj4SS*ku#6G-vlP9sG@NVD+slvN?yd&~1bAs;
z!wIFFSI&VyGO8-lLcz@<rizQvZ^j(p>3Owtbolm~tGZqW1O&+4=};3=QdTx>3}pf2
z^9uY!L_~zfSV!*{b8S}l6?x=US67#=S1AdwpTn*19o&6=p`b(9dgLlI1<CbS<OBm^
zD-~OP<|im9xB-7rbKJC^`_0qgNy#SL+9o!v1{oo&z&^l=_SFF|>9!4k#=nZK^bzz2
zsp8ZAqRZypS%wg-qz^VaEqe2b<J(@rqrnF#z=cSxgXrQ|o(R9gK?rdM7X_dJ@*{w3
z$i^uwEPQgPPfH!152z;q#y`_vEC8|Ee&&Zy!|Su1a4+~!WxsS9at;97fap#E9x#P~
z*BW=FrQpzyUhf?sKJfWINCK1Oxf^)avczYo(rq1*m3%;9RY!+z$W(L~9ft^5<*~QD
zJD>Zo@F{g}^`WFcC0ly|1$gpg)fj$cGo+}-<eRjdfvoB}2E&cyUPq9VmCk+26o+L&
za-epp<*y9&x5Ng&!p7d-=v43hY)F*-xH$E3u_Xj6a&G`@Z&t?}(S~)$z_ipM8E`q+
z>``5k(^OE%YKgMBoz{tJn6;mJ;IzA8Rsfli-R{QhwZ*+Zc}Cp){Ou?SPsj#ZA-4&7
zbRg|8`|I1+hK4wZLF&EmjawELSwan1*Uh=u$5xeH^Fl<&$px?bQ*81+&U@mQap%3S
zgvV}SZ>e1xK`VeInfYR?VM`R+VeXzfqrn*gJ&O>bDF9Q#F#l74pi8^$_P1A4Au{Nh
zKv0X$>tE!)e7P+XqO*XQRpsVexK}8PR2*!I4s!@Pi*^h1Pl9%L!B&@b7S{K|exo&y
zH8nMTZETz_<Cm4iO-xLj_Bezj=r3|$k#aP~FAW+S8>4<eN|Cz=Ahc$n)DEEQr|Ice
zXD!bGqW$_+0rH{Su)3A3Jta0qV6$sk^^jzmb$z0P45Y=W68RaDh3Qq6Y3qUyQdUwz
z8Ng`l7ykU5xAD?BLrqO^3dMgqt@B~>CResfG_PI@WS{%vY)1xP1E?j6V14+doR*HQ
zkSWESW@gqIaW%nU5XACUKp$r`_{}#G9Em01E2tUJnt9yKhE3CG3%HDwl=Qp99s=kg
zN<-Me&hG+lZBLYHgw15ulf#07%T8>sj=OZfhv*MR84Ri8WS^8~sjZ2+`cJ=2aR^0F
z%t?k|?b2<sIoCA+&PHz${KyVRB8J!Z`*$T+Z(Ch@dV1Ix#(}b48XBi5Wj3gg3%{V0
z9RW;hIPpE)#Zu03;lcgvN8dgh*8iz+L6<u%V`hJ)K;41a8!03}WD++1PSu_D5E8Ys
z4ARakH{A4Ll#1DpzLacsKi+{v{7<=)0Gr1KHB>JM2eh@gxViIP)-j>X64xL$LfA-y
z!4J63Xa7wH`isLL8Vg$vh=Uzd)_f1=h?Q{@g)|rg*>4D&91dpn%=i&5ARvm441I%&
zm9-rlk?pa#k`i%DTigw2XXilKBVDJ#Z?m0g$Xvm=jJ8)s$yp>tIu_%_tlEo*JzJIr
z%Mn=h6c$@udiB^B^PVjWD0ne{`1lc??qsDKeoIF-F$N+y4I7&}xD&6#^(3?IEJg(X
zr8&(M^;>>4?ZD|c4LbbJdKgJ5yN!x(Yk&aR{G~^)r4m2XLZ_`GKV0R}TWpnd0R>5V
zB9eiGut>cXect!k>&O!_<ijVsNi^VvzGBq6zjB&HwM^EHT94RE!hX=3|Mlw^R1Bbk
z1~svF*W?scRLH>O!M}kM1-Qq>YFy^Hr~>(Qr6u~@P|*A)9d-CGr@W43xnJ1WConB~
zW1}|!A=##NLL$Nb#B44$FMWXD9ITcHHqd|1ABdt>PnI=buFQeb-}O=oG`Ly9b62i(
zHC_picymyOscr{cAsRhTPy?kts2<pCuNb1BAV_Af&%UbOz@VY23Gr3X(9qCjXb7-<
z^DA2x3<_`x@yH1g4M+Hei=IB*xV+f|n+JJ7j&6KF0BJi;W`2H7NeD@_U5(*afwpXz
zeBxurX6j+ezxp<B{-bm$`#(fBh<g84*8Er0`+xWURa2m++Y^ljN^HJ<{Yu5mtoGvg
zDd(wJq}I9N(1qkk>i0Gri20{>rjw>2#u-D^O~;{2D@(r`U{@)Le|;?&x`(a|411Nx
zlLZ4i?nbU&Wyx%6JSttkT9(ayg<!rX7jM&sTugs^(<~KWbQ}Wz0EQBLhUkHWoI?m3
z(>qwmv2^%jdcq)JN9lSFqS3I20Z&1pj2kjssP}TKVXszu9;~^y0xopkolR5Cdy60w
zRroSeL>O{gmKpLo@({Hg_+H_%?hJW4z-T>On9D+5qqSrrE(zd?Mphnj15qf9Z<n2R
z2@DOL`l-lf^5?T5F5fiC<1K#3Eew3|ggG03%t`-xpU&B@mc=pmw7@Ep8R#a~`*Yne
zU^p3fYRiMbtja_l!?Q{6yS5@Ip!MYmnso4=+PV&O@uJV4K(3FZ(p5QeaL?@%)v|5&
zP%y_ikDY+{(h7M<22`>Rb~nc%14_1?Y~Jbfzl{zI2za0_FI#;e*-A_D*NEnM&_)=z
zjROA-!<+ENckBOu`@eMx+Lr5Ep|IO9e01o9l=&co0SIOcPPi)PEwXfhK~*_5-w<?L
zYG;~Lz9cETw}1xQQ&Lho$H&*&qxFLJ9HTX%;nibQOD$xuf>G+QA8=lWF5sJ?eGr<K
z1wpMU^G*?`fgqKa{6l8JlL1@GuVFEpFN0YW+RtkA6+Kr?lJ$Vwz0=CP-<lxNSsbl$
z-t^6Ra~JDwSJ-1bSKyjkOM@+tddow=-5v`TD1o$@LFmb`Whn6A!j#q38z*gD4rnut
zZI8!VtUjDa%=S03@c<RU4O+ei(hwl=0}$9GWS}GPEX|ujk=(b&X48`ROI0L-OY~q+
zL0a$YTOr$d2&HuZeo#&8G#`xO(G1cNLXx1)WM!J%e2DI{yE7l9+1CFUg{}U$PU-Si
z7wPGI6MysV?$=G29*rzAIt=&igzqIb<0Wg&mjXjVzG4box^=ggKg<o3q9JZ?@b-T(
zr-xYIvM%J~<8$oz@iUKEYy-Z^{1GeGyk+yxC!pnRtpK3aij#?lr16ZML&a-WnK($)
zg>1$YmP*Dcx^r|}LKx9d7`YiJyL`iMyy_WGE>xjhiU6%-@ZQ4$-XjFu&%abQv63ct
z5cn;a{_n6`(H+pFsE5)ZRPww6<?uId5Uoqdb%YQ(g@yc0nlcI)jnw4XM4%7=9k3es
zrph~&Z!MFyqt@c!RsJkGLQ4qdZ0-HIq+!3gSeNZl|59*)B`{#KU&$vREUi5{T5V*b
z#}vbyuoK@;7eqr|SG6;B7BM9-IK8YFo=Dgu`*6o_D$!|Z^kbOpSZcf_@6s-qLjbMP
zdkiY)el`;{KwNBkkZ&f}z|7)Y=Xe^z*wmjrduG#v3?ca{nM0fzU}R2CPAW!5WpFKa
z<ftJ)ih1{L!~dVqfL~cwZgxM(c?H*18l`=Tiv?F~^NmhB%Ge_)aSF-Gc=XyuKKIsm
z)(*bVnKd96_YInsAY0qfeJ6wle8es)`W6s(KEz3OEe*J6*0d7u#v@d2mIDcc^%1VB
zLD%yuNxj)gT1+UbOfz(fBwRNxBGpV-ed8bR<oR^Vq9B=x`1BEmuuWjfG*Cr#I;=kA
z_0m;4(RvnRjHPYNaMh1WT{GU_i{z*fp{z$=f{<hb_Q=-qusWdR*{)1_ubmcsxWL7w
zvNJ({ohEJA0xLE)zCGrKUtR8nb^*%gr|SD%l6-l8+eQC2OFh|ZAqusnuaH$W7CrAr
zU?EZjfXto?@;Uf3`*S(K3~D)J%9qrOhDw?1CS26UWS@S>py};4X6^#EzX_Wz$gPJs
z6$f3(@G%EbqO$gN3gNr&p(2q^dq=wC?wAaEeX4ET>u4{@)TI?G1Q_CHhUNui*kIxZ
z?B9`DU$srCUzc+x`Oj*O8Q5nm<laz-Mj;QYt?v;H7+w>~nK#2&b+hQ8Mn-+~rUx5q
z(fh(zRq6+92Tm@opPvn{qu%m8tb@{8JJe2MMa)iLx}SBin+$S}058GgZ@F;#tbKhR
z&t~iXSucr$_5XA~yBX@h1OZ`TX>Rx>)G=aW8!(x%%tZLr_9;awzBwWx!)cPe`()yB
z7sa_-E2~Pl+goz44Yt37;vG4wG!_DVo_P<yW!Wq@s>pIs1?()iz!PkHO!3)&FHp#R
zzk1#cqvy7G1&VFom#dH371=x#U@izC;u68{F8y<~HpeC__WM|8;?EIr*_#!~{Y>eF
z>ve06#b7#O(f)oX>8CF0msp>N>Alp-|97*bz-B3(#=)X6Ni+jAg!09c@Jn3qvj}}Z
zGV~sP`2sgLx1tM_=C`4g8>GVn(-^)FlMN1fq>;_5^==hFkPZW+h7$hkPP!nHL_?jo
z7OJGzZ{9r4$jImp`Dh5UL<A(mXPj7&+pgV9cfsI1wjLsjT5LI({@`b2FrbsAsy)ls
z$o2`>&`MS<a9SQ}gQ^lK1w|?(JHMf=AwGYf51tGrd6RZxz5I?08U-;&R5R_i379kr
zX_-RdMaX$&q;3h>SO3`JfE7}2CpJSldKTI@BUNr&kc$F7XX}vNv&g%Te34VYPqOVE
z7>l0EWHfUzKT_&qkaZVV3}xmiB0CfPPe>8ifl3GumxqF#T~sl2LcsFrFflM&?0y>Q
zf`6NvP)p%Z+yOs|_`?5~${S25W=JReDOgZYMZ5x~FC;CKhQ2Cp5h|k^8;=lkn|Kea
zF`eX<>M-Ap0{4TuQ-HYzjj^T<xub>Nc1!`?b-KUP2i|WTpc1W<3=Ca?EalEWpv}Ht
z9aN|S9>o1W|CUmR07$6phcI1f?$LrJqn0y_6)dnEl*F`R<-x){bm`#3RgSl$Xr$ob
zb#w^fIC5ph`X8QtKY**Q6;ewC=*|pPmgi<7v*?-nA@`Cs&-!$SDHM^QLBOxypO%&u
ziNh^DbS%~3(z=3NlL)|SWK`5wK+Z19m3UGzvgRHmsH4BEA6?l8>O_q7WtgU~F%}IB
z<MS#LCP*nCnl8}fsnL8J9`4hI`FPEbEIBRBE&IiQ8wTKo4HAR4G&0L!`e<=~)3J$p
zz^UqJSc=zB=4r}Y0KER*X1oD1IZ?$o1f<YI6cqei_z5ci?6OlmhTI||QDCgD(OMZA
zeozaUzKAdv)|zq~Tj8PsIzjsQ)(H$W41nJN|K6tFY>hH%7qL!piz)pzI0;v||6Wk@
zHjA>K-pP^ZFVjS?FR`TN+QhIaZ$3YORbEpyOl7uBtzA5MepS5n&kTi#DSAL2GsW$+
zvv{)WI_%wUgHj>1hP~)n`!E|4dTWw6b*Fl8;#Qp>ecYsA-n`Oqv9{k?NjduJ-`t;W
z;U^cq{<wa{acL2*zMoj9CSgMPGB5Ew@9%PHUfKqGjW_U{`8!yiw101P!&nbhU^LAD
z5ZqeHo$)`6Dar1?gRftLultAim;_G8_!qsJbaD%Ozhj&G&%0;FHlIg4<9OA68T3UA
zhE)ib<ZDMLB%xVa3<Zi+CsCv3E&Q_Yz_p4Bo77T)>MHBcxt9h9IX<3)$E&*cro#%E
zv{K?Ty5FE1cK@Rgf*+rlk^NtMiz6thP$h^UxIlGW0X15c^#%e<ZMtcyv?}2)Vcu1e
zcQ)O&5dw%e)DR>?Pim0~G6Wo5cX7Y(qLR_01m5KiEvEUu!bCnOD^}Q^v8jXwPJ*e(
zWxk;!03ID$Y0a5R=lH`M{sG4Revga<6OR7z)g*d;%>wdS(l)dv?%#0JgMd0U7y8gT
z=oLPQ`|E-NQh5HF)BneBI}TVRQhM!nCXt>x1ry{8<-uschP!2tU`fUl_a$51p`As3
zRy3q5Q+pjkhwajU1XP~H9p<8PGr3_(#d&Hd3{HJUoA(Cor?ZF}g{%&C(zil*1C(_P
z>9_%&cwWW&kFq|LKNcL_PW0RX0LC8SU3+z(*u<uW?_A%7E4&FBPZg0|ugr8R43b?G
z6!F$=ZXu5GqF(}mch+R>gEapJ%Kp1~8%g=rAwr1TMf#5-NNIfWS7#?cemq~fPR_4%
zC@y{f#ubT183%VfV$*Z&;t`Rv@HcVAASGST{Z&O-2n@lNVrIWMnJN6IFG%*O95}+W
zU;y(E>2DiK@lj)5L6P@Yis}v!8v=rY%4Uj?J~LEd*TH4oQ~3foq?A;Vx@YesTv<N}
zBitYeKo-em*Ctz_+fh1UL`Xz*f}EVsuMc7@?N!bt`TWwv4}mR@tcX4TP*g9)GKyL-
zfZt<<xsrv-Dzl`00MujwfSBoP!*eGa)Y<4S(%}8q7BaoF1oe*Z=d*Zvm=(2QTE4gg
z9R~;og8F+u5O6T2tzk_W;V>r4MHA@Y+v=xM!a}^WzqR+ba%7?+-c2sxHKDk;GXM7j
z_LvX<i}v$Wk2YGFr)1?<ncz9XYQ{u<zz}S6u{<3S-c?umeh@rO_>v`c6?TT-#nvco
zPv?_P;2-OdU9x6}{7rol`Fnrm%o13T-+O|Z$!NBrI$cQBIZxo<yc{nPICp~NgNG&^
z_yFzRV(X6A(Uv!0ccoZSS_}LjoQc@n8_Kd}``1OD5GdCi)a1)W3AFIyYw7YJz#|)s
z=WOu@dcZ2-*V@lTK7ZJ~t06m>ET}oO^Yik+4d`iy(%X2P_+iEkBWkMt4D1ntzy2k{
zi{hOd>wMXGWTv4*Tt<b|G3KfL%GhUwU)&#_=b^Fh5D3q|#DXOYX>eOmb24}Y*G(1F
z43*HVb);QL^wzveXPr%8M4}jwYkuKvv_ku16Jvd@>5mc@p(c`oDjxAvmm?`bNm-*x
zSRXvv)%s<YYCHE`dFBh1o&+k#<m$^k{00$_+%9<NUeDtkTvttAup3$WSxx*jSgNM5
z?U8JV`fW5%Yt;32k&*)rC20zDQSGG*BMY)vPeP2PUCi)dxSLcs;ZK=rg=Sf~1bZ#;
z-w2uQ0GicB@;#IT^4yQZb|Ds!Dd6`bBBBTvP~9l0yXr}~+oQ>uOlVDtULr$<lOwG=
zsP*~4^?83$pV7+${eiRrOFLX#H;nT3gOhHReS!$njH58h^+~_8yq124!S1zNrIOE%
zA-*7rfGKz~sm`b2>R#5cY{iqihN%g*ezoi76>i2gmC`QR|MiPpG4DFnCf^_t&?h#&
z1JV&3r6^jIK$KzVc3NCA)qd9A!)Da$ZxO1{mXa_g=TnugmM*-)SAF(Xp``xSq#oXp
z-ET~Buwyb2-F84cbuGs}ST{R8?}6<JaO7_|NY8BgU<Dca$X<#0tHck!@bxdWjS-j|
zAG)oOHUH04j39>Q&&Z*S$LsQarBAu$Saqggt{4M!s)g4PKoOuN{G(CX)3ti3z0*MT
zn44642dd(X8YFujx>D3UWTtUapE+5bAc-P0%6T<iE$2mNq{gs6eLL9Q21p*0x4~&$
z!K7BG5Hwz|@xQuNT%c)iL}N`NNSw$-l_wZ~s;sf5_14lPWB*7e=d%2f%o9G5q^O1`
zJBd+Iv=Nb!09qh70yC9&F0s<1g6jTDVH*lbMr_N@xyZ{`GIg{`0v<fta@V*XmmpBE
z@2&w0Aof2sz1%g}{9*~$5?<)J$^J0bXEDyO`%xx&HMzB5*(XnXS}5sv*U~0CadbpP
z9Z*99!|+vlve1A*IBO9ayEI1^TWP%!0tVJW{o~&(lw)3a`qo3d$fKv>tW3Hr=QO5D
znaUc!Pe>;H#{a!iLP7$^cjMr&unQ8U8|7Pc7_xJF%=Sf$XW!3PtWPHsxQcxKE-{nu
z=-|E7%RcrknxeDVdDw2Tjx`P@B>J+1dTg*xP^Zgk&Yo(v04yu90g`l9P8+RCk_`4;
zqiKtNANwdVt=54Ge|bg<^?abEy;C*^8$daURsVE?Z+Tkg)l`c@+XXJ-X=|N|`9qC)
zRo^-_0x)xnY3X)(r+lS1O&B6e5?O*Xn1d>r%mMb$gqM13b(gAr%o(Xh4`mL-oOZ$^
zt8(54SWUnsS?={6=jbz&<>86@+hnm_?h6YJ<`B;R$HRS(rsz0&(<m_$eP%BI7Qrim
zJ%Nh_CYLGePp6qBm|5>BJ~YDq=a#J-{DN~Hs2n<NgjG<v`kD$aEnMI4dq8DPvCt&=
zA-lZdCb*G{_i6vF2QnGiQgEe1jlg-y%)XX^G1rahx&2Ym*NoKq8o6_mJ+u+Z4S|t@
zbph#T<(<>4@vd@mT?k=icY0YUdS04o^Rn<O<>Z&*8s1(bOD=6ssu`V6rZ2`z25#Qy
z{}Ai7=N{pIVO-5_jMSFOMKHoT-bz-S7FMm;jp_C5#8O5Rg}DBbAIZ@~{4SjmH>V$`
z&~|<8S1$+8d#*ag;+WU*H|$f7)H7mb!j7A^Q`#2pOEa;5;~{2HYL~k0MVLH}d)eMm
zT^PWoLU3H(*<F0pOWJ#ErO75mP!rWV{SJscIEnQ-HzpscnFo{1_9}j~$K~c(j8S9N
zL8gK)VvqXv6G$@H^4VVI^<4c@L(6pU_SA;*h4b$XIg=FylXb<TPx}b!_vACHjP9#t
zLzQv&$A;g3l=wEwqGU6x<@Q%fG_XAHn9i>xN#(;FGA=zv-SeR~H{4FjvQz&!(b**7
zt5&p~JEkm~Xb~tl{^?Zt>B#Nv-dgv~$(=3xd1}S-7*m@YiBIhnb2L)jX0|DBh0c04
z*X`9)hFyY=VLGj~^cx4tkD3onU}xA$dvhIcClpuLdxG=UJUr5FkEW30Oj(&xT0Td#
z(iO8REomz#w;%B&QNGtio=oECPUIJ9hL#Gs=8#W-E5BuCRmkmI|Iz|p=DjVM*M}GP
za5s(e6rA3F?Bkj`L5e@(@qX>oZ1#7|xm6+4d4<Lyc{L|B?r$67?Mm-cGZ6APXee3E
zv!*kiVZQmbjI@sO<vh*1LM|dVAF7JwVEPCx%V@mfR&r)(Wsir*>?c<YSu<sM4;hE>
z{^|8&FZYgUYeLVFHkE99IV-*D1Y2zm5nemIh;FZ|YK)vI|0Iwn*7)naItkNJijar)
zrpfTQvUPV49iORi%??pX72zl2Xe}E7DKG2X;$!~^N$>VQyJZX3>5jHC2?dw1dSNfT
zQ)Di<*~&g(;+IQ8#p=3xw4$0F^CY#C$#b%piHDpuV(%1zKRHXQ)s-w;y^j{+8uYFn
z$8!_*>p7Dy02OU+x9k-$)oUQLF4oLt4X>~EmVlr0<-LR#k)-(PbQ4`Y=w9TNpV)O$
zyWk*lvDHc}X-4YfXi4rRtXw!9N8mh8kx~;c&VK39B(aV9625U&213cLU2W=_w~b|%
zGle&KASVk=u28S%4-PX`)X4u5DsXc6MO*CgVy}cNP1E<C-Zcp|O*fu#t4<>@&G&4_
zT;2mzFApK{(R*=kO)A;*2@PUmsUAsNB2}eAqcnAcMDdq@y{E>pwm(MOCIzl#GZv7_
z8NH^TK;qI!6^)zYyCz(6UJoJORaKlYgwyoh>{~6*<lpA^EPE~9xa^KiZwjkRWur5U
zPye6~_~t=bgs`!zvhE%BTKrh7J4<Kfm&4{fOj_s`;>W$ChFT(ggz6z|D|k!euF2w|
z&KvU7fO}~uc)Vo#1ZllwOqWkN$?TbTj7xIlW>*D2lWm`9*$`w2^x2EKiJmLnQS*?E
zrEyDqDQf+BSi$zF*?Opw_}O+@M9heqU59Rz^Zq{HFC$5p4pEQ2Yxs?IPr1Vjv@@r8
z3N(~FWf{|2l(8Hk0mJO1Y|Iq;yJfzU{xVejnKr9dTrpkN4~#ULRCS4seVUF!eBzmE
zd&#l*kL3$>%CaOy-g093-(Sm765<J34)0X)W$v@6csQE*#a^>ct()DT4ZXlMF1^UP
zV9XFYLh7qoZ}VVM@4{#e?EuNp%ahIJL{?*XFNT`({;jIzI>tWE1R=4y_2HzWBD=lD
zLpDMSQM_2b0L}TGWQ6D6f8ftw!me=NkM$Ja+Uv`N5ob6jv2TQO9y1r5X=RtJQwbd2
zeP()U<7gbqXpPtFE~>fe^-fKP*tnp!IB@AKT@TrJiKgj6mb%zd0;c=x4!71vosiZ-
zOMZ8ZEjEwQD3JNV(|>i!1OUe?-mX(Wp{(X=EU2$%&0nUd!yI-CccY-?V}_xhd?-&z
z`P22X!gj)8d!1Q9kIfx7v=6>A|J=M~?c%}F+v92NH5mnO-VoyX{eBlvX`H|e6UO*o
zk5;*plAmktV#Y(FIV1Ji3de?9pKiZUQIy2?fL?`rS}ps`&OV8CN?p!@vc%Mrxo(co
zX+7LGy3G%Hk4I1bxi5bAq#EI$+(r-H3bK-_<NcFVuB0W+jSj8;QJSBpV>nq`CO5Gg
zYkW*y!Q8E6xs7B4X>ZroSgddTOiG2SJ_P6ywHK7#X`g3et4b+8&BOKklM>Xci$*;M
zX;393Kfmc2A2<$7Cm$rti>v8VqKl_=#5O)<l@t3%J7$wDeOG2!VPoj#^Ghdd+K*UB
zw#*jvl%cORm-An@6yT$daIzSbx9F^(%vzMQN?X-BBmUWY-0Z64OI@G6hD_==`6n%W
zsHT>et=jz$ysZ4(a@5|tL>srKN@mcGjWlY8xAro&563^^SYT84>twX<i@w&kywusW
z)l#3X!{JNiCSFUh?LlgtQco$R={!4HAt!gZ^UGaQpLz+OOCmSQ$`KjEW<zOs@q@3s
z=i?`+72qJ<R#PJft}8;B21>?uGOOrWkzCtV<-SMvl#3c>y@iF@0%Qmp9BuI5buJ<$
z7n@wXQ@e=M8%D<XuZ8}5zdk+Wt1NSRr`6e@=9VnLVH627V6HQ1z3}xLWkQr{7M|W;
zUA{VO#Q%WD;&IiBE5q4_{cDL?14-Aa!v^LL5`{inB$dZ3e@UwEwf-O^BUNO25ZF+$
zWhb6tI+!MUa4^5nWG{}RklNy24RhPI)yjMzIneFHefg~2QKd(3o><`c?9$?Xtk4~a
zgRvyG=+20P!%ft=fMESEGcP_b;|(#jzQj-f41zjv0<iyV+OG6ikG~cJHcxewtL}o2
zfol0So6+OA&Lhn$QL#I=I<H4|mMhdR`?$HRk>OpvVopf^;q#+sYda_+7m$_2lEkNs
zEPIWIrq#}R2eXN15KuUU`Ljvkjynn1__t(G;wL|G=h>GO5oupBYyIs%IJ&mPwe2Cr
zEdO~%G~h%_*$elJ_dZc_Tr*UnaoYLNzwai^SR+A{WOd81j^o9{Eq{Dt%<8I|v#}t2
zG@6i9Ezf)3d&G|ZXrHv*TI1)kT(ph;wryVKnXnjJkIz@JvBD-~(9eIeGExhqC}AiU
zK&j9L9?)GQY2_3Bkr9hy;HKwC^46Gf75~|IgQ*Uvsx7>aU8SkWmzW;7e3(i|MQ6Qg
zWpS6FY1_>|iQpF@$80wTo+$HinD{TkgQFVZ2?3o)@~^M2B%K|UZx~_`UpSOu|E;Sx
z{wCMl*^F-OC&y5QiZI>&{wZ628ev}j{q^%7BVO3Wrrdk~fs}Z6wCeO0je%kJGR4Em
z_bzgU$=eQCkPJc9#p1gIML0rk-Te<vfVvG?Cbe>yv?b9G4*t;3OovB}Oc!a^Cykvx
znx5@D_7-pFHQ$Qyv$R*FO4b|OP@Ow*RDJonGnM@_hW6wb(@9d1ULs~GF>?IgD)*>7
zmFDai8%`)X;-HEJ#f(xk{p?h~*HAJzFv+}PIJm|mCo@LJ_k&}J)c1JIjbAch9brp0
zHX<c_zm|umz4uxyO$W5=hR8RXc4f|I>fkYJjuYRhg@uI!LN*SQpvN`w<NZLj2GI6T
z_}7o_1cvfgsmkll3R<a)Q{HMm2;00KiCMjUtz;N~%z3-l{x|U?sqc+SfuFC3`j5(g
z5-@M64s5TVo<F#;E&9~uhDc>&+jN0e|IT(xmwVAODfnmFB;C)K&&xMt_iF<==#N$^
ze!EsvA77~5v&H1U#T#cAqx{Fm8mkZB8sALLkG8s_@yfEMRab&ruJNs0J`G*T&s<Zn
zc?X6H*+Sfk4~rUE-9r3XUB4GB*p>!e{=q<$wCGow_My~t!ToSkN0_c%yeWNQWG_nT
zW-i5re6szI&-0{pXGt4RR|>jh7>>w^y?CyDUu-uc%W}g+a35p6?UGAga((U4ZmARP
zqC5Fnjw2%7{-}D6Gv$QZ5i7>3-NoR*(qJMfYjuawHLz)l|I3io%W<3(Z?S}YnNc9V
z>JkfK{eaAv{*-N#S6GR-ZymeM!;u3Ymbo;5Jj(#&%a@-l0gm5s;~bSAy|dAKT}6E>
zW^^IrBy)+IvAez6jzfnU@K_N-+Ru}AK%-)=ywVGWDTJaV_w5^^aJgzsCw`WyUF+^^
zvm-aRxSLm|)QFwlJpA3rBtu~GiiLUBASu8}Y*)dll<rWRfvD4qY<hIsc6rrpyY!*j
zk<h@hdQ3`k?S_M(+xkxa$wtApA##D-^&_7G9<w*jTVqCEr#o)$dPt%0B<*JrRY(4X
z#=@%t7B{)wtpizCDNolmeXe^z<Nb)r(_H-ZS<zGvdp9OA3$^X+(K{_YbeCRQ4`@0U
zcI+<JTQA_(TMMm*alpV@0Xn8zbDW6THDK9bMa+J2vFQ&)PWkMee)yRCPvpu#dkx*G
zRA1kaj^q)sVJfn5C0_Ce<Q#D+cLdJG(o{>G$euMgDpg87Vs0<@@?-Lp4Qp5xDRJ;|
zyNU63dt7&<dy1x7j?MZ>ok3ILp^SRVstDes7d*EuIbl0RjDS_x)QkT8au&S^>uSZ&
z@g=5{ji=?04|rL*UG|>PT-veC$$6`G)iG>a2=6WtuC?!#YQ<9`e8p_Ym-r+i1+c2x
z;YMhVz!*i^DL{$Sfag$^t>UZ;QBt-}^;zWmgC}bAem3%nBsId}P>D^J*on_~e$F&e
zqmP0oZ;3VDYOB`2___j}e$U!3iX>Zo+<`#>?Gs)uyRm@CA50W5>1%W9qpjs#Op6yU
zg(jCRt9Mrtggm9#S{!*sE^tJu&sFC3^+0ApwKh6KkZ4JHom(B(3UvUpzCs>o#7*{@
z3y8+7xj@k@<<j0pi(loL(&(M?{9mE@b+J>pl8rhWp&Wa>*`v&t9z0lKdQ8wYgo*Rj
zwRvEX9E!FIYyYbv<Nr$ka{p%!-9@ur8s>5xezu;!m%6lPCnYDwdl6K%z}i45C_bJz
zlZO<jZGc0>Owo9wm}ec2X>M(u0MRXo8=e&O200A>gNF{45<ZXN3t#H1(^(F0EUpMV
z^Y`Lua%3<P2W<f8Dc)c63l0n7S(ic6@!mVf%lk<osot{q@vcE@s^d2OzkbHm6{@=V
z-MI7L)VQ(i&_Xf>IxNsNKxTX6!+-nH;jd6(In)Dqh-T5v|GDBH19e~MLsNo0;@X1;
z*xXDz<w@CAq#zv5q4*1W+rGZOAO@HKdj1qN3^}h{q4Ne=-VfkxFE~nx#=jnK44eMb
z0hB95S$6*X`O>PD$3+(J^{YLhk46K0HVX?rpu^{P^f@g25kgAazz+pJEGhKGOn~bO
zb@>iiV6}!qae31e)K6UZ@xFybBWy?8B*3(gfOb4Wlhgw#sZk?E?g7w$5V<B$87cf<
z5D*=o*p=M1liFJBZ~T``70^QhFq#o{N%b?58eo5y9PZA`c#)PnE;a+Vli)}^XRY%s
z@Pj8Gc0g0xb<4=l=+gP~KGlbtxo|g{^1*f%rvZ6e+x#BSxt`plkBMQjyXljC1S^Q#
z4{nA$7&x~XprB^-bR|uu9U_JcbuAD{AzY4~l7^W3Q>LgYEbu{p0bL15!q6FK2VuxK
z@QD}tz61mPAAZAPSvq+JsBE*n1s7!8wkGl#Sz8?RK|lQ-k*F^G2?xq4aCc9g6-8RP
z2)Par#KTfsE?752b4J4E{`q%**E@M4gcbwpLnWXQ{i*hn134-iNT>{cez<``q^>VW
zC|wu#0x#eUdh<;RK{)$hUgwYFfNjfV1YI5;>}eKT>H@u@K~r7khK>$1G!l*-JBC^*
zu0D9J?{yFj9b{&2V2}&L<RcQemO`N30#5|9*8SKDAwhT^?wBHyHek~sq`!ky79j1e
zRcJ#$oDPHltsokZ?hN1CEoruT44j2j=FJ2lqvMem)TbKGT5Uw_?B#WVh7uY)Pk(+O
zhC5yvIXnV(PW(d<&Gd+@c1W+2g92ccPaEhjU;FP2EF$7729SZ!T(~^}KDm*hUS00s
z-Y193$+wS#7I%Ukd(J1ld2<ygfKPv?-^J}of+z`SK)m1j^k4EcB2qpYIy#fvIO*8=
zT_9%VPJ(M}Kyh<%admjK$D$j>nM2)Wj)*9w4S*n2wtru2n5-|yg3WXLeTGhHzJ%MB
zMb3Ojf`k!x1K=-7Yg#x|V(W^GfLD85&~0l$sDS|?%M)RtedSgJ`r2rMR+!(Q>M^f7
zI*Z@ifRl3zbiH}M*EQDqL&2uvp*K9~R-NLZ!>GC4lMJHLDOm4KzQ?0~c7bH3=0`>s
z(mA^k#U|z0ikbo&--v=scc>*weo4+u$Q*mt2qx8L5~GU&GV^3-8IzHkib@cpuyFu%
zfdqlpHT5YoM>xrSEf7fZpxng*og%J<zr6Jr2}wLOp5s7KG;A)XTV^i=oI5n~qVTW3
zmwCTU`fz((uW`yew-N)C@~05Qp-J?zbg`&EDCH1nBxvvH>80{z(FO)0EU*{q5v$_n
z<ot^8mZ!knk>|Jq+9)x|Wu}5I<p_edYQ1k787@#NWEL6Fn2^%>oN_gYMAH3yIwe1#
zv-TS(F|ojJinSapn|#<f5Y;be2N=(&pcf$ytQ}y-D9|9l?dYl1rt&k>E&_sI9MhF&
z6Q!PD@~P0Cp91&6qe8cy@_A9*Wi6TU%CjgiYN6TL*#-uqA<w-<9eo=AdP5Ls>oRw>
zY1$NVh=E|V1k@R~?q<3u?>tw8{ZG&eqMBP^>3^RXq$h14qFr-WGh@|mpgp|uu-dbd
zpcNDpBRmCld0&7WMMFhp00eAl6A+FeqriZJ#^odWheuzY{e7M@mmgt)<hu2tQO|~_
z-4Q704JZs~)KX!^Q-Rcz3hZ!%#KGTHhA}qAf;IsQdf8@>EX0F6dL3A*STOY83`VV>
z2zjRGJW5<(*2x|D=8ZwBdXgm}Az{Ten;3pwHRxit0l}dSjII^<uckn{ZUt6Jh)@Hf
zn}p4cMHYOazqrF<pyVgQ?E9v11OoYZAm+z`*1eut+W7~lWCs|=DbUa)m;#2AC<u5l
zz)hb5DfkqOL<FRKSAf5?`P&XMIoyHF-a<htJm?gNSw#Dbt;E0$B?02Y3EGX+5NPH-
zxq&umrj5j6pCY}`br8<R!uHiE#L@E>8)CqejtjDR?dNH`z@N8Zv#P-h7+gjb-E^i{
zaC<2T;Tv?50&1J<_ppwP<FemDaAppgy;W(v2P9T;K+DW~FdrY|TQm-QdNc?Sg}luM
zO7gU=8X!oi0Z++R8c_kaLO55=p-y$~UsXhQD=5YQ4;6f!OS)XW_<bol{eE^F$Onpg
zOKd(Ori1KxM5&as$KN*IjIFCyM1<;~_M6wj_!-TE9XD7O$3xJJ1Fs$nZY>T3p^P=4
z9r(Ro!lRjrootDTM<hj6e?Ul-uJG4`0Y`}30CZpGU=zk5TCf87gDFrEErGQ6=$S*?
z(v3cd9aZ=PIA)=De?94FgU{(70vp%OufQYewj=l4_^AkYJ{!}bwXiAHfQ3Nm;%b~v
zfB~Nu<BlU?b*`BYb~QFmb{X}fmu>;BIl@TUd>IQNg`oykUtsw8&PQ80)F0r4Ue47m
ze+zOnyDly5a2!sLy`vOlBw)PXBGqM;!&qfhCM3vyfhO@A=!p~{(lE$*y65ceZT9Hz
zfQw=fd3q=Cx0nEI9XN%ex6q6R>B2*t91E3NI(PZ<<&FdIy{)y<=$Myd&lHP@NGN_3
zn5qNqtsWw$YQ<qMe^)4Y;u;z34#JfI0xmeWXhbUlu44L6Qf}y_i+|iEU`Ha7%+l`8
z;jrwuE9Uvuqt}p-1f05{zegwhDswRJzzTZ<u<1-urH=#U2Hd~}7*B{o7MPIfCVk-^
z`!e9x1|0jJBLNVS-U)_6-CquaKuNrN_pT1GF-v7-IXGUNpyB>e;bMm{l3_=I?M;JU
zS?$Y#0Ib*1m1m^rxIA<VcxuQw1~B;|Pk(p=ELmChI+7ZG5f;2w8q;4=1YEXA;5%wS
z3`dxMuzO^lL-&pI!iCNpU8#;OAhE+J8VUwJ+&BpW*PEb~oaszM4pIS%A(#I1ru&v8
zC{Ptq#kaj3{}cl<YZPb&bl5w}A;jcVAG#uu7x=wF9!JE_dqC<u19$@F&t!G%n+wHM
z9NLruVuipLpXbES6}O@}5rH8*z)OGs0_W8y{}kQWR*sE=OSm8`oIk-Nzgoo64>aGB
zrLuYC%mO$d<l@g=(-teKXFWNmuEN?^6a~M2-L~q_q;gc^TUUvvzx+ty*)v|ywZv$b
zYK3Nlss@n)+fI-|?TV9+F9iGoH4RPV^r4jf45|ja3`qT4PZZW<i}#23uhKIxC_$~n
zR_0LUQ%=n8zB3$_fR%LM1$X=rWOVm{6a~yYx|!y$aG(RCE<o50uo~cnCXmxe06Mzp
zspv8%xxt=aeRQ}|Psu3bDk4z1aT@X+P9Rqyf@wG+!TCA95oN+(5~%@tYB(l<3$&%2
z(1`@3;)m3s;43;C43&3E7h^%dB?;>~(xt6G38$l^tR*0nZ8-5`9Ks!@?&S%tHD+S7
zn3hR)e*REU{1iX{0KjZJ*v?Q7XVR2FOjCJ2;d)n}%_wC0>`e$Gu;_5WLU(~DAVGk>
zz=geM;n04|rif?+klsgdr-hb-abS(kx`7%I01RMl5SZw=G%%}G1$0k@7^XE9JWfW2
zkE=M?>PKQNK-SL8foF~Pk$n5)$#JM0PJu(BKNSw(hp?UGWrRk;;!`+h0ziOX<1lO{
z;4bQij^}dD_kn490=-gNz)Uai2{Cej0%EzB9~A<eKE5ziDb?r*w8{3of%Ll^>gxAE
z^)?G1BCrkS${0cc?owrt#*yy>_;sSB!<Y{VE5e)?fzulxT6MVk*UN+R>2c%a;HbBA
zHz|NKXqE<ILGBa>^}f3xIs@WL!ch?I?lCRK&!!!$G>nX9Ok$Q6a0G}I>==yW!XHEA
z><8p?R@a&HMj=9=Y7~J76NcR(;=Kba(F*9LqP=!$xO&*4udoTxcBTSyz<}u>FC2lI
z+|hmkoQjh=J6v5Y;k@#0dK%_O7Fjvr#r|S3SPV1-fz?l)aF{^FR<T8|FcB6oGM$@l
za9=1q2O1de1)c}41t7mFu$@%tgw2F#b|VuK7J9Wia5A@mu-FEPMk~D3VE4A_AFk1>
zei?^FMT4gm>CyM9+yOUPsfYG5^A~CW$JPa;^#X8R1#WmtG>Fz{XlbL2_QP^RGkpuc
zF&Kecd2S&ZzXJkT+rgM>w#N+&Fh+}lXI;D?X=7c7=Z=GibopX4*&K}lk;~u51tB|9
zQw6rF<kZ{8mU;K2LWD4&#+%A-;YaJculn`o8Tm7cJbi;;La@h6U7!W)Lzqmz5r6^N
zN*n?%?8w2CnjwRW2fSNr(O=XCjN?D%SF?nsNl*|6`ry=;dc+B*f_4!}3`H6k{vs3b
zjlIYkAh4nWk}d=S#V{`<4DU`~!C=4}>6yTapds2K(rpZcBg{aF4H7yb1UeVFZ1tMn
zg4o{{!KI3zWrW}vGH5A=9LFToAoJD~_8bOwItJnk?vi-{iQ2Rxh|U^H6z|Fbu?m>R
z4fj6XYl1^~x(dyE+L2RMreNa&-~)>OvP0~nEkNvc(tD*K5Vacwf>l-Nj4ZOHA{|XA
zG3|>NgoJ*Y>jNVi4Ytf1?t1163!G^bUkc|BApr0%`UnaV_S)+ow$(Y~28{I1YA-Ju
zCZ=a_veqpalz`-$eztxgNZ_RPVWky|lq0!g;rtPr)2E*R`5HUlrB)@K6Vl}MnAL4T
z2uVPoXlXkbhOBQ1N$Aa+H{)PNV}VT_8>8piWNt7E+DJ8!j=ruR6-3~3^QBx7$hq;m
zUZ1Z?h1lrN9l_xsosi~Z!7X;e`aLO+%Q)u%UMn4F*=}kGkh*i{4b)aLc3@}EKkPwF
z_scUa;7b~UWI1MBW0GID42u8-yGeCt=Mon{6f%ptAkPIoWAF(|N-@a65&pEEHWl5M
z!<|!TGcz*`oHNrfYK{H;S<nuS7l;Q!`R_}u2{LZo(y$IVM+BTeoNnA$?C)V1$Bm7E
zcvcWRs|b>ZASpm@#hQwzJ_T&&qO8AE`J@>*Sp*UMz$rpiIVyQAaM%~99FRko5Z%JJ
z{0>{Gzx522A;?z2^QVCX8YsByP@0IqV!scAO#X>m=zn}k57H$pNKFui;S8u;<PJ7y
zAT{F<6)pOMyPg&cGxqh@zl#}xB>I2mgp{o#sfU~`^PRD~aL^n|`NnO9oNETY{|AKI
B(Ek7c

literal 0
HcmV?d00001

diff --git a/_build/jupyter_execute/44661da8d7b6632d7323190eded41307ef7514e245c37c044cb00987aa2adae3.png b/_build/jupyter_execute/44661da8d7b6632d7323190eded41307ef7514e245c37c044cb00987aa2adae3.png
new file mode 100644
index 0000000000000000000000000000000000000000..2629acc290267807b975288950c284371ad7182a
GIT binary patch
literal 23142
zcmeFZbySso*DksM0Rus4q!a~2x;s>)LrO$R=?3YBM-h+`0b!9UC5klCp%Ma%5Ri~s
zv~+i!dHcTKx4*N`9($a<&l%^h^NhjED=Y5%{>7Zvysm5h!tSfdUp#;1JPL)nsHh;T
zi9+G>qfj`hX9?ghb9ozI;g_iEy@#$^jux&SCQr>#swS>Zc8;!g)=#dwn?H52c68w9
z66WINxN7C<>f|EE&29gmZ{Tu#YRNr({%i<*$vGzlJr@*;#02@l`5>KRjY8@5D$3s0
z_DoqG_3+egI%!$oWyuu2dgI!)YwwgPZr_tl3VnO?VgAKTh4qg&uj=2<4}E*~C4Qdn
zOvs@4q)x&4hce`^C}qSNpI;%8Rlp5;eq-~{)Py<nRq;@VqEx}$5TUz8*U;)xT8F<!
zCx$MWxA`g)6Vnq7h81ENSy|aki8xFs{FlXsz6}2<Yw=x&m)~TY$-#>ps;v?5+QX#R
zH1JxH05d=GQER~wdYOCe?d?+yL3n5I@l8sGM(Cs9eQ|-jFCrp{-oJmpwsx~_HLH!4
zpOBdDDho^Vs0qBRK(jPjo$%++pC^o3GqLEmZ?86-JUK&1SS@-5zMU;>Ys>Y?lP7fJ
zQ%$)Wtr)bH^4G6ll`N3k$i8t`Rsi+z|9VHIx1=qyZ$$7;Pfx!}PF`HOFZ+>PU0vO#
z@54Lu%d(kwbPml}#Kn`Rr_K2I`A6wrD#TB(uBw}v-547iTOqzD`|*QKDrS0SCMGd4
zG$)5uLqo&U$7hi$Gc=ak^hamsZ1=mnH&|GDG8JPtxqO+KG%0_Hp<6pUS-82Q6BDVA
zj*my_qZHz&=H@~Y5~!*@R^ei_Mn*;+Avc(GUiq^G`E$P1zUo&eoB4je;O|I2DwFEC
z0fT7nO09qsg(?ejy4olC?t>*V+DeurPGsGr6}VP7BLqus>LLrsl*GJN#wWm~4V;h>
z*qNRs!#ZH`-oCNDtJxLtDm8U^<&vyy<E@i3S5S_o(j8mpcC=I(QG)6Tm5Hy>F7OPP
zPUrm&YOP7?*w?QMhwShjMyuTLjQ2NYT<3f6rKP1|z^Mgo$XlWrJ?t2%s9H*`d#U-%
z&cfP@pytI5+~1t*EjCy7_4N%651*=>OLJMUWoKg2kr8q_=X8CIxe)&$Y75UhCEtTL
z)k3T#Osldqv8H>bt9oYLaL*@UX*o13?3$?Pkn<__>oa|~UpjEv;PHUdRKr^D^+qyv
z9*-4$VtTR0<K6Kt<fq1KlWtgI6T>fY@FznhN#I;yneD*S#n0t@=56E-)yqO}xQ#mf
zc1Pu{tZv?YLF8=n_?~RzH{YPJ;5b^W308OD1)ec~);ww9TUbnY?%YvOR=zGGB4RY!
z8q2DvqLO+089`K24PS}NEk8b&FR`rZJ)a*7fBW`rZ#Cew{nfR*Ynz)>+XF@(60-?L
z{_kuD^68}g>0m-9CnqcZybpg^XdE=fi$_3&g@wWKsPu=1kpGeA$!`5=k=N$zhM?NV
zvTstBOixVOgVdV(3eJedom#&<JdsN9w&<Lgn`wR1;!`=})&69#(8SEltk84)iG+m2
z!)kZVYWL+yczzFwX6mU5*Snju9XJ(xli{1omW%zLw-yJujr4NVQWGV8geog5J-y#>
zN?pF3`(&d{&j=?Dlk(l7BtAE!kv>~Bx!GgfujQl8r?cnJ<1P&(AIwRgwtmpaI4@D>
ze|!*iN_ghX^e6si@(L~;iq%rG%Q3|t@SdZrgZqL_j9i+V^433d;$zaK(_0t=QXK1#
z-^fK?5p5eTvu&B}NVXoSaL(Nscz^GL|NcyZuX%d{caC*$_Ch?Y(fVNAl0cKeme!OB
z987ascSYiBnhU>6t;wDdTzvBF`MFZNq1Vp{NpP{t%N@_pkyR`ew^NHgy>VSG;_B6_
zfuA3j7sFT>de3Ju?TR{#h;UU-lcsr2o<nB*LEgi!?cDX4PX%=gA1%T{Ln)r)j0QRu
zs&|c@(?<~zB)w0gVM7br_P;`-TVeSo3fU)R)WFnn=oLTDQcl?TaXq@b(#0}@SHPw(
zbl9Q#^Pt}s+kq%`sr~1$DmGyiUZSCCor;#uN2@R~Y2L?cAh9}|iFbQYUGf)f!laH&
zJxV4DrF8z7TMMY2cB&<U$w2C>JzmuVb}X<zb498HZHv;Mh-HYbNiWq3ab;5k-h;S0
ztr?iyn*IZ2hriO`FKAEoufWQjfNRI`enr^T{_kg}`8u@%Fw7d$8Gqxg5*K+Pg~nXa
z<7^A|f9?Hn)XPW9Q~AByT-if#cTAd3uQhDS;O(_9a;wRvH3Xzfmr2-s^&1>Wapv7d
z0=Ysi-MZwr-O>7-uJ=-<ex;m#2|MPk@ya3#K7E|)H_^FFRc?#TiM*zCyHk^su%f<9
zoqT;pI6qXvii3mGm#0_qgRkfi_JH+hm7t-a;fT}si(EcqF5~j-g-<X{n(lgfdcJF4
z3AbvhSlM;+r`IOFA8oXAyRMF<;$NV2TIgd-XvyqV(dk?G^=Z?9#-~3|?*=PtiT|-T
zY{!=zB_A6bWmhWa7^3LKn}24=d+iKaR?a5bw$;=ZnYQ$Nv4325yz>|r4=<HEcl0&0
z@}IF<arr2^)&vFrll?hQFE7#K{mx&oX@7sQPv)MWfV2U@ox%IhyE}``5j1zB86-a#
z)z>MTKDF(_bV;9L;7QcAwaJB&Bf0DLn2c(9U$ALqU!tH0PETiqSZE4cZROk-k;(>A
z?DyW&*(!eO>cT=Ei0t&cWTd24<8_j%Ndng-Bx-&X_dJy+FiiaO#|pVc|Kn|47PXWg
zj~#1u@{gHs+;EzS*CnN=U+yvd^t;TKjC}e9Stk<{v+El6wpxmahLwT0w-_5+zL8b)
z=T^-6R7>UBw+mjdkuH2r7j<EQTb1ChKjQnOTaXPgdTVJYHX>qE^{L0Zt|Ft@_u}2B
zTlLO4?d(6`lQaTWmx6+VWaZ>GMqIimJTXH#Xb4b=(g9MdHJilnsMqekAb&*g>dl+x
zQIBy|PfroZr21Yn@pglSUyH_J0J>qI$9y+cuL#+NMn{u0Cz3kuu2ip*Qc=k(D4Z=H
z_xGvW<%1-blkT6?97#JhHFfv+VB2e>m6d+`aCdd?%dkVngU^qizj)D8U?lze^=s7H
z#>Thr-=95ye#S81c-xl>E1~<~0cD0<B$I>$5<&ATCeJ@8FuW+EsYwcV*w?51f|&kg
zhXp$yZ(C=l#nIk+-zVMZz(ACk>z@Xgc)D#!r?Ur(1vzk?GiT0pLmH~vpQVLsA!`Cv
zX7j6U_kha1$_c_u)ULRY(3?{T#B^e=p%CdVQ&THI<kTy%h%`-xYpqmF5x>vKSl`{v
zaa-*7-J1xBI)Fhcbe-2U^qj!A6QUJL?pPOd7%C37EvS9d&>#bQjatO%Y6!_`ZHlF0
zl;q{y-<<<K`WY{1)eaJsaCt6JayX52wYT%b_X(;?ZpURTO}ECf+_=$Lv-8`QdCc+A
zqa+-aM~@x_Rgtl(C2~Igk_f-!IRET7Qz!GjaB=w3TfT2Tyu3f+vs%j{CiWXiCw3zh
zKlMFE-B@^dx+54Qf3GJF4nE|!?dLF!;ALZD%l23uo9%z>DA?NCI{W8mM(~@NnHjWN
zsu+5)pnfdRu=e-TVA1yoTH#KZm?U^?_*k^$PU5+<XL)M9xA|a1_-TdgZmzq-@|n#}
zcHpZ&J*nQ`pG#MTt<X__dh95VnQDm^hQZ}?tlfSyRA!r?_r(s4=C_REZBB%jl37%f
z65rhoNs6QuPC_2)<oGbzq9X~NmxtV>k>7Uw{I5?5L$y90MFr!Kc~rEu<MwBh9WjtW
zIsgQyetuM@Vq^0W9)TBrSVTkyF=>*+5F?T?7|fmB-ui$57uXib=>aE0OTWw75j4=;
z($a!F8nvlPx|E+vSDIu8tV-28cmCO5_*8)D$x>ETQ;R}N2h`zUc9w_f3+j2BU6+5C
zH5@{6wcq@0TY#n)cTa?o9ss<G9;@|9hVb8LH(oc2#J6ln-T>*ks7*0-euo(TE(z1g
zsVU^^z1EwkB6D(b^eUfb!2o2)M<+qxO1gYqE)l{`Y)XpV)2B}{L3o5JsbX%J#xSyu
z{?Cs)Ai^T|sJgo{s_eFu`e`Jc|8lPO&eD)6Kn<e%Sl9=WC641#ITGs5<KuH5OIuao
zS~wW^+=gVn<9MA#_uJd|R_2fe#mU*>JY4PJ*mQ$mv^mjAizh}@{9Tynu?TD1j~_e$
zV`np>rJlxRWoKWJmab=tr7?||A1Fwtk??e?^Gkia^PNOG5sNi;*_dwijkfLk5aV^c
zJrK#eli3IWJ~J~j&RaYnARsm^ZRJD2pLZcDA;k0%yv><8Ikb$7jPe^#^DABEl3;>G
z>k1=zS=iaz_xAVE!565K0GM4#?y!JZX9-)@_yrM-<{y6;9E+No8qDEp{p!v3&Q2jf
z)E2WCbX4)HSC{x5$7=5Enndsd+Tnx!wlrQZZR7<J8yUDr-sVz=(cda)zO3%$fP;Bf
zyu|DBQPb?)9O%l;PI3C(*x1;M#teR28uCLgDcFgOU&qFVN9@AX3QjdgvTt}r@Xr2}
zXB5;m@^h;z=1)&w9xhMV8x&7?O%wBxnU%HWXze>mb9+0x5fel+(>I)t->j~>dd0Dz
zb4&38Nf;!~LN#>q%LDfPAS~XP;f_S!XSrHA53KA^9C$kvT8@QASNv$YJG|7BU%irX
zcNc;c<r?=Z-vC+u@jl~#IA#WmOkwBEvP(Npo;i2!T-0GvQPK0@;CS!qii!%~soPA~
zuhY*xD0diDg4ihOy>*lCi$S$J1-1IqjcG+vQqqcpg-@;R?c$EKkb6Yj7RX^$J&p77
z@^YTfN+^a%v*{4f46B5vxf_s<?+oPPr~#9{4;n}ifdCTvDZlDvvSS@u$o_ZSo@l3t
zPcnac2rNmeo63rc?;x>E&(3c2X{oQTw=k9jocb3R7yoE$YZJa&!-L#Eg!@~r4K8=?
z;IgWvd?++km(Ba$+Z)TCU-6G>ve0^``06D_#xCXr{cnLdcu*01w_vyN!oJk9jz#l#
z`e{V)Hr3sSC}#$HHR^DFe!j7>QAE1Xj8!`Sc?56g=!D+J#ztsF1V(seDx!q&YuaJf
z!=B|%$u66cA-Z#+>FMKMrnZoASL;vxgQ`l%K5dF_9>nid+~Qz>qOL#RAUr3>vaX81
zwE<8Egc+*S!|~IHrB;{uEihOpPNsqg8E&p`%A5==t3(9Hr+RUw`>cq<^fWCEl^}Qq
z5KaUQ|BI!irOhw%kXz>FbJDr)Qvv+zOr0}i(v|(l?&#>4BxK)4rY><C<{0*ugW{9U
z53oZaLgM(4sG6B&W=JqIXURBr3_)46w!WUbwihaKdRJ+?g4AZDf)_ATo_=Ky@AmSK
znCmbQ&+-kb-`I{rG@63&2Xpld*24Mm6+6HcU%R@Z8U6QyCccMI9ndib92J=cI_n8K
zj8MaE0LrF1*j*(Vv^0Z6maT1@rSJOl9!wylz&mrDso}o*Dk?;~BQ7M!4>IhXDWVc<
z4R}z(;=M{<Jj!)!f5Vw!RPR6HHJ2JFsW?>W!rGB63`NH9aCL)AIe=iO@5rdAbpN30
zUP|o9HYV8#CEM1ybY=8#B@Mj2jknPMxqY%JoZftBXo$n0Dh_b?NMuZEKTT-%pK$x3
zz{K8Ym-mn?UtFYZzDpw6NFsgI07VE=K{7DR1h5xWE!+}wU;1%Tc%<Q5@C8LBr6*8&
zLS4r;ZbxHj?;!-hfJG&-VQ+m3ZqY+QLBV*YEgq99P6g|W;C_x8{lWHPOR;&of{KdS
zd`}kS#3aANm*V3IMlv#}-7z0-63MMg<9@sJkH6TNG=^R_v#{U;kVCqPR3=2!Jb_T~
ztwVl`O-%d&fYj??J_kugs6+1y7pS;y@bbpMrdkK=FGl(jQZ3*Bqkv;Uh=G%XymJN?
zU!13!ISgwOXWA1=+!i04>~{r-sST%HhC&&tBRPOFAta0l84z<_eq+EWz`2FqqtNEp
zt&_be5=zcTjZh`Fc65C1hK-adG4h+=WoeMtefjrHMLOIMJX)?nwb1tBfF&l87ZO`4
z<ks#?MY3%5^r-s!`YEci$6mPHsMChDiWI+{IhB9-54WaLme7`I6A);&mWLC7LV-Le
z4=AH@*S2J64<5~PI!2ya%=IQb!+Y58P;X}qjujR=c;w47`o&!lwBhmEFe9cDkpU6}
zSvRPYlar&P%`TNho}grhsxaVhV4&n7Dl3g@Z9=GsNl0h`o~QN45A0+(x5dP_;6A7?
zwGYw4jtsros-{pCLLg7??!J%AblHI6g+U(!Ie_etO3xA#BbWt~BzPgvdwYS`Z9$vC
zf6rv4YLScJ;uY<cGUraut)KEpWv*LbxOaHyvODVG^8KRlw7A^Kc0mBI=bG`OQme0F
zWUR0PZg6o$!SuwRBV+0Qq{|JlD>O1P3%)<<dDeSCXfYdw=$CZQof#}2+?E`G&E^Hf
z0Z%gzToo{>TNIt>9T*i)!0A@MKI(*}Uze0jg|yVu({tW;K2^f&HIyb-1gruJ3LJ;7
ztc&s_9X$&&Eo9{rj<-)>(h1Xo%3gDseD~OotDJ>D|NcZP(V*^;!3)1a#~V9Z$`sw#
zuRpm5d{rigQY=RMH%`Nw$uO-PqwvsBZEv3-&IX~k_}z4e4>g7F|E1WnO7JU4_crs2
zy&Ixsdhe8fxS#X_Vdj_<h(;7nWC@I=oi1Px7FBNjEd(`1&Me)0?=Us*{U3#-$C1P~
znk$Tn@h>T-`P76wRnimZ-Mv1YtN;GXwT4$r3oAHE<tHDstb}3_f=>U66aIbLM3)19
z&ZRIF4yQ8-tO5)FstMn$-U)Mdc1FP1U$zD*K>&`o#OGaLC#y!r9rDQ3%uEw(X6%X+
z>d^dp-QMH{6htE+mhz11$7Y;~X!tUFYFL;i2||Dk$g!-)^*vv6Hm@nIJF`ma#x_P<
z1L_-=t5+MG1O6Y>g)Wd*UZtcUkV|Q64`960)*lUdz8g%M7C3_i@_QZg!<9z{w8S^j
z&M!ws^dZ&DJ$=d-6BFaQGD4%SzH8WZm4kz0{1|GL-{p?#u`H@DIoUsJ<)}@}%;?N6
zr!tF)CBgQlBq1Rg^I4S~^IrV?l$js$IaFJcvhv~{qRN)FhG}VOeV-o>oVy$r8mB4J
zO*CkzFdCe*XrPjVZkylil4ga~x-wdg;MppVRW*HmIzY5u!IE?TA60PTG&D3(Ex>KA
zZ}qD8RydnNwt~`F3V?5BhX3iw@re7dJ#6K0*trmj<RO@$Aa{9sdcJz~ssRd$PJkFM
zeUD+AAq?Tf#Khjg!P6!R-9qne8|-SYaBglc5xp3Ba>s+|UwObKcut0~{sBmbl&1IY
zt@kK%&-g@iSWH1kK#~yDa3Yg{Zwio_x~{HHz;5sr;46S}Q-cnW&JaQp(gCvFA?0i?
zmlyV`Bnvx2Fq8t0n2elU7T%-?8KNzYt>$=V_y}0HCW{gvpC1;RwR#z86|ydvwnSw?
zx(5u#2fW<Jy_pf&Y2O9h3x!7EYj(U1tb>-~l}Wjiu;Yo0k!|0XD&qXjZm75^Ma22N
z%3&H55Jf|F1U@0jQx+vdaP$0|b6wnyd%;zZYgAobOZ7^vVumW5Gb$m3sTdo-rIGY5
zo#F+QX94TEnc7rSQ&VMithVEG`IrqnSqCs27dQcE^TS%@g9K5lSL<CiRAd@LBkYiJ
z?&3v37)1COgU=E#*`-Uy5F^cDmstwg4c?zz1{S14Re03Q|Mb{n6IN6*Aitylz&ufj
zz}Gt3{Q77PYm>9Yc7UtIZitWHvXc%<FnCEApat*U5Mn`EVFv-ojJ(H(yTTnwg8YCN
z;c9gU3+%lRKudgfSDqNvYh=iwKYX~k*&#fh2=E{o*r4P`Wj1K29|3cl!egj9ITfOT
zDN<BZ6GEfW!7HpnLj6b~MZ<5A2sk^L%E<Spr?+>~y>LoV2E4?zH79-`c4J??GKT1Y
z0ZP*HpJ&fHfGRNukc)YLFI+`mKLyQa{t{{`*rB~2b=Z4>(;;JIbbP~QV8d1QhY2qc
z=p<^>2*?crfnm|n!p+o3$)pAKoJ+5&F#6Xg-DKp_!sEWZcEevffKN??3;fzz8U0&K
zBIQ|pyw3Z9Ex>p}z-P~vbV>0egYo^vMgH5jZ)d}roD)?#eK6LA4%OE5iQo;7<mIL{
z_2+3`a$8vmM`+vEXugw}4yaUr{``qgiY_5b0@fb}Wh%l#1TKi6v`r{FMB6mAv?9~f
zjbd7%b^^M#i-<u&WW27E^Kc@BQ3Xa%6q0UTi=a*4kD8N%#b#<B&B>V=b671(wW*Nm
z71h-}`lPqI?`FfS!3_2E_C`iWM_>069T=%}Q7y6PP%$)2%i#Ebq5N`|v$M;aAFcMN
zD+VsKL*J!CFzPT6CQ_xY1>)ln;1Efpq3YE-TPRkbDC5wt=tict*5~x3eQmjXoH7}s
zk|Od`z^c2!%+iwT$|5A%3pcLL`KUsD$j8?svE8Q?bpX*64NMtiBFza%hgKLB8ej_|
z{0?_0^c*8hV2^OXKLMbKE_*?(16oTqY~HA1C?|V?gM7N`1Av)M+&!YZ`-q(Zw&_0*
zty_)<2M2vkpDI-uKsbdtj5>s<o|!qwJy`_s3?dbfBJwds@KN^h9Tcm28i;5?KpZDQ
zO}hDo7ybeF^)pwCRUQp`O@g5}+v9Qv$<>`Xu|q!*m(wLZGZZXk=ek2EhRnAYe(kHh
zo0*+OiZhUphN|4y0jzZi8_tc)i4H)_oQKKDZJtV56;uVCK~z+9++_gpeK>dB!<;19
zOic|wEji#g)co`nb*2*(3=J9JcB9tGEyaBnc7{qal}bh{jY^>sjtPXSI#u`!a2J~=
zhpSW{#61dKoI7j$g_1wZ>{ptbyRG=2_o>ZROKpRIpl$rv$Y}h|_|#^Td)+_*Pp7x)
zJ=qb}Ru!6ia%tilxxUftxd>?oxw<W$Jr`m=3Mf>QmMD6J6VX3(7|5q5Bw@$|a=)>u
zNoUX9(zYk_oWH+6QX&&EO4W4F?d?rP)8j?7e*^#w<-{fc|87WR4N~8&Adc+!&$H#m
zv+Gh;1boG(BCl43f_|{hPaHTQuF^UP0#I&+;1Lo7&5GXu#rn%p%VZ&Y&%@>N@D$FO
z<z-a|2Ztb$&fO$AIl1DeGfIF`ab?uhh+)*TpdM~&zRonMl+>Xumn!Z7)L7LIBMeZ6
zu=T_|R+jqaE)o%$fr26d`vtjUyWgc@00OWR8Ykr&A3x>4hlPZ&I<RtIWoF($6eG~@
z9s(8ETP~hlP{2*bqGAkuV-3&>H*VZ0gd3RcOuf(mCC3M?9Ae-(O^1rjLG~*Kc2F*w
z!C+~=&ISL>8K>3S-Hq<MB<sMb7MZtG%0*D$wy<D<aKgUs-?;}wGa86oarY%`ysqIy
zue!AP)}NnE4*an7$Gqm~vsKXFfCEET5fpm7fI4uO3M^r3Qv;m~tei1iR070`rWIrf
zumUz6cC1eYU8B%tPHoI@*Wim|c~@#gc(^I>9l%_reh(pWS?J3pt<45nYBo0~?a9}F
z@F5gN9<EeJ!=K(9xRGAYRZy~M`vEmPm7yojP0#aK%<)i(rS1=JAh|Y)460n;0o{ZM
zbNbFr6s7S0M-Iz|?0g{^AW9t&eLbbtS`PKc?hwcUKsp_`&v^r4hxA1U>KQ_uAuu9}
zSMc9uL|=hXI#Nc!lk&U%xsNd43u#F?Y2JTn2_VXP@(skH1ZskEFjwc()}muHt#A|~
z^8LI=g(!k+0J44pN_<j|6!=Ir7EZ-I`&yZ6qPU%F3Q9T1J(MVbW|SNcWq?INHZhDu
zmvCJ+&%1Z;j$q*;VFQZpo;p7tpq{4wWYO?GIRndf3hEaY4vq-;(lXhC`3mPLWavRg
zd<QEA(wXyAr0~B7O-QRrej_U<2SU>wgu~^og{OU;n5Y1H*4p+qXYYyh>Cq-`Egml~
zFCgaXZr;n9Zm^knEij3Esc9e8Qr1PuVis~LR##oDF)E^?uDz;J4hL<exP>6mxV<xL
zJ|_V)EOz_|(S6lgBNS*-YnSRnLo1>QP*5@a7difJQ~pPG&C&TyW+sZyk68IF`>{VT
z7*`iim<P~Zy4Lx$pi5u*<&7!?0UMSJrkp3aB){vr<|qxwznB}$%)v>5wl<ZxmvebQ
zy~g?QxST8S`n$`Q=RN|fFy+F+q<Q(HAD?N-5HK@0BqUNGL{^H^#oTIYZ&#M&gZK@v
zy1W1q^yJS=@B-W~V?c30ozkE4KeGt@)$JR5{@1+)|Jxso2W7ss)daM9NKGh^wn5wY
z0hPTPWX|flWFS&1y?;@Sce4|AW(Sb`&9J>xfgk~m;381&REXpal>6ueNQ?^1_j6;>
z6zmVWLESjmn#YrYd;>(yHQW9?XBRVgdQCm;g<ch1eP?{>qcuF(^eAHp1c(x*@3UNX
z&jGN<J#TOCx@4G3ZG-qKOAAmzGqbXsAz)(X=M^0sxB!UX@ECEHj~RyYAE6qnc$7d-
zbk0#4<=+H;ZWD@+^{<4Cg$|=)WB!NsX?{C;@Ozo594+F^WNmF7H4H?y0d)~vq9Un-
z+H{0oRs-~WPf#~#M4x76Kwz}40pJQT;j`?ag1S2EjT_HPO9cRnvER~0F7>|0H$ZnG
z4UNI5NJwmi{F$H6%^iZLo4lXfg3$*ZM`C|E7TMBJLy-dW2OzWyIE_*IB;>J3;|~P1
z<m3pVr4DX_9C8&_8sJDoYGF}NizqMm2-|tri-?x}T1l&`N~su;XMcSpi@AKJh^<4m
zQ~rNwFZthI0{{O95gW;WXWA)MO2;4sjreL!ER=enY+4V0;e=G{=J60&$clYV9;hbK
zr_*PlMtKh<fiL9g=OH10-en+Y{^wkap%L~hEG*1qti~&<xS~R27vD9Xqk*=tQv4F^
zu7yvU=@tjD0V=_`P&xDF@mUg*x%c5*Pk@zNxp<3k4=<5;<ctdH3l8fDO&sj8Z5`NS
z(kFY*PLJlK1+06XgR1bfOLCXTrtc;s%v7fG*0we#NlD4^j@*7c`#||X$3V-#2Mr_*
zY;#iaumDri|GnsIYHN{;>ecyHX4nD43QAZKY+mxJjyN{0L@_s;ppAbm`*y1C+i%$m
zGhS6)H72`X@2h?dM&MOini?>VVRiNFZe1!si*bSyr`uoS<pPS0*0c~Xt2h3w!W3-c
zim6P55y=n~4tuFH!-tu*atTo$3w>cwi_EbP7nu@5F?i1bB!*|v(dtcS;#|@W@?Ls9
zg5AdU2px;o`ShU3td$gy{|_h&b$5YzOAzM?BxLk`1sE%3zBk7ONULJt5XU^HE+RiU
zOZ9zsf_Sj^uek{ZzR15Q4^!Nhh(Y*5#aNb~d3uN^t8nNfE!lVHw0#jWr3v5wfao!Z
zi34ah9-kdM0wQW`>D<kD?}kqeoWXsnI86FiB4G&cH{&$Gtw|hj^&;F2?wzOkJw#V;
z#Sksw`LW{A1`-UCq1y|0N8qgrmGQHO)hd$w3=9mefIC#a>KR_@zMM!xN9e0T3Z}71
zIrF5BE$lOrjW+fI5phb}+_2-)SW?6}R(?yX3sZlx%?+{iE@;A5Ki}g6*Ra0;S=1%x
z3@bdrQz>&L3kFXtjz4HW2w`Gn^+Aj97&1<1oE-W!+GETs1aTwfs54r&AQm;vTjp2z
zk#Z0?&FLk?8z!stS)~;NQ|`G`)Pm$lcL{hOQ<i3SuL>gm1A_x^x&(Z;F=`EJ=@ilw
z`1T+Bact<yi5IjfbT5#{9E!8S$AY$lC@e1{TIN&gkenT=T>-H&!3Kl5M`a)jrU5jM
z2`>ACyqmhOkZW|_|7gY{C>Rey>FcDVwn*VI1zFiMkP)U}R;NM7qoBw@zC5PQ^_?Qh
zln6eFMP7j)Gf)W;00w1a^kRN>6co>vEst2l5S!Q&NecI*c_8H@k;Q?aC@7)|!Ak*%
z`5RQb_f%9O@<$Or8JEUv8hSD_I~$>)e*%eYxmwlN#}5Mq-!aC&xijpz3HolAa{!{W
z=jp{FUkFto*_A7g*#6E@?m=4|va0AIb)x>mbb~?jLt-K(k=lE!g-4DoVl^~n2k4R9
zfb|KmQ0ZV9PxlC+!WTxO2UJs?5$Z6=nGeku(C3JVZU_p38z!96`In9^4t8;|9hlq{
zs#Ijyz2b5$vn{*Qpx{Ue=c)=th8!jrCFD4Uumk*4kg_kcJwSU~7<$c6Alx#bQN-f_
zC=Znfnu_>J#rIqsWPy<9+{w1kWl2in{QJ04f<6$Ud?8xlw@DvwX(36ocu5nvEfsi1
zq(JS1r;_mkV+5=xZjbxO6f)~%n_0kI0D5>U<7H>Z;j^>E_TOG&0b~TvOnGy>(BzpZ
z53(de*^!k4R1^*HV{jod@Ma<U8h{Qy?=33?HCwjags;}j<onFeZ~t4seRWI~aj0l~
zuL}p>gMfq~j~Cg#lbSP0Nwt9UL3Uo>+{^&6t+BaTj9)0HyUz}WVUew4*8@fZ1%*mG
zl*fah<e-4$F#+U&6l{6bf9Ix*kC`7y#!ysDf)w@^U~S;>!Vt{fRYgTbm1Log+}nT0
zD+@?U*uvkHxofqtJ@^Q+A(2=^ftca`C~zk0Z_@5eNKI7*-V_KQAm+)yF_Vyx(7R(a
z!H$}Pnizy}s+&+RNJ80bK9mKc@vsq?Bea;?Em)(OFy|oWCP6&goJ$X=VorlwgDuQ@
z3KGisxcc>GT2N=+j@(AT)=XSl8d9PqO8JQadqsHl`t@hvQJH3U$>K}3@WuuadV)9v
zPC}#vz(W)w#77Fs&dj2PH@JdQsqAU~2q66SCKv|7fdB-}LicSx)VD}E1i#`By>9sm
zfm)Gl1+^~<0s#tS*~^ra&G09>=#n8j^PyV!ytXC?1h)iYaDKG5P88IiJXPY;x&m<t
ziAk0%NV1^3bm`K4yISCE!kP9TqnrO)uC~b;7&`H(^zU1ZBGJLqvm*Su=D$e(`{fP>
z2u%*=lg;>+rl$2)*7Qr1l(QR&Z8iUjE9#JBO`Bd)ER9sg!X9t}fY=ReEr>94Z#>)F
z>{-~m|N6`pbJy-|!Wx#nb>ZJO-2ZjBW6+6Mew7@#U!AAJ{T6ipYSkd;t%$#%j4jom
zLB@DS&pb7#9MTL)i)IcQikYAe3sYERh*wrN)B86e5la9QULnyQ>#L=W(7ad-l4^y=
zJfDH!Tp<pNFlJ$qr?4ipYE^xpI+6J`8kQihaRUnKu)ARV_-hkZ*mm2J*tX6;%OtIQ
zgC9ixOrUs?2sr0w2L&C-#`_M)p1AR@sc#4+yd|oAV1}3+o{Uzx!L4M-MyK<d5&&F}
zdaR<Nf-es{Of&L1u4MR!#S4ATCLB3B3uYETFd<?gpkET;N=WVbohN01@ue%T_1S&k
z6bIk`OM!gtN;jd8I#JGP?d3##*$Sx}V2-Xhu~wc%;#xDUV`Fb`ug06?<nRuQ@8E69
z%ggh13kI(4zu;&wGvt{kuI_xTo0mCz>4je{4J)!)vkWb>K}0)(QhvV;(Yv@Ru(%*~
zI*rL9810tAXm7dFTTNDki7bU|Z=?r;CPX&;w!Z`YvG3mqIY)CBLvGRfnt6rzHuAa4
ze@%Y>r9Au}xwU63_`}GU@y<0k%J^ZQTqU5VfVjwZ@cU!_4r&0$lDlw;(3em@DvAg^
z-9)JtAETo1NMfa9a71wQFD!X@$-=vJyucn_U;inG92?8D5QRq@^l%^;u0<IeSsQX{
zYRuV<vq!kIN-S(fsbujnBUZ+Nce^$JJlrA&E6L%*_B5IP`C|MAZLB<&Zy*E=fxk3(
zF6pTF`RL-q*uQZ>RRq_Qq50KN<*DEuX6FB;LC#YWTE#VJDF7jXe738%{M!-^aV5{2
z-Z+f5ywF>Ao`iZbDkEcR9+I;jTKX{O`>A5;eqWT||ByF@JD|fFVEM6^-wGKQrf=2|
z@1;$u-wgwhNfC5RxYl}S0oS>m<Oy8oCl1#7>P649hyQrV?;T25;v%~!)5$GpzG3jr
zLK;5PU*RY>Eeel-xbEqz%(WZ+4o1qZo&xrZrCDQI+aHRu2wdGgAnR+g?c+QP%5KPL
zP{ZP46|tlZ!`s)`(792##;Z9#mCloqc?RYE8g$guKfaMrKD8dq>g#?7G2~wE#jUS(
zbr{8^b7~(Bzx_mEZT@(6OdTDj2Fxj&p};~Tw~A9c#Q2dJe59FY7EnJc1Y>aE)-{!s
z&NKQQX}og-Y3HbJW@M2LiCKm)0q<g4)PbniGCK~cb$GZA;3G2v#_jIyy4xU9mH#*h
ze`GlQ%?hTcO}<q{kbH)!NsBD)R%!lJ7JXP`w+;)~sKt;EFo-hfkI#CK`JdP`U0=R{
z3*;aFQRjp&-xS%mXq$7!uwsZi>OV)>$Sj}!vM?S9+VadNY^jNwn3})a7<2Zh=V*yt
z9H9xGzeX?IJbxB%SeABsCEv0>{oE1NAi>de{~x#srF*R^ZrXU%Fa7*br@iJUGOWfz
zRdGS^v6t|%HoU`lRaR60PFh1p!}1D|5<Jb80IEW)4R03jdJ!uhs<MH#;bOz>-RA(o
zHUBQa<3VoX2Z^4><rhp5*uaX+G%xl(?>4PI1q_nHJ~A=BY$v44ynk0|<`J^2+=7Dc
z_5C{YsEP{-T^pKwTJ-xkT7g`1aRa!Nru8Y+@X>o#Htuc|7kyv)@vN~d)e3f~C9pS9
zT)un(*xl6N^tyQ_sF<Iaz$BDNU{O0ms!}p%0t(IoMe^jb*t`1%S-6{lJ2EbB*_=oU
z2U3xQ7ng>N4awm><`6u#oc5=I9zg-9fGRdFxCg%ba1Zn-7D|os^Pdr(<;{DuY_T@%
zDg*jko`(h<Y#z0@@RtqznwPl+b03j--lh(tNsdEw^F0@})yy{p3b!f3pQcG9aP-~P
zym$)F{`;%kEIxj+!d@^Y+4*E9Z&J^qC4il;D?}zl8QxFneBd5djfae%c&Y^{{Qkey
z4f5|abjyv8-?W(sv2OqK&p$}<_kz~J_;6==h4_<=Xw>no-?=NqaH&i?cxMSht%64Y
z_-VZwPhP+f`hMHLz-&J<`c7|L5$l2F!fL*y;$ak-?tF{fUzbG$B%$}2&@2G?RYW;~
z3#{E-%)eRwQ^N<ZK|b~@r<rIs#ShV(BY&*(+c)jk;VGPNcI=jCaan>LmOusw@Ni!h
zNHd6a3b80rFeJ=mqCCJ?hvP{@9fst>q6j5FK;6yM%~AC26uSDiKRx*T(su-$Lub#O
za~=VTMV~tB9vzMll~(<T4y@YHxODT^Xz;wH147&Y$%pc=0)X!8H*aPumPe}x?p=QL
zV?Y1p^5W~8@GL3cNORCgrBipbp$x8OOTY%<etBTSm6DR;dWm^&gQttCC)b?Aadom6
zfeD|{$OT&;5rWWwW-*3jfQT=n*K{tH1q~Fk3dncm`p|?rxq)Z(*N^lZNBN@D+Kcj2
z<n6hTUl0@BGZHB*fPZetHFOf5mjc1`aCCGuLYLZ9hU&*j#|;lU7_{UQJcBz*oe-*^
z^X0-HLOan<OL9xnH!?;@HRA8*=2#5deYw*<*OA-;T@p&AB&r=!BzP&Pn%wE!&!M4B
z^r$M-x!}HwgodaigDV<Y56l6OPfC1RD11i}4M2G*YfY8_Yj4c7Gv>@D*p5L~S5c{C
zQ(x*ge=iy~vcHHX|NaOarICPP5#3+fu;Pxu{l27vU7Q%Mh^&_y2%efe?-o=L*l8L6
z3w3f%;yEP;XNZy{(ifDe6oyBM3JEkF97xE$aHfJc`<BdKZiziOtuCzhU+D0^Z)5sj
z$4`iy#oMDc4v9E19}2Y2GR8fIJ?SOsgcY1BTn!{teFUJ(G%0ZyxEOfRGX9vz^^DZr
zbCIFiXOSH>x1V$rhM{2(%;JiI=A(<qTj_EeXq);@2^BmvI5Y)kjHM$h2}PD>A0qP6
zb*4^}z?vrun`+W>nH<EZ-oOVk98R2T>`s`}+luDzfPqc9PEM_<a_n@qQShAt#U?Ay
zrNr}ek_KO{{2|JFs->ctdlUR4bA>p<c&Zn2ZSl5T?L{<$mk9hhGDlD(#_H~wk9q-K
zI;T-D^%hGLjy0aR%sXJc-=@({k=n95tnE==#S3+UJ7Yuo!{%P%$l)9p?e_OMJBn!H
zKd0213$AOG4G9d@M$ulHUAdas_6OG!w=%eIl;C-_5M8dXfQ6iFrkF^Wo8?I#p43~c
z@B^|X{*)sFh8S%=q`fJ(jTnb8C~~kM{ujgH-fI!zX6;A*GK|KwYxsp!e=h2WHa|J{
z79KNmK?%nncLi51MaN%!?M8Pu{q1-S)J|Gr$OwI?wj5F|Yw8@I8&L%34EDOQ)Q*-q
zlTIM)=9rH*Qaj2h@>%93DgugJT-T)BQlcI6ve-b5rC!{r!t`f5?vJ&ZnDCh?w8|L`
z4DWm-V&=~(qd%kwv@|jL&`NvAw>*HNGOpC!0@ES*%QQ3OF2bf<g9alH1*S<3gP`)D
zszEBQt?zY5r%G6+Ej*QvMB#qhRYTW|+2}ChKhoHI2J0-vw-@_!e&))_2GH57+dLVi
zH){oxZ3%F@5M`jjO2TcSZ^G#GfC>}_CXi7P9-80vo4**_*}XG|I_*9<WI;*f_0*}M
z!8g%tkphFGX2JuJbx}|%ioRU@^{M53In__5Pr<a$*i+5h-#CxD4T!EVO8F*+F#0Eg
zR>ueKfQ7!I!Q#()gWNK6_<in<H<{v_O^oSzR`ZID3e_zQiRf@}M=vFW##*DC*yvhC
zzpc@H-(==Pf#E-=YfXwy#H&FyCSDC{!rk$JfOl?2zU%lvxpPH*pxX#MgB8VE8xs_w
z3_R7&EQL?kUd%a2d2*V3ICMB+*wd2v-FYdU>Nq9-)}2-rHaao4P%wGcbytBv_d5FV
z^>aw078_gckArdl!w$EvaRXe&k~@Mo-AzxktnuoaPd;g9iXAfSa1OS_z0k6f%on^!
zC^WspS-yFASRY#}O$(BR%;mZJhKA=`_@k*F2kaFJ)=AdZ)POaKT5C`H#iMIw`g9sJ
zS*AwhOV_Th=WSFrd>{0&<Z%Cz*Y*QnQ~gw$$mbt6E)VPi-qx|M(WG#rcw3#p7N<1F
zevqJ1-n%k+TVXlYNr?qCTX0g4;5ukP#dZGLepGT=?k4^w`U8hmcNT$%v>vER4ZnUX
z!xihc!OCYT5$s14SutjarCH*)uEHz%>CNI$yuR1$3sC?(l@dpj-!sty!m`YhzDgEK
z*LtL1|NJgb^~l4ZVDT(TadXz=XVHZGK3jHAOgGhQH@3E>OHO^|rq#kR7GgNQk5rDM
z0nE_tJW)4hc~T$MNomZnLnEMMrN2_bEzMr+@N+j@p-aufM1YAxJ_oJzRk$&ss63*H
z`$x2;k@p)Y%_g87>y>y2kJp;n9Y0RKuAc-KLxiRi<^oJQjBNKzmPrIY3<uVw9%!z{
zd+!n7tlG`hEHX)N(vBkn7$4}zvy(GOXqIk!q3|sALQm+&+U`g9PF2sJKmYCf-FnL`
zn?m$^0yXW+kY%4ge-7za&dJGX-(!z3<zS7R@CqX~v4!_Y@+h~uh|3@E=&kj>$116O
zU~(Yy;6PI))^*5c$<J*#NN(kPKKV(*$xKCQ=z(LAk)E#p6i+wa;V<+B7o_8AF*#KE
zsBXdIx2u(w)o5b~3!mGFb`4XFK3%**YuxPNV@dw37#tOXg5BCsNe{Og?x58|qyD$W
zpYUtWyEaSVS?%h%6_^-t_MIo%`C2cJ#TGs@lQqW%Q<;nhUoI4uVbw6`kXsMXuz4HQ
z!1X}7NQyr#@oS?z>nyt?@aVhSl_UjPN@kfh0Nk#yHH6&j`%FmuB+`svsg~Eakk#Zu
zk&)3tx(wb@Z_4Ml1ZH%t#!aOZ5^Dv7VBsVLLkM=~v4iFBlHO2B>zJ9uPcQEqpWV6l
z`#eASS!X=~+~)!pCepljyXO|AYEDNF>C~h#(p4wVgo^A##VE7zS+d%?t+RVV3124v
z*`(hIih2+mEcv<Yw>f&}yLxiKWSgNb<p-PJrEJoE$7C9+??)~@6f9%((Uhj~xub=5
zD3T<xl#|GUqAybaML95tQ~Gr*d<g%r4Bc-MP%vwvF7>(5`1EIDxZliVl0&52twc3`
zow%z@Mtha_`W~B+-p7$zA%1J8S*+#hbo4B^e;Lfqs*i>B*wOnJL<p?W*5Df<{X=WD
zy1eG$VayyysPb&8fX*^t&HweOO0z}DWtz*1TN74C44coCN9fH2H!lW|yq5N;?P4vA
zW-Dp4o-td(!=yL)r`B+R(b6GGQnBQ9#-Q}-(4Z+vi?{s;vp7tgoWWb^HHT|%%SD}x
z!MB+B#bYnh3X$ub9;=VLxQ%}@pw<wj3#^sj+1O4n+B`WOYXQggPds@S#SrDt(3gd*
zJ@E$QnHZIc_VIc%%rjFF|B<>MX7}%3DyTiUQk(YYo>k^Oiz6M1dl#Dt6uybEqZq&W
zUpe|z(ng6RZJdtkZiO_Yx^kkwV?Ww*V6dn-lAusMyKF@_l=$I+#!jYOn{2C!^_eF|
z5uCJ#6jog+Z>w=VNo*NHLkbH9H1Q5S884*Te4H?N1|1qby%&twGYst{spPfYeR_7g
zmk%6nu$<K5Vj<dgsSb=be(I`Ml6{3wVCwaac$ipjM3TwK8RRz);;LAPnvwU}4YR!%
zcMNkBmZ<p3UPle8v;KOqBsDa>H-kM*mbODZGEOxds-0Fh>->Q)_oUt`8(+<6mcH$}
zzo~?z!)nax>H{DS_f|$%LobAtboywvTGh#0|02l7VGm4KKRp!Np}F(mb(EitJNHs=
z33ua|pKWBjG7ffX=DUH%sE$=C=+6e#u5Qk<<}M2jY=*~OpY}=7{8Fa}E?*qR7hZf&
zS}o|SPZV{rc<0tkZPAscD)%Co@>H==s=9!&oA8hXZQv03VN2}W1Uh7YKP$a*b1!w|
zl_#EyV|shqzK`+we$n84EnYWTR5*uO&1tv4H_4I#mT(YEGc@~u6nb8B_PkP3fZbk3
zyt6XY-W(B`H(K@P!Xy{A=O95dz|v2`+bi&1f3hi!(+<T&V$=GxpGwBWZz{5Xf+G{G
zJp7=E%|P3)a~xvgfj*LW9rg!5zZg8;#eaB*jfSmed;M|LA#B;JVEC@7kwA^@VJ}wc
z|H3C3Z#y2IdiWcx-M0>g{lTUP+x+UyAGmWE(jY|{BW!rD`EX%?Tw3#$MIM~oYAy6Z
zi?$)dX>o?#`eYLjy~We9%#HM6CA%WJ?l~mrk$~CaxlYOHgIUs2*3i%Z`9U(3aNk(w
zCDp5ff@R%Rj#Pf_?@U9^{*0^VD{8#92A;|dXj(!nv7l#zQBMebGwyy@2~Fn0Qe97V
zJ$6>dS8oy%6VHb1`oBG%*cp7!S@=qh&ne)tn-MD7G|UY8V#0Y%n|a)q9)jUT70?KD
zfKC2$f$Oi8WmZbKTD<Y~dLTTsL+$nh5R+uU_yPisnYlSHbf-ZN6o>Nxx5&*z(20xP
zY$qfYf$V#4;iNi1p!48dq2q?sYt7f59>1&M1J1*r%YXWMyG;5=KeOU+7Q5QY8kS(>
zQz^3#ZdtFD?Kw~P-z9qw-(52>_Be8oIy~VwWZ2_F?CfAnkl<ZCmvsCy;+0sx0*W}B
zfup#S`g>8HDOW`HOWybqu(+Ec?MEr1E*Q8K4A{X`Wn==8ZnUs3>dMOefr`q?>>eB;
zU+DS3IFkES>JiI0hz8%5Mk~rkx+X{;NAi-pBu~|KD_w_{Axw%;FAA|Mm)Z~a3pk7n
zqM8Q=25#6XJ9&gMKiz0h<UftwpB+CvDPP~&ai`M)8;cMEYxLHq&YJ=vX(Ro?I}6Q}
z{9xm1n1fE5-o}D(50B@}u@;yW`f8*d?m}q>)Uhniy6<_J4>zaWP30olwpJ;O5%1@i
zWdB}rna_X&h!p8}qCchkAG9XkU5P3*dvN^a<B#18V7e`a`|VeVi!}doj;m-dpu=f|
z?5M#JLud^0CE|fX<W=BJzh@QEi8+UY04cgMTyt`AFLq-<gH&@zLwuM?E2(DR2en!G
zPZ7z}{H3Q@M!$m+|8`2LqpiC_c3*bSK7amVbKWQY(gKB|g?m);GmaqBv}tN}3yDoS
zV;4GIdA=x@fwh3*r}IjD>eJdMX@Pey`F*^$T6cQRv^mP%H3u}ywYKmAO=0#o7(CJV
z`T=f2p{0>FaYo;`Res_^yCz4>=?41>y;A|R)b*BPbqcHRG&vh~W@&9@jg~if_fg{<
z2X!)!H$W#%YLH*`S5a{)_4$WAn2dGv&(Fmx{zpYv9VhunztB7mj&*<X=B{?K<PJYe
zmRsBJy#Qu`ez6HI(5K+<5o-fhwgbF-dR3*^dtQJ0pAHTeo&iQdnw89d*6jUSFRkvY
zvq|e{4>>TMORx<9w6F6OTK6Ybmq$)wdN`7FbLGhy09u2D!^E_qt_(^l7W?&Emt-dx
zIiR?1;e;bEtk?U93sjBYQpmLf=cCOSe<DD3|LtNMwU(JjKQz42h`Z-aouJcbEJI(u
zd;+HCqeY|BZz*k0x;6tycxqi5QY9o^Sgu`DtKcjDwA4~px=*?^U{OWzA;j&$dx__M
za{aSR3sfjc11dE=dPUK19p$IbbUyjBm!7P*M)SKL4c=M270<EMPKmko{)88M`_`#Z
zsuqvs*y%cUkT>`NNv$n)FRMB$59SILuej&hRY)Q91vMLdH1jn2!#O07bfhm{X`GnQ
z$PMTcvl}jsR2I{}W5P<BU%ldOn7Vzw>^i5@yWBH-{EO;i>8Da9bC_9BOx|l`G^?EM
zx{BR1QtOZt<gDKNn4XYq$)>%wm--a+d_J(v&muMwT`7?Hdx69uUH*>73ykEQh4RV*
zbh~Ug8iIfa=|F{LFO1kHhw9^co@nh|on>iG^mB;#6z8wMW%}+J?(y+)N4|aa2)$ve
zy>Rn$^gpZeal95ev{SdTz+;96>6_eB8oJIg{hW_S=?&3G;2xWWR+d>9{T1S@KH^m=
zJ44^~Cfrqduy&Ubbfob#`&y}VUJ$id{awrAZ2w--Fy0R1X^OexL8!YASh89(8jbU(
z`yC#l_W#l~a*Hdo`uPv^8^>Fr3bnWeypnidfbkeyZ$UukfZ5a2`;qaAolYF_5pD!7
zX`#Bw3E>WY=i~_018e%@#ha(cll2h{;z^|fhu`!rUJ<~4-<8Td&RWjZ$SC%(OfjeB
zq2HrB3|o2}v@WCNL7=0AF0?)6vgk-_0<uXR`qMz{m5f&PkI0Tu&D9vbvno&FY_)rB
zhheO}rhL{JTF<?A7gWphN3F<ve~2ym;Lx?4lrOj~*-pDQozPe-Ff;B=cxUaO<ZrcN
zz%77*!SPxy8~8I=bltILoxo)lV**k)WT-Tc!<PycnWRe1X@j1oM*SoI+)ak4FH*P*
zq9J|u3*C#**%})0<<BqW-lBAZGl%9<9EECzI9^T?Ga{|?t;TQFjOlIqbM^Ku<8{ml
zL~y)VNJx@lCG&8paP81I*9GFgVRZ?)<@Rd{T**jxI77gZGcelLzdlloL!){aDNU{%
zQ_+e}yZR@M41#Uiz8wE&2QZ6A|EQ1WVeoJl2)ZjAOg-e8EC*2mYah-VP^Ue#^nH)7
zeUOIUfWuONrQ6m<|8+Mp&Hd}Nh5ybd^B<?%{Lg5i2lL#P_YEy6MbyBt4Hi70pEWJ(
z%9WqK`{!0V1}x#IOJrnIv%tU0W|s2t@d07Tw!^D)@>>O(IO#;30-<BePH4_BNdS0D
zFtqNhjM~mGO6AhWhyT{7{P3?|+GgSryzpJfDFq?&>lsfz`gTQxgb;!Wo#KEFTKV5d
zQFq-JzeQD+@l@kqzj8mgrxeJ~5?w@5{-0>uY&z)rK<p6Er|9f)bLPFfHkXb3fBe$a
z`>ioUi1-Z^er2Zt^ZDP7`1!Acpdf{~g+Z!^7LNNR7OEa0E{4CP(4r7Dz-F2a7GdZN
z0YdL9aHU_tStkeJ0EMg{5bWUe73$;;<fMlSOLL%oPJ=<HWqiE8Ti74m5hKtr2VoaG
zHzyD4%xfZ;YNS8E{^TH>kijz$vfBh4)&qWAL|;ezZhmm2#~J81`C|{>Yzj&r>)$wQ
zT>&Stpzuz>S3G=3jhJ_bzu52ZxJ>`JOh8Nrz8>T(8zMT9!tUK7zH;Cg!c4xu_zAs@
zz<^ryeYgz$@zjta;y==(5K{(NS6q*-E%kq<g$`KMtrlmU*I&RwNkKCQy|D{}(G*di
z!HDiqvn~e<9w=v|9e)NnXQDhE+B$KUk)s7T2Z#etk5>a+|8(PknF0~o!L>cT@sPdb
zb)z)kC0N&b_5PCJ8gz1LoYS4rMR9e4C-^oT@$x~hgazUra!LW5X;f(1LW~^K04FN_
z87}7rDIVGzlEL){a%SV5-T2hh4$ktCJK*d_i+eZ(9RL6!1yLKCf#sn!6b@*agF_vf
z!Tk&2Vti)VX0Y%Y9LR(nvP{oHT-sx`$v!KUh*NtF{)FQMZTHa9p5i!;m<ZsM9!W66
z7ipPt*@_?REGq+*Ps3x30t@^c1bQT6A)NgU7M98R`ExSRP&8ET$cXe}q7XX>eCaee
z?~7H$zt|7Uf%P3eBL?)i1*q_Fw9r3rmcZsxN!NoU_q>Ni-`4fKpu>4>XU76oMbylX
zQ9u27IJ)Fui|x`Jtz*qs@Sz~5gwUDC9}h14%pe4GE(nh1YhWL{ZX8ex-|hV%Umxv=
z-a|}J(4H@{LP$XHz>_v*6zOs0f6{ms8i_i=m>tIZ0-kI%s|d=50qd?gJLX7f=nH^<
z^@0U~X%}cXHh_@&)PB4wg8k4XLq<<;51QNqD?b3db%)^dh{eG`zvs)5IXJCI1#yn0
zoz@+$@PnI%+q#1J!Eg6eMCC`CLlA%VoyC%p5;%jS!s}?gC6&_Fx$Sop)Tq=A$l(TX
z;sD@OB4fDuc~8vWzIGU{*`tQ8i9C05q;ozSd=6@1o4!iFqd@ye1j|>vXMMg@egxa0
z4{}@z;<9e>W2buz{j36D%|Z?g&^Up-K+^!7tAiSpw6wOclXQMwqiWMzhMw}cT-}1S
z{rb~G>GEcq2wvz6;Duv&c%Z)vIb{J3>gn;_{-p~|D8!6Xc8G^X3r;J56Rs?wC&*lC
z5BtpbaQ=7MC&Xcj{D7B&7s0*J5*rG2rkgOryfDi`AZ37KW@H4M<Z5Bk&@P0E8V0xv
z4JD{q>C^q_`Qh>cIE_OXY}G=b{#Za#W#QuLgg}x6mW(9usLu`0fk_90M<Ri>YJmpf
zj<>g;snq))(?#z?Lz^mSG7$v@1-S;*U*?gf4_?ab-z@y#U=f0T3dAPRI4mNLh6O7V
zMqJl(Q@Oe`5e~6{Z&ZufPWRhEudl6vF>Z-XJ(O9q-yJOD7|?f`|8}*Qo5LXr$cB2i
z3jJoGUSNh#z3dQ^G8FX<G3aMQ6U)rS%^H{yu&?!^W}B#t1i-l=07IA!VBP|Z{NMm=
zn`%oeu4e_uFmK>KGzZX|KM?tXNIp~Z^VVu<67x6PF&JdVW{X-FT;iIVo0E|KE@*&B
zzQA464Q`#!gQi`2a8-m7Ma@EcmVo{67eR;&f?#40f{u!()_Gt#ngv%3KX`5g!YMiV
zU^-@D+wnopgt1P9TZMLEuja;<mSl)qo8W-IqORWMtLQwCZ=m|`2DTwMO2-SD8zR8f
z;sqEPdYF*2M3Al@unsjq_(Q`*(XijXvaRQ2W+o!%XCS>+$e|sO0j`)XwW`1Zhat;{
z0pkI$5uAfItdb@%l=rBt4VFD)lnCrp)0PvMTML_ke0wSI{UIII&``OH98V$7=Ynm(
z(E@6H6C9Dr(1=^&JSDdY(Ks<8BI3!E#N#qm3)m#qs7(NIbL=G0ItR`CNNpCuC@p1_
z${&k{CT&`7ZtfB=7ZyJ^$}BEzr#`%GSnuz*2`502SFYOTS2iQ<PHK_mH?!<p*b8c&
z;Ns#E8G|$9AKzLUq%YDM+~YxWRy~<vXemGMCc$qa<@9qfBMIk-iG=_S<reOB-Lw|(
z+*0bxHyEygR&oo-abT0-g_inZX!g(O_N(5g;LBc0k3kL_5pW!nFhWDlh>Ig9qocEf
z;@UonQQ84HCIjS8YZTJ&EdIp@s<sX|^9BQb^mNj8@V^h<**m$5OC7D<#Y==@CAmxL
z5CguiW+Y*<2nh6n(XWc5pTAaNxZII@y{@2k=Mg`go7Hj*eGf^{doi~d1_s4{rl?b(
zr4hM#sBhGw$Ei)>%jW*Xh~n{>Hb;oAZjL~x-uM3i^;sgaOq`{m>IJ{|cnk&{cKs+8
zpyV6vMRm&<QFbLm8>2>LHWZ5k1vwxvKqas9!^L5&1`Y6+7kXU0cb4?7b!jBIL)!#o
zFh-=2(==N0!JiX|tu4^*0d?ua;Ks*sufLc=uMMn7L<CL}u>J<kl5KDjSNI6YAUC(s
zL$7;I55zk~oUkZZ=Cf}eJDBXPO;9kL(#+Y)Lmn|^#P|*vcsN792*N!;Z$mSjc%f$;
zup*ZK)-^o_?7DC~6(ji-OLOTj$kA>PEs#@U&Vn29U;cNP&^c-?f;F(J_LSM`f=m88
z)E)@%O%(Uwf{x5L)-C9%)fjn(323NCwmT+SxS-+f^2;bU02s3J^1a{<y;I)R(J=#o
zJ`*Gu=r|<>p9gd{4whJ|*R>e951H?$eFBOdv2{V62&1D2o<a!xX4r<Hn$wd*W(HsV
zwAI>g&1JQ4V30o4A&4anz68h%I(y(LrT|t<Ll>=^#29377)0?EBhQIoXexRJJ)$n{
zoaH>A=|ESz=KC)x8uo-JVK_Ge(2;S!G9*zPILhwRtGUr)^9#C$Ud#~UjbU-CjR#l{
z$H&Cn27eUTGtIy$e2;iG30nEVd&EUM2+1o2tq5-<<EmcbgAUXGqmpxtY4QxiFw;mT
zCTfO`xeRAms>D-DDTj$-G&(jpsBtJBiUQI~(5av`NYQv88;bQ15j*S%Iu{WYJJF&d
zxS3Lss>nPb9xzrQnN|>-QWV+sxc%ABneaoB68OINeV_Yz-ut?3oBItYcN)W>M!qWw
z94^=I{Ido1X+7i2rN-AWS`lw1MS6D8i^AFUdSa>i)bSulo1vTAH2LPEZl~9kS9g1<
z_Ly>)5^dwYay)IhM#KZLSzYZ3#5GRA1y>B2LKEbl)|;=<5Ay&j^HZzK`Yc$|>d+6-
zzjb$Y)tyYZG<9dywrzhInm*^~_>6&NB4ZA*8p5g*05<2SDTizBV+*ZDMdZGd%Wn9=
zB8VqA?!x-DyXO>}UtI7RJa|{zyHSOP-?<mR%n1~Me(LY#^;m)xnAX(3E>HLNPrseF
z7eq(g3Fs)@jf2xGUe-s-`TrI#t!?-rUCEhAfjl+g<e3_p5H#nXd>Mj!6%#4(J4z0e
zrP&iBQX2EHH_|Nbuv$YFZ*VJMpR>amTcIA{k9O65bt3<DPe66(hJ-cG8g^q;C-AEI
zNH3@*mts!z^120%?A6*Z55{;i$&L{VBWk%e#QU&cUYRe<KDf1oRcdHPQH}@>4qj{u
zGmi1Um#G5673CHe7gw29;=2%SQ-l@}MvCO0AqCT@_<c8y`f#Yt<Ps{IqU|<TNr~LM
z_uEHZC70vwu{X$Z*mj`40>YTX!){*puqN9l{%e*Pc_O+^_T!7r{(7;8=!($w2YHdd
z#m>{%kZVxVUr-2)rugQZDm5afn%U|#q8sgEkpy9*Qmnf9{no9*4zvaCA-yxS@*3B5
zc*}Dr)8HmMd0-eG{4+)*hfj&^Cwhssw|~I+@{0x-G%dqUEn>d~9xsUAMa%h%Y!P1B
zV5pGDst+UqZaJRXPV<%r7c#Aa5%bptL8y-m4}ZuJ6y~X1(O6c)&NC4>BAHJ1aSDZP
zoNLC+nIXOt)+jMg1+x&Z_{@okiK*<#>g{>$se~e4z5ZD9iU?AhC=}-;W{er5RR9DD
zUlLK`X2{|D=FbP`tt64`m~TnUmM=nRP76Ce_LdPQy8ueFfI3wF3~}F-Id^^|;YciL
z6+K=Hm{L&Ky60*@K^04;Uv+Q!)AG^L3v&asOqjVoF_BSlrY<Y?RT45%x`b1SHZOs}
zI}!b&BU)3P9nG~@`9)Up46f2)B!p9ivGOLfDpHH}s85-Y5)J0ye7=hEbg;psl)K^o
z7k!$_YKuZ>39;>vk4pfXJwUB>eB$lxog@)>rvM=X4PEVqzKJ^+A-1!nmhp462*tia
zw8v+<g8t0~llCr(H$w`Hs<g8EC<-jJZAt5%>cuzrn}EHaj46OImtsW|VZK|Lb>5^-
z*(3i)c@#MVXdGm}i8)irYZqsWS{@WOBV~1iy+c?fEsdd=xQ(XMI?t&5X{Tefxt5&=
zD>-kYxmeG|!pyO!mf3Gci%BOre8{AUuNsovzZ9F#g1=w46k=oc>E6$@wYVXR*~huV
z8l7jLk3KRg%3&=P*ZCr%d4_(Z%eZGDLJ382M~HWD+hm+P(KJE>qP9mzM+cD;s^lyh
z>F<A8%+3v)?&n!#=Z@)^R5I2TN(CM!!Ea0_3lIb!PbjD{+w%exD{GlgN!S3<G2_-u
zrsGjnhp$pIr6&H+B>8KtKV^<@x=8K1^P}_xOdOq0pQcg?wFC)R45eF!vXHWl_Ch$y
z%j9fR&C{&S`$HR;H}W>Km2~Q-2^L5`C91yiU3Y4P25l{o2K@&O3SrHSR>q#?LZpSx
zCf)HCRC8Yjt*x(1LmZswfB6npbzJRbH6dG$RJ_Pno1ol(9;RCQgY*QDh-%!orShpx
zMIf!MxCW{Y`9j|+t@qQmi*cSDGQ~g%J)lnK0=%a*mK94QIHQ}jnQJi*oW+J8odYI*
zgI0$tBiHj;2gY;#g2WL{rUPI!G`aAW-s3%@Q9%oa{PR1fcS*pO<SD`{y=-f0O1Ult
zQU)Ei&i3|4D2~T~GDRE);?Om)tC4E=Q?CERt0ktqPu~4s_P76%j&C+LUYZxb`%ThZ
RGM_!ZnI1Fk#MC95{|2uRx`qG%

literal 0
HcmV?d00001

diff --git a/_build/jupyter_execute/grids_2023.glue.json b/_build/jupyter_execute/grids_2023.glue.json
index f924487..5a4a094 100644
--- a/_build/jupyter_execute/grids_2023.glue.json
+++ b/_build/jupyter_execute/grids_2023.glue.json
@@ -1 +1 @@
-{"data-summ-q3": {"data": {"text/html": "<style type=\"text/css\">\n#T_91665 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_91665 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_91665 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_91665 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_91665 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_91665\">\n  <caption>The number of different locations and cities for the data. Note that there are 31 different municipalitites in all.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_91665_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_91665_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_91665_level0_row0\" class=\"row_heading level0 row0\" >Number of cities</th>\n      <td id=\"T_91665_row0_col0\" class=\"data row0 col0\" >21</td>\n      <td id=\"T_91665_row0_col1\" class=\"data row0 col1\" >19</td>\n    </tr>\n    <tr>\n      <th id=\"T_91665_level0_row1\" class=\"row_heading level0 row1\" >Number of locations</th>\n      <td id=\"T_91665_row1_col0\" class=\"data row1 col0\" >48</td>\n      <td id=\"T_91665_row1_col1\" class=\"data row1 col1\" >23</td>\n    </tr>\n    <tr>\n      <th id=\"T_91665_level0_row2\" class=\"row_heading level0 row2\" >Total objects</th>\n      <td id=\"T_91665_row2_col0\" class=\"data row2 col0\" >57,623</td>\n      <td id=\"T_91665_row2_col1\" class=\"data row2 col1\" >14,703</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x76f602293490>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "data-summ-q3"}}, "output_type": "display_data"}, "testing_training_chrono_2": {"data": {"image/png": "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", "text/plain": "<Figure size 600x500 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "testing_training_chrono_2"}}, "output_type": "display_data"}, "testing_training_doy_2": {"data": {"image/png": "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", "text/plain": "<Figure size 600x500 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "testing_training_doy_2"}}, "output_type": "display_data"}, "data-summary_2": {"data": {"text/html": "<style type=\"text/css\">\n#T_4afd1 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_4afd1 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_4afd1 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_4afd1 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_4afd1 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_4afd1\">\n  <caption>The observed values from the training and testing data. Remark that the testing data is only 22% of all the data. This is because we are only in the first year of a six year sampling period</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_4afd1_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_4afd1_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_4afd1_level0_row0\" class=\"row_heading level0 row0\" >weight all samples</th>\n      <td id=\"T_4afd1_row0_col0\" class=\"data row0 col0\" >0.78</td>\n      <td id=\"T_4afd1_row0_col1\" class=\"data row0 col1\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row1\" class=\"row_heading level0 row1\" >Number of samples</th>\n      <td id=\"T_4afd1_row1_col0\" class=\"data row1 col0\" >263</td>\n      <td id=\"T_4afd1_row1_col1\" class=\"data row1 col1\" >73</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row2\" class=\"row_heading level0 row2\" >Median</th>\n      <td id=\"T_4afd1_row2_col0\" class=\"data row2 col0\" >3.47</td>\n      <td id=\"T_4afd1_row2_col1\" class=\"data row2 col1\" >2.28</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row3\" class=\"row_heading level0 row3\" >Average</th>\n      <td id=\"T_4afd1_row3_col0\" class=\"data row3 col0\" >6.13</td>\n      <td id=\"T_4afd1_row3_col1\" class=\"data row3 col1\" >3.25</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row4\" class=\"row_heading level0 row4\" >25th percentile</th>\n      <td id=\"T_4afd1_row4_col0\" class=\"data row4 col0\" >1.52</td>\n      <td id=\"T_4afd1_row4_col1\" class=\"data row4 col1\" >0.78</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row5\" class=\"row_heading level0 row5\" >75th percentile</th>\n      <td id=\"T_4afd1_row5_col0\" class=\"data row5 col0\" >6.69</td>\n      <td id=\"T_4afd1_row5_col1\" class=\"data row5 col1\" >4.31</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x76f65a0b9dc0>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "data-summary_2"}}, "output_type": "display_data"}, "estimated-found-predicted-2023": {"data": {"image/png": "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", "text/plain": "<Figure size 640x480 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "estimated-found-predicted-2023"}}, "output_type": "display_data"}, "diference-estimated-found-predicted-2023": {"data": {"image/png": "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", "text/plain": "<Figure size 640x480 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "diference-estimated-found-predicted-2023"}}, "output_type": "display_data"}}
\ No newline at end of file
+{"data-summ-q3": {"data": {"text/html": "<style type=\"text/css\">\n#T_540d8 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_540d8 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_540d8 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_540d8 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_540d8 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_540d8\">\n  <caption>The number of different locations and cities for the data. Note that there are 31 different municipalitites in all.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_540d8_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_540d8_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_540d8_level0_row0\" class=\"row_heading level0 row0\" >Number of cities</th>\n      <td id=\"T_540d8_row0_col0\" class=\"data row0 col0\" >21</td>\n      <td id=\"T_540d8_row0_col1\" class=\"data row0 col1\" >19</td>\n    </tr>\n    <tr>\n      <th id=\"T_540d8_level0_row1\" class=\"row_heading level0 row1\" >Number of locations</th>\n      <td id=\"T_540d8_row1_col0\" class=\"data row1 col0\" >48</td>\n      <td id=\"T_540d8_row1_col1\" class=\"data row1 col1\" >23</td>\n    </tr>\n    <tr>\n      <th id=\"T_540d8_level0_row2\" class=\"row_heading level0 row2\" >Total objects</th>\n      <td id=\"T_540d8_row2_col0\" class=\"data row2 col0\" >57,623</td>\n      <td id=\"T_540d8_row2_col1\" class=\"data row2 col1\" >14,703</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7c6c3ec92fa0>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "data-summ-q3"}}, "output_type": "display_data"}, "testing_training_chrono_2": {"data": {"image/png": "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", "text/plain": "<Figure size 600x500 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "testing_training_chrono_2"}}, "output_type": "display_data"}, "testing_training_doy_2": {"data": {"image/png": "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", "text/plain": "<Figure size 600x500 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "testing_training_doy_2"}}, "output_type": "display_data"}, "data-summary_2": {"data": {"text/html": "<style type=\"text/css\">\n#T_59f14 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_59f14 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_59f14 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_59f14 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_59f14 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_59f14\">\n  <caption>The observed values from the training and testing data. Remark that the testing data is only 22% of all the data. This is because we are only in the first year of a six year sampling period</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_59f14_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_59f14_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_59f14_level0_row0\" class=\"row_heading level0 row0\" >weight all samples</th>\n      <td id=\"T_59f14_row0_col0\" class=\"data row0 col0\" >0.78</td>\n      <td id=\"T_59f14_row0_col1\" class=\"data row0 col1\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row1\" class=\"row_heading level0 row1\" >Number of samples</th>\n      <td id=\"T_59f14_row1_col0\" class=\"data row1 col0\" >263</td>\n      <td id=\"T_59f14_row1_col1\" class=\"data row1 col1\" >73</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row2\" class=\"row_heading level0 row2\" >Median</th>\n      <td id=\"T_59f14_row2_col0\" class=\"data row2 col0\" >3.47</td>\n      <td id=\"T_59f14_row2_col1\" class=\"data row2 col1\" >2.28</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row3\" class=\"row_heading level0 row3\" >Average</th>\n      <td id=\"T_59f14_row3_col0\" class=\"data row3 col0\" >6.13</td>\n      <td id=\"T_59f14_row3_col1\" class=\"data row3 col1\" >3.25</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row4\" class=\"row_heading level0 row4\" >25th percentile</th>\n      <td id=\"T_59f14_row4_col0\" class=\"data row4 col0\" >1.52</td>\n      <td id=\"T_59f14_row4_col1\" class=\"data row4 col1\" >0.78</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row5\" class=\"row_heading level0 row5\" >75th percentile</th>\n      <td id=\"T_59f14_row5_col0\" class=\"data row5 col0\" >6.69</td>\n      <td id=\"T_59f14_row5_col1\" class=\"data row5 col1\" >4.31</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7c6bfdf61a00>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "data-summary_2"}}, "output_type": "display_data"}, "estimated-found-predicted-2023": {"data": {"image/png": "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", "text/plain": "<Figure size 640x480 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "estimated-found-predicted-2023"}}, "output_type": "display_data"}, "diference-estimated-found-predicted-2023": {"data": {"image/png": "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", "text/plain": "<Figure size 640x480 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "diference-estimated-found-predicted-2023"}}, "output_type": "display_data"}}
\ No newline at end of file
diff --git a/_build/jupyter_execute/grids_2023.ipynb b/_build/jupyter_execute/grids_2023.ipynb
index 1b584e9..63a9341 100644
--- a/_build/jupyter_execute/grids_2023.ipynb
+++ b/_build/jupyter_execute/grids_2023.ipynb
@@ -496,21 +496,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_d0aab tr:nth-child(even) {\n",
+       "#T_556fc tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_d0aab tr:nth-child(odd) {\n",
+       "#T_556fc tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_d0aab tr {\n",
+       "#T_556fc tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_d0aab th:nth-child(1) {\n",
+       "#T_556fc th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_d0aab caption {\n",
+       "#T_556fc caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -518,16 +518,16 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_d0aab\">\n",
+       "<table id=\"T_556fc\">\n",
        "  <caption>Table 1: The objects of interest. The average pcs/m per sample for each object. The fail rate is the % of all samples that the object appeared in.</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank\" >&nbsp;</th>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_d0aab_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
-       "      <th id=\"T_d0aab_level0_col1\" class=\"col_heading level0 col1\" >quantity</th>\n",
-       "      <th id=\"T_d0aab_level0_col2\" class=\"col_heading level0 col2\" >fail rate</th>\n",
-       "      <th id=\"T_d0aab_level0_col3\" class=\"col_heading level0 col3\" >% of total</th>\n",
+       "      <th id=\"T_556fc_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
+       "      <th id=\"T_556fc_level0_col1\" class=\"col_heading level0 col1\" >quantity</th>\n",
+       "      <th id=\"T_556fc_level0_col2\" class=\"col_heading level0 col2\" >fail rate</th>\n",
+       "      <th id=\"T_556fc_level0_col3\" class=\"col_heading level0 col3\" >% of total</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th class=\"index_name level0\" >code</th>\n",
@@ -540,106 +540,106 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
-       "      <th id=\"T_d0aab_level1_row0\" class=\"row_heading level1 row0\" >Industrial pellets (nurdles)</th>\n",
-       "      <td id=\"T_d0aab_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
-       "      <td id=\"T_d0aab_row0_col1\" class=\"data row0 col1\" >2686</td>\n",
-       "      <td id=\"T_d0aab_row0_col2\" class=\"data row0 col2\" >0.22</td>\n",
-       "      <td id=\"T_d0aab_row0_col3\" class=\"data row0 col3\" >0.02</td>\n",
+       "      <th id=\"T_556fc_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
+       "      <th id=\"T_556fc_level1_row0\" class=\"row_heading level1 row0\" >Industrial pellets (nurdles)</th>\n",
+       "      <td id=\"T_556fc_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
+       "      <td id=\"T_556fc_row0_col1\" class=\"data row0 col1\" >2686</td>\n",
+       "      <td id=\"T_556fc_row0_col2\" class=\"data row0 col2\" >0.22</td>\n",
+       "      <td id=\"T_556fc_row0_col3\" class=\"data row0 col3\" >0.02</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
-       "      <th id=\"T_d0aab_level1_row1\" class=\"row_heading level1 row1\" >Cigarette filters</th>\n",
-       "      <td id=\"T_d0aab_row1_col0\" class=\"data row1 col0\" >1.12</td>\n",
-       "      <td id=\"T_d0aab_row1_col1\" class=\"data row1 col1\" >16458</td>\n",
-       "      <td id=\"T_d0aab_row1_col2\" class=\"data row1 col2\" >0.85</td>\n",
-       "      <td id=\"T_d0aab_row1_col3\" class=\"data row1 col3\" >0.15</td>\n",
+       "      <th id=\"T_556fc_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
+       "      <th id=\"T_556fc_level1_row1\" class=\"row_heading level1 row1\" >Cigarette filters</th>\n",
+       "      <td id=\"T_556fc_row1_col0\" class=\"data row1 col0\" >1.12</td>\n",
+       "      <td id=\"T_556fc_row1_col1\" class=\"data row1 col1\" >16458</td>\n",
+       "      <td id=\"T_556fc_row1_col2\" class=\"data row1 col2\" >0.85</td>\n",
+       "      <td id=\"T_556fc_row1_col3\" class=\"data row1 col3\" >0.15</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
-       "      <th id=\"T_d0aab_level1_row2\" class=\"row_heading level1 row2\" >Food wrappers; candy, snacks</th>\n",
-       "      <td id=\"T_d0aab_row2_col0\" class=\"data row2 col0\" >0.54</td>\n",
-       "      <td id=\"T_d0aab_row2_col1\" class=\"data row2 col1\" >6767</td>\n",
-       "      <td id=\"T_d0aab_row2_col2\" class=\"data row2 col2\" >0.86</td>\n",
-       "      <td id=\"T_d0aab_row2_col3\" class=\"data row2 col3\" >0.06</td>\n",
+       "      <th id=\"T_556fc_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
+       "      <th id=\"T_556fc_level1_row2\" class=\"row_heading level1 row2\" >Food wrappers; candy, snacks</th>\n",
+       "      <td id=\"T_556fc_row2_col0\" class=\"data row2 col0\" >0.54</td>\n",
+       "      <td id=\"T_556fc_row2_col1\" class=\"data row2 col1\" >6767</td>\n",
+       "      <td id=\"T_556fc_row2_col2\" class=\"data row2 col2\" >0.86</td>\n",
+       "      <td id=\"T_556fc_row2_col3\" class=\"data row2 col3\" >0.06</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
-       "      <th id=\"T_d0aab_level1_row3\" class=\"row_heading level1 row3\" >Toys and party favors</th>\n",
-       "      <td id=\"T_d0aab_row3_col0\" class=\"data row3 col0\" >0.05</td>\n",
-       "      <td id=\"T_d0aab_row3_col1\" class=\"data row3 col1\" >606</td>\n",
-       "      <td id=\"T_d0aab_row3_col2\" class=\"data row3 col2\" >0.48</td>\n",
-       "      <td id=\"T_d0aab_row3_col3\" class=\"data row3 col3\" >0.01</td>\n",
+       "      <th id=\"T_556fc_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
+       "      <th id=\"T_556fc_level1_row3\" class=\"row_heading level1 row3\" >Toys and party favors</th>\n",
+       "      <td id=\"T_556fc_row3_col0\" class=\"data row3 col0\" >0.05</td>\n",
+       "      <td id=\"T_556fc_row3_col1\" class=\"data row3 col1\" >606</td>\n",
+       "      <td id=\"T_556fc_row3_col2\" class=\"data row3 col2\" >0.48</td>\n",
+       "      <td id=\"T_556fc_row3_col3\" class=\"data row3 col3\" >0.01</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
-       "      <th id=\"T_d0aab_level1_row4\" class=\"row_heading level1 row4\" >Industrial sheeting</th>\n",
-       "      <td id=\"T_d0aab_row4_col0\" class=\"data row4 col0\" >0.30</td>\n",
-       "      <td id=\"T_d0aab_row4_col1\" class=\"data row4 col1\" >3356</td>\n",
-       "      <td id=\"T_d0aab_row4_col2\" class=\"data row4 col2\" >0.57</td>\n",
-       "      <td id=\"T_d0aab_row4_col3\" class=\"data row4 col3\" >0.03</td>\n",
+       "      <th id=\"T_556fc_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
+       "      <th id=\"T_556fc_level1_row4\" class=\"row_heading level1 row4\" >Industrial sheeting</th>\n",
+       "      <td id=\"T_556fc_row4_col0\" class=\"data row4 col0\" >0.30</td>\n",
+       "      <td id=\"T_556fc_row4_col1\" class=\"data row4 col1\" >3356</td>\n",
+       "      <td id=\"T_556fc_row4_col2\" class=\"data row4 col2\" >0.57</td>\n",
+       "      <td id=\"T_556fc_row4_col3\" class=\"data row4 col3\" >0.03</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
-       "      <th id=\"T_d0aab_level1_row5\" class=\"row_heading level1 row5\" >Shotgun cartridges</th>\n",
-       "      <td id=\"T_d0aab_row5_col0\" class=\"data row5 col0\" >0.08</td>\n",
-       "      <td id=\"T_d0aab_row5_col1\" class=\"data row5 col1\" >1030</td>\n",
-       "      <td id=\"T_d0aab_row5_col2\" class=\"data row5 col2\" >0.48</td>\n",
-       "      <td id=\"T_d0aab_row5_col3\" class=\"data row5 col3\" >0.01</td>\n",
+       "      <th id=\"T_556fc_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
+       "      <th id=\"T_556fc_level1_row5\" class=\"row_heading level1 row5\" >Shotgun cartridges</th>\n",
+       "      <td id=\"T_556fc_row5_col0\" class=\"data row5 col0\" >0.08</td>\n",
+       "      <td id=\"T_556fc_row5_col1\" class=\"data row5 col1\" >1030</td>\n",
+       "      <td id=\"T_556fc_row5_col2\" class=\"data row5 col2\" >0.48</td>\n",
+       "      <td id=\"T_556fc_row5_col3\" class=\"data row5 col3\" >0.01</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row6\" class=\"row_heading level0 row6\" >G89</th>\n",
-       "      <th id=\"T_d0aab_level1_row6\" class=\"row_heading level1 row6\" >Plastic construction waste</th>\n",
-       "      <td id=\"T_d0aab_row6_col0\" class=\"data row6 col0\" >0.14</td>\n",
-       "      <td id=\"T_d0aab_row6_col1\" class=\"data row6 col1\" >1970</td>\n",
-       "      <td id=\"T_d0aab_row6_col2\" class=\"data row6 col2\" >0.51</td>\n",
-       "      <td id=\"T_d0aab_row6_col3\" class=\"data row6 col3\" >0.02</td>\n",
+       "      <th id=\"T_556fc_level0_row6\" class=\"row_heading level0 row6\" >G89</th>\n",
+       "      <th id=\"T_556fc_level1_row6\" class=\"row_heading level1 row6\" >Plastic construction waste</th>\n",
+       "      <td id=\"T_556fc_row6_col0\" class=\"data row6 col0\" >0.14</td>\n",
+       "      <td id=\"T_556fc_row6_col1\" class=\"data row6 col1\" >1970</td>\n",
+       "      <td id=\"T_556fc_row6_col2\" class=\"data row6 col2\" >0.51</td>\n",
+       "      <td id=\"T_556fc_row6_col3\" class=\"data row6 col3\" >0.02</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row7\" class=\"row_heading level0 row7\" >G95</th>\n",
-       "      <th id=\"T_d0aab_level1_row7\" class=\"row_heading level1 row7\" >Cotton bud/swab sticks</th>\n",
-       "      <td id=\"T_d0aab_row7_col0\" class=\"data row7 col0\" >0.39</td>\n",
-       "      <td id=\"T_d0aab_row7_col1\" class=\"data row7 col1\" >4777</td>\n",
-       "      <td id=\"T_d0aab_row7_col2\" class=\"data row7 col2\" >0.74</td>\n",
-       "      <td id=\"T_d0aab_row7_col3\" class=\"data row7 col3\" >0.04</td>\n",
+       "      <th id=\"T_556fc_level0_row7\" class=\"row_heading level0 row7\" >G95</th>\n",
+       "      <th id=\"T_556fc_level1_row7\" class=\"row_heading level1 row7\" >Cotton bud/swab sticks</th>\n",
+       "      <td id=\"T_556fc_row7_col0\" class=\"data row7 col0\" >0.39</td>\n",
+       "      <td id=\"T_556fc_row7_col1\" class=\"data row7 col1\" >4777</td>\n",
+       "      <td id=\"T_556fc_row7_col2\" class=\"data row7 col2\" >0.74</td>\n",
+       "      <td id=\"T_556fc_row7_col3\" class=\"data row7 col3\" >0.04</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row8\" class=\"row_heading level0 row8\" >G96</th>\n",
-       "      <th id=\"T_d0aab_level1_row8\" class=\"row_heading level1 row8\" >Sanitary pads /panty liners/tampons and applicators</th>\n",
-       "      <td id=\"T_d0aab_row8_col0\" class=\"data row8 col0\" >0.04</td>\n",
-       "      <td id=\"T_d0aab_row8_col1\" class=\"data row8 col1\" >373</td>\n",
-       "      <td id=\"T_d0aab_row8_col2\" class=\"data row8 col2\" >0.29</td>\n",
-       "      <td id=\"T_d0aab_row8_col3\" class=\"data row8 col3\" >0.00</td>\n",
+       "      <th id=\"T_556fc_level0_row8\" class=\"row_heading level0 row8\" >G96</th>\n",
+       "      <th id=\"T_556fc_level1_row8\" class=\"row_heading level1 row8\" >Sanitary pads /panty liners/tampons and applicators</th>\n",
+       "      <td id=\"T_556fc_row8_col0\" class=\"data row8 col0\" >0.04</td>\n",
+       "      <td id=\"T_556fc_row8_col1\" class=\"data row8 col1\" >373</td>\n",
+       "      <td id=\"T_556fc_row8_col2\" class=\"data row8 col2\" >0.29</td>\n",
+       "      <td id=\"T_556fc_row8_col3\" class=\"data row8 col3\" >0.00</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row9\" class=\"row_heading level0 row9\" >Gcaps</th>\n",
-       "      <th id=\"T_d0aab_level1_row9\" class=\"row_heading level1 row9\" >Plastic bottle lids</th>\n",
-       "      <td id=\"T_d0aab_row9_col0\" class=\"data row9 col0\" >0.31</td>\n",
-       "      <td id=\"T_d0aab_row9_col1\" class=\"data row9 col1\" >3953</td>\n",
-       "      <td id=\"T_d0aab_row9_col2\" class=\"data row9 col2\" >0.84</td>\n",
-       "      <td id=\"T_d0aab_row9_col3\" class=\"data row9 col3\" >0.04</td>\n",
+       "      <th id=\"T_556fc_level0_row9\" class=\"row_heading level0 row9\" >Gcaps</th>\n",
+       "      <th id=\"T_556fc_level1_row9\" class=\"row_heading level1 row9\" >Plastic bottle lids</th>\n",
+       "      <td id=\"T_556fc_row9_col0\" class=\"data row9 col0\" >0.31</td>\n",
+       "      <td id=\"T_556fc_row9_col1\" class=\"data row9 col1\" >3953</td>\n",
+       "      <td id=\"T_556fc_row9_col2\" class=\"data row9 col2\" >0.84</td>\n",
+       "      <td id=\"T_556fc_row9_col3\" class=\"data row9 col3\" >0.04</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row10\" class=\"row_heading level0 row10\" >Gfoam</th>\n",
-       "      <th id=\"T_d0aab_level1_row10\" class=\"row_heading level1 row10\" >Expanded polystyrene</th>\n",
-       "      <td id=\"T_d0aab_row10_col0\" class=\"data row10 col0\" >1.02</td>\n",
-       "      <td id=\"T_d0aab_row10_col1\" class=\"data row10 col1\" >12871</td>\n",
-       "      <td id=\"T_d0aab_row10_col2\" class=\"data row10 col2\" >0.81</td>\n",
-       "      <td id=\"T_d0aab_row10_col3\" class=\"data row10 col3\" >0.12</td>\n",
+       "      <th id=\"T_556fc_level0_row10\" class=\"row_heading level0 row10\" >Gfoam</th>\n",
+       "      <th id=\"T_556fc_level1_row10\" class=\"row_heading level1 row10\" >Expanded polystyrene</th>\n",
+       "      <td id=\"T_556fc_row10_col0\" class=\"data row10 col0\" >1.02</td>\n",
+       "      <td id=\"T_556fc_row10_col1\" class=\"data row10 col1\" >12871</td>\n",
+       "      <td id=\"T_556fc_row10_col2\" class=\"data row10 col2\" >0.81</td>\n",
+       "      <td id=\"T_556fc_row10_col3\" class=\"data row10 col3\" >0.12</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row11\" class=\"row_heading level0 row11\" >Gfrags</th>\n",
-       "      <th id=\"T_d0aab_level1_row11\" class=\"row_heading level1 row11\" >Fragmented plastics</th>\n",
-       "      <td id=\"T_d0aab_row11_col0\" class=\"data row11 col0\" >1.34</td>\n",
-       "      <td id=\"T_d0aab_row11_col1\" class=\"data row11 col1\" >17479</td>\n",
-       "      <td id=\"T_d0aab_row11_col2\" class=\"data row11 col2\" >0.93</td>\n",
-       "      <td id=\"T_d0aab_row11_col3\" class=\"data row11 col3\" >0.16</td>\n",
+       "      <th id=\"T_556fc_level0_row11\" class=\"row_heading level0 row11\" >Gfrags</th>\n",
+       "      <th id=\"T_556fc_level1_row11\" class=\"row_heading level1 row11\" >Fragmented plastics</th>\n",
+       "      <td id=\"T_556fc_row11_col0\" class=\"data row11 col0\" >1.34</td>\n",
+       "      <td id=\"T_556fc_row11_col1\" class=\"data row11 col1\" >17479</td>\n",
+       "      <td id=\"T_556fc_row11_col2\" class=\"data row11 col2\" >0.93</td>\n",
+       "      <td id=\"T_556fc_row11_col3\" class=\"data row11 col3\" >0.16</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f602427b50>"
+       "<pandas.io.formats.style.Styler at 0x7c6c3ed037f0>"
       ]
      },
      "execution_count": 6,
@@ -759,12 +759,19 @@
    "execution_count": 7,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -818,7 +825,9 @@
     "slideshow": {
      "slide_type": ""
     },
-    "tags": []
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -842,12 +851,19 @@
    "execution_count": 9,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -867,12 +883,19 @@
    "execution_count": 10,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -918,12 +941,19 @@
    "execution_count": 11,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1023,12 +1053,19 @@
    "execution_count": 12,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1040,12 +1077,19 @@
    "execution_count": 13,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1116,12 +1160,19 @@
    "execution_count": 14,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1216,33 +1267,40 @@
    "execution_count": 15,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_0e66b tr:nth-child(even) {\n",
+       "#T_9a101 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_0e66b tr:nth-child(odd) {\n",
+       "#T_9a101 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_0e66b tr {\n",
+       "#T_9a101 tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_0e66b th:nth-child(1) {\n",
+       "#T_9a101 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_0e66b caption {\n",
+       "#T_9a101 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1250,120 +1308,120 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_0e66b\">\n",
+       "<table id=\"T_9a101\">\n",
        "  <caption>Table 4: The 94% probability interval of the objects of interest for Saint Sulpice. The median value is used for the predictions</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_0e66b_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_0e66b_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_0e66b_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_0e66b_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_0e66b_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_0e66b_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_0e66b_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_0e66b_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_0e66b_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_0e66b_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_9a101_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_9a101_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_9a101_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_9a101_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_9a101_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_9a101_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_9a101_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_9a101_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_9a101_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_9a101_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row0\" class=\"row_heading level0 row0\" >3%</th>\n",
-       "      <td id=\"T_0e66b_row0_col0\" class=\"data row0 col0\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col1\" class=\"data row0 col1\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col2\" class=\"data row0 col2\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col6\" class=\"data row0 col6\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col7\" class=\"data row0 col7\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col8\" class=\"data row0 col8\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col9\" class=\"data row0 col9\" >0.00</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row1\" class=\"row_heading level0 row1\" >25%</th>\n",
-       "      <td id=\"T_0e66b_row1_col0\" class=\"data row1 col0\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col2\" class=\"data row1 col2\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col3\" class=\"data row1 col3\" >0.01</td>\n",
-       "      <td id=\"T_0e66b_row1_col4\" class=\"data row1 col4\" >0.01</td>\n",
-       "      <td id=\"T_0e66b_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col6\" class=\"data row1 col6\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col7\" class=\"data row1 col7\" >0.01</td>\n",
-       "      <td id=\"T_0e66b_row1_col8\" class=\"data row1 col8\" >0.03</td>\n",
-       "      <td id=\"T_0e66b_row1_col9\" class=\"data row1 col9\" >0.00</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row2\" class=\"row_heading level0 row2\" >48%</th>\n",
-       "      <td id=\"T_0e66b_row2_col0\" class=\"data row2 col0\" >0.03</td>\n",
-       "      <td id=\"T_0e66b_row2_col1\" class=\"data row2 col1\" >0.42</td>\n",
-       "      <td id=\"T_0e66b_row2_col2\" class=\"data row2 col2\" >0.13</td>\n",
-       "      <td id=\"T_0e66b_row2_col3\" class=\"data row2 col3\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row2_col4\" class=\"data row2 col4\" >0.14</td>\n",
-       "      <td id=\"T_0e66b_row2_col5\" class=\"data row2 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row2_col6\" class=\"data row2 col6\" >0.30</td>\n",
-       "      <td id=\"T_0e66b_row2_col7\" class=\"data row2 col7\" >0.08</td>\n",
-       "      <td id=\"T_0e66b_row2_col8\" class=\"data row2 col8\" >0.12</td>\n",
-       "      <td id=\"T_0e66b_row2_col9\" class=\"data row2 col9\" >0.35</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row3\" class=\"row_heading level0 row3\" >50%</th>\n",
-       "      <td id=\"T_0e66b_row3_col0\" class=\"data row3 col0\" >0.08</td>\n",
-       "      <td id=\"T_0e66b_row3_col1\" class=\"data row3 col1\" >0.45</td>\n",
-       "      <td id=\"T_0e66b_row3_col2\" class=\"data row3 col2\" >0.13</td>\n",
-       "      <td id=\"T_0e66b_row3_col3\" class=\"data row3 col3\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row3_col4\" class=\"data row3 col4\" >0.16</td>\n",
-       "      <td id=\"T_0e66b_row3_col5\" class=\"data row3 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row3_col6\" class=\"data row3 col6\" >0.32</td>\n",
-       "      <td id=\"T_0e66b_row3_col7\" class=\"data row3 col7\" >0.09</td>\n",
-       "      <td id=\"T_0e66b_row3_col8\" class=\"data row3 col8\" >0.14</td>\n",
-       "      <td id=\"T_0e66b_row3_col9\" class=\"data row3 col9\" >0.41</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row4\" class=\"row_heading level0 row4\" >52%</th>\n",
-       "      <td id=\"T_0e66b_row4_col0\" class=\"data row4 col0\" >0.10</td>\n",
-       "      <td id=\"T_0e66b_row4_col1\" class=\"data row4 col1\" >0.46</td>\n",
-       "      <td id=\"T_0e66b_row4_col2\" class=\"data row4 col2\" >0.13</td>\n",
-       "      <td id=\"T_0e66b_row4_col3\" class=\"data row4 col3\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row4_col4\" class=\"data row4 col4\" >0.17</td>\n",
-       "      <td id=\"T_0e66b_row4_col5\" class=\"data row4 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row4_col6\" class=\"data row4 col6\" >0.34</td>\n",
-       "      <td id=\"T_0e66b_row4_col7\" class=\"data row4 col7\" >0.09</td>\n",
-       "      <td id=\"T_0e66b_row4_col8\" class=\"data row4 col8\" >0.14</td>\n",
-       "      <td id=\"T_0e66b_row4_col9\" class=\"data row4 col9\" >0.50</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row5\" class=\"row_heading level0 row5\" >75%</th>\n",
-       "      <td id=\"T_0e66b_row5_col0\" class=\"data row5 col0\" >0.54</td>\n",
-       "      <td id=\"T_0e66b_row5_col1\" class=\"data row5 col1\" >0.66</td>\n",
-       "      <td id=\"T_0e66b_row5_col2\" class=\"data row5 col2\" >0.48</td>\n",
-       "      <td id=\"T_0e66b_row5_col3\" class=\"data row5 col3\" >0.06</td>\n",
-       "      <td id=\"T_0e66b_row5_col4\" class=\"data row5 col4\" >0.31</td>\n",
-       "      <td id=\"T_0e66b_row5_col5\" class=\"data row5 col5\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row5_col6\" class=\"data row5 col6\" >0.52</td>\n",
-       "      <td id=\"T_0e66b_row5_col7\" class=\"data row5 col7\" >0.12</td>\n",
-       "      <td id=\"T_0e66b_row5_col8\" class=\"data row5 col8\" >0.23</td>\n",
-       "      <td id=\"T_0e66b_row5_col9\" class=\"data row5 col9\" >0.82</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row6\" class=\"row_heading level0 row6\" >97%</th>\n",
-       "      <td id=\"T_0e66b_row6_col0\" class=\"data row6 col0\" >1.39</td>\n",
-       "      <td id=\"T_0e66b_row6_col1\" class=\"data row6 col1\" >1.29</td>\n",
-       "      <td id=\"T_0e66b_row6_col2\" class=\"data row6 col2\" >0.91</td>\n",
-       "      <td id=\"T_0e66b_row6_col3\" class=\"data row6 col3\" >0.11</td>\n",
-       "      <td id=\"T_0e66b_row6_col4\" class=\"data row6 col4\" >2.83</td>\n",
-       "      <td id=\"T_0e66b_row6_col5\" class=\"data row6 col5\" >0.09</td>\n",
-       "      <td id=\"T_0e66b_row6_col6\" class=\"data row6 col6\" >1.00</td>\n",
-       "      <td id=\"T_0e66b_row6_col7\" class=\"data row6 col7\" >0.22</td>\n",
-       "      <td id=\"T_0e66b_row6_col8\" class=\"data row6 col8\" >0.41</td>\n",
-       "      <td id=\"T_0e66b_row6_col9\" class=\"data row6 col9\" >2.75</td>\n",
+       "      <th id=\"T_9a101_level0_row0\" class=\"row_heading level0 row0\" >3%</th>\n",
+       "      <td id=\"T_9a101_row0_col0\" class=\"data row0 col0\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col1\" class=\"data row0 col1\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col2\" class=\"data row0 col2\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col6\" class=\"data row0 col6\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col7\" class=\"data row0 col7\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col8\" class=\"data row0 col8\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col9\" class=\"data row0 col9\" >0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row1\" class=\"row_heading level0 row1\" >25%</th>\n",
+       "      <td id=\"T_9a101_row1_col0\" class=\"data row1 col0\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col1\" class=\"data row1 col1\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row1_col2\" class=\"data row1 col2\" >0.03</td>\n",
+       "      <td id=\"T_9a101_row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col4\" class=\"data row1 col4\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col6\" class=\"data row1 col6\" >0.01</td>\n",
+       "      <td id=\"T_9a101_row1_col7\" class=\"data row1 col7\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col8\" class=\"data row1 col8\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row1_col9\" class=\"data row1 col9\" >0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row2\" class=\"row_heading level0 row2\" >48%</th>\n",
+       "      <td id=\"T_9a101_row2_col0\" class=\"data row2 col0\" >0.08</td>\n",
+       "      <td id=\"T_9a101_row2_col1\" class=\"data row2 col1\" >0.46</td>\n",
+       "      <td id=\"T_9a101_row2_col2\" class=\"data row2 col2\" >0.35</td>\n",
+       "      <td id=\"T_9a101_row2_col3\" class=\"data row2 col3\" >0.03</td>\n",
+       "      <td id=\"T_9a101_row2_col4\" class=\"data row2 col4\" >0.16</td>\n",
+       "      <td id=\"T_9a101_row2_col5\" class=\"data row2 col5\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row2_col6\" class=\"data row2 col6\" >0.32</td>\n",
+       "      <td id=\"T_9a101_row2_col7\" class=\"data row2 col7\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row2_col8\" class=\"data row2 col8\" >0.11</td>\n",
+       "      <td id=\"T_9a101_row2_col9\" class=\"data row2 col9\" >0.68</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row3\" class=\"row_heading level0 row3\" >50%</th>\n",
+       "      <td id=\"T_9a101_row3_col0\" class=\"data row3 col0\" >0.12</td>\n",
+       "      <td id=\"T_9a101_row3_col1\" class=\"data row3 col1\" >0.47</td>\n",
+       "      <td id=\"T_9a101_row3_col2\" class=\"data row3 col2\" >0.39</td>\n",
+       "      <td id=\"T_9a101_row3_col3\" class=\"data row3 col3\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row3_col4\" class=\"data row3 col4\" >0.16</td>\n",
+       "      <td id=\"T_9a101_row3_col5\" class=\"data row3 col5\" >0.01</td>\n",
+       "      <td id=\"T_9a101_row3_col6\" class=\"data row3 col6\" >0.32</td>\n",
+       "      <td id=\"T_9a101_row3_col7\" class=\"data row3 col7\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row3_col8\" class=\"data row3 col8\" >0.11</td>\n",
+       "      <td id=\"T_9a101_row3_col9\" class=\"data row3 col9\" >0.74</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row4\" class=\"row_heading level0 row4\" >52%</th>\n",
+       "      <td id=\"T_9a101_row4_col0\" class=\"data row4 col0\" >0.22</td>\n",
+       "      <td id=\"T_9a101_row4_col1\" class=\"data row4 col1\" >0.48</td>\n",
+       "      <td id=\"T_9a101_row4_col2\" class=\"data row4 col2\" >0.43</td>\n",
+       "      <td id=\"T_9a101_row4_col3\" class=\"data row4 col3\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row4_col4\" class=\"data row4 col4\" >0.22</td>\n",
+       "      <td id=\"T_9a101_row4_col5\" class=\"data row4 col5\" >0.02</td>\n",
+       "      <td id=\"T_9a101_row4_col6\" class=\"data row4 col6\" >0.34</td>\n",
+       "      <td id=\"T_9a101_row4_col7\" class=\"data row4 col7\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row4_col8\" class=\"data row4 col8\" >0.12</td>\n",
+       "      <td id=\"T_9a101_row4_col9\" class=\"data row4 col9\" >0.74</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row5\" class=\"row_heading level0 row5\" >75%</th>\n",
+       "      <td id=\"T_9a101_row5_col0\" class=\"data row5 col0\" >0.68</td>\n",
+       "      <td id=\"T_9a101_row5_col1\" class=\"data row5 col1\" >0.93</td>\n",
+       "      <td id=\"T_9a101_row5_col2\" class=\"data row5 col2\" >0.57</td>\n",
+       "      <td id=\"T_9a101_row5_col3\" class=\"data row5 col3\" >0.08</td>\n",
+       "      <td id=\"T_9a101_row5_col4\" class=\"data row5 col4\" >0.33</td>\n",
+       "      <td id=\"T_9a101_row5_col5\" class=\"data row5 col5\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row5_col6\" class=\"data row5 col6\" >0.52</td>\n",
+       "      <td id=\"T_9a101_row5_col7\" class=\"data row5 col7\" >0.08</td>\n",
+       "      <td id=\"T_9a101_row5_col8\" class=\"data row5 col8\" >0.23</td>\n",
+       "      <td id=\"T_9a101_row5_col9\" class=\"data row5 col9\" >1.24</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row6\" class=\"row_heading level0 row6\" >97%</th>\n",
+       "      <td id=\"T_9a101_row6_col0\" class=\"data row6 col0\" >1.46</td>\n",
+       "      <td id=\"T_9a101_row6_col1\" class=\"data row6 col1\" >1.47</td>\n",
+       "      <td id=\"T_9a101_row6_col2\" class=\"data row6 col2\" >1.21</td>\n",
+       "      <td id=\"T_9a101_row6_col3\" class=\"data row6 col3\" >0.11</td>\n",
+       "      <td id=\"T_9a101_row6_col4\" class=\"data row6 col4\" >0.64</td>\n",
+       "      <td id=\"T_9a101_row6_col5\" class=\"data row6 col5\" >5.58</td>\n",
+       "      <td id=\"T_9a101_row6_col6\" class=\"data row6 col6\" >1.11</td>\n",
+       "      <td id=\"T_9a101_row6_col7\" class=\"data row6 col7\" >0.20</td>\n",
+       "      <td id=\"T_9a101_row6_col8\" class=\"data row6 col8\" >0.50</td>\n",
+       "      <td id=\"T_9a101_row6_col9\" class=\"data row6 col9\" >5.05</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5cff55910>"
+       "<pandas.io.formats.style.Styler at 0x7c6c3ec29580>"
       ]
      },
      "execution_count": 15,
@@ -1415,12 +1473,19 @@
    "execution_count": 16,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1451,12 +1516,19 @@
    "execution_count": 17,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1469,33 +1541,40 @@
    "execution_count": 18,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_ac8e3 tr:nth-child(even) {\n",
+       "#T_abf7a tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_ac8e3 tr:nth-child(odd) {\n",
+       "#T_abf7a tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_ac8e3 tr {\n",
+       "#T_abf7a tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_ac8e3 th:nth-child(1) {\n",
+       "#T_abf7a th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_ac8e3 caption {\n",
+       "#T_abf7a caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1503,146 +1582,146 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_ac8e3\">\n",
+       "<table id=\"T_abf7a\">\n",
        "  <caption>Table 5: The estimated amount in pcs/meter for each object that the participants expected to find.</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_ac8e3_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_ac8e3_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_ac8e3_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_ac8e3_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_ac8e3_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_ac8e3_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_ac8e3_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_ac8e3_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_ac8e3_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_ac8e3_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_abf7a_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_abf7a_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_abf7a_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_abf7a_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_abf7a_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_abf7a_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_abf7a_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_abf7a_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_abf7a_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_abf7a_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
-       "      <td id=\"T_ac8e3_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
-       "      <td id=\"T_ac8e3_row0_col1\" class=\"data row0 col1\" >1.12</td>\n",
-       "      <td id=\"T_ac8e3_row0_col2\" class=\"data row0 col2\" >0.54</td>\n",
-       "      <td id=\"T_ac8e3_row0_col3\" class=\"data row0 col3\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row0_col4\" class=\"data row0 col4\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row0_col5\" class=\"data row0 col5\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row0_col6\" class=\"data row0 col6\" >0.39</td>\n",
-       "      <td id=\"T_ac8e3_row0_col7\" class=\"data row0 col7\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row0_col8\" class=\"data row0 col8\" >0.31</td>\n",
-       "      <td id=\"T_ac8e3_row0_col9\" class=\"data row0 col9\" >1.34</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
-       "      <td id=\"T_ac8e3_row1_col0\" class=\"data row1 col0\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row1_col1\" class=\"data row1 col1\" >0.57</td>\n",
-       "      <td id=\"T_ac8e3_row1_col2\" class=\"data row1 col2\" >0.24</td>\n",
-       "      <td id=\"T_ac8e3_row1_col3\" class=\"data row1 col3\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row1_col4\" class=\"data row1 col4\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row1_col5\" class=\"data row1 col5\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row1_col6\" class=\"data row1 col6\" >0.16</td>\n",
-       "      <td id=\"T_ac8e3_row1_col7\" class=\"data row1 col7\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row1_col8\" class=\"data row1 col8\" >0.14</td>\n",
-       "      <td id=\"T_ac8e3_row1_col9\" class=\"data row1 col9\" >0.22</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
-       "      <td id=\"T_ac8e3_row2_col0\" class=\"data row2 col0\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row2_col1\" class=\"data row2 col1\" >0.80</td>\n",
-       "      <td id=\"T_ac8e3_row2_col2\" class=\"data row2 col2\" >0.20</td>\n",
-       "      <td id=\"T_ac8e3_row2_col3\" class=\"data row2 col3\" >0.02</td>\n",
-       "      <td id=\"T_ac8e3_row2_col4\" class=\"data row2 col4\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row2_col5\" class=\"data row2 col5\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row2_col6\" class=\"data row2 col6\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row2_col7\" class=\"data row2 col7\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row2_col8\" class=\"data row2 col8\" >0.25</td>\n",
-       "      <td id=\"T_ac8e3_row2_col9\" class=\"data row2 col9\" >1.20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
-       "      <td id=\"T_ac8e3_row3_col0\" class=\"data row3 col0\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row3_col1\" class=\"data row3 col1\" >0.35</td>\n",
-       "      <td id=\"T_ac8e3_row3_col2\" class=\"data row3 col2\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row3_col3\" class=\"data row3 col3\" >0.03</td>\n",
-       "      <td id=\"T_ac8e3_row3_col4\" class=\"data row3 col4\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row3_col5\" class=\"data row3 col5\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row3_col6\" class=\"data row3 col6\" >0.06</td>\n",
-       "      <td id=\"T_ac8e3_row3_col7\" class=\"data row3 col7\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row3_col8\" class=\"data row3 col8\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row3_col9\" class=\"data row3 col9\" >0.50</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
-       "      <td id=\"T_ac8e3_row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
-       "      <td id=\"T_ac8e3_row4_col1\" class=\"data row4 col1\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row4_col2\" class=\"data row4 col2\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row4_col3\" class=\"data row4 col3\" >0.02</td>\n",
-       "      <td id=\"T_ac8e3_row4_col4\" class=\"data row4 col4\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row4_col5\" class=\"data row4 col5\" >0.00</td>\n",
-       "      <td id=\"T_ac8e3_row4_col6\" class=\"data row4 col6\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row4_col7\" class=\"data row4 col7\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row4_col8\" class=\"data row4 col8\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row4_col9\" class=\"data row4 col9\" >0.12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
-       "      <td id=\"T_ac8e3_row5_col0\" class=\"data row5 col0\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row5_col1\" class=\"data row5 col1\" >0.50</td>\n",
-       "      <td id=\"T_ac8e3_row5_col2\" class=\"data row5 col2\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row5_col3\" class=\"data row5 col3\" >0.03</td>\n",
-       "      <td id=\"T_ac8e3_row5_col4\" class=\"data row5 col4\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row5_col5\" class=\"data row5 col5\" >0.00</td>\n",
-       "      <td id=\"T_ac8e3_row5_col6\" class=\"data row5 col6\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row5_col7\" class=\"data row5 col7\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row5_col8\" class=\"data row5 col8\" >0.20</td>\n",
-       "      <td id=\"T_ac8e3_row5_col9\" class=\"data row5 col9\" >0.20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
-       "      <td id=\"T_ac8e3_row6_col0\" class=\"data row6 col0\" >0.16</td>\n",
-       "      <td id=\"T_ac8e3_row6_col1\" class=\"data row6 col1\" >1.12</td>\n",
-       "      <td id=\"T_ac8e3_row6_col2\" class=\"data row6 col2\" >0.54</td>\n",
-       "      <td id=\"T_ac8e3_row6_col3\" class=\"data row6 col3\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row6_col4\" class=\"data row6 col4\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row6_col5\" class=\"data row6 col5\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row6_col6\" class=\"data row6 col6\" >0.39</td>\n",
-       "      <td id=\"T_ac8e3_row6_col7\" class=\"data row6 col7\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row6_col8\" class=\"data row6 col8\" >0.31</td>\n",
-       "      <td id=\"T_ac8e3_row6_col9\" class=\"data row6 col9\" >1.34</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
-       "      <td id=\"T_ac8e3_row7_col0\" class=\"data row7 col0\" >6.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col1\" class=\"data row7 col1\" >3.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col2\" class=\"data row7 col2\" >0.60</td>\n",
-       "      <td id=\"T_ac8e3_row7_col3\" class=\"data row7 col3\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row7_col4\" class=\"data row7 col4\" >0.40</td>\n",
-       "      <td id=\"T_ac8e3_row7_col5\" class=\"data row7 col5\" >0.03</td>\n",
-       "      <td id=\"T_ac8e3_row7_col6\" class=\"data row7 col6\" >0.80</td>\n",
-       "      <td id=\"T_ac8e3_row7_col7\" class=\"data row7 col7\" >1.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col8\" class=\"data row7 col8\" >2.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col9\" class=\"data row7 col9\" >1.34</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
-       "      <td id=\"T_ac8e3_row8_col0\" class=\"data row8 col0\" >0.40</td>\n",
-       "      <td id=\"T_ac8e3_row8_col1\" class=\"data row8 col1\" >1.50</td>\n",
-       "      <td id=\"T_ac8e3_row8_col2\" class=\"data row8 col2\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row8_col3\" class=\"data row8 col3\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row8_col4\" class=\"data row8 col4\" >1.10</td>\n",
-       "      <td id=\"T_ac8e3_row8_col5\" class=\"data row8 col5\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row8_col6\" class=\"data row8 col6\" >0.50</td>\n",
-       "      <td id=\"T_ac8e3_row8_col7\" class=\"data row8 col7\" >0.20</td>\n",
-       "      <td id=\"T_ac8e3_row8_col8\" class=\"data row8 col8\" >0.40</td>\n",
-       "      <td id=\"T_ac8e3_row8_col9\" class=\"data row8 col9\" >2.00</td>\n",
+       "      <th id=\"T_abf7a_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
+       "      <td id=\"T_abf7a_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
+       "      <td id=\"T_abf7a_row0_col1\" class=\"data row0 col1\" >1.12</td>\n",
+       "      <td id=\"T_abf7a_row0_col2\" class=\"data row0 col2\" >0.54</td>\n",
+       "      <td id=\"T_abf7a_row0_col3\" class=\"data row0 col3\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row0_col4\" class=\"data row0 col4\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row0_col5\" class=\"data row0 col5\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row0_col6\" class=\"data row0 col6\" >0.39</td>\n",
+       "      <td id=\"T_abf7a_row0_col7\" class=\"data row0 col7\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row0_col8\" class=\"data row0 col8\" >0.31</td>\n",
+       "      <td id=\"T_abf7a_row0_col9\" class=\"data row0 col9\" >1.34</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
+       "      <td id=\"T_abf7a_row1_col0\" class=\"data row1 col0\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row1_col1\" class=\"data row1 col1\" >0.57</td>\n",
+       "      <td id=\"T_abf7a_row1_col2\" class=\"data row1 col2\" >0.24</td>\n",
+       "      <td id=\"T_abf7a_row1_col3\" class=\"data row1 col3\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row1_col4\" class=\"data row1 col4\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row1_col5\" class=\"data row1 col5\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row1_col6\" class=\"data row1 col6\" >0.16</td>\n",
+       "      <td id=\"T_abf7a_row1_col7\" class=\"data row1 col7\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row1_col8\" class=\"data row1 col8\" >0.14</td>\n",
+       "      <td id=\"T_abf7a_row1_col9\" class=\"data row1 col9\" >0.22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
+       "      <td id=\"T_abf7a_row2_col0\" class=\"data row2 col0\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row2_col1\" class=\"data row2 col1\" >0.80</td>\n",
+       "      <td id=\"T_abf7a_row2_col2\" class=\"data row2 col2\" >0.20</td>\n",
+       "      <td id=\"T_abf7a_row2_col3\" class=\"data row2 col3\" >0.02</td>\n",
+       "      <td id=\"T_abf7a_row2_col4\" class=\"data row2 col4\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row2_col5\" class=\"data row2 col5\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row2_col6\" class=\"data row2 col6\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row2_col7\" class=\"data row2 col7\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row2_col8\" class=\"data row2 col8\" >0.25</td>\n",
+       "      <td id=\"T_abf7a_row2_col9\" class=\"data row2 col9\" >1.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
+       "      <td id=\"T_abf7a_row3_col0\" class=\"data row3 col0\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row3_col1\" class=\"data row3 col1\" >0.35</td>\n",
+       "      <td id=\"T_abf7a_row3_col2\" class=\"data row3 col2\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row3_col3\" class=\"data row3 col3\" >0.03</td>\n",
+       "      <td id=\"T_abf7a_row3_col4\" class=\"data row3 col4\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row3_col5\" class=\"data row3 col5\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row3_col6\" class=\"data row3 col6\" >0.06</td>\n",
+       "      <td id=\"T_abf7a_row3_col7\" class=\"data row3 col7\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row3_col8\" class=\"data row3 col8\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row3_col9\" class=\"data row3 col9\" >0.50</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
+       "      <td id=\"T_abf7a_row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
+       "      <td id=\"T_abf7a_row4_col1\" class=\"data row4 col1\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row4_col2\" class=\"data row4 col2\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row4_col3\" class=\"data row4 col3\" >0.02</td>\n",
+       "      <td id=\"T_abf7a_row4_col4\" class=\"data row4 col4\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row4_col5\" class=\"data row4 col5\" >0.00</td>\n",
+       "      <td id=\"T_abf7a_row4_col6\" class=\"data row4 col6\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row4_col7\" class=\"data row4 col7\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row4_col8\" class=\"data row4 col8\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row4_col9\" class=\"data row4 col9\" >0.12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
+       "      <td id=\"T_abf7a_row5_col0\" class=\"data row5 col0\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row5_col1\" class=\"data row5 col1\" >0.50</td>\n",
+       "      <td id=\"T_abf7a_row5_col2\" class=\"data row5 col2\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row5_col3\" class=\"data row5 col3\" >0.03</td>\n",
+       "      <td id=\"T_abf7a_row5_col4\" class=\"data row5 col4\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row5_col5\" class=\"data row5 col5\" >0.00</td>\n",
+       "      <td id=\"T_abf7a_row5_col6\" class=\"data row5 col6\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row5_col7\" class=\"data row5 col7\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row5_col8\" class=\"data row5 col8\" >0.20</td>\n",
+       "      <td id=\"T_abf7a_row5_col9\" class=\"data row5 col9\" >0.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
+       "      <td id=\"T_abf7a_row6_col0\" class=\"data row6 col0\" >0.16</td>\n",
+       "      <td id=\"T_abf7a_row6_col1\" class=\"data row6 col1\" >1.12</td>\n",
+       "      <td id=\"T_abf7a_row6_col2\" class=\"data row6 col2\" >0.54</td>\n",
+       "      <td id=\"T_abf7a_row6_col3\" class=\"data row6 col3\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row6_col4\" class=\"data row6 col4\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row6_col5\" class=\"data row6 col5\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row6_col6\" class=\"data row6 col6\" >0.39</td>\n",
+       "      <td id=\"T_abf7a_row6_col7\" class=\"data row6 col7\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row6_col8\" class=\"data row6 col8\" >0.31</td>\n",
+       "      <td id=\"T_abf7a_row6_col9\" class=\"data row6 col9\" >1.34</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
+       "      <td id=\"T_abf7a_row7_col0\" class=\"data row7 col0\" >6.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col1\" class=\"data row7 col1\" >3.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col2\" class=\"data row7 col2\" >0.60</td>\n",
+       "      <td id=\"T_abf7a_row7_col3\" class=\"data row7 col3\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row7_col4\" class=\"data row7 col4\" >0.40</td>\n",
+       "      <td id=\"T_abf7a_row7_col5\" class=\"data row7 col5\" >0.03</td>\n",
+       "      <td id=\"T_abf7a_row7_col6\" class=\"data row7 col6\" >0.80</td>\n",
+       "      <td id=\"T_abf7a_row7_col7\" class=\"data row7 col7\" >1.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col8\" class=\"data row7 col8\" >2.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col9\" class=\"data row7 col9\" >1.34</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
+       "      <td id=\"T_abf7a_row8_col0\" class=\"data row8 col0\" >0.40</td>\n",
+       "      <td id=\"T_abf7a_row8_col1\" class=\"data row8 col1\" >1.50</td>\n",
+       "      <td id=\"T_abf7a_row8_col2\" class=\"data row8 col2\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row8_col3\" class=\"data row8 col3\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row8_col4\" class=\"data row8 col4\" >1.10</td>\n",
+       "      <td id=\"T_abf7a_row8_col5\" class=\"data row8 col5\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row8_col6\" class=\"data row8 col6\" >0.50</td>\n",
+       "      <td id=\"T_abf7a_row8_col7\" class=\"data row8 col7\" >0.20</td>\n",
+       "      <td id=\"T_abf7a_row8_col8\" class=\"data row8 col8\" >0.40</td>\n",
+       "      <td id=\"T_abf7a_row8_col9\" class=\"data row8 col9\" >2.00</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c13c8700>"
+       "<pandas.io.formats.style.Styler at 0x7c6c098db280>"
       ]
      },
      "execution_count": 18,
@@ -1700,33 +1779,40 @@
    "execution_count": 19,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_208b1 tr:nth-child(even) {\n",
+       "#T_b354f tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_208b1 tr:nth-child(odd) {\n",
+       "#T_b354f tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_208b1 tr {\n",
+       "#T_b354f tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_208b1 th:nth-child(1) {\n",
+       "#T_b354f th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_208b1 caption {\n",
+       "#T_b354f caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1734,55 +1820,55 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_208b1\">\n",
+       "<table id=\"T_b354f\">\n",
        "  <caption>Table 6: The survey results of the objects of interest on October 5, 2023 in pieces per meter</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_208b1_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_208b1_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_208b1_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_208b1_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_208b1_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_208b1_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_208b1_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_208b1_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_208b1_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_208b1_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_b354f_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_b354f_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_b354f_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_b354f_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_b354f_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_b354f_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_b354f_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_b354f_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_b354f_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_b354f_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_208b1_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
-       "      <td id=\"T_208b1_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
-       "      <td id=\"T_208b1_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
-       "      <td id=\"T_208b1_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
-       "      <td id=\"T_208b1_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
-       "      <td id=\"T_208b1_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
-       "      <td id=\"T_208b1_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
-       "      <td id=\"T_208b1_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
-       "      <td id=\"T_208b1_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_208b1_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
-       "      <td id=\"T_208b1_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
-       "      <td id=\"T_208b1_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
-       "      <td id=\"T_208b1_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
-       "      <td id=\"T_208b1_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
-       "      <td id=\"T_208b1_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
-       "      <td id=\"T_208b1_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
-       "      <td id=\"T_208b1_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
-       "      <td id=\"T_208b1_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
+       "      <th id=\"T_b354f_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
+       "      <td id=\"T_b354f_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
+       "      <td id=\"T_b354f_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
+       "      <td id=\"T_b354f_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
+       "      <td id=\"T_b354f_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
+       "      <td id=\"T_b354f_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
+       "      <td id=\"T_b354f_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
+       "      <td id=\"T_b354f_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
+       "      <td id=\"T_b354f_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_b354f_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
+       "      <td id=\"T_b354f_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
+       "      <td id=\"T_b354f_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
+       "      <td id=\"T_b354f_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
+       "      <td id=\"T_b354f_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
+       "      <td id=\"T_b354f_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
+       "      <td id=\"T_b354f_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
+       "      <td id=\"T_b354f_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
+       "      <td id=\"T_b354f_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c16359d0>"
+       "<pandas.io.formats.style.Styler at 0x7c6bfdd33850>"
       ]
      },
      "execution_count": 19,
@@ -1838,21 +1924,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_46124 tr:nth-child(even) {\n",
+       "#T_075e0 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_46124 tr:nth-child(odd) {\n",
+       "#T_075e0 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_46124 tr {\n",
+       "#T_075e0 tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_46124 th:nth-child(1) {\n",
+       "#T_075e0 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_46124 caption {\n",
+       "#T_075e0 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1860,55 +1946,55 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_46124\">\n",
+       "<table id=\"T_075e0\">\n",
        "  <caption>Table 6: The survey results of the objects of interest on October 5, 2023 in pieces per meter</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_46124_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_46124_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_46124_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_46124_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_46124_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_46124_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_46124_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_46124_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_46124_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_46124_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_075e0_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_075e0_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_075e0_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_075e0_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_075e0_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_075e0_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_075e0_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_075e0_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_075e0_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_075e0_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_46124_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
-       "      <td id=\"T_46124_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
-       "      <td id=\"T_46124_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
-       "      <td id=\"T_46124_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
-       "      <td id=\"T_46124_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
-       "      <td id=\"T_46124_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
-       "      <td id=\"T_46124_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
-       "      <td id=\"T_46124_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
-       "      <td id=\"T_46124_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
-       "      <td id=\"T_46124_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
-       "      <td id=\"T_46124_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_46124_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
-       "      <td id=\"T_46124_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
-       "      <td id=\"T_46124_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
-       "      <td id=\"T_46124_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
-       "      <td id=\"T_46124_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
-       "      <td id=\"T_46124_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
-       "      <td id=\"T_46124_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
-       "      <td id=\"T_46124_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
-       "      <td id=\"T_46124_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
-       "      <td id=\"T_46124_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
-       "      <td id=\"T_46124_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
+       "      <th id=\"T_075e0_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
+       "      <td id=\"T_075e0_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
+       "      <td id=\"T_075e0_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
+       "      <td id=\"T_075e0_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
+       "      <td id=\"T_075e0_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
+       "      <td id=\"T_075e0_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
+       "      <td id=\"T_075e0_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
+       "      <td id=\"T_075e0_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
+       "      <td id=\"T_075e0_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_075e0_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
+       "      <td id=\"T_075e0_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
+       "      <td id=\"T_075e0_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
+       "      <td id=\"T_075e0_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
+       "      <td id=\"T_075e0_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
+       "      <td id=\"T_075e0_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
+       "      <td id=\"T_075e0_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
+       "      <td id=\"T_075e0_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
+       "      <td id=\"T_075e0_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c0e1c910>"
+       "<pandas.io.formats.style.Styler at 0x7c6bfd855ac0>"
       ]
      },
      "execution_count": 20,
@@ -2095,20 +2181,6 @@
     "p_diff_predicted[\"source\"] = \"difference² of predicted\""
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "editable": true,
-    "pycharm": {
-     "name": "#%% md\n"
-    },
-    "slideshow": {
-     "slide_type": ""
-    },
-    "tags": []
-   },
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": 24,
@@ -2178,21 +2250,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_a043f tr:nth-child(even) {\n",
+       "#T_565a7 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_a043f tr:nth-child(odd) {\n",
+       "#T_565a7 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_a043f tr {\n",
+       "#T_565a7 tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_a043f th:nth-child(1) {\n",
+       "#T_565a7 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_a043f caption {\n",
+       "#T_565a7 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -2200,75 +2272,75 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_a043f\">\n",
+       "<table id=\"T_565a7\">\n",
        "  <caption>Table 7: The average difference between what was found and the estimates of the participants and what was predicted using the empirical Bayes method</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_a043f_level0_col0\" class=\"col_heading level0 col0\" colspan=\"2\">average</th>\n",
+       "      <th id=\"T_565a7_level0_col0\" class=\"col_heading level0 col0\" colspan=\"2\">average</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th class=\"index_name level1\" >source</th>\n",
-       "      <th id=\"T_a043f_level1_col0\" class=\"col_heading level1 col0\" >difference² of estimated</th>\n",
-       "      <th id=\"T_a043f_level1_col1\" class=\"col_heading level1 col1\" >difference² of predicted</th>\n",
+       "      <th id=\"T_565a7_level1_col0\" class=\"col_heading level1 col0\" >difference² of estimated</th>\n",
+       "      <th id=\"T_565a7_level1_col1\" class=\"col_heading level1 col1\" >difference² of predicted</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
-       "      <td id=\"T_a043f_row0_col0\" class=\"data row0 col0\" >1.07</td>\n",
-       "      <td id=\"T_a043f_row0_col1\" class=\"data row0 col1\" >0.29</td>\n",
+       "      <th id=\"T_565a7_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
+       "      <td id=\"T_565a7_row0_col0\" class=\"data row0 col0\" >1.07</td>\n",
+       "      <td id=\"T_565a7_row0_col1\" class=\"data row0 col1\" >0.29</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
-       "      <td id=\"T_a043f_row1_col0\" class=\"data row1 col0\" >2.32</td>\n",
-       "      <td id=\"T_a043f_row1_col1\" class=\"data row1 col1\" >1.89</td>\n",
+       "      <th id=\"T_565a7_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
+       "      <td id=\"T_565a7_row1_col0\" class=\"data row1 col0\" >2.32</td>\n",
+       "      <td id=\"T_565a7_row1_col1\" class=\"data row1 col1\" >1.87</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
-       "      <td id=\"T_a043f_row2_col0\" class=\"data row2 col0\" >0.31</td>\n",
-       "      <td id=\"T_a043f_row2_col1\" class=\"data row2 col1\" >0.21</td>\n",
+       "      <th id=\"T_565a7_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
+       "      <td id=\"T_565a7_row2_col0\" class=\"data row2 col0\" >0.31</td>\n",
+       "      <td id=\"T_565a7_row2_col1\" class=\"data row2 col1\" >0.20</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
-       "      <td id=\"T_a043f_row3_col0\" class=\"data row3 col0\" >0.11</td>\n",
-       "      <td id=\"T_a043f_row3_col1\" class=\"data row3 col1\" >0.07</td>\n",
+       "      <th id=\"T_565a7_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
+       "      <td id=\"T_565a7_row3_col0\" class=\"data row3 col0\" >0.11</td>\n",
+       "      <td id=\"T_565a7_row3_col1\" class=\"data row3 col1\" >0.07</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
-       "      <td id=\"T_a043f_row4_col0\" class=\"data row4 col0\" >0.26</td>\n",
-       "      <td id=\"T_a043f_row4_col1\" class=\"data row4 col1\" >0.16</td>\n",
+       "      <th id=\"T_565a7_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
+       "      <td id=\"T_565a7_row4_col0\" class=\"data row4 col0\" >0.26</td>\n",
+       "      <td id=\"T_565a7_row4_col1\" class=\"data row4 col1\" >0.16</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
-       "      <td id=\"T_a043f_row5_col0\" class=\"data row5 col0\" >0.03</td>\n",
-       "      <td id=\"T_a043f_row5_col1\" class=\"data row5 col1\" >0.00</td>\n",
+       "      <th id=\"T_565a7_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
+       "      <td id=\"T_565a7_row5_col0\" class=\"data row5 col0\" >0.03</td>\n",
+       "      <td id=\"T_565a7_row5_col1\" class=\"data row5 col1\" >0.01</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row6\" class=\"row_heading level0 row6\" >G95</th>\n",
-       "      <td id=\"T_a043f_row6_col0\" class=\"data row6 col0\" >0.52</td>\n",
-       "      <td id=\"T_a043f_row6_col1\" class=\"data row6 col1\" >0.27</td>\n",
+       "      <th id=\"T_565a7_level0_row6\" class=\"row_heading level0 row6\" >G95</th>\n",
+       "      <td id=\"T_565a7_row6_col0\" class=\"data row6 col0\" >0.52</td>\n",
+       "      <td id=\"T_565a7_row6_col1\" class=\"data row6 col1\" >0.27</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row7\" class=\"row_heading level0 row7\" >G96</th>\n",
-       "      <td id=\"T_a043f_row7_col0\" class=\"data row7 col0\" >0.15</td>\n",
-       "      <td id=\"T_a043f_row7_col1\" class=\"data row7 col1\" >0.05</td>\n",
+       "      <th id=\"T_565a7_level0_row7\" class=\"row_heading level0 row7\" >G96</th>\n",
+       "      <td id=\"T_565a7_row7_col0\" class=\"data row7 col0\" >0.15</td>\n",
+       "      <td id=\"T_565a7_row7_col1\" class=\"data row7 col1\" >0.02</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row8\" class=\"row_heading level0 row8\" >Gcaps</th>\n",
-       "      <td id=\"T_a043f_row8_col0\" class=\"data row8 col0\" >0.26</td>\n",
-       "      <td id=\"T_a043f_row8_col1\" class=\"data row8 col1\" >0.07</td>\n",
+       "      <th id=\"T_565a7_level0_row8\" class=\"row_heading level0 row8\" >Gcaps</th>\n",
+       "      <td id=\"T_565a7_row8_col0\" class=\"data row8 col0\" >0.26</td>\n",
+       "      <td id=\"T_565a7_row8_col1\" class=\"data row8 col1\" >0.10</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row9\" class=\"row_heading level0 row9\" >Gfrags</th>\n",
-       "      <td id=\"T_a043f_row9_col0\" class=\"data row9 col0\" >8.11</td>\n",
-       "      <td id=\"T_a043f_row9_col1\" class=\"data row9 col1\" >7.71</td>\n",
+       "      <th id=\"T_565a7_level0_row9\" class=\"row_heading level0 row9\" >Gfrags</th>\n",
+       "      <td id=\"T_565a7_row9_col0\" class=\"data row9 col0\" >8.11</td>\n",
+       "      <td id=\"T_565a7_row9_col1\" class=\"data row9 col1\" >7.38</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5cced1e20>"
+       "<pandas.io.formats.style.Styler at 0x7c6c0c679be0>"
       ]
      },
      "execution_count": 25,
@@ -2411,21 +2483,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_368fb tr:nth-child(even) {\n",
+       "#T_5cefd tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_368fb tr:nth-child(odd) {\n",
+       "#T_5cefd tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_368fb tr {\n",
+       "#T_5cefd tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_368fb th:nth-child(1) {\n",
+       "#T_5cefd th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_368fb caption {\n",
+       "#T_5cefd caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -2433,142 +2505,142 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_368fb\">\n",
+       "<table id=\"T_5cefd\">\n",
        "  <caption>Table 8: Whether the observed value fell within the predicted interval</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_368fb_level0_col0\" class=\"col_heading level0 col0\" >object</th>\n",
-       "      <th id=\"T_368fb_level0_col1\" class=\"col_heading level0 col1\" >within 96% HDI</th>\n",
-       "      <th id=\"T_368fb_level0_col2\" class=\"col_heading level0 col2\" >within 50% HDI</th>\n",
+       "      <th id=\"T_5cefd_level0_col0\" class=\"col_heading level0 col0\" >object</th>\n",
+       "      <th id=\"T_5cefd_level0_col1\" class=\"col_heading level0 col1\" >within 96% HDI</th>\n",
+       "      <th id=\"T_5cefd_level0_col2\" class=\"col_heading level0 col2\" >within 50% HDI</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
-       "      <td id=\"T_368fb_row0_col0\" class=\"data row0 col0\" >G112</td>\n",
-       "      <td id=\"T_368fb_row0_col1\" class=\"data row0 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row0_col2\" class=\"data row0 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
+       "      <td id=\"T_5cefd_row0_col0\" class=\"data row0 col0\" >G112</td>\n",
+       "      <td id=\"T_5cefd_row0_col1\" class=\"data row0 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row0_col2\" class=\"data row0 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
-       "      <td id=\"T_368fb_row1_col0\" class=\"data row1 col0\" >G27</td>\n",
-       "      <td id=\"T_368fb_row1_col1\" class=\"data row1 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row1_col2\" class=\"data row1 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
+       "      <td id=\"T_5cefd_row1_col0\" class=\"data row1 col0\" >G27</td>\n",
+       "      <td id=\"T_5cefd_row1_col1\" class=\"data row1 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row1_col2\" class=\"data row1 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
-       "      <td id=\"T_368fb_row2_col0\" class=\"data row2 col0\" >G30</td>\n",
-       "      <td id=\"T_368fb_row2_col1\" class=\"data row2 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row2_col2\" class=\"data row2 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
+       "      <td id=\"T_5cefd_row2_col0\" class=\"data row2 col0\" >G30</td>\n",
+       "      <td id=\"T_5cefd_row2_col1\" class=\"data row2 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row2_col2\" class=\"data row2 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
-       "      <td id=\"T_368fb_row3_col0\" class=\"data row3 col0\" >G32</td>\n",
-       "      <td id=\"T_368fb_row3_col1\" class=\"data row3 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row3_col2\" class=\"data row3 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
+       "      <td id=\"T_5cefd_row3_col0\" class=\"data row3 col0\" >G32</td>\n",
+       "      <td id=\"T_5cefd_row3_col1\" class=\"data row3 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row3_col2\" class=\"data row3 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
-       "      <td id=\"T_368fb_row4_col0\" class=\"data row4 col0\" >G67</td>\n",
-       "      <td id=\"T_368fb_row4_col1\" class=\"data row4 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row4_col2\" class=\"data row4 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
+       "      <td id=\"T_5cefd_row4_col0\" class=\"data row4 col0\" >G67</td>\n",
+       "      <td id=\"T_5cefd_row4_col1\" class=\"data row4 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row4_col2\" class=\"data row4 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
-       "      <td id=\"T_368fb_row5_col0\" class=\"data row5 col0\" >G70</td>\n",
-       "      <td id=\"T_368fb_row5_col1\" class=\"data row5 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row5_col2\" class=\"data row5 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
+       "      <td id=\"T_5cefd_row5_col0\" class=\"data row5 col0\" >G70</td>\n",
+       "      <td id=\"T_5cefd_row5_col1\" class=\"data row5 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row5_col2\" class=\"data row5 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
-       "      <td id=\"T_368fb_row6_col0\" class=\"data row6 col0\" >G95</td>\n",
-       "      <td id=\"T_368fb_row6_col1\" class=\"data row6 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row6_col2\" class=\"data row6 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
+       "      <td id=\"T_5cefd_row6_col0\" class=\"data row6 col0\" >G95</td>\n",
+       "      <td id=\"T_5cefd_row6_col1\" class=\"data row6 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row6_col2\" class=\"data row6 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
-       "      <td id=\"T_368fb_row7_col0\" class=\"data row7 col0\" >G96</td>\n",
-       "      <td id=\"T_368fb_row7_col1\" class=\"data row7 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row7_col2\" class=\"data row7 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
+       "      <td id=\"T_5cefd_row7_col0\" class=\"data row7 col0\" >G96</td>\n",
+       "      <td id=\"T_5cefd_row7_col1\" class=\"data row7 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row7_col2\" class=\"data row7 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
-       "      <td id=\"T_368fb_row8_col0\" class=\"data row8 col0\" >Gcaps</td>\n",
-       "      <td id=\"T_368fb_row8_col1\" class=\"data row8 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row8_col2\" class=\"data row8 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
+       "      <td id=\"T_5cefd_row8_col0\" class=\"data row8 col0\" >Gcaps</td>\n",
+       "      <td id=\"T_5cefd_row8_col1\" class=\"data row8 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row8_col2\" class=\"data row8 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
-       "      <td id=\"T_368fb_row9_col0\" class=\"data row9 col0\" >Gfrags</td>\n",
-       "      <td id=\"T_368fb_row9_col1\" class=\"data row9 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row9_col2\" class=\"data row9 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
+       "      <td id=\"T_5cefd_row9_col0\" class=\"data row9 col0\" >Gfrags</td>\n",
+       "      <td id=\"T_5cefd_row9_col1\" class=\"data row9 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row9_col2\" class=\"data row9 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row10\" class=\"row_heading level0 row10\" >0</th>\n",
-       "      <td id=\"T_368fb_row10_col0\" class=\"data row10 col0\" >G112</td>\n",
-       "      <td id=\"T_368fb_row10_col1\" class=\"data row10 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row10_col2\" class=\"data row10 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row10\" class=\"row_heading level0 row10\" >0</th>\n",
+       "      <td id=\"T_5cefd_row10_col0\" class=\"data row10 col0\" >G112</td>\n",
+       "      <td id=\"T_5cefd_row10_col1\" class=\"data row10 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row10_col2\" class=\"data row10 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row11\" class=\"row_heading level0 row11\" >1</th>\n",
-       "      <td id=\"T_368fb_row11_col0\" class=\"data row11 col0\" >G27</td>\n",
-       "      <td id=\"T_368fb_row11_col1\" class=\"data row11 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row11_col2\" class=\"data row11 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row11\" class=\"row_heading level0 row11\" >1</th>\n",
+       "      <td id=\"T_5cefd_row11_col0\" class=\"data row11 col0\" >G27</td>\n",
+       "      <td id=\"T_5cefd_row11_col1\" class=\"data row11 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row11_col2\" class=\"data row11 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row12\" class=\"row_heading level0 row12\" >2</th>\n",
-       "      <td id=\"T_368fb_row12_col0\" class=\"data row12 col0\" >G30</td>\n",
-       "      <td id=\"T_368fb_row12_col1\" class=\"data row12 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row12_col2\" class=\"data row12 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row12\" class=\"row_heading level0 row12\" >2</th>\n",
+       "      <td id=\"T_5cefd_row12_col0\" class=\"data row12 col0\" >G30</td>\n",
+       "      <td id=\"T_5cefd_row12_col1\" class=\"data row12 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row12_col2\" class=\"data row12 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row13\" class=\"row_heading level0 row13\" >3</th>\n",
-       "      <td id=\"T_368fb_row13_col0\" class=\"data row13 col0\" >G32</td>\n",
-       "      <td id=\"T_368fb_row13_col1\" class=\"data row13 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row13_col2\" class=\"data row13 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row13\" class=\"row_heading level0 row13\" >3</th>\n",
+       "      <td id=\"T_5cefd_row13_col0\" class=\"data row13 col0\" >G32</td>\n",
+       "      <td id=\"T_5cefd_row13_col1\" class=\"data row13 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row13_col2\" class=\"data row13 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row14\" class=\"row_heading level0 row14\" >4</th>\n",
-       "      <td id=\"T_368fb_row14_col0\" class=\"data row14 col0\" >G67</td>\n",
-       "      <td id=\"T_368fb_row14_col1\" class=\"data row14 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row14_col2\" class=\"data row14 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row14\" class=\"row_heading level0 row14\" >4</th>\n",
+       "      <td id=\"T_5cefd_row14_col0\" class=\"data row14 col0\" >G67</td>\n",
+       "      <td id=\"T_5cefd_row14_col1\" class=\"data row14 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row14_col2\" class=\"data row14 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row15\" class=\"row_heading level0 row15\" >5</th>\n",
-       "      <td id=\"T_368fb_row15_col0\" class=\"data row15 col0\" >G70</td>\n",
-       "      <td id=\"T_368fb_row15_col1\" class=\"data row15 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row15_col2\" class=\"data row15 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row15\" class=\"row_heading level0 row15\" >5</th>\n",
+       "      <td id=\"T_5cefd_row15_col0\" class=\"data row15 col0\" >G70</td>\n",
+       "      <td id=\"T_5cefd_row15_col1\" class=\"data row15 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row15_col2\" class=\"data row15 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row16\" class=\"row_heading level0 row16\" >6</th>\n",
-       "      <td id=\"T_368fb_row16_col0\" class=\"data row16 col0\" >G95</td>\n",
-       "      <td id=\"T_368fb_row16_col1\" class=\"data row16 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row16_col2\" class=\"data row16 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row16\" class=\"row_heading level0 row16\" >6</th>\n",
+       "      <td id=\"T_5cefd_row16_col0\" class=\"data row16 col0\" >G95</td>\n",
+       "      <td id=\"T_5cefd_row16_col1\" class=\"data row16 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row16_col2\" class=\"data row16 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row17\" class=\"row_heading level0 row17\" >7</th>\n",
-       "      <td id=\"T_368fb_row17_col0\" class=\"data row17 col0\" >G96</td>\n",
-       "      <td id=\"T_368fb_row17_col1\" class=\"data row17 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row17_col2\" class=\"data row17 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row17\" class=\"row_heading level0 row17\" >7</th>\n",
+       "      <td id=\"T_5cefd_row17_col0\" class=\"data row17 col0\" >G96</td>\n",
+       "      <td id=\"T_5cefd_row17_col1\" class=\"data row17 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row17_col2\" class=\"data row17 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row18\" class=\"row_heading level0 row18\" >8</th>\n",
-       "      <td id=\"T_368fb_row18_col0\" class=\"data row18 col0\" >Gcaps</td>\n",
-       "      <td id=\"T_368fb_row18_col1\" class=\"data row18 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row18_col2\" class=\"data row18 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row18\" class=\"row_heading level0 row18\" >8</th>\n",
+       "      <td id=\"T_5cefd_row18_col0\" class=\"data row18 col0\" >Gcaps</td>\n",
+       "      <td id=\"T_5cefd_row18_col1\" class=\"data row18 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row18_col2\" class=\"data row18 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row19\" class=\"row_heading level0 row19\" >9</th>\n",
-       "      <td id=\"T_368fb_row19_col0\" class=\"data row19 col0\" >Gfrags</td>\n",
-       "      <td id=\"T_368fb_row19_col1\" class=\"data row19 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row19_col2\" class=\"data row19 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row19\" class=\"row_heading level0 row19\" >9</th>\n",
+       "      <td id=\"T_5cefd_row19_col0\" class=\"data row19 col0\" >Gfrags</td>\n",
+       "      <td id=\"T_5cefd_row19_col1\" class=\"data row19 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row19_col2\" class=\"data row19 col2\" >False</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c07e21f0>"
+       "<pandas.io.formats.style.Styler at 0x7c6bfcfdc5e0>"
       ]
      },
      "execution_count": 27,
@@ -2601,7 +2673,7 @@
      "data": {
       "text/plain": [
        "within 96% HDI    0.80\n",
-       "within 50% HDI    0.35\n",
+       "within 50% HDI    0.45\n",
        "dtype: float64"
       ]
      },
@@ -2635,7 +2707,7 @@
      "data": {
       "text/plain": [
        "within 96% HDI    16\n",
-       "within 50% HDI     7\n",
+       "within 50% HDI     9\n",
        "dtype: int64"
       ]
      },
@@ -2718,12 +2790,12 @@
      "text": [
       "Git repo: https://github.com/hammerdirt-analyst/solid-waste-team.git\n",
       "\n",
-      "Git branch: review\n",
+      "Git branch: main\n",
       "\n",
       "pandas    : 2.0.3\n",
+      "numpy     : 1.25.2\n",
       "matplotlib: 3.7.1\n",
       "seaborn   : 0.12.2\n",
-      "numpy     : 1.25.2\n",
       "\n"
      ]
     }
diff --git a/_build/jupyter_execute/plastic_shotgun_wadding.glue.json b/_build/jupyter_execute/plastic_shotgun_wadding.glue.json
index ee6006f..f7a750a 100644
--- a/_build/jupyter_execute/plastic_shotgun_wadding.glue.json
+++ b/_build/jupyter_execute/plastic_shotgun_wadding.glue.json
@@ -1 +1 @@
-{"percent_samps_feature": {"data": {"text/html": "<style type=\"text/css\">\n#T_c1fc0 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_c1fc0 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_c1fc0 tr {\n  font-size: 14px;\n}\n#T_c1fc0 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_c1fc0 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_c1fc0\">\n  <caption>Percent of samples collected with the designated land-use feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_c1fc0_level0_col0\" class=\"col_heading level0 col0\" >orchards</th>\n      <th id=\"T_c1fc0_level0_col1\" class=\"col_heading level0 col1\" >vineyards</th>\n      <th id=\"T_c1fc0_level0_col2\" class=\"col_heading level0 col2\" >buildings</th>\n      <th id=\"T_c1fc0_level0_col3\" class=\"col_heading level0 col3\" >forest</th>\n      <th id=\"T_c1fc0_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_c1fc0_level0_col5\" class=\"col_heading level0 col5\" >public_services</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_c1fc0_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_c1fc0_row0_col0\" class=\"data row0 col0\" >91%</td>\n      <td id=\"T_c1fc0_row0_col1\" class=\"data row0 col1\" >92%</td>\n      <td id=\"T_c1fc0_row0_col2\" class=\"data row0 col2\" >11%</td>\n      <td id=\"T_c1fc0_row0_col3\" class=\"data row0 col3\" >72%</td>\n      <td id=\"T_c1fc0_row0_col4\" class=\"data row0 col4\" >63%</td>\n      <td id=\"T_c1fc0_row0_col5\" class=\"data row0 col5\" >68%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_c1fc0_row1_col0\" class=\"data row1 col0\" >6%</td>\n      <td id=\"T_c1fc0_row1_col1\" class=\"data row1 col1\" >7%</td>\n      <td id=\"T_c1fc0_row1_col2\" class=\"data row1 col2\" >6%</td>\n      <td id=\"T_c1fc0_row1_col3\" class=\"data row1 col3\" >14%</td>\n      <td id=\"T_c1fc0_row1_col4\" class=\"data row1 col4\" >25%</td>\n      <td id=\"T_c1fc0_row1_col5\" class=\"data row1 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_c1fc0_row2_col0\" class=\"data row2 col0\" >0%</td>\n      <td id=\"T_c1fc0_row2_col1\" class=\"data row2 col1\" >0%</td>\n      <td id=\"T_c1fc0_row2_col2\" class=\"data row2 col2\" >1%</td>\n      <td id=\"T_c1fc0_row2_col3\" class=\"data row2 col3\" >0%</td>\n      <td id=\"T_c1fc0_row2_col4\" class=\"data row2 col4\" >1%</td>\n      <td id=\"T_c1fc0_row2_col5\" class=\"data row2 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_c1fc0_row3_col0\" class=\"data row3 col0\" >1%</td>\n      <td id=\"T_c1fc0_row3_col1\" class=\"data row3 col1\" >0%</td>\n      <td id=\"T_c1fc0_row3_col2\" class=\"data row3 col2\" >20%</td>\n      <td id=\"T_c1fc0_row3_col3\" class=\"data row3 col3\" >9%</td>\n      <td id=\"T_c1fc0_row3_col4\" class=\"data row3 col4\" >2%</td>\n      <td id=\"T_c1fc0_row3_col5\" class=\"data row3 col5\" >8%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_c1fc0_row4_col0\" class=\"data row4 col0\" >1%</td>\n      <td id=\"T_c1fc0_row4_col1\" class=\"data row4 col1\" >1%</td>\n      <td id=\"T_c1fc0_row4_col2\" class=\"data row4 col2\" >62%</td>\n      <td id=\"T_c1fc0_row4_col3\" class=\"data row4 col3\" >5%</td>\n      <td id=\"T_c1fc0_row4_col4\" class=\"data row4 col4\" >9%</td>\n      <td id=\"T_c1fc0_row4_col5\" class=\"data row4 col5\" >10%</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7896dc878ca0>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "percent_samps_feature"}}, "output_type": "display_data"}, "average_per_feature": {"data": {"text/html": "<style type=\"text/css\">\n#T_c091a tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_c091a tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_c091a tr {\n  font-size: 14px;\n}\n#T_c091a th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_c091a caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_c091a\">\n  <caption>The average number of shotgun shells per linear meter of shoreline by feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_c091a_level0_col0\" class=\"col_heading level0 col0\" >buildings</th>\n      <th id=\"T_c091a_level0_col1\" class=\"col_heading level0 col1\" >forest</th>\n      <th id=\"T_c091a_level0_col2\" class=\"col_heading level0 col2\" >orchards</th>\n      <th id=\"T_c091a_level0_col3\" class=\"col_heading level0 col3\" >public_services</th>\n      <th id=\"T_c091a_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_c091a_level0_col5\" class=\"col_heading level0 col5\" >vineyards</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_c091a_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_c091a_row0_col0\" class=\"data row0 col0\" >0.03</td>\n      <td id=\"T_c091a_row0_col1\" class=\"data row0 col1\" >0.08</td>\n      <td id=\"T_c091a_row0_col2\" class=\"data row0 col2\" >0.11</td>\n      <td id=\"T_c091a_row0_col3\" class=\"data row0 col3\" >0.13</td>\n      <td id=\"T_c091a_row0_col4\" class=\"data row0 col4\" >0.09</td>\n      <td id=\"T_c091a_row0_col5\" class=\"data row0 col5\" >0.10</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_c091a_row1_col0\" class=\"data row1 col0\" >0.59</td>\n      <td id=\"T_c091a_row1_col1\" class=\"data row1 col1\" >0.06</td>\n      <td id=\"T_c091a_row1_col2\" class=\"data row1 col2\" >0.01</td>\n      <td id=\"T_c091a_row1_col3\" class=\"data row1 col3\" >0.12</td>\n      <td id=\"T_c091a_row1_col4\" class=\"data row1 col4\" >0.18</td>\n      <td id=\"T_c091a_row1_col5\" class=\"data row1 col5\" >0.08</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_c091a_row2_col0\" class=\"data row2 col0\" >0.00</td>\n      <td id=\"T_c091a_row2_col1\" class=\"data row2 col1\" >-</td>\n      <td id=\"T_c091a_row2_col2\" class=\"data row2 col2\" >0.00</td>\n      <td id=\"T_c091a_row2_col3\" class=\"data row2 col3\" >0.01</td>\n      <td id=\"T_c091a_row2_col4\" class=\"data row2 col4\" >0.08</td>\n      <td id=\"T_c091a_row2_col5\" class=\"data row2 col5\" >-</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_c091a_row3_col0\" class=\"data row3 col0\" >0.04</td>\n      <td id=\"T_c091a_row3_col1\" class=\"data row3 col1\" >0.00</td>\n      <td id=\"T_c091a_row3_col2\" class=\"data row3 col2\" >0.01</td>\n      <td id=\"T_c091a_row3_col3\" class=\"data row3 col3\" >0.03</td>\n      <td id=\"T_c091a_row3_col4\" class=\"data row3 col4\" >0.09</td>\n      <td id=\"T_c091a_row3_col5\" class=\"data row3 col5\" >0.00</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_c091a_row4_col0\" class=\"data row4 col0\" >0.09</td>\n      <td id=\"T_c091a_row4_col1\" class=\"data row4 col1\" >0.68</td>\n      <td id=\"T_c091a_row4_col2\" class=\"data row4 col2\" >0.14</td>\n      <td id=\"T_c091a_row4_col3\" class=\"data row4 col3\" >0.03</td>\n      <td id=\"T_c091a_row4_col4\" class=\"data row4 col4\" >0.00</td>\n      <td id=\"T_c091a_row4_col5\" class=\"data row4 col5\" >0.12</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7896dca60c10>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "average_per_feature"}}, "output_type": "display_data"}, "region_scatter": {"data": {"image/png": "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", "text/plain": "<Figure size 640x480 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "region_scatter"}}, "output_type": "display_data"}, "region_ecdf": {"data": {"image/png": "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", "text/plain": "<Figure size 640x480 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "region_ecdf"}}, "output_type": "display_data"}, "region_qty_dist": {"data": {"text/html": "<style type=\"text/css\">\n#T_8ea89 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_8ea89 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_8ea89 tr {\n  font-size: 14px;\n}\n#T_8ea89 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_8ea89 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_8ea89\">\n  <caption>The distribution of the total number of plastic shotgun wadding found per sample for each region</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_8ea89_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_8ea89_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_8ea89_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_8ea89_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_8ea89_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_8ea89_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_8ea89_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_8ea89_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_8ea89_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_8ea89_row0_col0\" class=\"data row0 col0\" >58</td>\n      <td id=\"T_8ea89_row0_col1\" class=\"data row0 col1\" >1</td>\n      <td id=\"T_8ea89_row0_col2\" class=\"data row0 col2\" >2</td>\n      <td id=\"T_8ea89_row0_col3\" class=\"data row0 col3\" >0</td>\n      <td id=\"T_8ea89_row0_col4\" class=\"data row0 col4\" >0</td>\n      <td id=\"T_8ea89_row0_col5\" class=\"data row0 col5\" >0</td>\n      <td id=\"T_8ea89_row0_col6\" class=\"data row0 col6\" >1</td>\n      <td id=\"T_8ea89_row0_col7\" class=\"data row0 col7\" >8</td>\n    </tr>\n    <tr>\n      <th id=\"T_8ea89_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_8ea89_row1_col0\" class=\"data row1 col0\" >137</td>\n      <td id=\"T_8ea89_row1_col1\" class=\"data row1 col1\" >6</td>\n      <td id=\"T_8ea89_row1_col2\" class=\"data row1 col2\" >10</td>\n      <td id=\"T_8ea89_row1_col3\" class=\"data row1 col3\" >0</td>\n      <td id=\"T_8ea89_row1_col4\" class=\"data row1 col4\" >0</td>\n      <td id=\"T_8ea89_row1_col5\" class=\"data row1 col5\" >2</td>\n      <td id=\"T_8ea89_row1_col6\" class=\"data row1 col6\" >7</td>\n      <td id=\"T_8ea89_row1_col7\" class=\"data row1 col7\" >51</td>\n    </tr>\n    <tr>\n      <th id=\"T_8ea89_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_8ea89_row2_col0\" class=\"data row2 col0\" >55</td>\n      <td id=\"T_8ea89_row2_col1\" class=\"data row2 col1\" >1</td>\n      <td id=\"T_8ea89_row2_col2\" class=\"data row2 col2\" >4</td>\n      <td id=\"T_8ea89_row2_col3\" class=\"data row2 col3\" >0</td>\n      <td id=\"T_8ea89_row2_col4\" class=\"data row2 col4\" >0</td>\n      <td id=\"T_8ea89_row2_col5\" class=\"data row2 col5\" >0</td>\n      <td id=\"T_8ea89_row2_col6\" class=\"data row2 col6\" >0</td>\n      <td id=\"T_8ea89_row2_col7\" class=\"data row2 col7\" >22</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7896dca95d60>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "region_qty_dist"}}, "output_type": "display_data"}, "region_med_dist": {"data": {"text/html": "<style type=\"text/css\">\n#T_620b2 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_620b2 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_620b2 tr {\n  font-size: 14px;\n}\n#T_620b2 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_620b2 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_620b2\">\n  <caption>The distribution of the number of shotgun wadding found per meter of shoreline</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_620b2_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_620b2_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_620b2_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_620b2_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_620b2_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_620b2_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_620b2_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_620b2_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_620b2_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_620b2_row0_col0\" class=\"data row0 col0\" >58.00</td>\n      <td id=\"T_620b2_row0_col1\" class=\"data row0 col1\" >0.03</td>\n      <td id=\"T_620b2_row0_col2\" class=\"data row0 col2\" >0.05</td>\n      <td id=\"T_620b2_row0_col3\" class=\"data row0 col3\" >0.00</td>\n      <td id=\"T_620b2_row0_col4\" class=\"data row0 col4\" >0.00</td>\n      <td id=\"T_620b2_row0_col5\" class=\"data row0 col5\" >0.00</td>\n      <td id=\"T_620b2_row0_col6\" class=\"data row0 col6\" >0.03</td>\n      <td id=\"T_620b2_row0_col7\" class=\"data row0 col7\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_620b2_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_620b2_row1_col0\" class=\"data row1 col0\" >137.00</td>\n      <td id=\"T_620b2_row1_col1\" class=\"data row1 col1\" >0.17</td>\n      <td id=\"T_620b2_row1_col2\" class=\"data row1 col2\" >0.31</td>\n      <td id=\"T_620b2_row1_col3\" class=\"data row1 col3\" >0.00</td>\n      <td id=\"T_620b2_row1_col4\" class=\"data row1 col4\" >0.00</td>\n      <td id=\"T_620b2_row1_col5\" class=\"data row1 col5\" >0.05</td>\n      <td id=\"T_620b2_row1_col6\" class=\"data row1 col6\" >0.17</td>\n      <td id=\"T_620b2_row1_col7\" class=\"data row1 col7\" >1.64</td>\n    </tr>\n    <tr>\n      <th id=\"T_620b2_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_620b2_row2_col0\" class=\"data row2 col0\" >55.00</td>\n      <td id=\"T_620b2_row2_col1\" class=\"data row2 col1\" >0.02</td>\n      <td id=\"T_620b2_row2_col2\" class=\"data row2 col2\" >0.05</td>\n      <td id=\"T_620b2_row2_col3\" class=\"data row2 col3\" >0.00</td>\n      <td id=\"T_620b2_row2_col4\" class=\"data row2 col4\" >0.00</td>\n      <td id=\"T_620b2_row2_col5\" class=\"data row2 col5\" >0.00</td>\n      <td id=\"T_620b2_row2_col6\" class=\"data row2 col6\" >0.01</td>\n      <td id=\"T_620b2_row2_col7\" class=\"data row2 col7\" >0.30</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7896afba5880>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "region_med_dist"}}, "output_type": "display_data"}, "city_rankings": {"data": {"text/html": "<style type=\"text/css\">\n#T_75ad1 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_75ad1 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_75ad1 tr {\n  font-size: 14px;\n}\n#T_75ad1 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_75ad1 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_75ad1\">\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_75ad1_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n      <th id=\"T_75ad1_level0_col1\" class=\"col_heading level0 col1\" >nsamples</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_75ad1_level0_row0\" class=\"row_heading level0 row0\" >Saint-Gingolph</th>\n      <td id=\"T_75ad1_row0_col0\" class=\"data row0 col0\" >0.68</td>\n      <td id=\"T_75ad1_row0_col1\" class=\"data row0 col1\" >13</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row1\" class=\"row_heading level0 row1\" >Allaman</th>\n      <td id=\"T_75ad1_row1_col0\" class=\"data row1 col0\" >0.14</td>\n      <td id=\"T_75ad1_row1_col1\" class=\"data row1 col1\" >3</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row2\" class=\"row_heading level0 row2\" >Bourg-en-Lavaux</th>\n      <td id=\"T_75ad1_row2_col0\" class=\"data row2 col0\" >0.12</td>\n      <td id=\"T_75ad1_row2_col1\" class=\"data row2 col1\" >2</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row3\" class=\"row_heading level0 row3\" >La Tour-de-Peilz</th>\n      <td id=\"T_75ad1_row3_col0\" class=\"data row3 col0\" >0.12</td>\n      <td id=\"T_75ad1_row3_col1\" class=\"data row3 col1\" >25</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row4\" class=\"row_heading level0 row4\" >Montreux</th>\n      <td id=\"T_75ad1_row4_col0\" class=\"data row4 col0\" >0.11</td>\n      <td id=\"T_75ad1_row4_col1\" class=\"data row4 col1\" >53</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row5\" class=\"row_heading level0 row5\" >Vevey</th>\n      <td id=\"T_75ad1_row5_col0\" class=\"data row5 col0\" >0.11</td>\n      <td id=\"T_75ad1_row5_col1\" class=\"data row5 col1\" >44</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row6\" class=\"row_heading level0 row6\" >Saint-Sulpice (VD)</th>\n      <td id=\"T_75ad1_row6_col0\" class=\"data row6 col0\" >0.06</td>\n      <td id=\"T_75ad1_row6_col1\" class=\"data row6 col1\" >15</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row7\" class=\"row_heading level0 row7\" >Versoix</th>\n      <td id=\"T_75ad1_row7_col0\" class=\"data row7 col0\" >0.05</td>\n      <td id=\"T_75ad1_row7_col1\" class=\"data row7 col1\" >4</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row8\" class=\"row_heading level0 row8\" >Gen\u00e8ve</th>\n      <td id=\"T_75ad1_row8_col0\" class=\"data row8 col0\" >0.03</td>\n      <td id=\"T_75ad1_row8_col1\" class=\"data row8 col1\" >29</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row9\" class=\"row_heading level0 row9\" >Pr\u00e9verenges</th>\n      <td id=\"T_75ad1_row9_col0\" class=\"data row9 col0\" >0.01</td>\n      <td id=\"T_75ad1_row9_col1\" class=\"data row9 col1\" >15</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row10\" class=\"row_heading level0 row10\" >Tolochenaz</th>\n      <td id=\"T_75ad1_row10_col0\" class=\"data row10 col0\" >0.01</td>\n      <td id=\"T_75ad1_row10_col1\" class=\"data row10 col1\" >3</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row11\" class=\"row_heading level0 row11\" >Lausanne</th>\n      <td id=\"T_75ad1_row11_col0\" class=\"data row11 col0\" >0.01</td>\n      <td id=\"T_75ad1_row11_col1\" class=\"data row11 col1\" >20</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row12\" class=\"row_heading level0 row12\" >Gland</th>\n      <td id=\"T_75ad1_row12_col0\" class=\"data row12 col0\" >0.00</td>\n      <td id=\"T_75ad1_row12_col1\" class=\"data row12 col1\" >22</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row13\" class=\"row_heading level0 row13\" >Morges</th>\n      <td id=\"T_75ad1_row13_col0\" class=\"data row13 col0\" >0.00</td>\n      <td id=\"T_75ad1_row13_col1\" class=\"data row13 col1\" >1</td>\n    </tr>\n    <tr>\n      <th id=\"T_75ad1_level0_row14\" class=\"row_heading level0 row14\" >Rolle</th>\n      <td id=\"T_75ad1_row14_col0\" class=\"data row14 col0\" >0.00</td>\n      <td id=\"T_75ad1_row14_col1\" class=\"data row14 col1\" >1</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7896afd57f40>"}, "metadata": {"scrapbook": {"mime_prefix": "", "name": "city_rankings"}}, "output_type": "display_data"}}
\ No newline at end of file
+{"percent_samps_feature": {"data": {"text/html": "<style type=\"text/css\">\n#T_09e96 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_09e96 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_09e96 tr {\n  font-size: 14px;\n}\n#T_09e96 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_09e96 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_09e96\">\n  <caption>Percent of samples collected with the designated land-use feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_09e96_level0_col0\" class=\"col_heading level0 col0\" >orchards</th>\n      <th id=\"T_09e96_level0_col1\" class=\"col_heading level0 col1\" >vineyards</th>\n      <th id=\"T_09e96_level0_col2\" class=\"col_heading level0 col2\" >buildings</th>\n      <th id=\"T_09e96_level0_col3\" class=\"col_heading level0 col3\" >forest</th>\n      <th id=\"T_09e96_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_09e96_level0_col5\" class=\"col_heading level0 col5\" >public_services</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_09e96_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_09e96_row0_col0\" class=\"data row0 col0\" >91%</td>\n      <td id=\"T_09e96_row0_col1\" class=\"data row0 col1\" >92%</td>\n      <td id=\"T_09e96_row0_col2\" class=\"data row0 col2\" >11%</td>\n      <td id=\"T_09e96_row0_col3\" class=\"data row0 col3\" >72%</td>\n      <td id=\"T_09e96_row0_col4\" class=\"data row0 col4\" >63%</td>\n      <td id=\"T_09e96_row0_col5\" class=\"data row0 col5\" >68%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_09e96_row1_col0\" class=\"data row1 col0\" >6%</td>\n      <td id=\"T_09e96_row1_col1\" class=\"data row1 col1\" >7%</td>\n      <td id=\"T_09e96_row1_col2\" class=\"data row1 col2\" >6%</td>\n      <td id=\"T_09e96_row1_col3\" class=\"data row1 col3\" >14%</td>\n      <td id=\"T_09e96_row1_col4\" class=\"data row1 col4\" >25%</td>\n      <td id=\"T_09e96_row1_col5\" class=\"data row1 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_09e96_row2_col0\" class=\"data row2 col0\" >0%</td>\n      <td id=\"T_09e96_row2_col1\" class=\"data row2 col1\" >0%</td>\n      <td id=\"T_09e96_row2_col2\" class=\"data row2 col2\" >1%</td>\n      <td id=\"T_09e96_row2_col3\" class=\"data row2 col3\" >0%</td>\n      <td id=\"T_09e96_row2_col4\" class=\"data row2 col4\" >1%</td>\n      <td id=\"T_09e96_row2_col5\" class=\"data row2 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_09e96_row3_col0\" class=\"data row3 col0\" >1%</td>\n      <td id=\"T_09e96_row3_col1\" class=\"data row3 col1\" >0%</td>\n      <td id=\"T_09e96_row3_col2\" class=\"data row3 col2\" >20%</td>\n      <td id=\"T_09e96_row3_col3\" class=\"data row3 col3\" >9%</td>\n      <td id=\"T_09e96_row3_col4\" class=\"data row3 col4\" >2%</td>\n      <td id=\"T_09e96_row3_col5\" class=\"data row3 col5\" >8%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_09e96_row4_col0\" class=\"data row4 col0\" >1%</td>\n      <td id=\"T_09e96_row4_col1\" class=\"data row4 col1\" >1%</td>\n      <td id=\"T_09e96_row4_col2\" class=\"data row4 col2\" >62%</td>\n      <td id=\"T_09e96_row4_col3\" class=\"data row4 col3\" >5%</td>\n      <td id=\"T_09e96_row4_col4\" class=\"data row4 col4\" >9%</td>\n      <td id=\"T_09e96_row4_col5\" class=\"data row4 col5\" >10%</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7a2c78fa07f0>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "percent_samps_feature"}}, "output_type": "display_data"}, "average_per_feature": {"data": {"text/html": "<style type=\"text/css\">\n#T_1cbf2 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_1cbf2 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_1cbf2 tr {\n  font-size: 14px;\n}\n#T_1cbf2 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_1cbf2 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_1cbf2\">\n  <caption>The average number of shotgun shells per linear meter of shoreline by feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_1cbf2_level0_col0\" class=\"col_heading level0 col0\" >buildings</th>\n      <th id=\"T_1cbf2_level0_col1\" class=\"col_heading level0 col1\" >forest</th>\n      <th id=\"T_1cbf2_level0_col2\" class=\"col_heading level0 col2\" >orchards</th>\n      <th id=\"T_1cbf2_level0_col3\" class=\"col_heading level0 col3\" >public_services</th>\n      <th id=\"T_1cbf2_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_1cbf2_level0_col5\" class=\"col_heading level0 col5\" >vineyards</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_1cbf2_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_1cbf2_row0_col0\" class=\"data row0 col0\" >0.03</td>\n      <td id=\"T_1cbf2_row0_col1\" class=\"data row0 col1\" >0.08</td>\n      <td id=\"T_1cbf2_row0_col2\" class=\"data row0 col2\" >0.11</td>\n      <td id=\"T_1cbf2_row0_col3\" class=\"data row0 col3\" >0.13</td>\n      <td id=\"T_1cbf2_row0_col4\" class=\"data row0 col4\" >0.09</td>\n      <td id=\"T_1cbf2_row0_col5\" class=\"data row0 col5\" >0.10</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_1cbf2_row1_col0\" class=\"data row1 col0\" >0.59</td>\n      <td id=\"T_1cbf2_row1_col1\" class=\"data row1 col1\" >0.06</td>\n      <td id=\"T_1cbf2_row1_col2\" class=\"data row1 col2\" >0.01</td>\n      <td id=\"T_1cbf2_row1_col3\" class=\"data row1 col3\" >0.12</td>\n      <td id=\"T_1cbf2_row1_col4\" class=\"data row1 col4\" >0.18</td>\n      <td id=\"T_1cbf2_row1_col5\" class=\"data row1 col5\" >0.08</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_1cbf2_row2_col0\" class=\"data row2 col0\" >0.00</td>\n      <td id=\"T_1cbf2_row2_col1\" class=\"data row2 col1\" >-</td>\n      <td id=\"T_1cbf2_row2_col2\" class=\"data row2 col2\" >0.00</td>\n      <td id=\"T_1cbf2_row2_col3\" class=\"data row2 col3\" >0.01</td>\n      <td id=\"T_1cbf2_row2_col4\" class=\"data row2 col4\" >0.08</td>\n      <td id=\"T_1cbf2_row2_col5\" class=\"data row2 col5\" >-</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_1cbf2_row3_col0\" class=\"data row3 col0\" >0.04</td>\n      <td id=\"T_1cbf2_row3_col1\" class=\"data row3 col1\" >0.00</td>\n      <td id=\"T_1cbf2_row3_col2\" class=\"data row3 col2\" >0.01</td>\n      <td id=\"T_1cbf2_row3_col3\" class=\"data row3 col3\" >0.03</td>\n      <td id=\"T_1cbf2_row3_col4\" class=\"data row3 col4\" >0.09</td>\n      <td id=\"T_1cbf2_row3_col5\" class=\"data row3 col5\" >0.00</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_1cbf2_row4_col0\" class=\"data row4 col0\" >0.09</td>\n      <td id=\"T_1cbf2_row4_col1\" class=\"data row4 col1\" >0.68</td>\n      <td id=\"T_1cbf2_row4_col2\" class=\"data row4 col2\" >0.14</td>\n      <td id=\"T_1cbf2_row4_col3\" class=\"data row4 col3\" >0.03</td>\n      <td id=\"T_1cbf2_row4_col4\" class=\"data row4 col4\" >0.00</td>\n      <td id=\"T_1cbf2_row4_col5\" class=\"data row4 col5\" >0.12</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7a2cc40c9220>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "average_per_feature"}}, "output_type": "display_data"}, "region_scatter": {"data": {"image/png": "iVBORw0KGgoAAAANSUhEUgAAAnQAAAHWCAYAAAD+VRS3AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAACU9ElEQVR4nOzdd3iTVfvA8W+Spm2694JCy957owgyFBUZKoiKooLiFvSn8r64X8UtTnAjDkREEMUBKkvZS2Svslu6m86kGb8/DrSEJqUtbdOU+3NduTTnPHly0pKn93PGfTR2u92OEEIIIYTwWFp3N0AIIYQQQlwYCeiEEEIIITycBHRCCCGEEB5OAjohhBBCCA8nAZ0QQgghhIeTgE4IIYQQwsNJQCeEEEII4eEkoBNCCCGE8HBe7m5AXWSz2Th58iSBgYFoNBp3N0cIIYQQFwm73U5ubi5xcXFotRXvd5OAzomTJ08SHx/v7mYIIYQQ4iJ17NgxGjZsWOHjJaBzIjAwEFA/zKCgIDe3RgghhBAXC6PRSHx8fEksUlES0DlxZpg1KChIAjohhBBC1LrKTvmSRRFCCCGEEB5OAjohhBBCCA8nAZ0QQgghhIeTOXRCCCGEB7DZbJjNZnc3Q1wgvV6PTqer9vNKQCeEEELUcWazmaSkJGw2m7ubIqpBSEgIMTEx1ZrrVgI6IYQQog6z2+0kJyej0+mIj4+vVLJZUbfY7XYKCgpITU0FIDY2ttrOLQGdEEIIUYdZLBYKCgqIi4vDz8/P3c0RF8hgMACQmppKVFRUtQ2/SpgvhBBC1GFWqxUAb29vN7dEVJczgXlxcXG1nVMCOiGEEMIDyN7i9UdN/C4loBNCCCFEnZKQkMCMGTPc3QyPInPohBBCCFGnbNy4EX9/f3c3w6NIQCfcz5QH+WmQnw56X/CPhMAYd7dKCCFEJZnN5mqZ6xcZGVkNrbm4yJCrcK/8NFj5MrzbDT4ZBLMugU+vgJSdYLe7u3VCCCHK0b9/f+6//36mTJlCREQEgwcPZteuXVx11VUEBAQQHR3NuHHjSE9PL3lNbm4uN998M/7+/sTGxvLmm2/Sv39/Hn744ZJjzh1yPXr0KMOHDycgIICgoCBGjx7NqVOnSuqfeeYZOnXqxBdffEFCQgLBwcHceOON5Obm1saPoU6QgE64j80GOxbCmrfBZiktzzoMn18NOcfd1jQhhBAV8/nnn+Pl5cXff//NSy+9xGWXXUanTp3YtGkTv/76K6dOnWL06NElx0+ZMoW///6bxYsXs2zZMlavXs2WLVtcnt9utzNixAgyMzNZuXIly5Yt4+DBg4wZM8bhuIMHD7Jo0SJ++uknfvrpJ1auXMlLL71UY5+7rpEhV+E+eSmw+lXndYVZcGILhMTXbpuEEEJUSrNmzXjllVcAeOqpp+jSpQsvvvhiSf2nn35KfHw8+/btIzY2ls8//5yvv/6agQMHAvDZZ58RFxfn8vy///4727dvJykpifh49Tfhiy++oG3btmzcuJHu3bsDamu02bNnExgYCMC4ceP4448/eOGFF2rkc9c10kMn3MdigrxU1/WndtZeW4QQQlRJt27dSv5/8+bNLF++nICAgJJHq1atANWDdujQIYqLi+nRo0fJa4KDg2nZsqXL8+/evZv4+PiSYA6gTZs2hISEsHv37pKyhISEkmAO1C4MZ3ZkuBhID51wHy8ftfghN8V5fUy72m2PEEKISjt7NarNZmPYsGG8/PLLZY6LjY1l//79QNk8bPZy5kzb7XanedvOLdfr9Q71Go3motr7VnrohPsExsJljzuv8wuHuC612x4hhBAXpEuXLuzcuZOEhASaNWvm8PD396dp06bo9Xo2bNhQ8hqj0VgS6DnTpk0bjh49yrFjx0rKdu3aRU5ODq1bt67Rz+NJJKAT7qPRQOtrod9joDtrmXt4Mxi/BEIauq9tQgghKu2+++4jMzOTsWPHsmHDBg4dOsTSpUu54447sFqtBAYGctttt/F///d/LF++nJ07d3LHHXeg1Wpd7p4waNAgOnTowM0338yWLVvYsGEDt956K5dddpnDcO/FTgI64V7+EXDJZLh/I0xcDveshfG/QJTcdQkhhKeJi4vj77//xmq1csUVV9CuXTseeughgoOD0WpVyPHGG2/Qu3dvrrnmGgYNGkTfvn1p3bo1vr6+Ts+p0WhYtGgRoaGh9OvXj0GDBtGkSRPmzZtXmx+tztPYyxu4vkgZjUaCg4PJyckhKCjI3c0RQghxESsqKiIpKYnExESXQY8ny8/Pp0GDBrz++uvceeed7m5OrSjvd1rVGEQWRQghhBCi1mzdupU9e/bQo0cPcnJyeO655wAYPny4m1vm2SSgE0IIIUSteu2119i7dy/e3t507dqV1atXExER4e5meTQJ6IQQQghRazp37szmzZvd3Yx6RxZFCCGEEEJ4OAnohBBCCCE8nAR0QgghhBAeTgI6IYQQQggPJwGdEEIIIYSHk1WuolR+BhSkgzkfDKEQEAXe/ud/nRBCCCHcSnrohJJ1GL6+Ad7rAR8NgHe7wm/TIO+Uu1smhBBCVKuEhARmzJjhsn78+PGMGDGi1tpTHSSgE5CbAl9eByfOygtks8LmT2Hte2Axua9tQgghPFZKSgoPPfQQzZo1w9fXl+joaC655BJmzZpFQUGBu5tXr8iQq4DsY5BxwHndhg+h+wQIaVS7bRJCCOHRDh06RN++fQkJCeHFF1+kffv2WCwW9u3bx6effkpcXBzXXnut09cWFxej1+trucWeTXroBGQecl1XXKjm1AkhhLgwdjsU5bjtmmq12Vl7MIMftp1g7cEMrDZ7jb7fvffei5eXF5s2bWL06NG0bt2a9u3bc91117FkyRKGDRtWcqxGo2HWrFkMHz4cf39//ve//2G1WrnzzjtJTEzEYDDQsmVL3nrrLYf3ODM0+tprrxEbG0t4eDj33XcfxcXFJcekpqYybNgwDAYDiYmJfPXVV5X+LL/++iuXXHIJISEhhIeHc80113Dw4EGHY44fP86NN95IWFgY/v7+dOvWjfXr11f6vapKeugEhDZ2XeflA3q/2muLEELURznHYe/P8O936pra6x6I66wWn9WCX3ck8+yPu0jOKSopiw325elhbbiyXWy1v19GRgZLly7lxRdfxN/f+eI6jUbj8Pzpp59m+vTpvPnmm+h0Omw2Gw0bNuTbb78lIiKCNWvWcNdddxEbG8vo0aNLXrd8+XJiY2NZvnw5Bw4cYMyYMXTq1ImJEycCKug7duwYf/75J97e3jz44IOkpqZW6vPk5+czZcoU2rdvT35+Pk899RQjR45k27ZtaLVa8vLyuOyyy2jQoAGLFy8mJiaGLVu2YLPZKvmTqzoJ6ASENIbQBLUw4lxdboeA6NpukRBC1B/Zx2D2VZB9tLTs0HJoMwKueg0CImv07X/dkcw9X27h3P64lJwi7vlyCzNv6VLtQd2BAwew2+20bNnSoTwiIoKiIhVU3nfffbz88ssldTfddBN33HGHw/HPPvtsyf8nJiayZs0avv32W4eALjQ0lHfffRedTkerVq24+uqr+eOPP5g4cSL79u3jl19+Yd26dfTs2ROATz75hNatW1fq81x33XUOzz/55BOioqLYtWsX7dq14+uvvyYtLY2NGzcSFhYGQLNmzSr1HhdKhlwFBMXCLd9D1Fn/wDUaaH8DXDoZ9L7ua5sQQngyixnWzXQM5s7Ytcj1/OVqYrXZefbHXWWCOaCk7Nkfd9XY8Ou5vXAbNmxg27ZttG3bFpPJccFdt27dyrx+1qxZdOvWjcjISAICAvjoo484etTxZ9m2bVt0Ol3J89jY2JIeuN27d+Pl5eVw7latWhESElKpz3Hw4EFuuukmmjRpQlBQEImJiQAlbdm2bRudO3cuCebcQXrohBLeFG5dDPnpYDKCfwT4R4JvsLtbJoQQnqsgHbbPdV2/ZQ406qVuomvAhqRMh2HWc9mB5JwiNiRl0rtpeLW9b7NmzdBoNOzZs8ehvEmTJgAYDIYyrzl3aPbbb79l8uTJvP766/Tu3ZvAwEBeffXVMvPSzl08odFoSoY67XZ7SdmFGDZsGPHx8Xz00UfExcVhs9lo164dZrPZ5eepbdJDJ0oFREF0G3VxCW8mwZwQQlQHezm9X7Zi13XVIDXXdTBXleMqKjw8nMGDB/Puu++Sn1+1RSCrV6+mT58+3HvvvXTu3JlmzZqVWYhwPq1bt8ZisbBp06aSsr1795KdnV3hc2RkZLB7926mTZvGwIEDad26NVlZWQ7HdOjQgW3btpGZmVmp9lUnCeiEEEKImuIXBm1Hua7vPK7GeucAogIrNmWmosdVxvvvv4/FYqFbt27MmzeP3bt3s3fvXr788kv27NnjMEzqTLNmzdi0aRO//fYb+/bt48knn2Tjxo2VakPLli258sormThxIuvXr2fz5s1MmDChUj1qoaGhhIeH8+GHH3LgwAH+/PNPpkyZ4nDM2LFjiYmJYcSIEfz9998cOnSIBQsWsHbt2kq190JIQCeEEELUFC9f6Pug89WsTQZAZKsaffseiWHEBvviKmTUoFa79kis/rlfTZs2ZevWrQwaNIipU6fSsWNHunXrxjvvvMOjjz7K888/X+7rJ02axKhRoxgzZgw9e/YkIyODe++9t9Lt+Oyzz4iPj+eyyy5j1KhR3HXXXURFVXx1sVar5ZtvvmHz5s20a9eOyZMn8+qrrzoc4+3tzdKlS4mKiuKqq66iffv2vPTSS+cNWquTxm4vry/44mQ0GgkODiYnJ4egoCB3N0cIIYSnyz4KW79UCyH0/tBzEjS5DAJjzvvSoqIikpKSSExMxNe38j1pZ1a5Ag6LI84EeTWxylWUr7zfaVVjEFkUIYQQQtS0kEbQ7zHoPhG0OjUUW0uubBfLzFu6lMlDF1ODeehE7XPrkOuqVasYNmwYcXFxaDQaFi1aVO7xK1asQKPRlHmcu4pmwYIFtGnTBh8fH9q0acPChQtr8FMIIYQQFaDzUjnnajGYO+PKdrH89fjlzJ3Yi7du7MTcib346/HLJZirR9wa0OXn59OxY0fefffdSr1u7969JCcnlzyaN29eUrd27VrGjBnDuHHj+Oeffxg3bhyjR4+u1e03hBBCiLpGp9XQu2k4wzs1oHfTcHTamluMIWqfW4dchw4dytChQyv9uqioKJdJAWfMmMHgwYOZOnUqAFOnTmXlypXMmDGDuXPLyQUkhBBCCOGhPHKVa+fOnYmNjWXgwIEsX77coW7t2rUMGTLEoeyKK65gzZo1Ls9nMpkwGo0ODyGEEEIIT+FRAV1sbCwffvghCxYs4Pvvv6dly5YMHDiQVatWlRyTkpJCdLTj3qPR0dGkpKS4PO/06dMJDg4uecTHx9fYZxBCCCGEqG4etcq1ZcuWDhv99u7dm2PHjvHaa6/Rr1+/kvJzt/iw2+3lbvsxdepUhySBRqNRgjohhBBCeAyP6qFzplevXuzfv7/keUxMTJneuNTU1DK9dmfz8fEhKCjI4SGEEEII4Sk8PqDbunUrsbGly6579+7NsmXLHI5ZunQpffr0qe2mCSGEEELUCrcOuebl5XHgwIGS50lJSWzbto2wsDAaNWrE1KlTOXHiBHPmzAHUCtaEhATatm2L2Wzmyy+/ZMGCBSxYsKDkHA899BD9+vXj5ZdfZvjw4fzwww/8/vvv/PXXX7X++YQQQghRdxw+fJjExES2bt1Kp06d3N2cauXWHrpNmzbRuXNnOnfuDMCUKVPo3LkzTz31FADJyckcPXq05Hiz2cyjjz5Khw4duPTSS/nrr79YsmQJo0aVbnzcp08fvvnmGz777DM6dOjA7NmzmTdvHj179qzdDyeEEEJcxMaPH8+IESPKlJ/ZJCA7O7ta368iGxTUZ27toevfvz/lbSU7e/Zsh+ePPfYYjz322HnPe/3113P99ddfaPOEEEIIITyCx8+hE0IIIUQF2KyQtBr+/U7912Z1d4sAyMjIYOzYsTRs2BA/Pz/at29fZiOAhIQEZsyY4VDWqVMnnnnmmZJ6gJEjR6LRaEqen4/VauXOO+8kMTERg8FAy5Yteeutt8oc9+mnn9K2bVt8fHyIjY3l/vvvr+zHrHEelbZECCGEEFWwazH8+jgYT5aWBcXBlS9Dm2vd1y6gqKiIrl278vjjjxMUFMSSJUsYN24cTZo0qfB0qY0bNxIVFcVnn33GlVdeiU6nq9DrbDYbDRs25NtvvyUiIoI1a9Zw1113ERsby+jRowGYOXMmU6ZM4aWXXmLo0KHk5OTw999/V/nz1hQJ6IQQQoj6bNdi+PZW4JwpTsZkVT56To0FdT/99BMBAQEOZVarY89ggwYNePTRR0ueP/DAA/z666/Mnz+/wgFdZGQkACEhIcTExFS4fXq9nmeffbbkeWJiImvWrOHbb78tCej+97//8cgjj/DQQw+VHNe9e/cKv0dtkYBOCCGEqK9sVtUzd24wB6fLNPDrE9DqatBWrFerMgYMGMDMmTMdytavX88tt9xS8txqtfLSSy8xb948Tpw4gclkwmQy4e/vX+3tcWbWrFl8/PHHHDlyhMLCQsxmc8kK2NTUVE6ePMnAgQNrpS0XQgI6IYQQor46ssZxmLUMOxhPqOMSL632t/f396dZs2YOZcePH3d4/vrrr/Pmm28yY8YM2rdvj7+/Pw8//DBms7nkGK1WW2YRZXFx8QW379tvv2Xy5Mm8/vrr9O7dm8DAQF599VXWr18PgMFguOD3qC0S0AkhhBD1Vd6p6j2uBqxevZrhw4eX9NrZbDb2799P69atS46JjIwkOTm55LnRaCQpKcnhPHq9vsxwbkXeu0+fPtx7770lZQcPHiz5/8DAQBISEvjjjz8YMGBApc5d22SVqxBCCFFfBbje9rJKx9WAZs2asWzZMtasWcPu3bu5++67y2zhefnll/PFF1+wevVqduzYwW233VZm4cOZwCslJYWsrKwKv/emTZv47bff2LdvH08++SQbN250OOaZZ57h9ddf5+2332b//v1s2bKFd95558I+dA2QgE4IIYSorxr3UatZ0bg4QANBDdRxbvLkk0/SpUsXrrjiCvr3709MTEyZhMRTp06lX79+XHPNNVx11VWMGDGCpk2bOhzz+uuvs2zZMuLj40s2LDifSZMmMWrUKMaMGUPPnj3JyMhw6K0DuO2225gxYwbvv/8+bdu25ZprrnHYQ76u0NjLy+x7kTIajQQHB5OTk0NQUJC7myOEEOIiVlRURFJSEomJifj6+lb+BCWrXMFxccTpIK8GV7kK58r7nVY1BpEeOiGEEKI+a3OtCtqCYh3Lg+IkmKtHZFGEEEIIUd+1uValJjmyRi2ACIhWw6w1kKpEuIcEdEIIIcTFQKurkdQkom6QIVchhBBCCA8nAZ0QQgghhIeTgE4IIYQQwsNJQCeEEEII4eEkoBNCCCGE8HAS0AkhhBBCeDgJ6IQQQgjhMfr378/DDz9c6ddpNBoWLVpU7e2pKySgE0IIIUS1Gz9+PBqNBo1Gg16vp0mTJjz66KPk5+dX6PUrVqxAo9GQnZ3tUP7999/z/PPPlzxPSEhgxowZ1dhyzySJhYUQQghRI6688ko+++wziouLWb16NRMmTCA/P5+ZM2dW+ZxhYWHV2ML6Q3rohBBCiIuA1WZlY8pGfj70MxtTNmK1WWv8PX18fIiJiSE+Pp6bbrqJm2++uWTY026388orr9CkSRMMBgMdO3bku+++A+Dw4cMMGDAAgNDQUDQaDePHjwcch1z79+/PkSNHmDx5cklvYEU9/vjjtGjRAj8/P5o0acKTTz5JcXGxwzGLFy+mW7du+Pr6EhERwahRoy7sB1KDpIdOCCGEqOd+P/I7L214iVMFp0rKov2ieaLHEwxqPKjW2mEwGEqCpmnTpvH9998zc+ZMmjdvzqpVq7jllluIjIzkkksuYcGCBVx33XXs3buXoKAgDAZDmfN9//33dOzYkbvuuouJEydWqi2BgYHMnj2buLg4/v33XyZOnEhgYCCPPfYYAEuWLGHUqFH897//5YsvvsBsNrNkyZIL/yHUEAnohBBCiHrs9yO/M2XFFOzYHcpTC1KZsmIKb/R/o1aCug0bNvD1118zcOBA8vPzeeONN/jzzz/p3bs3AE2aNOGvv/7igw8+4LLLLisZWo2KiiIkJMTpOcPCwtDpdAQGBhITE1Op9kybNq3k/xMSEnjkkUeYN29eSUD3wgsvcOONN/Lss8+WHNexY8dKvUdtkoBOCCGEqKesNisvbXipTDAHYMeOBg0vb3iZAfED0Gl11f7+P/30EwEBAVgsFoqLixk+fDjvvPMOu3btoqioiMGDBzscbzab6dy5c7W3w5nvvvuOGTNmcODAAfLy8rBYLAQFBZXUb9u2rdK9fu4kAZ0QQghRT21J3eIwzHouO3ZSClLYkrqF7jHdq/39BwwYwMyZM9Hr9cTFxaHX6wFISkoC1LBmgwYNHF7j4+NT7e0417p160p636644gqCg4P55ptveP3110uOcTbEW5dJQCeEEELUU2kFadV6XGX5+/vTrFmzMuVt2rTBx8eHo0ePctlllzl9rbe3NwBWa/mLN7y9vc97zLn+/vtvGjduzH//+9+SsiNHjjgc06FDB/744w9uv/32Sp3bXSSgE0IIIeqpSL/Iaj2uugQGBvLoo48yefJkbDYbl1xyCUajkTVr1hAQEMBtt91G48aN0Wg0/PTTT1x11VUYDAYCAgLKnCshIYFVq1Zx44034uPjQ0RExHnfv1mzZhw9epRvvvmG7t27s2TJEhYuXOhwzNNPP83AgQNp2rQpN954IxaLhV9++aVkjl1dI2lLhBBCiHqqS1QXov2i0eA8nYcGDTF+MXSJ6lLLLYPnn3+ep556iunTp9O6dWuuuOIKfvzxRxITEwFo0KABzz77LE888QTR0dHcf//9Ts/z3HPPcfjwYZo2bUpkZMUC0+HDhzN58mTuv/9+OnXqxJo1a3jyyScdjunfvz/z589n8eLFdOrUicsvv5z169df2IeuQRq73V52puRFzmg0EhwcTE5OjsMESSGEEKK2FRUVkZSURGJiIr6+vpV+/ZlVroDD4ogzQV5trXIVpcr7nVY1BpEeOiGEEKIeG9R4EG/0f4MovyiH8mi/aAnm6hGZQyeEEELUc4MaD2JA/AC2pG4hrSCNSL9IukR1qZFUJcI9JKATQgghLgI6ra5GUpOIukGGXIUQQgghPJwEdEIIIYQQHk4COiGEEMIDSFKK+qMmfpcS0AkhhBB1mE6nFi6YzWY3t0RUl4KCAoCSrdCqgyyKEEIIIeowLy8v/Pz8SEtLQ6/Xo9VKX4ynstvtFBQUkJqaSkhISEmwXh0koBNCCCHqMI1GQ2xsLElJSWX2GxWeKSQkhJiYmGo9pwR0QgghRB3n7e1N8+bNZdi1HtDr9dXaM3eGBHRCCCGEB9BqtVXa+ktcHGQgXgghhBDCw0lAJ4QQQgjh4SSgE0IIIYTwcBLQCSGEEEJ4OLcGdKtWrWLYsGHExcWh0WhYtGhRucd///33DB48mMjISIKCgujduze//fabwzGzZ89Go9GUeRQVFdXgJxFCCCGEcB+3BnT5+fl07NiRd999t0LHr1q1isGDB/Pzzz+zefNmBgwYwLBhw9i6davDcUFBQSQnJzs8ZGWQEEIIIeort6YtGTp0KEOHDq3w8TNmzHB4/uKLL/LDDz/w448/0rlz55JyjUZT7Qn7hBBCCCHqKo+eQ2ez2cjNzSUsLMyhPC8vj8aNG9OwYUOuueaaMj145zKZTBiNRoeHEEIIIYSn8OiA7vXXXyc/P5/Ro0eXlLVq1YrZs2ezePFi5s6di6+vL3379mX//v0uzzN9+nSCg4NLHvHx8bXRfCGEEEKIaqGx2+12dzcC1DDpwoULGTFiRIWOnzt3LhMmTOCHH35g0KBBLo+z2Wx06dKFfv368fbbbzs9xmQyYTKZSp4bjUbi4+PJyckhKCioUp9DCCGEEKKqjEYjwcHBlY5BPHLrr3nz5nHnnXcyf/78coM5UFuldO/evdweOh8fH3x8fKq7mUIIIYQQtcLjhlznzp3L+PHj+frrr7n66qvPe7zdbmfbtm3ExsbWQuuEEEIIIWqfW3vo8vLyOHDgQMnzpKQktm3bRlhYGI0aNWLq1KmcOHGCOXPmACqYu/XWW3nrrbfo1asXKSkpABgMBoKDgwF49tln6dWrF82bN8doNPL222+zbds23nvvvdr/gEIIIYQQtcCtPXSbNm2ic+fOJSlHpkyZQufOnXnqqacASE5O5ujRoyXHf/DBB1gsFu677z5iY2NLHg899FDJMdnZ2dx11120bt2aIUOGcOLECVatWkWPHj1q98MJIYQQQtSSOrMooi6p6oREIYQQQogLUdUYxOPm0AkhhBBCCEcS0AkhhBBCeDgJ6IQQQgghPJwEdEIIIYQQHk4COiGEEEIIDycBnRBCCCGEh5OATgghhBDCw0lAJ4QQQgjh4SSgE0IIIYTwcBLQCSGEEEJ4OAnohBBCCCE8nJe7GyAqKT8D7DYwhIFO5+7WCCGEEKIOkIDOUxiTYf9S2PgxWE3Q9jroNBZCGrm7ZUIIIYRwMwnoPEFuCnx7GxxfX1q24kXYMhvu+E2COiGEEOIiJ3PoPMHJLY7B3BnGk7DpM7AW136bhBBCCFFnSEBX11lMsGWO6/p/v4WCjNprjxBCCCHqHAno6jwNaMpZ/FBenRBCCCEuChLQ1XVe3tDtDtf1nW8Bv8jaa48QQggh6hwJ6DxBTHtocUXZ8vCm0OkmSV8ihBBCXORklasnCIiCYe/Aya2wfpZKW9JhLDQbCMEN3N06IYQQQriZBHSeIjAaWl4JiZeCzQq+Qe5ukRBCCCHqCAnoPI23v7tbIIQQQog6RubQCSGEEEJ4OAnohBBCCCE8nAR0QgghhBAeTgI6IYQQQggPJwGdEEIIIYSHk4BOCCGEEMLDSUAnhBBCCOHhJKATQgghhPBwEtAJIYQQQng4CeiEEEIIITycBHRCCCGEEB5OAjohhBBCCA8nAZ0QQgghhIeTgE4IIYQQwsNJQCeEEEII4eEkoBNCCCGE8HAS0AkhhBBCeDgJ6IQQQgghPJwEdEIIIYQQHk4COiGEEEIIDycBnRBCCCGEh5OATgghhBDCw0lAJ4QQQgjh4dwa0K1atYphw4YRFxeHRqNh0aJF533NypUr6dq1K76+vjRp0oRZs2aVOWbBggW0adMGHx8f2rRpw8KFC2ug9XWczQbGZMg+Crmn3N0aIYQQQtQgtwZ0+fn5dOzYkXfffbdCxyclJXHVVVdx6aWXsnXrVv7zn//w4IMPsmDBgpJj1q5dy5gxYxg3bhz//PMP48aNY/To0axfv76mPkbdk5cGGz+CD/vBjPbw6RWwcyEUZLq7ZUIIIYSoARq73W53dyMANBoNCxcuZMSIES6Pefzxx1m8eDG7d+8uKZs0aRL//PMPa9euBWDMmDEYjUZ++eWXkmOuvPJKQkNDmTt3boXaYjQaCQ4OJicnh6CgoKp9IHcpMsIfz8LGj8vWDX0Vut0OOn3tt0sIIYQQ51XVGMSj5tCtXbuWIUOGOJRdccUVbNq0ieLi4nKPWbNmTa21063y02DTJ87r/nweclNqtz1CCCGEqHEeFdClpKQQHR3tUBYdHY3FYiE9Pb3cY1JSXAcyJpMJo9Ho8PBY2UfBVaeryQiFWbXbHiGEEELUOI8K6EANzZ7tzIjx2eXOjjm37GzTp08nODi45BEfH1+NLa5lPgHl13t51047hBBCCFFrPCqgi4mJKdPTlpqaipeXF+Hh4eUec26v3dmmTp1KTk5OyePYsWPV3/jaEhgH/hHO62I6gJ+LOiGEEEJ4LI8K6Hr37s2yZcscypYuXUq3bt3Q6/XlHtOnTx+X5/Xx8SEoKMjh4bECY+HGb0Dv51juHwHXfew62BNCCCGEx/Jy55vn5eVx4MCBkudJSUls27aNsLAwGjVqxNSpUzlx4gRz5swB1IrWd999lylTpjBx4kTWrl3LJ5984rB69aGHHqJfv368/PLLDB8+nB9++IHff/+dv/76q9Y/n1totRDXGe5dB4dXQ+puaNgdGnSDkIbubp0QQgghaoBb05asWLGCAQMGlCm/7bbbmD17NuPHj+fw4cOsWLGipG7lypVMnjyZnTt3EhcXx+OPP86kSZMcXv/dd98xbdo0Dh06RNOmTXnhhRcYNWpUhdvl0WlLhBBCCOGxqhqD1Jk8dHWJBHRCCCGEcIeLIg+dEEIIIYQoSwI6IYQQQggPJwGdEEIIIYSHc+sqV1ELzAWQdwqOrQdTLjTqDUGx4Bfu7pYJIYQQoppIQFefmfJg7xJYdA/YrKXlbUbAVa9AgOtky0IIIYTwHDLkWp8ZT8DCux2DOYBdi2DXYtd7vgohhBDCo0hAV5/9M8910LbmbchLrd32CCGEEKJGSEBXn2UfcV2Xlwo2S+21RQghhBA1RgK6+qzFENd1DbuDt3/ttUUIIYQQNUYCuvqsUR8IiitbrtHC4OfAEFLrTRJCCCFE9ZOArj4LiYfxS6DFUBXEAUS2hNsWQ2Qr97ZNCCGEENVG0pbUd2FNYNSHUJgJVgv4BkFAlLtbJYQQQohqJAHdxcA3SD2EEEIIUS/JkKsQQgghhIeTgE4IIYQQwsNJQCeEEEII4eEkoBNCCCGE8HBVXhSxYcMGVqxYQWpqKjabzaHujTfeuOCGCSGEEEKIiqlSQPfiiy8ybdo0WrZsSXR0NBqNpqTu7P8XQgghhBA1r0oB3VtvvcWnn37K+PHjq7k5QgghhBCisqo0h06r1dK3b9/qbosQQgghhKiCKgV0kydP5r333qvutgghhBBCiCqo0pDro48+ytVXX03Tpk1p06YNer3eof7777+vlsYJIYQQQojzq1JA98ADD7B8+XIGDBhAeHi4LIQQQgghhHCjKgV0c+bMYcGCBVx99dXV3R4hhBBCCFFJVQrowsLCaNq0aXW3RQghhKj7LCYoyAA74BcGel93t0iIqi2KeOaZZ3j66acpKCio7vYIIYQQdVf2UVj6FMzsAzN7wa9PQNZhd7dKCDR2u91e2Rd17tyZgwcPYrfbSUhIKLMoYsuWLdXWQHcwGo0EBweTk5NDUFCQu5sjhBCiLsg+Bp9eAcYTjuX+kTDhDwht7J521RV2O1jN4OXj7pZ4tKrGIFUach0xYkRVXiaEEEJ4Jrsd9vxUNpgDyE+DbV9Bv8dAV+UdNT1XcaHqudz6JaTtgUa9oO0oCI6/OH8eblKpHrp9+/bRokWLmmxPnSA9dEIIIRwU5sBX18Hxjc7rI1vB+J9Ub93FxFIMh/6Eb8aCzVpa7u0P45dAXGf3tc1DVTUGqdQcus6dO9O6dWsef/xx1q5dW+lGCiGEEB5J6wXeAa7rvf1Ao6u99tQVeSmw4E7HYA7AnA8LJkBuqnvadRGqVECXkZHBK6+8QkZGBiNHjiQ6Opo777yTxYsXU1RUVFNtFEIIIdzLxx963eO6vtd9asXrxSbnGJhynddlHIDC9Nptz0WsUgGdr68vw4YN4+OPPyY5OZmFCxcSGRnJE088QXh4OMOHD+fTTz8lNVUiciGEEPVMXGc1N+xczQZDwiVVP6+1WC24OLUTMg5BkbHq56ptFnP59ef23IkaU6VVrs7s37+fxYsX88MPP7B+/XreeOMN7rvvvuo4da2TOXRCCCGcyk+DjIOw9QsVrHS+BSJaQEBUFc+XrhZUrHpV9XRpNNBiKAx9BULiq7ftNSHrMLzTFWyWsnX+kXD3SghqUOvN8mRVjUGqLaA7W0ZGBpmZmTRv3ry6T10rJKATQghR46xW2PihymV3ruh2cMv3EBhd++2qDHM+rJsFfz5Xtu6Gz6H1taCtUsrbi1atLIo44/PPP2fJkiUlzx977DFCQkLo06cPR44cITw83GODOSGEEKJW5CXDyped153aoean1XXe/tDtdrjpW4jrAn7hkNgP7lwGzQZKMFeLqvSTfvHFFzEYDACsXbuWd999l1deeYWIiAgmT55crQ0UQggh6iVzPhRmua4/tav22nIh/MKgxRVwywKY9BeM/gLie4BPoLtbdlGpUsa/Y8eO0axZMwAWLVrE9ddfz1133UXfvn3p379/dbZPCCGEqJ+8fEHnrXZXcCakYe2250JdjKt865Aq9dAFBASQkZEBwNKlSxk0aBCgVsEWFhZWX+uEEEKI+so/Cjrd7LzOL0wtthCigqrUQzd48GAmTJhA586d2bdvH1dffTUAO3fuJCEhoTrbJ4QQQtRP3ga47HHIOqJ2WzgjIEotiJDVoaISqhTQvffee0ybNo1jx46xYMECwsPDAdi8eTNjx46t1gYKIYQQ9VZQLFz3MeSdUol4/SMhpBEExakUJkJUUI2kLfF0krZECCGEEO5Qq2lLPvvsM+bPn1+mfP78+Xz++edVOaUQQgghhKiiKgV0L730EhEREWXKo6KiePHFFy+4UUIIIYQQouKqFNAdOXKExMTEMuWNGzfm6NGjF9woIYQQQghRcVUK6KKioti+fXuZ8n/++adkgYQQQgghhKgdVQrobrzxRh588EGWL1+O1WrFarXy559/8tBDD3HjjTdW6lzvv/8+iYmJ+Pr60rVrV1avXu3y2PHjx6PRaMo82rZtW3LM7NmznR5TVFRUlY8qhBBCCFHnVSltyf/+9z+OHDnCwIED8fJSp7Bardx2222VmkM3b948Hn74Yd5//3369u3LBx98wNChQ9m1axeNGjUqc/xbb73FSy+9VPLcYrHQsWNHbrjhBofjgoKC2Lt3r0OZr69vZT6iEEIIIYTHuKC0Jfv372fr1q0YDAY6dOhA48aNK/X6nj170qVLF2bOnFlS1rp1a0aMGMH06dPP+/pFixYxatQokpKSSt579uzZPPzww2RnZ1eqLWeTtCVCCCGEcIdaTVsC8MknnzBy5EjGjRvH9ddfz9VXX83HH39c4debzWY2b97MkCFDHMqHDBnCmjVrKtyGQYMGlQkk8/LyaNy4MQ0bNuSaa65h69at5Z7HZDJhNBodHkIIIYQQnqJKAd2TTz7JQw89xLBhw5g/fz7z589n2LBhTJ48mWnTplXoHOnp6VitVqKjox3Ko6OjSUlJOe/rk5OT+eWXX5gwYYJDeatWrZg9ezaLFy9m7ty5+Pr60rdvX/bv3+/yXNOnTyc4OLjkER8fX6HPIIQQQghRF1RpyDUiIoJ33nmnzDZfc+fO5YEHHiA9Pf285zh58iQNGjRgzZo19O7du6T8hRde4IsvvmDPnj3lvn769Om8/vrrnDx5Em9vb5fH2Ww2unTpQr9+/Xj77bedHmMymTCZTCXPjUYj8fHxMuQqhBBCiFpV1SHXKi2KsFqtdOvWrUx5165dsVgsFTpHREQEOp2uTG9campqmV67c9ntdj799FPGjRtXbjAHoNVq6d69e7k9dD4+Pvj4+FSo3UIIIYQQdU2VhlxvueUWh4UMZ3z44YfcfPPNFTqHt7c3Xbt2ZdmyZQ7ly5Yto0+fPuW+duXKlRw4cIA777zzvO9jt9vZtm0bsbGxFWqXEEIIIYSnqVIPHagFCUuXLqVXr14ArFu3jmPHjnHrrbcyZcqUkuPeeOMNl+eYMmUK48aNo1u3bvTu3ZsPP/yQo0ePMmnSJACmTp3KiRMnmDNnTpn37tmzJ+3atStzzmeffZZevXrRvHlzjEYjb7/9Ntu2beO9996r6kcVQgghhKjTqhTQ7dixgy5dugBw8OBBACIjI4mMjGTHjh0lx2k0mnLPM2bMGDIyMnjuuedITk6mXbt2/PzzzyWrVpOTk8tsJZaTk8OCBQt46623nJ4zOzubu+66i5SUFIKDg+ncuTOrVq2iR48eVfmoQgghhBB13gXloauvJA+dEEIIIdyh1vPQCSGEEEKIukECOiGEEEIIDycBnRBCCCGEh5OATgghhBDCw0lAJ4QQQgjh4SSgE0IIIYTwcBLQCSGEEEJ4OAnohBBCCCE8nAR0QgghhBAeTgI6IYQQQggPJwGdEEIIIYSHk4BOCCGEEMLDSUAnhBBCCOHhJKATQgghhPBwEtAJIYQQQng4CeiEEEIIITycBHRCCCGEEB5OAjohhBBCCA8nAZ0QQgghhIeTgE4IIYQQwsN5ubsBwkNZLZCXApYi8DJAQAzodO5ulRBCXDysVshLPn0d9oWA2Ipfh3NTwZwLWi/wjwBv/5ptq6hxEtCJystLhc2zYe27UJQDhlC49BHocCMERLq7dUIIUf/lpcHWL2DN21CYpa7DfR6EzuPKvw6b8uD4Bvj5/yDjgAro2oyAQU9DSKNaa76ofhLQicox5cLyF2HzZ6VlhVmwdBoUZEC/x8Hb4L72CSFEfWfKh9WvwfpZpWWFWfDHs+qG+/InwcdFj1vyP/DFyNLnNgvs+A5OboHxSyAormbbLmqMzKETlZOXBls+d1639j3IP1W77RFCiItNfips/Mh53caPVL3T16XDb/9xXpd5CFJ2VE/7hFtIQCcqJz8V7DbndVYzFGTVbnuEEOJiU5ABNqvzOptF1TtTXAjJ21yf99DyC26acB8J6ETlnG/irN63dtohhBAXK/15prW4qtfqwDfE9euCG1a5ScL9JKATleMfCaGJzuti2qvVUkIIIWqOXwREtHBeF9EC/FwsivCPgp6TnNdptNDiiuppn3ALCehE5QTGwNi5KrA7W1AcXD+7bLkQQojqFRgNY76EgGjH8oDT5YFRzl+n84Jut0OT/o7lWi+44XMIalAjzRW1Q2O32+3ubkRdYzQaCQ4OJicnh6CgIHc3p27KOQ6ndkH6PohuAxEtIVguBkIIUWtyjkPaXkjdDVGtILJVxYZN89PUa4+sUb19jXqqXKIyZaZOqGoMIgGdExLQCSGEEMIdqhqDyJCrEEIIIYSHk4BOCCGEEMLDSUAnhBBCCOHhJKATQgghhPBwsperEEIIIWqOMRlSd0HSaghpBE0HQGCsrKqtZhLQCSGEEKJmZB+FOcPVXrFnaL1g7DeQ2A+8fNzXtnpGhlyFEEIIUf1MebD0ScdgDtR+s/NuhtwU97SrnpKATgghhBDVryAd9vzovM5igpNba7c99ZwMuQohhBDVxWaDvBQVsHj5qB0YtBdp34m1GGxW1/UFGbXXlouABHRCCCFEdchPg52LYNUrkJeq9ra+9BFof/3Fuc+1TyCENIbsI87rG3ar3fbUcxfpbYMQQghRjcyFsG4W/PyoCuZABXi/PgF/vQXmfPe2zx0CY+DKl5zXNRkAQXG12556TgI6IYQQ4kLlp8Kat53XrZ9ZGuRdbBIugVu+h6jW6rlvMFz6KIycdXH2WtYgGXIVQgghLlRBOljNzutsFshPh7DE2m1TXeAbBM0GQkx7KC4EnRf4R4FO7+6W1TsS0AkhhBAXystQfr3+PPX1XUCUu1tQ78mQqxBCCHGh/MIhornzutBE8I+o3faIi47bA7r333+fxMREfH196dq1K6tXr3Z57IoVK9BoNGUee/bscThuwYIFtGnTBh8fH9q0acPChQtr+mMIIYS4mAVGw+gvVGB3NkMo3PiVWiAgRA1y65DrvHnzePjhh3n//ffp27cvH3zwAUOHDmXXrl00atTI5ev27t1LUFBQyfPIyNKJlWvXrmXMmDE8//zzjBw5koULFzJ69Gj++usvevbsWaOfRwghxEUsqjXctRKSt8OpfyGqDcR1huCG7m6ZuAho7Ha73V1v3rNnT7p06cLMmTNLylq3bs2IESOYPn16meNXrFjBgAEDyMrKIiQkxOk5x4wZg9Fo5Jdffikpu/LKKwkNDWXu3LkVapfRaCQ4OJicnByHwFEIIYQQoiZVNQZx25Cr2Wxm8+bNDBkyxKF8yJAhrFmzptzXdu7cmdjYWAYOHMjy5csd6tauXVvmnFdcccV5zymEEEII4ancNuSanp6O1WolOjraoTw6OpqUFOcb9sbGxvLhhx/StWtXTCYTX3zxBQMHDmTFihX069cPgJSUlEqdE8BkMmEymUqeG43Gqn4sIYQQQoha5/a0JRqNxuG53W4vU3ZGy5YtadmyZcnz3r17c+zYMV577bWSgK6y5wSYPn06zz77bFWaL4QQQgjhdm4bco2IiECn05XpOUtNTS3Tw1aeXr16sX///pLnMTExlT7n1KlTycnJKXkcO3aswu8vhBBCCOFubgvovL296dq1K8uWLXMoX7ZsGX369KnwebZu3UpsbGzJ8969e5c559KlS8s9p4+PD0FBQQ6Pes94Eg78CateV5tJZx8Fm9XdrRJCCCFEFbh1yHXKlCmMGzeObt260bt3bz788EOOHj3KpEmTANVzduLECebMmQPAjBkzSEhIoG3btpjNZr788ksWLFjAggULSs750EMP0a9fP15++WWGDx/ODz/8wO+//85ff/3lls9YJ2UmwZxrVRB3hncA3LYYYjuD1u3pCYUQQghRCW4N6MaMGUNGRgbPPfccycnJtGvXjp9//pnGjRsDkJyczNGjpUGH2Wzm0Ucf5cSJExgMBtq2bcuSJUu46qqrSo7p06cP33zzDdOmTePJJ5+kadOmzJs3T3LQnVGYBYvvdwzmAMx58NUNcPdqCG7gnrYJIYQQokrcmoeurqrXeejS98O73VzX3/4rNO5de+0RQgghRAmPy0Mn3MRiKr++KLtWmiGEEEKI6iMB3cXGN1g9XAlrUnttEUIIIUS1kIDuYhMYA/3/47yu7SgIiKrd9gghhBDigrk9sbCoZTo9dBgNvkHw5/MqfYlPEPScBN0ngCHU3S0UQgghRCVJQHcx8guDjmOhSX+wFIHOGwKiVbAnhBBCCI8jAd3FSqOBoDh3t0IIIYQQ1UDm0AkhhBBCeDgJ6IQQQgghPJwEdEIIIYQQHk4COiGEEEIIDycBnRBCCCGEh5OATgghhKjrigvAlOvuVog6TNKWCCGEEHVVXhqc2gHrZoI5D9rfAM0HQ3BDd7dM1DES0AkhhBB1UX46LJ0G278pLTvyN4Q0hvFLICTefW0TdY4MuQpR04wnIWkVrP8A9v8OOcfd3SIhhCfIPOQYzJ2RfQTWzwKLufbbJOos6aEToiZlHIQvRkD20dIy/0i47UeIau22ZgkhPMCWL1zXbfsKet8nO/6IEtJDJ0RNyU+HBRMcgzmA/DSYeyPkJrunXUIIz2Atdl1ns9ReO4RHkIBOiJpSkAEntzivyzqsJjsLIYQrnca6rmszEgyhtdcWUedJQCdETSkuKL9eUhAIIcoT1Qqa9C9b7hcGl04BvaHWmyTqLplDJ0RNMYSClw9YTGXrNBoIjKn9NgkhPEdANIz8AA7+CeveB3M+tL4Wut2uVroKcRYJ6ET9YDGpOSXe/u5uSamAaOh1P/z1etm6jmPV4gghhChPYAx0uglaXKGucYYw0Ond3SpRB0lAJzxbfjqk7VEpQUxGaDsKmg2sG0k39QbofY/qqfvrdSjMAp9A6HE39LwLfIPc3UIhhKfwC3d3C0Qdp7Hb7XZ3N6KuMRqNBAcHk5OTQ1CQ/NGtswoy4c/nYdOnjuUhjU4n3Wzknnady2qFvGQoLgQvX3XHLXfYQgghnKhqDCKLIoTnyjpcNpgDlSZkzTvO5665g06negwjmqvM7hLMCSGEqGYS0AnPtX2e67ptX6u0IUIIIcRFQAI64bnK64GzFYPMJhBCCHGRkIBOeK72N7iua3UtGEJqrSlCCCGEO0lAJzxXRHNoMqBsuW8wDHiibqUwEUIIIWqQpC0RnisgCkbOgn1LYf1MMOdBiyuh172SdFMIIcRFRQI64dkCY6DrrdDqKrBZ1TCrl4+7W1U32GxgLQKdD2h17m6NEEKIGiQBnagf/CPc3YK6w2qBnKPwzzw4vgEiWkLX8Sovn7efu1snhBCiBkhAJ0R9k/IPzL5aJTIGtQ/khg9gzJfQfDDovN3bPiGEENVOFkUIUZ/knoIFE0qDuTPsNvj+LlUvhBCi3pGAToj6pCADMg85rzPnQc6x2m2PEEKIWiFDrkLUJ3Zr+fVWc+20o7qY8yEvVf3XOwACo0Av8wCFqC1pBWlkm7LRoCHYJ5hIv0h3N0m4IAGdEPWJIQz8IyE/rWydTg+hibXfpqoyJsPvz8CO+WoFs84butwG/R5Vq5uFEDXGbDWzPW07T/79JMfzjgMQHxjP832fp31Ee7xlLm6dI0OuQtQngbFwzQzndQOmec5q4MIsWPIIbP9GBXOgehc3fgR//g9Mee5tnxD13PHc40xcOrEkmAM4lnuMCUsncDz3eDmvFO4iAZ0Q9YlWC036w4Q/oekgCIiGht3hlu9V75an7J6RnwZ7lziv++dryE+t3fYIcRExWUzM2TUHi91Sps5is/DV7q8we9r0jYuADLmK2mcxgVavgg9R/XwCoGFXuOEzNfdM7wuGUHe3qnLy013X2axQlFN7bRHiIlNgKeDf9H9d1m9P305BcYEMu9YxEtCJ2mGzqWS3u3+EpFUQ1kzt8BASrya7i+rnG6Qensg3uPx6T+lpFMID+ep8aeDfgH1Z+5zWNwxsiI/syFPnSBeJqB1pu+GDfrB0GuxfCuvfh5m91T6sxUXubp2oa/wjIbqd87qES8DPQ+YCCuGBDHoDd7S/w2X9HW3vwOBlqMUWiYqQgE7UvPx0WHRv2WEyux0WTYK8iyjZbX4GpOyA7d+qHRyyj5VO+helAqLUzhYRLRzLYzrCiFngF+aedglRWYVZkLYX/v0O9v0GWUfAUvfnnzUNacq0ntPw0pYO5Om1ep7u/TQJwQnua5hwSYZcRc0rzILkbc7rLCZI2wOhjWu1SW6RmwI/3AcHfi8t8w2Gm+ZDg66gk6+jg7BEuO0nyD2pUpgEN1TpSgKi3N0yISomLxWWPa0W8pyhN8ANcyCxn5rfWkcFegdybdNr6dugL4dzDqPRaGgc1JgIQwS+XnW33Rcz+Qsiap6t7EopB5aLYMjVYoI17zoGc6B6Lb8cCfesvTiC2soKjFaPuM7ubokQlWO3w64fHIM5UNvyfTMW7lsP4c3c07byWExqi0BzLga9Hw0DomjYsKG7WyUqQIZcRc3zDYGQRs7rNBrXc6Xqk7xU2PSJ8zpzPpzcWrvtEULUrLxT8NebzutsFtj9U+22pyLy0mDlK/B+T5jZB97tCj8+BMaT7m6ZqAC3B3Tvv/8+iYmJ+Pr60rVrV1avXu3y2O+//57BgwcTGRlJUFAQvXv35rfffnM4Zvbs2Wg0mjKPoqKLoBeoogoy1Re0vNQQ1SnodLJbjaZsXe/71QT4+s5qhuIC1/XZR2qvLUKImmezQm6y6/qMA7XXloqwFMG692H1a6XXKpsV/p0P39+l5v9aitTfDmMyWIvd215RhlsDunnz5vHwww/z3//+l61bt3LppZcydOhQjh496vT4VatWMXjwYH7++Wc2b97MgAEDGDZsGFu3OvZuBAUFkZyc7PDw9ZUxf4pyIGk1zL0R3usJX4yAPT+rAK+mNeoFE5erZLd+YRDTHkbPgb4Pe25qjcrQGyCogev6Bl1rry1CiJqn94XYjq7rm1xWe22piNxTKqBz5vBqMJ6A36bBrL7wYT9Y/iLkyI4RdYnGbrfb3fXmPXv2pEuXLsycObOkrHXr1owYMYLp06dX6Bxt27ZlzJgxPPXUU4DqoXv44YfJzs6ucruMRiPBwcHk5OQQFFRPgg2rFXZ8BwvvKlt3+ZPQ6x7Xub1sVkBTPYmAi4xgzlP7cnrKNlTVwW4/fac7sWxdRHO47Ue1bZcQov5IWg2fX1O2PCAaJvyh8nDWFSn/wqxLXNdf8xb8+axjB0BYE3XtCpY5dtWpqjGI23rozGYzmzdvZsiQIQ7lQ4YMYc2aNRU6h81mIzc3l7AwxxQGeXl5NG7cmIYNG3LNNdeU6cG7KOWdhF8fd1638iXnm7kbk2Hvr/Dd7SrtyNF1Fz5M6xsEQXEXVzAHari52SC49h3wCy8ta3mV2pZLgjkh6p/YTjDmK8fe+YRLYPzPdSuYA9D7OZ8Wc4ZfaNk9lDMPwcHlNdsuUWFuW+Wanp6O1WolOjraoTw6OpqUlJQKneP1118nPz+f0aNHl5S1atWK2bNn0759e4xGI2+99RZ9+/bln3/+oXnz5k7PYzKZMJlMJc+NRmMVPlEdV5Cp0oc4Yy1W+dBCE0rLjCdh7ljHdCPb50LnW2HQ0xdfQFYd/MKg083QdCCYjODlA36R4Bvo7pYJIWqCbyC0uhoadFFTXnTe6jpQF7fi84+EFlc530M5pJEaXXG2f+v2edB2pNpyULiV29OWaM65I7Db7WXKnJk7dy7PPPMMP/zwA1FRpXmpevXqRa9evUqe9+3bly5duvDOO+/w9ttvOz3X9OnTefbZZ6v4CTyEVl9+/dl5hWw22D7fee64rXOg000S0FWVVgfBDYBy5tMJIeoPjUaNSgTFubsl5fMNgqtegbwUOLG5tDy4IVz7Liy+3/nr9H7quibczm0BXUREBDqdrkxvXGpqapleu3PNmzePO++8k/nz5zNo0KByj9VqtXTv3p39+/e7PGbq1KlMmTKl5LnRaCQ+vo51h18ov3A13yHzUNk63xC1EvWM/DTY/Knrc238GOK7g9bt9wNCCCGqS3BDGDtPrc7NTFJ/F4IbwpE1kO18sSK9JqlFX8Lt3DaHztvbm65du7Js2TKH8mXLltGnTx+Xr5s7dy7jx4/n66+/5uqrrz7v+9jtdrZt20ZsrOs5Sj4+PgQFBTk86owzw6GpuyDzsMpZVhWB0XD9p2UXPuj0cMNsCIgpLbPbyk+xYc5TvXiiZjn87pOq/rsX1So918SB1DwOpOaRnmc6/wuEqCFFxVaOZRawNyWX45kFFBVXwzaCAZEQ2wHaDof4HqpnMaEvNHbyd7nddRDd/sLfU1QLt3axTJkyhXHjxtGtWzd69+7Nhx9+yNGjR5k0aRKges5OnDjBnDlzABXM3Xrrrbz11lv06tWrpHfPYDAQHBwMwLPPPkuvXr1o3rw5RqORt99+m23btvHee++550NeiLw02PwZ/P2WCqK0XtD+Bhj4VNW672M6wKQ1sOdHtcAhui10GA3B8Y7bTvmFQqtrYJOLXrqOY8HLu2qfSVRMfhps/hz+ngGmXPW7b3e9mr9Y14du6imzxcq/J4w89t12DqapyeEtowN55foOtI0Lwkvn9rSe4iKSaixi1sqDfLX+KCaLDR8vLTf3bMSk/k2JCqzmNF2BsXD9Z3BqJ2z9AnQ+0PU2tUL/Ysgj6iHcmrYEVGLhV155heTkZNq1a8ebb75Jv379ABg/fjyHDx9mxYoVAPTv35+VK1eWOcdtt93G7NmzAZg8eTLff/89KSkpBAcH07lzZ5555hl69+5d4TbVibQlFhOsfh1Wvly2rkl/uO6TC5vHZrOUP2SamQQf9oeibMfyqDZwywIJKmqSxaQyzK9wkronsZ+6sMocxlp3IDWXq976C7PVsXfax0vLrw9fSmKETAoXtSO3qJhnf9zFd5vL5oG7oWtDnhrWhkDf88ybrqozozPVkcZKOFXVGMTtAV1dVCcCuqyjavsVV0Of96yF6DY19/52O2QlwV9vwe4f1KKJrrdD51tOT+oXNSb7qEr87PJ3v0b1ropaY7JYefqHnXyz8ZjT+jsvSeSJoS3R62RyuKh5h9Pzufz1Fdic/PXWauDPR/qTEOEir6io86oag8is9rrKlFP+PLaswzUb0Gk0ahHF0Jeg/+OAVnWtyx+smmcylv+7zzwsAV0tyyuysPmIi7Q/wMbDmeSbrIT4yfdD1LzsQrPTYA7AZofsAjMgAd3FRvpM66rzJXmsrXkLesPpJfcxEszVFq/z/O4DZM5KbfPRa4kNcT0vqUGIAR+9XE5F7fDzLr8vxs9H+mouRnIFqqv8I6H5EOd1QQ0c04yI+sU/QiX4dCYoTrbZcYMAHz339W/msv6ufk0w6OWPqKgd4f7etI1zPhTXNi6IcH9ZtHYxkoCurrKaoff9auuYswXGwrVvg0Z+deSnQcoO2L0Ejm9SW5XVB2cSfMZ1diwPjFHbhMmCFLdoGRPIE1e2RHtW56lOq+GZa9vQJFKGt0TtCQ/w4f2bu5B4zjy5xAh/3r+5C+EBPtX7hsWFkHUEDvwO+5aqKT+SRqnOkUURTtSJRRFpe+GTwTDgv+oPeNZh9QfdZlUrX4e9pVY8XqxyjsP82+H4htKy0AS4eT5EtHBbs6pVXqragi19v1qIEtJYFqS4Wb7JQnqeiV0njWg1GlrHBhIR4CNDXMItThmLOJFdyLHMAuLD/GgQYiA6qJpTlhTlqoVxP00u3fpL6wWDnoXON9fNbcw8nKxyrUZ1IqBL2QGz+qr/9/JVw3BFOSonGahs3i2vdE/b3K3ICAvvhr0/l60LTYQ7flXBrxBCiAtzcht8eJnzuvFLIOES53XGZLXAS6s/vX9tSMXf02ZTu1WYc0F3+u/fRbRXrKxyrW/8QiEgSvXSWIpUj9QZGq1K6Hixyk+Dfb84r8tKUhcSCeiEEOLCWEywtpyk/KteUwnrfc8KOky5cPhv+OX/SrcLS7wMrnkDwl3PQy1RkKlu1n9/GvLT1d+71sNgyAsQUs+25KxmMhGrrgqIhaGvOq/rfV/VVrnmp5++a6rE3AebDfJOqbslSx3Z5qi4QOXJcyU/ternLvkZ5VX9HEIIUR8UF6mbZFdyjqkOh7Ol/Atzxzju/Zq0Ej67Sm1lWB67HfYvgx/uU9diUFtR7voBvh4NuSnlv/4iJz10dZVWC00Hwu2/wO/PqC9JSDz0+z9oMsDxjuh88tLg0HK1jVR+GjTuC5c9DmFNy9/Cy3gSdnwPmz5Rk2JbXwO97lNz1cpLq1HTfILAy8d1gBlchbu4vDQ4vErt0JB3CuJ7Qf8n1M9IX81zUoQQwgNkFHsRGNcd7+MbnR8Q18VxKLQgE5Y+6fzYvFNwdG35vWy5yfDHM87rzuxpLaMvLkkPXV3mG6g2RB47D+7fDLctUXu5Vmbbp4JMWPYkfD9R7cOXlwo7F8IHl8Kpf12/zpgM39wMS/8LmYfUF23DR/DRALVAw50CoqHHXc7rEi5V9ZVRkAXLX4Dv7lCBc14q7F4MH/SDlH8uvL1CCOFhTmYXMuqDDaQ0H6tuoM+l1cElk1XO1DOKCyF5q+uTHlxe/psWF6iOBJeN2lL+6y9yEtB5Ar9QCI6rWkLZ3GT4Z27ZcmsxLHkE8jOcvy5lu/MvT2EWrHm7bDd7bdL7Qp8Hoc9DasEIqHkWbUfBqA9U72bydvjlCfh+klpmn1tOSpO8U7D5s7LlNota2ZWfVjOfQwgh6iCbzc6Sf5M5klHAE38aSRm1wHH+W0hj7OMWqt2EzqbVqdRaroQ3Lf+Ndd6l13RnqjL6chGRIdf6Lmm167qTW9UWY/7hjuU2K2z90vXrdi1SQ7/uzIcWEAWX/we636km4Xr7q3mFtmJYN1Oldjlj+1w1cfemec7bfGy96/c5tRMKc2pvZw4hhHCznMJiFm09AcCapBxuNPrxaN9PaB1iQWO3k2b1o3VMC4L0escXBkRD34fh50fLnlSrgzbDy3/jgCjofCts/LBsnbd/2byswoEEdPVdefO/NBoXCYo1assvV3Q+1InOXS9fCG3sWJa83TGYOyNlO2z6FC57AnTn/LN3NpxwNm0d+KxCCM9kylW9/BkHVVASHK96sc69DlXSKWMRKTlFZOSbaRhqICLAh7Bq2iFCq9Xg41V63TucUcD9i0v3l+7WOJRPnSVa0GhU0HZ8E2z/prTcyweu/+z8u9x4+cKlUyB9r1pIcYZPENyyQJKqn4cEdPVdwqXqS+ZsVWizweAbUrZcq4Vud8D2ec7P2fX2uttj5Wx4+YxNn0K3O8tumxbfQwW2dlvZ1yReBoaw6m2jEOLikJcGf70O62eVXoN9Q2DMF9ColxpirIL9p3K5ffZGjmcVlpT1ax7BK9d3JCb4whdxBRv03NY7gS1HtzmtH983gSCD3mkdAVEw9CU1vy55mwrGotuqxQznu3kGdX2+/lM1l+7UDnW+iJbVEgTXd/LTqe/8IuHyp7Dv/pHUnneSbwjBW6Mj9Mg6/BMHqMSNzhI+hjeDTrfAtnOGXiNbQ+dbQKerleZXWmG26zpzHuAkaAuIgqtegyVTHMsNoaq8Mgkx6zKrRc0lLC5UPbcB0RW7wAohqmbfr2oKyNmKsuHL6+C+9WXnoFVASk4h4z7ZQIrRcR7zqv3pvL50L88Ob4uf94X/ae/dNJw+TcNYczDTobxvs3B6JJznJtcQqh5Rrar25v4R6hHboWqvv0hJQFffmXMxhjdh7eVTeHXrW5wqOIVOo2Ng/AAe0euJO7nN+URT/wgY9Ax0ukmtbi3Oh45joVFPCKrD20+1HQn/fO28rtlg8AkuW+4doFYPN+yuUrTkHIOmg6DVNRDaqGbbW1vy02DLFyp1TVGOGlLvejv0fUjSAAhRE3JPwSoXuUStZtj7i8opWknHMgvLBHNnLNp2ggcGNqdR2IX/aY8K8mXGmM7sOGnk6/VH0Go03NSzEW1ig4iq7u3FRLWQgM7T5aWB3aruhpz2ttjZrDHz6N/Pl5RY7VaWHv2d/dkH+bj7NKJcnTsgUj3ie6iFEnUsH1tBcQF5xXl4a70JOTN0HNNeLYBI2e54sN4Alz/pevsY3yB1N3jVG2phRXV+1vP+jmpYcRGsmwWrXzurrBDWva+GNYa9VX96IYWoK2wWyDnquj51d5VOezJHDbM2DDUwonMDwvy8OZSWx6JtJ8kzWSgyW6t0Xmeigny5PMiXS5pFoAH0XjKfuC6TgM5T5abAvt9g/Uy1q0GLK6H3vRCS4DCJPw07r+3+3OkpkoxJJNkLXQd0Z+j06lFHmK1mjhqP8uH2D9mSuoUIQwQT2k+gS3QXwoJi1WrWTZ+p3jZzHjQfAgOmVWzbGZ2u+oaTc1NUypT1M9XE6OZXQJ/7yvyOalzeKVj7rvO6XYvg8mkS0AlR3bx8IKqtmgfmTOM+VTptYoQ//3dFS8IDvJm34RgpxiLaNQjm7bGdWbD5GH4+1T8dxlsCOY8gAZ0nyktVm9MfWlFatvEjtYjhruUOgUuRFo7mur5L3JKxk57xLjZerqN2Zezi9l9vx2K3AHCq4BSTV0xmbKux3N/pfoKC4tROGN1uB+xqmLW2N3bOS4VF98DBP0vLNn0M/34LE5dDRAWCy+pSlF1+3kDjiYt7b2AhaoJ/BAx+Vs2XO5dfmOtN7c8jKtCH9DwTv+5IISbYl8JiK8t2neLPPanMuqUr0UEyL/ZiJWG3J0rf7xjMnWEywvLpYC7dq9VL64Wfl1/ZY09rEHCeZeRAck4hv+5I5rHv/uHtP/ZxMDWPArOlKi2/YBmFGTy/7vmSYO5sc/fMJb3w9P5/Oi+1xD2ogeod27cUFj8AfzyvtpApMtZwQw84BnNnmIxqVwpzJfbTvVB6179/wPlKZyHEhWvQDUbMUtMtzojpAON/Pn+S3IIsSP4HfpsGPz6scormnsJutXBzCxuft/uH9wM+5asu+/h1fGNaRvvzvyW7yCoortGPJOou6aHzRP/Od12350cY/JzKdwRE+EYwpuUYPttZdicEb603XaK7lPtWxzILGPvROofl8W/+vp8ZozsxpG00hmpYTVUZueZc9mXtc1n/b9q/NAk5a+VYzgl1h5x21nyV1a/BlS+rBR+V2RO3Mv79znXdnh9hyP9Kfkc1zi8cGvWBo2vK1oU0gsBKbpUmhKgYQwi0Hw2Jl6pddnTe6vt4vu0bCzLhrzdgzTulZZs/g043E93pFrTzR5b0uofzFeG+wXwycgGjf8glp6CYqMC6Nd9Z1A7pofNE5W2NovNWeedO0+v03NLmFnrF9nI4zFfny7sD30WDhjUn1/Bv2r+cyj+F/ax8dfkmCy/9sschmAOVTmnK/H9IzTVVz+epBK2TRMhajZa7Wozlp35vMcTurZJa5pxQiwHWvOMYzJ3x6+Pl7xl4oc73O6pNfmEwcmbZbXcCouCmb8vfqkcIcWF0OpVQN6Y9RLas2F7cGQcdg7kzEvuhnX9r2SkURTnELr2bxy8JQ3vW9V9cXKSHzhN1HKMm2jutG6vuAM8S5RfFy/1e5lT+KXZl7CLMN4ymIU35NelX7lpWusl9pCGSdwe+S6uwVmg1WjLzzfy6M8Xp21htdjYmZdI4vJZ6mU4L9gmma3RXNp/aXFL2Vvdp9Nz7B4alr5Qm7/SPhPE/wRbnC0IA2PNT1fMknU+H0bDuPed1HW+q2EW9OoUmqGGerCRI2wuhiWquZXAdTkEjxMXIZlULus6l0ahefVd7S2ccpGuEFR//urOATdQu6aHzRCGN1Y4HZcobqU3rNTrIOQ7p+yD7GFiLCfMNo3V4a65rcR2XNryU3w7/xjvbHO8A0wrTmPDbBFLyVRBntdmx2pzsMHFaTlHtz6ML9gnmyV5PEuSthkp7RHejS+oBDNvmOu6GkZ8GafuguMDFmYCCjJpraEgj6HGX8/K+D7onfUlgDDTqDV3HQ5PLJJgToi6yWdVCpnNpdGApf1Qk3KAhzF8WRVyspIfOE/mFwYD/QPvrYf0HKlFsu+ug6QC1z+qat+Hvt9RFwScQet4DPSaonQGA9MJ0Zu+c7fTUucW57EzfSVxAHAE+XjSPCmB/ap7TY3smumdLrCbBTZh3zTyWHllKT794ghZMcn5g8jZofAkc+ct5fcuraqyN+IWpfWPbjiz9HbUdBc0uP/9+hkKIi5eXt7qe7/3FsdxmUav1tV7q/8/lHYA+sJZ7/kWdIgGdJ7EWq8myWp0asvMNhYgWag9S/0iVLHb5i7D2rJ43Uy6sekVlLb/yBfAJxGw1YzS7XuWZZEwCICLQh+eGt+Wmj9eX2Qp2QMtI4oINNfEpz0uj0dAwsCHj246HrCOQn+78wC1z1IbQX45UP7uzNehW86k6/MPBvw806KouwLW1CEIIUfssJrX1oNZLffcvRKM+aluwzEOO5Xt+hr4POyYJP2PQM2hkPuxFTYZcPUXWEfjzf/DZlbDgDkj5F1a/Cp8Ogc+vUfsFGk/AhlnOX7/tC5UbDfDR+RBpiHT5Vm3C2pT8f8f4EL6/pw/dEkLRaiAywIepQ1vx8nUdCAuo5cn959BqtGj1BjWM6Ux+GqCBiX9Ck8tVIGwIVTnqxnxZe1teeflIMCdEfWWzqcBr6TR1Pf5yJGz/tuR6WyXBDeC2H6HXPWprQq0XtL4Wet8PvSbBqI9UwKfRQGQruHGuGrGpQwngRe3T2O3n9r0Io9FIcHAwOTk5BAXVUFqLysg8DB9fruZ8aTQwdh4seUTtOXq2G+fCN2Ndn+eOpdCoJ3a7ne/3f88za58pc0i0XzRfXvUlMf6OwU52gZlCsxWNVkNUgA9abR1aSbX9W/h+YtnygCiVxDe4IRTmgDkXNFrwj1J56oQQ4kKl7VPXZ1OuY3mrYTDsTTV6UlUWk7ru2+3ge06C9NxTqudf5622aBT1RlVjEPmrVtcVF6k5cWcm8CdeBof/KhvMAZwvxjrdS6TRaLi80eVkm7L5YPsHFFpUWpJ2Ee14qe8LxOSkwOq31V1h+1EQ3IgQvzBC7Gmqp3DtQhVYth2p7h73LYNG3VXC4xNbILotNB2oAqnaCJyaDYIrpp9O2Ht6vl9sJ7juo9L5aoZg9RBCiOpiyoU/nikbzIHKN3nJwxcW0Hn5qATpzrgjf2RBplpwt/N7KDZB2+GqpzDgvBtIejyjyUhKfgq/Hv6V/OJ8BjUeRGJQIhF+dWfeovTQOVGneuiMJ2FmH5WUEmDgU/DPXBU8nWvwcyqh7bkb04P60t3+q8NFoNhaTFphGjmmHHx0PoTqfAld9hxsn+v42m53wiVTYNmT6ot8tnbXQ9+HYM61pW0E0Bvg1sVqrlpt7FtqLYbcZNUGL9+KJe8UQogLkXMcZrRX85id6fMgDHm+dttUUwoyYNVrsO59x/JmQ2D4O7U3hcUNckw5fLnrS2Ztd5zS1C26G6/0e4VIv+rtIa1qDCJz6DyB9qxeLpvV8fnZ1r4LQ18qu6VMQDTc8Ln6QuYmlxTrdXriAuJoHd6aJiFNCE36q2wwB3BoORxbVzaYA9jxHaTuLptIt7hQDf+e9X41SqdXc+liO1Y8eWc9l1tUzOH0fNYdzGDHiRxO5ZSzn6sQomq0Otd1Gq2aS2c11157akr6vrLBHMCBpbD/99pvTzXLzDex71Quaw+ms+9ULpl5pb+z47nHywRzAJtObeKXpF+wuQroa5kMudZ1/pHQ6Wb4e4Z6vn8ptBmugqhz5aWqORd3LlV7iZ7apYI5uxW+vVUllQ1ppObgRbdxfG1+Bqx1kQi39TDY8KHrNm7/BlpdDRs/Puec6ZCbIvnO3CAt18Qrv+7huy3HS1YoNww18PFt3WgZHYhGsskLceH8wtQoxT9OboQB4nvA+73h6teh+SA1RcUTWcwq/ZIr696Dlld67I30iaxCHvxmC5uPZJeUdW4UwrtjOxMXYuC7fa63cvxq91cMTRxa7b10VSE9dHWFuQCyjqotX3JPlZbr9NBjohoyBTi+EaLaqm1kztVkgKoLilMJZDVa+PkRWHCnCuYAso/CnGFqqOBsNovaON4ZvUHlUXOlKMf1BvDlJfY9j1RjEUnp+RzPLKCwuPaTGHuqYquNL9cdYf7m4w7pZo5nFXLTR+s5KT11QlQPvR/0f8L5cGPncXBiMxSkw3fj1eK2qjLlqvnLGQdd7xQBpBakciTnCCfzTmJyloS4uFD9Dcg4oG62K8pWrFKyuGyfUY0eeaCsfDOPzN/mEMwBbD2azeR52zAWmck0Zbp8fV5xnvTQibPkHIM//gc7F6i5YGFN4MqXVC4i30A1sf+2n+Dgn7B9HuxcCCM/hFM7YesXagi2x10Q17l0jlxuCvz5nPPJuvnpqvfu7AS3hhBoPgTWO0l7cnIrNB8MaXuctz/xMji+oWy5VlelJLq5RcWsT8rkuR93cTSzAL1Ow/BODZgyuAVxIe7JfedJ0nJNfPpXktO6zHwze1OMNJCfoxDVIzQB7vwd9v4Mu35Q19K2IyHrsEo1BWqV6rqZcM0bld8lJjNJpUTZ+7OaqxfVRvX4xXUquZHOMeWw9uRaXt/8Oin5KfjofBjRbAQT208k2v/03wTjCVjxsupNtJrVjkND/qeu3+dbMObtD21HqOk3zjQf4rGLzjLyzaw75Dxg23A4i+yCYoYmDOXPo386PaZvXF8CvQNrsokVJgGdu+Umw8rXIKadGrYsSIeMQ3DkbzVcGtECvP3UsGWXcepCodWpXrPoNtDqKkCjjjmbxeQ8mDsj4wAwpPS5lw/0nKS+7Of2xqXsgCEvwtYvHRc+gBoSbnOtCjT7PKDyvKXtURe27ndVaYXXpsNZTPh8U8nzYqud7zYfZ8eJHD6/owfRQb7qAnlm5a9fuFp1KwAwWazkmlz3aB5Ky+fyGtrCts4y5aneYm9/yQkoqs5mg8LTf/zPvu6ExEO7G06vAj0GvzxedmvB9L2qh6y8gM5arK6xOr26luYch9lXqcVxZ6TugtlXq/yacZ2xWm2sOraa//w9teQQk9XEvL3z2J+1nzf7v0mYtRi+uVndnJ+RfQS+HQejv1DX8PNpdjpzwbmjO94BKj/eufOoPUSeqbjc+sz8YjpFdaJRYCOO5h51qPPV+TKp4yT8XI1Q1TIZcnW3whxo3Fv1ym2do3rPGvdWiYMX3AE/3Kf+v1ilFsEnQAVzZ3j7lw3mAPS+an6HK9Fty5aFNIYJf0CbESpo9PJRwwa3/wzhTWHC72pLGq2Xyn3UdhSM/QZ8gmDoKyplybavwA6M/wV63euYN6kC0nJNPP/TLqd1e1JyOZZZADkn1OTcz4epx7r3VZkAwNdLR5i/66TPrWLqxt1krSgyqmkKC+5USbkX3g0nt6kAT4jKyDmu5oqdue6sn+V43dH7QNpedQ10tk90bGfXNxN2u+qJ++NZ+GwofDkK9i9TKarODuZKjrfB329zMjOPLSePMGPrm05PuyV1Cydzj2FP3e0YzJ1t6TQwVmDxWnA8jP8ZuoxXwZtWB62uUYFlaML5X19HBfmWn4w52KAnxj+Gj4d8zNhWYzF4GdBqtPRr2I+vr/6aRkEuEtu7gaQtcaLW0pZkHVFf4Ibd4NeparFDTPvSbvozNFq4+TtoennFe6JsVnXB+e0/ZeuC49XCCVf5jUx5pb10fmGlAWTuKdj2NYQ2Vs8P/K6CObsNNpwzYVbnDXf8qra9qoQjGflc9uoKl/Xr72tF9A83qhVXZ4toAeMWyQIMwGqz8/mawzznJDCOC/Zlwb19iHXTtm21ymJWK7MX3u1YrtHADXPUXr6SYFpURM4JlZop44BjeWQruOX70utO8nb4sB9l9krUesE9ayGyhfPzZxyAjwaq/bfPaDNC/VvNPASGMMjY79A7dvKmP7lxkZH/DA/n/9bd7LLpT3V+mBvyzfDbE64/3wNb1E17RRQXnQ5Y7eAbUumb9rrGWFjM/323nd92lp1TOLB1FG+M7kiwQd0gm61msoqysGMnQB9AQA0tcpHEwp7GYlYBV5sRsOj05vIdx6rVqOey22Dx/ar3zFUQdi6tDjqMVhNZ17ylhmAB4rrAVa/CzkXQdAAExpWd++AT4PxLmrJdJdE8Q6OFm+bBVzeUPdZqhh8fUkFWJVY+eek0GPQ6CovLTrDtFB9MyLE/ygZzoMr2/wbd7qjwe9VXOq2G4Z3iyCksZtbKg5gsasJu+wbBvDO288URzAHkpcCSKWXL7Xb48UFo0KVKczzFRcZuV0mCzw3mQE0vOfAHdD193Q5vBjd+o67XZxYvBMXByA8oCmxESno+f+w5xdGMQro0DqFZVADx/jaC/njeMZgDCE2EVkPV3OncU+qG3zcIfvsP1vCW/HBIy9HMAiIDGuKl8cJidz7NIlIfBN7lLE7z8qnclmF633p14xxk0PPstW3R6zT8/G8yNruKo69sG8PTw9qUBHMA3jrv0jmJdZAEdO5SkAE7FkKjXmDOV13xhVmu8xUZT6r5GRUN6EDNX7v0Eeh8i5qbV2RUq67mjind0H7ANLWK1hBS/rmsFrXZ/dlCE5ynTzkj5V/1mSoR0EUG+HBj93g+W3O4TN3VzXzx2eEiPQCoBSJtRoJfaIXfr74KD/Dh3gFNub5rQ7ILi/HVawn38yYsoJITsj1ZXqqaN6fRlO0xKcxS3wEJ6MT5FGaqkQlXts5Rc9AMIWr6S/MhcNfK01s1asEvDLMhmr8PpHPXF5ux2tS/xc/XQuMwPz65tRNB5y42SLhU5dP87CqVgeCMkEYw/H2yUo6wYIORBwbFcbxgP5c3upylR5aWaZrBy0ALrwAI8FfDpBYnK9w73Hhhu1nUAzHBvkwf1Z5HhrQkz1RMgI+eiABvAs8zHFvXSEBX2yzFkH9KzVm48Su1HBxUL1x5CSpBBXvHN6nFEoGxFRsu0vuqi8DeX+DXx8vWL/+fWsFq6AS5qZCfqvY89Y8Ev8jS3jsNZdtnt6kLVnnOV38Omx2u6RjLtmPZbD2WXVLurdPSr0UUHC1nyFmjk8URZ/Hx0hEf5ke8qwOsFtWLlZeq/mgERKuH3jMnN5/NbLGS6p1A6qi/0GggiiyiNr6K/sjK0oPk34rbpOeZyMgzYSyyEO7vTXiAt0NPSN2iUdcWV7Sl1x2L1capXBNpuf7Y7H5E+HujtWgoyCjgni+3lARzvRODeaxPMNHabHxzdmEdOx/d6pdVbx9Ar3vguzscgzlQKUfWvY+9z1ME+ubSprGJp9Y/zRv93+Cw8TD7skpHLwxeBmZe8jJRy15QU2CGv6fmZJ8d1MV1hssed5yXfZEK9NV7XAB3LgnoapM5Hw4uhyWPwLVvQfZxNWfON1jNWfP2V1+sMwsgzhaaqCa1Lpmijh8xE5r0r9iKvbxU5xm+z9i5SK1UmndzaWoSjQbaXgdXvKByLGm9oOvtKmXKGVmH1V2ksx4QUHMDK7nyKSPPxJ2zN/Hw4BZMuLQJu1OMhPrpaRzuz+ytp3i60+34ntjs/MXdJ5y/p1EoxUVwdC18d3vpymUvXxj8vBqq9+CfY15RMb/vTuW/C/8l36yG7gN9vHjlqhe5LHAmfju+VHtPXuS9Eu5yJCOfSV9uZndy6Sr8IW2jee7adsQE18GbCb8wde07ucV5ffcJ4BtMYbGVNQfSmfztNoyFKhAz6HVMu7o1Oq0Gs1VNfbi+fRhTWyYTvuSm0rnK3v4w4L9qfvO+X1XaKWe9aQAH/8Bn4KtMuDSMP0++S5G1iCdWP8HDXR7G39ufA1kHiDBE0CioEQ20gXgd31j62hs+U3O389Mhoa9aHBdQd4cQReVIQFebsg7Dt7eoYU5TnlowoAFu/0WtcCougqvfLJ1Td0ZQAxj1ker6H/2Fyvn291tqIYBWB1q9+uN0ds9K3ikVQGq9VH1xkRpe6nkvNLlMXUCsZrBZKNb5YdR5k3fTXKw2E/rCHEJ3/UhA1lE1N82Up4YSIltDy2tg70+l77NjAfR7DFa+7Nhm7wBVfmgFdLqpwr0hVrud7MJinlm8kwAfLxqF+ZFnsnA0U80Bub9bXxo06KqGjs/WoKvKpyQqJucYfHW9Yw+ApQh++T/176ppf7c17Qybzc6p3CJMxTa8vbREBfrgpTt/j++h9HwenrfNoSzXZOHeRUf4+bb7aL3/B5XHMaD+7j1ZV6Uai7hj9iYOpjmuMl668xRBvnqeu7Ytfj518M9S80GqN+uslaL2Bl1Iu3QKRdFt0OclU2z25+4vNmE5K8dsYbGV2WsOM7aHWgnp46Vlcjdvwr+5w/Em2JyvFrDdskBdc8tL5G63k5yRRVxIPLkp6jij2chz654jUB9Ig8AGGE1Gim3FfD34EzJvXkqu2Y4WG6EHfyHg8O/qWt59QqWDObvdzqlcE0XFVrx1WiIDvdFjUwGotVj9DQqMld5vN6mD35x6ymKCte9Dwx4q8Fj1MvS4W83N2POj+jJEtYaBT8PE5WqblaxD0GIoJPZTS8uPrlVflEHPqZxvX49WK6C8fNX2YJc+onrvjm2AXx+D9P2qq73DGLV4wZynArmTW9UE3LXvQW4yep9AQnpMJKVpP25ZNQUbNvo16Mej/R+l8cL71WKIgCh1Bzn0JTUBeP0s1ZMY30vd6cW0h+3fqiG8uC5qHskfz6k8e00vh6DYCv2Y/L29aB0byO7kXPJMFnYlO+5ekUooDcZ8pfL0bf4M0EC329XOGBV8j4uezaZyCp47nHPGihchrqPKg+UmmXlmftmZzIxl+0nLMxHk68WES5swtkc8kYGue3EKTBbeX+Fk8jrq7+dH2wqYfvd6fALDQStZm2pbirGoTDB3xqKtJ3jw8mY0qosBXVAc3Pj16evObLI7jmGVnx9vb3+LU+tP4eflx/XNb+Stm6/i4a8PUmwtDdaOZhbQNFKNpFzVJpyIHZ86H9EAdd0f+pqa8+xKcDwnCr344O8DjLh0IH+f/LukKrc4lz2ZapRlZMJQgvcvIz3yMq6bd5TMfDODWl3Df0bcT0IgpUnoKyi7wMzyvWm88useknOKCDF4sfj2FjTcNwfthg/V35egOLj8KWhxRflps0SNkCtabSkuVAFa/yfg82ug/Q3w6xMqrYL19Dy61N1qQ/v8NLVY4oY5kHCJynl0dK06JrKV+qLMu0UFc6B6VjZ9Ar88poK5L0eqYA5UL9zWL2DxAyoR5uo3VcbwpdNUsAVgykW3+g2arfuYh9rchs1uY8XxFdy24iFODn5KHZOXqlat/vstJPaHMV+qILHb7bBtrpqb4RMADbur5fVfXQ/J21RPYSU2pg4P8OGZYW2d3uB1axxKw1CDCtzaX69y4I2dq3LjVWaxyMXOaoZTO1zXZx5yPuxfS8wWK3M3HuG/C3eQlqdWZxuLLLyxbB+v/rYPY6HrRKCFxVYOpua7rN+fVkShb2S9mCfoiVLK2XbOYrOXDJHXSUFx0P4GrGO/4TeDN/9d9yynCtQ2jQWWAubs/pSfT77HvQMdr0Umi40jmQVc2jyCxGAtPll7y547NJHcSx4ms/lALNmH1IKzllc5bYbtiulszPBmfVIWEV7tifEv29Ns8DJwR8I1GJY+SfyPN/LesFhsdli6O50bPvuXE5bK5aK0Wm38/G8yk+dtI/n07/DBvpHErPoP2r/eUMEcqMV7iyZh37EArHX4d1lPSUBXW/R+ajXRtq9VQGYxO18Gb7fDypfUXAqTUa0sPXs/1G53wOrXnb9Ho16w1EneOVBB0PZvoN1I1TPnhM+enxgY1h7t6YUMGUUZrDIeVOkdzlj1mlrU4e2vegMBYjupIYJtX6tzH/hDLZgANczrVbnJzu0bBjP/7t50aKjOH+jjxb39m/LuTV0ce2d8AtVDVI6XT/n5ASNbut6btxak5pp498+DTuvmbz5GRr7rGwQ/H125iZPbxgXh510He4AuEuVtOeet0+JfF3vnzpFanMfbW99xWrfq5HI6J+jQaR3vSFftS+PBy5sTHx1OYUS70gqtjoxr3uDPwY9zX3ESdyb/xrs5uzhuLcQ+7G24/MnSnvKoNjBuEdoml3FH3yY8cWVL3vgllae6vsuwJtei1+rRoKFfXB++vuQVGi59Wt3sZx4iofiAuhlGJW9ftb+cHkAnTuWaeOW30kBUp9UwqCF4H/jZ6fGa5S+Qm7mfnPKGjkW1q/vfnvrCy1sNC65+Tc1fOHuiKqgvbVQbFbyd3ArBcbBvKRiPQ5MBKv+QzgfCmpb2zJ0rpJHrNCLR7VQ+owZd1XvF91QT37VeqqeuKAf8IgnU6ukT24d1yeuw2C2szPiHkdHt8bFZVfCUtkelTwk5Kzt2gy6q968gA0KbQIvBKv/dzu9hwH/UnIpK8PP2oltCGLNv70Gh2YJWqyEiwAd9BeZPiQrQaNQw/N8zSvMTnm3ANLcuisguKHaahxDU/c7J7EISI5wvBjLovbinfzN++je5zKiWTqvhjksS8faSf0fuEhXkS9u4IHaedJxK0TDUwB19E4kKrKsrXUvlFudiNBud1hm8DNi0eVzftQHfbzlRMvR6Q7d4Xlu6ly6NQrii5yTY/gXYLGQNnMarxn/558heYgNiKbYV88meL5l/aDFfXfUVCX0nQ+ebAa1aMOerksxG+sLEfk25oVtDrHboEnY/D0R0B62OgKMbCPxmvJomk3ApZCURcuxPmkeN43hWIX7eWkzFViwWG14V/C4Yi4rJLijGoNfRrkEQQb56fLLP6ZA4s8AvfR/kpZKefZA/k//m5jY34+uh24J5GrcHdO+//z6vvvoqycnJtG3blhkzZnDppZe6PH7lypVMmTKFnTt3EhcXx2OPPcakSY6LCBYsWMCTTz7JwYMHadq0KS+88AIjR46s6Y9yfoZQ8ItQd01n8l95B8CQ51WwdGyD+kIMmAZ6f2gxRO3x6hMM2FSgpzeoHhZnf4itxapn5ewePVDZvJsOgLxTJEe1IGPMJ9h03tiBA9kHaBrSFK1GS545jw0pG+gY2ZFxbcax8vhKGvrHkhLahr9TWpBqzqZ37wk08QvGYX1gSDzc/hsnbQUk20ysOvEX3rpGDLzsYaJ9wqjqTKwwf28oZwsrpwqz1QTd/b+p4d4mA9Qk/zO7W5jyVAC77zcVgDY5vZAi6wgkXqoSLTsZjjuZXciOEznsOmnkxtbeRJiOoDm0gmJDFAWN+5Orj8DL159Uo4k/96Ti7+PFoNbRBBm8yMgrYumuZAqKLQxoGUHjcD9sVj3/HM/h3+PZNI/xp3mMjvTi/cQFxLIncy+NDJ04mGJj/6l8WsX50aFhCHuMa9iftZ/LGg4gRJfAhsPZHEjNpV0Df9o3COFIwTb2Ze3j0phrSM7Usi4pg/hQAz2bhPBP1kpiDQkE6xrzx540YgN1jLp5Ed6LJpZmn/cNxjT4JXIDEll/cAntI9uTa85lb8ZBEgO68M8REyk5Zvo0jaBFTCDossnOh/2nCvjnaD5NIgK4ppkvgaZT2Pf+jE2jxdp8KPsKA/hpv4keCWE0izZgIY0Yix2vE1sh5V+sMR3QNegCFjM+ASH46MvPvh7oW/5lKyHCj49u7cZj320n83RvXmSAD6/d0JFGYdXf83jKWMShtDz+2p9OVJAvl7WIJDrIB4P0BJYRGejDB+O68si3/7A+KZP4MANTh7amwGzhQGoeS7an0CMxjNhg3wotgHEHvZOBLS+NF/e2f5x4Q0c277UTH6Th+0k9WXMom5YxBmKDDQxoGUmK0cQmYyQt79pO9KKxpMV343JzP9oE+HDwlJlLYvQ07mDl/Z0vMuufD5jU9glOZnuxal86Qb56ejWx4uutI8qgJaL4JOH7foaiPGg3Cv8fJ0NBJpb4nhy//iM25R7mcOEpOgbdTIuQFvgut/Px2FY0ighm1b5U3vhtB/1aRBETpCfano73waVoC9KxNhtMhj6Or/7Np1G4H10TQtBrtDw6pCXNogLYeDgTP28dweFqDl5Rs6tI6f44q49bOZlnp097PS20J2kY2oLbfCPQrnwVq96PUy1vIcmoYfWBDEL89AxuGU50/j7MFisnvBP5fX8O3l46BrWJJibYQLCh9lKI2O12TmYXsvVYNjtO5NAmLpgujUJoEGJA40ELPNy69de8efMYN24c77//Pn379uWDDz7g448/ZteuXTRqVHZ/tKSkJNq1a8fEiRO5++67+fvvv7n33nuZO3cu1113HQBr167l0ksv5fnnn2fkyJEsXLiQp556ir/++ouePXtWqF01tvVXcRHs/lHlj/MLhy9GqFWrq15zXBIf0RyGvQ1H16ktvKJawfd3qUCtw2iVE+kfJwl2245Sq5bWzywt03nDmC9g69ccuvz/2JV7hKTsJGIDYvlw+4c81espcsw5/HToJ/468ZfD6Z7u9TR+egNT//oPNnvp0q0WIS14b9B7DnM3juceZ/r66aw6scrhHBPaTWBc23GE+dbCBNnCHNj3Cyy6p3TIF9TS/Bu/Vj/zHQvhxwccX9egK1wyWeV9GvOVCvLO2kD7UFoeYz5YR3ahmR/GJdJ6+QQ0Z89B02gxDf+Ij08159XlpVvz3HNZU+zYmbWytEc1LtiX10d35L6vt5YEG6CGlT+5vQOf7nuO0YmTeejLJHJNpYsWQv30zLg5gbmHZjCi4cM8/PVBiopLP2NUoA8zbm6MXWNl6rzkklXBAHqdhm8ndePrDUeZv/FUSfnAVlG8emUU+VmnsFstpNsDeXOdkZ0pBXw1oRtLk+ewM20PQ6Ie5In5SVhspZeK9nFBvD6mPXd+voVjmWq+3XvD47n86NsYds93+PHmdb6LRYFjmbY0mb7NIpg91Bf9F8McV/IZQim86Qe0uxeT3+0+bv96F/8cLztcExPky6L7+p43vYXVZueUsYjMfDMajbo5iA70Raut3ovzyexC7vx8o0MKDq0G3hnbhctbR2HQnye35EUqK99MTqHqib310w2k5ZbeoPp56/hqQk86Ngyp9t/XhcrNOoz55Gb+c/wX1qSsLyl/usdr/LwhiD93Zzoc//Kodhh8NEyet6MkBx1Ai6gAvhjfkeP5BUycvbPMteDtWxLx0pt47acch++BRgP/uao1BaZixsacJOq7EaqiyQBo2B3r/qVsHzSVu9Y+SZG1dL5itF80swbMYfM+I0/8eNCh97pzfDAzL9cS8+3VJddNS1wPdvR9m5FfHsLHS8uvD17C9F/38tvO0uvHgpsa0W73G6xu8gh3Lzzq8PmaRvrz+fXxNPyyL1iKSLnhRx5YYWfj0dLvCcD/hrXAYoNnljju/nN3vyZMuqwpoZW9oa+iPclGxny4jpyz5ucGGbz4ZmJv2sTV4PafLlQ1BnHrLdAbb7zBnXfeyYQJE2jdujUzZswgPj6emTNnOj1+1qxZNGrUiBkzZtC6dWsmTJjAHXfcwWuvvVZyzIwZMxg8eDBTp06lVatWTJ06lYEDBzJjxoxa+lTlyD0JPn6Qugc2fKQWFhxaUTa/Ud+HVK66kEYQlqAWNJzpddu5CNqOgJgOjq/R6dVK1z4PQIPupeVthsPORWQ26sF7O2eTXphOx6iOvLDuBW5ufTMLDyzkVP6pMsEcQLR/dJlgDmBf9j4+2v4RptO9hIXFhaw8trJMMAfw8Y6POZJzpHI/p6rKSykbzAGc2gmr31D7MZ4bzIFKgXLkbxXIzbtZ9fCdlplv4qFvtpGWZ+LaduEk7v7AMZgDsNvw+WEiQxNKv06BPl60axDsEMwBTLi0CU/+4HgBB5VW46G5u7in3X/573fHHII5gKyCYp7/IZl72vyHJ+YfdgjmQM0723FUw2crjA7BHEConzcHU00OwRzAle1iGPrpfi79PI1+X2Yx6qujrD6YTWa+mYe+2U6wV0NubH4P//nusEMwB9CjSTgvLtlXEswlhPvRXbe3TDAHELD1QwaGZxDu781/Lg1BP39c2bQMhVkYFo7H0m40YX//jxljOhJ7TtAWZPDik/HdiA46/24XOq2GuBAD7RoE0zYumNhgQ7UHB0XFVt5ffsAhmAOVHPuBuVtINbpeAHCxC/X3JsjgxeMLtjsEcwAFZisTPt9ESh37+WUXZWNO3kr4j5OZ1uEeGgaqUZbmIc3JzootE8wBRAUZmHJOMAewLzWP7SlFPD5/v9Nrwc/bClm5U1PmpsZuhxd/3k37hqH8cCIIW6NLVEXSCohpR+qQZ7h/w/MOwRxAemE6aXlFPL74YJmpCFuP5fDFfm+Km11RUuZ1cgNNj37LgOZhNAjxY9X+DIdgDuDJ5Zmc6Pcq9yw6WubzHUzL5/W/0ihodxPWJoP4JsmvTDAHMO3HfTSKDMbrnO/mB6sOcSDV+Wro6paaW8SkLzc7BHMAxkILd3+5yaO+x24L6MxmM5s3b2bIkCEO5UOGDGHNmjVOX7N27doyx19xxRVs2rSJ4uLico9xdU4Ak8mE0Wh0eNSIQ6sAHWz5HHYvVvnh/vnG8RiNRg3NNuii0plotKWJX0GtUFwwUa0uve4TGPgUjPwA7t+khgyDG8DYr+GO3+DSR1XG8Z0LyYpqQcuwlmw5tYUD2Qew2C00CmxE6/DWLD60uExTW4S2YHfm7jLB3Bk/HPyBzCJ1AUsvTGfB/gUuP/Y3e7/B4ipFRnU6ezHGubKPwK6FzutArdRtO1L9fM8KsDPzzfx7Ql1Ub2prwLDTxdZjdhvByX/ROlZNyB/QKsrpZs/xYQaXF6rknCKKi31LVpGd63hWAcYCPdkFzld5Ng4P4M89aWXKr2gbw+JtJx3KNBq1h+Epo5Ohe2DfqTyaB7bnSColCVHP1iMxjJX7S9/rxvZBRG3/wOm5AKJ2fMywNqEkGgrU78KZzEPYi/PhyF8k6nP4/p4+fH5Hdx67oiUfjOvKLw/2o01sUJ0ZAsnINzN/83GndTY7/H2gchPPLzaZ+Wa2O+mFBfWzLW9FrDtYTbmEbP0KinLwyjZxd/PXeb7nOzzQfhoLNmaXOb5pZAB7U3LL3AydzdW1oE+zCL7ZcMJpnd0OG5MyWZ9iI63t+NLCHx/muE7rdH5fh8gOrNzjeoHCF1syyDhzrtMCt3/G7R39ubpDjNN/5/lmG6sO5TqkaDnbjzszyWh6HWltxvP55gyX7/33gXS6JZSdmPPp30mYXMylrU4ZeWYOZzjf6/ZYZiHp5SzCqmvcNskjPT0dq9VKdLRjLpzo6GhSUsr+IQRISUlxerzFYiE9PZ3Y2FiXx7g6J8D06dN59tlnq/hJKiE/FcISSzdhNuerlaxn0+jU/Dhvf5UqxOTkC28ywk+T1dy4iX9CeFPH+oCo05nwo1Q+I0sRJlsxfl5+WGwWjKffs9hWjL/enxxT2S+6wcvgtLykCVZTyWbQVrvV5SRhgCxTFhabBS9tDf9zyy8bzJTQ6dXP0xVTTunKzoLSi4/5rCyh3lq76+ztgL4ovWQFpZ+3zmlg5uriB2qortDsIiAFfPU6jEWuA2OL1Y6zvx0BPl5kn3P36aXVUHSei6UdDTkFzo+xWO0Od/rBPjjeeJxDV5RJcDBozpPCxl5sUnMYLUXERhiIDTFwWYuocl/jLlarHZPF9e/r3J4n4ai8nx1Qppfa3ew2M7rT/8aLrfDwV0mq1/mqSHIKyv7b9/fRkV3o+t97edcCHy8teeV8/pzCYmx2Ozbvs1Z0a7Xk5Z10eryflx9Zua5/3sYiC1avc1aHF2Xj763Fz9vL6ecI8PEqN9ix2OxY0OHlHUBOoetUQtkFZqcrz7MKzBTbbPhQs9MWzOf5d1gbQWV1cfus03Pvtu12e7l34M6OP7e8suecOnUqOTk5JY9jx45VuP2VkthPJeltfLqbPHUnxPdwPMZmUQslkv+F2A7nT5arK2eOQWiC2kEiqg0hdrUAIsIQQevw1gBoNVr2Z+6na3TZFBZJOUm0O3t5/TlahLbA30utNPTX+zs9xxkD4gfUziqnJv1d11kt0PwK1/WNekPK6aHUht1KioMNegJOp1LYk2FTq4VdyIvrW3LHveNkDt0Tys4b1Gk1+LhYWabRaIgI9CqT8uAMk8VK43DXP8fCYkuZYUqAf0/k0CPRsS3FVjuBvnpcjUIa9DpMtjxaN3D+fvlmi8PQ55oTFgoaD3DZtpzGQ1h/0kyRd6haWe2Mlw9e/mGql9UD0tGcL0VK32YRtdgazxNi0BPoIk2JRkONLGC5IN6B5CaqBXv+2XtoHRtIRr6Zvw5k0D2x7Hc9KS2fdg2CXZ7O4K1zeS3YdyqXLo1CXL62S+MQQny0BJw1j4+CTBKCE50evz97Pz2auk4Z071xCP6nHKf+WOP7svGkiZ0ncuiZGF7mNUnp+bSJdT2/KzHCH/+8w/ilbKBnouulcd0SwtiTXLZDYHCbGPxrYWFRmL833i4W4Oh1GsIDzj/Fo65wW0AXERGBTqcr03OWmppapoftjJiYGKfHe3l5ER4eXu4xrs4J4OPjQ1BQkMOjRoQlwoE/VSoPnV7lmOv7UNkN7PcsUQmEG/aAYxtV4lxnLn+y/JQgWq16z6EvE7nlS5r5RnFl4pVkFWXRMbIjPx76kQhDBCObjcRH5/iP1mg2YraaaR/evsxpNWh4vMfjhBnURSzSL5Lb292Or67sH/8ovyguibuk/J9LdQlNVLtUnEujgb4PQmxH9XM9l1an5h5unaOCwqCGJVVRQb48ekULAN5Zn03qJc853dbGHteFnUURJfMwdpww0jImoMx8r0VbT3BHX+cX3bE9Y9iZtZ4bezr/tzr+klj25mxkWCfngYKNIiYPKbuY6O+D6QxpE02In+Oqsd93nWJMt3in53pgYBP+OLGIZNMueiaW/aP09fqjPH5ly5Lnv+zKIK3NeOeBmF84qY2uZt2hLD7fXkBxr/udvmdBjwexGJNP/7uu+/tLRgT48My1zpNgd4oPoXF4BfZZvohFBfnyyOnv1rlu7B5PREDdSmES4huGrd114BdG+Oa3eWZABBoN/PxvMtd1aVhmAUyuyUJekYVujUOcni/cy8SDlzi/fpuKrTw0sLnTG66W0YFogIld/An859PSCq2OcK0v1yRcXeY1qQWpNI/yp0VU2X+TWg1MuyyMkK1n7fet1ZHWexofbczkt52nGNsjHj9vx89XYLaSlW+mp5NgFuCZy6OI2vwmwds+4D+Xhjm9UW0a6Y+/t46T54xmRAb4cEXb6FqZXhER4M2ky5o6rburXxMi69i/w/K4LaDz9vama9euLFu2zKF82bJl9OnTx+lrevfuXeb4pUuX0q1bN/R6fbnHuDpnrQqIhhHvQdpetX9rSAJs/QpGzylN3qs3qPkQfR9U6TUa91UJifs9qlZpgup5u2E2tBulVsyeT4Mu6HvdxzV2XyyFmSQEJfBA5weIMkTh6+VLdlE2MwbMoEeM6i300nhxTcJQunmHM6PrI9zWehwGL3V31zK0JZ9c8Qntwh17qhr4N+CzKz+jZ0zPknNcmXAlnwz5hPgg50FDtQttpH4uPe5SQ9agFo/cslAFc0Gxaq/EbhPUdmmgVrje8Dn8Mw8636rmI/qXBkx6nZbhHRvw9o2dsdntvPavH5nXLyxdlOLtT37XSSRf+TExcY1KLm56nYYNSZl8PbEXwzrGlEz6zS40MaprDK9e3564071pkYE+PDa0Mbf0iebfrHV0aJbCo1fGExmogsG4YF+eH9GcmJgDPLfxca7pZuX/rmym0rqg5uW9PqY12dr17ClaxJtjm9E0UqX+CPL1YkK/hhRqjvDerQkMahOJVqMu4snGfO66LJH/Xt2CyIDS95p+XSv6tNRye/tb2Jm5jgmDvLn9kpiSnsoW0QFMGdyc9vF63hzbnKaR/lhsdh77PQfjLb9ibz5EBb1aHdZW13Js1GLuWpxKYoQ/reIjyeh4E+YrX4PA06ukg+IouPJNNB1GE6jXQOM68F2toA4NgvlmYi/anl4J5+etY+Klicy6pWvJ7084d+a79c7YziVJb8P9vZl2dWseGdKSQN/aS1tREV46LzQhjSm4bTHF0W1ov+8dvhmbSLOoAN5cto9Zt3ThkmbqGu2l1TC8QzQd47156KpAbu/bAP/TAVHr2EDmjmtF022vclPobl4b2crhWvDokBbEhhhYvjeNryb0oOPpBOu+ei2ju8Xz7PC2tIr2p2nqHyWL5eyN+sCNXxO07GkeievPQ50fIsQnBID4wHie7fkKgT7efDKuHeO6x5b0DHZqGMx3d/egSc7akoVK9gbdSBv9I8+ss2Gzw5RBiTTyt7Do1ib0bx6KRqNGGq5uH03beB0zrmvJ3f0SSq4PLaMDmXVLFzo2DMIeHA8FGTTf8jwLxrcu6XX08dJyU/cGzLkuljYBefRvHlZy3ms6xDJ/Um8ahtZOD63B24vxfRvz0qj2xASp30N0kA8vjmzHHX0TPSr9UJ1IWzJr1ix69+7Nhx9+yEcffcTOnTtp3LgxU6dO5cSJE8yZMwcoTVty9913M3HiRNauXcukSZMc0pasWbOGfv368cILLzB8+HB++OEHpk2bVjfSlpxhMat5Wnab+kJqvdTDUqT+EPoEquDPYgLj6e25tFo1bKhBzfU688ewMvLTwVpMOlbMGg0atBTbi/HWemPHjt1up9hWjF6rIxQtBqsN/EIp1nmTUZSB1WbFoDeUm4IkNT+VAkuBGj70icDfxw29FOYCteLVZlUBcnBDx3pLkfpZ2Kyqd86O+rkHRKmeUxdSjUWYLDZ8vbREaPOwm/MotmvJ8wrFy9uHYIM32QVm8opUMuRQfz0GvRcFJgtpeQVY7XYM3naiA4PQarScMhZhttjw0oFeX4DJasLgZcBkM6FDh8lswGK1o9XaCPXTUmAtwGqz4uvlS4hPGKnGQgotxXhp7YT4aymyFlFsLcbXy5fiYgMF5mK0GjB4Wym0FuDj5YVBF0x2QTF2VFtiAkOwWK2cyMnDarPjpYVAPzuFlkJCfEIwW83kmHPQa3ywFPujQYfBW0fE6QAwLT+NfJMWq02Hj05PTJABr+I8KMrGbLNQ6GUgq9gXDXr8vPVEBvqQVpCG3W4joKgInd2KXaPHy9sPL40NAiJd/vzrsow8EwVmKzqthogAb7y9JF1JZZz5bul1GqJqIL1MdcvLS8HbnI9Gq8eoCaXAqkOv0+BjN5FfbEOj0eDjo6HAbkSv0RGs8SW7SIdVo8XP24dwstV1yMsHAmNKrwVaDV5ayDWb0etsBBo02Kx+5BYVY7eDr5cWX28dIX7eYC6EwnS1Asc3EKzFWMy5WNBg8gvHaM6j2GpFp9ET6hNOoS0Lk6WYQAwUFOuw2u3odVrMGgjU2Qi05uBls6Dx8iXd5k+hRYNOC94GGxqNnVBLMXkWL4xWPVaNBr2+GB89hBvCKS4wkloAJpsGL52WIINetbEgEwozsaGuk9lWPRarHZ3OTlSAL4YidR02agIw2nzQoCHET++WHUPsdjupRhNmqw29l5boQB+3LcCqagzi1oAOVGLhV155heTkZNq1a8ebb75Jv379ABg/fjyHDx9mxYoVJcevXLmSyZMnlyQWfvzxx8skFv7uu++YNm0ahw4dKkksPGrUqAq3qcYDOiGEEEIIJzw2oKuLJKATQgghhDt4ZGJhIYQQQghx4SSgE0IIIYTwcBLQCSGEEEJ4OAnohBBCCCE8nAR0QgghhBAeTgI6IYQQQggPJwGdEEIIIYSHk4Du/9u7/5io6z8O4M9D5Tx3xyngcYhomJuT0lI0FZ2gE6R02myuiaE2nGlqZenW0gXGmswfmdOVWO3UuX6Z2kwbhuNHPwQlPUxxYJlG8iMRkEOYnXiv7x99uXmBJHKfD/fB52O7P/jc+z6f1+vZ9dnLz/0iIiIi0jgOdEREREQax4GOiIiISOM40BERERFpXM+uLsAXtfy8rcPh6OJKiIiI6GHSMnu0zCL3iwNdGxoaGgAA4eHhXVwJERERPYwaGhpgNpvve71OOjoCPgRcLhcqKipgMpmg0+m6rA6Hw4Hw8HD8+eefCAgI6LI6/svYsWNRWFjY1WW0i1l6D7P0DuboPVrJEvD9PLWSpa/nCDx4liKChoYGDBgwAH5+9//OOF6ha4Ofnx8GDhzY1WW4BQQE+PT/WD169PDp+u7GLL2HWXoHc/QeX88S0E6evp6lVnIEHizLjlyZa8EPRVCnLV++vKtL6DaYpfcwS+9gjt7FPL2DObbGl1x9mMPhgNlsRn19vWb+JeKrmKX3MEvvYI7ewyy9h1l6j9pZ8gqdD9Pr9UhJSYFer+/qUjSPWXoPs/QO5ug9zNJ7mKX3qJ0lr9ARERERaRyv0BERERFpHAc6IiIiIo3jQEdERESkcRzoFLRhwwaMHTsWJpMJFosFzz77LEpLSz3WiAhSU1MxYMAAGAwGxMbGori42GPNrl27EBsbi4CAAOh0Oty4caPN4x09ehTjxo2DwWBAcHAw5syZo1RrqlMry9zcXOh0ujZvvv4llvdLzeflxYsXMXv2bAQHByMgIAATJ05ETk6Oku2pSs0sz5w5g7i4OPTt2xdBQUFYsmQJbt68qWR7qvFGjrW1tVi5ciWGDRuGPn36YNCgQXjllVdQX1/vsZ+6ujokJSXBbDbDbDYjKSnpnudULVIzy3fffRfR0dHo06cP+vbtq0Z7qlIryytXriA5ORkREREwGAx49NFHkZKSAqfT2aF6OdApKC8vD8uXL0dBQQGysrLQ3NyM+Ph4NDY2utds3LgR7733Hnbs2IHCwkJYrVbExcW5f34MAJqampCQkIC33nrrnsc6cOAAkpKS8OKLL+Ls2bP46aefkJiYqGh/alIry+joaFRWVnrcFi9ejEceeQRjxoxRvE81qPm8nDFjBpqbm5GdnY3Tp0/jySefxMyZM1FVVaVoj2pRK8uKigpMmzYNQ4cOxcmTJ5GZmYni4mIsWrRI6RZV4Y0cKyoqUFFRgc2bN+PcuXPYvXs3MjMzkZyc7HGsxMREFBUVITMzE5mZmSgqKkJSUpKq/SpJzSydTifmzp2LZcuWqdqjWtTKsqSkBC6XCxkZGSguLsbWrVuxc+fOds+tbRJSzbVr1wSA5OXliYiIy+USq9Uq6enp7jW3bt0Ss9ksO3fubPX4nJwcASB1dXUe22/fvi1hYWHy8ccfK1q/L1Eqy39zOp1isVjknXfe8Wr9vkSpLKurqwWAfP/99+5tDodDAMjx48eVaaaLKZVlRkaGWCwWuXPnjnub3W4XAPLrr78q00wX6myOLb788kvx9/eX27dvi4jIhQsXBIAUFBS41+Tn5wsAKSkpUaibrqVUlnez2WxiNpu9XruvUSPLFhs3bpSIiIgO1ccrdCpqucQaGBgIALh8+TKqqqoQHx/vXqPX6xETE4MTJ07c937PnDmD8vJy+Pn5YdSoUQgNDcXTTz/d6mWd7kSpLP/t8OHDuH79ere5EtIWpbIMCgrC8OHDsXfvXjQ2NqK5uRkZGRkICQlBVFSUd5vwEUpl+ffff8Pf39/jdx0NBgMA4Mcff/RG6T7FWzm2fKFrz57//Mplfn4+zGYzxo0b514zfvx4mM3mTp0nfJlSWT6M1Myyvr7efZz7xYFOJSKC119/HZMmTcLjjz8OAO6XnUJCQjzWhoSEdOglqd9//x0AkJqainXr1uHIkSPo168fYmJiUFtb66UOfIeSWf7bJ598gunTpyM8PPzBC/ZhSmap0+mQlZUFu90Ok8mE3r17Y+vWrcjMzOyW77dRMsupU6eiqqoKmzZtgtPpRF1dnfvlmMrKSi914Bu8lWNNTQ3S0tLw0ksvubdVVVXBYrG0WmuxWLrN2wDupmSWDxs1s7x06RK2b9+OpUuXdqhGDnQqWbFiBX755Rd89tlnre7T6XQef4tIq23tcblcAIC1a9fiueeeQ1RUFGw2G3Q6Hfbv39+5wn2Qklne7erVqzh27Fir9410J0pmKSJ4+eWXYbFY8MMPP+DUqVOYPXs2Zs6c2e2GEEDZLB977DHs2bMHW7ZsQZ8+fWC1WjFkyBCEhISgR48ena7dl3gjR4fDgRkzZiAyMhIpKSnt7qO9/Wid0lk+TNTKsqKiAgkJCZg7dy4WL17coRo50Klg5cqVOHz4MHJycjBw4ED3dqvVCgCtJvlr1661mvjbExoaCgCIjIx0b9Pr9RgyZAjKyso6U7rPUTrLu9lsNgQFBWHWrFkPXrAPUzrL7OxsHDlyBJ9//jkmTpyI0aNH44MPPoDBYMCePXu804SPUON5mZiYiKqqKpSXl6Ompgapqamorq5GRERE5xvwEd7IsaGhAQkJCTAajTh06BB69erlsZ+//vqr1XGrq6sf+Dzhq5TO8mGiVpYVFRWYMmUKJkyYgF27dnW4Tg50ChIRrFixAgcPHkR2dnarE29ERASsViuysrLc25xOJ/Ly8hAdHX3fx4mKioJer/f4OPXt27dx5coVDB48uPON+AC1srz7eDabDQsWLOh2JzG1smxqagIAj/d9tfzdclVZ69R+XgL/vJxjNBrxxRdfoHfv3oiLi+tUD77AWzk6HA7Ex8fD398fhw8fRu/evT32M2HCBNTX1+PUqVPubSdPnkR9ff0D//fwNWpl+TBQM8vy8nLExsZi9OjRsNlsrc6b91swKWTZsmViNpslNzdXKisr3bempib3mvT0dDGbzXLw4EE5d+6czJs3T0JDQ8XhcLjXVFZWit1ul48++sj9qUG73S41NTXuNa+++qqEhYXJsWPHpKSkRJKTk8VisUhtba2qPStFzSxFRI4fPy4A5MKFC6r1qBa1sqyurpagoCCZM2eOFBUVSWlpqaxevVp69eolRUVFqvetBDWfl9u3b5fTp09LaWmp7NixQwwGg2zbtk3VfpXijRwdDoeMGzdORowYIb/99pvHfpqbm937SUhIkJEjR0p+fr7k5+fLiBEjZObMmar3rBQ1s/zjjz/EbrfL+vXrxWg0it1uF7vdLg0NDar3rQS1siwvL5ehQ4fK1KlT5erVqx5rOoIDnYIAtHmz2WzuNS6XS1JSUsRqtYper5fJkyfLuXPnPPaTkpLyn/txOp3yxhtviMViEZPJJNOmTZPz58+r1Kny1MxSRGTevHkSHR2tQmfqUzPLwsJCiY+Pl8DAQDGZTDJ+/Hj59ttvVepUeWpmmZSUJIGBgeLv7y8jR46UvXv3qtSl8ryRY8tXvrR1u3z5sntdTU2NzJ8/X0wmk5hMJpk/f/5/fn2RlqiZ5cKFC9tck5OTo17DClIrS5vNds81HaH7f9FEREREpFF8Dx0RERGRxnGgIyIiItI4DnREREREGseBjoiIiEjjONARERERaRwHOiIiIiKN40BHREREpHEc6IiIiIg0jgMdEVEHxcbG4rXXXuvqMoiI3DjQEREpKDc3FzqdDjdu3OjqUoioG+NAR0RERKRxHOiIiNrR2NiIBQsWwGg0IjQ0FFu2bPG4f9++fRgzZgxMJhOsVisSExNx7do1AMCVK1cwZcoUAEC/fv2g0+mwaNEiAICIYOPGjRgyZAgMBgOeeOIJfPXVV6r2RkTdBwc6IqJ2rFmzBjk5OTh06BC+++475Obm4vTp0+77nU4n0tLScPbsWXz99de4fPmye2gLDw/HgQMHAAClpaWorKzEtm3bAADr1q2DzWbDhx9+iOLiYqxatQovvPAC8vLyVO+RiLRPJyLS1UUQEfmimzdvIigoCHv37sXzzz8PAKitrcXAgQOxZMkSvP/++60eU1hYiKeeegoNDQ0wGo3Izc3FlClTUFdXh759+wL456pfcHAwsrOzMWHCBPdjFy9ejKamJnz66adqtEdE3UjPri6AiMhXXbp0CU6n02PoCgwMxLBhw9x/2+12pKamoqioCLW1tXC5XACAsrIyREZGtrnfCxcu4NatW4iLi/PY7nQ6MWrUKAU6IaLujgMdEdE9/NcLGI2NjYiPj0d8fDz27duH/v37o6ysDNOnT4fT6bzn41qGvqNHjyIsLMzjPr1e3/nCieihw4GOiOgehg4dil69eqGgoACDBg0CANTV1eHixYuIiYlBSUkJrl+/jvT0dISHhwMAfv75Z499+Pv7AwDu3Lnj3hYZGQm9Xo+ysjLExMSo1A0RdWcc6IiI7sFoNCI5ORlr1qxBUFAQQkJCsHbtWvj5/fN5skGDBsHf3x/bt2/H0qVLcf78eaSlpXnsY/DgwdDpdDhy5AieeeYZGAwGmEwmrF69GqtWrYLL5cKkSZPgcDhw4sQJGI1GLFy4sCvaJSIN46dciYjasWnTJkyePBmzZs3CtGnTMGnSJERFRQEA+vfvj927d2P//v2IjIxEeno6Nm/e7PH4sLAwrF+/Hm+++SZCQkKwYsUKAEBaWhrefvttbNiwAcOHD8f06dPxzTffICIiQvUeiUj7+ClXIiIiIo3jFToiIiIijeNAR0RERKRxHOiIiIiINI4DHREREZHGcaAjIiIi0jgOdEREREQax4GOiIiISOM40BERERFpHAc6IiIiIo3jQEdERESkcRzoiIiIiDSOAx0RERGRxv0P9gDUgbr7MsoAAAAASUVORK5CYII=", "text/plain": "<Figure size 640x480 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "region_scatter"}}, "output_type": "display_data"}, "region_ecdf": {"data": {"image/png": "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", "text/plain": "<Figure size 640x480 with 1 Axes>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "region_ecdf"}}, "output_type": "display_data"}, "region_qty_dist": {"data": {"text/html": "<style type=\"text/css\">\n#T_59bce tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_59bce tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_59bce tr {\n  font-size: 14px;\n}\n#T_59bce th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_59bce caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_59bce\">\n  <caption>The distribution of the total number of plastic shotgun wadding found per sample for each region</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_59bce_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_59bce_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_59bce_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_59bce_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_59bce_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_59bce_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_59bce_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_59bce_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_59bce_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_59bce_row0_col0\" class=\"data row0 col0\" >58</td>\n      <td id=\"T_59bce_row0_col1\" class=\"data row0 col1\" >1</td>\n      <td id=\"T_59bce_row0_col2\" class=\"data row0 col2\" >2</td>\n      <td id=\"T_59bce_row0_col3\" class=\"data row0 col3\" >0</td>\n      <td id=\"T_59bce_row0_col4\" class=\"data row0 col4\" >0</td>\n      <td id=\"T_59bce_row0_col5\" class=\"data row0 col5\" >0</td>\n      <td id=\"T_59bce_row0_col6\" class=\"data row0 col6\" >1</td>\n      <td id=\"T_59bce_row0_col7\" class=\"data row0 col7\" >8</td>\n    </tr>\n    <tr>\n      <th id=\"T_59bce_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_59bce_row1_col0\" class=\"data row1 col0\" >137</td>\n      <td id=\"T_59bce_row1_col1\" class=\"data row1 col1\" >6</td>\n      <td id=\"T_59bce_row1_col2\" class=\"data row1 col2\" >10</td>\n      <td id=\"T_59bce_row1_col3\" class=\"data row1 col3\" >0</td>\n      <td id=\"T_59bce_row1_col4\" class=\"data row1 col4\" >0</td>\n      <td id=\"T_59bce_row1_col5\" class=\"data row1 col5\" >2</td>\n      <td id=\"T_59bce_row1_col6\" class=\"data row1 col6\" >7</td>\n      <td id=\"T_59bce_row1_col7\" class=\"data row1 col7\" >51</td>\n    </tr>\n    <tr>\n      <th id=\"T_59bce_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_59bce_row2_col0\" class=\"data row2 col0\" >55</td>\n      <td id=\"T_59bce_row2_col1\" class=\"data row2 col1\" >1</td>\n      <td id=\"T_59bce_row2_col2\" class=\"data row2 col2\" >4</td>\n      <td id=\"T_59bce_row2_col3\" class=\"data row2 col3\" >0</td>\n      <td id=\"T_59bce_row2_col4\" class=\"data row2 col4\" >0</td>\n      <td id=\"T_59bce_row2_col5\" class=\"data row2 col5\" >0</td>\n      <td id=\"T_59bce_row2_col6\" class=\"data row2 col6\" >0</td>\n      <td id=\"T_59bce_row2_col7\" class=\"data row2 col7\" >22</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7a2c708dd2e0>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "region_qty_dist"}}, "output_type": "display_data"}, "region_med_dist": {"data": {"text/html": "<style type=\"text/css\">\n#T_94f7e tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_94f7e tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_94f7e tr {\n  font-size: 14px;\n}\n#T_94f7e th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_94f7e caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_94f7e\">\n  <caption>The distribution of the number of shotgun wadding found per meter of shoreline</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_94f7e_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_94f7e_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_94f7e_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_94f7e_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_94f7e_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_94f7e_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_94f7e_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_94f7e_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_94f7e_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_94f7e_row0_col0\" class=\"data row0 col0\" >58.00</td>\n      <td id=\"T_94f7e_row0_col1\" class=\"data row0 col1\" >0.03</td>\n      <td id=\"T_94f7e_row0_col2\" class=\"data row0 col2\" >0.05</td>\n      <td id=\"T_94f7e_row0_col3\" class=\"data row0 col3\" >0.00</td>\n      <td id=\"T_94f7e_row0_col4\" class=\"data row0 col4\" >0.00</td>\n      <td id=\"T_94f7e_row0_col5\" class=\"data row0 col5\" >0.00</td>\n      <td id=\"T_94f7e_row0_col6\" class=\"data row0 col6\" >0.03</td>\n      <td id=\"T_94f7e_row0_col7\" class=\"data row0 col7\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_94f7e_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_94f7e_row1_col0\" class=\"data row1 col0\" >137.00</td>\n      <td id=\"T_94f7e_row1_col1\" class=\"data row1 col1\" >0.17</td>\n      <td id=\"T_94f7e_row1_col2\" class=\"data row1 col2\" >0.31</td>\n      <td id=\"T_94f7e_row1_col3\" class=\"data row1 col3\" >0.00</td>\n      <td id=\"T_94f7e_row1_col4\" class=\"data row1 col4\" >0.00</td>\n      <td id=\"T_94f7e_row1_col5\" class=\"data row1 col5\" >0.05</td>\n      <td id=\"T_94f7e_row1_col6\" class=\"data row1 col6\" >0.17</td>\n      <td id=\"T_94f7e_row1_col7\" class=\"data row1 col7\" >1.64</td>\n    </tr>\n    <tr>\n      <th id=\"T_94f7e_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_94f7e_row2_col0\" class=\"data row2 col0\" >55.00</td>\n      <td id=\"T_94f7e_row2_col1\" class=\"data row2 col1\" >0.02</td>\n      <td id=\"T_94f7e_row2_col2\" class=\"data row2 col2\" >0.05</td>\n      <td id=\"T_94f7e_row2_col3\" class=\"data row2 col3\" >0.00</td>\n      <td id=\"T_94f7e_row2_col4\" class=\"data row2 col4\" >0.00</td>\n      <td id=\"T_94f7e_row2_col5\" class=\"data row2 col5\" >0.00</td>\n      <td id=\"T_94f7e_row2_col6\" class=\"data row2 col6\" >0.01</td>\n      <td id=\"T_94f7e_row2_col7\" class=\"data row2 col7\" >0.30</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7a2cc40878b0>"}, "metadata": {"scrapbook": {"mime_prefix": "application/papermill.record/", "name": "region_med_dist"}}, "output_type": "display_data"}, "city_rankings": {"data": {"text/html": "<style type=\"text/css\">\n#T_92448 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_92448 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_92448 tr {\n  font-size: 14px;\n}\n#T_92448 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_92448 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_92448\">\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_92448_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n      <th id=\"T_92448_level0_col1\" class=\"col_heading level0 col1\" >nsamples</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_92448_level0_row0\" class=\"row_heading level0 row0\" >Saint-Gingolph</th>\n      <td id=\"T_92448_row0_col0\" class=\"data row0 col0\" >0.68</td>\n      <td id=\"T_92448_row0_col1\" class=\"data row0 col1\" >13</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row1\" class=\"row_heading level0 row1\" >Allaman</th>\n      <td id=\"T_92448_row1_col0\" class=\"data row1 col0\" >0.14</td>\n      <td id=\"T_92448_row1_col1\" class=\"data row1 col1\" >3</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row2\" class=\"row_heading level0 row2\" >Bourg-en-Lavaux</th>\n      <td id=\"T_92448_row2_col0\" class=\"data row2 col0\" >0.12</td>\n      <td id=\"T_92448_row2_col1\" class=\"data row2 col1\" >2</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row3\" class=\"row_heading level0 row3\" >La Tour-de-Peilz</th>\n      <td id=\"T_92448_row3_col0\" class=\"data row3 col0\" >0.12</td>\n      <td id=\"T_92448_row3_col1\" class=\"data row3 col1\" >25</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row4\" class=\"row_heading level0 row4\" >Montreux</th>\n      <td id=\"T_92448_row4_col0\" class=\"data row4 col0\" >0.11</td>\n      <td id=\"T_92448_row4_col1\" class=\"data row4 col1\" >53</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row5\" class=\"row_heading level0 row5\" >Vevey</th>\n      <td id=\"T_92448_row5_col0\" class=\"data row5 col0\" >0.11</td>\n      <td id=\"T_92448_row5_col1\" class=\"data row5 col1\" >44</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row6\" class=\"row_heading level0 row6\" >Saint-Sulpice (VD)</th>\n      <td id=\"T_92448_row6_col0\" class=\"data row6 col0\" >0.06</td>\n      <td id=\"T_92448_row6_col1\" class=\"data row6 col1\" >15</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row7\" class=\"row_heading level0 row7\" >Versoix</th>\n      <td id=\"T_92448_row7_col0\" class=\"data row7 col0\" >0.05</td>\n      <td id=\"T_92448_row7_col1\" class=\"data row7 col1\" >4</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row8\" class=\"row_heading level0 row8\" >Gen\u00e8ve</th>\n      <td id=\"T_92448_row8_col0\" class=\"data row8 col0\" >0.03</td>\n      <td id=\"T_92448_row8_col1\" class=\"data row8 col1\" >29</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row9\" class=\"row_heading level0 row9\" >Pr\u00e9verenges</th>\n      <td id=\"T_92448_row9_col0\" class=\"data row9 col0\" >0.01</td>\n      <td id=\"T_92448_row9_col1\" class=\"data row9 col1\" >15</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row10\" class=\"row_heading level0 row10\" >Tolochenaz</th>\n      <td id=\"T_92448_row10_col0\" class=\"data row10 col0\" >0.01</td>\n      <td id=\"T_92448_row10_col1\" class=\"data row10 col1\" >3</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row11\" class=\"row_heading level0 row11\" >Lausanne</th>\n      <td id=\"T_92448_row11_col0\" class=\"data row11 col0\" >0.01</td>\n      <td id=\"T_92448_row11_col1\" class=\"data row11 col1\" >20</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row12\" class=\"row_heading level0 row12\" >Gland</th>\n      <td id=\"T_92448_row12_col0\" class=\"data row12 col0\" >0.00</td>\n      <td id=\"T_92448_row12_col1\" class=\"data row12 col1\" >22</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row13\" class=\"row_heading level0 row13\" >Morges</th>\n      <td id=\"T_92448_row13_col0\" class=\"data row13 col0\" >0.00</td>\n      <td id=\"T_92448_row13_col1\" class=\"data row13 col1\" >1</td>\n    </tr>\n    <tr>\n      <th id=\"T_92448_level0_row14\" class=\"row_heading level0 row14\" >Rolle</th>\n      <td id=\"T_92448_row14_col0\" class=\"data row14 col0\" >0.00</td>\n      <td id=\"T_92448_row14_col1\" class=\"data row14 col1\" >1</td>\n    </tr>\n  </tbody>\n</table>\n", "text/plain": "<pandas.io.formats.style.Styler at 0x7a2c708f6250>"}, "metadata": {"scrapbook": {"mime_prefix": "", "name": "city_rankings"}}, "output_type": "display_data"}}
\ No newline at end of file
diff --git a/_build/jupyter_execute/plastic_shotgun_wadding.ipynb b/_build/jupyter_execute/plastic_shotgun_wadding.ipynb
index e5250dc..31a1496 100644
--- a/_build/jupyter_execute/plastic_shotgun_wadding.ipynb
+++ b/_build/jupyter_execute/plastic_shotgun_wadding.ipynb
@@ -530,20 +530,20 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_75ad1 tr:nth-child(even) {\n",
+       "#T_92448 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_75ad1 tr:nth-child(odd) {\n",
+       "#T_92448 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_75ad1 tr {\n",
+       "#T_92448 tr {\n",
        "  font-size: 14px;\n",
        "}\n",
-       "#T_75ad1 th:nth-child(1) {\n",
+       "#T_92448 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_75ad1 caption {\n",
+       "#T_92448 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -551,95 +551,95 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_75ad1\">\n",
+       "<table id=\"T_92448\">\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_75ad1_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
-       "      <th id=\"T_75ad1_level0_col1\" class=\"col_heading level0 col1\" >nsamples</th>\n",
+       "      <th id=\"T_92448_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
+       "      <th id=\"T_92448_level0_col1\" class=\"col_heading level0 col1\" >nsamples</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row0\" class=\"row_heading level0 row0\" >Saint-Gingolph</th>\n",
-       "      <td id=\"T_75ad1_row0_col0\" class=\"data row0 col0\" >0.68</td>\n",
-       "      <td id=\"T_75ad1_row0_col1\" class=\"data row0 col1\" >13</td>\n",
+       "      <th id=\"T_92448_level0_row0\" class=\"row_heading level0 row0\" >Saint-Gingolph</th>\n",
+       "      <td id=\"T_92448_row0_col0\" class=\"data row0 col0\" >0.68</td>\n",
+       "      <td id=\"T_92448_row0_col1\" class=\"data row0 col1\" >13</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row1\" class=\"row_heading level0 row1\" >Allaman</th>\n",
-       "      <td id=\"T_75ad1_row1_col0\" class=\"data row1 col0\" >0.14</td>\n",
-       "      <td id=\"T_75ad1_row1_col1\" class=\"data row1 col1\" >3</td>\n",
+       "      <th id=\"T_92448_level0_row1\" class=\"row_heading level0 row1\" >Allaman</th>\n",
+       "      <td id=\"T_92448_row1_col0\" class=\"data row1 col0\" >0.14</td>\n",
+       "      <td id=\"T_92448_row1_col1\" class=\"data row1 col1\" >3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row2\" class=\"row_heading level0 row2\" >Bourg-en-Lavaux</th>\n",
-       "      <td id=\"T_75ad1_row2_col0\" class=\"data row2 col0\" >0.12</td>\n",
-       "      <td id=\"T_75ad1_row2_col1\" class=\"data row2 col1\" >2</td>\n",
+       "      <th id=\"T_92448_level0_row2\" class=\"row_heading level0 row2\" >Bourg-en-Lavaux</th>\n",
+       "      <td id=\"T_92448_row2_col0\" class=\"data row2 col0\" >0.12</td>\n",
+       "      <td id=\"T_92448_row2_col1\" class=\"data row2 col1\" >2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row3\" class=\"row_heading level0 row3\" >La Tour-de-Peilz</th>\n",
-       "      <td id=\"T_75ad1_row3_col0\" class=\"data row3 col0\" >0.12</td>\n",
-       "      <td id=\"T_75ad1_row3_col1\" class=\"data row3 col1\" >25</td>\n",
+       "      <th id=\"T_92448_level0_row3\" class=\"row_heading level0 row3\" >La Tour-de-Peilz</th>\n",
+       "      <td id=\"T_92448_row3_col0\" class=\"data row3 col0\" >0.12</td>\n",
+       "      <td id=\"T_92448_row3_col1\" class=\"data row3 col1\" >25</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row4\" class=\"row_heading level0 row4\" >Montreux</th>\n",
-       "      <td id=\"T_75ad1_row4_col0\" class=\"data row4 col0\" >0.11</td>\n",
-       "      <td id=\"T_75ad1_row4_col1\" class=\"data row4 col1\" >53</td>\n",
+       "      <th id=\"T_92448_level0_row4\" class=\"row_heading level0 row4\" >Montreux</th>\n",
+       "      <td id=\"T_92448_row4_col0\" class=\"data row4 col0\" >0.11</td>\n",
+       "      <td id=\"T_92448_row4_col1\" class=\"data row4 col1\" >53</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row5\" class=\"row_heading level0 row5\" >Vevey</th>\n",
-       "      <td id=\"T_75ad1_row5_col0\" class=\"data row5 col0\" >0.11</td>\n",
-       "      <td id=\"T_75ad1_row5_col1\" class=\"data row5 col1\" >44</td>\n",
+       "      <th id=\"T_92448_level0_row5\" class=\"row_heading level0 row5\" >Vevey</th>\n",
+       "      <td id=\"T_92448_row5_col0\" class=\"data row5 col0\" >0.11</td>\n",
+       "      <td id=\"T_92448_row5_col1\" class=\"data row5 col1\" >44</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row6\" class=\"row_heading level0 row6\" >Saint-Sulpice (VD)</th>\n",
-       "      <td id=\"T_75ad1_row6_col0\" class=\"data row6 col0\" >0.06</td>\n",
-       "      <td id=\"T_75ad1_row6_col1\" class=\"data row6 col1\" >15</td>\n",
+       "      <th id=\"T_92448_level0_row6\" class=\"row_heading level0 row6\" >Saint-Sulpice (VD)</th>\n",
+       "      <td id=\"T_92448_row6_col0\" class=\"data row6 col0\" >0.06</td>\n",
+       "      <td id=\"T_92448_row6_col1\" class=\"data row6 col1\" >15</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row7\" class=\"row_heading level0 row7\" >Versoix</th>\n",
-       "      <td id=\"T_75ad1_row7_col0\" class=\"data row7 col0\" >0.05</td>\n",
-       "      <td id=\"T_75ad1_row7_col1\" class=\"data row7 col1\" >4</td>\n",
+       "      <th id=\"T_92448_level0_row7\" class=\"row_heading level0 row7\" >Versoix</th>\n",
+       "      <td id=\"T_92448_row7_col0\" class=\"data row7 col0\" >0.05</td>\n",
+       "      <td id=\"T_92448_row7_col1\" class=\"data row7 col1\" >4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row8\" class=\"row_heading level0 row8\" >Genève</th>\n",
-       "      <td id=\"T_75ad1_row8_col0\" class=\"data row8 col0\" >0.03</td>\n",
-       "      <td id=\"T_75ad1_row8_col1\" class=\"data row8 col1\" >29</td>\n",
+       "      <th id=\"T_92448_level0_row8\" class=\"row_heading level0 row8\" >Genève</th>\n",
+       "      <td id=\"T_92448_row8_col0\" class=\"data row8 col0\" >0.03</td>\n",
+       "      <td id=\"T_92448_row8_col1\" class=\"data row8 col1\" >29</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row9\" class=\"row_heading level0 row9\" >Préverenges</th>\n",
-       "      <td id=\"T_75ad1_row9_col0\" class=\"data row9 col0\" >0.01</td>\n",
-       "      <td id=\"T_75ad1_row9_col1\" class=\"data row9 col1\" >15</td>\n",
+       "      <th id=\"T_92448_level0_row9\" class=\"row_heading level0 row9\" >Préverenges</th>\n",
+       "      <td id=\"T_92448_row9_col0\" class=\"data row9 col0\" >0.01</td>\n",
+       "      <td id=\"T_92448_row9_col1\" class=\"data row9 col1\" >15</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row10\" class=\"row_heading level0 row10\" >Tolochenaz</th>\n",
-       "      <td id=\"T_75ad1_row10_col0\" class=\"data row10 col0\" >0.01</td>\n",
-       "      <td id=\"T_75ad1_row10_col1\" class=\"data row10 col1\" >3</td>\n",
+       "      <th id=\"T_92448_level0_row10\" class=\"row_heading level0 row10\" >Tolochenaz</th>\n",
+       "      <td id=\"T_92448_row10_col0\" class=\"data row10 col0\" >0.01</td>\n",
+       "      <td id=\"T_92448_row10_col1\" class=\"data row10 col1\" >3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row11\" class=\"row_heading level0 row11\" >Lausanne</th>\n",
-       "      <td id=\"T_75ad1_row11_col0\" class=\"data row11 col0\" >0.01</td>\n",
-       "      <td id=\"T_75ad1_row11_col1\" class=\"data row11 col1\" >20</td>\n",
+       "      <th id=\"T_92448_level0_row11\" class=\"row_heading level0 row11\" >Lausanne</th>\n",
+       "      <td id=\"T_92448_row11_col0\" class=\"data row11 col0\" >0.01</td>\n",
+       "      <td id=\"T_92448_row11_col1\" class=\"data row11 col1\" >20</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row12\" class=\"row_heading level0 row12\" >Gland</th>\n",
-       "      <td id=\"T_75ad1_row12_col0\" class=\"data row12 col0\" >0.00</td>\n",
-       "      <td id=\"T_75ad1_row12_col1\" class=\"data row12 col1\" >22</td>\n",
+       "      <th id=\"T_92448_level0_row12\" class=\"row_heading level0 row12\" >Gland</th>\n",
+       "      <td id=\"T_92448_row12_col0\" class=\"data row12 col0\" >0.00</td>\n",
+       "      <td id=\"T_92448_row12_col1\" class=\"data row12 col1\" >22</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row13\" class=\"row_heading level0 row13\" >Morges</th>\n",
-       "      <td id=\"T_75ad1_row13_col0\" class=\"data row13 col0\" >0.00</td>\n",
-       "      <td id=\"T_75ad1_row13_col1\" class=\"data row13 col1\" >1</td>\n",
+       "      <th id=\"T_92448_level0_row13\" class=\"row_heading level0 row13\" >Morges</th>\n",
+       "      <td id=\"T_92448_row13_col0\" class=\"data row13 col0\" >0.00</td>\n",
+       "      <td id=\"T_92448_row13_col1\" class=\"data row13 col1\" >1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row14\" class=\"row_heading level0 row14\" >Rolle</th>\n",
-       "      <td id=\"T_75ad1_row14_col0\" class=\"data row14 col0\" >0.00</td>\n",
-       "      <td id=\"T_75ad1_row14_col1\" class=\"data row14 col1\" >1</td>\n",
+       "      <th id=\"T_92448_level0_row14\" class=\"row_heading level0 row14\" >Rolle</th>\n",
+       "      <td id=\"T_92448_row14_col0\" class=\"data row14 col0\" >0.00</td>\n",
+       "      <td id=\"T_92448_row14_col1\" class=\"data row14 col1\" >1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x7896afd57f40>"
+       "<pandas.io.formats.style.Styler at 0x7a2c708f6250>"
       ]
      },
      "metadata": {
@@ -661,6 +661,71 @@
     "cp = cpm.style.set_table_styles(table_css_styles).format(precision=2)\n",
     "glue('city_rankings', cp, display=True)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "989efbdc-f400-4894-8424-a5c4856595ca",
+   "metadata": {
+    "editable": true,
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "\n",
+       "\n",
+       "This script updated 21/03/2024 in Biel, CH\n",
+       "\n",
+       "❤️ __what you do everyday:__ *analyst at hammerdirt*\n"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import datetime as dt\n",
+    "from IPython.display import Markdown as md\n",
+    "today = dt.datetime.now().date().strftime(\"%d/%m/%Y\")\n",
+    "where = \"Biel, CH\"\n",
+    "\n",
+    "my_block = f\"\"\"\n",
+    "\n",
+    "This script updated {today} in {where}\n",
+    "\n",
+    "\\u2764\\ufe0f __what you do everyday:__ *analyst at hammerdirt*\n",
+    "\"\"\"\n",
+    "\n",
+    "md(my_block)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11d8473e-9271-4828-b1fc-ecbcf2f28765",
+   "metadata": {
+    "editable": true,
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
diff --git a/docs/_images/3b10867ba4b3bf65b1dee903696e5accfa2c51ba007dd2cfe381a0658d975cc4.png b/docs/_images/3b10867ba4b3bf65b1dee903696e5accfa2c51ba007dd2cfe381a0658d975cc4.png
new file mode 100644
index 0000000000000000000000000000000000000000..604743772dcdb124e526c53ff536d2c99428151a
GIT binary patch
literal 20187
zcmeIaXH-<(vNqa)2qF>$BuG$_f=Fs42T_!$D2Nz{0*wfga|T7CAW53k7>JT2NX{ro
zRuPb#bB;~s)^hK2_Bnfu^NsJ`al@bcqu<7UyVsg)&YD$ERXxuPymMRe6d4m43WYkQ
ztfZiULJ^`-D1t=N<M7FJ)><vRN!Z_bV6SO~v3D}GH9_4nw70gfvbQjMa?a7j*3Qhz
z63s8hFT{85slC0mouq)k^Z)z;zm=`2KtCC&KV0O5wbDa76pGRic@d<`rJ12nx0RF?
z<nK8rEDpLj)7}_sSY4(%M`Fx9s)V9BN2>DX>|0G@V)mTOl8a<5A1*e2`aa1!qfYBU
zOiM>)b(O+_?wH><-LQb54+Ck<w@4X?eXn8(t`Tx>?ioe+2%VU~%}yLhtK)uj$;fD_
zsZS-&%{_}3YB<Nv&i>>sox3gpH8pkkhdWq!qgK`Y-+s%SnJ0@XY;9GeU>3jn^yx*>
z__m%d<WlZ}4c22{Pt5(!xb8<rzwE}dZa7urL!_XnxL3vmH`O3jR#sNHaYNTWUYHGY
z?fP{Byw|HiOT5i<1qB68IURobpFe-%I#z?>hunL=BL*$CkwN8Q_sOY$q70BfMf@25
z%Uhwa9EMviL?}VZDKsR6TwnV}kn+{5D7s7ce@||+vrk?vr9_*yCyb8NzDQ0@-7VwQ
zXuWprTDoqzX!IrREe9<Hh2&$=^MaAFvC2=LuoDmv{LawyZ;rk+AMeg+5Hi{ti{3xn
zTju2E{*`|Bqw4JvPImTgt(<!J-1K{EE2pGn+?zL4`r3*?cde}jqj|NS9337cNZ7r4
z_wJm&wz7hPN<dYPZ`GHWyRN!76q-p6zR<%g5!$5sTpBEIjb7r%6aRgjrecnaALaxV
z`CIPqY*Okst}Lx_$d=%48s0=Ph+Cg49&*jh&AfZ=epW$1K(s{X$d=z5XJ(9rJxN>v
z<I*{_U1a(GmS4*7b<G?SRE*-@)*=Tt_p4j+qCfLZRMmG{1gb-XQokm7jnw!s%Xubn
zslJWcwhIhUTFvi$=N2MW;w|;Vz3i-~jE!eJ>#2eMXl_47f|^n5?J_cU_Oa;&AHffm
zd&9jxQ+4Oig;&U}riXGwW<@k@ln5MA=H7`9Tew;o>L;2a&3?QisI9FneEQS(M(~-^
z%*cpqFdZ2W3%KD^k!QaHB<!Y8R5Ub1S2OQtf9|!gU+km%?$VrU-jhSlCYx~g<4tN-
z*4xI$oM=qz2rR^aU5CueSFdb$CS%rnO_N+$Bg4aM-^srS2n;+gE{?sFTM-eX@7Y^$
zn30BiGF0KRKP`7uizzTH=zUP-E`h2(*gESp<Z@wjbo5@XUZP&5Yo67xY_5mg#*gbS
z{rv7$x;iw3FlzG3D8o~>v631|UB8#^<Z|y~$n3pc`Qx;hApR3GC%+Q1csD$3QRdn!
z9B+7S)Se(wvD$FfVz4aw=SRhLeDzVHRrSH!3pi)r=lw;iFw8uUJ;x#E@l(%!rxVol
zeK99^P-MYKLdiNY9wyhmE-}>>ulSnj%7b#p%k}=0(_md`>PfQpbH4*$pB1yMKP4t;
zP=o4NXo`)Eg^jX0>d%({yk8XOzNUP*d~_H_DYsAM?a$_km0Bu!fs=8wT^W(5V3k%%
zyPc?X>(*r1e9p&bU7y_XgHG;82l#v0kD`$;O|>$j^jv4TFdewIeyi#>{IFL?o>Ak2
z3TGSTL;BzVC4QaRm3_(~8Q~E<T!rwo*6oy9O!Icn<Cqq|`q7$M`zOWymE9>RDdAYG
zlA4;@D7ThsEsM^W-9vhkR+74tRsE_G4s*0up8Xz~&#g{1Y7E7#)xIE!jEie-ioB3<
z_v7&b(~kDlKNStF`!;;4Jvq8f-@hAt3!?KbH~l(l{iEE;YRF}p1x3Lksj%4h<>8lS
zbS#qg-@oM4zdFSsA<^4u9@USH?JY1xyQ~=(Sq(46`s~0SgjLKlZaO_SHkPiLM!}&N
zYP|3#4~6&wES90K&@6I#JD$C|3YM2^?^DWxrrO9-I8UJFE&9FvLypZ>+8e^9B#imZ
zk*ZT>#n1b1K6=C?<GS$<<`0(yhU5S8<*}veBhRUhB=wfJml@F*@=Mw|e81O4tcC{G
zm%Y7FpR{vt7hu|?O~S*&QOvULe>AtI;;nuaJ%9YHJ4?CilUA&R9e4HqTFZ?jQ+Sev
z-U9z0KkleM{-l+O-0Z}O6XJ=tVfAL{26*phDfJgUKiS1kP0hn>WbkloXYzfv;m)97
za@S720KTmF(k&*G4sAPojzBVaUeqC&o=vYwj7#=Oa&p8G9qi%PtB(%COj_Rl%ziBP
z>eShWV1cR!@1`^EWkmGkw_(<KTb6D#<#d4ce4qLG(PcIzX68>G$NTs1D^}`GW<4yJ
zidZ!3Og(i3m$u8wd{}_-nd4(;=W3)r7Q9;`P`&iCW{^meXJr4~h)LkmW~jyzxi*$3
zNL3eg?;1Vn6|-M2Yih1~?o85`+0RDIi(WDBHU@`7&Mf}MJg4-PBCE?wdVTkwb|kYQ
zAt6t4dxGdL&HT=wp_E?nPUAa&zScY*{O+{#Qg`;_0)tvYh!$%LDp}yEGqrQ4`pk2Q
z2hw6iE&g1c@6HY`rDJEe6}ob5M9!&9pt@Z)I?5xubHy=*&G@Qe>Qi=`u-8rIt!l<i
z($66}!IlyHs2IkLMn`7mRx!o2e1jWhJo>^5^IvGz`6@G~ENElH{%~*j==9mMC$B0f
z90Pylez-FY8<3io_MSzIiI~NoH;73HRBii$Z4G(gbzz*-rM_hEJP&r=SHICO43tLB
zb!CoQi_Z*K%L!Dh5LUWwj>Ved&hzpH>3i<@g~=Uakx58Tzj!m0xe0um;>Vk>175#2
zX^!Fnw_NdH?lL<&apYrz)o)sAy&{;@i*-H^OJ212jpaA18mw3qc^%B_OYclXs>O)}
z{`vF3vSjqQ?9K$ulP6EobxMW9WVRUE;>D(6s<_Ub^WIsXCR)nl?o3mk&MqGMa63_Q
z1BUl!&VJYf{}cAxQpNi1zGABm@M4v&W~f)>jCIl4db5n$>-Cg!RHskZISqR#4wgC0
z4wj4M<>d{yEmtPUdh~T_u6KAHMwTy?1^W<@xZXBA*v$31TvQeu5a2NTEOo4;kBb;@
zpnqXWQ#Cy5>6`HVpIvH5%zTp>Yaf>({_^7rEbJJEWE(_M_P42m9RJ&IMt2(+UQw{9
ze0kOdvBP4hqSw@6w(rX&n8dZ-b?{+3smkkobL$;)rb`2*eEL-h$4@cc`FQix-$4BJ
z0{HXqu~Qz?cTn1r44U~)6t|R=-Z?Jzf$PnfzybdFN(dt)4Nbn5OT5zj$jO@kzdUO`
zFsZ1aI^{w_!Tfz?v>qanKHU6wu6`0&%*_x6c`z1vd3ha=&91D+#qI0ZQoHHXXU<H0
zNrE72P|z#gqAs&Zd--wE#Gun~3YdyGGsW)KVoM;+1?m0-Nrxb0BEcPKlsi5L2b~gO
zmK+eEB+JuE8-YG$sZSc%XxMPm>77LUD1|UuthB{Se`YABq!L_;^m;2A?9&GPKUiWT
zR>)|3=3^LE%!>7_m}RnI{i^}%`cuqOj#*dtZYwDnG(~XjgU6Tz4<Rt@xp%ok2A^Ph
zz!4^0CpPR}KlUv+Ff7b;XKm8r&*%3g@fX?IBdo~Ke#Qmzc<g!$TJ&0v%hI{XY(*lx
z<F~d^Ybqut6@Xc=6zrUwFU5wOU(oA0`<%6^2<N^PCuldN=KJD>%idz~$--suRa5PW
zs-3B~N~hw?83YYb`W~Bfs0-@2iN)gKsc-c9$%<jDBIey8F6&d^NAK>xrlqECx{&lL
zcDZUVG~TKzR?=Y(rt(3)abS<D5jirU4s*W|1dyX!p6@V!fB4=OB?3}p$juz87JAlA
zjTrivUKOvis%mPSK7Cr;ZHq5a%4sV~>(jkJSa1l?TZD_5uowU?T;BrvXdA8fm+7#B
zC@JZ<F!NA9`_Yx0inV6;BJc&tEAC7f*gb$~E<0~_Y1`?_K@3V&i>(7^(p=^+pRSd8
z2ExV)Q~jvw)>Vdn#t+vjTRvVhR7?AHLU@G2!@FlYW?^k1pNx*zxv0f)YoV8U@6$hB
zG6x#nIqw3tw;!lp-}+i?=zBqjtm^VmrCk=fLGXE>2&>n=jVpfX7EE6(ENw<cM#a(L
zo^1N_+d1~mha}6ajMf6`dM=)Ktd-6Gd_E7Lc4}|A8XuJ?<MwuQzJ~_!XKis;By7fx
z0YX@_(EL$q#w2Q?l%f*-pwjhA8Xp&zpKiG$T{Z#i!y6;TMwrtyG!phRR5ms?xP0*E
z;LGd4U9P+9xVlR6$F$6+aT@D?u^(lKJ?Zu|pM*H(=DQ4y6fyu5a$(YIq)A?f5)j6W
zzP~vScw6}Ck8>z+GU`f7q(^wKqej3Y&HzhdrJO8%aA^=|$(cj~5T}@1wHpM#jRl{g
z@!ofs^(N#B6x)kwKi*&WM+Jn0Z19G`f3jNIl9eN^#hGzQGcz-%Gm?Zp^R4c${pkL@
zZ@DZaqQB%|rOkwMTavIWUlct~&Va-U01cG-?yJOr0=?ZVTELAprX_i*K-k_Mc|qws
zmyt%cFO9hC9zD0q#RIk{2g{wN=Q49s0X}~lU;?<lU%)8GNQ$7!3TGjJ;+IeW1Cs5g
z+nL3!y#e646`d6}MiLt&WRxylkdaB;*jOJt&mR*!GxIdz_65iCLG%8?LJ^qSK!C0n
z(?`$)EXof0o`WB2cWSG8Wkg#}8{TD0r`8x5R1xBto4>@)UNvr83J+T9>3I}B+>X-8
zynnf7@VcELR>FPTI&>)RB=Pa%rx_kda#)$atnpgfz!8Y=@urO~syH4;(j=Sp{!TR^
zA)()&w1Ney_kU?Rf^k<JY(1`ys~e_{TK~l5_Rcp1T#ebPSw|~iG?=C^QwbrVa0nrq
zVE=R7*)5RrV8w0N0j+)jY_66d9uCRQ;Z||=&gX8#i>t%V=+4#eaOlyUe&{*#-XB%6
zw^R;`%Wu>WGP*I_DZNrdl$@OWqsqf=Y<#?u+kpnAbFIzlI4UM8_|&;ysGs?_a&sYa
z&>5pX4~NFWz^R)k|679huXL|8d3SRj4SS*ku#6G-vlP9sG@NVD+slvN?yd&~1bAs;
z!wIFFSI&VyGO8-lLcz@<rizQvZ^j(p>3Owtbolm~tGZqW1O&+4=};3=QdTx>3}pf2
z^9uY!L_~zfSV!*{b8S}l6?x=US67#=S1AdwpTn*19o&6=p`b(9dgLlI1<CbS<OBm^
zD-~OP<|im9xB-7rbKJC^`_0qgNy#SL+9o!v1{oo&z&^l=_SFF|>9!4k#=nZK^bzz2
zsp8ZAqRZypS%wg-qz^VaEqe2b<J(@rqrnF#z=cSxgXrQ|o(R9gK?rdM7X_dJ@*{w3
z$i^uwEPQgPPfH!152z;q#y`_vEC8|Ee&&Zy!|Su1a4+~!WxsS9at;97fap#E9x#P~
z*BW=FrQpzyUhf?sKJfWINCK1Oxf^)avczYo(rq1*m3%;9RY!+z$W(L~9ft^5<*~QD
zJD>Zo@F{g}^`WFcC0ly|1$gpg)fj$cGo+}-<eRjdfvoB}2E&cyUPq9VmCk+26o+L&
za-epp<*y9&x5Ng&!p7d-=v43hY)F*-xH$E3u_Xj6a&G`@Z&t?}(S~)$z_ipM8E`q+
z>``5k(^OE%YKgMBoz{tJn6;mJ;IzA8Rsfli-R{QhwZ*+Zc}Cp){Ou?SPsj#ZA-4&7
zbRg|8`|I1+hK4wZLF&EmjawELSwan1*Uh=u$5xeH^Fl<&$px?bQ*81+&U@mQap%3S
zgvV}SZ>e1xK`VeInfYR?VM`R+VeXzfqrn*gJ&O>bDF9Q#F#l74pi8^$_P1A4Au{Nh
zKv0X$>tE!)e7P+XqO*XQRpsVexK}8PR2*!I4s!@Pi*^h1Pl9%L!B&@b7S{K|exo&y
zH8nMTZETz_<Cm4iO-xLj_Bezj=r3|$k#aP~FAW+S8>4<eN|Cz=Ahc$n)DEEQr|Ice
zXD!bGqW$_+0rH{Su)3A3Jta0qV6$sk^^jzmb$z0P45Y=W68RaDh3Qq6Y3qUyQdUwz
z8Ng`l7ykU5xAD?BLrqO^3dMgqt@B~>CResfG_PI@WS{%vY)1xP1E?j6V14+doR*HQ
zkSWESW@gqIaW%nU5XACUKp$r`_{}#G9Em01E2tUJnt9yKhE3CG3%HDwl=Qp99s=kg
zN<-Me&hG+lZBLYHgw15ulf#07%T8>sj=OZfhv*MR84Ri8WS^8~sjZ2+`cJ=2aR^0F
z%t?k|?b2<sIoCA+&PHz${KyVRB8J!Z`*$T+Z(Ch@dV1Ix#(}b48XBi5Wj3gg3%{V0
z9RW;hIPpE)#Zu03;lcgvN8dgh*8iz+L6<u%V`hJ)K;41a8!03}WD++1PSu_D5E8Ys
z4ARakH{A4Ll#1DpzLacsKi+{v{7<=)0Gr1KHB>JM2eh@gxViIP)-j>X64xL$LfA-y
z!4J63Xa7wH`isLL8Vg$vh=Uzd)_f1=h?Q{@g)|rg*>4D&91dpn%=i&5ARvm441I%&
zm9-rlk?pa#k`i%DTigw2XXilKBVDJ#Z?m0g$Xvm=jJ8)s$yp>tIu_%_tlEo*JzJIr
z%Mn=h6c$@udiB^B^PVjWD0ne{`1lc??qsDKeoIF-F$N+y4I7&}xD&6#^(3?IEJg(X
zr8&(M^;>>4?ZD|c4LbbJdKgJ5yN!x(Yk&aR{G~^)r4m2XLZ_`GKV0R}TWpnd0R>5V
zB9eiGut>cXect!k>&O!_<ijVsNi^VvzGBq6zjB&HwM^EHT94RE!hX=3|Mlw^R1Bbk
z1~svF*W?scRLH>O!M}kM1-Qq>YFy^Hr~>(Qr6u~@P|*A)9d-CGr@W43xnJ1WConB~
zW1}|!A=##NLL$Nb#B44$FMWXD9ITcHHqd|1ABdt>PnI=buFQeb-}O=oG`Ly9b62i(
zHC_picymyOscr{cAsRhTPy?kts2<pCuNb1BAV_Af&%UbOz@VY23Gr3X(9qCjXb7-<
z^DA2x3<_`x@yH1g4M+Hei=IB*xV+f|n+JJ7j&6KF0BJi;W`2H7NeD@_U5(*afwpXz
zeBxurX6j+ezxp<B{-bm$`#(fBh<g84*8Er0`+xWURa2m++Y^ljN^HJ<{Yu5mtoGvg
zDd(wJq}I9N(1qkk>i0Gri20{>rjw>2#u-D^O~;{2D@(r`U{@)Le|;?&x`(a|411Nx
zlLZ4i?nbU&Wyx%6JSttkT9(ayg<!rX7jM&sTugs^(<~KWbQ}Wz0EQBLhUkHWoI?m3
z(>qwmv2^%jdcq)JN9lSFqS3I20Z&1pj2kjssP}TKVXszu9;~^y0xopkolR5Cdy60w
zRroSeL>O{gmKpLo@({Hg_+H_%?hJW4z-T>On9D+5qqSrrE(zd?Mphnj15qf9Z<n2R
z2@DOL`l-lf^5?T5F5fiC<1K#3Eew3|ggG03%t`-xpU&B@mc=pmw7@Ep8R#a~`*Yne
zU^p3fYRiMbtja_l!?Q{6yS5@Ip!MYmnso4=+PV&O@uJV4K(3FZ(p5QeaL?@%)v|5&
zP%y_ikDY+{(h7M<22`>Rb~nc%14_1?Y~Jbfzl{zI2za0_FI#;e*-A_D*NEnM&_)=z
zjROA-!<+ENckBOu`@eMx+Lr5Ep|IO9e01o9l=&co0SIOcPPi)PEwXfhK~*_5-w<?L
zYG;~Lz9cETw}1xQQ&Lho$H&*&qxFLJ9HTX%;nibQOD$xuf>G+QA8=lWF5sJ?eGr<K
z1wpMU^G*?`fgqKa{6l8JlL1@GuVFEpFN0YW+RtkA6+Kr?lJ$Vwz0=CP-<lxNSsbl$
z-t^6Ra~JDwSJ-1bSKyjkOM@+tddow=-5v`TD1o$@LFmb`Whn6A!j#q38z*gD4rnut
zZI8!VtUjDa%=S03@c<RU4O+ei(hwl=0}$9GWS}GPEX|ujk=(b&X48`ROI0L-OY~q+
zL0a$YTOr$d2&HuZeo#&8G#`xO(G1cNLXx1)WM!J%e2DI{yE7l9+1CFUg{}U$PU-Si
z7wPGI6MysV?$=G29*rzAIt=&igzqIb<0Wg&mjXjVzG4box^=ggKg<o3q9JZ?@b-T(
zr-xYIvM%J~<8$oz@iUKEYy-Z^{1GeGyk+yxC!pnRtpK3aij#?lr16ZML&a-WnK($)
zg>1$YmP*Dcx^r|}LKx9d7`YiJyL`iMyy_WGE>xjhiU6%-@ZQ4$-XjFu&%abQv63ct
z5cn;a{_n6`(H+pFsE5)ZRPww6<?uId5Uoqdb%YQ(g@yc0nlcI)jnw4XM4%7=9k3es
zrph~&Z!MFyqt@c!RsJkGLQ4qdZ0-HIq+!3gSeNZl|59*)B`{#KU&$vREUi5{T5V*b
z#}vbyuoK@;7eqr|SG6;B7BM9-IK8YFo=Dgu`*6o_D$!|Z^kbOpSZcf_@6s-qLjbMP
zdkiY)el`;{KwNBkkZ&f}z|7)Y=Xe^z*wmjrduG#v3?ca{nM0fzU}R2CPAW!5WpFKa
z<ftJ)ih1{L!~dVqfL~cwZgxM(c?H*18l`=Tiv?F~^NmhB%Ge_)aSF-Gc=XyuKKIsm
z)(*bVnKd96_YInsAY0qfeJ6wle8es)`W6s(KEz3OEe*J6*0d7u#v@d2mIDcc^%1VB
zLD%yuNxj)gT1+UbOfz(fBwRNxBGpV-ed8bR<oR^Vq9B=x`1BEmuuWjfG*Cr#I;=kA
z_0m;4(RvnRjHPYNaMh1WT{GU_i{z*fp{z$=f{<hb_Q=-qusWdR*{)1_ubmcsxWL7w
zvNJ({ohEJA0xLE)zCGrKUtR8nb^*%gr|SD%l6-l8+eQC2OFh|ZAqusnuaH$W7CrAr
zU?EZjfXto?@;Uf3`*S(K3~D)J%9qrOhDw?1CS26UWS@S>py};4X6^#EzX_Wz$gPJs
z6$f3(@G%EbqO$gN3gNr&p(2q^dq=wC?wAaEeX4ET>u4{@)TI?G1Q_CHhUNui*kIxZ
z?B9`DU$srCUzc+x`Oj*O8Q5nm<laz-Mj;QYt?v;H7+w>~nK#2&b+hQ8Mn-+~rUx5q
z(fh(zRq6+92Tm@opPvn{qu%m8tb@{8JJe2MMa)iLx}SBin+$S}058GgZ@F;#tbKhR
z&t~iXSucr$_5XA~yBX@h1OZ`TX>Rx>)G=aW8!(x%%tZLr_9;awzBwWx!)cPe`()yB
z7sa_-E2~Pl+goz44Yt37;vG4wG!_DVo_P<yW!Wq@s>pIs1?()iz!PkHO!3)&FHp#R
zzk1#cqvy7G1&VFom#dH371=x#U@izC;u68{F8y<~HpeC__WM|8;?EIr*_#!~{Y>eF
z>ve06#b7#O(f)oX>8CF0msp>N>Alp-|97*bz-B3(#=)X6Ni+jAg!09c@Jn3qvj}}Z
zGV~sP`2sgLx1tM_=C`4g8>GVn(-^)FlMN1fq>;_5^==hFkPZW+h7$hkPP!nHL_?jo
z7OJGzZ{9r4$jImp`Dh5UL<A(mXPj7&+pgV9cfsI1wjLsjT5LI({@`b2FrbsAsy)ls
z$o2`>&`MS<a9SQ}gQ^lK1w|?(JHMf=AwGYf51tGrd6RZxz5I?08U-;&R5R_i379kr
zX_-RdMaX$&q;3h>SO3`JfE7}2CpJSldKTI@BUNr&kc$F7XX}vNv&g%Te34VYPqOVE
z7>l0EWHfUzKT_&qkaZVV3}xmiB0CfPPe>8ifl3GumxqF#T~sl2LcsFrFflM&?0y>Q
zf`6NvP)p%Z+yOs|_`?5~${S25W=JReDOgZYMZ5x~FC;CKhQ2Cp5h|k^8;=lkn|Kea
zF`eX<>M-Ap0{4TuQ-HYzjj^T<xub>Nc1!`?b-KUP2i|WTpc1W<3=Ca?EalEWpv}Ht
z9aN|S9>o1W|CUmR07$6phcI1f?$LrJqn0y_6)dnEl*F`R<-x){bm`#3RgSl$Xr$ob
zb#w^fIC5ph`X8QtKY**Q6;ewC=*|pPmgi<7v*?-nA@`Cs&-!$SDHM^QLBOxypO%&u
ziNh^DbS%~3(z=3NlL)|SWK`5wK+Z19m3UGzvgRHmsH4BEA6?l8>O_q7WtgU~F%}IB
z<MS#LCP*nCnl8}fsnL8J9`4hI`FPEbEIBRBE&IiQ8wTKo4HAR4G&0L!`e<=~)3J$p
zz^UqJSc=zB=4r}Y0KER*X1oD1IZ?$o1f<YI6cqei_z5ci?6OlmhTI||QDCgD(OMZA
zeozaUzKAdv)|zq~Tj8PsIzjsQ)(H$W41nJN|K6tFY>hH%7qL!piz)pzI0;v||6Wk@
zHjA>K-pP^ZFVjS?FR`TN+QhIaZ$3YORbEpyOl7uBtzA5MepS5n&kTi#DSAL2GsW$+
zvv{)WI_%wUgHj>1hP~)n`!E|4dTWw6b*Fl8;#Qp>ecYsA-n`Oqv9{k?NjduJ-`t;W
z;U^cq{<wa{acL2*zMoj9CSgMPGB5Ew@9%PHUfKqGjW_U{`8!yiw101P!&nbhU^LAD
z5ZqeHo$)`6Dar1?gRftLultAim;_G8_!qsJbaD%Ozhj&G&%0;FHlIg4<9OA68T3UA
zhE)ib<ZDMLB%xVa3<Zi+CsCv3E&Q_Yz_p4Bo77T)>MHBcxt9h9IX<3)$E&*cro#%E
zv{K?Ty5FE1cK@Rgf*+rlk^NtMiz6thP$h^UxIlGW0X15c^#%e<ZMtcyv?}2)Vcu1e
zcQ)O&5dw%e)DR>?Pim0~G6Wo5cX7Y(qLR_01m5KiEvEUu!bCnOD^}Q^v8jXwPJ*e(
zWxk;!03ID$Y0a5R=lH`M{sG4Revga<6OR7z)g*d;%>wdS(l)dv?%#0JgMd0U7y8gT
z=oLPQ`|E-NQh5HF)BneBI}TVRQhM!nCXt>x1ry{8<-uschP!2tU`fUl_a$51p`As3
zRy3q5Q+pjkhwajU1XP~H9p<8PGr3_(#d&Hd3{HJUoA(Cor?ZF}g{%&C(zil*1C(_P
z>9_%&cwWW&kFq|LKNcL_PW0RX0LC8SU3+z(*u<uW?_A%7E4&FBPZg0|ugr8R43b?G
z6!F$=ZXu5GqF(}mch+R>gEapJ%Kp1~8%g=rAwr1TMf#5-NNIfWS7#?cemq~fPR_4%
zC@y{f#ubT183%VfV$*Z&;t`Rv@HcVAASGST{Z&O-2n@lNVrIWMnJN6IFG%*O95}+W
zU;y(E>2DiK@lj)5L6P@Yis}v!8v=rY%4Uj?J~LEd*TH4oQ~3foq?A;Vx@YesTv<N}
zBitYeKo-em*Ctz_+fh1UL`Xz*f}EVsuMc7@?N!bt`TWwv4}mR@tcX4TP*g9)GKyL-
zfZt<<xsrv-Dzl`00MujwfSBoP!*eGa)Y<4S(%}8q7BaoF1oe*Z=d*Zvm=(2QTE4gg
z9R~;og8F+u5O6T2tzk_W;V>r4MHA@Y+v=xM!a}^WzqR+ba%7?+-c2sxHKDk;GXM7j
z_LvX<i}v$Wk2YGFr)1?<ncz9XYQ{u<zz}S6u{<3S-c?umeh@rO_>v`c6?TT-#nvco
zPv?_P;2-OdU9x6}{7rol`Fnrm%o13T-+O|Z$!NBrI$cQBIZxo<yc{nPICp~NgNG&^
z_yFzRV(X6A(Uv!0ccoZSS_}LjoQc@n8_Kd}``1OD5GdCi)a1)W3AFIyYw7YJz#|)s
z=WOu@dcZ2-*V@lTK7ZJ~t06m>ET}oO^Yik+4d`iy(%X2P_+iEkBWkMt4D1ntzy2k{
zi{hOd>wMXGWTv4*Tt<b|G3KfL%GhUwU)&#_=b^Fh5D3q|#DXOYX>eOmb24}Y*G(1F
z43*HVb);QL^wzveXPr%8M4}jwYkuKvv_ku16Jvd@>5mc@p(c`oDjxAvmm?`bNm-*x
zSRXvv)%s<YYCHE`dFBh1o&+k#<m$^k{00$_+%9<NUeDtkTvttAup3$WSxx*jSgNM5
z?U8JV`fW5%Yt;32k&*)rC20zDQSGG*BMY)vPeP2PUCi)dxSLcs;ZK=rg=Sf~1bZ#;
z-w2uQ0GicB@;#IT^4yQZb|Ds!Dd6`bBBBTvP~9l0yXr}~+oQ>uOlVDtULr$<lOwG=
zsP*~4^?83$pV7+${eiRrOFLX#H;nT3gOhHReS!$njH58h^+~_8yq124!S1zNrIOE%
zA-*7rfGKz~sm`b2>R#5cY{iqihN%g*ezoi76>i2gmC`QR|MiPpG4DFnCf^_t&?h#&
z1JV&3r6^jIK$KzVc3NCA)qd9A!)Da$ZxO1{mXa_g=TnugmM*-)SAF(Xp``xSq#oXp
z-ET~Buwyb2-F84cbuGs}ST{R8?}6<JaO7_|NY8BgU<Dca$X<#0tHck!@bxdWjS-j|
zAG)oOHUH04j39>Q&&Z*S$LsQarBAu$Saqggt{4M!s)g4PKoOuN{G(CX)3ti3z0*MT
zn44642dd(X8YFujx>D3UWTtUapE+5bAc-P0%6T<iE$2mNq{gs6eLL9Q21p*0x4~&$
z!K7BG5Hwz|@xQuNT%c)iL}N`NNSw$-l_wZ~s;sf5_14lPWB*7e=d%2f%o9G5q^O1`
zJBd+Iv=Nb!09qh70yC9&F0s<1g6jTDVH*lbMr_N@xyZ{`GIg{`0v<fta@V*XmmpBE
z@2&w0Aof2sz1%g}{9*~$5?<)J$^J0bXEDyO`%xx&HMzB5*(XnXS}5sv*U~0CadbpP
z9Z*99!|+vlve1A*IBO9ayEI1^TWP%!0tVJW{o~&(lw)3a`qo3d$fKv>tW3Hr=QO5D
znaUc!Pe>;H#{a!iLP7$^cjMr&unQ8U8|7Pc7_xJF%=Sf$XW!3PtWPHsxQcxKE-{nu
z=-|E7%RcrknxeDVdDw2Tjx`P@B>J+1dTg*xP^Zgk&Yo(v04yu90g`l9P8+RCk_`4;
zqiKtNANwdVt=54Ge|bg<^?abEy;C*^8$daURsVE?Z+Tkg)l`c@+XXJ-X=|N|`9qC)
zRo^-_0x)xnY3X)(r+lS1O&B6e5?O*Xn1d>r%mMb$gqM13b(gAr%o(Xh4`mL-oOZ$^
zt8(54SWUnsS?={6=jbz&<>86@+hnm_?h6YJ<`B;R$HRS(rsz0&(<m_$eP%BI7Qrim
zJ%Nh_CYLGePp6qBm|5>BJ~YDq=a#J-{DN~Hs2n<NgjG<v`kD$aEnMI4dq8DPvCt&=
zA-lZdCb*G{_i6vF2QnGiQgEe1jlg-y%)XX^G1rahx&2Ym*NoKq8o6_mJ+u+Z4S|t@
zbph#T<(<>4@vd@mT?k=icY0YUdS04o^Rn<O<>Z&*8s1(bOD=6ssu`V6rZ2`z25#Qy
z{}Ai7=N{pIVO-5_jMSFOMKHoT-bz-S7FMm;jp_C5#8O5Rg}DBbAIZ@~{4SjmH>V$`
z&~|<8S1$+8d#*ag;+WU*H|$f7)H7mb!j7A^Q`#2pOEa;5;~{2HYL~k0MVLH}d)eMm
zT^PWoLU3H(*<F0pOWJ#ErO75mP!rWV{SJscIEnQ-HzpscnFo{1_9}j~$K~c(j8S9N
zL8gK)VvqXv6G$@H^4VVI^<4c@L(6pU_SA;*h4b$XIg=FylXb<TPx}b!_vACHjP9#t
zLzQv&$A;g3l=wEwqGU6x<@Q%fG_XAHn9i>xN#(;FGA=zv-SeR~H{4FjvQz&!(b**7
zt5&p~JEkm~Xb~tl{^?Zt>B#Nv-dgv~$(=3xd1}S-7*m@YiBIhnb2L)jX0|DBh0c04
z*X`9)hFyY=VLGj~^cx4tkD3onU}xA$dvhIcClpuLdxG=UJUr5FkEW30Oj(&xT0Td#
z(iO8REomz#w;%B&QNGtio=oECPUIJ9hL#Gs=8#W-E5BuCRmkmI|Iz|p=DjVM*M}GP
za5s(e6rA3F?Bkj`L5e@(@qX>oZ1#7|xm6+4d4<Lyc{L|B?r$67?Mm-cGZ6APXee3E
zv!*kiVZQmbjI@sO<vh*1LM|dVAF7JwVEPCx%V@mfR&r)(Wsir*>?c<YSu<sM4;hE>
z{^|8&FZYgUYeLVFHkE99IV-*D1Y2zm5nemIh;FZ|YK)vI|0Iwn*7)naItkNJijar)
zrpfTQvUPV49iORi%??pX72zl2Xe}E7DKG2X;$!~^N$>VQyJZX3>5jHC2?dw1dSNfT
zQ)Di<*~&g(;+IQ8#p=3xw4$0F^CY#C$#b%piHDpuV(%1zKRHXQ)s-w;y^j{+8uYFn
z$8!_*>p7Dy02OU+x9k-$)oUQLF4oLt4X>~EmVlr0<-LR#k)-(PbQ4`Y=w9TNpV)O$
zyWk*lvDHc}X-4YfXi4rRtXw!9N8mh8kx~;c&VK39B(aV9625U&213cLU2W=_w~b|%
zGle&KASVk=u28S%4-PX`)X4u5DsXc6MO*CgVy}cNP1E<C-Zcp|O*fu#t4<>@&G&4_
zT;2mzFApK{(R*=kO)A;*2@PUmsUAsNB2}eAqcnAcMDdq@y{E>pwm(MOCIzl#GZv7_
z8NH^TK;qI!6^)zYyCz(6UJoJORaKlYgwyoh>{~6*<lpA^EPE~9xa^KiZwjkRWur5U
zPye6~_~t=bgs`!zvhE%BTKrh7J4<Kfm&4{fOj_s`;>W$ChFT(ggz6z|D|k!euF2w|
z&KvU7fO}~uc)Vo#1ZllwOqWkN$?TbTj7xIlW>*D2lWm`9*$`w2^x2EKiJmLnQS*?E
zrEyDqDQf+BSi$zF*?Opw_}O+@M9heqU59Rz^Zq{HFC$5p4pEQ2Yxs?IPr1Vjv@@r8
z3N(~FWf{|2l(8Hk0mJO1Y|Iq;yJfzU{xVejnKr9dTrpkN4~#ULRCS4seVUF!eBzmE
zd&#l*kL3$>%CaOy-g093-(Sm765<J34)0X)W$v@6csQE*#a^>ct()DT4ZXlMF1^UP
zV9XFYLh7qoZ}VVM@4{#e?EuNp%ahIJL{?*XFNT`({;jIzI>tWE1R=4y_2HzWBD=lD
zLpDMSQM_2b0L}TGWQ6D6f8ftw!me=NkM$Ja+Uv`N5ob6jv2TQO9y1r5X=RtJQwbd2
zeP()U<7gbqXpPtFE~>fe^-fKP*tnp!IB@AKT@TrJiKgj6mb%zd0;c=x4!71vosiZ-
zOMZ8ZEjEwQD3JNV(|>i!1OUe?-mX(Wp{(X=EU2$%&0nUd!yI-CccY-?V}_xhd?-&z
z`P22X!gj)8d!1Q9kIfx7v=6>A|J=M~?c%}F+v92NH5mnO-VoyX{eBlvX`H|e6UO*o
zk5;*plAmktV#Y(FIV1Ji3de?9pKiZUQIy2?fL?`rS}ps`&OV8CN?p!@vc%Mrxo(co
zX+7LGy3G%Hk4I1bxi5bAq#EI$+(r-H3bK-_<NcFVuB0W+jSj8;QJSBpV>nq`CO5Gg
zYkW*y!Q8E6xs7B4X>ZroSgddTOiG2SJ_P6ywHK7#X`g3et4b+8&BOKklM>Xci$*;M
zX;393Kfmc2A2<$7Cm$rti>v8VqKl_=#5O)<l@t3%J7$wDeOG2!VPoj#^Ghdd+K*UB
zw#*jvl%cORm-An@6yT$daIzSbx9F^(%vzMQN?X-BBmUWY-0Z64OI@G6hD_==`6n%W
zsHT>et=jz$ysZ4(a@5|tL>srKN@mcGjWlY8xAro&563^^SYT84>twX<i@w&kywusW
z)l#3X!{JNiCSFUh?LlgtQco$R={!4HAt!gZ^UGaQpLz+OOCmSQ$`KjEW<zOs@q@3s
z=i?`+72qJ<R#PJft}8;B21>?uGOOrWkzCtV<-SMvl#3c>y@iF@0%Qmp9BuI5buJ<$
z7n@wXQ@e=M8%D<XuZ8}5zdk+Wt1NSRr`6e@=9VnLVH627V6HQ1z3}xLWkQr{7M|W;
zUA{VO#Q%WD;&IiBE5q4_{cDL?14-Aa!v^LL5`{inB$dZ3e@UwEwf-O^BUNO25ZF+$
zWhb6tI+!MUa4^5nWG{}RklNy24RhPI)yjMzIneFHefg~2QKd(3o><`c?9$?Xtk4~a
zgRvyG=+20P!%ft=fMESEGcP_b;|(#jzQj-f41zjv0<iyV+OG6ikG~cJHcxewtL}o2
zfol0So6+OA&Lhn$QL#I=I<H4|mMhdR`?$HRk>OpvVopf^;q#+sYda_+7m$_2lEkNs
zEPIWIrq#}R2eXN15KuUU`Ljvkjynn1__t(G;wL|G=h>GO5oupBYyIs%IJ&mPwe2Cr
zEdO~%G~h%_*$elJ_dZc_Tr*UnaoYLNzwai^SR+A{WOd81j^o9{Eq{Dt%<8I|v#}t2
zG@6i9Ezf)3d&G|ZXrHv*TI1)kT(ph;wryVKnXnjJkIz@JvBD-~(9eIeGExhqC}AiU
zK&j9L9?)GQY2_3Bkr9hy;HKwC^46Gf75~|IgQ*Uvsx7>aU8SkWmzW;7e3(i|MQ6Qg
zWpS6FY1_>|iQpF@$80wTo+$HinD{TkgQFVZ2?3o)@~^M2B%K|UZx~_`UpSOu|E;Sx
z{wCMl*^F-OC&y5QiZI>&{wZ628ev}j{q^%7BVO3Wrrdk~fs}Z6wCeO0je%kJGR4Em
z_bzgU$=eQCkPJc9#p1gIML0rk-Te<vfVvG?Cbe>yv?b9G4*t;3OovB}Oc!a^Cykvx
znx5@D_7-pFHQ$Qyv$R*FO4b|OP@Ow*RDJonGnM@_hW6wb(@9d1ULs~GF>?IgD)*>7
zmFDai8%`)X;-HEJ#f(xk{p?h~*HAJzFv+}PIJm|mCo@LJ_k&}J)c1JIjbAch9brp0
zHX<c_zm|umz4uxyO$W5=hR8RXc4f|I>fkYJjuYRhg@uI!LN*SQpvN`w<NZLj2GI6T
z_}7o_1cvfgsmkll3R<a)Q{HMm2;00KiCMjUtz;N~%z3-l{x|U?sqc+SfuFC3`j5(g
z5-@M64s5TVo<F#;E&9~uhDc>&+jN0e|IT(xmwVAODfnmFB;C)K&&xMt_iF<==#N$^
ze!EsvA77~5v&H1U#T#cAqx{Fm8mkZB8sALLkG8s_@yfEMRab&ruJNs0J`G*T&s<Zn
zc?X6H*+Sfk4~rUE-9r3XUB4GB*p>!e{=q<$wCGow_My~t!ToSkN0_c%yeWNQWG_nT
zW-i5re6szI&-0{pXGt4RR|>jh7>>w^y?CyDUu-uc%W}g+a35p6?UGAga((U4ZmARP
zqC5Fnjw2%7{-}D6Gv$QZ5i7>3-NoR*(qJMfYjuawHLz)l|I3io%W<3(Z?S}YnNc9V
z>JkfK{eaAv{*-N#S6GR-ZymeM!;u3Ymbo;5Jj(#&%a@-l0gm5s;~bSAy|dAKT}6E>
zW^^IrBy)+IvAez6jzfnU@K_N-+Ru}AK%-)=ywVGWDTJaV_w5^^aJgzsCw`WyUF+^^
zvm-aRxSLm|)QFwlJpA3rBtu~GiiLUBASu8}Y*)dll<rWRfvD4qY<hIsc6rrpyY!*j
zk<h@hdQ3`k?S_M(+xkxa$wtApA##D-^&_7G9<w*jTVqCEr#o)$dPt%0B<*JrRY(4X
z#=@%t7B{)wtpizCDNolmeXe^z<Nb)r(_H-ZS<zGvdp9OA3$^X+(K{_YbeCRQ4`@0U
zcI+<JTQA_(TMMm*alpV@0Xn8zbDW6THDK9bMa+J2vFQ&)PWkMee)yRCPvpu#dkx*G
zRA1kaj^q)sVJfn5C0_Ce<Q#D+cLdJG(o{>G$euMgDpg87Vs0<@@?-Lp4Qp5xDRJ;|
zyNU63dt7&<dy1x7j?MZ>ok3ILp^SRVstDes7d*EuIbl0RjDS_x)QkT8au&S^>uSZ&
z@g=5{ji=?04|rL*UG|>PT-veC$$6`G)iG>a2=6WtuC?!#YQ<9`e8p_Ym-r+i1+c2x
z;YMhVz!*i^DL{$Sfag$^t>UZ;QBt-}^;zWmgC}bAem3%nBsId}P>D^J*on_~e$F&e
zqmP0oZ;3VDYOB`2___j}e$U!3iX>Zo+<`#>?Gs)uyRm@CA50W5>1%W9qpjs#Op6yU
zg(jCRt9Mrtggm9#S{!*sE^tJu&sFC3^+0ApwKh6KkZ4JHom(B(3UvUpzCs>o#7*{@
z3y8+7xj@k@<<j0pi(loL(&(M?{9mE@b+J>pl8rhWp&Wa>*`v&t9z0lKdQ8wYgo*Rj
zwRvEX9E!FIYyYbv<Nr$ka{p%!-9@ur8s>5xezu;!m%6lPCnYDwdl6K%z}i45C_bJz
zlZO<jZGc0>Owo9wm}ec2X>M(u0MRXo8=e&O200A>gNF{45<ZXN3t#H1(^(F0EUpMV
z^Y`Lua%3<P2W<f8Dc)c63l0n7S(ic6@!mVf%lk<osot{q@vcE@s^d2OzkbHm6{@=V
z-MI7L)VQ(i&_Xf>IxNsNKxTX6!+-nH;jd6(In)Dqh-T5v|GDBH19e~MLsNo0;@X1;
z*xXDz<w@CAq#zv5q4*1W+rGZOAO@HKdj1qN3^}h{q4Ne=-VfkxFE~nx#=jnK44eMb
z0hB95S$6*X`O>PD$3+(J^{YLhk46K0HVX?rpu^{P^f@g25kgAazz+pJEGhKGOn~bO
zb@>iiV6}!qae31e)K6UZ@xFybBWy?8B*3(gfOb4Wlhgw#sZk?E?g7w$5V<B$87cf<
z5D*=o*p=M1liFJBZ~T``70^QhFq#o{N%b?58eo5y9PZA`c#)PnE;a+Vli)}^XRY%s
z@Pj8Gc0g0xb<4=l=+gP~KGlbtxo|g{^1*f%rvZ6e+x#BSxt`plkBMQjyXljC1S^Q#
z4{nA$7&x~XprB^-bR|uu9U_JcbuAD{AzY4~l7^W3Q>LgYEbu{p0bL15!q6FK2VuxK
z@QD}tz61mPAAZAPSvq+JsBE*n1s7!8wkGl#Sz8?RK|lQ-k*F^G2?xq4aCc9g6-8RP
z2)Par#KTfsE?752b4J4E{`q%**E@M4gcbwpLnWXQ{i*hn134-iNT>{cez<``q^>VW
zC|wu#0x#eUdh<;RK{)$hUgwYFfNjfV1YI5;>}eKT>H@u@K~r7khK>$1G!l*-JBC^*
zu0D9J?{yFj9b{&2V2}&L<RcQemO`N30#5|9*8SKDAwhT^?wBHyHek~sq`!ky79j1e
zRcJ#$oDPHltsokZ?hN1CEoruT44j2j=FJ2lqvMem)TbKGT5Uw_?B#WVh7uY)Pk(+O
zhC5yvIXnV(PW(d<&Gd+@c1W+2g92ccPaEhjU;FP2EF$7729SZ!T(~^}KDm*hUS00s
z-Y193$+wS#7I%Ukd(J1ld2<ygfKPv?-^J}of+z`SK)m1j^k4EcB2qpYIy#fvIO*8=
zT_9%VPJ(M}Kyh<%admjK$D$j>nM2)Wj)*9w4S*n2wtru2n5-|yg3WXLeTGhHzJ%MB
zMb3Ojf`k!x1K=-7Yg#x|V(W^GfLD85&~0l$sDS|?%M)RtedSgJ`r2rMR+!(Q>M^f7
zI*Z@ifRl3zbiH}M*EQDqL&2uvp*K9~R-NLZ!>GC4lMJHLDOm4KzQ?0~c7bH3=0`>s
z(mA^k#U|z0ikbo&--v=scc>*weo4+u$Q*mt2qx8L5~GU&GV^3-8IzHkib@cpuyFu%
zfdqlpHT5YoM>xrSEf7fZpxng*og%J<zr6Jr2}wLOp5s7KG;A)XTV^i=oI5n~qVTW3
zmwCTU`fz((uW`yew-N)C@~05Qp-J?zbg`&EDCH1nBxvvH>80{z(FO)0EU*{q5v$_n
z<ot^8mZ!knk>|Jq+9)x|Wu}5I<p_edYQ1k787@#NWEL6Fn2^%>oN_gYMAH3yIwe1#
zv-TS(F|ojJinSapn|#<f5Y;be2N=(&pcf$ytQ}y-D9|9l?dYl1rt&k>E&_sI9MhF&
z6Q!PD@~P0Cp91&6qe8cy@_A9*Wi6TU%CjgiYN6TL*#-uqA<w-<9eo=AdP5Ls>oRw>
zY1$NVh=E|V1k@R~?q<3u?>tw8{ZG&eqMBP^>3^RXq$h14qFr-WGh@|mpgp|uu-dbd
zpcNDpBRmCld0&7WMMFhp00eAl6A+FeqriZJ#^odWheuzY{e7M@mmgt)<hu2tQO|~_
z-4Q704JZs~)KX!^Q-Rcz3hZ!%#KGTHhA}qAf;IsQdf8@>EX0F6dL3A*STOY83`VV>
z2zjRGJW5<(*2x|D=8ZwBdXgm}Az{Ten;3pwHRxit0l}dSjII^<uckn{ZUt6Jh)@Hf
zn}p4cMHYOazqrF<pyVgQ?E9v11OoYZAm+z`*1eut+W7~lWCs|=DbUa)m;#2AC<u5l
zz)hb5DfkqOL<FRKSAf5?`P&XMIoyHF-a<htJm?gNSw#Dbt;E0$B?02Y3EGX+5NPH-
zxq&umrj5j6pCY}`br8<R!uHiE#L@E>8)CqejtjDR?dNH`z@N8Zv#P-h7+gjb-E^i{
zaC<2T;Tv?50&1J<_ppwP<FemDaAppgy;W(v2P9T;K+DW~FdrY|TQm-QdNc?Sg}luM
zO7gU=8X!oi0Z++R8c_kaLO55=p-y$~UsXhQD=5YQ4;6f!OS)XW_<bol{eE^F$Onpg
zOKd(Ori1KxM5&as$KN*IjIFCyM1<;~_M6wj_!-TE9XD7O$3xJJ1Fs$nZY>T3p^P=4
z9r(Ro!lRjrootDTM<hj6e?Ul-uJG4`0Y`}30CZpGU=zk5TCf87gDFrEErGQ6=$S*?
z(v3cd9aZ=PIA)=De?94FgU{(70vp%OufQYewj=l4_^AkYJ{!}bwXiAHfQ3Nm;%b~v
zfB~Nu<BlU?b*`BYb~QFmb{X}fmu>;BIl@TUd>IQNg`oykUtsw8&PQ80)F0r4Ue47m
ze+zOnyDly5a2!sLy`vOlBw)PXBGqM;!&qfhCM3vyfhO@A=!p~{(lE$*y65ceZT9Hz
zfQw=fd3q=Cx0nEI9XN%ex6q6R>B2*t91E3NI(PZ<<&FdIy{)y<=$Myd&lHP@NGN_3
zn5qNqtsWw$YQ<qMe^)4Y;u;z34#JfI0xmeWXhbUlu44L6Qf}y_i+|iEU`Ha7%+l`8
z;jrwuE9Uvuqt}p-1f05{zegwhDswRJzzTZ<u<1-urH=#U2Hd~}7*B{o7MPIfCVk-^
z`!e9x1|0jJBLNVS-U)_6-CquaKuNrN_pT1GF-v7-IXGUNpyB>e;bMm{l3_=I?M;JU
zS?$Y#0Ib*1m1m^rxIA<VcxuQw1~B;|Pk(p=ELmChI+7ZG5f;2w8q;4=1YEXA;5%wS
z3`dxMuzO^lL-&pI!iCNpU8#;OAhE+J8VUwJ+&BpW*PEb~oaszM4pIS%A(#I1ru&v8
zC{Ptq#kaj3{}cl<YZPb&bl5w}A;jcVAG#uu7x=wF9!JE_dqC<u19$@F&t!G%n+wHM
z9NLruVuipLpXbES6}O@}5rH8*z)OGs0_W8y{}kQWR*sE=OSm8`oIk-Nzgoo64>aGB
zrLuYC%mO$d<l@g=(-teKXFWNmuEN?^6a~M2-L~q_q;gc^TUUvvzx+ty*)v|ywZv$b
zYK3Nlss@n)+fI-|?TV9+F9iGoH4RPV^r4jf45|ja3`qT4PZZW<i}#23uhKIxC_$~n
zR_0LUQ%=n8zB3$_fR%LM1$X=rWOVm{6a~yYx|!y$aG(RCE<o50uo~cnCXmxe06Mzp
zspv8%xxt=aeRQ}|Psu3bDk4z1aT@X+P9Rqyf@wG+!TCA95oN+(5~%@tYB(l<3$&%2
z(1`@3;)m3s;43;C43&3E7h^%dB?;>~(xt6G38$l^tR*0nZ8-5`9Ks!@?&S%tHD+S7
zn3hR)e*REU{1iX{0KjZJ*v?Q7XVR2FOjCJ2;d)n}%_wC0>`e$Gu;_5WLU(~DAVGk>
zz=geM;n04|rif?+klsgdr-hb-abS(kx`7%I01RMl5SZw=G%%}G1$0k@7^XE9JWfW2
zkE=M?>PKQNK-SL8foF~Pk$n5)$#JM0PJu(BKNSw(hp?UGWrRk;;!`+h0ziOX<1lO{
z;4bQij^}dD_kn490=-gNz)Uai2{Cej0%EzB9~A<eKE5ziDb?r*w8{3of%Ll^>gxAE
z^)?G1BCrkS${0cc?owrt#*yy>_;sSB!<Y{VE5e)?fzulxT6MVk*UN+R>2c%a;HbBA
zHz|NKXqE<ILGBa>^}f3xIs@WL!ch?I?lCRK&!!!$G>nX9Ok$Q6a0G}I>==yW!XHEA
z><8p?R@a&HMj=9=Y7~J76NcR(;=Kba(F*9LqP=!$xO&*4udoTxcBTSyz<}u>FC2lI
z+|hmkoQjh=J6v5Y;k@#0dK%_O7Fjvr#r|S3SPV1-fz?l)aF{^FR<T8|FcB6oGM$@l
za9=1q2O1de1)c}41t7mFu$@%tgw2F#b|VuK7J9Wia5A@mu-FEPMk~D3VE4A_AFk1>
zei?^FMT4gm>CyM9+yOUPsfYG5^A~CW$JPa;^#X8R1#WmtG>Fz{XlbL2_QP^RGkpuc
zF&Kecd2S&ZzXJkT+rgM>w#N+&Fh+}lXI;D?X=7c7=Z=GibopX4*&K}lk;~u51tB|9
zQw6rF<kZ{8mU;K2LWD4&#+%A-;YaJculn`o8Tm7cJbi;;La@h6U7!W)Lzqmz5r6^N
zN*n?%?8w2CnjwRW2fSNr(O=XCjN?D%SF?nsNl*|6`ry=;dc+B*f_4!}3`H6k{vs3b
zjlIYkAh4nWk}d=S#V{`<4DU`~!C=4}>6yTapds2K(rpZcBg{aF4H7yb1UeVFZ1tMn
zg4o{{!KI3zWrW}vGH5A=9LFToAoJD~_8bOwItJnk?vi-{iQ2Rxh|U^H6z|Fbu?m>R
z4fj6XYl1^~x(dyE+L2RMreNa&-~)>OvP0~nEkNvc(tD*K5Vacwf>l-Nj4ZOHA{|XA
zG3|>NgoJ*Y>jNVi4Ytf1?t1163!G^bUkc|BApr0%`UnaV_S)+ow$(Y~28{I1YA-Ju
zCZ=a_veqpalz`-$eztxgNZ_RPVWky|lq0!g;rtPr)2E*R`5HUlrB)@K6Vl}MnAL4T
z2uVPoXlXkbhOBQ1N$Aa+H{)PNV}VT_8>8piWNt7E+DJ8!j=ruR6-3~3^QBx7$hq;m
zUZ1Z?h1lrN9l_xsosi~Z!7X;e`aLO+%Q)u%UMn4F*=}kGkh*i{4b)aLc3@}EKkPwF
z_scUa;7b~UWI1MBW0GID42u8-yGeCt=Mon{6f%ptAkPIoWAF(|N-@a65&pEEHWl5M
z!<|!TGcz*`oHNrfYK{H;S<nuS7l;Q!`R_}u2{LZo(y$IVM+BTeoNnA$?C)V1$Bm7E
zcvcWRs|b>ZASpm@#hQwzJ_T&&qO8AE`J@>*Sp*UMz$rpiIVyQAaM%~99FRko5Z%JJ
z{0>{Gzx522A;?z2^QVCX8YsByP@0IqV!scAO#X>m=zn}k57H$pNKFui;S8u;<PJ7y
zAT{F<6)pOMyPg&cGxqh@zl#}xB>I2mgp{o#sfU~`^PRD~aL^n|`NnO9oNETY{|AKI
B(Ek7c

literal 0
HcmV?d00001

diff --git a/docs/_images/44661da8d7b6632d7323190eded41307ef7514e245c37c044cb00987aa2adae3.png b/docs/_images/44661da8d7b6632d7323190eded41307ef7514e245c37c044cb00987aa2adae3.png
new file mode 100644
index 0000000000000000000000000000000000000000..2629acc290267807b975288950c284371ad7182a
GIT binary patch
literal 23142
zcmeFZbySso*DksM0Rus4q!a~2x;s>)LrO$R=?3YBM-h+`0b!9UC5klCp%Ma%5Ri~s
zv~+i!dHcTKx4*N`9($a<&l%^h^NhjED=Y5%{>7Zvysm5h!tSfdUp#;1JPL)nsHh;T
zi9+G>qfj`hX9?ghb9ozI;g_iEy@#$^jux&SCQr>#swS>Zc8;!g)=#dwn?H52c68w9
z66WINxN7C<>f|EE&29gmZ{Tu#YRNr({%i<*$vGzlJr@*;#02@l`5>KRjY8@5D$3s0
z_DoqG_3+egI%!$oWyuu2dgI!)YwwgPZr_tl3VnO?VgAKTh4qg&uj=2<4}E*~C4Qdn
zOvs@4q)x&4hce`^C}qSNpI;%8Rlp5;eq-~{)Py<nRq;@VqEx}$5TUz8*U;)xT8F<!
zCx$MWxA`g)6Vnq7h81ENSy|aki8xFs{FlXsz6}2<Yw=x&m)~TY$-#>ps;v?5+QX#R
zH1JxH05d=GQER~wdYOCe?d?+yL3n5I@l8sGM(Cs9eQ|-jFCrp{-oJmpwsx~_HLH!4
zpOBdDDho^Vs0qBRK(jPjo$%++pC^o3GqLEmZ?86-JUK&1SS@-5zMU;>Ys>Y?lP7fJ
zQ%$)Wtr)bH^4G6ll`N3k$i8t`Rsi+z|9VHIx1=qyZ$$7;Pfx!}PF`HOFZ+>PU0vO#
z@54Lu%d(kwbPml}#Kn`Rr_K2I`A6wrD#TB(uBw}v-547iTOqzD`|*QKDrS0SCMGd4
zG$)5uLqo&U$7hi$Gc=ak^hamsZ1=mnH&|GDG8JPtxqO+KG%0_Hp<6pUS-82Q6BDVA
zj*my_qZHz&=H@~Y5~!*@R^ei_Mn*;+Avc(GUiq^G`E$P1zUo&eoB4je;O|I2DwFEC
z0fT7nO09qsg(?ejy4olC?t>*V+DeurPGsGr6}VP7BLqus>LLrsl*GJN#wWm~4V;h>
z*qNRs!#ZH`-oCNDtJxLtDm8U^<&vyy<E@i3S5S_o(j8mpcC=I(QG)6Tm5Hy>F7OPP
zPUrm&YOP7?*w?QMhwShjMyuTLjQ2NYT<3f6rKP1|z^Mgo$XlWrJ?t2%s9H*`d#U-%
z&cfP@pytI5+~1t*EjCy7_4N%651*=>OLJMUWoKg2kr8q_=X8CIxe)&$Y75UhCEtTL
z)k3T#Osldqv8H>bt9oYLaL*@UX*o13?3$?Pkn<__>oa|~UpjEv;PHUdRKr^D^+qyv
z9*-4$VtTR0<K6Kt<fq1KlWtgI6T>fY@FznhN#I;yneD*S#n0t@=56E-)yqO}xQ#mf
zc1Pu{tZv?YLF8=n_?~RzH{YPJ;5b^W308OD1)ec~);ww9TUbnY?%YvOR=zGGB4RY!
z8q2DvqLO+089`K24PS}NEk8b&FR`rZJ)a*7fBW`rZ#Cew{nfR*Ynz)>+XF@(60-?L
z{_kuD^68}g>0m-9CnqcZybpg^XdE=fi$_3&g@wWKsPu=1kpGeA$!`5=k=N$zhM?NV
zvTstBOixVOgVdV(3eJedom#&<JdsN9w&<Lgn`wR1;!`=})&69#(8SEltk84)iG+m2
z!)kZVYWL+yczzFwX6mU5*Snju9XJ(xli{1omW%zLw-yJujr4NVQWGV8geog5J-y#>
zN?pF3`(&d{&j=?Dlk(l7BtAE!kv>~Bx!GgfujQl8r?cnJ<1P&(AIwRgwtmpaI4@D>
ze|!*iN_ghX^e6si@(L~;iq%rG%Q3|t@SdZrgZqL_j9i+V^433d;$zaK(_0t=QXK1#
z-^fK?5p5eTvu&B}NVXoSaL(Nscz^GL|NcyZuX%d{caC*$_Ch?Y(fVNAl0cKeme!OB
z987ascSYiBnhU>6t;wDdTzvBF`MFZNq1Vp{NpP{t%N@_pkyR`ew^NHgy>VSG;_B6_
zfuA3j7sFT>de3Ju?TR{#h;UU-lcsr2o<nB*LEgi!?cDX4PX%=gA1%T{Ln)r)j0QRu
zs&|c@(?<~zB)w0gVM7br_P;`-TVeSo3fU)R)WFnn=oLTDQcl?TaXq@b(#0}@SHPw(
zbl9Q#^Pt}s+kq%`sr~1$DmGyiUZSCCor;#uN2@R~Y2L?cAh9}|iFbQYUGf)f!laH&
zJxV4DrF8z7TMMY2cB&<U$w2C>JzmuVb}X<zb498HZHv;Mh-HYbNiWq3ab;5k-h;S0
ztr?iyn*IZ2hriO`FKAEoufWQjfNRI`enr^T{_kg}`8u@%Fw7d$8Gqxg5*K+Pg~nXa
z<7^A|f9?Hn)XPW9Q~AByT-if#cTAd3uQhDS;O(_9a;wRvH3Xzfmr2-s^&1>Wapv7d
z0=Ysi-MZwr-O>7-uJ=-<ex;m#2|MPk@ya3#K7E|)H_^FFRc?#TiM*zCyHk^su%f<9
zoqT;pI6qXvii3mGm#0_qgRkfi_JH+hm7t-a;fT}si(EcqF5~j-g-<X{n(lgfdcJF4
z3AbvhSlM;+r`IOFA8oXAyRMF<;$NV2TIgd-XvyqV(dk?G^=Z?9#-~3|?*=PtiT|-T
zY{!=zB_A6bWmhWa7^3LKn}24=d+iKaR?a5bw$;=ZnYQ$Nv4325yz>|r4=<HEcl0&0
z@}IF<arr2^)&vFrll?hQFE7#K{mx&oX@7sQPv)MWfV2U@ox%IhyE}``5j1zB86-a#
z)z>MTKDF(_bV;9L;7QcAwaJB&Bf0DLn2c(9U$ALqU!tH0PETiqSZE4cZROk-k;(>A
z?DyW&*(!eO>cT=Ei0t&cWTd24<8_j%Ndng-Bx-&X_dJy+FiiaO#|pVc|Kn|47PXWg
zj~#1u@{gHs+;EzS*CnN=U+yvd^t;TKjC}e9Stk<{v+El6wpxmahLwT0w-_5+zL8b)
z=T^-6R7>UBw+mjdkuH2r7j<EQTb1ChKjQnOTaXPgdTVJYHX>qE^{L0Zt|Ft@_u}2B
zTlLO4?d(6`lQaTWmx6+VWaZ>GMqIimJTXH#Xb4b=(g9MdHJilnsMqekAb&*g>dl+x
zQIBy|PfroZr21Yn@pglSUyH_J0J>qI$9y+cuL#+NMn{u0Cz3kuu2ip*Qc=k(D4Z=H
z_xGvW<%1-blkT6?97#JhHFfv+VB2e>m6d+`aCdd?%dkVngU^qizj)D8U?lze^=s7H
z#>Thr-=95ye#S81c-xl>E1~<~0cD0<B$I>$5<&ATCeJ@8FuW+EsYwcV*w?51f|&kg
zhXp$yZ(C=l#nIk+-zVMZz(ACk>z@Xgc)D#!r?Ur(1vzk?GiT0pLmH~vpQVLsA!`Cv
zX7j6U_kha1$_c_u)ULRY(3?{T#B^e=p%CdVQ&THI<kTy%h%`-xYpqmF5x>vKSl`{v
zaa-*7-J1xBI)Fhcbe-2U^qj!A6QUJL?pPOd7%C37EvS9d&>#bQjatO%Y6!_`ZHlF0
zl;q{y-<<<K`WY{1)eaJsaCt6JayX52wYT%b_X(;?ZpURTO}ECf+_=$Lv-8`QdCc+A
zqa+-aM~@x_Rgtl(C2~Igk_f-!IRET7Qz!GjaB=w3TfT2Tyu3f+vs%j{CiWXiCw3zh
zKlMFE-B@^dx+54Qf3GJF4nE|!?dLF!;ALZD%l23uo9%z>DA?NCI{W8mM(~@NnHjWN
zsu+5)pnfdRu=e-TVA1yoTH#KZm?U^?_*k^$PU5+<XL)M9xA|a1_-TdgZmzq-@|n#}
zcHpZ&J*nQ`pG#MTt<X__dh95VnQDm^hQZ}?tlfSyRA!r?_r(s4=C_REZBB%jl37%f
z65rhoNs6QuPC_2)<oGbzq9X~NmxtV>k>7Uw{I5?5L$y90MFr!Kc~rEu<MwBh9WjtW
zIsgQyetuM@Vq^0W9)TBrSVTkyF=>*+5F?T?7|fmB-ui$57uXib=>aE0OTWw75j4=;
z($a!F8nvlPx|E+vSDIu8tV-28cmCO5_*8)D$x>ETQ;R}N2h`zUc9w_f3+j2BU6+5C
zH5@{6wcq@0TY#n)cTa?o9ss<G9;@|9hVb8LH(oc2#J6ln-T>*ks7*0-euo(TE(z1g
zsVU^^z1EwkB6D(b^eUfb!2o2)M<+qxO1gYqE)l{`Y)XpV)2B}{L3o5JsbX%J#xSyu
z{?Cs)Ai^T|sJgo{s_eFu`e`Jc|8lPO&eD)6Kn<e%Sl9=WC641#ITGs5<KuH5OIuao
zS~wW^+=gVn<9MA#_uJd|R_2fe#mU*>JY4PJ*mQ$mv^mjAizh}@{9Tynu?TD1j~_e$
zV`np>rJlxRWoKWJmab=tr7?||A1Fwtk??e?^Gkia^PNOG5sNi;*_dwijkfLk5aV^c
zJrK#eli3IWJ~J~j&RaYnARsm^ZRJD2pLZcDA;k0%yv><8Ikb$7jPe^#^DABEl3;>G
z>k1=zS=iaz_xAVE!565K0GM4#?y!JZX9-)@_yrM-<{y6;9E+No8qDEp{p!v3&Q2jf
z)E2WCbX4)HSC{x5$7=5Enndsd+Tnx!wlrQZZR7<J8yUDr-sVz=(cda)zO3%$fP;Bf
zyu|DBQPb?)9O%l;PI3C(*x1;M#teR28uCLgDcFgOU&qFVN9@AX3QjdgvTt}r@Xr2}
zXB5;m@^h;z=1)&w9xhMV8x&7?O%wBxnU%HWXze>mb9+0x5fel+(>I)t->j~>dd0Dz
zb4&38Nf;!~LN#>q%LDfPAS~XP;f_S!XSrHA53KA^9C$kvT8@QASNv$YJG|7BU%irX
zcNc;c<r?=Z-vC+u@jl~#IA#WmOkwBEvP(Npo;i2!T-0GvQPK0@;CS!qii!%~soPA~
zuhY*xD0diDg4ihOy>*lCi$S$J1-1IqjcG+vQqqcpg-@;R?c$EKkb6Yj7RX^$J&p77
z@^YTfN+^a%v*{4f46B5vxf_s<?+oPPr~#9{4;n}ifdCTvDZlDvvSS@u$o_ZSo@l3t
zPcnac2rNmeo63rc?;x>E&(3c2X{oQTw=k9jocb3R7yoE$YZJa&!-L#Eg!@~r4K8=?
z;IgWvd?++km(Ba$+Z)TCU-6G>ve0^``06D_#xCXr{cnLdcu*01w_vyN!oJk9jz#l#
z`e{V)Hr3sSC}#$HHR^DFe!j7>QAE1Xj8!`Sc?56g=!D+J#ztsF1V(seDx!q&YuaJf
z!=B|%$u66cA-Z#+>FMKMrnZoASL;vxgQ`l%K5dF_9>nid+~Qz>qOL#RAUr3>vaX81
zwE<8Egc+*S!|~IHrB;{uEihOpPNsqg8E&p`%A5==t3(9Hr+RUw`>cq<^fWCEl^}Qq
z5KaUQ|BI!irOhw%kXz>FbJDr)Qvv+zOr0}i(v|(l?&#>4BxK)4rY><C<{0*ugW{9U
z53oZaLgM(4sG6B&W=JqIXURBr3_)46w!WUbwihaKdRJ+?g4AZDf)_ATo_=Ky@AmSK
znCmbQ&+-kb-`I{rG@63&2Xpld*24Mm6+6HcU%R@Z8U6QyCccMI9ndib92J=cI_n8K
zj8MaE0LrF1*j*(Vv^0Z6maT1@rSJOl9!wylz&mrDso}o*Dk?;~BQ7M!4>IhXDWVc<
z4R}z(;=M{<Jj!)!f5Vw!RPR6HHJ2JFsW?>W!rGB63`NH9aCL)AIe=iO@5rdAbpN30
zUP|o9HYV8#CEM1ybY=8#B@Mj2jknPMxqY%JoZftBXo$n0Dh_b?NMuZEKTT-%pK$x3
zz{K8Ym-mn?UtFYZzDpw6NFsgI07VE=K{7DR1h5xWE!+}wU;1%Tc%<Q5@C8LBr6*8&
zLS4r;ZbxHj?;!-hfJG&-VQ+m3ZqY+QLBV*YEgq99P6g|W;C_x8{lWHPOR;&of{KdS
zd`}kS#3aANm*V3IMlv#}-7z0-63MMg<9@sJkH6TNG=^R_v#{U;kVCqPR3=2!Jb_T~
ztwVl`O-%d&fYj??J_kugs6+1y7pS;y@bbpMrdkK=FGl(jQZ3*Bqkv;Uh=G%XymJN?
zU!13!ISgwOXWA1=+!i04>~{r-sST%HhC&&tBRPOFAta0l84z<_eq+EWz`2FqqtNEp
zt&_be5=zcTjZh`Fc65C1hK-adG4h+=WoeMtefjrHMLOIMJX)?nwb1tBfF&l87ZO`4
z<ks#?MY3%5^r-s!`YEci$6mPHsMChDiWI+{IhB9-54WaLme7`I6A);&mWLC7LV-Le
z4=AH@*S2J64<5~PI!2ya%=IQb!+Y58P;X}qjujR=c;w47`o&!lwBhmEFe9cDkpU6}
zSvRPYlar&P%`TNho}grhsxaVhV4&n7Dl3g@Z9=GsNl0h`o~QN45A0+(x5dP_;6A7?
zwGYw4jtsros-{pCLLg7??!J%AblHI6g+U(!Ie_etO3xA#BbWt~BzPgvdwYS`Z9$vC
zf6rv4YLScJ;uY<cGUraut)KEpWv*LbxOaHyvODVG^8KRlw7A^Kc0mBI=bG`OQme0F
zWUR0PZg6o$!SuwRBV+0Qq{|JlD>O1P3%)<<dDeSCXfYdw=$CZQof#}2+?E`G&E^Hf
z0Z%gzToo{>TNIt>9T*i)!0A@MKI(*}Uze0jg|yVu({tW;K2^f&HIyb-1gruJ3LJ;7
ztc&s_9X$&&Eo9{rj<-)>(h1Xo%3gDseD~OotDJ>D|NcZP(V*^;!3)1a#~V9Z$`sw#
zuRpm5d{rigQY=RMH%`Nw$uO-PqwvsBZEv3-&IX~k_}z4e4>g7F|E1WnO7JU4_crs2
zy&Ixsdhe8fxS#X_Vdj_<h(;7nWC@I=oi1Px7FBNjEd(`1&Me)0?=Us*{U3#-$C1P~
znk$Tn@h>T-`P76wRnimZ-Mv1YtN;GXwT4$r3oAHE<tHDstb}3_f=>U66aIbLM3)19
z&ZRIF4yQ8-tO5)FstMn$-U)Mdc1FP1U$zD*K>&`o#OGaLC#y!r9rDQ3%uEw(X6%X+
z>d^dp-QMH{6htE+mhz11$7Y;~X!tUFYFL;i2||Dk$g!-)^*vv6Hm@nIJF`ma#x_P<
z1L_-=t5+MG1O6Y>g)Wd*UZtcUkV|Q64`960)*lUdz8g%M7C3_i@_QZg!<9z{w8S^j
z&M!ws^dZ&DJ$=d-6BFaQGD4%SzH8WZm4kz0{1|GL-{p?#u`H@DIoUsJ<)}@}%;?N6
zr!tF)CBgQlBq1Rg^I4S~^IrV?l$js$IaFJcvhv~{qRN)FhG}VOeV-o>oVy$r8mB4J
zO*CkzFdCe*XrPjVZkylil4ga~x-wdg;MppVRW*HmIzY5u!IE?TA60PTG&D3(Ex>KA
zZ}qD8RydnNwt~`F3V?5BhX3iw@re7dJ#6K0*trmj<RO@$Aa{9sdcJz~ssRd$PJkFM
zeUD+AAq?Tf#Khjg!P6!R-9qne8|-SYaBglc5xp3Ba>s+|UwObKcut0~{sBmbl&1IY
zt@kK%&-g@iSWH1kK#~yDa3Yg{Zwio_x~{HHz;5sr;46S}Q-cnW&JaQp(gCvFA?0i?
zmlyV`Bnvx2Fq8t0n2elU7T%-?8KNzYt>$=V_y}0HCW{gvpC1;RwR#z86|ydvwnSw?
zx(5u#2fW<Jy_pf&Y2O9h3x!7EYj(U1tb>-~l}Wjiu;Yo0k!|0XD&qXjZm75^Ma22N
z%3&H55Jf|F1U@0jQx+vdaP$0|b6wnyd%;zZYgAobOZ7^vVumW5Gb$m3sTdo-rIGY5
zo#F+QX94TEnc7rSQ&VMithVEG`IrqnSqCs27dQcE^TS%@g9K5lSL<CiRAd@LBkYiJ
z?&3v37)1COgU=E#*`-Uy5F^cDmstwg4c?zz1{S14Re03Q|Mb{n6IN6*Aitylz&ufj
zz}Gt3{Q77PYm>9Yc7UtIZitWHvXc%<FnCEApat*U5Mn`EVFv-ojJ(H(yTTnwg8YCN
z;c9gU3+%lRKudgfSDqNvYh=iwKYX~k*&#fh2=E{o*r4P`Wj1K29|3cl!egj9ITfOT
zDN<BZ6GEfW!7HpnLj6b~MZ<5A2sk^L%E<Spr?+>~y>LoV2E4?zH79-`c4J??GKT1Y
z0ZP*HpJ&fHfGRNukc)YLFI+`mKLyQa{t{{`*rB~2b=Z4>(;;JIbbP~QV8d1QhY2qc
z=p<^>2*?crfnm|n!p+o3$)pAKoJ+5&F#6Xg-DKp_!sEWZcEevffKN??3;fzz8U0&K
zBIQ|pyw3Z9Ex>p}z-P~vbV>0egYo^vMgH5jZ)d}roD)?#eK6LA4%OE5iQo;7<mIL{
z_2+3`a$8vmM`+vEXugw}4yaUr{``qgiY_5b0@fb}Wh%l#1TKi6v`r{FMB6mAv?9~f
zjbd7%b^^M#i-<u&WW27E^Kc@BQ3Xa%6q0UTi=a*4kD8N%#b#<B&B>V=b671(wW*Nm
z71h-}`lPqI?`FfS!3_2E_C`iWM_>069T=%}Q7y6PP%$)2%i#Ebq5N`|v$M;aAFcMN
zD+VsKL*J!CFzPT6CQ_xY1>)ln;1Efpq3YE-TPRkbDC5wt=tict*5~x3eQmjXoH7}s
zk|Od`z^c2!%+iwT$|5A%3pcLL`KUsD$j8?svE8Q?bpX*64NMtiBFza%hgKLB8ej_|
z{0?_0^c*8hV2^OXKLMbKE_*?(16oTqY~HA1C?|V?gM7N`1Av)M+&!YZ`-q(Zw&_0*
zty_)<2M2vkpDI-uKsbdtj5>s<o|!qwJy`_s3?dbfBJwds@KN^h9Tcm28i;5?KpZDQ
zO}hDo7ybeF^)pwCRUQp`O@g5}+v9Qv$<>`Xu|q!*m(wLZGZZXk=ek2EhRnAYe(kHh
zo0*+OiZhUphN|4y0jzZi8_tc)i4H)_oQKKDZJtV56;uVCK~z+9++_gpeK>dB!<;19
zOic|wEji#g)co`nb*2*(3=J9JcB9tGEyaBnc7{qal}bh{jY^>sjtPXSI#u`!a2J~=
zhpSW{#61dKoI7j$g_1wZ>{ptbyRG=2_o>ZROKpRIpl$rv$Y}h|_|#^Td)+_*Pp7x)
zJ=qb}Ru!6ia%tilxxUftxd>?oxw<W$Jr`m=3Mf>QmMD6J6VX3(7|5q5Bw@$|a=)>u
zNoUX9(zYk_oWH+6QX&&EO4W4F?d?rP)8j?7e*^#w<-{fc|87WR4N~8&Adc+!&$H#m
zv+Gh;1boG(BCl43f_|{hPaHTQuF^UP0#I&+;1Lo7&5GXu#rn%p%VZ&Y&%@>N@D$FO
z<z-a|2Ztb$&fO$AIl1DeGfIF`ab?uhh+)*TpdM~&zRonMl+>Xumn!Z7)L7LIBMeZ6
zu=T_|R+jqaE)o%$fr26d`vtjUyWgc@00OWR8Ykr&A3x>4hlPZ&I<RtIWoF($6eG~@
z9s(8ETP~hlP{2*bqGAkuV-3&>H*VZ0gd3RcOuf(mCC3M?9Ae-(O^1rjLG~*Kc2F*w
z!C+~=&ISL>8K>3S-Hq<MB<sMb7MZtG%0*D$wy<D<aKgUs-?;}wGa86oarY%`ysqIy
zue!AP)}NnE4*an7$Gqm~vsKXFfCEET5fpm7fI4uO3M^r3Qv;m~tei1iR070`rWIrf
zumUz6cC1eYU8B%tPHoI@*Wim|c~@#gc(^I>9l%_reh(pWS?J3pt<45nYBo0~?a9}F
z@F5gN9<EeJ!=K(9xRGAYRZy~M`vEmPm7yojP0#aK%<)i(rS1=JAh|Y)460n;0o{ZM
zbNbFr6s7S0M-Iz|?0g{^AW9t&eLbbtS`PKc?hwcUKsp_`&v^r4hxA1U>KQ_uAuu9}
zSMc9uL|=hXI#Nc!lk&U%xsNd43u#F?Y2JTn2_VXP@(skH1ZskEFjwc()}muHt#A|~
z^8LI=g(!k+0J44pN_<j|6!=Ir7EZ-I`&yZ6qPU%F3Q9T1J(MVbW|SNcWq?INHZhDu
zmvCJ+&%1Z;j$q*;VFQZpo;p7tpq{4wWYO?GIRndf3hEaY4vq-;(lXhC`3mPLWavRg
zd<QEA(wXyAr0~B7O-QRrej_U<2SU>wgu~^og{OU;n5Y1H*4p+qXYYyh>Cq-`Egml~
zFCgaXZr;n9Zm^knEij3Esc9e8Qr1PuVis~LR##oDF)E^?uDz;J4hL<exP>6mxV<xL
zJ|_V)EOz_|(S6lgBNS*-YnSRnLo1>QP*5@a7difJQ~pPG&C&TyW+sZyk68IF`>{VT
z7*`iim<P~Zy4Lx$pi5u*<&7!?0UMSJrkp3aB){vr<|qxwznB}$%)v>5wl<ZxmvebQ
zy~g?QxST8S`n$`Q=RN|fFy+F+q<Q(HAD?N-5HK@0BqUNGL{^H^#oTIYZ&#M&gZK@v
zy1W1q^yJS=@B-W~V?c30ozkE4KeGt@)$JR5{@1+)|Jxso2W7ss)daM9NKGh^wn5wY
z0hPTPWX|flWFS&1y?;@Sce4|AW(Sb`&9J>xfgk~m;381&REXpal>6ueNQ?^1_j6;>
z6zmVWLESjmn#YrYd;>(yHQW9?XBRVgdQCm;g<ch1eP?{>qcuF(^eAHp1c(x*@3UNX
z&jGN<J#TOCx@4G3ZG-qKOAAmzGqbXsAz)(X=M^0sxB!UX@ECEHj~RyYAE6qnc$7d-
zbk0#4<=+H;ZWD@+^{<4Cg$|=)WB!NsX?{C;@Ozo594+F^WNmF7H4H?y0d)~vq9Un-
z+H{0oRs-~WPf#~#M4x76Kwz}40pJQT;j`?ag1S2EjT_HPO9cRnvER~0F7>|0H$ZnG
z4UNI5NJwmi{F$H6%^iZLo4lXfg3$*ZM`C|E7TMBJLy-dW2OzWyIE_*IB;>J3;|~P1
z<m3pVr4DX_9C8&_8sJDoYGF}NizqMm2-|tri-?x}T1l&`N~su;XMcSpi@AKJh^<4m
zQ~rNwFZthI0{{O95gW;WXWA)MO2;4sjreL!ER=enY+4V0;e=G{=J60&$clYV9;hbK
zr_*PlMtKh<fiL9g=OH10-en+Y{^wkap%L~hEG*1qti~&<xS~R27vD9Xqk*=tQv4F^
zu7yvU=@tjD0V=_`P&xDF@mUg*x%c5*Pk@zNxp<3k4=<5;<ctdH3l8fDO&sj8Z5`NS
z(kFY*PLJlK1+06XgR1bfOLCXTrtc;s%v7fG*0we#NlD4^j@*7c`#||X$3V-#2Mr_*
zY;#iaumDri|GnsIYHN{;>ecyHX4nD43QAZKY+mxJjyN{0L@_s;ppAbm`*y1C+i%$m
zGhS6)H72`X@2h?dM&MOini?>VVRiNFZe1!si*bSyr`uoS<pPS0*0c~Xt2h3w!W3-c
zim6P55y=n~4tuFH!-tu*atTo$3w>cwi_EbP7nu@5F?i1bB!*|v(dtcS;#|@W@?Ls9
zg5AdU2px;o`ShU3td$gy{|_h&b$5YzOAzM?BxLk`1sE%3zBk7ONULJt5XU^HE+RiU
zOZ9zsf_Sj^uek{ZzR15Q4^!Nhh(Y*5#aNb~d3uN^t8nNfE!lVHw0#jWr3v5wfao!Z
zi34ah9-kdM0wQW`>D<kD?}kqeoWXsnI86FiB4G&cH{&$Gtw|hj^&;F2?wzOkJw#V;
z#Sksw`LW{A1`-UCq1y|0N8qgrmGQHO)hd$w3=9mefIC#a>KR_@zMM!xN9e0T3Z}71
zIrF5BE$lOrjW+fI5phb}+_2-)SW?6}R(?yX3sZlx%?+{iE@;A5Ki}g6*Ra0;S=1%x
z3@bdrQz>&L3kFXtjz4HW2w`Gn^+Aj97&1<1oE-W!+GETs1aTwfs54r&AQm;vTjp2z
zk#Z0?&FLk?8z!stS)~;NQ|`G`)Pm$lcL{hOQ<i3SuL>gm1A_x^x&(Z;F=`EJ=@ilw
z`1T+Bact<yi5IjfbT5#{9E!8S$AY$lC@e1{TIN&gkenT=T>-H&!3Kl5M`a)jrU5jM
z2`>ACyqmhOkZW|_|7gY{C>Rey>FcDVwn*VI1zFiMkP)U}R;NM7qoBw@zC5PQ^_?Qh
zln6eFMP7j)Gf)W;00w1a^kRN>6co>vEst2l5S!Q&NecI*c_8H@k;Q?aC@7)|!Ak*%
z`5RQb_f%9O@<$Or8JEUv8hSD_I~$>)e*%eYxmwlN#}5Mq-!aC&xijpz3HolAa{!{W
z=jp{FUkFto*_A7g*#6E@?m=4|va0AIb)x>mbb~?jLt-K(k=lE!g-4DoVl^~n2k4R9
zfb|KmQ0ZV9PxlC+!WTxO2UJs?5$Z6=nGeku(C3JVZU_p38z!96`In9^4t8;|9hlq{
zs#Ijyz2b5$vn{*Qpx{Ue=c)=th8!jrCFD4Uumk*4kg_kcJwSU~7<$c6Alx#bQN-f_
zC=Znfnu_>J#rIqsWPy<9+{w1kWl2in{QJ04f<6$Ud?8xlw@DvwX(36ocu5nvEfsi1
zq(JS1r;_mkV+5=xZjbxO6f)~%n_0kI0D5>U<7H>Z;j^>E_TOG&0b~TvOnGy>(BzpZ
z53(de*^!k4R1^*HV{jod@Ma<U8h{Qy?=33?HCwjags;}j<onFeZ~t4seRWI~aj0l~
zuL}p>gMfq~j~Cg#lbSP0Nwt9UL3Uo>+{^&6t+BaTj9)0HyUz}WVUew4*8@fZ1%*mG
zl*fah<e-4$F#+U&6l{6bf9Ix*kC`7y#!ysDf)w@^U~S;>!Vt{fRYgTbm1Log+}nT0
zD+@?U*uvkHxofqtJ@^Q+A(2=^ftca`C~zk0Z_@5eNKI7*-V_KQAm+)yF_Vyx(7R(a
z!H$}Pnizy}s+&+RNJ80bK9mKc@vsq?Bea;?Em)(OFy|oWCP6&goJ$X=VorlwgDuQ@
z3KGisxcc>GT2N=+j@(AT)=XSl8d9PqO8JQadqsHl`t@hvQJH3U$>K}3@WuuadV)9v
zPC}#vz(W)w#77Fs&dj2PH@JdQsqAU~2q66SCKv|7fdB-}LicSx)VD}E1i#`By>9sm
zfm)Gl1+^~<0s#tS*~^ra&G09>=#n8j^PyV!ytXC?1h)iYaDKG5P88IiJXPY;x&m<t
ziAk0%NV1^3bm`K4yISCE!kP9TqnrO)uC~b;7&`H(^zU1ZBGJLqvm*Su=D$e(`{fP>
z2u%*=lg;>+rl$2)*7Qr1l(QR&Z8iUjE9#JBO`Bd)ER9sg!X9t}fY=ReEr>94Z#>)F
z>{-~m|N6`pbJy-|!Wx#nb>ZJO-2ZjBW6+6Mew7@#U!AAJ{T6ipYSkd;t%$#%j4jom
zLB@DS&pb7#9MTL)i)IcQikYAe3sYERh*wrN)B86e5la9QULnyQ>#L=W(7ad-l4^y=
zJfDH!Tp<pNFlJ$qr?4ipYE^xpI+6J`8kQihaRUnKu)ARV_-hkZ*mm2J*tX6;%OtIQ
zgC9ixOrUs?2sr0w2L&C-#`_M)p1AR@sc#4+yd|oAV1}3+o{Uzx!L4M-MyK<d5&&F}
zdaR<Nf-es{Of&L1u4MR!#S4ATCLB3B3uYETFd<?gpkET;N=WVbohN01@ue%T_1S&k
z6bIk`OM!gtN;jd8I#JGP?d3##*$Sx}V2-Xhu~wc%;#xDUV`Fb`ug06?<nRuQ@8E69
z%ggh13kI(4zu;&wGvt{kuI_xTo0mCz>4je{4J)!)vkWb>K}0)(QhvV;(Yv@Ru(%*~
zI*rL9810tAXm7dFTTNDki7bU|Z=?r;CPX&;w!Z`YvG3mqIY)CBLvGRfnt6rzHuAa4
ze@%Y>r9Au}xwU63_`}GU@y<0k%J^ZQTqU5VfVjwZ@cU!_4r&0$lDlw;(3em@DvAg^
z-9)JtAETo1NMfa9a71wQFD!X@$-=vJyucn_U;inG92?8D5QRq@^l%^;u0<IeSsQX{
zYRuV<vq!kIN-S(fsbujnBUZ+Nce^$JJlrA&E6L%*_B5IP`C|MAZLB<&Zy*E=fxk3(
zF6pTF`RL-q*uQZ>RRq_Qq50KN<*DEuX6FB;LC#YWTE#VJDF7jXe738%{M!-^aV5{2
z-Z+f5ywF>Ao`iZbDkEcR9+I;jTKX{O`>A5;eqWT||ByF@JD|fFVEM6^-wGKQrf=2|
z@1;$u-wgwhNfC5RxYl}S0oS>m<Oy8oCl1#7>P649hyQrV?;T25;v%~!)5$GpzG3jr
zLK;5PU*RY>Eeel-xbEqz%(WZ+4o1qZo&xrZrCDQI+aHRu2wdGgAnR+g?c+QP%5KPL
zP{ZP46|tlZ!`s)`(792##;Z9#mCloqc?RYE8g$guKfaMrKD8dq>g#?7G2~wE#jUS(
zbr{8^b7~(Bzx_mEZT@(6OdTDj2Fxj&p};~Tw~A9c#Q2dJe59FY7EnJc1Y>aE)-{!s
z&NKQQX}og-Y3HbJW@M2LiCKm)0q<g4)PbniGCK~cb$GZA;3G2v#_jIyy4xU9mH#*h
ze`GlQ%?hTcO}<q{kbH)!NsBD)R%!lJ7JXP`w+;)~sKt;EFo-hfkI#CK`JdP`U0=R{
z3*;aFQRjp&-xS%mXq$7!uwsZi>OV)>$Sj}!vM?S9+VadNY^jNwn3})a7<2Zh=V*yt
z9H9xGzeX?IJbxB%SeABsCEv0>{oE1NAi>de{~x#srF*R^ZrXU%Fa7*br@iJUGOWfz
zRdGS^v6t|%HoU`lRaR60PFh1p!}1D|5<Jb80IEW)4R03jdJ!uhs<MH#;bOz>-RA(o
zHUBQa<3VoX2Z^4><rhp5*uaX+G%xl(?>4PI1q_nHJ~A=BY$v44ynk0|<`J^2+=7Dc
z_5C{YsEP{-T^pKwTJ-xkT7g`1aRa!Nru8Y+@X>o#Htuc|7kyv)@vN~d)e3f~C9pS9
zT)un(*xl6N^tyQ_sF<Iaz$BDNU{O0ms!}p%0t(IoMe^jb*t`1%S-6{lJ2EbB*_=oU
z2U3xQ7ng>N4awm><`6u#oc5=I9zg-9fGRdFxCg%ba1Zn-7D|os^Pdr(<;{DuY_T@%
zDg*jko`(h<Y#z0@@RtqznwPl+b03j--lh(tNsdEw^F0@})yy{p3b!f3pQcG9aP-~P
zym$)F{`;%kEIxj+!d@^Y+4*E9Z&J^qC4il;D?}zl8QxFneBd5djfae%c&Y^{{Qkey
z4f5|abjyv8-?W(sv2OqK&p$}<_kz~J_;6==h4_<=Xw>no-?=NqaH&i?cxMSht%64Y
z_-VZwPhP+f`hMHLz-&J<`c7|L5$l2F!fL*y;$ak-?tF{fUzbG$B%$}2&@2G?RYW;~
z3#{E-%)eRwQ^N<ZK|b~@r<rIs#ShV(BY&*(+c)jk;VGPNcI=jCaan>LmOusw@Ni!h
zNHd6a3b80rFeJ=mqCCJ?hvP{@9fst>q6j5FK;6yM%~AC26uSDiKRx*T(su-$Lub#O
za~=VTMV~tB9vzMll~(<T4y@YHxODT^Xz;wH147&Y$%pc=0)X!8H*aPumPe}x?p=QL
zV?Y1p^5W~8@GL3cNORCgrBipbp$x8OOTY%<etBTSm6DR;dWm^&gQttCC)b?Aadom6
zfeD|{$OT&;5rWWwW-*3jfQT=n*K{tH1q~Fk3dncm`p|?rxq)Z(*N^lZNBN@D+Kcj2
z<n6hTUl0@BGZHB*fPZetHFOf5mjc1`aCCGuLYLZ9hU&*j#|;lU7_{UQJcBz*oe-*^
z^X0-HLOan<OL9xnH!?;@HRA8*=2#5deYw*<*OA-;T@p&AB&r=!BzP&Pn%wE!&!M4B
z^r$M-x!}HwgodaigDV<Y56l6OPfC1RD11i}4M2G*YfY8_Yj4c7Gv>@D*p5L~S5c{C
zQ(x*ge=iy~vcHHX|NaOarICPP5#3+fu;Pxu{l27vU7Q%Mh^&_y2%efe?-o=L*l8L6
z3w3f%;yEP;XNZy{(ifDe6oyBM3JEkF97xE$aHfJc`<BdKZiziOtuCzhU+D0^Z)5sj
z$4`iy#oMDc4v9E19}2Y2GR8fIJ?SOsgcY1BTn!{teFUJ(G%0ZyxEOfRGX9vz^^DZr
zbCIFiXOSH>x1V$rhM{2(%;JiI=A(<qTj_EeXq);@2^BmvI5Y)kjHM$h2}PD>A0qP6
zb*4^}z?vrun`+W>nH<EZ-oOVk98R2T>`s`}+luDzfPqc9PEM_<a_n@qQShAt#U?Ay
zrNr}ek_KO{{2|JFs->ctdlUR4bA>p<c&Zn2ZSl5T?L{<$mk9hhGDlD(#_H~wk9q-K
zI;T-D^%hGLjy0aR%sXJc-=@({k=n95tnE==#S3+UJ7Yuo!{%P%$l)9p?e_OMJBn!H
zKd0213$AOG4G9d@M$ulHUAdas_6OG!w=%eIl;C-_5M8dXfQ6iFrkF^Wo8?I#p43~c
z@B^|X{*)sFh8S%=q`fJ(jTnb8C~~kM{ujgH-fI!zX6;A*GK|KwYxsp!e=h2WHa|J{
z79KNmK?%nncLi51MaN%!?M8Pu{q1-S)J|Gr$OwI?wj5F|Yw8@I8&L%34EDOQ)Q*-q
zlTIM)=9rH*Qaj2h@>%93DgugJT-T)BQlcI6ve-b5rC!{r!t`f5?vJ&ZnDCh?w8|L`
z4DWm-V&=~(qd%kwv@|jL&`NvAw>*HNGOpC!0@ES*%QQ3OF2bf<g9alH1*S<3gP`)D
zszEBQt?zY5r%G6+Ej*QvMB#qhRYTW|+2}ChKhoHI2J0-vw-@_!e&))_2GH57+dLVi
zH){oxZ3%F@5M`jjO2TcSZ^G#GfC>}_CXi7P9-80vo4**_*}XG|I_*9<WI;*f_0*}M
z!8g%tkphFGX2JuJbx}|%ioRU@^{M53In__5Pr<a$*i+5h-#CxD4T!EVO8F*+F#0Eg
zR>ueKfQ7!I!Q#()gWNK6_<in<H<{v_O^oSzR`ZID3e_zQiRf@}M=vFW##*DC*yvhC
zzpc@H-(==Pf#E-=YfXwy#H&FyCSDC{!rk$JfOl?2zU%lvxpPH*pxX#MgB8VE8xs_w
z3_R7&EQL?kUd%a2d2*V3ICMB+*wd2v-FYdU>Nq9-)}2-rHaao4P%wGcbytBv_d5FV
z^>aw078_gckArdl!w$EvaRXe&k~@Mo-AzxktnuoaPd;g9iXAfSa1OS_z0k6f%on^!
zC^WspS-yFASRY#}O$(BR%;mZJhKA=`_@k*F2kaFJ)=AdZ)POaKT5C`H#iMIw`g9sJ
zS*AwhOV_Th=WSFrd>{0&<Z%Cz*Y*QnQ~gw$$mbt6E)VPi-qx|M(WG#rcw3#p7N<1F
zevqJ1-n%k+TVXlYNr?qCTX0g4;5ukP#dZGLepGT=?k4^w`U8hmcNT$%v>vER4ZnUX
z!xihc!OCYT5$s14SutjarCH*)uEHz%>CNI$yuR1$3sC?(l@dpj-!sty!m`YhzDgEK
z*LtL1|NJgb^~l4ZVDT(TadXz=XVHZGK3jHAOgGhQH@3E>OHO^|rq#kR7GgNQk5rDM
z0nE_tJW)4hc~T$MNomZnLnEMMrN2_bEzMr+@N+j@p-aufM1YAxJ_oJzRk$&ss63*H
z`$x2;k@p)Y%_g87>y>y2kJp;n9Y0RKuAc-KLxiRi<^oJQjBNKzmPrIY3<uVw9%!z{
zd+!n7tlG`hEHX)N(vBkn7$4}zvy(GOXqIk!q3|sALQm+&+U`g9PF2sJKmYCf-FnL`
zn?m$^0yXW+kY%4ge-7za&dJGX-(!z3<zS7R@CqX~v4!_Y@+h~uh|3@E=&kj>$116O
zU~(Yy;6PI))^*5c$<J*#NN(kPKKV(*$xKCQ=z(LAk)E#p6i+wa;V<+B7o_8AF*#KE
zsBXdIx2u(w)o5b~3!mGFb`4XFK3%**YuxPNV@dw37#tOXg5BCsNe{Og?x58|qyD$W
zpYUtWyEaSVS?%h%6_^-t_MIo%`C2cJ#TGs@lQqW%Q<;nhUoI4uVbw6`kXsMXuz4HQ
z!1X}7NQyr#@oS?z>nyt?@aVhSl_UjPN@kfh0Nk#yHH6&j`%FmuB+`svsg~Eakk#Zu
zk&)3tx(wb@Z_4Ml1ZH%t#!aOZ5^Dv7VBsVLLkM=~v4iFBlHO2B>zJ9uPcQEqpWV6l
z`#eASS!X=~+~)!pCepljyXO|AYEDNF>C~h#(p4wVgo^A##VE7zS+d%?t+RVV3124v
z*`(hIih2+mEcv<Yw>f&}yLxiKWSgNb<p-PJrEJoE$7C9+??)~@6f9%((Uhj~xub=5
zD3T<xl#|GUqAybaML95tQ~Gr*d<g%r4Bc-MP%vwvF7>(5`1EIDxZliVl0&52twc3`
zow%z@Mtha_`W~B+-p7$zA%1J8S*+#hbo4B^e;Lfqs*i>B*wOnJL<p?W*5Df<{X=WD
zy1eG$VayyysPb&8fX*^t&HweOO0z}DWtz*1TN74C44coCN9fH2H!lW|yq5N;?P4vA
zW-Dp4o-td(!=yL)r`B+R(b6GGQnBQ9#-Q}-(4Z+vi?{s;vp7tgoWWb^HHT|%%SD}x
z!MB+B#bYnh3X$ub9;=VLxQ%}@pw<wj3#^sj+1O4n+B`WOYXQggPds@S#SrDt(3gd*
zJ@E$QnHZIc_VIc%%rjFF|B<>MX7}%3DyTiUQk(YYo>k^Oiz6M1dl#Dt6uybEqZq&W
zUpe|z(ng6RZJdtkZiO_Yx^kkwV?Ww*V6dn-lAusMyKF@_l=$I+#!jYOn{2C!^_eF|
z5uCJ#6jog+Z>w=VNo*NHLkbH9H1Q5S884*Te4H?N1|1qby%&twGYst{spPfYeR_7g
zmk%6nu$<K5Vj<dgsSb=be(I`Ml6{3wVCwaac$ipjM3TwK8RRz);;LAPnvwU}4YR!%
zcMNkBmZ<p3UPle8v;KOqBsDa>H-kM*mbODZGEOxds-0Fh>->Q)_oUt`8(+<6mcH$}
zzo~?z!)nax>H{DS_f|$%LobAtboywvTGh#0|02l7VGm4KKRp!Np}F(mb(EitJNHs=
z33ua|pKWBjG7ffX=DUH%sE$=C=+6e#u5Qk<<}M2jY=*~OpY}=7{8Fa}E?*qR7hZf&
zS}o|SPZV{rc<0tkZPAscD)%Co@>H==s=9!&oA8hXZQv03VN2}W1Uh7YKP$a*b1!w|
zl_#EyV|shqzK`+we$n84EnYWTR5*uO&1tv4H_4I#mT(YEGc@~u6nb8B_PkP3fZbk3
zyt6XY-W(B`H(K@P!Xy{A=O95dz|v2`+bi&1f3hi!(+<T&V$=GxpGwBWZz{5Xf+G{G
zJp7=E%|P3)a~xvgfj*LW9rg!5zZg8;#eaB*jfSmed;M|LA#B;JVEC@7kwA^@VJ}wc
z|H3C3Z#y2IdiWcx-M0>g{lTUP+x+UyAGmWE(jY|{BW!rD`EX%?Tw3#$MIM~oYAy6Z
zi?$)dX>o?#`eYLjy~We9%#HM6CA%WJ?l~mrk$~CaxlYOHgIUs2*3i%Z`9U(3aNk(w
zCDp5ff@R%Rj#Pf_?@U9^{*0^VD{8#92A;|dXj(!nv7l#zQBMebGwyy@2~Fn0Qe97V
zJ$6>dS8oy%6VHb1`oBG%*cp7!S@=qh&ne)tn-MD7G|UY8V#0Y%n|a)q9)jUT70?KD
zfKC2$f$Oi8WmZbKTD<Y~dLTTsL+$nh5R+uU_yPisnYlSHbf-ZN6o>Nxx5&*z(20xP
zY$qfYf$V#4;iNi1p!48dq2q?sYt7f59>1&M1J1*r%YXWMyG;5=KeOU+7Q5QY8kS(>
zQz^3#ZdtFD?Kw~P-z9qw-(52>_Be8oIy~VwWZ2_F?CfAnkl<ZCmvsCy;+0sx0*W}B
zfup#S`g>8HDOW`HOWybqu(+Ec?MEr1E*Q8K4A{X`Wn==8ZnUs3>dMOefr`q?>>eB;
zU+DS3IFkES>JiI0hz8%5Mk~rkx+X{;NAi-pBu~|KD_w_{Axw%;FAA|Mm)Z~a3pk7n
zqM8Q=25#6XJ9&gMKiz0h<UftwpB+CvDPP~&ai`M)8;cMEYxLHq&YJ=vX(Ro?I}6Q}
z{9xm1n1fE5-o}D(50B@}u@;yW`f8*d?m}q>)Uhniy6<_J4>zaWP30olwpJ;O5%1@i
zWdB}rna_X&h!p8}qCchkAG9XkU5P3*dvN^a<B#18V7e`a`|VeVi!}doj;m-dpu=f|
z?5M#JLud^0CE|fX<W=BJzh@QEi8+UY04cgMTyt`AFLq-<gH&@zLwuM?E2(DR2en!G
zPZ7z}{H3Q@M!$m+|8`2LqpiC_c3*bSK7amVbKWQY(gKB|g?m);GmaqBv}tN}3yDoS
zV;4GIdA=x@fwh3*r}IjD>eJdMX@Pey`F*^$T6cQRv^mP%H3u}ywYKmAO=0#o7(CJV
z`T=f2p{0>FaYo;`Res_^yCz4>=?41>y;A|R)b*BPbqcHRG&vh~W@&9@jg~if_fg{<
z2X!)!H$W#%YLH*`S5a{)_4$WAn2dGv&(Fmx{zpYv9VhunztB7mj&*<X=B{?K<PJYe
zmRsBJy#Qu`ez6HI(5K+<5o-fhwgbF-dR3*^dtQJ0pAHTeo&iQdnw89d*6jUSFRkvY
zvq|e{4>>TMORx<9w6F6OTK6Ybmq$)wdN`7FbLGhy09u2D!^E_qt_(^l7W?&Emt-dx
zIiR?1;e;bEtk?U93sjBYQpmLf=cCOSe<DD3|LtNMwU(JjKQz42h`Z-aouJcbEJI(u
zd;+HCqeY|BZz*k0x;6tycxqi5QY9o^Sgu`DtKcjDwA4~px=*?^U{OWzA;j&$dx__M
za{aSR3sfjc11dE=dPUK19p$IbbUyjBm!7P*M)SKL4c=M270<EMPKmko{)88M`_`#Z
zsuqvs*y%cUkT>`NNv$n)FRMB$59SILuej&hRY)Q91vMLdH1jn2!#O07bfhm{X`GnQ
z$PMTcvl}jsR2I{}W5P<BU%ldOn7Vzw>^i5@yWBH-{EO;i>8Da9bC_9BOx|l`G^?EM
zx{BR1QtOZt<gDKNn4XYq$)>%wm--a+d_J(v&muMwT`7?Hdx69uUH*>73ykEQh4RV*
zbh~Ug8iIfa=|F{LFO1kHhw9^co@nh|on>iG^mB;#6z8wMW%}+J?(y+)N4|aa2)$ve
zy>Rn$^gpZeal95ev{SdTz+;96>6_eB8oJIg{hW_S=?&3G;2xWWR+d>9{T1S@KH^m=
zJ44^~Cfrqduy&Ubbfob#`&y}VUJ$id{awrAZ2w--Fy0R1X^OexL8!YASh89(8jbU(
z`yC#l_W#l~a*Hdo`uPv^8^>Fr3bnWeypnidfbkeyZ$UukfZ5a2`;qaAolYF_5pD!7
zX`#Bw3E>WY=i~_018e%@#ha(cll2h{;z^|fhu`!rUJ<~4-<8Td&RWjZ$SC%(OfjeB
zq2HrB3|o2}v@WCNL7=0AF0?)6vgk-_0<uXR`qMz{m5f&PkI0Tu&D9vbvno&FY_)rB
zhheO}rhL{JTF<?A7gWphN3F<ve~2ym;Lx?4lrOj~*-pDQozPe-Ff;B=cxUaO<ZrcN
zz%77*!SPxy8~8I=bltILoxo)lV**k)WT-Tc!<PycnWRe1X@j1oM*SoI+)ak4FH*P*
zq9J|u3*C#**%})0<<BqW-lBAZGl%9<9EECzI9^T?Ga{|?t;TQFjOlIqbM^Ku<8{ml
zL~y)VNJx@lCG&8paP81I*9GFgVRZ?)<@Rd{T**jxI77gZGcelLzdlloL!){aDNU{%
zQ_+e}yZR@M41#Uiz8wE&2QZ6A|EQ1WVeoJl2)ZjAOg-e8EC*2mYah-VP^Ue#^nH)7
zeUOIUfWuONrQ6m<|8+Mp&Hd}Nh5ybd^B<?%{Lg5i2lL#P_YEy6MbyBt4Hi70pEWJ(
z%9WqK`{!0V1}x#IOJrnIv%tU0W|s2t@d07Tw!^D)@>>O(IO#;30-<BePH4_BNdS0D
zFtqNhjM~mGO6AhWhyT{7{P3?|+GgSryzpJfDFq?&>lsfz`gTQxgb;!Wo#KEFTKV5d
zQFq-JzeQD+@l@kqzj8mgrxeJ~5?w@5{-0>uY&z)rK<p6Er|9f)bLPFfHkXb3fBe$a
z`>ioUi1-Z^er2Zt^ZDP7`1!Acpdf{~g+Z!^7LNNR7OEa0E{4CP(4r7Dz-F2a7GdZN
z0YdL9aHU_tStkeJ0EMg{5bWUe73$;;<fMlSOLL%oPJ=<HWqiE8Ti74m5hKtr2VoaG
zHzyD4%xfZ;YNS8E{^TH>kijz$vfBh4)&qWAL|;ezZhmm2#~J81`C|{>Yzj&r>)$wQ
zT>&Stpzuz>S3G=3jhJ_bzu52ZxJ>`JOh8Nrz8>T(8zMT9!tUK7zH;Cg!c4xu_zAs@
zz<^ryeYgz$@zjta;y==(5K{(NS6q*-E%kq<g$`KMtrlmU*I&RwNkKCQy|D{}(G*di
z!HDiqvn~e<9w=v|9e)NnXQDhE+B$KUk)s7T2Z#etk5>a+|8(PknF0~o!L>cT@sPdb
zb)z)kC0N&b_5PCJ8gz1LoYS4rMR9e4C-^oT@$x~hgazUra!LW5X;f(1LW~^K04FN_
z87}7rDIVGzlEL){a%SV5-T2hh4$ktCJK*d_i+eZ(9RL6!1yLKCf#sn!6b@*agF_vf
z!Tk&2Vti)VX0Y%Y9LR(nvP{oHT-sx`$v!KUh*NtF{)FQMZTHa9p5i!;m<ZsM9!W66
z7ipPt*@_?REGq+*Ps3x30t@^c1bQT6A)NgU7M98R`ExSRP&8ET$cXe}q7XX>eCaee
z?~7H$zt|7Uf%P3eBL?)i1*q_Fw9r3rmcZsxN!NoU_q>Ni-`4fKpu>4>XU76oMbylX
zQ9u27IJ)Fui|x`Jtz*qs@Sz~5gwUDC9}h14%pe4GE(nh1YhWL{ZX8ex-|hV%Umxv=
z-a|}J(4H@{LP$XHz>_v*6zOs0f6{ms8i_i=m>tIZ0-kI%s|d=50qd?gJLX7f=nH^<
z^@0U~X%}cXHh_@&)PB4wg8k4XLq<<;51QNqD?b3db%)^dh{eG`zvs)5IXJCI1#yn0
zoz@+$@PnI%+q#1J!Eg6eMCC`CLlA%VoyC%p5;%jS!s}?gC6&_Fx$Sop)Tq=A$l(TX
z;sD@OB4fDuc~8vWzIGU{*`tQ8i9C05q;ozSd=6@1o4!iFqd@ye1j|>vXMMg@egxa0
z4{}@z;<9e>W2buz{j36D%|Z?g&^Up-K+^!7tAiSpw6wOclXQMwqiWMzhMw}cT-}1S
z{rb~G>GEcq2wvz6;Duv&c%Z)vIb{J3>gn;_{-p~|D8!6Xc8G^X3r;J56Rs?wC&*lC
z5BtpbaQ=7MC&Xcj{D7B&7s0*J5*rG2rkgOryfDi`AZ37KW@H4M<Z5Bk&@P0E8V0xv
z4JD{q>C^q_`Qh>cIE_OXY}G=b{#Za#W#QuLgg}x6mW(9usLu`0fk_90M<Ri>YJmpf
zj<>g;snq))(?#z?Lz^mSG7$v@1-S;*U*?gf4_?ab-z@y#U=f0T3dAPRI4mNLh6O7V
zMqJl(Q@Oe`5e~6{Z&ZufPWRhEudl6vF>Z-XJ(O9q-yJOD7|?f`|8}*Qo5LXr$cB2i
z3jJoGUSNh#z3dQ^G8FX<G3aMQ6U)rS%^H{yu&?!^W}B#t1i-l=07IA!VBP|Z{NMm=
zn`%oeu4e_uFmK>KGzZX|KM?tXNIp~Z^VVu<67x6PF&JdVW{X-FT;iIVo0E|KE@*&B
zzQA464Q`#!gQi`2a8-m7Ma@EcmVo{67eR;&f?#40f{u!()_Gt#ngv%3KX`5g!YMiV
zU^-@D+wnopgt1P9TZMLEuja;<mSl)qo8W-IqORWMtLQwCZ=m|`2DTwMO2-SD8zR8f
z;sqEPdYF*2M3Al@unsjq_(Q`*(XijXvaRQ2W+o!%XCS>+$e|sO0j`)XwW`1Zhat;{
z0pkI$5uAfItdb@%l=rBt4VFD)lnCrp)0PvMTML_ke0wSI{UIII&``OH98V$7=Ynm(
z(E@6H6C9Dr(1=^&JSDdY(Ks<8BI3!E#N#qm3)m#qs7(NIbL=G0ItR`CNNpCuC@p1_
z${&k{CT&`7ZtfB=7ZyJ^$}BEzr#`%GSnuz*2`502SFYOTS2iQ<PHK_mH?!<p*b8c&
z;Ns#E8G|$9AKzLUq%YDM+~YxWRy~<vXemGMCc$qa<@9qfBMIk-iG=_S<reOB-Lw|(
z+*0bxHyEygR&oo-abT0-g_inZX!g(O_N(5g;LBc0k3kL_5pW!nFhWDlh>Ig9qocEf
z;@UonQQ84HCIjS8YZTJ&EdIp@s<sX|^9BQb^mNj8@V^h<**m$5OC7D<#Y==@CAmxL
z5CguiW+Y*<2nh6n(XWc5pTAaNxZII@y{@2k=Mg`go7Hj*eGf^{doi~d1_s4{rl?b(
zr4hM#sBhGw$Ei)>%jW*Xh~n{>Hb;oAZjL~x-uM3i^;sgaOq`{m>IJ{|cnk&{cKs+8
zpyV6vMRm&<QFbLm8>2>LHWZ5k1vwxvKqas9!^L5&1`Y6+7kXU0cb4?7b!jBIL)!#o
zFh-=2(==N0!JiX|tu4^*0d?ua;Ks*sufLc=uMMn7L<CL}u>J<kl5KDjSNI6YAUC(s
zL$7;I55zk~oUkZZ=Cf}eJDBXPO;9kL(#+Y)Lmn|^#P|*vcsN792*N!;Z$mSjc%f$;
zup*ZK)-^o_?7DC~6(ji-OLOTj$kA>PEs#@U&Vn29U;cNP&^c-?f;F(J_LSM`f=m88
z)E)@%O%(Uwf{x5L)-C9%)fjn(323NCwmT+SxS-+f^2;bU02s3J^1a{<y;I)R(J=#o
zJ`*Gu=r|<>p9gd{4whJ|*R>e951H?$eFBOdv2{V62&1D2o<a!xX4r<Hn$wd*W(HsV
zwAI>g&1JQ4V30o4A&4anz68h%I(y(LrT|t<Ll>=^#29377)0?EBhQIoXexRJJ)$n{
zoaH>A=|ESz=KC)x8uo-JVK_Ge(2;S!G9*zPILhwRtGUr)^9#C$Ud#~UjbU-CjR#l{
z$H&Cn27eUTGtIy$e2;iG30nEVd&EUM2+1o2tq5-<<EmcbgAUXGqmpxtY4QxiFw;mT
zCTfO`xeRAms>D-DDTj$-G&(jpsBtJBiUQI~(5av`NYQv88;bQ15j*S%Iu{WYJJF&d
zxS3Lss>nPb9xzrQnN|>-QWV+sxc%ABneaoB68OINeV_Yz-ut?3oBItYcN)W>M!qWw
z94^=I{Ido1X+7i2rN-AWS`lw1MS6D8i^AFUdSa>i)bSulo1vTAH2LPEZl~9kS9g1<
z_Ly>)5^dwYay)IhM#KZLSzYZ3#5GRA1y>B2LKEbl)|;=<5Ay&j^HZzK`Yc$|>d+6-
zzjb$Y)tyYZG<9dywrzhInm*^~_>6&NB4ZA*8p5g*05<2SDTizBV+*ZDMdZGd%Wn9=
zB8VqA?!x-DyXO>}UtI7RJa|{zyHSOP-?<mR%n1~Me(LY#^;m)xnAX(3E>HLNPrseF
z7eq(g3Fs)@jf2xGUe-s-`TrI#t!?-rUCEhAfjl+g<e3_p5H#nXd>Mj!6%#4(J4z0e
zrP&iBQX2EHH_|Nbuv$YFZ*VJMpR>amTcIA{k9O65bt3<DPe66(hJ-cG8g^q;C-AEI
zNH3@*mts!z^120%?A6*Z55{;i$&L{VBWk%e#QU&cUYRe<KDf1oRcdHPQH}@>4qj{u
zGmi1Um#G5673CHe7gw29;=2%SQ-l@}MvCO0AqCT@_<c8y`f#Yt<Ps{IqU|<TNr~LM
z_uEHZC70vwu{X$Z*mj`40>YTX!){*puqN9l{%e*Pc_O+^_T!7r{(7;8=!($w2YHdd
z#m>{%kZVxVUr-2)rugQZDm5afn%U|#q8sgEkpy9*Qmnf9{no9*4zvaCA-yxS@*3B5
zc*}Dr)8HmMd0-eG{4+)*hfj&^Cwhssw|~I+@{0x-G%dqUEn>d~9xsUAMa%h%Y!P1B
zV5pGDst+UqZaJRXPV<%r7c#Aa5%bptL8y-m4}ZuJ6y~X1(O6c)&NC4>BAHJ1aSDZP
zoNLC+nIXOt)+jMg1+x&Z_{@okiK*<#>g{>$se~e4z5ZD9iU?AhC=}-;W{er5RR9DD
zUlLK`X2{|D=FbP`tt64`m~TnUmM=nRP76Ce_LdPQy8ueFfI3wF3~}F-Id^^|;YciL
z6+K=Hm{L&Ky60*@K^04;Uv+Q!)AG^L3v&asOqjVoF_BSlrY<Y?RT45%x`b1SHZOs}
zI}!b&BU)3P9nG~@`9)Up46f2)B!p9ivGOLfDpHH}s85-Y5)J0ye7=hEbg;psl)K^o
z7k!$_YKuZ>39;>vk4pfXJwUB>eB$lxog@)>rvM=X4PEVqzKJ^+A-1!nmhp462*tia
zw8v+<g8t0~llCr(H$w`Hs<g8EC<-jJZAt5%>cuzrn}EHaj46OImtsW|VZK|Lb>5^-
z*(3i)c@#MVXdGm}i8)irYZqsWS{@WOBV~1iy+c?fEsdd=xQ(XMI?t&5X{Tefxt5&=
zD>-kYxmeG|!pyO!mf3Gci%BOre8{AUuNsovzZ9F#g1=w46k=oc>E6$@wYVXR*~huV
z8l7jLk3KRg%3&=P*ZCr%d4_(Z%eZGDLJ382M~HWD+hm+P(KJE>qP9mzM+cD;s^lyh
z>F<A8%+3v)?&n!#=Z@)^R5I2TN(CM!!Ea0_3lIb!PbjD{+w%exD{GlgN!S3<G2_-u
zrsGjnhp$pIr6&H+B>8KtKV^<@x=8K1^P}_xOdOq0pQcg?wFC)R45eF!vXHWl_Ch$y
z%j9fR&C{&S`$HR;H}W>Km2~Q-2^L5`C91yiU3Y4P25l{o2K@&O3SrHSR>q#?LZpSx
zCf)HCRC8Yjt*x(1LmZswfB6npbzJRbH6dG$RJ_Pno1ol(9;RCQgY*QDh-%!orShpx
zMIf!MxCW{Y`9j|+t@qQmi*cSDGQ~g%J)lnK0=%a*mK94QIHQ}jnQJi*oW+J8odYI*
zgI0$tBiHj;2gY;#g2WL{rUPI!G`aAW-s3%@Q9%oa{PR1fcS*pO<SD`{y=-f0O1Ult
zQU)Ei&i3|4D2~T~GDRE);?Om)tC4E=Q?CERt0ktqPu~4s_P76%j&C+LUYZxb`%ThZ
RGM_!ZnI1Fk#MC95{|2uRx`qG%

literal 0
HcmV?d00001

diff --git a/docs/_images/5f56302bedbd28c12ef38d5cf2f3c7abb0bd6ee7496fb1c9f71718a65c2dfa91.png b/docs/_images/5f56302bedbd28c12ef38d5cf2f3c7abb0bd6ee7496fb1c9f71718a65c2dfa91.png
deleted file mode 100644
index bc0e582a7ce41d419cc1f8854cbcef6a51b8ab2a..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 19985
zcmeIaS6EcxmMvO<fFg>B0wPIJlpv{)927w^C>hBDg$R;Ca#92&D><qNh$I0e=NyV4
zC_!=-$siP&JD0or^xpS=-Cy6n_u)L82P`aBty=5<XBczNF;>uhWtlT1G$be#>WrMM
zlqw2^k4B;Jl1~!BJM%dkb?_qOD6Q?NW`l8jW^8YUQZjb5wX$)vvUtSkY-aCZVPlQv
z6yW6HV0`T8XzL)%#r5=m9l&X0Z_YJLaxwr;a>`a##{q>RGe&;!K1yU-pioL)a#DBH
zU6PhZUG<`VOtq|c2a<f`W<2@i?W2c}R@@xezp57w-yH5+{J{~c8?PJO&(-leCMH_9
zB0<4Pp{Un#l(MkUvMfKk;)Q%x+$%JjAIUtfrS{j!)-Ei;IL>o@Lww$KF5V%*cel&6
zODMdP+T<KLIeEcH`LR5oz`#IRyBk<|2~21GZ@*}4I}^(5VlXWGxYg@7Zk$Z)oLl~l
zoC=THM9}L%&}p$hT{S%zR~5C-UF3c2^*$}FO8*ReDXZUy4_Dv6f6wWrSVo4vbLWoF
zqQpI0+t0C<%uGy7gp-cKL1AIe-eHEwpNC>&{GLC*h>?<#;>cjUE5(P>Mt)T?zV}Zr
zxg+86tS3!K&AU^sF*7#|Yeb%(nxB`MZI8Z1XDIan|KpnR+@FO$T0vW%@88vJw4~*=
zzdrf#Q7!YVMz-dbvxbz^hYK3NxZlLb%RPF;<mKh{Jy$pOlScOML=PdOkV*LH!R~zO
zRTh@sQoCsnD!udM<cptr{+`nmgE>z}rv#^~)Td*;<Lm3Io~7zv<&Lx8`(uHRk6)>O
z4et2bUOCBLzk%|C(?#+u>OTVpaPcHfkwjgN-Mr@I*&~-PAUF7-_H3r)D&gAi1P9;d
z__KXl742m1#^Ry%At-L!iQCrIyBHg-wEH>Q=H%q;4j<~4PhVN5#tu%9@R{@K-NDS=
z)7o7=-BBHoAxVbH3*25Bx~r&2dRf5w1Kj1xhDBe7aR}?yJcFPuV@nvF$@)}N`jH+J
zlWL(A|1a`s5>7ae;ga8Yc&bQ-`P~6KGdbgXsL#X8V|jjofjgx}-qhd5wvLMkI(P42
z9$%*RN?$B3{LrCz?F!-G*&HHg)2Fe#CZumzl-?URygWff)LUq#AbzxCqUEHj`fDJc
z0al2Kn>(U8^fKDKix&0h(IeF3(ehjTiJ{h`<#<9|Lyn96p_2^(=qKNANZ!306cS?E
z9C9g1)b+LdN?E|$w~U-se^jdvHWY9syu7^Be2>rZ@bJL**zeB9qM!cc!yRR&dL_7S
z&aI~&9}p*YzU;)93>BK84%S;3Mw|xpU%Y&Io|5w3>R8oKk$HGa8H3xeE0U6uCr_U?
z!N&2J^}e~v#FXN9Xl!L3NV35ZPU6Rt+%DegQ?Iyw4bRg@`z=AwRZEd9$5iK$Qafxs
zIzV9D<IPRoVs5uTkB`>Fz1JGZB-Uo$s1!OaY9d!z{B*cE(WY9?#YGTh*`I@Fw9uQ5
z*q@5TAz$}=oPZ7e<m6<IPSH!aWryQKoI?xUvz{!q>-<)OwQ#jE$47^w+1Jg%x-MR9
zl40;{?9bJ8{hgJ$Q**p8A-?yE8Ab0pL%veEsqD7(yUCY;SkQI?l`QPUbn8~MWnS4!
znp;oSYK{-X8N3f7;rE_wEiUC$@iVpT`IYrcLq)Fh$<KCRWrW=R+z6(;$<}$?$i(#e
zw7GEQ&KvV^($eDVxvfGSSsa6kLdR~4j=}}Q%Yw9L!4t){)6>%<<Kko$6&1fxYADoQ
z)SGe`q9Vo;OP==rd4TNK+L~?k{)&jO^U^O)22mI8tgNggK|4Qq8`GVVJYC=#8eeA1
zp-^Hy+S=M`w7W6ulWpE;UE;8qTe7iIv5IfIHgV_o_pFBYX!eDkcX#ug==iOu+uGVz
z4AMrLvDg%`M7cLC1y6_haU|GGl~k6iS6?&*Q&CV+$&8jeT@tdtYSI!$H~}}=*x1+u
z`ykpfeqn#>A~`wPP*F@F7mshYOa>q4E&Zj<eaYYPtYN11WW1))*JHc-z!IaseBpE3
zUXlx?xiuoOTD{MC>eQ(b@8d&kszj=0?n537mRd7M`@x5Ki*N7!_mB5?cgex3Hs?A=
z%_1WsQMAI2t@_*jx;EeP^hKWh_#_SIi4$^Q+23BS__dj1Sd%hZ@r>fag&Avw&V*ZX
z3JT0uuHXeU)WHUd`sqTzvKYwIkNkO!iAmaoltW3hMC{8Mj*81KzldvXciQAlx4$Mr
zQ3a&M?FZjLqbYojk8m}5_HEbb_YV#aA!=g4ybo|S$7Wz{j;mwI;EL-T9b8nuT|cR3
zO%*&X8WL?UbbnB|xcN<nfd@?2z;*T_Y?SQ%`{%f-{+!R&%I_)>dpcY^JAQohEX)&}
zmQ6ibTI$1}L4t{C5xu^AcYepMTJ?1ifg3Is?=5SpLPQ!aVqP)VoVuOPcjqI-n4SIo
zBAapXa_8lQMIQM4qlsEyQd+@??ELBku;Zv$L$4uE;)Rfqkn{Ni8?zk?-?J#lMAv*O
zIIdi&n~sC1JLj^(|Mcf)qdI&@2OCTBIS{9_HFMu9#B%y9^7id*EyC9*ohp%(lHz2k
zq&b-99Qd=iq#!p`l=RY2XZsG(1<b4K=LZJkDx0xVF<pH`goNv@%;AWq@}kjYzdvQ$
z3Mc1i7x;l+L_|c~9xi@bHuZ{KRz+ogvs>aiKR+d8#FO|01iQbp^8;VKVq#=`+n8Y{
z@Z@{ovvJSZ{F<YLxH#%D_f@g}JpIL#JA^%N?+{cU?O8f64c^h#rgpAK_Bz~K?^WRX
zR`JXx#dBK+lHFj54MVEe9&5Px-i-$j9)!>ey{0m7@r7_martt`OxqhF=Oyi+@4Ao|
zu9wtKh3Y5{@nJFqC4F^D{W^B13fmQo*KCTt4;KwZx4x?>CJ9Ck4r=FBtO$$mFQFlr
zeth_qEnMPA@aDrWZ(*T!c6WKak34E`^_%YfS*SeR9!65ySe1LMb~5;wxOLT*=1Tb@
z=g$(G?nq`CQ8x?JOVUgAv$2LN^je#JDiRNJAKn7vI)0FEAch?L$i$=!H|8$n^gF5|
zb8a$#0aNRP2m9LNd1^66*P6AUJUB4W$%0=^4(lvecWZFKcd=LXYC4VS2P3{jIjP2S
z5_F<mY`nbW4H7QcR)hB)itzHtf&~5Ff1xxBG5*!_?t6|7MPg@jhEigsW-PcY4`hsd
zv6{d@b*qPb-S4aSezVVYC3h5>bvz#Yd<DYnSl(;EC0aMI7v3;;Zg#yxbvbfpIIhwr
zz~)29{PjIcZ9yyu4k7%-tHwjC>_2vT;>WE#6hWSMX1;SYgYwPfc{<3N4FP24<JF#n
zR{S)4k8iuV2{YddVPs<R^YKCDmH%c#ticOAQsw|5V_mR&swuc&$ZBO7NlOqp*1=%D
zfuSrpi+Jw+ncP{QUNKQl5pDCqBl!3rjmYWu_sM821J>kwuL1)vMAR#i3-wNH`$xEt
zVytWl6VR9P7|{-C*$3PHdDHSgzgYCSY!8_Sy?QlO>r0TMUlGG&(!ADoJ(b&LOcYYc
z?X-KLrLez(VDs;~k|QE&;c9jdHoO1+!0x$B`csYUGkE@aP<?#lPI>d8l!u3CN6bx=
z!@aF*qf+GLk@#wHtW1e#+!~XHQws3PI~@q)t;8;uhp}6LeM34vI5_yIU%~(5lg4zX
z!1zphtijaYVtyvLCN@dvO>OP%F~~8J$s%a<n=*&_-W(ltUiIFSJ=|({$+*|)+8~PS
zE|7y<AbT$i6<zO46fhsFbTu_Kjq+fY1}A9EHlFi7-e(XPb72M~*@P)7a9Mv8e%MT%
z;<ab-yFXXK$cPc*y$M|OSk@9DWNs;U>fSxQq1E}kX6`R%NNai>IFu~pWMwBHT|2If
z4C!m8%U{f^+>nQyp!w0^*5e)@xDT8&n1G<;uZVqDNRUc^j7Ik%VYh)R7+@*EC@v&x
zHDKG`T(=l1yp~_J{V;F;x>7<Tc&zL4*8%Mc=bK+G2QmP8(whiYvJNsdJHPzM*uC+Q
zk-9I-%8#^El3{}9=vswnMUHB^{K|A;GGv36vVRZ9tyt_I7kU82hEqSd9S*k!Hb)$~
z?I07*4Vs4-LlzWWZ=@J;Tg>IN><<BO6Pb|EPR!sj;s0}PMlpcOdt)gQZ(#ew#d#va
z*y4MkG!MQ$(eOH0mw7f6k2cpXv8F31C_sJxq!B#b67H}uBZuSh*H6rNkaiD2sQ?Sh
zI#g9v2g@AH*J;3#RY}D~Ff2Sgk<W?A&Qnp%b8g~rnU({25G<LxThcQ#ryYgGyyWk0
z=cI48v?h(;eIs_GlmlOB>-Uec<D-4oKi_1Km^oPP#D4cB=@oz?cb*gB^;CPhLs)M<
zJ{&(TaK~AT?@SPYgX(^q&jQ1LPIP7plF{t2P0j3pp|=^N3-wPkMK;Xj<XI?>ZM9z$
zb<a^!_wKnx$=thFj+@0yH3khXJL6Ow9UZg2cT;O8xLCVCzO3zBGEbdg<K;l7MQPwN
zNoZZM%n!z<lF0vbu*zM)(EIS#yLaz=EUh~BS8KYd3_b2Z&fW#o=DN3#dHPTk$$t9f
zj*}UQ*6(G)>Ghm`XncV@_(B(I5>;FNX=Z{eR{WO%DoxEL+7KBvy}Ae{6@R#oQ_EDQ
z!`UIX%gP#*U%kgRu=yb~^G%9Zo=D?@Bh&_=4U>$5f`ik8fGo~aPy_`9U15B?#y&!)
z?4(q)GPE{gG`>Wim>#sYPIt~Aw<k0Dyz0n+mXuUw%Yx&hl3|C#gX)OxJd|FA^V8ZN
zcOAUqgdBg}4;xF^+}+=wUNz)rwrR+&^IqA|!xMCm>04u0ct&Uh24%NC)S(Cv`Fox|
z;LzP>eP<|0ymlsuQy<ok(?>Y;tA4KW3xRS?XZ=Yx7Tgh*sl;6bHeV@`|3MK(>GzN9
z7Klu7+{XB!mjyEHrkfSxxP1ZBtV3ED4gN~`Z&q7mJt~}6Hb;ZozDp){qIUGzcqhcb
zOK1#frgHL>FEKsiwQK&{%fl25466kn6Tzd@t;Er&(l2^es7Ru~7#lZFX{nrSZUP@q
zXDnP$pzNLhq!yK}hPYb`(Ry?k$_BuEv94lBG<XO`KiAF9#8eGsA;~gCL_P1rEka>U
zJSeK<6T8Q{Zp-&C^krtjfk8>^`<fJxbE<EPp|2sAwme)?<hJz$N#64E@>vq*08Cxh
z>WE$82O{|u4vrAG_sA-%`(UarD`oT4kP09MUb*`cm3P_2d7;-Iq8(JXmv|nXxUQ1o
zn2H0`I^r@N3e^d0cmu%jRoZUPNwbV`@8e`~&%OJwx}UW2l`EW=wX582Im~y>#+#=Y
zgF!-S0V{(y2x}*8xnZB-LQkGOJNMHv-wggt-@RFXn(N%9OLBnM;A)s|-pqY*%>F7+
z*7Ys7nxdSX9F(d701Sj3f8B;s>{nkV8N8W(Gy)$^v!89xF{ny_g+QCNU%+%G%#Ix+
zAO%8mf4*V&8x`?3u9|~-s6JY9OUBx}C62Lvgr|`z0a=RC@Jn#t?%PX~6|2?L)8P_x
zp#ozQaHp>QlZ`<Xj>|uz!5fN9+s^abj6p?Z0-<dN0Lm0(o4Hr)dEnOsNC8x_QhwTm
zRA9uGfS8PaCYY<*2vQE@vzIHQ6%K!XJwPGFO>;OyH(;^ua;HV4O1G(8zqfGMaskS2
z-r1yvNp2rIL0X}02;A*fqvb!6gq=Rg&WpSK`4|)&jJ_R~T3RXyr}{RfDWRfY;d~2X
zAPXAZr_T=%3(%Hj2u}t8v^j9(Z5Kr-v^wD~#M)!H46WHTKA9>f3!8y47^8{+{Nj!v
z2wbXFjOT6ACyJ8}ro3bl;<~?FqICa$gpmD=Y~B{FgjXe`hIE-B$ZM8RAt^n4m>{zY
z`S8h@*ZxzJ5FR=aXFlBMv(%O&@Pc{4fu;*Mq#9W*8=S}ae@Cm4LT%I7(lTGpB`%&a
zGc%*=d32Ue*r;e|WEehb3IzeAMN|(I6yehYuu<S$5IA4%&zCReF++N7Y?OkGb`OdN
zG5UcIauiV2ZsaroJVNU0TbBJCwpGZ-z{R21-TbHkEe^12l+|!?Xc(P{o9IgYQ*h-T
z)WjoL)ux|@KfyLv3X<dF+a!*6RqlmQM@|nyky&8UauyZt6O~$9TPr!h4qq(n^!u~b
zP$BI;CuI_Nntd9#8mV(dmG*wHCBOoqVrV^tq^26?wUog2Lap2b;Y1JD(%fvny`%&6
zYzqLMQ?+mng0L|uPLIF6CoIBrPW}3pR<_-xp8N2}sG6gf*jai}S)?!ml%3+F^YzI^
z0wU72$EksVt^SVjS=3C-%&_YnPKJ7Vv`~Si?;U`}i~i}kyEItvoJ`^%Ld(!I8X)eR
z>%m}wiB6gQwT72xOrU^R`uR2ZnnDb>$Br$Ev*y4asiPyV+(kTcaUkD(ZK959*>hpI
zgbVUJVk>h1<fdScr@>K-;evcDH8o%<A;C<oO*TNx?@N;*gIcN;;1CuvS!arvyLQ1N
z!s+Hv696hG1oA`c0qwqR<-9V|1^^J+6AGt}1}MlQHzbWSsG;i-f6G!c>^79LEzlY`
zdFIT`AM*^{MkpkZwzKD(4t_Q!We`t#cQ;_p)dO<T4*1sKS4%3m#ap?$C364(KY;nJ
zn9O10?>aj2f$`5mE$XC_+NA(H5)>YO9pGxs(N;d6%~%rDA9bT5j>At&zCm{Y3E>dj
zn*tcT0y{C&;Fw4qG2*^jrRO|khQt*y_w7=G3H@iIO=>D)O|Y02!^Jn<aVxV&`>R~<
zj_n~)rVNI(J&gO1WG|cyIhyt?aa~;<{eEw6FSHAwefHAF$A?KmMqZu-Odk3PfQ6AQ
zqc;UVzXv6rs5P1~MgBK<M`Yo%g6`GR7Ffko$TDoLK_Fx*>oa2kOD*8r!fLBq_ay*M
zWMkU;zcnmTvmTOK{^<i6QXd|D>@m)ek7h%C$jERjV^O6kG#pqO(2<gA&m<8;4R&{j
zM?{<hS37YV>QoXZL#B15W@=S6HAt}Mu3Wj|IyQC(jtwB8!=RoF<eix~%ctt~;>C+n
zLqllk)v$TQ0ltT96adv?SCY{5@^9HwS*q!;+)UxR0!bJ!g}b}E3k@n#QjLCWe^5wL
zE)e&>^!E<__kBq{iv}=j23;;_pPZwnmIZflg<7KxkgD?!aPvkPb?E$Z&NWdP&On}c
z1h8GtuIXZqZb=w)>WC{wyILcetMtX-KG*TY=`fmkdUDW~D4TqF8TGj5Egpl{&XvXf
z+)evV<YZbqf6Own^U7b@)Eveni#)^s?7E3T5bV+3K+W84+@C*=Ny?cm;eZRG48=#$
zXb2TxS4s(db+CUSA*3nZN3MI@%Zc+QEXql(=x$N9mtP@KklSo5q{I`Rrd$K-+^i#J
z_-x!jG}oEf(!o`Ot#sYo@W4V23u~CPJ-&MFTC{N}7}JNGp%9+t;pkQc@SSk6ZECo6
zhgdP(h(jfyTdVQvs@wC>I{06fovxt)U&MOHfA?S;z6@H+Y#JLm?^9D#GcZsM2PUe7
z$Cs@)Uv@p(ozK$Br`OW6BZQb}x-rv+_|;fm0vxn+GPN4(c(7xa;;|tIg;*na_eb3l
zPS5@A*{sZz_u!L+!U3FUs86+3jKym_g|Sg5{+iDstAGj8HkR5*<3>8?F&Y2o<^R_u
znA<d-gPzI+!|@KWv9Ymwwq__4@&#UpZZ=v9u<jmGW;R+AkD!A3HByEi&~rFr=(P*&
ze)6kVubw-9eroyC9g+xAL7#Js_$Rk8{_qJl7H}`F>K&$U-@ZXr+M?eN9f4Ji8@lJY
zsRJeQInKrrO1Y=sgU!4cqhg48SZI1``RCW^Fp(9c&j2YC?J%dfs>$Y`bmwKxa-GgT
zVzt;E$GF|)l5v;KP63ONQXZt%0ldKg-H8bVjc@WSEG!5nD~G3^k5=qrd~;LW5}GA}
zQJ28*qG03!Fcbm#D99ifsHQ7-=MqV&xfusqkS>#XifhInw%HqVUWlnbkUoos;@B86
z7j!xUu~@}$&o|dqIGvkNP^;dBtSZ(HouXZ6g#W|Ax}YYQ8FLm+mXe8`xJ~KKg9FEq
z4PsM`i-)g-)Hn_8$?Lql=V5v@_U!1GE3YeAqzI5kcp(G>)f%ruQHJT&)$p1c@1P%7
z0%Y}`dpcBnzYzP?5LUBYF|r;D&@oQTou7dCEXU+;7aB1)K7fUf>R+51f&K&1V24VC
z+oU-})pIPEr0JF=YyOa8Lds1@RvE7@U;yw*&37d$lyeFl%yM}fe|s-2dbBewy1#^U
zkGY+Gt3$g{>vy;3gKxDSUAbtJmLJS%j7Uv5XVpxtHi!hGAi%w7=-;S*RBij`#5a}~
z2FrZmHaKnYcl0K-AZ;7Y2-q&9$M$})Q2W~fIEGH!&2|geMJbY8S!2x3+N1{z1N0m^
zZ@uvMkN))*G7WiT{SDPPSJ+WxSxX^|%9o2H>Cj*G!$lvYRRLJ@VXqS$NzVF($v+-x
zIIT~&yh%uS*t_-j-6$q~OoF(lFu*>jq<i1qc}`2<BVaXnpDCIG4ro(>bp+I+SN{VU
z3bH0h=Aw%n=9M`smI`}wRD$}1ktW@>jz}W@%O_Hw;TX+@sR_1yUb}|Xdw5Yj!74&H
z4+;%61H_f1S5~MUjl|zYp(K(js@iNzJv<`4V`al-Hi;$w$uIsSXqhlt<K7Q)v_keT
zbgj$$TU%v`&d@ZzzNR3npunCh4E?V_GTZ-Tx~1O|oz67cg{q}S#sfOw9||!X#*khB
z?mvh2=4MIFVJMv7b)IG9FWxs`Yi+G7z7U1=bkxrscpZ#v_waKc$agE;mv+nREyp^F
zCwATgc!l)CkhTS&Ii$~wO%{p$_3N<#l#%aK9wM%O|FcBMW3sysQ`y-=8P&9<SK`a!
zm}SCjp<<yCu-5C%<OEcLcvTMiQqR*A^N1i4KeK0dFV?^+sjkMy!@vj1K=09EFvTk{
zu>hD>@NCtfzP{drsTDpa+h(895G>(JbjkLq%0oNr`?fm&<|HsuM8UGY9x!kZg~10o
zJ$)A-WQ8w&uqRWOH)zmrZo0$K#0jwVFj$4A_6elhR|Y-bOTvyfD6T7;!i?qG!#l7k
z>t~v4dm9~w?+%x8-b|KwIhQ!Dhpec7JbcV{rj;BuH9fuXEsYq3hlhuhRWnZjF*1oa
z(4!c}@p!Jx6YXmvy?;TL#;-LWD7)A{!e+b$yg*7X8VBJCu^Q{rNg`CS)sQ3<sPctg
z$W`90|CbI$hj{C4a(4`@t`mZnQ@xJ>xOzxJ>l_8hJJV*o`roeh=C)5#U;gvMDhkuL
zQ5l&1^Gco2btp(tO-&GkAtEKGUR;{TWW7H&Q6T?DCSrB0ui;*h#`@aY8tp8+0X>U%
zgV8XsC1?Eze}cg*l;m&HDxm;e8ZOEIr#}IT^MXW8JDVtA<4i_`v^Q8!OOv3XTWj1H
zNRId=)L{{kk##TyXaS4^g|v#?zyq+3t18kD&F9MIQ%t}Tk-1BIw0<TGw<e&~-XDh`
zK327+goG-~0ZxAF5n1S5B5iuOgljq_=ig-w!5a0e#dWU&m_=1?c8Nf_=?~Z)ucy?`
z1e$tH&;ko~lZVqpO0q*J*l4>R&uc~k?dVJxb@?o=45i70!)#4V6rjqrhjPe)l@}Ix
z)nNDt9jPZ_x>O!eDj=l;d?r?#Fjyfr9xgj4^Sc(RtF`qle3wu=j6ph}J_)w}`$bHw
zs&Tt55=V8=Jc>{AfKlup*qeV}u19B3Vd3GKcLUC%avpwt1!hM?N?nV@dU0z&H%<BJ
zh)L5!fb}}u(t>t1!EH%Nd=$X!_mDvkpi#UsZN;y9O8xKZ*}y78Ys6D-;4WO%2iaGA
z7-YKN2pxMk&Ho!t!hfH=@UKVeuwfzDk;7C0O4LeysLsjP$zx8Tq4#M9xBlhvxB6iO
z>ya}&3gUK{YCHv5p#>87sWWG`oSl$s4bW!7l3wNyxolnPOE2c;Qo)88z6qOq1^#Zl
zgtz!*ek&tL<%GiGVq(bvYH`JV3mmzhkf{UN8h}Sw!h2z~ZP1)lxqbV#FFo3BN@~fu
zV*k3ZaCwv^E1Yc16x~d1qs7D(OvN<^BNxEG-TE<+k-nXnG-xeD0qVZ=e8e3CohYc|
zPY@Hw>Wm`r;8&9Jb*Rd3r;dwz#%Dpjb^s}t-V98I43d{I1Z^QdQlFX{iKC+<GYx6v
z)_DP?051c2&e*gZsEZ*N&EB8_t9sRz+46T!W?C}cG4@4PL%cRxP$Wrt1iE3^xMgSr
z`@}ku7V_-jEZO(tvflnb2@RQUB}hylOy^d^`_D!kzu&><EkBRMU1AkSMi8Zbr%UlW
zsVXLL)AL~qLp@GOux$Bi-HL=4mdKcYHbnH#w|9~8-W{%8W7ltiHQf>Rk0)XKmu9@&
z9k8jKyT%!Q{|L0(tv;6Sy|0prkk*AqbiE>Bl$a%}JC@XCyT_D_MDs0N0z2G-Pl#`N
z(0p+~v9H-P_po=na{>c)aQ)TFMe%Hm?kEqB0Lwk6?w5IW)fxwS&;9ByI*L~}{Nn<P
zE~!=5cvH<$PF)OT?!0xlcTiW|<){@Ng7jTo)BqR!K&$!AQfl)B%fYqX`-|oqd;fAl
z{s%8#@NK1I@vjn`WjqmxlC09X0vlHUpj%No=ENVoN4{rozsXs?YNII+Hen0M=hFov
z?sMLETs<^h<>Lor5ywN`HMJ*-w_5*;EIDo)XS}z+;DDgTa9E0uOHCs%yqjW1j+15N
z4EMDAkK;%PF_Gw=Mzd&3w_+$&Ui8OjwZ8Y=P0}@Q4$GFghpaw_6rAt0^dwj%htl5&
z^gp=E|LN-dSD*6`M%+KL1|Z-GLPFU1I;4jKjj2lgoAAH&D^SKFt@D>>E;qv@V+XoH
zg6`WKc6N5acjz6~01(BRaKT9AGtFS+*Qe6r-_IuUG`p-WoSug!D)37Dpyu`E)GxpA
zi$^(=qGA-vP8bQ4Mp@oqVzMWft2JUgsw@;VqCB@8O><G{(w8)DaMn?@!<B#ryxYJN
zsM3RPh?JDSVvb_8bm#70c(-2Xtj@Wg$w6a6N+$N_oR+@RML4cwvlK#0Z(rZ&uySS*
z$0x|$_I7PEq^O~(qV0efeWzDg;$h?Xlz12+ML^n(hyK{w`xYe#eHEiCM?qo5sx`@g
zVRXYDt>7+-51v(c5fA(nq^XOH3IB4omj1bHesB}^lC$0bdstmhJUrPK8y~`hq#0<G
z7C>x(x%7r-$iIb_`y$9a1UBB1<u6g-1Ix*+MLr^ihAMmd5H~*moJ^eY#*ILjJ=p^T
z1OU?PG7=vzDBs8%61Ss@GVjJOtarJz*5<tP=et#6XN=`;l8^&*<Bfc~{wC2WHC5X)
zubn2!uTlg#`C)hE%jl5OeE09Dc~<^LKPea0#yj}*-!@X@!GD!rcK=whuoBFx<etW3
zT8sa-fP}1fDe<p3PW>Wi#HaIN(HSl$cmakUSg$BO`@F;!!Xqn*fBdUYjDLSGK*8_r
z#5R+hP%B)ZLFql%owzw7E!8Ob+V+f`;7dz<xf|z}lRtel&v@Tn?eA`#<H+s?r*N<E
zb@z?AJ&@zQ+R28)|BsVUMw}QS<EVP;VWC+@g=zfFt0ql(2Ak<I@(Rdg?e|E8o+}oo
z>+E;z*uQ}*n!o$^DozV(Vh_`A|Mj&G6OymWYA*b}Y1z6VUwYT2MPDsU19GNk=L8$e
z+|fVqpSTxEs&f8HF=U$666PkP4xJy2r?35<b7-b$oPqD~!EgEGiD&rA_&@5(XcV~z
zvt28kAL+==RBGJY<`Ck_y>o@>+6}_eQv<7iPWw=tB-$nzz*lImmM_Pu-=P!7tD>sU
z-mfdW5NLZS;#re@uy)F3;68^O?%+J@@lvVV9~=CilO){Bg~eo((H)8;=!+4|XRMD;
zoDZ)H$zA(xCs;(B!4MFyt3O-fJteIC;l5)xSL8-FF_pds#A#r$eVZ8B4$19VzN;0{
z)?ehiC>SaEO|0evUpi{o_ebs7?|t((#Y=yEYR0PHt~=s>f6aDJ&u8~=r|j@<V*Of7
z-n0~nH16Pa@B0Gn>ZTS-eGN!37n9DK<p29b*Ws&WjqJN!BV17w0Zs61qNFd&?fo3@
zDnXM6NM3na8=NiXZd&_Q%p&xk54^V9W0pbEiZJ>buuAjo@BO+66E9uHyG&Z68k_Lp
zq({!aPCH&`(`yf~27F$k7?zY_`kzEGqi2wMWB+f)k)FCc+I=yZxpRwf&ZEmQxKs1H
zHb+|kq%Bi2pYT<mxO3D$X<nB2uq8qg3i#q2?d=h;C`ewA*O1lYj#pVulXTXoYH@ra
zTYok{txCTEzZdy<XWYi&;qc!%<3BKidxfxglO2gw&^eE5^O`6F0v4hr-?6;pzzYG)
zofoywhnE!x@cZ*<)dfqWBsNh~;2)QDFd6FcC1%yLV&_X>Wz|`Yyie|&Y&~*zKJRyo
zKXOX(UM!Im2Nv_3o`>5Z&C<PDbBC$Tp~t(M`gHE~^a5>rauT%kgsj6Mo}jmF4tn%f
zbL07O+uAK+V{6XYES*`CZw#l%Pdnsak2VPFe?ube9eY)a2CXK$V%cNab>>q?3Y}?|
zWlsVfqv{Ib>dOMH*@Bes8hM9Iv%d9;R|F9fg$|DI=U<X!VTO<mwmkEjWH9!8&k`!q
zzI&+k);*Sitq)#~%T%mn7ceAO_Gui8FI|2+T<I|I0nd&9OY5y)8~h@-aaQE(6N&)~
ziDIi|&R%4lh(XRJ^%YC!$Qoyy`^!G)-qIG$yHiroBk3^vI9;=a)t0{2>Ga;&+qwhA
z(^0YPEK|}#{coO-bnMkfWX!i$%YAoKRTT$TiYnBW%SkP_ekoI);vKT8U9L5+t<Ukc
z>1HblY`FdwC$sjOVM32Ys`M!NDB$0`rcuN`=epB1^&t}GJmfq_aGuv_I)ek&aLXQc
zj_+oP_@o5eDO#A0pY$)UarPk#p;Fk){nTG8ydhqU`>-_IQfxiWvgTSdcTkky+LJsd
z)0ZXBC!W{poK${EzN|Mp35?de1$+$UmHFIiCs*8Qk_GNHPt*J%>ef*fUp|*d_)!y2
z0RI`v8@?gw>v+qMRZm)7+43dbcf$cGCMVqZKetk|M5;bg@tqJawPyc@S32_bX-O>=
z<+`!lZ3aflf&EW%{m!qSeS)#k$=Tm2_b$~ANAzCtUrv2$zE%HYX~%<@l}>eHIp<KE
z)15AKvjwH?MRz9hbre2nqtmHfk5sd0_8!>>A0ixXVG4_hr=xMvl%4D^mMnWpxEynn
zT#v*;YcD!-IGhotczqP#IAQTT$optSgg4Kfw&-3LlW-r+;&WmKp8~ChSgIT=nu{k)
z@?Nq9-3}~yqUD=zYn|Q?Z99cCY+M4b+jf2bHq8uT3(dF2!%Ziy%epf8&zx-&?4^Bi
z;^nylUca8KcLuJ8S>_oLe@opLlauE>PW5zctp?g^m1*SN$sAPGyECWTUE{bu-i&tn
zX{2h^ztcXKL%@~SZbI6}X4}7|T*b!6u;`W7^F=UYm6fc9q2<a#!_~c<-*=Zn3mi++
z2$YWcUx;V#Mf@>7PuqQb;hK_h#%I;qquc#rA<CF&v(diRBUH>nu~L_87rAL+llNs6
z`+N4620pGOEpQ*2$Cd5s#kWvrbUu_x!$Jsi@Ye(yVY+GboAL0dgk6tIc{<x?9>lTc
zEV<L@yA1om%dQs@s@85}%CK!?c=fb>i1CwC9eWKCG4t(T!tPySZ#6r^DiZB`C4%?J
zufT3v&FCb}<NN)ueaC%HyRT)NMeEMsn1#erxf&MC#?Sf3*Rx$8Eq2~-TGfge_cEL)
z2)pM%O^?!eZzP2xwa9Sdt9+ky;1zY*+^CyE?vIXZ-K<Zv=isK)`J{DcLiRXP+k+Eb
zHom`g%zo$(hoydQY&?x>S@)<WoiD241KZaWD$9KE!TYM+s6$Qa9X*^N(_yZi#Pc=v
zo$gTXN}3Zm)Y-Blx(A~g^w!ary<@1#b0*b}PO2EMMbtI67}^Rkil<z;OS~ylDxGH;
zMG>%gXO(O62L%<!hU<uiS7}O#r8al<j+r(rd3&2!sATv{Udx#rT3;4-ezji@f=P47
z$+ktV?A#M=;U4|PW?n<Js3{xvC286{X@OGrPd;ytSh(ltH?vUQ8QJH{a%~>_N-MDh
zG0iPSVyr_CSGgD-e#reyYhk;esT1sBZAX|u8|>lrBy=1H&9SMejU8TEDj8GLA@6f+
zaHp<tr{|<_p%|}#U8{Yo%h{B9kA}^M<Hn7}zj>xzxpAzv^Fq<q1J%{Nwp4tG)d-Vr
z?)Xb;6Q$C}8hj|g;SYEz2$F_eHGjL10yl@XR5u>7ig5isHF_AIN!zcZ-aA!<q*Je>
z&{rihdNV~bA-5=ZNza@y>t8GiT(ql;ous$Jx|vYEduMih=i{oJH2E3qi7>On7p8~W
zCKi;jvTsFRU=GOypQ&W5XlDd0tflvOp9*=LAbH5}M(8N<`GmsV!8e!c{@6&muCkoO
zIbYkHly%6}k8;6&eZ^P0vgvg6qz|0<ro`&zw6~v+?iDjlk~S`uX<Olw1p(*QWlp?%
zes}V+jn?O>liL9b^;~14-g2d*G{N$70;eB~iyuq(QkT9fSnRg?foA>kF$J4NarP6T
z|L0w)6Xu^@+IunwD{2d(zNMwbk9&!?G3zg42MLy>@?KqaRKI~m{f>GX4GhxSNRr~|
zb0en)(nEhw=$&D?xJ0RA{_?&NuPwvcf$OZ8Ps!S@1nC3`-eGKQ>)=%bdXd32kt+9Y
zL3&qX%EMSG^fCYVSv>y4#mhqiK@lGH7avy-&OT(n{+U;*-zViv?s{nGN!f=HjT7^t
znNORY!cF@9bfjdoS=V(9lkX4A`kZdT`YhVtPQD-PVJYNI*|S>}HQ$ZDv0kIYe>rFH
z^x@^JJdf9mnp1GNPcnM6MVPLsP0w$9pB9?rDZi)I&Y#=cbv1m+HDcIo+>8miW^WWJ
zl&lQ%*0TZ6CnhEyrLL}>`gNR|lY$y16vNZK>zXg{Lf1ILgd~si=LlzJi*b;RaF^qb
zg$zl)Xz%p_JG@c%=Jhr9%>@sgkKNw;qOLT`DZVc*ls-H4A;tHJhS9c?t;G%XeEc8T
zZWS@R3PKT*slJ{Y2Wv?Z&&1z3c^rf~Rh!!9eSZ?!?Ts>LTN+7hG+}mlc}SJfIaRp#
z?S$^+=|M_CgUiY+nYJ7}ms(hful$hwED-qC&Gg0{Vqf-3{k8)-S!Ltf$Ko8Fv#T22
zrGj%+0;$5}lskvoXC2F0kB;%QsE#d2Hg|I&n}qTG+LY5&sRhdF3B}>LeK9;A%X9im
z(%Uu-PD(#po{p9$v*)!|T+uDIO0!TKw~=+0rSBK@|0v(Kq~Lr%-}z)sYUsq4VJ^k%
z5}P4qtD;K7@TWD_X>Av)kKItT3Ix4ZW_a}k3_^XPl8rV4&KVvbvRGn&u<hU|OXuwe
z%tFywXFsVIZEm*7&MlpsW#}|=aUZYo9x6~5bh{C>f4m@sX6NJ#6BtjC?hJe^=^+{=
z)HgYhJG?N$vN|4q@p7@9bRUcOvD@0|o++k%Z=!^M+}YD0yjozw5FxsU6DNS#t_zfv
zm1ws?EAIEM@?newYs&)bl?Q`H_xMx_nrD6N3+Y?enW^$0d+mGr0(vvO*UZAR6)FD3
znqFa*p6>Bz&M7s9<pwa`z2g>|BHFOIqH3vERQ;(pUfsR^ZuR<F-`Is>&f%`#$GMor
zLb{y6M9Fa#y?xJQp3jcq*|DozhIe(mD^FDk7n_f+vs4~g-pDe~Dfl=O<R~~N3q;+K
z%(&yt)aOETvXd{u^Zz_0rIjn&**~^@)i7^JhQcr1$&u!I;h9Q?K26DC^!?)lgz9KD
zQW}Xc#TWByQeXla?W*s0_|9v#GE>-VUrBU}{rbKacyN({^8LXk_5{cy5vN4sRAjwA
zyT0mH!3xI^Wgc)Ijf?!~UirPgX57*{vC@=hD>NG^uJ?^E=B&Q3Ev&4fYvV=ERfCZ3
zlD}>3n6DpA)u`!DXwcLKG7coqnMlGtR#ENd_`VqD5^oZn#F=*O?QqG?%AZr)pQ>Tt
z`MRvWy{lrTM`6gxZ@I30X@L0ji+CW2q96A#5|Pm>T3K-bDe#)GZ~|yV`q;OGQdA1N
zY-+l15HHRO_8G4Z$(G}=Rad~H3Iv#Y=T|$`PX%sNxX6ZWC^Qd<9FRuLd9M#Jcj5>0
z(2!7a<}w~I9?ZLGMXYP9^R{Zxd-V+8!WyRIEA!;fOxG})qmB2og7doz57n=lqdQ6;
zNt2)W({xMv2yJBCUqe^eURCfVVBHudfX&b^^Z>FW{VWUyxq<80w#8#%VbMHkTk8G#
z^=nci+Osl2-z_>~o)Qg=SLk^|3ty9|Ta9J=lF3vEPZEwIR>K;vMfp<SqNho<UQM^-
z>ZSR0Vffb^`QIP6ai^qw-2(d`(&Jj}nt2<}7f;Xpk~8VI>O9=iE^<nh6IxiNp~S}I
z?jEGrd~IFbC2Nkm*Btkxc@tOpP;-}TEc>Cc)$Xm-foUzvN_ubMP@SVq@ji6dCN9lf
zFG=U9Lwqx{Z}=9++ccJW^OoJzD>4dm7I4YF5;dM~Pqv{=(FPs&f&?Q|)2qZ}b4SsS
zfG8@uiAATYrf$09ZzPBn2{6C@=s3=BpSZNYDZaaGh{jn@jF*yHkt}az9cS%#r10K#
zr)gI)btXZd@_SF00Y%%F+&m|YN7ZGzTKc5!jfveQ+{Jgg?=%)4Thj@o%A`2urjctm
zblGGwTR7?5(BQ{kuGH^1pp!^aA+r+S_q=!Vvq<d5_neK0!W_kKKXP2xS?6w9?s<hX
z+%EN<i<R13nc1Zso=%81Bl|+p%lNuh_}!rAfoi<&_EZ5?-r;mplL<`wO^fuo-}h6$
zN#huX*2_N+RIxuPn`{3VO1jPv4rIqIT4ki(UHD!qm6B)m;!*tC>qJ|E&3xkFuKRxO
zFUkiFgC3G3=e3;orfpY~Rkk4M^L{auXkT4$#K*nC)xUE<+HPJ@cCfu4a$nC<=4Pjv
zAsNSd#j0Y!w8q`tf$ut|GrUa)Wm!dn4{lw^B=nLvNwkmmS%O}Exw~sW+?#og-^d?e
z`0ik=G4zgsa}NT9*<bz$RW$|YwT8pBjMq4hecML4tWy4}xsecHn9}W7V;Xk6!1ysH
zxyqb5e%tcK>gc1;6d!x$#c%?OwMv1$6C9f@?<!x+MDfK{Q(|m{wJ0ynJUk%liVnA0
z9ac+J>t$TWHZ_<{#moNA*mV{`4G?!F)*iYLB`h`Z-2D8~_#R6o4$Uz_*(qkCFXlC`
z!o#rUdE*(s|AXZ!{XYCp1lR_1$=d}xJ#fv2<{1!ffbkmxg!2adei+cY;Z{0<*tqHG
zA;*<KoX1*Ntawtn-cy9YoG(tEgxBDWU;42i;HslwJ+<RS!*j1Q&HZO=84P8nwP{8w
zYn^n7eB5>Gj`ayCyhN!?A4wXm>sQm^hozTgn9Y}@d=DsrOBTI4xko4TGTV~lg2IVQ
zwue>Ao@4t@WG$(OPZ?<A6%|_J$SEF04tvVJi^`VXq~y@P4Rl3Upojk&EMP`sutq@i
z0tTKxj3egvcY05vnbPYbiHgzZDyalXzMnAn<kra9l-cW%E8R3H&A8KlE&XZ4`NiJ_
zyIy1-jv`X(-K!j9&whQdblZO3sTP>^8oS<b)~|l~YD&<|S3}A8XGOPuJ}{tFb{b91
zk-1C#4d1WCx9F7O{-tWA7vZaGho8CpwespoODQ`O`7F*8pQU}PQ-nc=SDgBs#W5Q~
zAnq_@cR!5YbiZlOzUefZPB-h%-1*gZVR!lwObI%^Xr9_v6`bY7UI?g%mU!S+RK@Tm
zcnzG9{uh1czp6d|tN(Rot|sW8FQgI#%7H;1GF`c#zCG`J$6EdVN&^<A;&_2!#jQ6V
zLEEx%87O#z%iF>9YAdUqK!j*JI@~`+LQ;<@ivCrWtb83f8bA%w*{fE05@7Q{#3T6U
zr0(~#<EjbE+|9N?*g-@H>GD(z7u8nW{}Kt*)z!1aWkAWAJ{~dzN4|I7q5RrV@{z7O
z{mait!*E6ZGbm)NsGt@H{~|A}MBd)sKz0RwLrqDxD#yQk(G>gg4IF_FGQ;su>qgc`
zJK^s#{p*X1pvxK~aPvMOgPIpFTq=ZjKY`vAW`+pk5XOh(=g!@RposK{ZK}2?L5_z4
ze(rNn&XCj6h5*+OsC+_Qo1hNq0|6rRw__Gh*8mF(SXBrS3g*v^&CR?ZvCRLv2$N@|
zzY8R)Bp@as;vnFM`T~n86%ktwS{3VggA7LZi4&Ki2<m9J+uI)K4(EYImizGQuh9yD
z;Sw91pb8KGfiux!U1Cx)ya323FF%c|!~_PIq%?eipsfP!RoS0jg-a4%q9E|w&T{@c
z0JqGq>OTzltXpCYlWCH*P@Kk{pM@}c7F{f}os`76=B$m$gW3Z|WA9+d2m>$&5SYA9
zN?Ni@0fNEI<9U;CF-(~=3K7VqgSR8}Y#62khwb5<)0P=w)^QZ88X}_v62K!Mg&5@7
z9km~l)KYDNHsKp+B!F0p5M@BCG7sv)rIE5XFfUarvDUXPUtj^=;KGk=sw%gwDPT-@
zZ|T96&jE4gEsSW9nXb@wKB)hIfxZreGzvPp&Q}-NsbM}3YGcuziRWfxc`#il1f8^j
z*RELt|I>D0Gn9b<aj?c)0z{lVh`19G`_RvO!TeXJ+>sT=iR|BmslL()j5<;PO*!4L
z#_M~wRyYiUH~#dgAc9EXr^5MB2f#d-$Blc>1GK_70twZh)$!DB@qH}s@?f>6NPK)e
zq7dT)fg5m#qJh|M3sMo}I#MlKfMzjT!;T0WKrVui&{t+#s}8H#9_zxO|0V5K5|0TH
zP|XqX&$HOwJ@;&wFg7+deFJVQq5`em8sBfeY-0-aQ~HiZ3E<U`UgB-6(g%T(s?A-w
zlD}-))`%;Jwg5Jm(uA}I)U)yZTOh<>E0|}uAk6iK(J^v+z`}P;S%j%8XjjrnExpMz
z@PSOesHm<UB?QybynQqpEmm9ug9?JUsHiB>ZXw_ZfQ6m@bASj8%jOa+Ngj^kvs+aZ
zdV*3V0}L3#C%SA!!gKEngbHq05v!mdTaRA-41+zsT)Q+@HB4=S1zy7$Be1AhaSYIY
ziMYXrxprR}zWwks5>cYY$Hm2+&ocKS`56ZM?nJoCi#wHOht<3pzw+gP)QYXbjV+E9
z*SjwQsO67l)8IWD(4g-H#1VqHzrqa78ZS>^<VW@9+2_fBqBHMG;)&I>4+1W5jMn0l
z5FS=mRt&5V3lmd4h$|D>^GfSIfRNctZE}`D+zRA<CY)t6=P9VEA1B<h#31UL@J*oO
z|A28cGLpsuUr`Md2b+x)DlV0X62__T;{#@3RoTE$1N*dORFi27Y_l3~L;{!%B|Od4
zwFn1n4t9VSwhgT!wiPAhzMX^U|CE5#p?LeYPuWso2Nt-mVqLCt*h^^OP(KraLAeRg
z0E{4UE{kJ;mXQJ3fQ69}#s@lmz={y-7M{zfe;E%Pgv*JY7@%uvPqaii#w`Fl-FM8x
z|3Q?qS)!0b#wjwgZinL*25&2bjt^_9mBdCV`(W4(=I)3(oPvVF1ZG^JJk5w-l~uDi
zSB!!xxZ>)k#LU-LGS(?BQ>XfX5kIAgHY9v1V{c!GhXwvJBJEO=l6nEs*kGM%57(4%
z)(%`WkF>WEY_K^B5j~c5KnwxWUC{dGCK|BuN+EDM)v{Etp}h`Vp6P&4K?$5r2_|hy
zK$Por=oWkS4QC+7+U5+xik~P9NbWPhOER37e`aXq8_WR<{AOP{#?&+pSjKV4#sSYi
z@x_Z1n?vTQ@xTMD2lHC3Ikq-%TewzaH+}C-M1)a>N~$%8>qI5(fcdWk`e7_^O*&y2
zI)NNu1K}Bi!NwVf@L=Fl{$hF%XCUMc49w9mK()B0dJMdbc!Mgpc#+jg<e>+(v?9(}
z>S+=*B%QhBXJb6T14BN6JQHCKIHtTnBIBt!+)k`Wfl|yibrqN_Xb=wYfnYUjsQ76j
z5{DEauZdun#%spa^Yn%kQ$&Y=(47E7#G%Tgy~R1mrBu1|yKGi*K+%uJ!vYEI_XB!L
zN(_hztdSqEj_HE@s|{F)dy3!%iXI*w4?d-4zW>reJ&;%lmpd19J*9PX1QxBT3{I)=
zrP`I%N(5mEsa3f-5yY`5CAj>-h#ntoB4Q+=lr;Dk14O^{fs<;5%cVUaAW?#gj2Cji
zWc`rPy)zs+%8m$`5XOBGuzwNTQ3I(Ekd(UgfI6|tZu06##2$D(i6EH?=Vh-ffo(Dc
z2}dWg;!x3bf@T5>#9>mSmuKmIdyRnTuM=dYSl|(l8d^b8QUCPx#)30Kt|8(E5gZx<
zb%9Qabu!2X@=u*UjZocKi^?%LrsctcwA%TjMZ@DK^j<s0IA>&Ut*mlnRIreJM_21q
z#CIDZWnIqf)0x^5XpV#EU*T?Ah=+l~cvrlefJ}5^U0RHnx3>}!<H~Z8d3OTj`?3Zs
zK)*9aV0da1#d;s>$xy{ZR`kONM-#}H2rnCWA+hZa)&LR_dfaz4m2dD_RiN&D=~!^I
z2SQ>GU|oP9sf)W_$A`}l9W!!cY+IcQcZR>^8%h9UsTJnLw}Gr#2L1+`^^Q%^iSjBB
z>)G^o5CfkAB>nUIN3h6B>GQhh#IbINMY988Kn<<E6}Ow>zVZ&_n+PUEFazYvdBN0@
zF|GTh<B?D#uLCiA=AnwAw+#fEVE@xp8{inAPCWCEP8G<&OIxDwLg>X3^7Jcu-%Fo{
z`WmZiQ`H2P-2kEvj=r!Z+&G1bXdQ&Hd%$1<)uVFQo#Ax-0Z_4#!=n?-V)bJdr_sE;
zF2L;q%|0Ozd0|PP@9elBY8*SgfU|U>DcO*u5j_a-$r15CIJyN$hXJF^BRY6rVg{;t
z2d)ykrwD!mw@ZU;fSd%rt$cXOR!~-1c@Fd$jtr~t)DgIf(P2=#e1JrV$Sja`fdiq$
zR()G+n*Eu;=kl#5FFG+DJd5d|&qo0aiD}<N9z6j0F9wn?xAjQrc?oahVJ85Yu*t|X
z1hl_AevtCK4AFIHYiq}!v0}FpDKvl0XFY<1mUA>T?eC?7fBi$O(&g0L0DdV4Y_)}3
zey^X(6vK@GqjaFBz(fXO$AeE>-I_hl5WR_gKqcfxOLh5j;xyT<sKb4dSKAfG0AGMR
z+77~G(e~Vpu~)&t@Q?yuh}vpp_GW;A5ZN#Epj=aG5dIe=$;8i}KdV0WRgf!YF2SY3
zxc>}fovlNyhfbZ)zy*<yaeEZ2VzO{F_zmL9fJrqz#s>kz$ZGJjuUSV7IRisCqA7t8
z-1+mX<z|w+{`pk*AK6;C!J}Vk;nYCt&9B@b0X5WBAPB@7xCO!A+-aW~`|!?>%C&(I
z021lTi|m@`;6#9N+7XKY{UX;My_li@ay+<V8UV%0?VpxF*eFy?ae(lRkZeahaid5;
zN#CILw}|aqxC(7Kh_Hn~cz|cO*o$>hHy{)PZll}rp?X{^izXp<-VI3Y1#MIakfpeM
zgDRSUhC9F@mCxxagGBK6c_YZ9Ou%-z0e^(Y-$>7TyNn1Qzz@tI2hq=pJX`qy<Ue||
zF&D!--wfV78*>dvv@Q<<aOfJPyIggVo?cm2_T;!Hjt;D|{Ba<NF_>*R8KYt#y@7eH
z<8U~aV-OO*1lT|0avY7(*ZuOi4iZVqeAL`*M{FNFcK~@PNe_T98h)!*a2|Ww62LpO
z!yx5!#z|@9>BR#}joYI4DsUdnA$&}yENCR{Q8oX^6B!UbIHD8=GJ7d*c-a|*R$^W<
z@a&b5)qE?^Ujk7Zx+~qEA#Huq%th>v#2}K%@GTp$^Xk}BI9dr{A@*Q*vlH^`-~0ud
z2XlD86L^BAAv|*cW-$;{FksX~+{gRl$5?n8f>>T1#PI>>1AarAHyL0ne-DBKSMU^T
zj`p&%pg;l0kSb(5;j=#v(mexY=lDRzDFCQVpyJu;_QyU5G-6#Pjti;;ac~<kF8aa4
zVUTyx#`Px<y=oCqZ;Ku^ksu3&V52usC5S`Du2KY56&4_GC;TV@*zFuY+7?jw3XPW|
zZg4|hAmQfj0$D}O0BvXyz|)Kf10ifDLg-2W7G*r7q<9cH(N23;ZdJ1>>Oz`^NZ*Vp
ziU(;W?|=gU<PK^RNWM=&7Gr@d6!IJi<PyU9^Rx@<k-UoB`@#0G4W`bIFazQO0>lc{
zMc`C3t&wxD6*v)w|JR{v&x%WYk0TJ^3W8<88P1FSod{(Q!5HIS`<))^O;js5M0BU<
z==f!KAu|<$vYk*EiV-!^I9Q|Bpql%;F+c}0LUQz&+u}_SET(#H$H((OO&BV*OM`_B
zcbyIuP)wJP-k@93>)D&Xg~0$#p56@N_bt$O&4I)5ia0NE!xo|8{~6%WD<%;5g(x8X
zQ*s$t72AwkLve#aGAj_PtU~NUXAw;d;_ID|l}6E)MZ}6!QvPSr&87DqNI*Hn!ot!F
zFuw_+Y=fTbZ1fy(+<8G<%hybeV6kwECqohrb6C67d7#*KZN-7@AHARd2q;$TXS7(H
zP)RDNBEucFmWKx%L7AZbTW7=>c@oeZlqmuLgAiF53maQIQW<sg+}wtQp8@3)%Z(eY
zzyON}@6>l>Ea56P0b!SGHKw{Z%nFFqeDLIs4DiwnNEc;Yn2ovp_Bg+iSvao%{Dp;?
znR#Gy2if6)+HWwqQ-kLX^Z|u;6LNzKDTjWISCs{bh~QZ|2rAa|+MUH5?5xut)8+J>
zHPKT$1eTaF5WS53{QMNd>BZ!&_|=Smy8$a3fF>^P^Ji{~bLWiyV*KL+2V6C*Tq4l6
z<AAt~hLl0877a>{C-g28csOioPtX0$L6h*Z;R=sk`@XN1S`;)iPoS<=0s|MtoV!?Z
zM0f^)xERpoHd~h@f)WmS3{heWy*ri}p5Wlnj8vs7&LMOn{UdfQbbw05o2duR6A$P=
zOGaD}f{;M0zH_|m)(@@Id-l{OAq8d{_Yp3o6bPsv|M+wf>;s;yC9j9Uuz&&=kz*VH
z{$Y!B&>Y08h0;THZ+m4_0iHVnj&luIu?WE(cI^lrI}$tSp#JX%K@rdhlGoi1!y`$k
z%He?#hT2g5!YQw9)0Sg_UI)sjl>bk%x-ZAXv($T6&(5r>!{gada?;9Dd6Gtc{})E;
Bs3-sc

diff --git a/docs/_images/a17b221991c8fe26eb7f6c3320065aff20d9460441e62fe8c1e0623ccdeb4808.png b/docs/_images/a17b221991c8fe26eb7f6c3320065aff20d9460441e62fe8c1e0623ccdeb4808.png
deleted file mode 100644
index 091d046dcc6f1a511ddc48283c61eb222c4ff15a..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 23131
zcmeFZcRZH=`!{}GgzPRvwg?%Sg^WlxWha~LhLxFhm37I8WR)#KLXvFC9)*&!S7v6(
z$od^;@9+Kj-k;y^{@wTEd*A=w@5j4GkFIr|=W86t^LRd=$16hTiYg@;6B&Xal<I0q
zdI&-wjv$z{qr~vaT+z>W@Yi_{<!c`LF7_VY*6w!5Wor-DTP_~AoUU_t*}30wa&Z<H
zk`xjZ<Z$%xaJ?ffEPVT49}seJcMu*XI~oo@Lh7n!d<Q|Ot<gW2eEH{22x8o>u5{7B
zCv|z$+s8n8n0U?a^RA*IKdE{wZbOLpnUON-lz`qdHQmQFM~HlL`IRp|c%ZR!nx0Nq
z;o`;Yqj<V|y&=fSllK$|?jcXdGFBgk1{mw94KA&yuZ(*x6Up59IOyP|U8X(T-K`se
z$KmmKwJbp`Rs@U1>iUYLoaE%>RJIYjq@<+upw%`E-lmK0pnx~|nBp1XJ-xF$;_%)x
zM=g8wt9?aUtP09qJw2-a{<5iQX<2#&TC7y?@dO;6gPWV^!i5W^rKjsxb3gHludlDK
z{rV;Dc>=y~K<wt`w)Xq?8Ly`r8QoGcGK9VLj6y;}JTd4cH8{_oXABGstX^H8GWcUV
zdyvb`z`*eL!esi7PI9s!TL0hsGs$Ha*QepUKQdzWeP$*_nl4+T<<lpct5>g@(ci=K
z8zgAkm%V-+7YoC<;h`U{Xux+~N~&>qm{~$XB9AH*&tJfw*8P2Mj*EwfI59DCZGHV-
zbTsAR{ZnGcuou0&B%H@;Ba)L(93di-bDtF8%r49S)S(5h|NQl9a&C?U{?iY?WU%mU
zc(`e3h$%_fQU%^zT3XU#rNJ61?unC5SVk%x$IDwP8T4(N{vFwu8kY7jrrBcEL>$;g
zR-_n_MJiKx=r+5L!E7v;VS1?*E+N_&M`VH<amynOmqW+iz+D{)L!^kT=nzZC_@|c<
z3!=3%xW!h=2s!bPrKMZ?;R;Gh8g7IN95~^uy6$q)A<fI<1o>Vi-R;TUvPw#^>1j7N
z!tsx#TEBg}mTyo<@bF5SGzOt!lf_f9N;i&;vBA(Mi&ztU`t-?Tm*mJ1tCf+e6BqoY
z`fr?5dB{eIe5>^pXOg&e)YR1U2)w&K)j}NL5`oXBX(#SwYW#&%VDL!kafPF};;qH#
zsH7COM{)7t#NytJ`<`55KS)WQJ_=xgOQ@--^~yB_?n_sD{s@CBPmBj0D)*$ztsm^J
z+I)C&uG04xPir)DxZ8BA^=P$cbpZVtlMqI6d#gVi3kYs)&2?jSoc*;!PphVIT}Utq
z^;ERv81Cs)<}hk@=iUk$Y~1}pO!8H=D#VAR5i=b|i171WPQnpz^YUJLdG%6GUt>#)
za*2?*IIXCt=urxa{xh=)FfyAR-N9nw;(Z1Byp=UI({mX?t!tA_)-Em&69kMFD|U8Q
z8~R?^s6NZhefRMr6$XQG9IHKF;XGP6Y`-?~4!!61@85ga>E~&^D`_}*0QZ+z;%1P0
zeDjWq5}DUAg_`S&)P#=u2T6P@ySvs)DZco+H{6_KKb#(YJrfznrOFArrs42FMo>`j
z7#mwme*WoO-%2mOjmFPAkLol81|SMAuD;xexwA5IJ|rY$KH<&HuT))$XD(S-unC^&
zqG!iq4aIh5ib@bId$w%7g3kU+*U9e8eQa@Q*bn1UjcFVlWW;R->X+1QGVy37>salY
zyt%P(usT1VZ^X+<w4!O)A+wCf=L_CIbO?Lt^ya9RpNOmEMY-JOxB4~v!DqE@tMty?
z71_;iHq}32LME05U+3#TzfutMHS;3j-u~A3T{{wLHYJ#_K>>&&httFpv>fMU86~U7
z6x^?h^;g{R3G;ow!{=~Y(Z)9Q!!rekkE!o^vo48xE*hM@_3hZ#63e#VKfb!{Zr;{P
zlRh3!#rpo+D;u|;-_^}(eXzq7x0|-trz7QNzjwsH^4oH*Jv`XOM@2O!Sq4VTbR|u{
zd^;wl_W~jlcI4hoZS$u5ZC#(eowmNhAc20rdbY93UE-<X=BLjb!aAY|SY^B@78Vwg
zWxR!I>*_oo2JZjKQjh2P_SS`6$f6d%xjdZX`)f8?)P@+|j+C>Hq(4*Y^qJ?@NF_F!
z>D>G76!G;jzg0ILS}b;<>dqWhYe>vHYWV})p8qnEvbX2&|9X;H>tNOP6fZBc9M4Dl
zDM9jVvX%_-?9Q3@q2xY$>uuyO^$QFtT_*|d-@o6vFP)q6p*bB5v;41y-?}gu^Kw?+
znTx^Z^j-fOk-2B5uK5dh<SYsh{0+wZqSP|f<-XZ#hU?WHiv-ln)Lg2~e}lHhJM-z7
z=+)awUG!&ucLon1u^D~r>3Uh>z=Nk)91ZT=&xr}rsTyOPWL#}FDM!?*F(phEYf)<<
zyH?&4`1MQwaltv#Oqq%GL=ss8Hpg4zC)#nFD)C&aUzi#Hx&HZcIBuj6bB&yX6?X<F
z+B<e`cyRlqD4IpGKdpyJWTg;r9LIgG6Qe!D-GXUMP<nnPO~h?VY4jHkhX|ThXl?EN
z`Tb*ltWJi7l~wnp$s5itwI7Z52pvZ%MT=g(?0f5CnNzpYl#xSoTGXCX4DmzmAxz`D
zUqfzQFLTIyBz<=ye=O})l92g>kdPy(vc5Do-c+}X<vxgrcn7l<`{c=k8t>JqoQD_Q
zf7X^apPjz^<SZ#fmZpzsGLzrG+cv7b*<2Zognv!LpSuy?6VI4h-M)Q$?W^B4xYOPu
zWAVC>B)nRI){ywGua-fRRdeaV4<Aw+@E;HSv%p(-7yAyD|K#*Ep`V|h$6`OJLr?m-
z%cU(Hgry9P-dhJB#O*{(R#sMAU0r+S9>&C|z(&Q=(H)_te#qISA;8Pq#<8B5R8k`B
zwK5VxNJ3>bRPJ;Q_IOnc11oE^ka>0E*RNmm>#i0T7rS~%yd!ep<RlVz5{pkv49mOx
z^!m=vna}}Yv&v(diGuHb&UCqL%<KC2`eylUt*EK1i@HB+`9{EjC^#U&EBnl@CAIe<
zXj#wqX1Th%-+%j7l3v)t%<3tLus9I}aoF42i!Vwt^$JA%x7QTA5QUt+i7!T$q2b{q
zW@cu+xta{A(w-XLBZIFUa*SWwU#sytbK`3<CFB6STEy1wpC2XIW5<v;Ceau|;`xBY
zot>TSwI*ua=T}(24Gm>qeQA;`>5^W2F!bi8&q8jJPTgJ4%Brf9r%oMt_39OZ+`M`7
z+O=yO($Y)<M#aq|Rd*u&56jBRM6BN*@$vC#gh;C`_nR(;O^yt~M@NTh<SOdv(Wpe7
zz$9oG+FpO0mKM#YpO<O>;fbq<htgAt+oj&C7Uug95Y|WT^km)ry@<Zv6h`^Vrj4q(
zwKW?eB7$4|^5RF`VW_!Ks*HE>%CF6>t+pQd!>Ff{E}U>*SFT(^mthR6Ox`drA0H{q
zPY6sE3kyqcrJIfa)~I*&pUI|hoALU9?d|D@fP7%^JXUR#l#ZnP&N51!KmYFYXWC0)
z6z^V|zV+Bm{650PDJCsSi`f1ccv(FM12i==!_Dr$cCT1aTwK5Z#+#yRud<ulzBryG
zP&mtU`CfHY6h#Cc9~%`FRYp{2tYpA>Kb)=5@8JhKnWdcCgFio}e*6%ywzhWvv*F~s
zIq1;R(V?z*>5}L0_U>-ir(8{CrBkA!y727W`@367utBOIUS`?Bg+CRW%lNKT&3&Km
z%b{Up<csIkrk9kIRM*getO=7Fk&~0Nu{5Y3!!9ob`+$Ev5C-E@iKYC`)_Bkiq%|60
zVd0(Cpu-oDzMYTx^k6cL8v^T;l$ARU_IK@mFMi?Ve3Y2TbMfLuvFpu8&j<V|hmg~r
zc`^8zMcv&;2?^YsoDkoV(&hX*VU8jL4j~nB09Gu6={fJWSwz7sp;c&9BBZXa{^;pb
z0a8-Zsi`SW*gf&^80y;E!W&Y-#FURJZVz`_2JLg}>gtv`_Hn*?^CqFaT@8ZqXw6%X
z)iLuc85hp<_4Snn?0OBpb;<ZXJKH(?;VBW$tkU)3)<GoRW9i$g#<}^$MSg*+MX~Tz
z-~HcTTLuS>(LsY%^oX26NDbyU7ZSsxj0|B;PNNcw1m#HjjtE-bQ_|8V7k0kWzA7(&
z+!Rh7iEkgR@#dD2x&|2O4BYXf*jSFLswx_GcHwh3`eU6w=XF4i_zv0YQ=Omp0<7_Z
zk9FY*yK_<a!e>+U4ea(69a<h9<w)#w+ruBXzdqMyXO#AEjBD%Y?xu@Y$?<D$X))9i
zix=Rm*At2J70Ft!d7FmGefA7CL^Px%U8BUuk56rGZYuMLb8?<Mc~b1wH<3CUIkO6w
zc0k*4-Q8Ms%WQs2qQ+J3xp>ET8rXE|T3Uj?1F5K}9;K!hy$IS}ew%ywsRYbkYN}vG
zMMd@Z8S9$^MR7153-zVSO0XrH$HpwYmWQ|}Cno`3JcGgbly{k#@q)ikR-5|e%g5nI
z2TQGkiv?w5O#S`+Z71J{R*StcIRlGcVB-WQC(IRm?>oeSyEEoBUI{QR5qP!f)@ZxU
zrNPjZ28SLt42Sp1NS}bPV2ba~Op<30Ee*{PTz9hQB_pr--jf&(7+mGn-EQ%ob^rm9
z{;b$IK!s`#+2l4lR}S}Ja<iJ}#+s75kLeme=1CD9#xw$`AVGZYE|%0!FDyiKB?&WB
zjo&9C7Xj=+7EOtivNwLYzDT4nQnxJ4xMByZKMo?w#DtZ3%8M5Q5GIUPY{J9Cxz3$C
z?(FP*cZQLX5g!vXAh)%(6<$;0SFlBX^k^?L_0;lmbaS&3(g^b$n~)G%Y+ggpXlh_!
zaBuxoN=gcR1(t?fY(~amyM&6WDi<#=$@0*f&k4q+rqdC;>FC$kstyC%9<qnyGo44P
z@6H$-8&_{xzYihxfrW{srw@ZyCqo%56ykX<YwR&?$yN63XM_VtW;m^>r4^Et#PIXy
z&$V|X>=OV}+W;D(w^39iScjPmC8efrgAGT<x(2y68iER$%oZNs*>o#DW!Hc|VeAf;
zPiHd|ro;NvGxh4Zj*bqrTJyIeB_1mdQEDzF@mB~8yZ}JxcWc1N)&$45@CG`~>hY%6
z9`J1;%&WI=gKTe|F|BA0qhu!QmrK4T*SWt{Qa)#By?)Kagi}_Q1*)pMo?G$vbaPa)
zAX9Gt{%VOn6A?K*T0@+W5A=_)B<T$rUunB`ZE%0f9bUXv?ZF30ISd}Lsjm-9%X>x1
z%WIQscmu-vWD~W#pw1i&dL)BzBEK^yr;X^aZEIH-Ij$nSb$Hm+C_Op(TISo?i?EVQ
z-@JLbwmq>we_7*=Iq8=IeUgEJ0V)4&ksDtMi4Z_pRGeH~0PNe`S!-ZTS3+4*R8(~A
z*fE{SUAfbzPalPi^{viNQYD(naQ>$M;r>=Nrq#|6O>f`6O{_K?wnB76935-{Qx+NA
z%suNe#^USitEQ!;w7a<+Ir6cmhuWq!3WX&iw};LaS=2GXHV=mi6X6i<S<@fiTpfQH
z8+)vF?`IcMuHM-a$)F2JU=)f|2_g&hme8t;fPlct&T!4>l5)DAlG2QIMdU0IG4XqN
zWGESG&^^ZtSGxo#`SOWDxn;~Y!Rf_^zQ>UUzhTDM_;^~C7?y~)<AKb8ids{|9U#@a
zUc2`AFlTAtCG-8@U=(jH4ZR_Ulq}`5#*wF;Q7mcNs<SKC4ha}Qe#>J%{WSmuCm~OV
zQ?s`|Id>C5pz?x2Id_bP=04;Zw0cHw!O`(_vBjB{yBQZ$RaMbs<pZ&0eb}V|pdmqy
z>O+;gcctNOjHjmiUz#$&Z?r-U@XD@>zPY)10@4x+9?)csG&V=jzPkBU2z?!5=k~82
zc~8>Nh6Z^Qgzd~QjMVzl78De42QI4?=s%|lJlywYk@Yz?_c5*MW=UOM%`HDm1qI|_
zXO126{?x!r)ApX8HngIE0)v7@>X>Q_%e!37q+_rUv0N$~!onqrJ#w7cKSi8+v~Jws
z&(6;F=&`we-4zOu%IfOBKt{@qbG9erVP+-=kO9^Qdpjt;+gHA=mxx>-USoHpO(H2d
z7}0i393B4Hh!(B={RSHgpGiJ`{Fp53D+al}>fsB$f>L<A+TE3!6Qb9T0J%U4In@Ku
z*|)LMvX!k;2x*O-on+z;AC-Vwfo&&h-+cnX1qTztU<#w9(f*&`mozlUZVVJfK%_~m
zem)yaeF5F0VHAw_A3vrmzww2v#%oy-(y^vzs^^aZYpCPV8-Py}L%KggLNcA=kdDb*
z_GFat5-hf;BLkLYWAO{QW|9yQ(qCjuduO)$oy=-&u#tr?(WP*zGh0JaTOX1|387-1
zAAHRVSZEDEW46n9{oT2CQ<u6>>!z@*i^0V0?d=L$S`@HcT_+kb=*`OcZ7N;8O24<i
z-}k~u*!;bo?i?EsPWjI`Nvvhx?;Gl{OF+6RvTR`Eynp`Atkq0s0=g*y5C`{M*rk94
z#=m|O>ZpH8ce?FQUESSE=p_gVtsRV7J(J%eM?(*+tmGYOQv&T|PU+fRkIfM0EOdXc
zdk~nc9?xi#zh+C^TfAMvKJ>1Btk=S%5XZ*I$&J=IcDhe&TW^sd0uQ(;r1ziT@$E}3
zKw-GDDG(yRvsg865d0;(@;x{a4~*;dy|O3B!4aLey>k3?&rhOEO$RsP!}ceF0x=_8
z<HRZD{I?=(k_Xq$xp-y#g{0VD^2)&7>0!RMqz2txNKWYYs&eL+-Z9}!v7X2Ae_6JK
zRHnu?&c#;b^yr@);&+26&t>4w1RRhnQR$ztUyHpwVh6}d<2)&)pFMvB5H|~>r$sq9
z5Wq&C{~=SnSE*pjjiwcm3vj&z(3%PSNohre3gDQ_tW?PIZ7#HSK@@J?5`-;uC0*8O
zLkgu#BvwhWDUFvAuB^25eMTHR;!nWAG8Dqov3>H@Keg6rNF1I${|D6;WfMd}$lm#o
z0U|2cfl^u-t9zjdTv%r}c4!y7Qn}@m9PHMFN$x(O1cU|}69Mq~`1$1o>~5BppIzRk
z7#SV?oemF}W7m~<l#GnOqNv>6-5shn^VxmMmaktKWV}~GLPLq_cV?MkIn|q?pz3UE
z6eFRfWs{JDQ~p*Lu!0sA7Q{d_=0BE2`UzdLVypB1p{hEaU?7hkJ*oilL)5XC!((NH
z5jdW2Wp<jOb@nDEOh8nT@$&M*E!jYNBC7CR6Vr$IBH=O?RZ{<lj6Z=4u%K``1#*^&
z(jwruAzHn(v=EtBd%T12<k6NU=O+PSGYoQbHoz!IOQHD3J`I4WnczA)FTR`*u|o9p
z^gM=vikyZFr<5k`X?62vB+xY0W3|53e{Oy)p3F_MK)3be>}(k13<zul2$aiE3*4KZ
zcPuiiqJjG6%+LL<&Q8D%v=ft)7#SHE+28&8Qg=5_;||U10qVcUW4WMWc~JY*6CPkJ
z=rDkS>FiMe`oMg?d!7+k_%>Q2_x*$80ub2=V8G4I0J5vX@K`%IgadrD`IvgX{lkYZ
z%iil#$`H6PUS3{~y_py^0@qE`d!;NuZ9G3(BMIf>#L`j}uqj-SH&DV3C2KN*4j5sy
z;D0Dr1HSu_Inw?H?j;MJ)Ai1sCdf289WHY!N)M-qtOUxpIQ?VUahH2PdWlICd_T(+
zjU0<s(a#j(;<^NE$tf<b9IZAOo!9vW{P!xFE^p}+7y!z&g{pRjvOxz%w|e`}AB}6*
zl2b1Pn4|}68oRl>KkDt(8I?FVI4JX2(8FQ@3O|PGME&q!pZny=i?A|H9gPD6>&tI`
zy^`*?a{fG!4N591oq#!8K76?R=+Pr3CEI}_<Ei=i(-7SrLptw*Db}dXh>wro`0-Wy
zV1LVU=SN9Hb61z<!S49s;`MYfy9Wj(7UlybmcnSw5_A}7TzB^k9uI}Nx{gk4)Co~V
zv}OVRTnrXpfl*1it({#2z8%Ic7Z8&>RQ%V+8%Sw+@DCq8gyQAW$8<RXC~M;ZqiX8u
zJ%S2HLs9X5Wo2c1nO)Z@c#Kb<Ka<PFG&D2-$KC~y_d5_zKRb9c@VU9UuuT>!FdS@b
zY-RQzm?C0g5`hrjS$;bXm4-5Uk5D_&(9`q4!W8q{yoJSfball;u2+Ye@H?dCGMDiS
zPGhxINGw#i5Ac9>qL5gCXb?aFGPivBVhH38uj)g#1gN9hVad$w?fimq<3#IGbg1E0
zPn|lY1{8h7*k@|_Jsl{5_n?-h!D3GWS4rpK-~iFWx7qlQ{LKD&E>3YzWu-udxEane
zQ>7^iziqT?YPHRaYOuX?=ML=sw+fuUtQ4o`=6Ip-3Uds*qM`8s;8{DMM^8JbC9k`<
zSlWtlanjJxaKfm4mKkWW11LlfX%C95{^6BZZEW#C^FF{!@V%<2NCeEGw>md5!2w{n
z`VRmnQ^-eLoSg8_>o;${(6nHyfPq7&2{!AG&i~`;XlrM8SF^;TZllxU?gF>(pM~e1
zJ(zYF>E9Jj<Mnmj8S<7TOR%EoU0htS*ugh9lK@$3n2j6;iZ6{+z5Zrv5BEoN;>78}
z!NJg0X&{aXNZWJ9^s!j@!p=l6wa4%C=g$Le&;=wRznRk`#+Veo9GH!1SU<`Gkw>A*
zE`>!2R91&o2{V)lASVD!_|a)*ZmtVA=FTnyI3D1Z>z&V*>!-Q62w{m-&%qwLYvZm_
zjUp`&fjoQa>gwW>^Xnqo{$G{Q<FNxIHYFtjqSVHGA0bc?4{zB(c!mhx3!H>`%9}Um
z(tV~#fsk2=+m&B>*E4zWi^L%g^Oy8ahZ<}eu;JaLUMO?W-vK2DK1%iG#+OgbCBN2w
z$S%R|bc9S-&^j%<C<jyuDl+)p77!2sH1r_p3BJ8Z1RfcZO0ct$-tir7DC?<Va7KL|
zkjP1S?!GhD%N<;u6gElF$kkL>T3%*nG=-4&3UCd9CpEQ~(8v8P?OeU%r-Lesir6k(
zv0nX}dj3vtiDd)9?$F@i@js06{1vKoL7}4kei}-)H?-_K+lO~2<Fsdni=Qp_7Z5^u
z%yPm11l%zJ0u%sATwL5dpwX(B(QIXMvxY!c*bI<=^4Ip+=zu8%UU6xxjyXpqnt$V5
z{o#S%C^B7E2sroFty^nA#@O^`UPQ{pqfnOW?G<fx)(ifXjlbI1gKED8n3Ox-gN>I7
zAR%->(y<pYDmJ?aSQ4so1OZ;1e=`~Q(034wjlbXGV`gRs+3YxeT6eVo$U!Rh3sIoS
zAc*^&J6O;m0LIcWQ)A;q-6ZrG-?)sk)z{Z6AG8$d6->;{g+qK|-tbIIO%-wfu2#Fh
zIgFM{kRO79AZvP`y~l3%)_L?83rkde!0z?0#pXa+w7d%@5e@j`!6M_;J@LO+VK}}@
z+GU%apT`3=%L@92MBwhSBmgEWSX*k^+HLJ|T$=u=yHqSvxKMHiPBAf>jDStX!0kzr
zkgzcNnjVzDhib+ehzBXZO+lc5!=aF4`}|y+Br`z%$Cnr3S(n16`U~{GH3Z3z1#FF8
ze|X+`L<&%-O(PB?<+XGIRSD44%^>7BcZK-KkqLnLD4P#udT45DDox$<tgNhU*m$L$
zKdz?A2eG--t`nn~WpNAiGEUJHJ}ym7O@9yq5Hbsb%0vIbGP~ntW8K-xkx&kiphW`+
zDNXv?a-mQKC+=24x|H!+Qh?bL0b&g;od}63P$(xWCr4R7-eljMe6J&(*JidmCEv2)
z0vbj}lbJx9+=F5}-|z)JMC5SzW7CYs0!TmYsr`Y3-5<wb;e!FD@*)Tv$BrKl1zrX?
z(@!N0a=t%pL&C#R6~qTh-d8^B*MS#&{Vm|`=2C=Z;LcyA%H*wcG;fAK4Y1Jnpe{oi
z-@hj?ee0|Ya39^vQB3DFT>LLvkBp40fttn%Bns5XO6ab-`}>Bu@CVq@5L@KXas{|@
zDc1=F$Oh;`Krw{Mj!>9R0)Bw+*7vW{Vs(}E)VbL^l2TJC-k4AV3YgFo{+Easl9pzk
z64L<Kkf4qbG{$Qcw~VuFIP-tPo<b|hE)U;Ae$nP0My#P+OF)o(l#P97fn`Hrwe#IO
zCYWSEgoRdOHV7~k#A$(-VJ&gD*@opuv6*dV;PG1Fgg78%)%yOT_qc4)l#4CJg_;Im
z*5@Me{3Z!k>{m+O#ige^PpRSgOLpZgbE{nFu)0nL3z$au#r&%;pNze~6;>@zt!v23
z2`g0f`gP7i!xybHWcd8|1`D>tNNsH`qL9>kEY8~S#nsDOpcxuq3;o4%V4E#3Q&Lk?
zfB*hHS(*i;?V+J3a$-sblko1HjNDxApasa9d^!nif3@*Wxb6R?cK@%(_^*oo|Mf50
zgS0+7dmWTpP+CLk>f}H>h~66WqlOfaM->gX+8vTmKzRCNIC~)exWLtkF5w20uXkJe
zCR+QmQviVRQA)~lo<1-ow#41iDd#=rk0~lD_SSg2APSIn>UURU&`{DG2jD5LO5{hE
z7OEI{t&T+luZuJSGDG7fTJZ9@X8<JzyZDD3S_1qO`;ndkZ!3b}vEIfW4r2+~MZ{%H
z7U+S}_5gapYdEM#Pl##&(iG!<y^^v60`>X_$?*xGGg{WC+tz22EdPp3e?#eo&v}=F
zRdV{|AejQ7gWF+zs-e`}f03>Qs-M-`UsSCztS<zfg6N3WC=eCumD<#<TnRII8K#nR
zFEUb7IaC84li1+Nsta5V=<e{)&_Fz_pwuVml9aZWv!4Yes;SoZm(Gi;XHeCY_eyHx
zBW_JJDCmc)z=!PL7YU04Icx=$&$nt%0UBCb(5Zs&5t3Yo*iicF6<?pIPYSx4eKmgV
z-yZ0QI{DZ9p_i^9ZjUaVdENi|EdPfm<o|y0e`1*V_rVe0wVefE>;pVE6m!H7sL$RU
zpa5<?k1Fy%H$|F^Hwur?Vic`zL6XbP$pN|a+`r~JJ_X?OF*M-4bxtc5<lt!Zz{m-b
z<0ui>Rj|DatGoY*eFnXxx6n|ac6%yvZEZ~fsv|T6e<n^KpP<3*Ab&8)WD~MD3VmW_
zU>!VDJjL!TeB$<BZ()E!`#rEmB0xcDC5vDzp|FkHh0^5Y`SZrB);heHvzRp@94kVP
zaXexriDPN1r-OAb_vAm;eQPT*XuIzr<9piC@@O^o<*2$ra97+)fod3*qkg8@Upq#w
zKgOJ-7pq`<((@zo5y>~KPvU@0#{q625O$Tu$L&YOr-AP!revB=_)=oY4u}SJGjP@y
zbNc4lK;#G`pQk6&wnaFI8tt0u(3?nzGNwkHzZSC!nN?;Q(K9lV1_d2*Zh=-5`ts%N
zmLrdM@qdaQ_!^_4yGcrX3e+7|t7CO2aSO$t#VG8mPSz7h?au5|$Ki@IDDejx*EC>@
zYj18G2VK)Hb~@<^GvbX%k{7%t&>60rM5!Id_>`Srb2bq0@{LN^AUkL2?YlVt3_cVt
z0S?jz)R1I}+f3jdkUK(5d>zvM30a@gcNRGYHwd;_8Y4sdKM+qi^*h2EIBLg&EP-l)
zPB3r_CAe6M7iS6a8mEYc?$v+Bq!JuEdYkjtsd70K`WQIp?i>i|_e22$0_(~sZ-TCe
zQ9%Uv0r`Y{yQdE8GLAICN#gTUm--0c)w+9Moz^_(C@doy2a80kK<syS?e76ov}#9%
zqO$-RfhNEE+qB}AsG2MMzS2XzJX`y{?e%Z39jK+fS15o-45s=6dLAc#v>3NItc>F*
z7cy4o$1KeTuV(A<eNJXHGBQFPBVjS2@Id+fosYY_)8&|7+ka5Jd$&4k8qGia31a5<
zf4;|SA7f>u)YjGpXA#{A#D8zwE%=BkTzKQOore9N&E=aDBJdmd&O8GFL{&v48=%&4
z#)t11{fVsLR|;Lx=l_zN0y<v~sCLQHp8Nn~4T?D+)Zr<z3_7$xIHnge!#{g=O7?K?
z*V@KLGtA|y+rtvJ_V!l|qR@v_=KmbcgHcd&1-a?ga0MmmIsu)s@1?0Ecy1;J9Wp=`
z56`kWLu-NhxAfA<YPvT#5;Q_#gH53%ENH+$tVO_;t$?Kk9c8-iDO|t(bmxe;ekxpg
zq&|Qd)X}gD9tE!)Al$0?^4B`dLegsnI9cd-!LF0e;KfzS+rt$taA61y_Vf{GP%#XI
zQGhi_4TS;H2=KJjf5%-AEC3)eHo~Mj^&;qlKG4ro{ss9*2lNS~QCogL<Zy3J-skrh
zqdqi_KzSFt4!?#y{z6Mm94H?(4GjVW=zuK1Z3qHfk*%%m2_b28{!~xv_h@acjEdgq
zKaGkSXu$%@13`^H0IEc6{m~I?;n(l!cE|__1JMj+<UvCZ11lE70p%iakY^one?L_a
zTQE2qqW>E1kzy5UPE-;zFrZr;cp2Ho=0^bvFtJRaQ+-31M~V{wUoa}Xj})%YH#z_!
zj6+V26%c_ymo=KTFtD9*Y;t!eIuit{%TPKB%8F`I#a4s7E-et%F*o}2bu&krnh1Z*
z^$2_Gz~ybzokuF~!J=5;7DHSivej;U(ged+UY`xWzSy0epLVbn=}&{GC)_KAt|eLY
z^Dvr<KR^gCPPJ`?Uwf{dA*2(y*v~g=^>@AbgGuheOYO^-&*_~y)Q7zRl>zFVgPJ0^
zwpJEOs!8w^D1jV8OmV_${si26yB6FUA%8+)uQb%9@g6rG^QEK!8bG;j2(s_NfCpj|
zYKp1$Sa>grTK*D}pFekqqYXf5Oppn<R1H2B3^E8?0HWo!0&5!2<tL5f<KwZf7>_)+
z2R9PqRYgStR5ydg!v*68Q=AN{1@Iswu(g6~RnRd`?JhEYO$=Or3y4h^1ePQE8C2j(
zY%)CYm#_{?0{!sE*AlKXXDDN0V%9b{!$53)7h^g3qZ<TSLiEcZ%3xVoC=~p*mL$jh
zX+b*zKb5mFl_uObnKjhA5=OS2{o?vLDwO`fXb?G@uZ?<-TSE+~^!$<djzCcOuicSP
z8@;Eqh?KA}H6#muoiX5C0W&7f#G*^b4&u%%;H*{#OMl%=|1X7x5HMY<f?=LG`3uCN
zQ!wR(xTg2-*C2urAZYbkSt&)qDoqDU>8IOoZ95+QR8@!HF$jSu1+p(%>L3WP7YO3*
z?TtG9pc<@Reqdq{j&4*P2vM-W+j`v~m}3*vQ(95N9-Bh`@9x)sPv-vx+w8x8QQ)&V
zx+U@-L=wgxnczVnVIlsPY03UES*4vuE+H&|nMHEA-^dMSc@|}Jdy`Tt46ye+S5h4p
zb>M~z^Ijlf7v<wHxP8QeFxF}V|2V#zMeZ&gm<1JK2((zqASr$EByW7jxp+`%<YN0k
z&0bGmU({#K3e_TkuaoqYg7Go@I;z@#GYT7WLHU%pO<RmI<U)vhZ&jV2!cqXwR2>P7
z10&v4)RQ0KnZF~lYikeUy;R_y6aZzN>}3YQYv2NU>9@VJW9S-!{vw_kx1!wt8>7>N
ze>Gw=(4l2!#sWSS6hVWrr&wuM>!}1KQ?$w!J~Hyf#Az6a!ei`+0J0HQ!Arb#5Wv=`
zhorYst8;T+-%C1^k`efa6t<MC;F&X?b|A3=)mvIxs&MscqJ_Ejqxkr&t1q(p94Drx
z^!iT1RxqUen#H>GltO{Bk#*>|J;k%L03+%?YC*VIhiZQ@p$^Im)QSfN#C}yCF?5Yw
ztX+}o#u@X9gJS2{pC4zDl9R&)^()z9_(9z-wgWcyFy?r+mLflUve#fW`fIsWvJd&|
z&;6G-`rjw{KUPOx<)D_W0x6P>*(1!P$6ZDC8eiWBmvyM6so|I7NDqOJ>peR^qyghd
zp3VqH>l3xz2FG(TJ|w8VWQ+I^H=fHu^Pxt9%ObM9<^ARHQ7e6{rxS98a81$zrtq1_
zVDIKy5H$yj0yA=WZ?mT9ND5JWO5tf*1q;#Nq^)Eja5Y}`p;w8c7~4^SVKOT!oIFO>
zX)o3%rGVcZGoh~)plL&-2nKLk>IvmN;kYVc!bVM0AL-CC{7z_PjrC;BOzT4jDw%nU
zEwqYYA`fd*6%Ow{Bk098GVKYwy&@E$X_Q9Tcpd<Z?Y8{LwfH)kCX_8ErQm@(#-DOR
z6<H;4CF1C{_~lRE$bR}j44|5!d3x^wCe>IijaKU?iKw4_VYUxKes6<kq4IkGsj3?t
z)(cxXxWVH}J`}nE!%sF%WEF_@WXG&YTo>FDfuH__V<va8s$TYxJ;-QVS32bF6?t|t
z{b1cmDS(xz`H8dwU>ws;Bn-1nq;SX4&&CAvjVMzdVV(|e?$R>UiIFA|5H4>1l%V;$
zv#F`6Z~8ae_U>H6WYZ6j;SA`Ekh&~$OCH*xBW)i%CQBXi$TZroG)^T%lD~`u!(q!)
zhG-Vp8+>|{NWF*?Cn4O?BghW1si|hR`v3-`Pf)_@*@2huvlOvR%+Fu54H(5$t3*Nm
z&-YL6Hn?apU~yurvr_Q~s_AAjT~vvI$IM?s->TTDIJ$i7!6aeWrChy*PQZ_m@&kJq
zO94w-6<7`i(y1Q|jvFImZ|h!l-(ftc*>6zOQV)p_rj?zRoqRJuegakt>@1BKm?c{x
z4jLUv-Ans<Oc(nu;<#{Gy~WtZ14#FJ$9TjI<ER15Mq;Aswq%(bd5}Y*(l(DQc(4R|
zSViq*jYl27lDJkH%_5nsIJ=2}6v)O<D;gNm_inao5xFwsxN!^!g@_%Rb93AJu!g!9
za36Xtu2%<?2vQGqX$4@+BrjisH|^fp=J8h(Td80@c@Z<1M0jnc8D7&Ma($irNB{3q
z&EJFHR`xo5K))RL-@Raggwg35Q7T-T4uzF!V4-DS$mxf?#(4PT*Gl8Yv+B}h0P8Bc
z-taP<A)g>|Bq7YWSMfG)tj;~J67~oOd|vFK-^1BFD%cKxhuCfhnaWBVwIy$)Jv7Av
z6{L33=VDf&20<y6f+q4C(@!KqtdPowW*mMw7$$hC3``V3tWSv`L*rNEfN&x#VhVke
z5Pee?=cL@viZMcXpr688O#gW9M39_V=y|7SQZT0!ICL6F8mp84Jo)b)Djgwa(48a5
zjKkUhB<ANuCxZ~Tg^}ISsUpXTxS|kOkFHo;-*AUuo3!z`<LaYj!ezM>f6TQfLV^I+
zK3x~nPw*Y{E0^%(KnJ+33s&xbHf#J31Jb{Dc|3urM@}!O01FIAHws{!HkOAO7=+A3
zJg+5aGL?JxT@m}|w;_^u1Dz}4wR8<-v{BDGaK%vCQG=S5B7JtI>&Tig&IpmkWb#7&
z;rvAGG<t{n5%^?j{G)0x%FD{imV$(YnjVyP|E2ANT$+2I%OExwktS#l$oFT#Z6OAd
zci}mdqygMt?O&z<Z53(!^5sqYZIE2R;*{%`4x4P!jqeI4&PZ1TvfvETdLI?k`NE7X
z?eE6ot-#advsm!F7o=y-x2BLiL26ooz72=w)5oW%aIahX+0R}@$86?#vaS6{rJGd1
zpR+(J)m(oIMnEP|99OUm3=YqZ9{;ZE-BKa0K?k2D&cb(Tf$rA^xPJ{u=yxDNeFOjS
zZ4~xAYp3fx-l&fp2tE5qpujvG2DWPhHXy?AM_V7VKZKlm9dawsVP`$n5`qPA$9s9s
zdb1arQZ;`5hJk2!QgTIZMR9j`fRN?+wJY$wC{`Kz@xa|Pfd@Mdpyo{jjf+64rG!#|
zR`t0nCBj0oMu;27^xya5(Z7vc;fadG=Zi%W93$YEx>q)rwSVbT+bOIenZ4XOQ;;xB
z>YYcWDcCR6Dz#1YFR30w7?E36vju0caqn9Q=Mj$T*lJzyvrJg^<GW3AQ=Z&z^}RZi
zMG)kJ$48x{3gs0;*0^y_y_+%m1$_1rkQn2#&H3_#NQQ>HbW;9uNn&ABv!&neO&{;N
zht5TuDA<v1eE2Gf_%MqmYJ~msnh)k1RpvgS-BrLXYZ8@KPUn+<Be2f1HMo(+tB54#
znPN?S6a%74+iF1i&(HF_^`jO$@wfE)FZC+@|1N+2u-UO-eE$9QF)bzAYhRH)%*0{l
z{v9U@Tnyr`#Yl%Wv<GUd-L;s&hrY3Zr1OB_7{!FDNY=@0vUjk<Y^53$<m0MVkKqDT
zpu#Pr0FY>VLLIq!T>p>=XUo;1n4m9Io+Mg=RN75lLlvl#oK44&otFN&@!_z1!6{5P
zQSVWlJk9}OL1J%oX11IC{fH}}NNw^TU8KL2G?YJu8Jd2Q2`5(S%5sn)LaFQ7$^Y?7
zIv5{}!l>fn6J*|b#5JF$iejQiv6HCL$1$F@@RQWj2s}j_^^nt`DN+==*^_I8ktNB@
zBc0~76L4PhIfA1@(p4UWcGCdZ6cdz3Xc3D05Gcc(nzA$+UnWc6TzeYjLv~D;NC)F8
z>3Ph+$pf(><tT}*PC|T6NV15@vp_$A!Esx~D)AuTF6fCGUfs`3oBR$Cw7t6&YTJCV
z8qx`A+~?jgffwB6)0zZYC-j{L3Fj$+YRW*GG4n*3d{Xq02>Qr{wKSL|%o-UkilmbS
zNhZmx;JeSyrRwN+eGDR+Z4Am-=9g7tChX>6{gq-H?Hz^Xu!evAIs7j^^o|i^iexDI
z+2~|z;F3}_G?8XPchlIk49c72H?JAI?zIT65cPD;O^S~X1}OV&aPS>e0R5B4;!d{E
z>w8ny)*Ufq(z4g!+tL#fx+!Ecofj?T`UhbmmT1PG<T@6MMRtcaANZ<*+Kgppjs&In
zI`k{$8^7im3*5bp^00q#w2zYQQC5sUX(Ip?^5rb^gF_MAtj>3KE2U7~2({dgAHX2+
zpD49Hm>bh}AQu)>C&MWxXKr-M$tfbE{(w|2W0CZx{111PTP(cV=}O?_+8Dwhz}cY<
zFc6z>Ww+zotvE3u7+2y_(xI9}Z=zlTg*SeO(kc8>*;5I#yH7i`_{<u7SXncc@gVjP
zcmkZ=-fC}H3mR!KE3u{kO%Cmghz6K{JpVuYP_&L2pSQi}M<{(0DbAw|ZNJ5GWGx68
zkTbBLZCnNaQD7_8gM3?HjXz)-b6o{?u4Vx;efI3xMCTU)m6-fn&g1pwj+}%D=Y6n@
zF`mzMZznlMX(fuI#t1@NSnWCsHq-pnswT&CZ>r*#bzzmOQ?at5jB3G~bIK=^S|Zp&
z;kLie9zS<RK|nyVOD)boP}y@p86!oy%tYsgtSHnxJ`hHnQy}5JUL$e!{9)K#EXN$p
zE2*-4@{K6Rb>v`lO}MPYj_`aQRcyORa#GU$r;*HH8*+oOBk%-$HGlbe)bV`qm!qmC
zYAPgJgj(wU@R6q+g<@*Nu}7b=skcOLO2$s4AS5y*K4a@4J?8BB&iOv^m-IUbV?9<6
zS9*DpZ9UfIruybyUXXHI3@N_l@a@XdSPgSqpmbO(ee~rMtZ^ttq`NUY(9EzJr0Y1k
zB<av3uFSZV=^ZX}wXT5-{4zv~dD_WT+M0IdgdGY~%SzqqDZzIGeq`-8ZaVJxYnG?<
z5l>#6Z13rm^b9f7XTd4=etfn-VZ~UP9ubjxMdoEv`$!TvmAx<ck}&lpbMSLE*@)?r
z(GSqiW5)<df@JZ<X*JnU(K~)A1hZs=rAVta1xp%T*_E!_nG1V)Qold*)r#&>qAPc_
z#;a|m#EYxk<aGb;m%Nx#rBjxrGfVXT8!f8sUAyDU9wp{AVM4;*?-E$-qO1!IrZO*E
z<z4h+PdkdlBO6C(nP|7&h94>qgzjU*zAxEwsa!H}gNowp2*yF);YbE$>qGJ&r6<qc
zU9ls1%jMi?hs>nz+&-I#`+^bZ4=5H&+%UiY{qR)NX3QD0yh=wGwXK&0gn}s{MMrA4
z7W_g7P%YzdegCK<t<^|oVVOT7uOP#*YmM!_f@QPr#}~@JU369+I4>j9^!|QOkKRn9
zc-2`m3<a?(Oa4GL(~S$dw9YR_aV44in&pX3O#-5lNE-4TsgVEnJ|ITM>_Syi`!xce
z_s{wgu6YGYfI;Lzk$k{<IX36yNSN2XitM6$UVmg6KXmO|3Y9r`=Zmhnu8CYft8^Ty
z9;atWGU>!zc;_Kzjpng9Yo#=<C+qSJwhDrwFN((-2R_js94MFk_+0IK69z>mYrEb;
zz?Gvk?#qLMP@+}g(>i0&XH?s_OL=YXv`w6Lw(6u^-Y2yqYvurpvz7;S+P@jgQcaw|
z-A24HN0BuqoPy)?^8&cHIg+zio<^Ru38Tx0fOP3;;%%*ChR0`#t)y`G<G+`yAUdtC
zMH-jPwWCGPwPkJz*S(s2OIexVPky+t&3<;>g&@O#T}VVdfjB<plUkUUnSyRHq2rBb
z*E%(cZWD-OhEBDT4QXm=JR;m!>?dcxa(L`DLywAz3Nexi9NM>y7M|_lr-wJX6FSc!
zZ?eoe52ecI3=Zm4O&$G?xG2gPK8<R^<Zs%ZGl;*jo!LY(<R|_iWb?Jj^Or_+_cpg~
zv6a7IFcNn<Ypasn{Wwg#+;ZDjx!;djl>SoLIZwpS$mR-V$Q5ek!=yjc1IwnRuU`k(
z<jBbO_z*yKdzP=|Hd27&F((A|Tx#&Vlb_7vpP}*8Rzk6x#!SUkW|!Va9|0?vkKf&<
ztwiA^he5*HpAKd+nRQ=CkiB)C(Ou;3MbV^$IAj_5^)U1D0~v*yDenNs__N$q<hQkh
zn95007#@Em7H_i6J6nrT5UhEg^gNT5YDt!$EQC|RElXA$y+)72MIpC$rjbNM3X@sW
zku8ws!?ALOC2(+)Tw<>p103E_R+<L`w@sQpx9LAsdn&`u;bzTQv0p<;JD!R!FF%V6
z8H)>Cu)LSPx)t)&yYKbQd;&U2;tTYh#+YrMa=G?l_S58qrOb^NkYz2b0i*f7iZe-B
z%ehg6YqB^#osS|!;?2yL6R*ma|FFMxzoLs4NhesNM7S-!RFZNK4wVnkc2@U$ur{h7
zF7$eHWLCU%;^IF#cLe4)w0ObUG@r2L2OdnzpXX(RAFrFP02!hJ&TaC?FAVtiz-8??
zYI4t9+$d|=^JmzmN}fg;Q{xN7?B3GYVEdb%&?b4RMm{7u^D^;ck*o!&@*oj{p|0s0
zNK$6n<375fr}q4lKW8X8=F(Wq0w(!4m6w`YDkB|-pPhLkEg9+(RkB&5{7!Br>?&xS
zo86BS1#neJtD+w}2ZLh}qk*KIj$JIpvM^q~chjmLS)<2g>3p0iGea~Z^J^$4IO*cL
zzc<fK{1Uz(9NUgGCR$cl?cJO{9@jl`r8*j{9`q)>oS^(OUM;$Yad6=F5Xa!}dAaW0
za1=J)BoR5Lz^YGdsPV4xW$4>uy5a;~lEQ7HKfKpJ;gWg-?7jORnRHf#RFSl=JdVB@
zUp$#HA9O58obC403gw9p3O@DIq>h<*TOLVKhVYE@QEbAS3ikGS#Ur5Y1|5uN<j3o%
zJ}uH+Q0IQ$=XeC?c$TS&WlbCViUy0v=isl6>>f&EJ4CuQPqYYUNAFImT4Jl5-dAdH
zsT?qP)5dihiE(eWm|>s$*~MRGH0v;z3o-=lh-j$(!mF|}8gg>-(O)3pYFMbG7c}`l
z>*`BFTa&6Q*#pa+M@@>&>+KgsG-n^-DQMz;bGqv&QQ_O|vA!3Tvb9ba@s0kONsM9^
zFK%?0TwN6wJ#5CCiF$@`$G<tJ`M#c#7CQOrykvKp<7wWWxw2cMfDsC}q<>>#KHsC7
zbjAGpX4P;WRbSEL*<DlYk8Xc3)T2s%S{kcK#jOaikUiyz^+9ZK&y3aa+uQ^-^25>k
zrrMLOZIU?SUW-kg`$v%J2l=}T7Iie=5Jyt8L3g5?Brla4nD<3G?df8QWbO~Uj1xae
zk#3|ZL!hO;uOTRC50>FJG#0)>dv3p#Vt^J_bapQ06gsSus>uXPmhyn)jsBxw%nBKW
zGk@ZV%j|6@r)U}6IJS_3&OhXFzq#V1g$;+}Q+~H|C5K)cz9wk-s#akKIPq6LGuLg6
z`EpKvWornVv+$)dHvY5DcESC`ufUY>?!^@4B_|6Z9*Yna{q6nIgOOcc=UMvN2+@RC
z?4uX%gOzSM*Gx^jK)(RpOA)BdmcBk+A<KHR?0w21@jE7`oJ~_b7QQJ9=Qw{W%~IN@
z&)xrVne?OjWS!U+`-{sACI#Ok&7=d>_xAS4_7cQzeiE#r4QT7fCaT%{=iM4BH%8r}
z4}fSdri9MVGV3Pd^BZ#~<5=`njR~qaL9}{^cI{_?Qz181D)2pgF-k@0jxLw{;l^v|
zQCJ+B0Lx;A|6ar?Gp%EMgC*?oPo=D{$I01&3_#<}{jvXKV!M%LprNe{98Yjcf`0&g
zp><V)evk@r=iCb^xO7$kDs72fQE{}h6yz~f{6QMQQd$a~7^on8tu%9@Gx4~(&5L)<
zhfneHTl=Jlj`2;^8_G&5lT~jm8%rz?$a-%5Vjo5nhF|FR_qs4RwjE8b+UTd~{^P?|
zY@yvBK)+SDwLs$I+)JLHv22??uW|AVP1W@XqDXo|orNKHUT(^gsJoQmTdXQ~Rf>10
zDQZc#XZu^fGD}!bJ<~bG&5c1|Ypf6QW;6+Ou`jGw4Xqo`3Nlw_M!X{@B<2(r*52~9
z{r>&r#>=<5GV^X8&L)?z@>~Uj=ZOL(R=PTjPRj98FAP?x#1w913tOHkV>R}@Kg?I)
zYNR0JPk4i2kP4*D{Guhgbzi#Hu^}4%goVUyi64Vn;H`vyk4BJVabQWZFk)k3dH@ZS
z*THp2wAs<w`RT_4EpT&WWMo{l7dMyn#{Om+2*xYe-HtSgmq_~I1H3`P#b!UbNh_Og
z2XUXe?ZtkGiUSl^1jD<m+;2Y_cq+I3yOV?lK&byWDxFa<y+6tz*=+^o`nXf}?RXHP
z>SCp5?JGt9>e$-yv!}Rdewh+PCD2V2-OF6<I>_(-h6Wet$e^V7X`<prIkYh7mz74f
zeHQmbr(5Ik6CcX3D7NgHrL9sqnaym^@T=%>tehHyAv_4?Qa#`+Kd4Jtwf^*2J#-)?
zLC`Vj%;_7|dxDN%kBI#mmp*TNK3Vi8aiXxWlq)>~a&Xi+fq}-HJQ{jOOtED{Oqxtk
zlS9TCRSkEt^o3Do&<QSCSs{Xg-G5e%(<&p4+%9agNH~w+Uz%2M%J4G3xv_)x@85s=
zn)$A`Kk-#I`@rj%-eyOUJL`hYW>q0c7I#UhHmT6wtbv!7;ZE^~k@e=6G7Gc1YhDeR
zKJ`gdY@r(GL(M&CPbRdY%_nFli(HiUnAgd+IpL1D-nda%yE$|-lxhU*M`@>ccoKKd
z<$GLVKYs?r;ujt|RLgToUUyEGuBF)(U+Pip5dcF*gmg(}RU?B^vpE?R{}whbk|*lL
z<BxlODlQ_M!4K>FHlIk>idDHyhc&mgX{v-h8i?)f)NW6T56XB92J^vkr}$e#<?0s>
z_wJ;eyPfEzP@!jwACdC9bXC~&%)NW}uG`sh0~eGiC%=sSU`%+1T`vM+>~K*$BQ}mV
z-AB<PXy3E047i>yXvEQn2m{)Mzkh8Mo16(Ws2#xp%t6~-&8o6viJ19QQftoBxXCIK
zZ?Ox4uUij%b;dh=8W9b2E{nYyGgm&b8aLS2jWN-|mEE@+tvfn&-y7tSq|(Nn%r+12
zFji7|Akm>4+do`DQy~D?@%P9GH+h-(=H@_WwA9S0js%U`_AlZ_GmhVM2kV^PDzQa8
zuF>^QcvBBu@`ZS%2hE2x!bV<ZaZejY`-|gk4m8yn%|X}ua2F9l(5AT)Vzx&iE8hc|
zxX9!U*$bnRR%j@nTs@rMB{{L@MT`Jp?z;cS6Y?fdTuq~+tf2IXx4$a5^@;YA8}AMk
zJoCiDazSdsW%k&oPb0T0eMYK%$*&Gvb@lcRe_NuLXcMR=R{pjVDHpI6u<aWsnVFlN
zhGuBB>i7`QV=KS9s=j>k#_EUT%I8jg(R*Gqzx^E@w)oa+KXn9qsid+Zb{58eO#~9V
z&@LqO<gM$ZB6!p@p<@N@Mf|&#0t7h!o^bHMaN$wPPb>6jhG((~_BSMeB=5`l%TfLB
z@KPy<a-X{v4hY)7Ud|H(v@~90@nFkK-Pu5AAwC5fx)2-$l?X1NhO<9usH@*Ic_{?P
z=LEUr!BG>i_?qBo5B>yem&;GU8YwR?4=#SbKlR$T!hNk}y2*#FExu9x(u-R@hJ{+a
zv8|1Sp1$SbgMtk?ae8`sIEv?G?^jnhH{Fd6ANGGf``#;=p`xkQz(9uW3)dZX667z(
z_xErI^zrnmpsh0b+)eshw{Kr&)u<|Eoef<U5&q|LkyYh6pQustJG(Rbf1--XL1(Ti
zxC<u1#S5L7DblH`g+DvG;Q$aUgjH$JMYQ!lJv|-eZcDGXkUe|;oDc!iO(>X}-$7pu
z_+h<Q$IiH>f<rY6+!7F(Pj3XvdoI!uQ?VR{L4f0UP#*}|p?`Ux7&=&NKzK$iIncX?
zn&(hE6KId#QFVS>iolBgfesnR&=!j)UPvSK4~C((1VHkzx>VKFj(*ILFY!jr=~nHr
zC&815_Unk*s%2&5oPWzDAwdu3Atfs-4)Beyf3taL4c#HoIVtf1ehaJ`=ot#5!tdeE
zPl9nC=bLK8?W74l?l`vtXm+fgK0P_|ASR|2pf@!tNmo{81|1$$LSPwlgGM^C@?UA*
zW4dNC$OJIW%0Nn^!aviw8<}8VReAU&HR03&^f5x?HwLAPY;B)Ka0QlYG!VGD!9fxs
z&})RY)+EaZU0{-Qj)FsypqJ%3v>!va&&7-j0kP@nG0>8c1r6?COft!8>-_k!6}%UC
zbf+4>&Ql2R@sR=&<*#ZBSQpNCX?{^sPX+~86tm>V`Q<|M8i}dt>GeKUcC-Vq(tk$`
z+zP?l+dgPV2Z95N9PaJn>Nj!w?nd^Yy?Zc=jAv)dDsr?lE;tUBaT8OsMZq0Tf|ooQ
zY+-jd=I_CAOVHpzfPmjC1VY6WbYKu7wSN|0pkbuKWxP1q3pG`PhxA&NJ2%+tgF)K=
z>;Bf%Y*J+pu$5Sr@|cfZahL&`D-?QdVeE5FV@CSt4AqA}LFWg7TQNi-Fv&N=2VM$@
zZ{2wT?Nwk%CV3)p`+@x79xZNjKM+nzaNS<BuCtpO2fr2?dACM7IttzoTg`jj8mnc5
zcGgztZ0Upf#UDkxesWrepnE^KE<G#Z>;d#Tl;0Yp0egiq8yxw8_8qH4)t}G{{S7B9
z_y+`VpF8)a_YZ90x;ekiB`o3&t!JDMtAL!>ees3+?!M%h&m~B$W}jR&i^`X)UBF&?
z-NuFs8aYA-pg|@QoJh6cq$Q4gBV~8H4UDWuaBvU<^wcXUg&?uu82eEHX4zOI7K|{=
z7uLd06tadILytU|U6@XNRONG$L7Q5@^e(*a79C&_@pxa{X`m<t?M2!$Bb^%nOG@+m
z_llr^6z{>@5GbGxUgjy#QY2_zU7meO=yBFiTzov&xtjxz4|f|5#hr>cIiZ0+4x}LT
z=HU1b4e;&QL2b#&>HcHj45Nq@4w_5#VVC4WSp5kNM~ke_frJzTDG54Ji}JtRaP#y`
z@E#8^S{>P2dfoF3<_#Kd1R$gRd`~WX;#6QzP!J~54?QMANeO8OPsquDKO0!c)+y)j
z<N^BWgyyzW92^P&aG!xgtnAjHSe?!6_wVh%_IWNRLmw7+Lkz$`>@mCto9|P;F4wEq
zuW7-jwg6tDI8pk%P97AL(IjYagB*5x{X*Ckdsv}n+3_W3J3kfgUM;aW1D>nXWe3n~
zK?j9dmHUi_ucBaFSp^&uU<k&H(~x5SIqCvVP~h7ThuJLiS~j^9VtVRQMUKd7{cbU=
zi?Ukl3wr9q(4$F-0nGk00@`iRQ3FxzBD6nRe!tKvTcXr?kOJmrEu<ZaKMy+%skgA3
zc)$?+C?%ypKvP?r0d64W+|9(|?(uO;@Q^n{?-i_IezXm6b3~l(QpGg%+hGy(2GGfc
zQ)1Mio##7vUR0vb0aQ-+|EcZ-#R_=9)Zq+@TR`D@Eq#Mb^FKcDqF?g?v>}{E>j@?%
z{<)rvB$xUf6$q)ekgj2t;UF3mf<aHlRamPtFz7$QTFrdwpt)IT;meC8IJwIbIJWOA
zqcxn_m+e6aw1s1NXjoa#fPLsuTG|=d$B!YHwnIeoaDxT6RXzP7O~we?kigo1#vKm7
zg8pc*_*Bk6N`Vjq#WDCa6VVPdw88Jf?vgmPd+|wpBrzPcorUwe2ox%A4Q3my%+B(F
zj|pwrg9EzyUWnU@-C3Ksi1vDchomgT@>yBArjp;IuZ4!1Xu}8R!~KoV+FcMFZuj~`
z>J54M!#OMHw~_DgJYRo&Ko7NnCh+4v(a;T^A|Djka!!$AI3`>fc3@;=Bv@;z-%mA^
zJX@|D7np=|Mj*N*ppAlH+-hlURe>`H$mJ?Tdj#Uj4x`X6c|GX)uM^`=HI0afK#x3u
z_7U_T73jD^HwT6TdQ1zQ8{kpf!C^TAttr*=x6n5FtlJ_UGN=b0!vU>Dk08G4LQ4=2
zSnufmIoL(aq-e`84oq`8Q#SIyy2Ztyvt#rZd`1Hdiofq(&%2UVC_^IYGA0P8@WJUH
zx7N0mmC*emC$@!&1)JH0pPpkr)0B1c{c>`0c755()pO8frw1w2T#S~DO$a$9AyLtM
z+xJ=mI|5xn8|m!l-H)J|2=;zlLW1GR65q`wW3W$Jf#Da-ZGNHPLK{j*O+~$;Igl{`
zN?grqtGWA|A97VFoP>5&tyUSL6Pg#Gsn81QE3hFeLVIRhN{aD!H)MHvhFqZJXxNRm
z061E3{>uvn3;%UxXg4W*Ki#mZy9|x~B$=$;dz}LRPb23V6lEEP;WeGiG!qR)fer}f
z!r}s=peQ;FhnN;iLxl#AMntxTf`v$FJOxdlfmo)}0CF->D*;!8#Xt%MPy)k3L@`}m
zP=r7{r5JQQ{O(788TRyj@B2LW`+WCxAJ0V|h<xM7{srXiboZPi%?`Qo%Vv}0@%O{a
zA5BcVaHYkOt}Df$y=sdG@J{ZikLWyDR_6g1#io0|x=HSvtG0C<G?s9&#jt-ILzUlI
zKWeF_Sj|wM9(YEkA)xl=7W&ZNN^(e~f|Dx3Rhc)`Z88bK8`WAk0V~n9n>Uk-i=9F$
zbUq(dLeH$~KMCg&3rdS+P!gO59zF7-Jv&D<OkwtsSDUo^+`XUHwwISdN8|#Bh~6d9
zfjacV2fKU=YSJv-25P6hb*t=@UN3OX$1O;NofPkUYRe{$>|*tXI6LeeU2**EWW|p_
zWP$dpcLb}sAkQk$NoyPKKn~>M>9bgx=t}s*hXXhEmxU^oO1ZXN5g?{EoAGg+RwfgJ
z;%nKyrX%6XLI0^Qy_78c56`~p@isdH@K9gO7vH#!2^W9u_vOB4iu=mdo}MpbWcQ7U
zaiaCF&b#~P+SUX(>amJhu2H$CLRp6spXNXN<+iXf8-^~8u)jcQ($P&l-#D1A^w5(r
zy~ol&f`WrZ$_xw+dWDCF@2TGg&pJi{PYXAEZ2R=6nWfgBXKzEC7754Hz0RlZNm2i9
zJdW#cw;qzQAOdI-K(i*xy(Dn{wCwEcSX{=vos}~Hs1GcPn-kfRlSWUUzUZ5dDSv)S
zy+~|vi|$AkcOyw7@&kYzO9&j2F=^uErCG}x$9}S^RIjgPhMG>6g^fxz37eXd5)vx^
zQ<qcl;?dHj^SNrQe2;zVb?J<M3r=@&_W7+MZX<nc5)Y@2Wn7#aP>F?2OcZdd;rNaj
zd^^N@nAMPx=)^g;AT31Q-#y#LQ0>HW!RHopv%xI%AC$`2G~Xn;!YozS&laWDikQBR
z1(HbS_^$p8ue~3cA6WQR*=&*mFxi5reHOMkBEpt9h6iUgv2w*Vh}9&|El<vLc7`4g
z(RQyPa^Y<dgQt(X4^mfE3saZG8pmxPv3t(EE~8Hb8@m5Nb9Gjh75w>h_Yr%SHf*TZ
zgd|;|y$Uf$^%xjDr!HVX!JSwLD;E@Ai5{7;3AC~BPAc9FFIsFdCoGEgEGoYtGt87)
z?JC$mKSlB!g;9_UF>gP=J3W8Azku1ugRQ>sIq}^Ww;=x6A-@1%#u#fS$OXf-V)tTU
z(~Khf9Rw%dy?=i%-8qC2!(5JLy5XmrA2Uv@yKvzhzNxK^4REoJR|dmiD>ABwpS-yu
z%RTRt7ao$OCVwX(C7l>A340RU*)T?fany_|F%z#ohr(MgQ>Eu<*XneodhG>YmX(TC
znCNWk>guuX-@R;jiUKC<y@8-}m(x*!w1+C`;!Fxv$mhL~`yz8J-9EgP&fZaLTMJXI
z7RSGVYuuLIybn9|nw5R!34PyE=l$>kOEdmssHy3YwT%tC)EsR2@%1lWxoNE1<pN2G
zfN^jdt`F>9t?i%(Q%Y7I2`ohdc<tWsSNFb@Q34yRaH_ev9jRF-WmI_b?zNhv(ul^X
zi(-w*A%=K=VN9u}dsqo`kMcP*pj9U#1B5k3YKPHll&CNr;VFn*GBUN;BM}XaH0p@@
zbZbLgl(9C|2!TC*vQ-A~!psHl@4dP`XwS$CimjATA;3lO?IdG~xHGI<$oP4*tCB4D
zSTE5EY!}qbF2BhM^R!QW(lRd@K0X!(A8}5gbOAgoSiG8po}t7F6tc7o(Ou2i4(zN!
zx^yEpyA5#h(mF|uFgNQ9%Axc(vY|}eR72*;N8>g7y&?6y^#w)sX_l|c1SUG#5hXK7
z^=tsVv~_fZvLZ_EkXu0C@Onuey}<_k{(Ll^?ss~f*)stMz@*HHpUP7d>kqD-+0n{!
zeLnTX>CwBj1kGT)e*HCsz9h6Ud$V_PT&Ps~)5%mkf;aZ|swfik5?(#Es7&79XKQ3v
zYx)r5zE|lMMuxXFH8r0%N4l6c+pQWb!yX$T=LDi@&fhpNRAHBI?cQ_ywvzX!^x9IA
z+AM=+(SoBp^kyV&G0T#<kLbaxL%GQbDN%=?yp^*g7?o8^wi(qRviOqbQ0fA{QrKpb
zd2C$VG%WveCkY=?8w|2Ab-Jl|zcM|yB<?tJ7G86&97Ejh9VQ8Eu-T*kR!1eA`0e(R
z0?9KFB~Nxk;{24emfQTl&TMMZ5C~R|jz0qPD7t3!HFonkw75XfhI$}3?A29&=TEY5
zTJEiX(@N6jI9=AYwXFdLaG-c<{g;s=ys~p5t0<*Of+Ho4k<7@Z-}5X&NV(~`czl$^
zA#&8M!TDIPn1*bQZj#{LpdgFI3B4%{0#)m(tO%>IaE;0UuA%M8L}KSgf-)E}6wuG2
zAcN${h5`5$h}o)|u%!Js8i739M{_d&R|xWd8jBu|XgV59%eLC-2zpld`>gQ((JTD3
Fe*tiy$1VT>

diff --git a/docs/_sources/grids_2023.ipynb b/docs/_sources/grids_2023.ipynb
index 62b2e8b..7047ecf 100644
--- a/docs/_sources/grids_2023.ipynb
+++ b/docs/_sources/grids_2023.ipynb
@@ -496,21 +496,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_d0aab tr:nth-child(even) {\n",
+       "#T_556fc tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_d0aab tr:nth-child(odd) {\n",
+       "#T_556fc tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_d0aab tr {\n",
+       "#T_556fc tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_d0aab th:nth-child(1) {\n",
+       "#T_556fc th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_d0aab caption {\n",
+       "#T_556fc caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -518,16 +518,16 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_d0aab\">\n",
+       "<table id=\"T_556fc\">\n",
        "  <caption>Table 1: The objects of interest. The average pcs/m per sample for each object. The fail rate is the % of all samples that the object appeared in.</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank\" >&nbsp;</th>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_d0aab_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
-       "      <th id=\"T_d0aab_level0_col1\" class=\"col_heading level0 col1\" >quantity</th>\n",
-       "      <th id=\"T_d0aab_level0_col2\" class=\"col_heading level0 col2\" >fail rate</th>\n",
-       "      <th id=\"T_d0aab_level0_col3\" class=\"col_heading level0 col3\" >% of total</th>\n",
+       "      <th id=\"T_556fc_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
+       "      <th id=\"T_556fc_level0_col1\" class=\"col_heading level0 col1\" >quantity</th>\n",
+       "      <th id=\"T_556fc_level0_col2\" class=\"col_heading level0 col2\" >fail rate</th>\n",
+       "      <th id=\"T_556fc_level0_col3\" class=\"col_heading level0 col3\" >% of total</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th class=\"index_name level0\" >code</th>\n",
@@ -540,106 +540,106 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
-       "      <th id=\"T_d0aab_level1_row0\" class=\"row_heading level1 row0\" >Industrial pellets (nurdles)</th>\n",
-       "      <td id=\"T_d0aab_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
-       "      <td id=\"T_d0aab_row0_col1\" class=\"data row0 col1\" >2686</td>\n",
-       "      <td id=\"T_d0aab_row0_col2\" class=\"data row0 col2\" >0.22</td>\n",
-       "      <td id=\"T_d0aab_row0_col3\" class=\"data row0 col3\" >0.02</td>\n",
+       "      <th id=\"T_556fc_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
+       "      <th id=\"T_556fc_level1_row0\" class=\"row_heading level1 row0\" >Industrial pellets (nurdles)</th>\n",
+       "      <td id=\"T_556fc_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
+       "      <td id=\"T_556fc_row0_col1\" class=\"data row0 col1\" >2686</td>\n",
+       "      <td id=\"T_556fc_row0_col2\" class=\"data row0 col2\" >0.22</td>\n",
+       "      <td id=\"T_556fc_row0_col3\" class=\"data row0 col3\" >0.02</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
-       "      <th id=\"T_d0aab_level1_row1\" class=\"row_heading level1 row1\" >Cigarette filters</th>\n",
-       "      <td id=\"T_d0aab_row1_col0\" class=\"data row1 col0\" >1.12</td>\n",
-       "      <td id=\"T_d0aab_row1_col1\" class=\"data row1 col1\" >16458</td>\n",
-       "      <td id=\"T_d0aab_row1_col2\" class=\"data row1 col2\" >0.85</td>\n",
-       "      <td id=\"T_d0aab_row1_col3\" class=\"data row1 col3\" >0.15</td>\n",
+       "      <th id=\"T_556fc_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
+       "      <th id=\"T_556fc_level1_row1\" class=\"row_heading level1 row1\" >Cigarette filters</th>\n",
+       "      <td id=\"T_556fc_row1_col0\" class=\"data row1 col0\" >1.12</td>\n",
+       "      <td id=\"T_556fc_row1_col1\" class=\"data row1 col1\" >16458</td>\n",
+       "      <td id=\"T_556fc_row1_col2\" class=\"data row1 col2\" >0.85</td>\n",
+       "      <td id=\"T_556fc_row1_col3\" class=\"data row1 col3\" >0.15</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
-       "      <th id=\"T_d0aab_level1_row2\" class=\"row_heading level1 row2\" >Food wrappers; candy, snacks</th>\n",
-       "      <td id=\"T_d0aab_row2_col0\" class=\"data row2 col0\" >0.54</td>\n",
-       "      <td id=\"T_d0aab_row2_col1\" class=\"data row2 col1\" >6767</td>\n",
-       "      <td id=\"T_d0aab_row2_col2\" class=\"data row2 col2\" >0.86</td>\n",
-       "      <td id=\"T_d0aab_row2_col3\" class=\"data row2 col3\" >0.06</td>\n",
+       "      <th id=\"T_556fc_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
+       "      <th id=\"T_556fc_level1_row2\" class=\"row_heading level1 row2\" >Food wrappers; candy, snacks</th>\n",
+       "      <td id=\"T_556fc_row2_col0\" class=\"data row2 col0\" >0.54</td>\n",
+       "      <td id=\"T_556fc_row2_col1\" class=\"data row2 col1\" >6767</td>\n",
+       "      <td id=\"T_556fc_row2_col2\" class=\"data row2 col2\" >0.86</td>\n",
+       "      <td id=\"T_556fc_row2_col3\" class=\"data row2 col3\" >0.06</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
-       "      <th id=\"T_d0aab_level1_row3\" class=\"row_heading level1 row3\" >Toys and party favors</th>\n",
-       "      <td id=\"T_d0aab_row3_col0\" class=\"data row3 col0\" >0.05</td>\n",
-       "      <td id=\"T_d0aab_row3_col1\" class=\"data row3 col1\" >606</td>\n",
-       "      <td id=\"T_d0aab_row3_col2\" class=\"data row3 col2\" >0.48</td>\n",
-       "      <td id=\"T_d0aab_row3_col3\" class=\"data row3 col3\" >0.01</td>\n",
+       "      <th id=\"T_556fc_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
+       "      <th id=\"T_556fc_level1_row3\" class=\"row_heading level1 row3\" >Toys and party favors</th>\n",
+       "      <td id=\"T_556fc_row3_col0\" class=\"data row3 col0\" >0.05</td>\n",
+       "      <td id=\"T_556fc_row3_col1\" class=\"data row3 col1\" >606</td>\n",
+       "      <td id=\"T_556fc_row3_col2\" class=\"data row3 col2\" >0.48</td>\n",
+       "      <td id=\"T_556fc_row3_col3\" class=\"data row3 col3\" >0.01</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
-       "      <th id=\"T_d0aab_level1_row4\" class=\"row_heading level1 row4\" >Industrial sheeting</th>\n",
-       "      <td id=\"T_d0aab_row4_col0\" class=\"data row4 col0\" >0.30</td>\n",
-       "      <td id=\"T_d0aab_row4_col1\" class=\"data row4 col1\" >3356</td>\n",
-       "      <td id=\"T_d0aab_row4_col2\" class=\"data row4 col2\" >0.57</td>\n",
-       "      <td id=\"T_d0aab_row4_col3\" class=\"data row4 col3\" >0.03</td>\n",
+       "      <th id=\"T_556fc_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
+       "      <th id=\"T_556fc_level1_row4\" class=\"row_heading level1 row4\" >Industrial sheeting</th>\n",
+       "      <td id=\"T_556fc_row4_col0\" class=\"data row4 col0\" >0.30</td>\n",
+       "      <td id=\"T_556fc_row4_col1\" class=\"data row4 col1\" >3356</td>\n",
+       "      <td id=\"T_556fc_row4_col2\" class=\"data row4 col2\" >0.57</td>\n",
+       "      <td id=\"T_556fc_row4_col3\" class=\"data row4 col3\" >0.03</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
-       "      <th id=\"T_d0aab_level1_row5\" class=\"row_heading level1 row5\" >Shotgun cartridges</th>\n",
-       "      <td id=\"T_d0aab_row5_col0\" class=\"data row5 col0\" >0.08</td>\n",
-       "      <td id=\"T_d0aab_row5_col1\" class=\"data row5 col1\" >1030</td>\n",
-       "      <td id=\"T_d0aab_row5_col2\" class=\"data row5 col2\" >0.48</td>\n",
-       "      <td id=\"T_d0aab_row5_col3\" class=\"data row5 col3\" >0.01</td>\n",
+       "      <th id=\"T_556fc_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
+       "      <th id=\"T_556fc_level1_row5\" class=\"row_heading level1 row5\" >Shotgun cartridges</th>\n",
+       "      <td id=\"T_556fc_row5_col0\" class=\"data row5 col0\" >0.08</td>\n",
+       "      <td id=\"T_556fc_row5_col1\" class=\"data row5 col1\" >1030</td>\n",
+       "      <td id=\"T_556fc_row5_col2\" class=\"data row5 col2\" >0.48</td>\n",
+       "      <td id=\"T_556fc_row5_col3\" class=\"data row5 col3\" >0.01</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row6\" class=\"row_heading level0 row6\" >G89</th>\n",
-       "      <th id=\"T_d0aab_level1_row6\" class=\"row_heading level1 row6\" >Plastic construction waste</th>\n",
-       "      <td id=\"T_d0aab_row6_col0\" class=\"data row6 col0\" >0.14</td>\n",
-       "      <td id=\"T_d0aab_row6_col1\" class=\"data row6 col1\" >1970</td>\n",
-       "      <td id=\"T_d0aab_row6_col2\" class=\"data row6 col2\" >0.51</td>\n",
-       "      <td id=\"T_d0aab_row6_col3\" class=\"data row6 col3\" >0.02</td>\n",
+       "      <th id=\"T_556fc_level0_row6\" class=\"row_heading level0 row6\" >G89</th>\n",
+       "      <th id=\"T_556fc_level1_row6\" class=\"row_heading level1 row6\" >Plastic construction waste</th>\n",
+       "      <td id=\"T_556fc_row6_col0\" class=\"data row6 col0\" >0.14</td>\n",
+       "      <td id=\"T_556fc_row6_col1\" class=\"data row6 col1\" >1970</td>\n",
+       "      <td id=\"T_556fc_row6_col2\" class=\"data row6 col2\" >0.51</td>\n",
+       "      <td id=\"T_556fc_row6_col3\" class=\"data row6 col3\" >0.02</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row7\" class=\"row_heading level0 row7\" >G95</th>\n",
-       "      <th id=\"T_d0aab_level1_row7\" class=\"row_heading level1 row7\" >Cotton bud/swab sticks</th>\n",
-       "      <td id=\"T_d0aab_row7_col0\" class=\"data row7 col0\" >0.39</td>\n",
-       "      <td id=\"T_d0aab_row7_col1\" class=\"data row7 col1\" >4777</td>\n",
-       "      <td id=\"T_d0aab_row7_col2\" class=\"data row7 col2\" >0.74</td>\n",
-       "      <td id=\"T_d0aab_row7_col3\" class=\"data row7 col3\" >0.04</td>\n",
+       "      <th id=\"T_556fc_level0_row7\" class=\"row_heading level0 row7\" >G95</th>\n",
+       "      <th id=\"T_556fc_level1_row7\" class=\"row_heading level1 row7\" >Cotton bud/swab sticks</th>\n",
+       "      <td id=\"T_556fc_row7_col0\" class=\"data row7 col0\" >0.39</td>\n",
+       "      <td id=\"T_556fc_row7_col1\" class=\"data row7 col1\" >4777</td>\n",
+       "      <td id=\"T_556fc_row7_col2\" class=\"data row7 col2\" >0.74</td>\n",
+       "      <td id=\"T_556fc_row7_col3\" class=\"data row7 col3\" >0.04</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row8\" class=\"row_heading level0 row8\" >G96</th>\n",
-       "      <th id=\"T_d0aab_level1_row8\" class=\"row_heading level1 row8\" >Sanitary pads /panty liners/tampons and applicators</th>\n",
-       "      <td id=\"T_d0aab_row8_col0\" class=\"data row8 col0\" >0.04</td>\n",
-       "      <td id=\"T_d0aab_row8_col1\" class=\"data row8 col1\" >373</td>\n",
-       "      <td id=\"T_d0aab_row8_col2\" class=\"data row8 col2\" >0.29</td>\n",
-       "      <td id=\"T_d0aab_row8_col3\" class=\"data row8 col3\" >0.00</td>\n",
+       "      <th id=\"T_556fc_level0_row8\" class=\"row_heading level0 row8\" >G96</th>\n",
+       "      <th id=\"T_556fc_level1_row8\" class=\"row_heading level1 row8\" >Sanitary pads /panty liners/tampons and applicators</th>\n",
+       "      <td id=\"T_556fc_row8_col0\" class=\"data row8 col0\" >0.04</td>\n",
+       "      <td id=\"T_556fc_row8_col1\" class=\"data row8 col1\" >373</td>\n",
+       "      <td id=\"T_556fc_row8_col2\" class=\"data row8 col2\" >0.29</td>\n",
+       "      <td id=\"T_556fc_row8_col3\" class=\"data row8 col3\" >0.00</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row9\" class=\"row_heading level0 row9\" >Gcaps</th>\n",
-       "      <th id=\"T_d0aab_level1_row9\" class=\"row_heading level1 row9\" >Plastic bottle lids</th>\n",
-       "      <td id=\"T_d0aab_row9_col0\" class=\"data row9 col0\" >0.31</td>\n",
-       "      <td id=\"T_d0aab_row9_col1\" class=\"data row9 col1\" >3953</td>\n",
-       "      <td id=\"T_d0aab_row9_col2\" class=\"data row9 col2\" >0.84</td>\n",
-       "      <td id=\"T_d0aab_row9_col3\" class=\"data row9 col3\" >0.04</td>\n",
+       "      <th id=\"T_556fc_level0_row9\" class=\"row_heading level0 row9\" >Gcaps</th>\n",
+       "      <th id=\"T_556fc_level1_row9\" class=\"row_heading level1 row9\" >Plastic bottle lids</th>\n",
+       "      <td id=\"T_556fc_row9_col0\" class=\"data row9 col0\" >0.31</td>\n",
+       "      <td id=\"T_556fc_row9_col1\" class=\"data row9 col1\" >3953</td>\n",
+       "      <td id=\"T_556fc_row9_col2\" class=\"data row9 col2\" >0.84</td>\n",
+       "      <td id=\"T_556fc_row9_col3\" class=\"data row9 col3\" >0.04</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row10\" class=\"row_heading level0 row10\" >Gfoam</th>\n",
-       "      <th id=\"T_d0aab_level1_row10\" class=\"row_heading level1 row10\" >Expanded polystyrene</th>\n",
-       "      <td id=\"T_d0aab_row10_col0\" class=\"data row10 col0\" >1.02</td>\n",
-       "      <td id=\"T_d0aab_row10_col1\" class=\"data row10 col1\" >12871</td>\n",
-       "      <td id=\"T_d0aab_row10_col2\" class=\"data row10 col2\" >0.81</td>\n",
-       "      <td id=\"T_d0aab_row10_col3\" class=\"data row10 col3\" >0.12</td>\n",
+       "      <th id=\"T_556fc_level0_row10\" class=\"row_heading level0 row10\" >Gfoam</th>\n",
+       "      <th id=\"T_556fc_level1_row10\" class=\"row_heading level1 row10\" >Expanded polystyrene</th>\n",
+       "      <td id=\"T_556fc_row10_col0\" class=\"data row10 col0\" >1.02</td>\n",
+       "      <td id=\"T_556fc_row10_col1\" class=\"data row10 col1\" >12871</td>\n",
+       "      <td id=\"T_556fc_row10_col2\" class=\"data row10 col2\" >0.81</td>\n",
+       "      <td id=\"T_556fc_row10_col3\" class=\"data row10 col3\" >0.12</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row11\" class=\"row_heading level0 row11\" >Gfrags</th>\n",
-       "      <th id=\"T_d0aab_level1_row11\" class=\"row_heading level1 row11\" >Fragmented plastics</th>\n",
-       "      <td id=\"T_d0aab_row11_col0\" class=\"data row11 col0\" >1.34</td>\n",
-       "      <td id=\"T_d0aab_row11_col1\" class=\"data row11 col1\" >17479</td>\n",
-       "      <td id=\"T_d0aab_row11_col2\" class=\"data row11 col2\" >0.93</td>\n",
-       "      <td id=\"T_d0aab_row11_col3\" class=\"data row11 col3\" >0.16</td>\n",
+       "      <th id=\"T_556fc_level0_row11\" class=\"row_heading level0 row11\" >Gfrags</th>\n",
+       "      <th id=\"T_556fc_level1_row11\" class=\"row_heading level1 row11\" >Fragmented plastics</th>\n",
+       "      <td id=\"T_556fc_row11_col0\" class=\"data row11 col0\" >1.34</td>\n",
+       "      <td id=\"T_556fc_row11_col1\" class=\"data row11 col1\" >17479</td>\n",
+       "      <td id=\"T_556fc_row11_col2\" class=\"data row11 col2\" >0.93</td>\n",
+       "      <td id=\"T_556fc_row11_col3\" class=\"data row11 col3\" >0.16</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f602427b50>"
+       "<pandas.io.formats.style.Styler at 0x7c6c3ed037f0>"
       ]
      },
      "execution_count": 6,
@@ -759,18 +759,25 @@
    "execution_count": 7,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_91665 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_91665 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_91665 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_91665 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_91665 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_91665\">\n  <caption>The number of different locations and cities for the data. Note that there are 31 different municipalitites in all.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_91665_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_91665_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_91665_level0_row0\" class=\"row_heading level0 row0\" >Number of cities</th>\n      <td id=\"T_91665_row0_col0\" class=\"data row0 col0\" >21</td>\n      <td id=\"T_91665_row0_col1\" class=\"data row0 col1\" >19</td>\n    </tr>\n    <tr>\n      <th id=\"T_91665_level0_row1\" class=\"row_heading level0 row1\" >Number of locations</th>\n      <td id=\"T_91665_row1_col0\" class=\"data row1 col0\" >48</td>\n      <td id=\"T_91665_row1_col1\" class=\"data row1 col1\" >23</td>\n    </tr>\n    <tr>\n      <th id=\"T_91665_level0_row2\" class=\"row_heading level0 row2\" >Total objects</th>\n      <td id=\"T_91665_row2_col0\" class=\"data row2 col0\" >57,623</td>\n      <td id=\"T_91665_row2_col1\" class=\"data row2 col1\" >14,703</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x76f602293490>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_540d8 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_540d8 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_540d8 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_540d8 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_540d8 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_540d8\">\n  <caption>The number of different locations and cities for the data. Note that there are 31 different municipalitites in all.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_540d8_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_540d8_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_540d8_level0_row0\" class=\"row_heading level0 row0\" >Number of cities</th>\n      <td id=\"T_540d8_row0_col0\" class=\"data row0 col0\" >21</td>\n      <td id=\"T_540d8_row0_col1\" class=\"data row0 col1\" >19</td>\n    </tr>\n    <tr>\n      <th id=\"T_540d8_level0_row1\" class=\"row_heading level0 row1\" >Number of locations</th>\n      <td id=\"T_540d8_row1_col0\" class=\"data row1 col0\" >48</td>\n      <td id=\"T_540d8_row1_col1\" class=\"data row1 col1\" >23</td>\n    </tr>\n    <tr>\n      <th id=\"T_540d8_level0_row2\" class=\"row_heading level0 row2\" >Total objects</th>\n      <td id=\"T_540d8_row2_col0\" class=\"data row2 col0\" >57,623</td>\n      <td id=\"T_540d8_row2_col1\" class=\"data row2 col1\" >14,703</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7c6c3ec92fa0>"
      },
      "metadata": {
       "scrapbook": {
@@ -832,7 +839,9 @@
     "slideshow": {
      "slide_type": ""
     },
-    "tags": []
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
@@ -870,12 +879,19 @@
    "execution_count": 9,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
@@ -909,18 +925,25 @@
    "execution_count": 10,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_4afd1 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_4afd1 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_4afd1 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_4afd1 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_4afd1 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_4afd1\">\n  <caption>The observed values from the training and testing data. Remark that the testing data is only 22% of all the data. This is because we are only in the first year of a six year sampling period</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_4afd1_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_4afd1_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_4afd1_level0_row0\" class=\"row_heading level0 row0\" >weight all samples</th>\n      <td id=\"T_4afd1_row0_col0\" class=\"data row0 col0\" >0.78</td>\n      <td id=\"T_4afd1_row0_col1\" class=\"data row0 col1\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row1\" class=\"row_heading level0 row1\" >Number of samples</th>\n      <td id=\"T_4afd1_row1_col0\" class=\"data row1 col0\" >263</td>\n      <td id=\"T_4afd1_row1_col1\" class=\"data row1 col1\" >73</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row2\" class=\"row_heading level0 row2\" >Median</th>\n      <td id=\"T_4afd1_row2_col0\" class=\"data row2 col0\" >3.47</td>\n      <td id=\"T_4afd1_row2_col1\" class=\"data row2 col1\" >2.28</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row3\" class=\"row_heading level0 row3\" >Average</th>\n      <td id=\"T_4afd1_row3_col0\" class=\"data row3 col0\" >6.13</td>\n      <td id=\"T_4afd1_row3_col1\" class=\"data row3 col1\" >3.25</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row4\" class=\"row_heading level0 row4\" >25th percentile</th>\n      <td id=\"T_4afd1_row4_col0\" class=\"data row4 col0\" >1.52</td>\n      <td id=\"T_4afd1_row4_col1\" class=\"data row4 col1\" >0.78</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row5\" class=\"row_heading level0 row5\" >75th percentile</th>\n      <td id=\"T_4afd1_row5_col0\" class=\"data row5 col0\" >6.69</td>\n      <td id=\"T_4afd1_row5_col1\" class=\"data row5 col1\" >4.31</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x76f65a0b9dc0>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_59f14 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_59f14 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_59f14 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_59f14 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_59f14 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_59f14\">\n  <caption>The observed values from the training and testing data. Remark that the testing data is only 22% of all the data. This is because we are only in the first year of a six year sampling period</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_59f14_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_59f14_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_59f14_level0_row0\" class=\"row_heading level0 row0\" >weight all samples</th>\n      <td id=\"T_59f14_row0_col0\" class=\"data row0 col0\" >0.78</td>\n      <td id=\"T_59f14_row0_col1\" class=\"data row0 col1\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row1\" class=\"row_heading level0 row1\" >Number of samples</th>\n      <td id=\"T_59f14_row1_col0\" class=\"data row1 col0\" >263</td>\n      <td id=\"T_59f14_row1_col1\" class=\"data row1 col1\" >73</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row2\" class=\"row_heading level0 row2\" >Median</th>\n      <td id=\"T_59f14_row2_col0\" class=\"data row2 col0\" >3.47</td>\n      <td id=\"T_59f14_row2_col1\" class=\"data row2 col1\" >2.28</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row3\" class=\"row_heading level0 row3\" >Average</th>\n      <td id=\"T_59f14_row3_col0\" class=\"data row3 col0\" >6.13</td>\n      <td id=\"T_59f14_row3_col1\" class=\"data row3 col1\" >3.25</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row4\" class=\"row_heading level0 row4\" >25th percentile</th>\n      <td id=\"T_59f14_row4_col0\" class=\"data row4 col0\" >1.52</td>\n      <td id=\"T_59f14_row4_col1\" class=\"data row4 col1\" >0.78</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row5\" class=\"row_heading level0 row5\" >75th percentile</th>\n      <td id=\"T_59f14_row5_col0\" class=\"data row5 col0\" >6.69</td>\n      <td id=\"T_59f14_row5_col1\" class=\"data row5 col1\" >4.31</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7c6bfdf61a00>"
      },
      "metadata": {
       "scrapbook": {
@@ -974,12 +997,19 @@
    "execution_count": 11,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1079,12 +1109,19 @@
    "execution_count": 12,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1096,12 +1133,19 @@
    "execution_count": 13,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1172,12 +1216,19 @@
    "execution_count": 14,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1272,33 +1323,40 @@
    "execution_count": 15,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_0e66b tr:nth-child(even) {\n",
+       "#T_9a101 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_0e66b tr:nth-child(odd) {\n",
+       "#T_9a101 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_0e66b tr {\n",
+       "#T_9a101 tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_0e66b th:nth-child(1) {\n",
+       "#T_9a101 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_0e66b caption {\n",
+       "#T_9a101 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1306,120 +1364,120 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_0e66b\">\n",
+       "<table id=\"T_9a101\">\n",
        "  <caption>Table 4: The 94% probability interval of the objects of interest for Saint Sulpice. The median value is used for the predictions</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_0e66b_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_0e66b_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_0e66b_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_0e66b_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_0e66b_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_0e66b_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_0e66b_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_0e66b_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_0e66b_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_0e66b_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_9a101_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_9a101_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_9a101_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_9a101_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_9a101_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_9a101_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_9a101_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_9a101_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_9a101_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_9a101_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row0\" class=\"row_heading level0 row0\" >3%</th>\n",
-       "      <td id=\"T_0e66b_row0_col0\" class=\"data row0 col0\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col1\" class=\"data row0 col1\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col2\" class=\"data row0 col2\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col6\" class=\"data row0 col6\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col7\" class=\"data row0 col7\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col8\" class=\"data row0 col8\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col9\" class=\"data row0 col9\" >0.00</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row1\" class=\"row_heading level0 row1\" >25%</th>\n",
-       "      <td id=\"T_0e66b_row1_col0\" class=\"data row1 col0\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col2\" class=\"data row1 col2\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col3\" class=\"data row1 col3\" >0.01</td>\n",
-       "      <td id=\"T_0e66b_row1_col4\" class=\"data row1 col4\" >0.01</td>\n",
-       "      <td id=\"T_0e66b_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col6\" class=\"data row1 col6\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col7\" class=\"data row1 col7\" >0.01</td>\n",
-       "      <td id=\"T_0e66b_row1_col8\" class=\"data row1 col8\" >0.03</td>\n",
-       "      <td id=\"T_0e66b_row1_col9\" class=\"data row1 col9\" >0.00</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row2\" class=\"row_heading level0 row2\" >48%</th>\n",
-       "      <td id=\"T_0e66b_row2_col0\" class=\"data row2 col0\" >0.03</td>\n",
-       "      <td id=\"T_0e66b_row2_col1\" class=\"data row2 col1\" >0.42</td>\n",
-       "      <td id=\"T_0e66b_row2_col2\" class=\"data row2 col2\" >0.13</td>\n",
-       "      <td id=\"T_0e66b_row2_col3\" class=\"data row2 col3\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row2_col4\" class=\"data row2 col4\" >0.14</td>\n",
-       "      <td id=\"T_0e66b_row2_col5\" class=\"data row2 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row2_col6\" class=\"data row2 col6\" >0.30</td>\n",
-       "      <td id=\"T_0e66b_row2_col7\" class=\"data row2 col7\" >0.08</td>\n",
-       "      <td id=\"T_0e66b_row2_col8\" class=\"data row2 col8\" >0.12</td>\n",
-       "      <td id=\"T_0e66b_row2_col9\" class=\"data row2 col9\" >0.35</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row3\" class=\"row_heading level0 row3\" >50%</th>\n",
-       "      <td id=\"T_0e66b_row3_col0\" class=\"data row3 col0\" >0.08</td>\n",
-       "      <td id=\"T_0e66b_row3_col1\" class=\"data row3 col1\" >0.45</td>\n",
-       "      <td id=\"T_0e66b_row3_col2\" class=\"data row3 col2\" >0.13</td>\n",
-       "      <td id=\"T_0e66b_row3_col3\" class=\"data row3 col3\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row3_col4\" class=\"data row3 col4\" >0.16</td>\n",
-       "      <td id=\"T_0e66b_row3_col5\" class=\"data row3 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row3_col6\" class=\"data row3 col6\" >0.32</td>\n",
-       "      <td id=\"T_0e66b_row3_col7\" class=\"data row3 col7\" >0.09</td>\n",
-       "      <td id=\"T_0e66b_row3_col8\" class=\"data row3 col8\" >0.14</td>\n",
-       "      <td id=\"T_0e66b_row3_col9\" class=\"data row3 col9\" >0.41</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row4\" class=\"row_heading level0 row4\" >52%</th>\n",
-       "      <td id=\"T_0e66b_row4_col0\" class=\"data row4 col0\" >0.10</td>\n",
-       "      <td id=\"T_0e66b_row4_col1\" class=\"data row4 col1\" >0.46</td>\n",
-       "      <td id=\"T_0e66b_row4_col2\" class=\"data row4 col2\" >0.13</td>\n",
-       "      <td id=\"T_0e66b_row4_col3\" class=\"data row4 col3\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row4_col4\" class=\"data row4 col4\" >0.17</td>\n",
-       "      <td id=\"T_0e66b_row4_col5\" class=\"data row4 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row4_col6\" class=\"data row4 col6\" >0.34</td>\n",
-       "      <td id=\"T_0e66b_row4_col7\" class=\"data row4 col7\" >0.09</td>\n",
-       "      <td id=\"T_0e66b_row4_col8\" class=\"data row4 col8\" >0.14</td>\n",
-       "      <td id=\"T_0e66b_row4_col9\" class=\"data row4 col9\" >0.50</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row5\" class=\"row_heading level0 row5\" >75%</th>\n",
-       "      <td id=\"T_0e66b_row5_col0\" class=\"data row5 col0\" >0.54</td>\n",
-       "      <td id=\"T_0e66b_row5_col1\" class=\"data row5 col1\" >0.66</td>\n",
-       "      <td id=\"T_0e66b_row5_col2\" class=\"data row5 col2\" >0.48</td>\n",
-       "      <td id=\"T_0e66b_row5_col3\" class=\"data row5 col3\" >0.06</td>\n",
-       "      <td id=\"T_0e66b_row5_col4\" class=\"data row5 col4\" >0.31</td>\n",
-       "      <td id=\"T_0e66b_row5_col5\" class=\"data row5 col5\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row5_col6\" class=\"data row5 col6\" >0.52</td>\n",
-       "      <td id=\"T_0e66b_row5_col7\" class=\"data row5 col7\" >0.12</td>\n",
-       "      <td id=\"T_0e66b_row5_col8\" class=\"data row5 col8\" >0.23</td>\n",
-       "      <td id=\"T_0e66b_row5_col9\" class=\"data row5 col9\" >0.82</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row6\" class=\"row_heading level0 row6\" >97%</th>\n",
-       "      <td id=\"T_0e66b_row6_col0\" class=\"data row6 col0\" >1.39</td>\n",
-       "      <td id=\"T_0e66b_row6_col1\" class=\"data row6 col1\" >1.29</td>\n",
-       "      <td id=\"T_0e66b_row6_col2\" class=\"data row6 col2\" >0.91</td>\n",
-       "      <td id=\"T_0e66b_row6_col3\" class=\"data row6 col3\" >0.11</td>\n",
-       "      <td id=\"T_0e66b_row6_col4\" class=\"data row6 col4\" >2.83</td>\n",
-       "      <td id=\"T_0e66b_row6_col5\" class=\"data row6 col5\" >0.09</td>\n",
-       "      <td id=\"T_0e66b_row6_col6\" class=\"data row6 col6\" >1.00</td>\n",
-       "      <td id=\"T_0e66b_row6_col7\" class=\"data row6 col7\" >0.22</td>\n",
-       "      <td id=\"T_0e66b_row6_col8\" class=\"data row6 col8\" >0.41</td>\n",
-       "      <td id=\"T_0e66b_row6_col9\" class=\"data row6 col9\" >2.75</td>\n",
+       "      <th id=\"T_9a101_level0_row0\" class=\"row_heading level0 row0\" >3%</th>\n",
+       "      <td id=\"T_9a101_row0_col0\" class=\"data row0 col0\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col1\" class=\"data row0 col1\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col2\" class=\"data row0 col2\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col6\" class=\"data row0 col6\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col7\" class=\"data row0 col7\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col8\" class=\"data row0 col8\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col9\" class=\"data row0 col9\" >0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row1\" class=\"row_heading level0 row1\" >25%</th>\n",
+       "      <td id=\"T_9a101_row1_col0\" class=\"data row1 col0\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col1\" class=\"data row1 col1\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row1_col2\" class=\"data row1 col2\" >0.03</td>\n",
+       "      <td id=\"T_9a101_row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col4\" class=\"data row1 col4\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col6\" class=\"data row1 col6\" >0.01</td>\n",
+       "      <td id=\"T_9a101_row1_col7\" class=\"data row1 col7\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col8\" class=\"data row1 col8\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row1_col9\" class=\"data row1 col9\" >0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row2\" class=\"row_heading level0 row2\" >48%</th>\n",
+       "      <td id=\"T_9a101_row2_col0\" class=\"data row2 col0\" >0.08</td>\n",
+       "      <td id=\"T_9a101_row2_col1\" class=\"data row2 col1\" >0.46</td>\n",
+       "      <td id=\"T_9a101_row2_col2\" class=\"data row2 col2\" >0.35</td>\n",
+       "      <td id=\"T_9a101_row2_col3\" class=\"data row2 col3\" >0.03</td>\n",
+       "      <td id=\"T_9a101_row2_col4\" class=\"data row2 col4\" >0.16</td>\n",
+       "      <td id=\"T_9a101_row2_col5\" class=\"data row2 col5\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row2_col6\" class=\"data row2 col6\" >0.32</td>\n",
+       "      <td id=\"T_9a101_row2_col7\" class=\"data row2 col7\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row2_col8\" class=\"data row2 col8\" >0.11</td>\n",
+       "      <td id=\"T_9a101_row2_col9\" class=\"data row2 col9\" >0.68</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row3\" class=\"row_heading level0 row3\" >50%</th>\n",
+       "      <td id=\"T_9a101_row3_col0\" class=\"data row3 col0\" >0.12</td>\n",
+       "      <td id=\"T_9a101_row3_col1\" class=\"data row3 col1\" >0.47</td>\n",
+       "      <td id=\"T_9a101_row3_col2\" class=\"data row3 col2\" >0.39</td>\n",
+       "      <td id=\"T_9a101_row3_col3\" class=\"data row3 col3\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row3_col4\" class=\"data row3 col4\" >0.16</td>\n",
+       "      <td id=\"T_9a101_row3_col5\" class=\"data row3 col5\" >0.01</td>\n",
+       "      <td id=\"T_9a101_row3_col6\" class=\"data row3 col6\" >0.32</td>\n",
+       "      <td id=\"T_9a101_row3_col7\" class=\"data row3 col7\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row3_col8\" class=\"data row3 col8\" >0.11</td>\n",
+       "      <td id=\"T_9a101_row3_col9\" class=\"data row3 col9\" >0.74</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row4\" class=\"row_heading level0 row4\" >52%</th>\n",
+       "      <td id=\"T_9a101_row4_col0\" class=\"data row4 col0\" >0.22</td>\n",
+       "      <td id=\"T_9a101_row4_col1\" class=\"data row4 col1\" >0.48</td>\n",
+       "      <td id=\"T_9a101_row4_col2\" class=\"data row4 col2\" >0.43</td>\n",
+       "      <td id=\"T_9a101_row4_col3\" class=\"data row4 col3\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row4_col4\" class=\"data row4 col4\" >0.22</td>\n",
+       "      <td id=\"T_9a101_row4_col5\" class=\"data row4 col5\" >0.02</td>\n",
+       "      <td id=\"T_9a101_row4_col6\" class=\"data row4 col6\" >0.34</td>\n",
+       "      <td id=\"T_9a101_row4_col7\" class=\"data row4 col7\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row4_col8\" class=\"data row4 col8\" >0.12</td>\n",
+       "      <td id=\"T_9a101_row4_col9\" class=\"data row4 col9\" >0.74</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row5\" class=\"row_heading level0 row5\" >75%</th>\n",
+       "      <td id=\"T_9a101_row5_col0\" class=\"data row5 col0\" >0.68</td>\n",
+       "      <td id=\"T_9a101_row5_col1\" class=\"data row5 col1\" >0.93</td>\n",
+       "      <td id=\"T_9a101_row5_col2\" class=\"data row5 col2\" >0.57</td>\n",
+       "      <td id=\"T_9a101_row5_col3\" class=\"data row5 col3\" >0.08</td>\n",
+       "      <td id=\"T_9a101_row5_col4\" class=\"data row5 col4\" >0.33</td>\n",
+       "      <td id=\"T_9a101_row5_col5\" class=\"data row5 col5\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row5_col6\" class=\"data row5 col6\" >0.52</td>\n",
+       "      <td id=\"T_9a101_row5_col7\" class=\"data row5 col7\" >0.08</td>\n",
+       "      <td id=\"T_9a101_row5_col8\" class=\"data row5 col8\" >0.23</td>\n",
+       "      <td id=\"T_9a101_row5_col9\" class=\"data row5 col9\" >1.24</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row6\" class=\"row_heading level0 row6\" >97%</th>\n",
+       "      <td id=\"T_9a101_row6_col0\" class=\"data row6 col0\" >1.46</td>\n",
+       "      <td id=\"T_9a101_row6_col1\" class=\"data row6 col1\" >1.47</td>\n",
+       "      <td id=\"T_9a101_row6_col2\" class=\"data row6 col2\" >1.21</td>\n",
+       "      <td id=\"T_9a101_row6_col3\" class=\"data row6 col3\" >0.11</td>\n",
+       "      <td id=\"T_9a101_row6_col4\" class=\"data row6 col4\" >0.64</td>\n",
+       "      <td id=\"T_9a101_row6_col5\" class=\"data row6 col5\" >5.58</td>\n",
+       "      <td id=\"T_9a101_row6_col6\" class=\"data row6 col6\" >1.11</td>\n",
+       "      <td id=\"T_9a101_row6_col7\" class=\"data row6 col7\" >0.20</td>\n",
+       "      <td id=\"T_9a101_row6_col8\" class=\"data row6 col8\" >0.50</td>\n",
+       "      <td id=\"T_9a101_row6_col9\" class=\"data row6 col9\" >5.05</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5cff55910>"
+       "<pandas.io.formats.style.Styler at 0x7c6c3ec29580>"
       ]
      },
      "execution_count": 15,
@@ -1471,12 +1529,19 @@
    "execution_count": 16,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1507,12 +1572,19 @@
    "execution_count": 17,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1525,33 +1597,40 @@
    "execution_count": 18,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_ac8e3 tr:nth-child(even) {\n",
+       "#T_abf7a tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_ac8e3 tr:nth-child(odd) {\n",
+       "#T_abf7a tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_ac8e3 tr {\n",
+       "#T_abf7a tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_ac8e3 th:nth-child(1) {\n",
+       "#T_abf7a th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_ac8e3 caption {\n",
+       "#T_abf7a caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1559,146 +1638,146 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_ac8e3\">\n",
+       "<table id=\"T_abf7a\">\n",
        "  <caption>Table 5: The estimated amount in pcs/meter for each object that the participants expected to find.</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_ac8e3_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_ac8e3_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_ac8e3_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_ac8e3_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_ac8e3_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_ac8e3_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_ac8e3_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_ac8e3_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_ac8e3_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_ac8e3_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_abf7a_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_abf7a_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_abf7a_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_abf7a_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_abf7a_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_abf7a_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_abf7a_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_abf7a_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_abf7a_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_abf7a_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
-       "      <td id=\"T_ac8e3_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
-       "      <td id=\"T_ac8e3_row0_col1\" class=\"data row0 col1\" >1.12</td>\n",
-       "      <td id=\"T_ac8e3_row0_col2\" class=\"data row0 col2\" >0.54</td>\n",
-       "      <td id=\"T_ac8e3_row0_col3\" class=\"data row0 col3\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row0_col4\" class=\"data row0 col4\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row0_col5\" class=\"data row0 col5\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row0_col6\" class=\"data row0 col6\" >0.39</td>\n",
-       "      <td id=\"T_ac8e3_row0_col7\" class=\"data row0 col7\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row0_col8\" class=\"data row0 col8\" >0.31</td>\n",
-       "      <td id=\"T_ac8e3_row0_col9\" class=\"data row0 col9\" >1.34</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
-       "      <td id=\"T_ac8e3_row1_col0\" class=\"data row1 col0\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row1_col1\" class=\"data row1 col1\" >0.57</td>\n",
-       "      <td id=\"T_ac8e3_row1_col2\" class=\"data row1 col2\" >0.24</td>\n",
-       "      <td id=\"T_ac8e3_row1_col3\" class=\"data row1 col3\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row1_col4\" class=\"data row1 col4\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row1_col5\" class=\"data row1 col5\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row1_col6\" class=\"data row1 col6\" >0.16</td>\n",
-       "      <td id=\"T_ac8e3_row1_col7\" class=\"data row1 col7\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row1_col8\" class=\"data row1 col8\" >0.14</td>\n",
-       "      <td id=\"T_ac8e3_row1_col9\" class=\"data row1 col9\" >0.22</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
-       "      <td id=\"T_ac8e3_row2_col0\" class=\"data row2 col0\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row2_col1\" class=\"data row2 col1\" >0.80</td>\n",
-       "      <td id=\"T_ac8e3_row2_col2\" class=\"data row2 col2\" >0.20</td>\n",
-       "      <td id=\"T_ac8e3_row2_col3\" class=\"data row2 col3\" >0.02</td>\n",
-       "      <td id=\"T_ac8e3_row2_col4\" class=\"data row2 col4\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row2_col5\" class=\"data row2 col5\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row2_col6\" class=\"data row2 col6\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row2_col7\" class=\"data row2 col7\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row2_col8\" class=\"data row2 col8\" >0.25</td>\n",
-       "      <td id=\"T_ac8e3_row2_col9\" class=\"data row2 col9\" >1.20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
-       "      <td id=\"T_ac8e3_row3_col0\" class=\"data row3 col0\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row3_col1\" class=\"data row3 col1\" >0.35</td>\n",
-       "      <td id=\"T_ac8e3_row3_col2\" class=\"data row3 col2\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row3_col3\" class=\"data row3 col3\" >0.03</td>\n",
-       "      <td id=\"T_ac8e3_row3_col4\" class=\"data row3 col4\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row3_col5\" class=\"data row3 col5\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row3_col6\" class=\"data row3 col6\" >0.06</td>\n",
-       "      <td id=\"T_ac8e3_row3_col7\" class=\"data row3 col7\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row3_col8\" class=\"data row3 col8\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row3_col9\" class=\"data row3 col9\" >0.50</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
-       "      <td id=\"T_ac8e3_row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
-       "      <td id=\"T_ac8e3_row4_col1\" class=\"data row4 col1\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row4_col2\" class=\"data row4 col2\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row4_col3\" class=\"data row4 col3\" >0.02</td>\n",
-       "      <td id=\"T_ac8e3_row4_col4\" class=\"data row4 col4\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row4_col5\" class=\"data row4 col5\" >0.00</td>\n",
-       "      <td id=\"T_ac8e3_row4_col6\" class=\"data row4 col6\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row4_col7\" class=\"data row4 col7\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row4_col8\" class=\"data row4 col8\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row4_col9\" class=\"data row4 col9\" >0.12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
-       "      <td id=\"T_ac8e3_row5_col0\" class=\"data row5 col0\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row5_col1\" class=\"data row5 col1\" >0.50</td>\n",
-       "      <td id=\"T_ac8e3_row5_col2\" class=\"data row5 col2\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row5_col3\" class=\"data row5 col3\" >0.03</td>\n",
-       "      <td id=\"T_ac8e3_row5_col4\" class=\"data row5 col4\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row5_col5\" class=\"data row5 col5\" >0.00</td>\n",
-       "      <td id=\"T_ac8e3_row5_col6\" class=\"data row5 col6\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row5_col7\" class=\"data row5 col7\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row5_col8\" class=\"data row5 col8\" >0.20</td>\n",
-       "      <td id=\"T_ac8e3_row5_col9\" class=\"data row5 col9\" >0.20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
-       "      <td id=\"T_ac8e3_row6_col0\" class=\"data row6 col0\" >0.16</td>\n",
-       "      <td id=\"T_ac8e3_row6_col1\" class=\"data row6 col1\" >1.12</td>\n",
-       "      <td id=\"T_ac8e3_row6_col2\" class=\"data row6 col2\" >0.54</td>\n",
-       "      <td id=\"T_ac8e3_row6_col3\" class=\"data row6 col3\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row6_col4\" class=\"data row6 col4\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row6_col5\" class=\"data row6 col5\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row6_col6\" class=\"data row6 col6\" >0.39</td>\n",
-       "      <td id=\"T_ac8e3_row6_col7\" class=\"data row6 col7\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row6_col8\" class=\"data row6 col8\" >0.31</td>\n",
-       "      <td id=\"T_ac8e3_row6_col9\" class=\"data row6 col9\" >1.34</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
-       "      <td id=\"T_ac8e3_row7_col0\" class=\"data row7 col0\" >6.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col1\" class=\"data row7 col1\" >3.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col2\" class=\"data row7 col2\" >0.60</td>\n",
-       "      <td id=\"T_ac8e3_row7_col3\" class=\"data row7 col3\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row7_col4\" class=\"data row7 col4\" >0.40</td>\n",
-       "      <td id=\"T_ac8e3_row7_col5\" class=\"data row7 col5\" >0.03</td>\n",
-       "      <td id=\"T_ac8e3_row7_col6\" class=\"data row7 col6\" >0.80</td>\n",
-       "      <td id=\"T_ac8e3_row7_col7\" class=\"data row7 col7\" >1.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col8\" class=\"data row7 col8\" >2.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col9\" class=\"data row7 col9\" >1.34</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
-       "      <td id=\"T_ac8e3_row8_col0\" class=\"data row8 col0\" >0.40</td>\n",
-       "      <td id=\"T_ac8e3_row8_col1\" class=\"data row8 col1\" >1.50</td>\n",
-       "      <td id=\"T_ac8e3_row8_col2\" class=\"data row8 col2\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row8_col3\" class=\"data row8 col3\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row8_col4\" class=\"data row8 col4\" >1.10</td>\n",
-       "      <td id=\"T_ac8e3_row8_col5\" class=\"data row8 col5\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row8_col6\" class=\"data row8 col6\" >0.50</td>\n",
-       "      <td id=\"T_ac8e3_row8_col7\" class=\"data row8 col7\" >0.20</td>\n",
-       "      <td id=\"T_ac8e3_row8_col8\" class=\"data row8 col8\" >0.40</td>\n",
-       "      <td id=\"T_ac8e3_row8_col9\" class=\"data row8 col9\" >2.00</td>\n",
+       "      <th id=\"T_abf7a_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
+       "      <td id=\"T_abf7a_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
+       "      <td id=\"T_abf7a_row0_col1\" class=\"data row0 col1\" >1.12</td>\n",
+       "      <td id=\"T_abf7a_row0_col2\" class=\"data row0 col2\" >0.54</td>\n",
+       "      <td id=\"T_abf7a_row0_col3\" class=\"data row0 col3\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row0_col4\" class=\"data row0 col4\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row0_col5\" class=\"data row0 col5\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row0_col6\" class=\"data row0 col6\" >0.39</td>\n",
+       "      <td id=\"T_abf7a_row0_col7\" class=\"data row0 col7\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row0_col8\" class=\"data row0 col8\" >0.31</td>\n",
+       "      <td id=\"T_abf7a_row0_col9\" class=\"data row0 col9\" >1.34</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
+       "      <td id=\"T_abf7a_row1_col0\" class=\"data row1 col0\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row1_col1\" class=\"data row1 col1\" >0.57</td>\n",
+       "      <td id=\"T_abf7a_row1_col2\" class=\"data row1 col2\" >0.24</td>\n",
+       "      <td id=\"T_abf7a_row1_col3\" class=\"data row1 col3\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row1_col4\" class=\"data row1 col4\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row1_col5\" class=\"data row1 col5\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row1_col6\" class=\"data row1 col6\" >0.16</td>\n",
+       "      <td id=\"T_abf7a_row1_col7\" class=\"data row1 col7\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row1_col8\" class=\"data row1 col8\" >0.14</td>\n",
+       "      <td id=\"T_abf7a_row1_col9\" class=\"data row1 col9\" >0.22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
+       "      <td id=\"T_abf7a_row2_col0\" class=\"data row2 col0\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row2_col1\" class=\"data row2 col1\" >0.80</td>\n",
+       "      <td id=\"T_abf7a_row2_col2\" class=\"data row2 col2\" >0.20</td>\n",
+       "      <td id=\"T_abf7a_row2_col3\" class=\"data row2 col3\" >0.02</td>\n",
+       "      <td id=\"T_abf7a_row2_col4\" class=\"data row2 col4\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row2_col5\" class=\"data row2 col5\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row2_col6\" class=\"data row2 col6\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row2_col7\" class=\"data row2 col7\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row2_col8\" class=\"data row2 col8\" >0.25</td>\n",
+       "      <td id=\"T_abf7a_row2_col9\" class=\"data row2 col9\" >1.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
+       "      <td id=\"T_abf7a_row3_col0\" class=\"data row3 col0\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row3_col1\" class=\"data row3 col1\" >0.35</td>\n",
+       "      <td id=\"T_abf7a_row3_col2\" class=\"data row3 col2\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row3_col3\" class=\"data row3 col3\" >0.03</td>\n",
+       "      <td id=\"T_abf7a_row3_col4\" class=\"data row3 col4\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row3_col5\" class=\"data row3 col5\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row3_col6\" class=\"data row3 col6\" >0.06</td>\n",
+       "      <td id=\"T_abf7a_row3_col7\" class=\"data row3 col7\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row3_col8\" class=\"data row3 col8\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row3_col9\" class=\"data row3 col9\" >0.50</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
+       "      <td id=\"T_abf7a_row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
+       "      <td id=\"T_abf7a_row4_col1\" class=\"data row4 col1\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row4_col2\" class=\"data row4 col2\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row4_col3\" class=\"data row4 col3\" >0.02</td>\n",
+       "      <td id=\"T_abf7a_row4_col4\" class=\"data row4 col4\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row4_col5\" class=\"data row4 col5\" >0.00</td>\n",
+       "      <td id=\"T_abf7a_row4_col6\" class=\"data row4 col6\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row4_col7\" class=\"data row4 col7\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row4_col8\" class=\"data row4 col8\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row4_col9\" class=\"data row4 col9\" >0.12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
+       "      <td id=\"T_abf7a_row5_col0\" class=\"data row5 col0\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row5_col1\" class=\"data row5 col1\" >0.50</td>\n",
+       "      <td id=\"T_abf7a_row5_col2\" class=\"data row5 col2\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row5_col3\" class=\"data row5 col3\" >0.03</td>\n",
+       "      <td id=\"T_abf7a_row5_col4\" class=\"data row5 col4\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row5_col5\" class=\"data row5 col5\" >0.00</td>\n",
+       "      <td id=\"T_abf7a_row5_col6\" class=\"data row5 col6\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row5_col7\" class=\"data row5 col7\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row5_col8\" class=\"data row5 col8\" >0.20</td>\n",
+       "      <td id=\"T_abf7a_row5_col9\" class=\"data row5 col9\" >0.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
+       "      <td id=\"T_abf7a_row6_col0\" class=\"data row6 col0\" >0.16</td>\n",
+       "      <td id=\"T_abf7a_row6_col1\" class=\"data row6 col1\" >1.12</td>\n",
+       "      <td id=\"T_abf7a_row6_col2\" class=\"data row6 col2\" >0.54</td>\n",
+       "      <td id=\"T_abf7a_row6_col3\" class=\"data row6 col3\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row6_col4\" class=\"data row6 col4\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row6_col5\" class=\"data row6 col5\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row6_col6\" class=\"data row6 col6\" >0.39</td>\n",
+       "      <td id=\"T_abf7a_row6_col7\" class=\"data row6 col7\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row6_col8\" class=\"data row6 col8\" >0.31</td>\n",
+       "      <td id=\"T_abf7a_row6_col9\" class=\"data row6 col9\" >1.34</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
+       "      <td id=\"T_abf7a_row7_col0\" class=\"data row7 col0\" >6.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col1\" class=\"data row7 col1\" >3.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col2\" class=\"data row7 col2\" >0.60</td>\n",
+       "      <td id=\"T_abf7a_row7_col3\" class=\"data row7 col3\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row7_col4\" class=\"data row7 col4\" >0.40</td>\n",
+       "      <td id=\"T_abf7a_row7_col5\" class=\"data row7 col5\" >0.03</td>\n",
+       "      <td id=\"T_abf7a_row7_col6\" class=\"data row7 col6\" >0.80</td>\n",
+       "      <td id=\"T_abf7a_row7_col7\" class=\"data row7 col7\" >1.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col8\" class=\"data row7 col8\" >2.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col9\" class=\"data row7 col9\" >1.34</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
+       "      <td id=\"T_abf7a_row8_col0\" class=\"data row8 col0\" >0.40</td>\n",
+       "      <td id=\"T_abf7a_row8_col1\" class=\"data row8 col1\" >1.50</td>\n",
+       "      <td id=\"T_abf7a_row8_col2\" class=\"data row8 col2\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row8_col3\" class=\"data row8 col3\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row8_col4\" class=\"data row8 col4\" >1.10</td>\n",
+       "      <td id=\"T_abf7a_row8_col5\" class=\"data row8 col5\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row8_col6\" class=\"data row8 col6\" >0.50</td>\n",
+       "      <td id=\"T_abf7a_row8_col7\" class=\"data row8 col7\" >0.20</td>\n",
+       "      <td id=\"T_abf7a_row8_col8\" class=\"data row8 col8\" >0.40</td>\n",
+       "      <td id=\"T_abf7a_row8_col9\" class=\"data row8 col9\" >2.00</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c13c8700>"
+       "<pandas.io.formats.style.Styler at 0x7c6c098db280>"
       ]
      },
      "execution_count": 18,
@@ -1756,33 +1835,40 @@
    "execution_count": 19,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_208b1 tr:nth-child(even) {\n",
+       "#T_b354f tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_208b1 tr:nth-child(odd) {\n",
+       "#T_b354f tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_208b1 tr {\n",
+       "#T_b354f tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_208b1 th:nth-child(1) {\n",
+       "#T_b354f th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_208b1 caption {\n",
+       "#T_b354f caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1790,55 +1876,55 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_208b1\">\n",
+       "<table id=\"T_b354f\">\n",
        "  <caption>Table 6: The survey results of the objects of interest on October 5, 2023 in pieces per meter</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_208b1_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_208b1_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_208b1_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_208b1_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_208b1_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_208b1_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_208b1_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_208b1_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_208b1_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_208b1_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_b354f_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_b354f_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_b354f_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_b354f_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_b354f_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_b354f_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_b354f_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_b354f_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_b354f_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_b354f_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_208b1_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
-       "      <td id=\"T_208b1_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
-       "      <td id=\"T_208b1_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
-       "      <td id=\"T_208b1_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
-       "      <td id=\"T_208b1_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
-       "      <td id=\"T_208b1_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
-       "      <td id=\"T_208b1_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
-       "      <td id=\"T_208b1_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
-       "      <td id=\"T_208b1_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_208b1_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
-       "      <td id=\"T_208b1_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
-       "      <td id=\"T_208b1_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
-       "      <td id=\"T_208b1_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
-       "      <td id=\"T_208b1_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
-       "      <td id=\"T_208b1_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
-       "      <td id=\"T_208b1_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
-       "      <td id=\"T_208b1_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
-       "      <td id=\"T_208b1_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
+       "      <th id=\"T_b354f_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
+       "      <td id=\"T_b354f_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
+       "      <td id=\"T_b354f_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
+       "      <td id=\"T_b354f_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
+       "      <td id=\"T_b354f_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
+       "      <td id=\"T_b354f_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
+       "      <td id=\"T_b354f_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
+       "      <td id=\"T_b354f_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
+       "      <td id=\"T_b354f_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_b354f_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
+       "      <td id=\"T_b354f_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
+       "      <td id=\"T_b354f_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
+       "      <td id=\"T_b354f_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
+       "      <td id=\"T_b354f_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
+       "      <td id=\"T_b354f_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
+       "      <td id=\"T_b354f_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
+       "      <td id=\"T_b354f_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
+       "      <td id=\"T_b354f_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c16359d0>"
+       "<pandas.io.formats.style.Styler at 0x7c6bfdd33850>"
       ]
      },
      "execution_count": 19,
@@ -1894,21 +1980,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_46124 tr:nth-child(even) {\n",
+       "#T_075e0 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_46124 tr:nth-child(odd) {\n",
+       "#T_075e0 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_46124 tr {\n",
+       "#T_075e0 tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_46124 th:nth-child(1) {\n",
+       "#T_075e0 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_46124 caption {\n",
+       "#T_075e0 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1916,55 +2002,55 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_46124\">\n",
+       "<table id=\"T_075e0\">\n",
        "  <caption>Table 6: The survey results of the objects of interest on October 5, 2023 in pieces per meter</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_46124_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_46124_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_46124_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_46124_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_46124_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_46124_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_46124_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_46124_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_46124_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_46124_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_075e0_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_075e0_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_075e0_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_075e0_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_075e0_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_075e0_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_075e0_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_075e0_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_075e0_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_075e0_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_46124_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
-       "      <td id=\"T_46124_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
-       "      <td id=\"T_46124_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
-       "      <td id=\"T_46124_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
-       "      <td id=\"T_46124_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
-       "      <td id=\"T_46124_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
-       "      <td id=\"T_46124_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
-       "      <td id=\"T_46124_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
-       "      <td id=\"T_46124_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
-       "      <td id=\"T_46124_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
-       "      <td id=\"T_46124_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_46124_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
-       "      <td id=\"T_46124_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
-       "      <td id=\"T_46124_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
-       "      <td id=\"T_46124_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
-       "      <td id=\"T_46124_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
-       "      <td id=\"T_46124_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
-       "      <td id=\"T_46124_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
-       "      <td id=\"T_46124_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
-       "      <td id=\"T_46124_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
-       "      <td id=\"T_46124_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
-       "      <td id=\"T_46124_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
+       "      <th id=\"T_075e0_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
+       "      <td id=\"T_075e0_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
+       "      <td id=\"T_075e0_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
+       "      <td id=\"T_075e0_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
+       "      <td id=\"T_075e0_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
+       "      <td id=\"T_075e0_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
+       "      <td id=\"T_075e0_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
+       "      <td id=\"T_075e0_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
+       "      <td id=\"T_075e0_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_075e0_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
+       "      <td id=\"T_075e0_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
+       "      <td id=\"T_075e0_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
+       "      <td id=\"T_075e0_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
+       "      <td id=\"T_075e0_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
+       "      <td id=\"T_075e0_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
+       "      <td id=\"T_075e0_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
+       "      <td id=\"T_075e0_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
+       "      <td id=\"T_075e0_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c0e1c910>"
+       "<pandas.io.formats.style.Styler at 0x7c6bfd855ac0>"
       ]
      },
      "execution_count": 20,
@@ -2018,7 +2104,7 @@
    "outputs": [
     {
      "data": {
-      "application/papermill.record/image/png": "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",
+      "application/papermill.record/image/png": "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",
       "application/papermill.record/text/plain": "<Figure size 640x480 with 1 Axes>"
      },
      "metadata": {
@@ -2165,20 +2251,6 @@
     "p_diff_predicted[\"source\"] = \"difference² of predicted\""
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "editable": true,
-    "pycharm": {
-     "name": "#%% md\n"
-    },
-    "slideshow": {
-     "slide_type": ""
-    },
-    "tags": []
-   },
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": 24,
@@ -2197,7 +2269,7 @@
    "outputs": [
     {
      "data": {
-      "application/papermill.record/image/png": "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",
+      "application/papermill.record/image/png": "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",
       "application/papermill.record/text/plain": "<Figure size 640x480 with 1 Axes>"
      },
      "metadata": {
@@ -2262,21 +2334,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_a043f tr:nth-child(even) {\n",
+       "#T_565a7 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_a043f tr:nth-child(odd) {\n",
+       "#T_565a7 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_a043f tr {\n",
+       "#T_565a7 tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_a043f th:nth-child(1) {\n",
+       "#T_565a7 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_a043f caption {\n",
+       "#T_565a7 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -2284,75 +2356,75 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_a043f\">\n",
+       "<table id=\"T_565a7\">\n",
        "  <caption>Table 7: The average difference between what was found and the estimates of the participants and what was predicted using the empirical Bayes method</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_a043f_level0_col0\" class=\"col_heading level0 col0\" colspan=\"2\">average</th>\n",
+       "      <th id=\"T_565a7_level0_col0\" class=\"col_heading level0 col0\" colspan=\"2\">average</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th class=\"index_name level1\" >source</th>\n",
-       "      <th id=\"T_a043f_level1_col0\" class=\"col_heading level1 col0\" >difference² of estimated</th>\n",
-       "      <th id=\"T_a043f_level1_col1\" class=\"col_heading level1 col1\" >difference² of predicted</th>\n",
+       "      <th id=\"T_565a7_level1_col0\" class=\"col_heading level1 col0\" >difference² of estimated</th>\n",
+       "      <th id=\"T_565a7_level1_col1\" class=\"col_heading level1 col1\" >difference² of predicted</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
-       "      <td id=\"T_a043f_row0_col0\" class=\"data row0 col0\" >1.07</td>\n",
-       "      <td id=\"T_a043f_row0_col1\" class=\"data row0 col1\" >0.29</td>\n",
+       "      <th id=\"T_565a7_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
+       "      <td id=\"T_565a7_row0_col0\" class=\"data row0 col0\" >1.07</td>\n",
+       "      <td id=\"T_565a7_row0_col1\" class=\"data row0 col1\" >0.29</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
-       "      <td id=\"T_a043f_row1_col0\" class=\"data row1 col0\" >2.32</td>\n",
-       "      <td id=\"T_a043f_row1_col1\" class=\"data row1 col1\" >1.89</td>\n",
+       "      <th id=\"T_565a7_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
+       "      <td id=\"T_565a7_row1_col0\" class=\"data row1 col0\" >2.32</td>\n",
+       "      <td id=\"T_565a7_row1_col1\" class=\"data row1 col1\" >1.87</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
-       "      <td id=\"T_a043f_row2_col0\" class=\"data row2 col0\" >0.31</td>\n",
-       "      <td id=\"T_a043f_row2_col1\" class=\"data row2 col1\" >0.21</td>\n",
+       "      <th id=\"T_565a7_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
+       "      <td id=\"T_565a7_row2_col0\" class=\"data row2 col0\" >0.31</td>\n",
+       "      <td id=\"T_565a7_row2_col1\" class=\"data row2 col1\" >0.20</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
-       "      <td id=\"T_a043f_row3_col0\" class=\"data row3 col0\" >0.11</td>\n",
-       "      <td id=\"T_a043f_row3_col1\" class=\"data row3 col1\" >0.07</td>\n",
+       "      <th id=\"T_565a7_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
+       "      <td id=\"T_565a7_row3_col0\" class=\"data row3 col0\" >0.11</td>\n",
+       "      <td id=\"T_565a7_row3_col1\" class=\"data row3 col1\" >0.07</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
-       "      <td id=\"T_a043f_row4_col0\" class=\"data row4 col0\" >0.26</td>\n",
-       "      <td id=\"T_a043f_row4_col1\" class=\"data row4 col1\" >0.16</td>\n",
+       "      <th id=\"T_565a7_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
+       "      <td id=\"T_565a7_row4_col0\" class=\"data row4 col0\" >0.26</td>\n",
+       "      <td id=\"T_565a7_row4_col1\" class=\"data row4 col1\" >0.16</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
-       "      <td id=\"T_a043f_row5_col0\" class=\"data row5 col0\" >0.03</td>\n",
-       "      <td id=\"T_a043f_row5_col1\" class=\"data row5 col1\" >0.00</td>\n",
+       "      <th id=\"T_565a7_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
+       "      <td id=\"T_565a7_row5_col0\" class=\"data row5 col0\" >0.03</td>\n",
+       "      <td id=\"T_565a7_row5_col1\" class=\"data row5 col1\" >0.01</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row6\" class=\"row_heading level0 row6\" >G95</th>\n",
-       "      <td id=\"T_a043f_row6_col0\" class=\"data row6 col0\" >0.52</td>\n",
-       "      <td id=\"T_a043f_row6_col1\" class=\"data row6 col1\" >0.27</td>\n",
+       "      <th id=\"T_565a7_level0_row6\" class=\"row_heading level0 row6\" >G95</th>\n",
+       "      <td id=\"T_565a7_row6_col0\" class=\"data row6 col0\" >0.52</td>\n",
+       "      <td id=\"T_565a7_row6_col1\" class=\"data row6 col1\" >0.27</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row7\" class=\"row_heading level0 row7\" >G96</th>\n",
-       "      <td id=\"T_a043f_row7_col0\" class=\"data row7 col0\" >0.15</td>\n",
-       "      <td id=\"T_a043f_row7_col1\" class=\"data row7 col1\" >0.05</td>\n",
+       "      <th id=\"T_565a7_level0_row7\" class=\"row_heading level0 row7\" >G96</th>\n",
+       "      <td id=\"T_565a7_row7_col0\" class=\"data row7 col0\" >0.15</td>\n",
+       "      <td id=\"T_565a7_row7_col1\" class=\"data row7 col1\" >0.02</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row8\" class=\"row_heading level0 row8\" >Gcaps</th>\n",
-       "      <td id=\"T_a043f_row8_col0\" class=\"data row8 col0\" >0.26</td>\n",
-       "      <td id=\"T_a043f_row8_col1\" class=\"data row8 col1\" >0.07</td>\n",
+       "      <th id=\"T_565a7_level0_row8\" class=\"row_heading level0 row8\" >Gcaps</th>\n",
+       "      <td id=\"T_565a7_row8_col0\" class=\"data row8 col0\" >0.26</td>\n",
+       "      <td id=\"T_565a7_row8_col1\" class=\"data row8 col1\" >0.10</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row9\" class=\"row_heading level0 row9\" >Gfrags</th>\n",
-       "      <td id=\"T_a043f_row9_col0\" class=\"data row9 col0\" >8.11</td>\n",
-       "      <td id=\"T_a043f_row9_col1\" class=\"data row9 col1\" >7.71</td>\n",
+       "      <th id=\"T_565a7_level0_row9\" class=\"row_heading level0 row9\" >Gfrags</th>\n",
+       "      <td id=\"T_565a7_row9_col0\" class=\"data row9 col0\" >8.11</td>\n",
+       "      <td id=\"T_565a7_row9_col1\" class=\"data row9 col1\" >7.38</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5cced1e20>"
+       "<pandas.io.formats.style.Styler at 0x7c6c0c679be0>"
       ]
      },
      "execution_count": 25,
@@ -2495,21 +2567,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_368fb tr:nth-child(even) {\n",
+       "#T_5cefd tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_368fb tr:nth-child(odd) {\n",
+       "#T_5cefd tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_368fb tr {\n",
+       "#T_5cefd tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_368fb th:nth-child(1) {\n",
+       "#T_5cefd th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_368fb caption {\n",
+       "#T_5cefd caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -2517,142 +2589,142 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_368fb\">\n",
+       "<table id=\"T_5cefd\">\n",
        "  <caption>Table 8: Whether the observed value fell within the predicted interval</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_368fb_level0_col0\" class=\"col_heading level0 col0\" >object</th>\n",
-       "      <th id=\"T_368fb_level0_col1\" class=\"col_heading level0 col1\" >within 96% HDI</th>\n",
-       "      <th id=\"T_368fb_level0_col2\" class=\"col_heading level0 col2\" >within 50% HDI</th>\n",
+       "      <th id=\"T_5cefd_level0_col0\" class=\"col_heading level0 col0\" >object</th>\n",
+       "      <th id=\"T_5cefd_level0_col1\" class=\"col_heading level0 col1\" >within 96% HDI</th>\n",
+       "      <th id=\"T_5cefd_level0_col2\" class=\"col_heading level0 col2\" >within 50% HDI</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
-       "      <td id=\"T_368fb_row0_col0\" class=\"data row0 col0\" >G112</td>\n",
-       "      <td id=\"T_368fb_row0_col1\" class=\"data row0 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row0_col2\" class=\"data row0 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
+       "      <td id=\"T_5cefd_row0_col0\" class=\"data row0 col0\" >G112</td>\n",
+       "      <td id=\"T_5cefd_row0_col1\" class=\"data row0 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row0_col2\" class=\"data row0 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
-       "      <td id=\"T_368fb_row1_col0\" class=\"data row1 col0\" >G27</td>\n",
-       "      <td id=\"T_368fb_row1_col1\" class=\"data row1 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row1_col2\" class=\"data row1 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
+       "      <td id=\"T_5cefd_row1_col0\" class=\"data row1 col0\" >G27</td>\n",
+       "      <td id=\"T_5cefd_row1_col1\" class=\"data row1 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row1_col2\" class=\"data row1 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
-       "      <td id=\"T_368fb_row2_col0\" class=\"data row2 col0\" >G30</td>\n",
-       "      <td id=\"T_368fb_row2_col1\" class=\"data row2 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row2_col2\" class=\"data row2 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
+       "      <td id=\"T_5cefd_row2_col0\" class=\"data row2 col0\" >G30</td>\n",
+       "      <td id=\"T_5cefd_row2_col1\" class=\"data row2 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row2_col2\" class=\"data row2 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
-       "      <td id=\"T_368fb_row3_col0\" class=\"data row3 col0\" >G32</td>\n",
-       "      <td id=\"T_368fb_row3_col1\" class=\"data row3 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row3_col2\" class=\"data row3 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
+       "      <td id=\"T_5cefd_row3_col0\" class=\"data row3 col0\" >G32</td>\n",
+       "      <td id=\"T_5cefd_row3_col1\" class=\"data row3 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row3_col2\" class=\"data row3 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
-       "      <td id=\"T_368fb_row4_col0\" class=\"data row4 col0\" >G67</td>\n",
-       "      <td id=\"T_368fb_row4_col1\" class=\"data row4 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row4_col2\" class=\"data row4 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
+       "      <td id=\"T_5cefd_row4_col0\" class=\"data row4 col0\" >G67</td>\n",
+       "      <td id=\"T_5cefd_row4_col1\" class=\"data row4 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row4_col2\" class=\"data row4 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
-       "      <td id=\"T_368fb_row5_col0\" class=\"data row5 col0\" >G70</td>\n",
-       "      <td id=\"T_368fb_row5_col1\" class=\"data row5 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row5_col2\" class=\"data row5 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
+       "      <td id=\"T_5cefd_row5_col0\" class=\"data row5 col0\" >G70</td>\n",
+       "      <td id=\"T_5cefd_row5_col1\" class=\"data row5 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row5_col2\" class=\"data row5 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
-       "      <td id=\"T_368fb_row6_col0\" class=\"data row6 col0\" >G95</td>\n",
-       "      <td id=\"T_368fb_row6_col1\" class=\"data row6 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row6_col2\" class=\"data row6 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
+       "      <td id=\"T_5cefd_row6_col0\" class=\"data row6 col0\" >G95</td>\n",
+       "      <td id=\"T_5cefd_row6_col1\" class=\"data row6 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row6_col2\" class=\"data row6 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
-       "      <td id=\"T_368fb_row7_col0\" class=\"data row7 col0\" >G96</td>\n",
-       "      <td id=\"T_368fb_row7_col1\" class=\"data row7 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row7_col2\" class=\"data row7 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
+       "      <td id=\"T_5cefd_row7_col0\" class=\"data row7 col0\" >G96</td>\n",
+       "      <td id=\"T_5cefd_row7_col1\" class=\"data row7 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row7_col2\" class=\"data row7 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
-       "      <td id=\"T_368fb_row8_col0\" class=\"data row8 col0\" >Gcaps</td>\n",
-       "      <td id=\"T_368fb_row8_col1\" class=\"data row8 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row8_col2\" class=\"data row8 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
+       "      <td id=\"T_5cefd_row8_col0\" class=\"data row8 col0\" >Gcaps</td>\n",
+       "      <td id=\"T_5cefd_row8_col1\" class=\"data row8 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row8_col2\" class=\"data row8 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
-       "      <td id=\"T_368fb_row9_col0\" class=\"data row9 col0\" >Gfrags</td>\n",
-       "      <td id=\"T_368fb_row9_col1\" class=\"data row9 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row9_col2\" class=\"data row9 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
+       "      <td id=\"T_5cefd_row9_col0\" class=\"data row9 col0\" >Gfrags</td>\n",
+       "      <td id=\"T_5cefd_row9_col1\" class=\"data row9 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row9_col2\" class=\"data row9 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row10\" class=\"row_heading level0 row10\" >0</th>\n",
-       "      <td id=\"T_368fb_row10_col0\" class=\"data row10 col0\" >G112</td>\n",
-       "      <td id=\"T_368fb_row10_col1\" class=\"data row10 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row10_col2\" class=\"data row10 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row10\" class=\"row_heading level0 row10\" >0</th>\n",
+       "      <td id=\"T_5cefd_row10_col0\" class=\"data row10 col0\" >G112</td>\n",
+       "      <td id=\"T_5cefd_row10_col1\" class=\"data row10 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row10_col2\" class=\"data row10 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row11\" class=\"row_heading level0 row11\" >1</th>\n",
-       "      <td id=\"T_368fb_row11_col0\" class=\"data row11 col0\" >G27</td>\n",
-       "      <td id=\"T_368fb_row11_col1\" class=\"data row11 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row11_col2\" class=\"data row11 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row11\" class=\"row_heading level0 row11\" >1</th>\n",
+       "      <td id=\"T_5cefd_row11_col0\" class=\"data row11 col0\" >G27</td>\n",
+       "      <td id=\"T_5cefd_row11_col1\" class=\"data row11 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row11_col2\" class=\"data row11 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row12\" class=\"row_heading level0 row12\" >2</th>\n",
-       "      <td id=\"T_368fb_row12_col0\" class=\"data row12 col0\" >G30</td>\n",
-       "      <td id=\"T_368fb_row12_col1\" class=\"data row12 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row12_col2\" class=\"data row12 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row12\" class=\"row_heading level0 row12\" >2</th>\n",
+       "      <td id=\"T_5cefd_row12_col0\" class=\"data row12 col0\" >G30</td>\n",
+       "      <td id=\"T_5cefd_row12_col1\" class=\"data row12 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row12_col2\" class=\"data row12 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row13\" class=\"row_heading level0 row13\" >3</th>\n",
-       "      <td id=\"T_368fb_row13_col0\" class=\"data row13 col0\" >G32</td>\n",
-       "      <td id=\"T_368fb_row13_col1\" class=\"data row13 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row13_col2\" class=\"data row13 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row13\" class=\"row_heading level0 row13\" >3</th>\n",
+       "      <td id=\"T_5cefd_row13_col0\" class=\"data row13 col0\" >G32</td>\n",
+       "      <td id=\"T_5cefd_row13_col1\" class=\"data row13 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row13_col2\" class=\"data row13 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row14\" class=\"row_heading level0 row14\" >4</th>\n",
-       "      <td id=\"T_368fb_row14_col0\" class=\"data row14 col0\" >G67</td>\n",
-       "      <td id=\"T_368fb_row14_col1\" class=\"data row14 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row14_col2\" class=\"data row14 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row14\" class=\"row_heading level0 row14\" >4</th>\n",
+       "      <td id=\"T_5cefd_row14_col0\" class=\"data row14 col0\" >G67</td>\n",
+       "      <td id=\"T_5cefd_row14_col1\" class=\"data row14 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row14_col2\" class=\"data row14 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row15\" class=\"row_heading level0 row15\" >5</th>\n",
-       "      <td id=\"T_368fb_row15_col0\" class=\"data row15 col0\" >G70</td>\n",
-       "      <td id=\"T_368fb_row15_col1\" class=\"data row15 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row15_col2\" class=\"data row15 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row15\" class=\"row_heading level0 row15\" >5</th>\n",
+       "      <td id=\"T_5cefd_row15_col0\" class=\"data row15 col0\" >G70</td>\n",
+       "      <td id=\"T_5cefd_row15_col1\" class=\"data row15 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row15_col2\" class=\"data row15 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row16\" class=\"row_heading level0 row16\" >6</th>\n",
-       "      <td id=\"T_368fb_row16_col0\" class=\"data row16 col0\" >G95</td>\n",
-       "      <td id=\"T_368fb_row16_col1\" class=\"data row16 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row16_col2\" class=\"data row16 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row16\" class=\"row_heading level0 row16\" >6</th>\n",
+       "      <td id=\"T_5cefd_row16_col0\" class=\"data row16 col0\" >G95</td>\n",
+       "      <td id=\"T_5cefd_row16_col1\" class=\"data row16 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row16_col2\" class=\"data row16 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row17\" class=\"row_heading level0 row17\" >7</th>\n",
-       "      <td id=\"T_368fb_row17_col0\" class=\"data row17 col0\" >G96</td>\n",
-       "      <td id=\"T_368fb_row17_col1\" class=\"data row17 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row17_col2\" class=\"data row17 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row17\" class=\"row_heading level0 row17\" >7</th>\n",
+       "      <td id=\"T_5cefd_row17_col0\" class=\"data row17 col0\" >G96</td>\n",
+       "      <td id=\"T_5cefd_row17_col1\" class=\"data row17 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row17_col2\" class=\"data row17 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row18\" class=\"row_heading level0 row18\" >8</th>\n",
-       "      <td id=\"T_368fb_row18_col0\" class=\"data row18 col0\" >Gcaps</td>\n",
-       "      <td id=\"T_368fb_row18_col1\" class=\"data row18 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row18_col2\" class=\"data row18 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row18\" class=\"row_heading level0 row18\" >8</th>\n",
+       "      <td id=\"T_5cefd_row18_col0\" class=\"data row18 col0\" >Gcaps</td>\n",
+       "      <td id=\"T_5cefd_row18_col1\" class=\"data row18 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row18_col2\" class=\"data row18 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row19\" class=\"row_heading level0 row19\" >9</th>\n",
-       "      <td id=\"T_368fb_row19_col0\" class=\"data row19 col0\" >Gfrags</td>\n",
-       "      <td id=\"T_368fb_row19_col1\" class=\"data row19 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row19_col2\" class=\"data row19 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row19\" class=\"row_heading level0 row19\" >9</th>\n",
+       "      <td id=\"T_5cefd_row19_col0\" class=\"data row19 col0\" >Gfrags</td>\n",
+       "      <td id=\"T_5cefd_row19_col1\" class=\"data row19 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row19_col2\" class=\"data row19 col2\" >False</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c07e21f0>"
+       "<pandas.io.formats.style.Styler at 0x7c6bfcfdc5e0>"
       ]
      },
      "execution_count": 27,
@@ -2685,7 +2757,7 @@
      "data": {
       "text/plain": [
        "within 96% HDI    0.80\n",
-       "within 50% HDI    0.35\n",
+       "within 50% HDI    0.45\n",
        "dtype: float64"
       ]
      },
@@ -2719,7 +2791,7 @@
      "data": {
       "text/plain": [
        "within 96% HDI    16\n",
-       "within 50% HDI     7\n",
+       "within 50% HDI     9\n",
        "dtype: int64"
       ]
      },
@@ -2802,12 +2874,12 @@
      "text": [
       "Git repo: https://github.com/hammerdirt-analyst/solid-waste-team.git\n",
       "\n",
-      "Git branch: review\n",
+      "Git branch: main\n",
       "\n",
       "pandas    : 2.0.3\n",
+      "numpy     : 1.25.2\n",
       "matplotlib: 3.7.1\n",
       "seaborn   : 0.12.2\n",
-      "numpy     : 1.25.2\n",
       "\n"
      ]
     }
diff --git a/docs/_sources/plastic_shotgun_wadding.ipynb b/docs/_sources/plastic_shotgun_wadding.ipynb
index d590d80..d7a79bb 100644
--- a/docs/_sources/plastic_shotgun_wadding.ipynb
+++ b/docs/_sources/plastic_shotgun_wadding.ipynb
@@ -216,8 +216,8 @@
    "outputs": [
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_c1fc0 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_c1fc0 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_c1fc0 tr {\n  font-size: 14px;\n}\n#T_c1fc0 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_c1fc0 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_c1fc0\">\n  <caption>Percent of samples collected with the designated land-use feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_c1fc0_level0_col0\" class=\"col_heading level0 col0\" >orchards</th>\n      <th id=\"T_c1fc0_level0_col1\" class=\"col_heading level0 col1\" >vineyards</th>\n      <th id=\"T_c1fc0_level0_col2\" class=\"col_heading level0 col2\" >buildings</th>\n      <th id=\"T_c1fc0_level0_col3\" class=\"col_heading level0 col3\" >forest</th>\n      <th id=\"T_c1fc0_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_c1fc0_level0_col5\" class=\"col_heading level0 col5\" >public_services</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_c1fc0_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_c1fc0_row0_col0\" class=\"data row0 col0\" >91%</td>\n      <td id=\"T_c1fc0_row0_col1\" class=\"data row0 col1\" >92%</td>\n      <td id=\"T_c1fc0_row0_col2\" class=\"data row0 col2\" >11%</td>\n      <td id=\"T_c1fc0_row0_col3\" class=\"data row0 col3\" >72%</td>\n      <td id=\"T_c1fc0_row0_col4\" class=\"data row0 col4\" >63%</td>\n      <td id=\"T_c1fc0_row0_col5\" class=\"data row0 col5\" >68%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_c1fc0_row1_col0\" class=\"data row1 col0\" >6%</td>\n      <td id=\"T_c1fc0_row1_col1\" class=\"data row1 col1\" >7%</td>\n      <td id=\"T_c1fc0_row1_col2\" class=\"data row1 col2\" >6%</td>\n      <td id=\"T_c1fc0_row1_col3\" class=\"data row1 col3\" >14%</td>\n      <td id=\"T_c1fc0_row1_col4\" class=\"data row1 col4\" >25%</td>\n      <td id=\"T_c1fc0_row1_col5\" class=\"data row1 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_c1fc0_row2_col0\" class=\"data row2 col0\" >0%</td>\n      <td id=\"T_c1fc0_row2_col1\" class=\"data row2 col1\" >0%</td>\n      <td id=\"T_c1fc0_row2_col2\" class=\"data row2 col2\" >1%</td>\n      <td id=\"T_c1fc0_row2_col3\" class=\"data row2 col3\" >0%</td>\n      <td id=\"T_c1fc0_row2_col4\" class=\"data row2 col4\" >1%</td>\n      <td id=\"T_c1fc0_row2_col5\" class=\"data row2 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_c1fc0_row3_col0\" class=\"data row3 col0\" >1%</td>\n      <td id=\"T_c1fc0_row3_col1\" class=\"data row3 col1\" >0%</td>\n      <td id=\"T_c1fc0_row3_col2\" class=\"data row3 col2\" >20%</td>\n      <td id=\"T_c1fc0_row3_col3\" class=\"data row3 col3\" >9%</td>\n      <td id=\"T_c1fc0_row3_col4\" class=\"data row3 col4\" >2%</td>\n      <td id=\"T_c1fc0_row3_col5\" class=\"data row3 col5\" >8%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_c1fc0_row4_col0\" class=\"data row4 col0\" >1%</td>\n      <td id=\"T_c1fc0_row4_col1\" class=\"data row4 col1\" >1%</td>\n      <td id=\"T_c1fc0_row4_col2\" class=\"data row4 col2\" >62%</td>\n      <td id=\"T_c1fc0_row4_col3\" class=\"data row4 col3\" >5%</td>\n      <td id=\"T_c1fc0_row4_col4\" class=\"data row4 col4\" >9%</td>\n      <td id=\"T_c1fc0_row4_col5\" class=\"data row4 col5\" >10%</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7896dc878ca0>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_09e96 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_09e96 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_09e96 tr {\n  font-size: 14px;\n}\n#T_09e96 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_09e96 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_09e96\">\n  <caption>Percent of samples collected with the designated land-use feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_09e96_level0_col0\" class=\"col_heading level0 col0\" >orchards</th>\n      <th id=\"T_09e96_level0_col1\" class=\"col_heading level0 col1\" >vineyards</th>\n      <th id=\"T_09e96_level0_col2\" class=\"col_heading level0 col2\" >buildings</th>\n      <th id=\"T_09e96_level0_col3\" class=\"col_heading level0 col3\" >forest</th>\n      <th id=\"T_09e96_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_09e96_level0_col5\" class=\"col_heading level0 col5\" >public_services</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_09e96_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_09e96_row0_col0\" class=\"data row0 col0\" >91%</td>\n      <td id=\"T_09e96_row0_col1\" class=\"data row0 col1\" >92%</td>\n      <td id=\"T_09e96_row0_col2\" class=\"data row0 col2\" >11%</td>\n      <td id=\"T_09e96_row0_col3\" class=\"data row0 col3\" >72%</td>\n      <td id=\"T_09e96_row0_col4\" class=\"data row0 col4\" >63%</td>\n      <td id=\"T_09e96_row0_col5\" class=\"data row0 col5\" >68%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_09e96_row1_col0\" class=\"data row1 col0\" >6%</td>\n      <td id=\"T_09e96_row1_col1\" class=\"data row1 col1\" >7%</td>\n      <td id=\"T_09e96_row1_col2\" class=\"data row1 col2\" >6%</td>\n      <td id=\"T_09e96_row1_col3\" class=\"data row1 col3\" >14%</td>\n      <td id=\"T_09e96_row1_col4\" class=\"data row1 col4\" >25%</td>\n      <td id=\"T_09e96_row1_col5\" class=\"data row1 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_09e96_row2_col0\" class=\"data row2 col0\" >0%</td>\n      <td id=\"T_09e96_row2_col1\" class=\"data row2 col1\" >0%</td>\n      <td id=\"T_09e96_row2_col2\" class=\"data row2 col2\" >1%</td>\n      <td id=\"T_09e96_row2_col3\" class=\"data row2 col3\" >0%</td>\n      <td id=\"T_09e96_row2_col4\" class=\"data row2 col4\" >1%</td>\n      <td id=\"T_09e96_row2_col5\" class=\"data row2 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_09e96_row3_col0\" class=\"data row3 col0\" >1%</td>\n      <td id=\"T_09e96_row3_col1\" class=\"data row3 col1\" >0%</td>\n      <td id=\"T_09e96_row3_col2\" class=\"data row3 col2\" >20%</td>\n      <td id=\"T_09e96_row3_col3\" class=\"data row3 col3\" >9%</td>\n      <td id=\"T_09e96_row3_col4\" class=\"data row3 col4\" >2%</td>\n      <td id=\"T_09e96_row3_col5\" class=\"data row3 col5\" >8%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_09e96_row4_col0\" class=\"data row4 col0\" >1%</td>\n      <td id=\"T_09e96_row4_col1\" class=\"data row4 col1\" >1%</td>\n      <td id=\"T_09e96_row4_col2\" class=\"data row4 col2\" >62%</td>\n      <td id=\"T_09e96_row4_col3\" class=\"data row4 col3\" >5%</td>\n      <td id=\"T_09e96_row4_col4\" class=\"data row4 col4\" >9%</td>\n      <td id=\"T_09e96_row4_col5\" class=\"data row4 col5\" >10%</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7a2c78fa07f0>"
      },
      "metadata": {
       "scrapbook": {
@@ -289,8 +289,8 @@
    "outputs": [
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_c091a tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_c091a tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_c091a tr {\n  font-size: 14px;\n}\n#T_c091a th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_c091a caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_c091a\">\n  <caption>The average number of shotgun shells per linear meter of shoreline by feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_c091a_level0_col0\" class=\"col_heading level0 col0\" >buildings</th>\n      <th id=\"T_c091a_level0_col1\" class=\"col_heading level0 col1\" >forest</th>\n      <th id=\"T_c091a_level0_col2\" class=\"col_heading level0 col2\" >orchards</th>\n      <th id=\"T_c091a_level0_col3\" class=\"col_heading level0 col3\" >public_services</th>\n      <th id=\"T_c091a_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_c091a_level0_col5\" class=\"col_heading level0 col5\" >vineyards</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_c091a_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_c091a_row0_col0\" class=\"data row0 col0\" >0.03</td>\n      <td id=\"T_c091a_row0_col1\" class=\"data row0 col1\" >0.08</td>\n      <td id=\"T_c091a_row0_col2\" class=\"data row0 col2\" >0.11</td>\n      <td id=\"T_c091a_row0_col3\" class=\"data row0 col3\" >0.13</td>\n      <td id=\"T_c091a_row0_col4\" class=\"data row0 col4\" >0.09</td>\n      <td id=\"T_c091a_row0_col5\" class=\"data row0 col5\" >0.10</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_c091a_row1_col0\" class=\"data row1 col0\" >0.59</td>\n      <td id=\"T_c091a_row1_col1\" class=\"data row1 col1\" >0.06</td>\n      <td id=\"T_c091a_row1_col2\" class=\"data row1 col2\" >0.01</td>\n      <td id=\"T_c091a_row1_col3\" class=\"data row1 col3\" >0.12</td>\n      <td id=\"T_c091a_row1_col4\" class=\"data row1 col4\" >0.18</td>\n      <td id=\"T_c091a_row1_col5\" class=\"data row1 col5\" >0.08</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_c091a_row2_col0\" class=\"data row2 col0\" >0.00</td>\n      <td id=\"T_c091a_row2_col1\" class=\"data row2 col1\" >-</td>\n      <td id=\"T_c091a_row2_col2\" class=\"data row2 col2\" >0.00</td>\n      <td id=\"T_c091a_row2_col3\" class=\"data row2 col3\" >0.01</td>\n      <td id=\"T_c091a_row2_col4\" class=\"data row2 col4\" >0.08</td>\n      <td id=\"T_c091a_row2_col5\" class=\"data row2 col5\" >-</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_c091a_row3_col0\" class=\"data row3 col0\" >0.04</td>\n      <td id=\"T_c091a_row3_col1\" class=\"data row3 col1\" >0.00</td>\n      <td id=\"T_c091a_row3_col2\" class=\"data row3 col2\" >0.01</td>\n      <td id=\"T_c091a_row3_col3\" class=\"data row3 col3\" >0.03</td>\n      <td id=\"T_c091a_row3_col4\" class=\"data row3 col4\" >0.09</td>\n      <td id=\"T_c091a_row3_col5\" class=\"data row3 col5\" >0.00</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_c091a_row4_col0\" class=\"data row4 col0\" >0.09</td>\n      <td id=\"T_c091a_row4_col1\" class=\"data row4 col1\" >0.68</td>\n      <td id=\"T_c091a_row4_col2\" class=\"data row4 col2\" >0.14</td>\n      <td id=\"T_c091a_row4_col3\" class=\"data row4 col3\" >0.03</td>\n      <td id=\"T_c091a_row4_col4\" class=\"data row4 col4\" >0.00</td>\n      <td id=\"T_c091a_row4_col5\" class=\"data row4 col5\" >0.12</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7896dca60c10>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_1cbf2 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_1cbf2 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_1cbf2 tr {\n  font-size: 14px;\n}\n#T_1cbf2 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_1cbf2 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_1cbf2\">\n  <caption>The average number of shotgun shells per linear meter of shoreline by feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_1cbf2_level0_col0\" class=\"col_heading level0 col0\" >buildings</th>\n      <th id=\"T_1cbf2_level0_col1\" class=\"col_heading level0 col1\" >forest</th>\n      <th id=\"T_1cbf2_level0_col2\" class=\"col_heading level0 col2\" >orchards</th>\n      <th id=\"T_1cbf2_level0_col3\" class=\"col_heading level0 col3\" >public_services</th>\n      <th id=\"T_1cbf2_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_1cbf2_level0_col5\" class=\"col_heading level0 col5\" >vineyards</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_1cbf2_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_1cbf2_row0_col0\" class=\"data row0 col0\" >0.03</td>\n      <td id=\"T_1cbf2_row0_col1\" class=\"data row0 col1\" >0.08</td>\n      <td id=\"T_1cbf2_row0_col2\" class=\"data row0 col2\" >0.11</td>\n      <td id=\"T_1cbf2_row0_col3\" class=\"data row0 col3\" >0.13</td>\n      <td id=\"T_1cbf2_row0_col4\" class=\"data row0 col4\" >0.09</td>\n      <td id=\"T_1cbf2_row0_col5\" class=\"data row0 col5\" >0.10</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_1cbf2_row1_col0\" class=\"data row1 col0\" >0.59</td>\n      <td id=\"T_1cbf2_row1_col1\" class=\"data row1 col1\" >0.06</td>\n      <td id=\"T_1cbf2_row1_col2\" class=\"data row1 col2\" >0.01</td>\n      <td id=\"T_1cbf2_row1_col3\" class=\"data row1 col3\" >0.12</td>\n      <td id=\"T_1cbf2_row1_col4\" class=\"data row1 col4\" >0.18</td>\n      <td id=\"T_1cbf2_row1_col5\" class=\"data row1 col5\" >0.08</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_1cbf2_row2_col0\" class=\"data row2 col0\" >0.00</td>\n      <td id=\"T_1cbf2_row2_col1\" class=\"data row2 col1\" >-</td>\n      <td id=\"T_1cbf2_row2_col2\" class=\"data row2 col2\" >0.00</td>\n      <td id=\"T_1cbf2_row2_col3\" class=\"data row2 col3\" >0.01</td>\n      <td id=\"T_1cbf2_row2_col4\" class=\"data row2 col4\" >0.08</td>\n      <td id=\"T_1cbf2_row2_col5\" class=\"data row2 col5\" >-</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_1cbf2_row3_col0\" class=\"data row3 col0\" >0.04</td>\n      <td id=\"T_1cbf2_row3_col1\" class=\"data row3 col1\" >0.00</td>\n      <td id=\"T_1cbf2_row3_col2\" class=\"data row3 col2\" >0.01</td>\n      <td id=\"T_1cbf2_row3_col3\" class=\"data row3 col3\" >0.03</td>\n      <td id=\"T_1cbf2_row3_col4\" class=\"data row3 col4\" >0.09</td>\n      <td id=\"T_1cbf2_row3_col5\" class=\"data row3 col5\" >0.00</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_1cbf2_row4_col0\" class=\"data row4 col0\" >0.09</td>\n      <td id=\"T_1cbf2_row4_col1\" class=\"data row4 col1\" >0.68</td>\n      <td id=\"T_1cbf2_row4_col2\" class=\"data row4 col2\" >0.14</td>\n      <td id=\"T_1cbf2_row4_col3\" class=\"data row4 col3\" >0.03</td>\n      <td id=\"T_1cbf2_row4_col4\" class=\"data row4 col4\" >0.00</td>\n      <td id=\"T_1cbf2_row4_col5\" class=\"data row4 col5\" >0.12</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7a2cc40c9220>"
      },
      "metadata": {
       "scrapbook": {
@@ -462,8 +462,8 @@
    "outputs": [
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_8ea89 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_8ea89 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_8ea89 tr {\n  font-size: 14px;\n}\n#T_8ea89 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_8ea89 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_8ea89\">\n  <caption>The distribution of the total number of plastic shotgun wadding found per sample for each region</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_8ea89_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_8ea89_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_8ea89_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_8ea89_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_8ea89_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_8ea89_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_8ea89_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_8ea89_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_8ea89_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_8ea89_row0_col0\" class=\"data row0 col0\" >58</td>\n      <td id=\"T_8ea89_row0_col1\" class=\"data row0 col1\" >1</td>\n      <td id=\"T_8ea89_row0_col2\" class=\"data row0 col2\" >2</td>\n      <td id=\"T_8ea89_row0_col3\" class=\"data row0 col3\" >0</td>\n      <td id=\"T_8ea89_row0_col4\" class=\"data row0 col4\" >0</td>\n      <td id=\"T_8ea89_row0_col5\" class=\"data row0 col5\" >0</td>\n      <td id=\"T_8ea89_row0_col6\" class=\"data row0 col6\" >1</td>\n      <td id=\"T_8ea89_row0_col7\" class=\"data row0 col7\" >8</td>\n    </tr>\n    <tr>\n      <th id=\"T_8ea89_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_8ea89_row1_col0\" class=\"data row1 col0\" >137</td>\n      <td id=\"T_8ea89_row1_col1\" class=\"data row1 col1\" >6</td>\n      <td id=\"T_8ea89_row1_col2\" class=\"data row1 col2\" >10</td>\n      <td id=\"T_8ea89_row1_col3\" class=\"data row1 col3\" >0</td>\n      <td id=\"T_8ea89_row1_col4\" class=\"data row1 col4\" >0</td>\n      <td id=\"T_8ea89_row1_col5\" class=\"data row1 col5\" >2</td>\n      <td id=\"T_8ea89_row1_col6\" class=\"data row1 col6\" >7</td>\n      <td id=\"T_8ea89_row1_col7\" class=\"data row1 col7\" >51</td>\n    </tr>\n    <tr>\n      <th id=\"T_8ea89_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_8ea89_row2_col0\" class=\"data row2 col0\" >55</td>\n      <td id=\"T_8ea89_row2_col1\" class=\"data row2 col1\" >1</td>\n      <td id=\"T_8ea89_row2_col2\" class=\"data row2 col2\" >4</td>\n      <td id=\"T_8ea89_row2_col3\" class=\"data row2 col3\" >0</td>\n      <td id=\"T_8ea89_row2_col4\" class=\"data row2 col4\" >0</td>\n      <td id=\"T_8ea89_row2_col5\" class=\"data row2 col5\" >0</td>\n      <td id=\"T_8ea89_row2_col6\" class=\"data row2 col6\" >0</td>\n      <td id=\"T_8ea89_row2_col7\" class=\"data row2 col7\" >22</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7896dca95d60>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_59bce tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_59bce tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_59bce tr {\n  font-size: 14px;\n}\n#T_59bce th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_59bce caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_59bce\">\n  <caption>The distribution of the total number of plastic shotgun wadding found per sample for each region</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_59bce_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_59bce_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_59bce_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_59bce_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_59bce_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_59bce_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_59bce_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_59bce_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_59bce_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_59bce_row0_col0\" class=\"data row0 col0\" >58</td>\n      <td id=\"T_59bce_row0_col1\" class=\"data row0 col1\" >1</td>\n      <td id=\"T_59bce_row0_col2\" class=\"data row0 col2\" >2</td>\n      <td id=\"T_59bce_row0_col3\" class=\"data row0 col3\" >0</td>\n      <td id=\"T_59bce_row0_col4\" class=\"data row0 col4\" >0</td>\n      <td id=\"T_59bce_row0_col5\" class=\"data row0 col5\" >0</td>\n      <td id=\"T_59bce_row0_col6\" class=\"data row0 col6\" >1</td>\n      <td id=\"T_59bce_row0_col7\" class=\"data row0 col7\" >8</td>\n    </tr>\n    <tr>\n      <th id=\"T_59bce_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_59bce_row1_col0\" class=\"data row1 col0\" >137</td>\n      <td id=\"T_59bce_row1_col1\" class=\"data row1 col1\" >6</td>\n      <td id=\"T_59bce_row1_col2\" class=\"data row1 col2\" >10</td>\n      <td id=\"T_59bce_row1_col3\" class=\"data row1 col3\" >0</td>\n      <td id=\"T_59bce_row1_col4\" class=\"data row1 col4\" >0</td>\n      <td id=\"T_59bce_row1_col5\" class=\"data row1 col5\" >2</td>\n      <td id=\"T_59bce_row1_col6\" class=\"data row1 col6\" >7</td>\n      <td id=\"T_59bce_row1_col7\" class=\"data row1 col7\" >51</td>\n    </tr>\n    <tr>\n      <th id=\"T_59bce_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_59bce_row2_col0\" class=\"data row2 col0\" >55</td>\n      <td id=\"T_59bce_row2_col1\" class=\"data row2 col1\" >1</td>\n      <td id=\"T_59bce_row2_col2\" class=\"data row2 col2\" >4</td>\n      <td id=\"T_59bce_row2_col3\" class=\"data row2 col3\" >0</td>\n      <td id=\"T_59bce_row2_col4\" class=\"data row2 col4\" >0</td>\n      <td id=\"T_59bce_row2_col5\" class=\"data row2 col5\" >0</td>\n      <td id=\"T_59bce_row2_col6\" class=\"data row2 col6\" >0</td>\n      <td id=\"T_59bce_row2_col7\" class=\"data row2 col7\" >22</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7a2c708dd2e0>"
      },
      "metadata": {
       "scrapbook": {
@@ -475,8 +475,8 @@
     },
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_620b2 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_620b2 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_620b2 tr {\n  font-size: 14px;\n}\n#T_620b2 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_620b2 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_620b2\">\n  <caption>The distribution of the number of shotgun wadding found per meter of shoreline</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_620b2_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_620b2_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_620b2_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_620b2_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_620b2_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_620b2_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_620b2_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_620b2_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_620b2_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_620b2_row0_col0\" class=\"data row0 col0\" >58.00</td>\n      <td id=\"T_620b2_row0_col1\" class=\"data row0 col1\" >0.03</td>\n      <td id=\"T_620b2_row0_col2\" class=\"data row0 col2\" >0.05</td>\n      <td id=\"T_620b2_row0_col3\" class=\"data row0 col3\" >0.00</td>\n      <td id=\"T_620b2_row0_col4\" class=\"data row0 col4\" >0.00</td>\n      <td id=\"T_620b2_row0_col5\" class=\"data row0 col5\" >0.00</td>\n      <td id=\"T_620b2_row0_col6\" class=\"data row0 col6\" >0.03</td>\n      <td id=\"T_620b2_row0_col7\" class=\"data row0 col7\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_620b2_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_620b2_row1_col0\" class=\"data row1 col0\" >137.00</td>\n      <td id=\"T_620b2_row1_col1\" class=\"data row1 col1\" >0.17</td>\n      <td id=\"T_620b2_row1_col2\" class=\"data row1 col2\" >0.31</td>\n      <td id=\"T_620b2_row1_col3\" class=\"data row1 col3\" >0.00</td>\n      <td id=\"T_620b2_row1_col4\" class=\"data row1 col4\" >0.00</td>\n      <td id=\"T_620b2_row1_col5\" class=\"data row1 col5\" >0.05</td>\n      <td id=\"T_620b2_row1_col6\" class=\"data row1 col6\" >0.17</td>\n      <td id=\"T_620b2_row1_col7\" class=\"data row1 col7\" >1.64</td>\n    </tr>\n    <tr>\n      <th id=\"T_620b2_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_620b2_row2_col0\" class=\"data row2 col0\" >55.00</td>\n      <td id=\"T_620b2_row2_col1\" class=\"data row2 col1\" >0.02</td>\n      <td id=\"T_620b2_row2_col2\" class=\"data row2 col2\" >0.05</td>\n      <td id=\"T_620b2_row2_col3\" class=\"data row2 col3\" >0.00</td>\n      <td id=\"T_620b2_row2_col4\" class=\"data row2 col4\" >0.00</td>\n      <td id=\"T_620b2_row2_col5\" class=\"data row2 col5\" >0.00</td>\n      <td id=\"T_620b2_row2_col6\" class=\"data row2 col6\" >0.01</td>\n      <td id=\"T_620b2_row2_col7\" class=\"data row2 col7\" >0.30</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7896afba5880>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_94f7e tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_94f7e tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_94f7e tr {\n  font-size: 14px;\n}\n#T_94f7e th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_94f7e caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_94f7e\">\n  <caption>The distribution of the number of shotgun wadding found per meter of shoreline</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_94f7e_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_94f7e_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_94f7e_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_94f7e_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_94f7e_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_94f7e_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_94f7e_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_94f7e_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_94f7e_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_94f7e_row0_col0\" class=\"data row0 col0\" >58.00</td>\n      <td id=\"T_94f7e_row0_col1\" class=\"data row0 col1\" >0.03</td>\n      <td id=\"T_94f7e_row0_col2\" class=\"data row0 col2\" >0.05</td>\n      <td id=\"T_94f7e_row0_col3\" class=\"data row0 col3\" >0.00</td>\n      <td id=\"T_94f7e_row0_col4\" class=\"data row0 col4\" >0.00</td>\n      <td id=\"T_94f7e_row0_col5\" class=\"data row0 col5\" >0.00</td>\n      <td id=\"T_94f7e_row0_col6\" class=\"data row0 col6\" >0.03</td>\n      <td id=\"T_94f7e_row0_col7\" class=\"data row0 col7\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_94f7e_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_94f7e_row1_col0\" class=\"data row1 col0\" >137.00</td>\n      <td id=\"T_94f7e_row1_col1\" class=\"data row1 col1\" >0.17</td>\n      <td id=\"T_94f7e_row1_col2\" class=\"data row1 col2\" >0.31</td>\n      <td id=\"T_94f7e_row1_col3\" class=\"data row1 col3\" >0.00</td>\n      <td id=\"T_94f7e_row1_col4\" class=\"data row1 col4\" >0.00</td>\n      <td id=\"T_94f7e_row1_col5\" class=\"data row1 col5\" >0.05</td>\n      <td id=\"T_94f7e_row1_col6\" class=\"data row1 col6\" >0.17</td>\n      <td id=\"T_94f7e_row1_col7\" class=\"data row1 col7\" >1.64</td>\n    </tr>\n    <tr>\n      <th id=\"T_94f7e_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_94f7e_row2_col0\" class=\"data row2 col0\" >55.00</td>\n      <td id=\"T_94f7e_row2_col1\" class=\"data row2 col1\" >0.02</td>\n      <td id=\"T_94f7e_row2_col2\" class=\"data row2 col2\" >0.05</td>\n      <td id=\"T_94f7e_row2_col3\" class=\"data row2 col3\" >0.00</td>\n      <td id=\"T_94f7e_row2_col4\" class=\"data row2 col4\" >0.00</td>\n      <td id=\"T_94f7e_row2_col5\" class=\"data row2 col5\" >0.00</td>\n      <td id=\"T_94f7e_row2_col6\" class=\"data row2 col6\" >0.01</td>\n      <td id=\"T_94f7e_row2_col7\" class=\"data row2 col7\" >0.30</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7a2cc40878b0>"
      },
      "metadata": {
       "scrapbook": {
@@ -612,20 +612,20 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_75ad1 tr:nth-child(even) {\n",
+       "#T_92448 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_75ad1 tr:nth-child(odd) {\n",
+       "#T_92448 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_75ad1 tr {\n",
+       "#T_92448 tr {\n",
        "  font-size: 14px;\n",
        "}\n",
-       "#T_75ad1 th:nth-child(1) {\n",
+       "#T_92448 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_75ad1 caption {\n",
+       "#T_92448 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -633,95 +633,95 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_75ad1\">\n",
+       "<table id=\"T_92448\">\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_75ad1_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
-       "      <th id=\"T_75ad1_level0_col1\" class=\"col_heading level0 col1\" >nsamples</th>\n",
+       "      <th id=\"T_92448_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
+       "      <th id=\"T_92448_level0_col1\" class=\"col_heading level0 col1\" >nsamples</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row0\" class=\"row_heading level0 row0\" >Saint-Gingolph</th>\n",
-       "      <td id=\"T_75ad1_row0_col0\" class=\"data row0 col0\" >0.68</td>\n",
-       "      <td id=\"T_75ad1_row0_col1\" class=\"data row0 col1\" >13</td>\n",
+       "      <th id=\"T_92448_level0_row0\" class=\"row_heading level0 row0\" >Saint-Gingolph</th>\n",
+       "      <td id=\"T_92448_row0_col0\" class=\"data row0 col0\" >0.68</td>\n",
+       "      <td id=\"T_92448_row0_col1\" class=\"data row0 col1\" >13</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row1\" class=\"row_heading level0 row1\" >Allaman</th>\n",
-       "      <td id=\"T_75ad1_row1_col0\" class=\"data row1 col0\" >0.14</td>\n",
-       "      <td id=\"T_75ad1_row1_col1\" class=\"data row1 col1\" >3</td>\n",
+       "      <th id=\"T_92448_level0_row1\" class=\"row_heading level0 row1\" >Allaman</th>\n",
+       "      <td id=\"T_92448_row1_col0\" class=\"data row1 col0\" >0.14</td>\n",
+       "      <td id=\"T_92448_row1_col1\" class=\"data row1 col1\" >3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row2\" class=\"row_heading level0 row2\" >Bourg-en-Lavaux</th>\n",
-       "      <td id=\"T_75ad1_row2_col0\" class=\"data row2 col0\" >0.12</td>\n",
-       "      <td id=\"T_75ad1_row2_col1\" class=\"data row2 col1\" >2</td>\n",
+       "      <th id=\"T_92448_level0_row2\" class=\"row_heading level0 row2\" >Bourg-en-Lavaux</th>\n",
+       "      <td id=\"T_92448_row2_col0\" class=\"data row2 col0\" >0.12</td>\n",
+       "      <td id=\"T_92448_row2_col1\" class=\"data row2 col1\" >2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row3\" class=\"row_heading level0 row3\" >La Tour-de-Peilz</th>\n",
-       "      <td id=\"T_75ad1_row3_col0\" class=\"data row3 col0\" >0.12</td>\n",
-       "      <td id=\"T_75ad1_row3_col1\" class=\"data row3 col1\" >25</td>\n",
+       "      <th id=\"T_92448_level0_row3\" class=\"row_heading level0 row3\" >La Tour-de-Peilz</th>\n",
+       "      <td id=\"T_92448_row3_col0\" class=\"data row3 col0\" >0.12</td>\n",
+       "      <td id=\"T_92448_row3_col1\" class=\"data row3 col1\" >25</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row4\" class=\"row_heading level0 row4\" >Montreux</th>\n",
-       "      <td id=\"T_75ad1_row4_col0\" class=\"data row4 col0\" >0.11</td>\n",
-       "      <td id=\"T_75ad1_row4_col1\" class=\"data row4 col1\" >53</td>\n",
+       "      <th id=\"T_92448_level0_row4\" class=\"row_heading level0 row4\" >Montreux</th>\n",
+       "      <td id=\"T_92448_row4_col0\" class=\"data row4 col0\" >0.11</td>\n",
+       "      <td id=\"T_92448_row4_col1\" class=\"data row4 col1\" >53</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row5\" class=\"row_heading level0 row5\" >Vevey</th>\n",
-       "      <td id=\"T_75ad1_row5_col0\" class=\"data row5 col0\" >0.11</td>\n",
-       "      <td id=\"T_75ad1_row5_col1\" class=\"data row5 col1\" >44</td>\n",
+       "      <th id=\"T_92448_level0_row5\" class=\"row_heading level0 row5\" >Vevey</th>\n",
+       "      <td id=\"T_92448_row5_col0\" class=\"data row5 col0\" >0.11</td>\n",
+       "      <td id=\"T_92448_row5_col1\" class=\"data row5 col1\" >44</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row6\" class=\"row_heading level0 row6\" >Saint-Sulpice (VD)</th>\n",
-       "      <td id=\"T_75ad1_row6_col0\" class=\"data row6 col0\" >0.06</td>\n",
-       "      <td id=\"T_75ad1_row6_col1\" class=\"data row6 col1\" >15</td>\n",
+       "      <th id=\"T_92448_level0_row6\" class=\"row_heading level0 row6\" >Saint-Sulpice (VD)</th>\n",
+       "      <td id=\"T_92448_row6_col0\" class=\"data row6 col0\" >0.06</td>\n",
+       "      <td id=\"T_92448_row6_col1\" class=\"data row6 col1\" >15</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row7\" class=\"row_heading level0 row7\" >Versoix</th>\n",
-       "      <td id=\"T_75ad1_row7_col0\" class=\"data row7 col0\" >0.05</td>\n",
-       "      <td id=\"T_75ad1_row7_col1\" class=\"data row7 col1\" >4</td>\n",
+       "      <th id=\"T_92448_level0_row7\" class=\"row_heading level0 row7\" >Versoix</th>\n",
+       "      <td id=\"T_92448_row7_col0\" class=\"data row7 col0\" >0.05</td>\n",
+       "      <td id=\"T_92448_row7_col1\" class=\"data row7 col1\" >4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row8\" class=\"row_heading level0 row8\" >Genève</th>\n",
-       "      <td id=\"T_75ad1_row8_col0\" class=\"data row8 col0\" >0.03</td>\n",
-       "      <td id=\"T_75ad1_row8_col1\" class=\"data row8 col1\" >29</td>\n",
+       "      <th id=\"T_92448_level0_row8\" class=\"row_heading level0 row8\" >Genève</th>\n",
+       "      <td id=\"T_92448_row8_col0\" class=\"data row8 col0\" >0.03</td>\n",
+       "      <td id=\"T_92448_row8_col1\" class=\"data row8 col1\" >29</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row9\" class=\"row_heading level0 row9\" >Préverenges</th>\n",
-       "      <td id=\"T_75ad1_row9_col0\" class=\"data row9 col0\" >0.01</td>\n",
-       "      <td id=\"T_75ad1_row9_col1\" class=\"data row9 col1\" >15</td>\n",
+       "      <th id=\"T_92448_level0_row9\" class=\"row_heading level0 row9\" >Préverenges</th>\n",
+       "      <td id=\"T_92448_row9_col0\" class=\"data row9 col0\" >0.01</td>\n",
+       "      <td id=\"T_92448_row9_col1\" class=\"data row9 col1\" >15</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row10\" class=\"row_heading level0 row10\" >Tolochenaz</th>\n",
-       "      <td id=\"T_75ad1_row10_col0\" class=\"data row10 col0\" >0.01</td>\n",
-       "      <td id=\"T_75ad1_row10_col1\" class=\"data row10 col1\" >3</td>\n",
+       "      <th id=\"T_92448_level0_row10\" class=\"row_heading level0 row10\" >Tolochenaz</th>\n",
+       "      <td id=\"T_92448_row10_col0\" class=\"data row10 col0\" >0.01</td>\n",
+       "      <td id=\"T_92448_row10_col1\" class=\"data row10 col1\" >3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row11\" class=\"row_heading level0 row11\" >Lausanne</th>\n",
-       "      <td id=\"T_75ad1_row11_col0\" class=\"data row11 col0\" >0.01</td>\n",
-       "      <td id=\"T_75ad1_row11_col1\" class=\"data row11 col1\" >20</td>\n",
+       "      <th id=\"T_92448_level0_row11\" class=\"row_heading level0 row11\" >Lausanne</th>\n",
+       "      <td id=\"T_92448_row11_col0\" class=\"data row11 col0\" >0.01</td>\n",
+       "      <td id=\"T_92448_row11_col1\" class=\"data row11 col1\" >20</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row12\" class=\"row_heading level0 row12\" >Gland</th>\n",
-       "      <td id=\"T_75ad1_row12_col0\" class=\"data row12 col0\" >0.00</td>\n",
-       "      <td id=\"T_75ad1_row12_col1\" class=\"data row12 col1\" >22</td>\n",
+       "      <th id=\"T_92448_level0_row12\" class=\"row_heading level0 row12\" >Gland</th>\n",
+       "      <td id=\"T_92448_row12_col0\" class=\"data row12 col0\" >0.00</td>\n",
+       "      <td id=\"T_92448_row12_col1\" class=\"data row12 col1\" >22</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row13\" class=\"row_heading level0 row13\" >Morges</th>\n",
-       "      <td id=\"T_75ad1_row13_col0\" class=\"data row13 col0\" >0.00</td>\n",
-       "      <td id=\"T_75ad1_row13_col1\" class=\"data row13 col1\" >1</td>\n",
+       "      <th id=\"T_92448_level0_row13\" class=\"row_heading level0 row13\" >Morges</th>\n",
+       "      <td id=\"T_92448_row13_col0\" class=\"data row13 col0\" >0.00</td>\n",
+       "      <td id=\"T_92448_row13_col1\" class=\"data row13 col1\" >1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row14\" class=\"row_heading level0 row14\" >Rolle</th>\n",
-       "      <td id=\"T_75ad1_row14_col0\" class=\"data row14 col0\" >0.00</td>\n",
-       "      <td id=\"T_75ad1_row14_col1\" class=\"data row14 col1\" >1</td>\n",
+       "      <th id=\"T_92448_level0_row14\" class=\"row_heading level0 row14\" >Rolle</th>\n",
+       "      <td id=\"T_92448_row14_col0\" class=\"data row14 col0\" >0.00</td>\n",
+       "      <td id=\"T_92448_row14_col1\" class=\"data row14 col1\" >1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x7896afd57f40>"
+       "<pandas.io.formats.style.Styler at 0x7a2c708f6250>"
       ]
      },
      "metadata": {
@@ -743,6 +743,71 @@
     "cp = cpm.style.set_table_styles(table_css_styles).format(precision=2)\n",
     "glue('city_rankings', cp, display=True)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "989efbdc-f400-4894-8424-a5c4856595ca",
+   "metadata": {
+    "editable": true,
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "\n",
+       "\n",
+       "This script updated 21/03/2024 in Biel, CH\n",
+       "\n",
+       "❤️ __what you do everyday:__ *analyst at hammerdirt*\n"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import datetime as dt\n",
+    "from IPython.display import Markdown as md\n",
+    "today = dt.datetime.now().date().strftime(\"%d/%m/%Y\")\n",
+    "where = \"Biel, CH\"\n",
+    "\n",
+    "my_block = f\"\"\"\n",
+    "\n",
+    "This script updated {today} in {where}\n",
+    "\n",
+    "\\u2764\\ufe0f __what you do everyday:__ *analyst at hammerdirt*\n",
+    "\"\"\"\n",
+    "\n",
+    "md(my_block)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11d8473e-9271-4828-b1fc-ecbcf2f28765",
+   "metadata": {
+    "editable": true,
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
diff --git a/docs/grids_2023.html b/docs/grids_2023.html
index b58b44f..8122853 100644
--- a/docs/grids_2023.html
+++ b/docs/grids_2023.html
@@ -476,21 +476,21 @@ <h3><span class="section-number">3.1.3. </span>Reducing dimensionality: find the
 <div class="cell tag_remove-input docutils container">
 <div class="cell_output docutils container">
 <div class="output text_html"><style type="text/css">
-#T_d0aab tr:nth-child(even) {
+#T_556fc tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_d0aab tr:nth-child(odd) {
+#T_556fc tr:nth-child(odd) {
   background: #FFF;
 }
-#T_d0aab tr {
+#T_556fc tr {
   font-size: 14px;
   padding: 12px;
 }
-#T_d0aab th:nth-child(1) {
+#T_556fc th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_d0aab caption {
+#T_556fc caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -498,16 +498,16 @@ <h3><span class="section-number">3.1.3. </span>Reducing dimensionality: find the
   margin-top: 10px;
 }
 </style>
-<table id="T_d0aab">
+<table id="T_556fc">
   <caption>Table 1: The objects of interest. The average pcs/m per sample for each object. The fail rate is the % of all samples that the object appeared in.</caption>
   <thead>
     <tr>
       <th class="blank" >&nbsp;</th>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_d0aab_level0_col0" class="col_heading level0 col0" >pcs/m</th>
-      <th id="T_d0aab_level0_col1" class="col_heading level0 col1" >quantity</th>
-      <th id="T_d0aab_level0_col2" class="col_heading level0 col2" >fail rate</th>
-      <th id="T_d0aab_level0_col3" class="col_heading level0 col3" >% of total</th>
+      <th id="T_556fc_level0_col0" class="col_heading level0 col0" >pcs/m</th>
+      <th id="T_556fc_level0_col1" class="col_heading level0 col1" >quantity</th>
+      <th id="T_556fc_level0_col2" class="col_heading level0 col2" >fail rate</th>
+      <th id="T_556fc_level0_col3" class="col_heading level0 col3" >% of total</th>
     </tr>
     <tr>
       <th class="index_name level0" >code</th>
@@ -520,100 +520,100 @@ <h3><span class="section-number">3.1.3. </span>Reducing dimensionality: find the
   </thead>
   <tbody>
     <tr>
-      <th id="T_d0aab_level0_row0" class="row_heading level0 row0" >G112</th>
-      <th id="T_d0aab_level1_row0" class="row_heading level1 row0" >Industrial pellets (nurdles)</th>
-      <td id="T_d0aab_row0_col0" class="data row0 col0" >0.16</td>
-      <td id="T_d0aab_row0_col1" class="data row0 col1" >2686</td>
-      <td id="T_d0aab_row0_col2" class="data row0 col2" >0.22</td>
-      <td id="T_d0aab_row0_col3" class="data row0 col3" >0.02</td>
+      <th id="T_556fc_level0_row0" class="row_heading level0 row0" >G112</th>
+      <th id="T_556fc_level1_row0" class="row_heading level1 row0" >Industrial pellets (nurdles)</th>
+      <td id="T_556fc_row0_col0" class="data row0 col0" >0.16</td>
+      <td id="T_556fc_row0_col1" class="data row0 col1" >2686</td>
+      <td id="T_556fc_row0_col2" class="data row0 col2" >0.22</td>
+      <td id="T_556fc_row0_col3" class="data row0 col3" >0.02</td>
     </tr>
     <tr>
-      <th id="T_d0aab_level0_row1" class="row_heading level0 row1" >G27</th>
-      <th id="T_d0aab_level1_row1" class="row_heading level1 row1" >Cigarette filters</th>
-      <td id="T_d0aab_row1_col0" class="data row1 col0" >1.12</td>
-      <td id="T_d0aab_row1_col1" class="data row1 col1" >16458</td>
-      <td id="T_d0aab_row1_col2" class="data row1 col2" >0.85</td>
-      <td id="T_d0aab_row1_col3" class="data row1 col3" >0.15</td>
+      <th id="T_556fc_level0_row1" class="row_heading level0 row1" >G27</th>
+      <th id="T_556fc_level1_row1" class="row_heading level1 row1" >Cigarette filters</th>
+      <td id="T_556fc_row1_col0" class="data row1 col0" >1.12</td>
+      <td id="T_556fc_row1_col1" class="data row1 col1" >16458</td>
+      <td id="T_556fc_row1_col2" class="data row1 col2" >0.85</td>
+      <td id="T_556fc_row1_col3" class="data row1 col3" >0.15</td>
     </tr>
     <tr>
-      <th id="T_d0aab_level0_row2" class="row_heading level0 row2" >G30</th>
-      <th id="T_d0aab_level1_row2" class="row_heading level1 row2" >Food wrappers; candy, snacks</th>
-      <td id="T_d0aab_row2_col0" class="data row2 col0" >0.54</td>
-      <td id="T_d0aab_row2_col1" class="data row2 col1" >6767</td>
-      <td id="T_d0aab_row2_col2" class="data row2 col2" >0.86</td>
-      <td id="T_d0aab_row2_col3" class="data row2 col3" >0.06</td>
+      <th id="T_556fc_level0_row2" class="row_heading level0 row2" >G30</th>
+      <th id="T_556fc_level1_row2" class="row_heading level1 row2" >Food wrappers; candy, snacks</th>
+      <td id="T_556fc_row2_col0" class="data row2 col0" >0.54</td>
+      <td id="T_556fc_row2_col1" class="data row2 col1" >6767</td>
+      <td id="T_556fc_row2_col2" class="data row2 col2" >0.86</td>
+      <td id="T_556fc_row2_col3" class="data row2 col3" >0.06</td>
     </tr>
     <tr>
-      <th id="T_d0aab_level0_row3" class="row_heading level0 row3" >G32</th>
-      <th id="T_d0aab_level1_row3" class="row_heading level1 row3" >Toys and party favors</th>
-      <td id="T_d0aab_row3_col0" class="data row3 col0" >0.05</td>
-      <td id="T_d0aab_row3_col1" class="data row3 col1" >606</td>
-      <td id="T_d0aab_row3_col2" class="data row3 col2" >0.48</td>
-      <td id="T_d0aab_row3_col3" class="data row3 col3" >0.01</td>
+      <th id="T_556fc_level0_row3" class="row_heading level0 row3" >G32</th>
+      <th id="T_556fc_level1_row3" class="row_heading level1 row3" >Toys and party favors</th>
+      <td id="T_556fc_row3_col0" class="data row3 col0" >0.05</td>
+      <td id="T_556fc_row3_col1" class="data row3 col1" >606</td>
+      <td id="T_556fc_row3_col2" class="data row3 col2" >0.48</td>
+      <td id="T_556fc_row3_col3" class="data row3 col3" >0.01</td>
     </tr>
     <tr>
-      <th id="T_d0aab_level0_row4" class="row_heading level0 row4" >G67</th>
-      <th id="T_d0aab_level1_row4" class="row_heading level1 row4" >Industrial sheeting</th>
-      <td id="T_d0aab_row4_col0" class="data row4 col0" >0.30</td>
-      <td id="T_d0aab_row4_col1" class="data row4 col1" >3356</td>
-      <td id="T_d0aab_row4_col2" class="data row4 col2" >0.57</td>
-      <td id="T_d0aab_row4_col3" class="data row4 col3" >0.03</td>
+      <th id="T_556fc_level0_row4" class="row_heading level0 row4" >G67</th>
+      <th id="T_556fc_level1_row4" class="row_heading level1 row4" >Industrial sheeting</th>
+      <td id="T_556fc_row4_col0" class="data row4 col0" >0.30</td>
+      <td id="T_556fc_row4_col1" class="data row4 col1" >3356</td>
+      <td id="T_556fc_row4_col2" class="data row4 col2" >0.57</td>
+      <td id="T_556fc_row4_col3" class="data row4 col3" >0.03</td>
     </tr>
     <tr>
-      <th id="T_d0aab_level0_row5" class="row_heading level0 row5" >G70</th>
-      <th id="T_d0aab_level1_row5" class="row_heading level1 row5" >Shotgun cartridges</th>
-      <td id="T_d0aab_row5_col0" class="data row5 col0" >0.08</td>
-      <td id="T_d0aab_row5_col1" class="data row5 col1" >1030</td>
-      <td id="T_d0aab_row5_col2" class="data row5 col2" >0.48</td>
-      <td id="T_d0aab_row5_col3" class="data row5 col3" >0.01</td>
+      <th id="T_556fc_level0_row5" class="row_heading level0 row5" >G70</th>
+      <th id="T_556fc_level1_row5" class="row_heading level1 row5" >Shotgun cartridges</th>
+      <td id="T_556fc_row5_col0" class="data row5 col0" >0.08</td>
+      <td id="T_556fc_row5_col1" class="data row5 col1" >1030</td>
+      <td id="T_556fc_row5_col2" class="data row5 col2" >0.48</td>
+      <td id="T_556fc_row5_col3" class="data row5 col3" >0.01</td>
     </tr>
     <tr>
-      <th id="T_d0aab_level0_row6" class="row_heading level0 row6" >G89</th>
-      <th id="T_d0aab_level1_row6" class="row_heading level1 row6" >Plastic construction waste</th>
-      <td id="T_d0aab_row6_col0" class="data row6 col0" >0.14</td>
-      <td id="T_d0aab_row6_col1" class="data row6 col1" >1970</td>
-      <td id="T_d0aab_row6_col2" class="data row6 col2" >0.51</td>
-      <td id="T_d0aab_row6_col3" class="data row6 col3" >0.02</td>
+      <th id="T_556fc_level0_row6" class="row_heading level0 row6" >G89</th>
+      <th id="T_556fc_level1_row6" class="row_heading level1 row6" >Plastic construction waste</th>
+      <td id="T_556fc_row6_col0" class="data row6 col0" >0.14</td>
+      <td id="T_556fc_row6_col1" class="data row6 col1" >1970</td>
+      <td id="T_556fc_row6_col2" class="data row6 col2" >0.51</td>
+      <td id="T_556fc_row6_col3" class="data row6 col3" >0.02</td>
     </tr>
     <tr>
-      <th id="T_d0aab_level0_row7" class="row_heading level0 row7" >G95</th>
-      <th id="T_d0aab_level1_row7" class="row_heading level1 row7" >Cotton bud/swab sticks</th>
-      <td id="T_d0aab_row7_col0" class="data row7 col0" >0.39</td>
-      <td id="T_d0aab_row7_col1" class="data row7 col1" >4777</td>
-      <td id="T_d0aab_row7_col2" class="data row7 col2" >0.74</td>
-      <td id="T_d0aab_row7_col3" class="data row7 col3" >0.04</td>
+      <th id="T_556fc_level0_row7" class="row_heading level0 row7" >G95</th>
+      <th id="T_556fc_level1_row7" class="row_heading level1 row7" >Cotton bud/swab sticks</th>
+      <td id="T_556fc_row7_col0" class="data row7 col0" >0.39</td>
+      <td id="T_556fc_row7_col1" class="data row7 col1" >4777</td>
+      <td id="T_556fc_row7_col2" class="data row7 col2" >0.74</td>
+      <td id="T_556fc_row7_col3" class="data row7 col3" >0.04</td>
     </tr>
     <tr>
-      <th id="T_d0aab_level0_row8" class="row_heading level0 row8" >G96</th>
-      <th id="T_d0aab_level1_row8" class="row_heading level1 row8" >Sanitary pads /panty liners/tampons and applicators</th>
-      <td id="T_d0aab_row8_col0" class="data row8 col0" >0.04</td>
-      <td id="T_d0aab_row8_col1" class="data row8 col1" >373</td>
-      <td id="T_d0aab_row8_col2" class="data row8 col2" >0.29</td>
-      <td id="T_d0aab_row8_col3" class="data row8 col3" >0.00</td>
+      <th id="T_556fc_level0_row8" class="row_heading level0 row8" >G96</th>
+      <th id="T_556fc_level1_row8" class="row_heading level1 row8" >Sanitary pads /panty liners/tampons and applicators</th>
+      <td id="T_556fc_row8_col0" class="data row8 col0" >0.04</td>
+      <td id="T_556fc_row8_col1" class="data row8 col1" >373</td>
+      <td id="T_556fc_row8_col2" class="data row8 col2" >0.29</td>
+      <td id="T_556fc_row8_col3" class="data row8 col3" >0.00</td>
     </tr>
     <tr>
-      <th id="T_d0aab_level0_row9" class="row_heading level0 row9" >Gcaps</th>
-      <th id="T_d0aab_level1_row9" class="row_heading level1 row9" >Plastic bottle lids</th>
-      <td id="T_d0aab_row9_col0" class="data row9 col0" >0.31</td>
-      <td id="T_d0aab_row9_col1" class="data row9 col1" >3953</td>
-      <td id="T_d0aab_row9_col2" class="data row9 col2" >0.84</td>
-      <td id="T_d0aab_row9_col3" class="data row9 col3" >0.04</td>
+      <th id="T_556fc_level0_row9" class="row_heading level0 row9" >Gcaps</th>
+      <th id="T_556fc_level1_row9" class="row_heading level1 row9" >Plastic bottle lids</th>
+      <td id="T_556fc_row9_col0" class="data row9 col0" >0.31</td>
+      <td id="T_556fc_row9_col1" class="data row9 col1" >3953</td>
+      <td id="T_556fc_row9_col2" class="data row9 col2" >0.84</td>
+      <td id="T_556fc_row9_col3" class="data row9 col3" >0.04</td>
     </tr>
     <tr>
-      <th id="T_d0aab_level0_row10" class="row_heading level0 row10" >Gfoam</th>
-      <th id="T_d0aab_level1_row10" class="row_heading level1 row10" >Expanded polystyrene</th>
-      <td id="T_d0aab_row10_col0" class="data row10 col0" >1.02</td>
-      <td id="T_d0aab_row10_col1" class="data row10 col1" >12871</td>
-      <td id="T_d0aab_row10_col2" class="data row10 col2" >0.81</td>
-      <td id="T_d0aab_row10_col3" class="data row10 col3" >0.12</td>
+      <th id="T_556fc_level0_row10" class="row_heading level0 row10" >Gfoam</th>
+      <th id="T_556fc_level1_row10" class="row_heading level1 row10" >Expanded polystyrene</th>
+      <td id="T_556fc_row10_col0" class="data row10 col0" >1.02</td>
+      <td id="T_556fc_row10_col1" class="data row10 col1" >12871</td>
+      <td id="T_556fc_row10_col2" class="data row10 col2" >0.81</td>
+      <td id="T_556fc_row10_col3" class="data row10 col3" >0.12</td>
     </tr>
     <tr>
-      <th id="T_d0aab_level0_row11" class="row_heading level0 row11" >Gfrags</th>
-      <th id="T_d0aab_level1_row11" class="row_heading level1 row11" >Fragmented plastics</th>
-      <td id="T_d0aab_row11_col0" class="data row11 col0" >1.34</td>
-      <td id="T_d0aab_row11_col1" class="data row11 col1" >17479</td>
-      <td id="T_d0aab_row11_col2" class="data row11 col2" >0.93</td>
-      <td id="T_d0aab_row11_col3" class="data row11 col3" >0.16</td>
+      <th id="T_556fc_level0_row11" class="row_heading level0 row11" >Gfrags</th>
+      <th id="T_556fc_level1_row11" class="row_heading level1 row11" >Fragmented plastics</th>
+      <td id="T_556fc_row11_col0" class="data row11 col0" >1.34</td>
+      <td id="T_556fc_row11_col1" class="data row11 col1" >17479</td>
+      <td id="T_556fc_row11_col2" class="data row11 col2" >0.93</td>
+      <td id="T_556fc_row11_col3" class="data row11 col3" >0.16</td>
     </tr>
   </tbody>
 </table>
@@ -650,96 +650,13 @@ <h3><span class="section-number">3.1.5. </span>Semester project<a class="headerl
 <img alt="_images/lac-leman_city_labels.jpeg" src="_images/lac-leman_city_labels.jpeg" />
 <p class="caption"><span class="caption-number">Fig. 3.1 </span><span class="caption-text">Previous survey results from Lake Geneva</span><a class="headerlink" href="#lac-leman-cities" title="Permalink to this image">#</a></p>
 </div>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">summ_data</span> <span class="o">=</span> <span class="n">cbd</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-
-<span class="n">summ_data</span><span class="p">[</span><span class="s2">&quot;use group&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">summ_data</span><span class="o">.</span><span class="n">code</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">use_groups_i</span><span class="p">[</span><span class="n">x</span><span class="p">])</span>
-
-<span class="n">summ_data</span><span class="p">[</span><span class="s2">&quot;ug&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">summ_data</span><span class="p">[</span><span class="s2">&quot;use group&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">abbrev_use_g</span><span class="p">[</span><span class="n">x</span><span class="p">])</span>
-<span class="n">summ_data</span><span class="p">[</span><span class="n">summ_data</span><span class="p">[</span><span class="s2">&quot;use group&quot;</span><span class="p">]</span> <span class="o">==</span> <span class="s1">&#39;Personal consumption&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">code</span><span class="o">.</span><span class="n">unique</span><span class="p">()</span>
-<span class="n">summ_data</span><span class="p">[</span><span class="s2">&quot;date&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">to_datetime</span><span class="p">(</span><span class="n">summ_data</span><span class="p">[</span><span class="s2">&quot;date&quot;</span><span class="p">],</span> <span class="nb">format</span><span class="o">=</span><span class="s2">&quot;%Y-%m-</span><span class="si">%d</span><span class="s2">&quot;</span><span class="p">)</span>
-
-<span class="n">sd_x</span> <span class="o">=</span> <span class="n">summ_data</span><span class="o">.</span><span class="n">groupby</span><span class="p">([</span><span class="s2">&quot;loc_date&quot;</span><span class="p">,</span> <span class="s2">&quot;date&quot;</span><span class="p">,</span> <span class="s2">&quot;city&quot;</span><span class="p">,</span> <span class="s2">&quot;Project&quot;</span><span class="p">,</span> <span class="s2">&quot;doy&quot;</span><span class="p">],</span> <span class="n">as_index</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span><span class="o">.</span><span class="n">agg</span><span class="p">({</span><span class="s2">&quot;pcs/m&quot;</span><span class="p">:</span> <span class="s1">&#39;sum&#39;</span><span class="p">,</span> <span class="s1">&#39;quantity&#39;</span><span class="p">:</span><span class="s1">&#39;sum&#39;</span><span class="p">})</span>
-<span class="n">sd_x_sp</span> <span class="o">=</span> <span class="n">sd_x</span><span class="p">[</span><span class="n">sd_x</span><span class="o">.</span><span class="n">city</span> <span class="o">==</span> <span class="s1">&#39;Saint-Sulpice (VD)&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">groupby</span><span class="p">([</span><span class="s2">&quot;loc_date&quot;</span><span class="p">,</span> <span class="s2">&quot;date&quot;</span><span class="p">,</span> <span class="s2">&quot;city&quot;</span><span class="p">,</span> <span class="s2">&quot;Project&quot;</span><span class="p">,</span> <span class="s2">&quot;doy&quot;</span><span class="p">],</span> <span class="n">as_index</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span><span class="o">.</span><span class="n">agg</span><span class="p">({</span><span class="s2">&quot;pcs/m&quot;</span><span class="p">:</span> <span class="s1">&#39;sum&#39;</span><span class="p">,</span> <span class="s1">&#39;quantity&#39;</span><span class="p">:</span><span class="s1">&#39;sum&#39;</span><span class="p">})</span>
-
-<span class="n">trg</span> <span class="o">=</span> <span class="n">summ_data</span><span class="p">[</span><span class="n">summ_data</span><span class="o">.</span><span class="n">Project</span> <span class="o">==</span> <span class="s2">&quot;before may 2021&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-<span class="n">tst</span> <span class="o">=</span> <span class="n">summ_data</span><span class="p">[</span><span class="n">summ_data</span><span class="o">.</span><span class="n">Project</span> <span class="o">==</span> <span class="s2">&quot;after may 2021&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-<span class="n">trg_c</span><span class="p">,</span> <span class="n">tst_c</span> <span class="o">=</span> <span class="n">trg</span><span class="o">.</span><span class="n">city</span><span class="o">.</span><span class="n">nunique</span><span class="p">(),</span> <span class="n">tst</span><span class="o">.</span><span class="n">city</span><span class="o">.</span><span class="n">nunique</span><span class="p">()</span>
-<span class="n">trg_lc</span><span class="p">,</span> <span class="n">tst_lc</span> <span class="o">=</span> <span class="n">trg</span><span class="o">.</span><span class="n">slug</span><span class="o">.</span><span class="n">nunique</span><span class="p">(),</span> <span class="n">tst</span><span class="o">.</span><span class="n">slug</span><span class="o">.</span><span class="n">nunique</span><span class="p">()</span>
-<span class="n">trg_q</span><span class="p">,</span> <span class="n">tst_q</span> <span class="o">=</span> <span class="n">trg</span><span class="o">.</span><span class="n">quantity</span><span class="o">.</span><span class="n">sum</span><span class="p">(),</span> <span class="n">tst</span><span class="o">.</span><span class="n">quantity</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
-
-<span class="n">data_magnitude</span> <span class="o">=</span> <span class="p">[</span>
-    <span class="p">{</span><span class="s2">&quot;before may 2021&quot;</span><span class="p">:</span><span class="n">trg_c</span><span class="p">,</span> <span class="s2">&quot;after may 2021&quot;</span><span class="p">:</span><span class="n">tst_c</span><span class="p">},</span>
-    <span class="p">{</span><span class="s2">&quot;before may 2021&quot;</span><span class="p">:</span><span class="n">trg_lc</span><span class="p">,</span> <span class="s2">&quot;after may 2021&quot;</span><span class="p">:</span><span class="n">tst_lc</span><span class="p">},</span>
-    <span class="p">{</span><span class="s2">&quot;before may 2021&quot;</span><span class="p">:</span><span class="n">trg_q</span><span class="p">,</span> <span class="s2">&quot;after may 2021&quot;</span><span class="p">:</span><span class="n">tst_q</span><span class="p">}</span>
-    
-<span class="p">]</span>
-
-<span class="n">cities_set</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">set</span><span class="p">([</span><span class="o">*</span><span class="n">trg</span><span class="o">.</span><span class="n">city</span><span class="o">.</span><span class="n">unique</span><span class="p">(),</span> <span class="o">*</span><span class="n">tst</span><span class="o">.</span><span class="n">city</span><span class="o">.</span><span class="n">unique</span><span class="p">()]))</span>
-<span class="n">n_ind_cities</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">cities_set</span><span class="p">)</span>
-
-<span class="n">caption</span> <span class="o">=</span> <span class="sa">f</span><span class="s1">&#39;The number of different locations and cities for the data. Note that there are </span><span class="si">{</span><span class="n">n_ind_cities</span><span class="si">}</span><span class="s1"> different municipalitites in all.&#39;</span>
-
-<span class="n">data_summ_q</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">data_magnitude</span><span class="p">,</span> <span class="n">index</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;Number of cities&quot;</span><span class="p">,</span> <span class="s2">&quot;Number of locations&quot;</span><span class="p">,</span> <span class="s2">&quot;Total objects&quot;</span><span class="p">])</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s1">&#39;int&#39;</span><span class="p">)</span>
-<span class="n">data_summ_q</span> <span class="o">=</span> <span class="n">data_summ_q</span><span class="o">.</span><span class="n">style</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">formatter</span><span class="o">=</span><span class="s2">&quot;</span><span class="si">{:,}</span><span class="s2">&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">set_table_styles</span><span class="p">(</span><span class="n">table_large_font</span><span class="p">)</span><span class="o">.</span><span class="n">set_caption</span><span class="p">(</span><span class="n">caption</span><span class="p">)</span>
-<span class="n">styled</span> <span class="o">=</span> <span class="n">data_summ_q</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">formatter</span><span class="o">=</span><span class="s2">&quot;</span><span class="si">{:,}</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">subset</span><span class="o">=</span><span class="n">pd</span><span class="o">.</span><span class="n">IndexSlice</span><span class="p">[[</span><span class="s1">&#39;Total objects&#39;</span><span class="p">],</span> <span class="p">:])</span>
-<span class="n">glue</span><span class="p">(</span><span class="s2">&quot;data-summ-q3&quot;</span><span class="p">,</span> <span class="n">styled</span><span class="p">,</span> <span class="n">display</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
-</pre></div>
-</div>
-</div>
-</div>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># all the data by date</span>
-<span class="n">the_99th_percentile</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">quantile</span><span class="p">(</span><span class="n">sd_x</span><span class="p">[</span><span class="s1">&#39;pcs/m&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> <span class="mf">.99</span><span class="p">)</span>
-<span class="n">px</span> <span class="o">=</span> <span class="mi">1</span><span class="o">/</span><span class="n">plt</span><span class="o">.</span><span class="n">rcParams</span><span class="p">[</span><span class="s1">&#39;figure.dpi&#39;</span><span class="p">]</span>  <span class="c1"># pixel in inches</span>
-<span class="n">fig</span><span class="p">,</span> <span class="n">ax</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">600</span><span class="o">*</span><span class="n">px</span><span class="p">,</span><span class="mi">500</span><span class="o">*</span><span class="n">px</span><span class="p">))</span>
-
-<span class="n">sns</span><span class="o">.</span><span class="n">scatterplot</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="n">sd_x</span><span class="p">,</span> <span class="n">x</span><span class="o">=</span><span class="s1">&#39;date&#39;</span><span class="p">,</span> <span class="n">y</span><span class="o">=</span><span class="s1">&#39;pcs/m&#39;</span><span class="p">,</span><span class="n">ax</span><span class="o">=</span><span class="n">ax</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="s2">&quot;dodgerblue&quot;</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">0.6</span><span class="p">,</span><span class="n">label</span><span class="o">=</span><span class="s2">&quot;lac léman&quot;</span><span class="p">)</span>
-<span class="n">sns</span><span class="o">.</span><span class="n">scatterplot</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="n">sd_x_sp</span><span class="p">,</span> <span class="n">x</span><span class="o">=</span><span class="s1">&#39;date&#39;</span><span class="p">,</span> <span class="n">y</span><span class="o">=</span><span class="s1">&#39;pcs/m&#39;</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="s2">&quot;magenta&quot;</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">&quot;solid-waste-team&quot;</span><span class="p">,</span> <span class="n">ax</span><span class="o">=</span><span class="n">ax</span><span class="p">)</span>
-
-<span class="n">ax</span><span class="o">.</span><span class="n">set_ylim</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="n">the_99th_percentile</span><span class="p">)</span>
-<span class="n">ax</span><span class="o">.</span><span class="n">legend</span><span class="p">(</span><span class="n">loc</span><span class="o">=</span><span class="s2">&quot;upper left&quot;</span><span class="p">)</span>
-<span class="n">ax</span><span class="o">.</span><span class="n">set_xlabel</span><span class="p">(</span><span class="s2">&quot;&quot;</span><span class="p">)</span>
-<span class="n">glue</span><span class="p">(</span><span class="s2">&quot;testing_training_chrono_2&quot;</span><span class="p">,</span> <span class="n">fig</span><span class="p">,</span> <span class="n">display</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
-<span class="n">plt</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
-</pre></div>
-</div>
-</div>
-</div>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># all the data day of year</span>
-<span class="n">fig</span><span class="p">,</span> <span class="n">ax</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">600</span><span class="o">*</span><span class="n">px</span><span class="p">,</span> <span class="mi">500</span><span class="o">*</span><span class="n">px</span><span class="p">))</span>
-
-<span class="n">sns</span><span class="o">.</span><span class="n">scatterplot</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="n">sd_x</span><span class="p">,</span> <span class="n">x</span><span class="o">=</span><span class="s1">&#39;doy&#39;</span><span class="p">,</span> <span class="n">y</span><span class="o">=</span><span class="s1">&#39;pcs/m&#39;</span><span class="p">,</span> <span class="n">ax</span><span class="o">=</span><span class="n">ax</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="s2">&quot;dodgerblue&quot;</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">0.6</span><span class="p">,</span><span class="n">label</span><span class="o">=</span><span class="s2">&quot;lac léman&quot;</span><span class="p">)</span>
-<span class="n">sns</span><span class="o">.</span><span class="n">scatterplot</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="n">sd_x_sp</span><span class="p">,</span> <span class="n">x</span><span class="o">=</span><span class="s1">&#39;doy&#39;</span><span class="p">,</span> <span class="n">y</span><span class="o">=</span><span class="s1">&#39;pcs/m&#39;</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="s2">&quot;magenta&quot;</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">&quot;solid-waste-team&quot;</span><span class="p">,</span> <span class="n">ax</span><span class="o">=</span><span class="n">ax</span><span class="p">)</span>
-<span class="n">ax</span><span class="o">.</span><span class="n">set_ylim</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="n">the_99th_percentile</span><span class="p">)</span>
-<span class="n">ax</span><span class="o">.</span><span class="n">set_xlabel</span><span class="p">(</span><span class="s2">&quot;Day of the year&quot;</span><span class="p">)</span>
-<span class="n">glue</span><span class="p">(</span><span class="s1">&#39;testing_training_doy_2&#39;</span><span class="p">,</span> <span class="n">fig</span><span class="p">,</span> <span class="n">display</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
-<span class="n">plt</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
-</pre></div>
-</div>
-</div>
+<div class="cell tag_remove-input docutils container">
 </div>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">testing_vals</span><span class="o">=</span> <span class="n">sd_x</span><span class="p">[</span><span class="n">sd_x</span><span class="o">.</span><span class="n">Project</span> <span class="o">==</span> <span class="s2">&quot;after may 2021&quot;</span><span class="p">][</span><span class="s1">&#39;pcs/m&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">values</span>
-<span class="n">training_vals</span> <span class="o">=</span> <span class="n">sd_x</span><span class="p">[</span><span class="n">sd_x</span><span class="o">.</span><span class="n">Project</span> <span class="o">==</span> <span class="s2">&quot;before may 2021&quot;</span><span class="p">][</span><span class="s1">&#39;pcs/m&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">values</span>
-
-
-<span class="n">train_quantiles</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">quantile</span><span class="p">(</span><span class="n">training_vals</span><span class="p">,</span> <span class="n">some_quants</span><span class="p">)</span>
-<span class="n">test_quantiles</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">quantile</span><span class="p">(</span><span class="n">testing_vals</span><span class="p">,</span> <span class="n">some_quants</span><span class="p">)</span>
-
-<span class="n">training_testing_summary</span> <span class="o">=</span> <span class="n">training_testing_compare</span><span class="p">(</span><span class="n">testing_vals</span><span class="p">,</span> <span class="n">training_vals</span><span class="p">,</span> <span class="n">test_quantiles</span><span class="p">,</span> <span class="n">train_quantiles</span><span class="p">)</span>
-<span class="n">caption</span> <span class="o">=</span> <span class="s2">&quot;The observed values from the training and testing data. Remark that the testing data is only 22</span><span class="si">% o</span><span class="s2">f all the data. This is because we are only in the first year of a six year sampling period&quot;</span>
-<span class="n">sum_table</span> <span class="o">=</span> <span class="n">training_testing_summary</span><span class="o">.</span><span class="n">set_caption</span><span class="p">(</span><span class="n">caption</span><span class="p">)</span>
-<span class="n">sum_table</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">formatter</span><span class="o">=</span><span class="s2">&quot;</span><span class="si">{:.0f}</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">subset</span><span class="o">=</span><span class="n">pd</span><span class="o">.</span><span class="n">IndexSlice</span><span class="p">[[</span><span class="s1">&#39;Number of samples&#39;</span><span class="p">],</span> <span class="p">:])</span>
-<span class="n">glue</span><span class="p">(</span><span class="s2">&quot;data-summary_2&quot;</span><span class="p">,</span> <span class="n">sum_table</span><span class="p">,</span> <span class="n">display</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
-</pre></div>
+<div class="cell tag_remove-input docutils container">
 </div>
+<div class="cell tag_remove-input docutils container">
 </div>
+<div class="cell tag_remove-input docutils container">
 </div>
 <table class="colwidths-auto table">
 <thead>
@@ -750,21 +667,21 @@ <h3><span class="section-number">3.1.5. </span>Semester project<a class="headerl
 <tbody>
 <tr class="row-even"><td class="text-center"><p><img alt="_images/7ab4e526755b1bd0c125af402f84168bdfa710d48fd34fff7e3f01fe1588fb3b.png" src="_images/7ab4e526755b1bd0c125af402f84168bdfa710d48fd34fff7e3f01fe1588fb3b.png" /></p></td>
 <td class="text-center"><p><span class="output text_html"><style type="text/css">
-#T_4afd1 tr:nth-child(even) {
+#T_59f14 tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_4afd1 tr:nth-child(odd) {
+#T_59f14 tr:nth-child(odd) {
   background: #FFF;
 }
-#T_4afd1 tr {
+#T_59f14 tr {
   font-size: 14px;
   padding: 12px;
 }
-#T_4afd1 th:nth-child(1) {
+#T_59f14 th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_4afd1 caption {
+#T_59f14 caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -772,66 +689,66 @@ <h3><span class="section-number">3.1.5. </span>Semester project<a class="headerl
   margin-top: 10px;
 }
 </style>
-<table id="T_4afd1">
+<table id="T_59f14">
   <caption>The observed values from the training and testing data. Remark that the testing data is only 22% of all the data. This is because we are only in the first year of a six year sampling period</caption>
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_4afd1_level0_col0" class="col_heading level0 col0" >before may 2021</th>
-      <th id="T_4afd1_level0_col1" class="col_heading level0 col1" >after may 2021</th>
+      <th id="T_59f14_level0_col0" class="col_heading level0 col0" >before may 2021</th>
+      <th id="T_59f14_level0_col1" class="col_heading level0 col1" >after may 2021</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_4afd1_level0_row0" class="row_heading level0 row0" >weight all samples</th>
-      <td id="T_4afd1_row0_col0" class="data row0 col0" >0.78</td>
-      <td id="T_4afd1_row0_col1" class="data row0 col1" >0.22</td>
+      <th id="T_59f14_level0_row0" class="row_heading level0 row0" >weight all samples</th>
+      <td id="T_59f14_row0_col0" class="data row0 col0" >0.78</td>
+      <td id="T_59f14_row0_col1" class="data row0 col1" >0.22</td>
     </tr>
     <tr>
-      <th id="T_4afd1_level0_row1" class="row_heading level0 row1" >Number of samples</th>
-      <td id="T_4afd1_row1_col0" class="data row1 col0" >263</td>
-      <td id="T_4afd1_row1_col1" class="data row1 col1" >73</td>
+      <th id="T_59f14_level0_row1" class="row_heading level0 row1" >Number of samples</th>
+      <td id="T_59f14_row1_col0" class="data row1 col0" >263</td>
+      <td id="T_59f14_row1_col1" class="data row1 col1" >73</td>
     </tr>
     <tr>
-      <th id="T_4afd1_level0_row2" class="row_heading level0 row2" >Median</th>
-      <td id="T_4afd1_row2_col0" class="data row2 col0" >3.47</td>
-      <td id="T_4afd1_row2_col1" class="data row2 col1" >2.28</td>
+      <th id="T_59f14_level0_row2" class="row_heading level0 row2" >Median</th>
+      <td id="T_59f14_row2_col0" class="data row2 col0" >3.47</td>
+      <td id="T_59f14_row2_col1" class="data row2 col1" >2.28</td>
     </tr>
     <tr>
-      <th id="T_4afd1_level0_row3" class="row_heading level0 row3" >Average</th>
-      <td id="T_4afd1_row3_col0" class="data row3 col0" >6.13</td>
-      <td id="T_4afd1_row3_col1" class="data row3 col1" >3.25</td>
+      <th id="T_59f14_level0_row3" class="row_heading level0 row3" >Average</th>
+      <td id="T_59f14_row3_col0" class="data row3 col0" >6.13</td>
+      <td id="T_59f14_row3_col1" class="data row3 col1" >3.25</td>
     </tr>
     <tr>
-      <th id="T_4afd1_level0_row4" class="row_heading level0 row4" >25th percentile</th>
-      <td id="T_4afd1_row4_col0" class="data row4 col0" >1.52</td>
-      <td id="T_4afd1_row4_col1" class="data row4 col1" >0.78</td>
+      <th id="T_59f14_level0_row4" class="row_heading level0 row4" >25th percentile</th>
+      <td id="T_59f14_row4_col0" class="data row4 col0" >1.52</td>
+      <td id="T_59f14_row4_col1" class="data row4 col1" >0.78</td>
     </tr>
     <tr>
-      <th id="T_4afd1_level0_row5" class="row_heading level0 row5" >75th percentile</th>
-      <td id="T_4afd1_row5_col0" class="data row5 col0" >6.69</td>
-      <td id="T_4afd1_row5_col1" class="data row5 col1" >4.31</td>
+      <th id="T_59f14_level0_row5" class="row_heading level0 row5" >75th percentile</th>
+      <td id="T_59f14_row5_col0" class="data row5 col0" >6.69</td>
+      <td id="T_59f14_row5_col1" class="data row5 col1" >4.31</td>
     </tr>
   </tbody>
 </table>
 </span></p></td>
 </tr>
 <tr class="row-odd"><td class="text-center"><p><span class="output text_html"><style type="text/css">
-#T_91665 tr:nth-child(even) {
+#T_540d8 tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_91665 tr:nth-child(odd) {
+#T_540d8 tr:nth-child(odd) {
   background: #FFF;
 }
-#T_91665 tr {
+#T_540d8 tr {
   font-size: 14px;
   padding: 12px;
 }
-#T_91665 th:nth-child(1) {
+#T_540d8 th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_91665 caption {
+#T_540d8 caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -839,30 +756,30 @@ <h3><span class="section-number">3.1.5. </span>Semester project<a class="headerl
   margin-top: 10px;
 }
 </style>
-<table id="T_91665">
+<table id="T_540d8">
   <caption>The number of different locations and cities for the data. Note that there are 31 different municipalitites in all.</caption>
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_91665_level0_col0" class="col_heading level0 col0" >before may 2021</th>
-      <th id="T_91665_level0_col1" class="col_heading level0 col1" >after may 2021</th>
+      <th id="T_540d8_level0_col0" class="col_heading level0 col0" >before may 2021</th>
+      <th id="T_540d8_level0_col1" class="col_heading level0 col1" >after may 2021</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_91665_level0_row0" class="row_heading level0 row0" >Number of cities</th>
-      <td id="T_91665_row0_col0" class="data row0 col0" >21</td>
-      <td id="T_91665_row0_col1" class="data row0 col1" >19</td>
+      <th id="T_540d8_level0_row0" class="row_heading level0 row0" >Number of cities</th>
+      <td id="T_540d8_row0_col0" class="data row0 col0" >21</td>
+      <td id="T_540d8_row0_col1" class="data row0 col1" >19</td>
     </tr>
     <tr>
-      <th id="T_91665_level0_row1" class="row_heading level0 row1" >Number of locations</th>
-      <td id="T_91665_row1_col0" class="data row1 col0" >48</td>
-      <td id="T_91665_row1_col1" class="data row1 col1" >23</td>
+      <th id="T_540d8_level0_row1" class="row_heading level0 row1" >Number of locations</th>
+      <td id="T_540d8_row1_col0" class="data row1 col0" >48</td>
+      <td id="T_540d8_row1_col1" class="data row1 col1" >23</td>
     </tr>
     <tr>
-      <th id="T_91665_level0_row2" class="row_heading level0 row2" >Total objects</th>
-      <td id="T_91665_row2_col0" class="data row2 col0" >57,623</td>
-      <td id="T_91665_row2_col1" class="data row2 col1" >14,703</td>
+      <th id="T_540d8_level0_row2" class="row_heading level0 row2" >Total objects</th>
+      <td id="T_540d8_row2_col0" class="data row2 col0" >57,623</td>
+      <td id="T_540d8_row2_col1" class="data row2 col1" >14,703</td>
     </tr>
   </tbody>
 </table>
@@ -871,135 +788,11 @@ <h3><span class="section-number">3.1.5. </span>Semester project<a class="headerl
 </tr>
 </tbody>
 </table>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">sampler_from_multinomial</span><span class="p">(</span><span class="n">normed</span><span class="p">,</span> <span class="n">xrange</span><span class="p">,</span> <span class="n">nsamples</span><span class="p">):</span>
-    
-    <span class="n">choose</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">default_rng</span><span class="p">()</span>
-    <span class="n">nunique</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">unique</span><span class="p">(</span><span class="n">normed</span><span class="p">)</span>
-    <span class="n">norm_nunique</span> <span class="o">=</span> <span class="n">nunique</span><span class="o">/</span><span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">nunique</span><span class="p">)</span>
-    <span class="n">found</span> <span class="o">=</span> <span class="n">choose</span><span class="o">.</span><span class="n">multinomial</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">pvals</span><span class="o">=</span><span class="n">norm_nunique</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">nsamples</span><span class="p">)</span>
-    <span class="n">ft</span> <span class="o">=</span> <span class="n">found</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
-    <span class="n">samples</span> <span class="o">=</span> <span class="p">[]</span>
-    <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">asum</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">ft</span><span class="p">):</span>
-        <span class="k">if</span> <span class="n">asum</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
-            <span class="n">samples</span> <span class="o">+=</span> <span class="p">[</span><span class="mi">0</span><span class="p">]</span>
-        <span class="k">else</span><span class="p">:</span>
-            <span class="n">choices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="n">normed</span> <span class="o">==</span> <span class="n">nunique</span><span class="p">[</span><span class="n">i</span><span class="p">])</span>
-            <span class="n">samps</span> <span class="o">=</span> <span class="n">choose</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">choices</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">size</span><span class="o">=</span><span class="n">asum</span><span class="p">)</span>
-            <span class="n">samples</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">xrange</span><span class="p">[</span><span class="n">samps</span><span class="p">])</span>
-
-    <span class="k">return</span> <span class="n">samples</span><span class="p">,</span> <span class="n">nunique</span><span class="p">,</span> <span class="n">norm_nunique</span><span class="p">,</span> <span class="n">ft</span>
-
-<span class="k">def</span> <span class="nf">period_pieces</span><span class="p">(</span><span class="n">start</span><span class="p">,</span> <span class="n">end</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span>
-    <span class="c1"># the results in pieces per meter for one code from a subset of data</span>
-    <span class="n">date_mask</span> <span class="o">=</span> <span class="p">(</span><span class="n">data</span><span class="p">[</span><span class="s2">&quot;date&quot;</span><span class="p">]</span> <span class="o">&gt;=</span> <span class="n">start</span><span class="p">)</span> <span class="o">&amp;</span> <span class="p">(</span><span class="n">data</span><span class="p">[</span><span class="s2">&quot;date&quot;</span><span class="p">]</span> <span class="o">&lt;=</span> <span class="n">end</span><span class="p">)</span>
-    <span class="n">period_one</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="n">date_mask</span><span class="p">]</span>
-    <span class="n">pone_pcs</span> <span class="o">=</span> <span class="n">period_one</span><span class="o">.</span><span class="n">pcs_m</span><span class="o">.</span><span class="n">values</span>
-
-    <span class="k">return</span> <span class="n">pone_pcs</span>
-
-<span class="k">def</span> <span class="nf">period_k_and_n</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">xrange</span><span class="p">,</span> <span class="n">add_one</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
-
-    <span class="n">pone_k</span> <span class="o">=</span> <span class="p">[(</span><span class="n">data</span> <span class="o">&gt;=</span> <span class="n">x</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">xrange</span><span class="p">]</span>
-    <span class="n">pone_notk</span> <span class="o">=</span> <span class="p">[(</span><span class="n">data</span> <span class="o">&lt;</span> <span class="n">x</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">xrange</span><span class="p">]</span>
-
-    <span class="k">if</span> <span class="n">add_one</span><span class="p">:</span>
-        <span class="c1"># if the use is for beta dist. This is the same</span>
-        <span class="c1"># as mulitplying the likelihood * uninform prior (0.5) or beta(1,1)</span>
-        <span class="n">pone_k_n_minus_k</span> <span class="o">=</span> <span class="p">[(</span><span class="n">x</span><span class="o">+</span><span class="mi">1</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> <span class="o">-</span> <span class="n">x</span><span class="o">+</span><span class="mi">1</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">pone_k</span><span class="p">]</span>
-    <span class="k">else</span><span class="p">:</span>
-        <span class="n">pone_k_n_minus_k</span> <span class="o">=</span> <span class="p">[(</span><span class="n">x</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> <span class="o">-</span> <span class="n">x</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">pone_k</span><span class="p">]</span>
-        
-    
-
-    <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">pone_k</span><span class="p">),</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">pone_notk</span><span class="p">),</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">pone_k_n_minus_k</span><span class="p">)</span>
-
-<span class="k">def</span> <span class="nf">period_beta</span><span class="p">(</span><span class="n">k</span><span class="p">):</span>
-    
-         
-    <span class="k">return</span> <span class="n">beta</span><span class="p">(</span><span class="o">*</span><span class="n">k</span><span class="p">)</span>
-        
-
-<span class="k">def</span> <span class="nf">current_possible_prior_locations</span><span class="p">(</span><span class="n">landuse</span><span class="p">,</span> <span class="n">locations</span><span class="p">,</span> <span class="n">attribute</span><span class="p">):</span>    
-
-    <span class="c1"># indentify the magnitude(s) of the attribute of interest from the</span>
-    <span class="c1"># locations in the current data there may be more than one, in this </span>
-    <span class="c1"># example we use all the possible magnitudes for the attribute</span>
-    <span class="c1"># locations = data[data.city == city].location.unique()</span>
-
-    <span class="c1"># magnitudes for the attribute from all the locations in the municipality</span>
-    <span class="n">moa</span> <span class="o">=</span> <span class="n">magnitude_of_attribute</span> <span class="o">=</span> <span class="n">landuse</span><span class="o">.</span><span class="n">loc</span><span class="p">[</span><span class="n">locations</span><span class="p">][</span><span class="n">attribute</span><span class="p">]</span><span class="o">.</span><span class="n">unique</span><span class="p">()</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s1">&#39;int&#39;</span><span class="p">)</span>
-
-    <span class="c1"># identify locations that have the same attribute by magnitude of attribute</span>
-    <span class="n">possible_locations</span> <span class="o">=</span> <span class="n">landuse</span><span class="p">[</span><span class="n">landuse</span><span class="p">[</span><span class="n">attribute</span><span class="p">]</span><span class="o">.</span><span class="n">isin</span><span class="p">(</span><span class="n">moa</span><span class="p">)]</span><span class="o">.</span><span class="n">index</span>
-
-    <span class="c1"># remove the locations that are in the likelihood function</span>
-    <span class="n">prior_locations</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">possible_locations</span> <span class="k">if</span> <span class="n">x</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">locations</span><span class="p">]</span>
-
-    <span class="k">return</span> <span class="n">locations</span><span class="p">,</span> <span class="n">possible_locations</span><span class="p">,</span> <span class="n">prior_locations</span>
-
-
-<span class="k">def</span> <span class="nf">make_expected</span><span class="p">(</span><span class="n">lh_tuple</span><span class="p">,</span> <span class="n">prior_tuple</span><span class="p">,</span> <span class="n">xrange</span><span class="p">):</span>
-    <span class="n">res</span> <span class="o">=</span> <span class="p">[]</span>
-    <span class="n">betas</span><span class="o">=</span><span class="p">[]</span>
-    <span class="c1"># print(lh_tuple, prior_tuple)</span>
-    <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">xrange</span><span class="p">)):</span>
-        <span class="n">alpha</span> <span class="o">=</span> <span class="n">prior_tuple</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
-        <span class="n">betai</span> <span class="o">=</span> <span class="n">prior_tuple</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span>
-        <span class="n">success</span> <span class="o">=</span> <span class="n">lh_tuple</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
-        <span class="n">n</span> <span class="o">=</span> <span class="n">lh_tuple</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span> <span class="o">+</span> <span class="n">lh_tuple</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span> 
-        <span class="n">numerator</span> <span class="o">=</span> <span class="n">alpha</span> <span class="o">+</span> <span class="n">success</span>
-        <span class="n">denominator</span> <span class="o">=</span> <span class="n">alpha</span> <span class="o">+</span> <span class="n">betai</span> <span class="o">+</span> <span class="n">n</span>
-        <span class="k">if</span> <span class="n">numerator</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
-            <span class="n">numerator</span> <span class="o">=</span> <span class="mi">1</span>
-        <span class="n">abeta</span> <span class="o">=</span> <span class="n">beta</span><span class="p">(</span><span class="n">numerator</span><span class="p">,</span> <span class="p">(</span><span class="n">betai</span> <span class="o">+</span> <span class="n">lh_tuple</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span> <span class="o">+</span> <span class="n">lh_tuple</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">0</span><span class="p">]))</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
-        <span class="n">betas</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">abeta</span><span class="p">)</span>
-        <span class="c1"># print(alpha, betai, success, numerator, n, denominator)</span>
-        <span class="k">if</span> <span class="n">numerator</span> <span class="o">&gt;=</span> <span class="n">denominator</span><span class="p">:</span>
-            <span class="n">numerator</span> <span class="o">=</span> <span class="n">denominator</span><span class="o">-</span><span class="mi">1</span>
-            
-        <span class="n">expected</span> <span class="o">=</span> <span class="n">numerator</span><span class="o">/</span><span class="n">denominator</span>
-        <span class="n">res</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">expected</span><span class="p">)</span>
-    <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">res</span><span class="p">),</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">betas</span><span class="p">)</span> 
-</pre></div>
-</div>
-</div>
-</div>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">an_xrange</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">11</span><span class="p">)</span>
-</pre></div>
-</div>
-</div>
-</div>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">comb_lu_agg</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_csv</span><span class="p">(</span><span class="s2">&quot;resources/data/u_comb_lu_cover_street_rivers.csv&quot;</span><span class="p">)</span>
-
-<span class="n">lu_scaled</span> <span class="o">=</span> <span class="n">comb_lu_agg</span><span class="o">.</span><span class="n">pivot</span><span class="p">(</span><span class="n">columns</span><span class="o">=</span><span class="s2">&quot;use&quot;</span><span class="p">,</span> <span class="n">values</span><span class="o">=</span><span class="s2">&quot;scaled&quot;</span><span class="p">,</span> <span class="n">index</span><span class="o">=</span><span class="s2">&quot;slug&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">fillna</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
-
-<span class="n">lu_magnitude</span> <span class="o">=</span> <span class="n">comb_lu_agg</span><span class="o">.</span><span class="n">pivot</span><span class="p">(</span><span class="n">columns</span><span class="o">=</span><span class="s2">&quot;use&quot;</span><span class="p">,</span> <span class="n">values</span><span class="o">=</span><span class="s2">&quot;magnitude&quot;</span><span class="p">,</span> <span class="n">index</span><span class="o">=</span><span class="s2">&quot;slug&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">fillna</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
-
-<span class="n">lu_binned</span> <span class="o">=</span> <span class="n">comb_lu_agg</span><span class="o">.</span><span class="n">pivot</span><span class="p">(</span><span class="n">columns</span><span class="o">=</span><span class="s2">&quot;use&quot;</span><span class="p">,</span> <span class="n">values</span><span class="o">=</span><span class="s2">&quot;binned&quot;</span><span class="p">,</span> <span class="n">index</span><span class="o">=</span><span class="s2">&quot;slug&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">fillna</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
-
-<span class="c1"># not_these = [&#39;amphion&#39;, &#39;anthy&#39;, &#39;excenevex&#39;, &#39;lugrin&#39;, &#39;meillerie&#39;, &#39;saint-disdille&#39;, &#39;tougues&#39;]</span>
-<span class="n">merge_locations</span> <span class="o">=</span> <span class="n">cbd</span><span class="o">.</span><span class="n">slug</span><span class="o">.</span><span class="n">unique</span><span class="p">()</span>
-<span class="n">cbdu</span> <span class="o">=</span> <span class="n">cbd</span><span class="p">[</span><span class="o">~</span><span class="n">cbd</span><span class="o">.</span><span class="n">slug</span><span class="o">.</span><span class="n">isin</span><span class="p">(</span><span class="n">not_these</span><span class="p">)]</span><span class="o">.</span><span class="n">merge</span><span class="p">(</span><span class="n">lu_scaled</span><span class="p">[</span><span class="n">lu_scaled</span><span class="o">.</span><span class="n">index</span><span class="o">.</span><span class="n">isin</span><span class="p">(</span><span class="n">merge_locations</span> <span class="p">)],</span> <span class="n">left_on</span><span class="o">=</span><span class="s2">&quot;slug&quot;</span><span class="p">,</span> <span class="n">right_index</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">validate</span><span class="o">=</span><span class="s2">&quot;many_to_one&quot;</span><span class="p">,</span> <span class="n">how</span><span class="o">=</span><span class="s2">&quot;outer&quot;</span><span class="p">)</span>
-
-<span class="n">cbdu</span><span class="p">[</span><span class="s2">&quot;use group&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">cbdu</span><span class="o">.</span><span class="n">code</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">use_groups_i</span><span class="p">[</span><span class="n">x</span><span class="p">])</span>
-
-<span class="n">cbdu</span><span class="p">[</span><span class="s2">&quot;ug&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">cbdu</span><span class="p">[</span><span class="s2">&quot;use group&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">abbrev_use_g</span><span class="p">[</span><span class="n">x</span><span class="p">])</span>
-<span class="n">cbdu</span><span class="p">[</span><span class="n">cbdu</span><span class="p">[</span><span class="s2">&quot;use group&quot;</span><span class="p">]</span> <span class="o">==</span> <span class="s1">&#39;Personal consumption&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">code</span><span class="o">.</span><span class="n">unique</span><span class="p">()</span>
-<span class="n">cbdu</span><span class="p">[</span><span class="s2">&quot;date&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">to_datetime</span><span class="p">(</span><span class="n">cbdu</span><span class="p">[</span><span class="s2">&quot;date&quot;</span><span class="p">],</span> <span class="nb">format</span><span class="o">=</span><span class="s2">&quot;%Y-%m-</span><span class="si">%d</span><span class="s2">&quot;</span><span class="p">)</span>
-
-<span class="n">attribute_columns</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">lu_scaled</span><span class="o">.</span><span class="n">columns</span> <span class="k">if</span> <span class="n">x</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">&quot;Geroell&quot;</span><span class="p">,</span> <span class="s2">&quot;Stausee&quot;</span><span class="p">,</span> <span class="s2">&quot;See&quot;</span><span class="p">,</span> <span class="s2">&quot;Sumpf&quot;</span><span class="p">,</span> <span class="s2">&quot;Stadtzentr&quot;</span><span class="p">,</span> <span class="s2">&quot;Fels&quot;</span><span class="p">]]</span>
-<span class="n">work_columns</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">cbdu</span><span class="o">.</span><span class="n">columns</span> <span class="k">if</span> <span class="n">x</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">&quot;Geroell&quot;</span><span class="p">,</span> <span class="s2">&quot;Stausee&quot;</span><span class="p">,</span> <span class="s2">&quot;See&quot;</span><span class="p">,</span> <span class="s2">&quot;Sumpf&quot;</span><span class="p">,</span> <span class="s2">&quot;Stadtzentr&quot;</span><span class="p">,</span> <span class="s2">&quot;Fels&quot;</span><span class="p">]]</span>
-<span class="n">cbdu</span> <span class="o">=</span> <span class="n">cbdu</span><span class="p">[</span><span class="n">work_columns</span><span class="p">]</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-<span class="n">cbdu</span><span class="o">.</span><span class="n">rename</span><span class="p">(</span><span class="n">columns</span><span class="o">=</span><span class="p">{</span><span class="s2">&quot;pcs/m&quot;</span><span class="p">:</span><span class="s2">&quot;pcs_m&quot;</span><span class="p">},</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-</pre></div>
+<div class="cell tag_remove-input docutils container">
 </div>
+<div class="cell tag_remove-input docutils container">
 </div>
+<div class="cell tag_remove-input docutils container">
 </div>
 </div>
 <div class="section" id="expected-survey-results-saint-sulpice">
@@ -1011,122 +804,26 @@ <h3><span class="section-number">3.3.1. </span>Predicted values using empirical
 |:------------------------:|:----------------------------:|
 |{glue:}`ssp-outlook-2024` | {glue:}`ssp-2024-meds`|
 |{glue:}`ssp-summary` | {glue:}`ssp-predicted_samples`| -->
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">city</span> <span class="o">=</span>  <span class="s1">&#39;Saint-Sulpice (VD)&#39;</span>
-<span class="n">start</span><span class="p">,</span> <span class="n">end</span> <span class="o">=</span> <span class="s2">&quot;2015-11-15&quot;</span><span class="p">,</span> <span class="s2">&quot;2021-05-31&quot;</span>
-<span class="n">index_range</span> <span class="o">=</span> <span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
-<span class="n">xrange</span> <span class="o">=</span>  <span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="o">*</span><span class="n">index_range</span><span class="p">,</span> <span class="n">step</span><span class="o">=</span><span class="mf">.01</span><span class="p">)</span>
-<span class="n">uninformed_tuple</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([(</span><span class="mi">1</span><span class="p">,</span><span class="mi">1</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">xrange</span><span class="p">])</span>
-
-
-<span class="n">g_resa</span> <span class="o">=</span> <span class="n">cbdu</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-<span class="n">g_resa</span> <span class="o">=</span> <span class="n">g_resa</span><span class="o">.</span><span class="n">groupby</span><span class="p">([</span><span class="s1">&#39;loc_date&#39;</span><span class="p">,</span> <span class="s1">&#39;date&#39;</span><span class="p">,</span><span class="s1">&#39;slug&#39;</span><span class="p">,</span> <span class="s1">&#39;city&#39;</span><span class="p">,</span> <span class="s1">&#39;Project&#39;</span><span class="p">,</span> <span class="s1">&#39;code&#39;</span><span class="p">],</span> <span class="n">as_index</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span><span class="o">.</span><span class="n">agg</span><span class="p">({</span><span class="s1">&#39;pcs_m&#39;</span><span class="p">:</span><span class="s1">&#39;sum&#39;</span><span class="p">,</span> <span class="s1">&#39;quantity&#39;</span><span class="p">:</span><span class="s1">&#39;sum&#39;</span><span class="p">})</span>
-<span class="n">g_resadt</span> <span class="o">=</span> <span class="n">g_resa</span><span class="o">.</span><span class="n">groupby</span><span class="p">([</span><span class="s1">&#39;loc_date&#39;</span><span class="p">,</span> <span class="s1">&#39;date&#39;</span><span class="p">,</span><span class="s1">&#39;slug&#39;</span><span class="p">,</span> <span class="s1">&#39;city&#39;</span><span class="p">,</span> <span class="s1">&#39;Project&#39;</span><span class="p">],</span> <span class="n">as_index</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span><span class="o">.</span><span class="n">agg</span><span class="p">({</span><span class="s1">&#39;pcs_m&#39;</span><span class="p">:</span><span class="s1">&#39;sum&#39;</span><span class="p">,</span> <span class="s1">&#39;quantity&#39;</span><span class="p">:</span><span class="s1">&#39;sum&#39;</span><span class="p">})</span>
-
-<span class="c1"># define the prior, likelihood data and likelihood locations</span>
-<span class="n">posterior_df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">index</span><span class="o">=</span><span class="n">xrange</span><span class="p">)</span>
-<span class="n">predictions</span> <span class="o">=</span> <span class="p">{}</span>
-
-<span class="k">for</span> <span class="n">code</span> <span class="ow">in</span> <span class="n">toi</span><span class="p">:</span>
-    
-    <span class="c1"># code_index = 1</span>
-    <span class="n">city_index</span> <span class="o">=</span> <span class="mi">0</span>
-    <span class="n">attribute_index</span> <span class="o">=</span> <span class="mi">2</span>
-    
-    <span class="n">this_code</span> <span class="o">=</span>  <span class="n">code</span>
-    <span class="n">this_attribute</span> <span class="o">=</span> <span class="n">attribute_columns</span><span class="p">[</span><span class="n">attribute_index</span><span class="p">]</span>
-    <span class="n">this_city</span> <span class="o">=</span> <span class="n">cois</span><span class="p">[</span><span class="n">city_index</span><span class="p">]</span>
-    
-    <span class="n">prior_data</span> <span class="o">=</span> <span class="n">g_resa</span><span class="p">[(</span><span class="n">g_resa</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="n">this_code</span><span class="p">)</span><span class="o">&amp;</span><span class="p">(</span><span class="n">g_resa</span><span class="o">.</span><span class="n">city</span> <span class="o">!=</span> <span class="n">city</span><span class="p">)</span><span class="o">&amp;</span><span class="p">(</span><span class="n">g_resa</span><span class="o">.</span><span class="n">Project</span> <span class="o">==</span><span class="s2">&quot;before may 2021&quot;</span><span class="p">)]</span>
-    <span class="n">lh_data</span> <span class="o">=</span> <span class="n">g_resa</span><span class="p">[(</span><span class="n">g_resa</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="n">this_code</span><span class="p">)</span><span class="o">&amp;</span><span class="p">(</span><span class="n">g_resa</span><span class="o">.</span><span class="n">city</span> <span class="o">==</span> <span class="n">city</span><span class="p">)]</span>
-
-    <span class="c1"># here the locations from Saint Sulpice are indentified</span>
-    <span class="n">lh_locations</span> <span class="o">=</span> <span class="n">lh_data</span><span class="o">.</span><span class="n">slug</span><span class="o">.</span><span class="n">unique</span><span class="p">()</span>
-
-    <span class="c1"># remove any location with no land-use data</span>
-    <span class="n">regions</span> <span class="o">=</span> <span class="n">lac_leman_regions</span><span class="p">[</span><span class="o">~</span><span class="n">lac_leman_regions</span><span class="o">.</span><span class="n">slug</span><span class="o">.</span><span class="n">isin</span><span class="p">(</span><span class="n">not_these</span><span class="p">)]</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-    <span class="c1"># identify the region of interest</span>
-    <span class="n">lh_regions</span> <span class="o">=</span> <span class="n">regions</span><span class="p">[</span><span class="n">regions</span><span class="o">.</span><span class="n">slug</span><span class="o">.</span><span class="n">isin</span><span class="p">(</span><span class="n">lh_locations</span><span class="p">)]</span><span class="o">.</span><span class="n">alabel</span><span class="o">.</span><span class="n">unique</span><span class="p">()</span>
-    <span class="c1"># retireve any other survey locations in the region</span>
-    <span class="n">regional_locations</span> <span class="o">=</span> <span class="n">regions</span><span class="p">[</span><span class="n">regions</span><span class="o">.</span><span class="n">alabel</span><span class="o">.</span><span class="n">isin</span><span class="p">(</span><span class="n">lh_regions</span><span class="p">)]</span><span class="o">.</span><span class="n">slug</span><span class="o">.</span><span class="n">unique</span><span class="p">()</span>
-    <span class="c1"># retrieve the land use values of all locations in the region</span>
-    <span class="n">land_use_data_of_interest</span> <span class="o">=</span> <span class="n">lu_binned</span><span class="o">.</span><span class="n">loc</span><span class="p">[</span><span class="n">regional_locations</span><span class="p">]</span>
-
-    <span class="c1"># the locations from Saint Sulpice as well as regional locations are passed</span>
-    <span class="c1"># to the current_possible_prior_locations method. The land use values are</span>
-    <span class="c1"># compared and the locations with similar land use values are identified.</span>
-    <span class="n">locations</span><span class="p">,</span> <span class="n">possible_locations</span><span class="p">,</span> <span class="n">prior_locations</span> <span class="o">=</span> <span class="n">current_possible_prior_locations</span><span class="p">(</span><span class="n">land_use_data_of_interest</span><span class="p">,</span> <span class="n">lh_locations</span><span class="p">,</span> <span class="n">this_attribute</span><span class="p">)</span>
-    
-    <span class="n">prior_args</span> <span class="o">=</span> <span class="p">{</span>
-        <span class="s1">&#39;prior_data&#39;</span><span class="p">:</span><span class="n">prior_data</span><span class="p">[</span><span class="n">prior_data</span><span class="o">.</span><span class="n">slug</span><span class="o">.</span><span class="n">isin</span><span class="p">(</span><span class="n">prior_locations</span><span class="p">)],</span>
-        <span class="s1">&#39;start&#39;</span><span class="p">:</span> <span class="n">start</span><span class="p">,</span>
-        <span class="s1">&#39;end&#39;</span><span class="p">:</span> <span class="n">end</span><span class="p">,</span>
-        <span class="s1">&#39;xrange&#39;</span><span class="p">:</span><span class="n">xrange</span><span class="p">,</span>
-        <span class="s1">&#39;uninformed_prior&#39;</span><span class="p">:</span> <span class="n">uninformed_tuple</span><span class="p">,</span>
-    <span class="p">}</span>
-    <span class="c1"># grid approximation of the prior</span>
-    <span class="n">grid_prior</span><span class="p">,</span> <span class="n">beta_prior</span><span class="p">,</span> <span class="n">prior_k_n</span><span class="p">,</span> <span class="n">prior_df</span><span class="p">,</span> <span class="n">pcs</span> <span class="o">=</span> <span class="n">prior_distributions</span><span class="p">(</span><span class="o">**</span><span class="n">prior_args</span><span class="p">)</span>
-    
-    <span class="n">posterior_args</span> <span class="o">=</span> <span class="p">{</span>
-        <span class="s1">&#39;lh_data&#39;</span><span class="p">:</span><span class="n">lh_data</span><span class="p">,</span>
-        <span class="s1">&#39;start&#39;</span><span class="p">:</span> <span class="n">start</span><span class="p">,</span>
-        <span class="s1">&#39;end&#39;</span><span class="p">:</span> <span class="s2">&quot;2022-12-31&quot;</span><span class="p">,</span>
-        <span class="s1">&#39;un_informed&#39;</span><span class="p">:</span> <span class="n">uninformed_tuple</span><span class="p">,</span>
-        <span class="s1">&#39;informed_prior&#39;</span><span class="p">:</span> <span class="n">prior_k_n</span>
-    <span class="p">}</span>
-    
-    <span class="c1"># grid approximation of posterior</span>
-    <span class="n">informed</span><span class="p">,</span> <span class="n">uninformed</span><span class="p">,</span> <span class="n">beta_p</span><span class="p">,</span> <span class="n">lh_pcs</span> <span class="o">=</span> <span class="n">posterior_distribution</span><span class="p">(</span><span class="o">**</span><span class="n">posterior_args</span><span class="p">)</span>
-    
-    <span class="c1"># the quantiles from the observed data</span>
-    <span class="n">prior_quants</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">quantile</span><span class="p">(</span><span class="n">pcs</span><span class="p">,</span> <span class="n">some_quants</span><span class="p">)</span>
-    <span class="n">post_quants</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">quantile</span><span class="p">(</span><span class="n">lh_pcs</span><span class="p">,</span> <span class="n">some_quants</span><span class="p">)</span>
-    
-    <span class="c1"># data frame with normalized results</span>
-    <span class="n">post_df</span> <span class="o">=</span> <span class="n">make_results_df</span><span class="p">(</span><span class="n">prior_df</span><span class="o">.</span><span class="n">copy</span><span class="p">(),</span> <span class="n">informed</span><span class="p">,</span> <span class="n">source</span><span class="o">=</span><span class="s2">&quot;Informed post&quot;</span><span class="p">,</span> <span class="n">source_norm</span><span class="o">=</span><span class="s2">&quot;Ip_n&quot;</span><span class="p">)</span>
-    <span class="n">post_df</span> <span class="o">=</span> <span class="n">make_results_df</span><span class="p">(</span><span class="n">post_df</span><span class="p">,</span> <span class="n">uninformed</span><span class="p">,</span> <span class="n">source</span><span class="o">=</span><span class="s2">&quot;Uninformed post&quot;</span><span class="p">,</span> <span class="n">source_norm</span><span class="o">=</span><span class="s2">&quot;Un_n&quot;</span><span class="p">)</span>
-    
-    <span class="c1"># samples from posterior </span>
-    <span class="n">sim_2024</span> <span class="o">=</span> <span class="n">sampler_from_multinomial</span><span class="p">(</span><span class="n">post_df</span><span class="p">[</span><span class="s2">&quot;Ip_n&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> <span class="n">xrange</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">pcs</span><span class="p">)</span> <span class="o">+</span> <span class="nb">len</span><span class="p">(</span><span class="n">lh_pcs</span><span class="p">))</span>
-    <span class="n">sim_quants</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">quantile</span><span class="p">(</span><span class="n">sim_2024</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">some_quants</span><span class="p">)</span>
-    
-    
-    <span class="n">predictions</span><span class="o">.</span><span class="n">update</span><span class="p">({</span><span class="n">this_code</span><span class="p">:</span><span class="n">sim_quants</span><span class="p">})</span>
-    <span class="n">posterior_df</span><span class="p">[</span><span class="n">this_code</span><span class="p">]</span><span class="o">=</span><span class="n">informed</span>
-
-<span class="n">index</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;</span><span class="si">{:.0%}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">some_quants</span><span class="p">]</span>
-<span class="n">pred_quants</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">predictions</span><span class="p">,</span> <span class="n">index</span><span class="o">=</span><span class="n">index</span><span class="p">)</span>
-</pre></div>
-</div>
-</div>
-</div>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">objects</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;G112&quot;</span><span class="p">,</span> <span class="s2">&quot;G27&quot;</span><span class="p">,</span> <span class="s2">&quot;G30&quot;</span><span class="p">,</span> <span class="s2">&quot;G32&quot;</span><span class="p">,</span> <span class="s2">&quot;G67&quot;</span><span class="p">,</span> <span class="s2">&quot;G70&quot;</span><span class="p">,</span> <span class="s2">&quot;G95&quot;</span><span class="p">,</span> <span class="s2">&quot;G96&quot;</span><span class="p">,</span> <span class="s2">&quot;Gcaps&quot;</span><span class="p">,</span> <span class="s2">&quot;Gfrags&quot;</span><span class="p">]</span>
-<span class="n">pred_quants</span> <span class="o">=</span> <span class="n">pred_quants</span><span class="p">[</span><span class="n">objects</span><span class="p">]</span>
-<span class="n">caption</span> <span class="o">=</span> <span class="s2">&quot;Table 4: The 94% probability interval of the objects of interest for Saint Sulpice. The median value is used for the predictions&quot;</span>
-<span class="n">pred_quants</span><span class="o">.</span><span class="n">style</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">precision</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">set_table_styles</span><span class="p">(</span><span class="n">table_large_font</span><span class="p">)</span><span class="o">.</span><span class="n">set_caption</span><span class="p">(</span><span class="n">caption</span><span class="p">)</span>
-</pre></div>
-</div>
+<div class="cell tag_remove-input docutils container">
 </div>
+<div class="cell tag_remove-input docutils container">
 <div class="cell_output docutils container">
 <div class="output text_html"><style type="text/css">
-#T_0e66b tr:nth-child(even) {
+#T_9a101 tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_0e66b tr:nth-child(odd) {
+#T_9a101 tr:nth-child(odd) {
   background: #FFF;
 }
-#T_0e66b tr {
+#T_9a101 tr {
   font-size: 14px;
   padding: 12px;
 }
-#T_0e66b th:nth-child(1) {
+#T_9a101 th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_0e66b caption {
+#T_9a101 caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -1134,114 +831,114 @@ <h3><span class="section-number">3.3.1. </span>Predicted values using empirical
   margin-top: 10px;
 }
 </style>
-<table id="T_0e66b">
+<table id="T_9a101">
   <caption>Table 4: The 94% probability interval of the objects of interest for Saint Sulpice. The median value is used for the predictions</caption>
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_0e66b_level0_col0" class="col_heading level0 col0" >G112</th>
-      <th id="T_0e66b_level0_col1" class="col_heading level0 col1" >G27</th>
-      <th id="T_0e66b_level0_col2" class="col_heading level0 col2" >G30</th>
-      <th id="T_0e66b_level0_col3" class="col_heading level0 col3" >G32</th>
-      <th id="T_0e66b_level0_col4" class="col_heading level0 col4" >G67</th>
-      <th id="T_0e66b_level0_col5" class="col_heading level0 col5" >G70</th>
-      <th id="T_0e66b_level0_col6" class="col_heading level0 col6" >G95</th>
-      <th id="T_0e66b_level0_col7" class="col_heading level0 col7" >G96</th>
-      <th id="T_0e66b_level0_col8" class="col_heading level0 col8" >Gcaps</th>
-      <th id="T_0e66b_level0_col9" class="col_heading level0 col9" >Gfrags</th>
+      <th id="T_9a101_level0_col0" class="col_heading level0 col0" >G112</th>
+      <th id="T_9a101_level0_col1" class="col_heading level0 col1" >G27</th>
+      <th id="T_9a101_level0_col2" class="col_heading level0 col2" >G30</th>
+      <th id="T_9a101_level0_col3" class="col_heading level0 col3" >G32</th>
+      <th id="T_9a101_level0_col4" class="col_heading level0 col4" >G67</th>
+      <th id="T_9a101_level0_col5" class="col_heading level0 col5" >G70</th>
+      <th id="T_9a101_level0_col6" class="col_heading level0 col6" >G95</th>
+      <th id="T_9a101_level0_col7" class="col_heading level0 col7" >G96</th>
+      <th id="T_9a101_level0_col8" class="col_heading level0 col8" >Gcaps</th>
+      <th id="T_9a101_level0_col9" class="col_heading level0 col9" >Gfrags</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_0e66b_level0_row0" class="row_heading level0 row0" >3%</th>
-      <td id="T_0e66b_row0_col0" class="data row0 col0" >0.00</td>
-      <td id="T_0e66b_row0_col1" class="data row0 col1" >0.00</td>
-      <td id="T_0e66b_row0_col2" class="data row0 col2" >0.00</td>
-      <td id="T_0e66b_row0_col3" class="data row0 col3" >0.00</td>
-      <td id="T_0e66b_row0_col4" class="data row0 col4" >0.00</td>
-      <td id="T_0e66b_row0_col5" class="data row0 col5" >0.00</td>
-      <td id="T_0e66b_row0_col6" class="data row0 col6" >0.00</td>
-      <td id="T_0e66b_row0_col7" class="data row0 col7" >0.00</td>
-      <td id="T_0e66b_row0_col8" class="data row0 col8" >0.00</td>
-      <td id="T_0e66b_row0_col9" class="data row0 col9" >0.00</td>
-    </tr>
-    <tr>
-      <th id="T_0e66b_level0_row1" class="row_heading level0 row1" >25%</th>
-      <td id="T_0e66b_row1_col0" class="data row1 col0" >0.00</td>
-      <td id="T_0e66b_row1_col1" class="data row1 col1" >0.00</td>
-      <td id="T_0e66b_row1_col2" class="data row1 col2" >0.00</td>
-      <td id="T_0e66b_row1_col3" class="data row1 col3" >0.01</td>
-      <td id="T_0e66b_row1_col4" class="data row1 col4" >0.01</td>
-      <td id="T_0e66b_row1_col5" class="data row1 col5" >0.00</td>
-      <td id="T_0e66b_row1_col6" class="data row1 col6" >0.00</td>
-      <td id="T_0e66b_row1_col7" class="data row1 col7" >0.01</td>
-      <td id="T_0e66b_row1_col8" class="data row1 col8" >0.03</td>
-      <td id="T_0e66b_row1_col9" class="data row1 col9" >0.00</td>
-    </tr>
-    <tr>
-      <th id="T_0e66b_level0_row2" class="row_heading level0 row2" >48%</th>
-      <td id="T_0e66b_row2_col0" class="data row2 col0" >0.03</td>
-      <td id="T_0e66b_row2_col1" class="data row2 col1" >0.42</td>
-      <td id="T_0e66b_row2_col2" class="data row2 col2" >0.13</td>
-      <td id="T_0e66b_row2_col3" class="data row2 col3" >0.04</td>
-      <td id="T_0e66b_row2_col4" class="data row2 col4" >0.14</td>
-      <td id="T_0e66b_row2_col5" class="data row2 col5" >0.00</td>
-      <td id="T_0e66b_row2_col6" class="data row2 col6" >0.30</td>
-      <td id="T_0e66b_row2_col7" class="data row2 col7" >0.08</td>
-      <td id="T_0e66b_row2_col8" class="data row2 col8" >0.12</td>
-      <td id="T_0e66b_row2_col9" class="data row2 col9" >0.35</td>
-    </tr>
-    <tr>
-      <th id="T_0e66b_level0_row3" class="row_heading level0 row3" >50%</th>
-      <td id="T_0e66b_row3_col0" class="data row3 col0" >0.08</td>
-      <td id="T_0e66b_row3_col1" class="data row3 col1" >0.45</td>
-      <td id="T_0e66b_row3_col2" class="data row3 col2" >0.13</td>
-      <td id="T_0e66b_row3_col3" class="data row3 col3" >0.04</td>
-      <td id="T_0e66b_row3_col4" class="data row3 col4" >0.16</td>
-      <td id="T_0e66b_row3_col5" class="data row3 col5" >0.00</td>
-      <td id="T_0e66b_row3_col6" class="data row3 col6" >0.32</td>
-      <td id="T_0e66b_row3_col7" class="data row3 col7" >0.09</td>
-      <td id="T_0e66b_row3_col8" class="data row3 col8" >0.14</td>
-      <td id="T_0e66b_row3_col9" class="data row3 col9" >0.41</td>
-    </tr>
-    <tr>
-      <th id="T_0e66b_level0_row4" class="row_heading level0 row4" >52%</th>
-      <td id="T_0e66b_row4_col0" class="data row4 col0" >0.10</td>
-      <td id="T_0e66b_row4_col1" class="data row4 col1" >0.46</td>
-      <td id="T_0e66b_row4_col2" class="data row4 col2" >0.13</td>
-      <td id="T_0e66b_row4_col3" class="data row4 col3" >0.04</td>
-      <td id="T_0e66b_row4_col4" class="data row4 col4" >0.17</td>
-      <td id="T_0e66b_row4_col5" class="data row4 col5" >0.00</td>
-      <td id="T_0e66b_row4_col6" class="data row4 col6" >0.34</td>
-      <td id="T_0e66b_row4_col7" class="data row4 col7" >0.09</td>
-      <td id="T_0e66b_row4_col8" class="data row4 col8" >0.14</td>
-      <td id="T_0e66b_row4_col9" class="data row4 col9" >0.50</td>
-    </tr>
-    <tr>
-      <th id="T_0e66b_level0_row5" class="row_heading level0 row5" >75%</th>
-      <td id="T_0e66b_row5_col0" class="data row5 col0" >0.54</td>
-      <td id="T_0e66b_row5_col1" class="data row5 col1" >0.66</td>
-      <td id="T_0e66b_row5_col2" class="data row5 col2" >0.48</td>
-      <td id="T_0e66b_row5_col3" class="data row5 col3" >0.06</td>
-      <td id="T_0e66b_row5_col4" class="data row5 col4" >0.31</td>
-      <td id="T_0e66b_row5_col5" class="data row5 col5" >0.04</td>
-      <td id="T_0e66b_row5_col6" class="data row5 col6" >0.52</td>
-      <td id="T_0e66b_row5_col7" class="data row5 col7" >0.12</td>
-      <td id="T_0e66b_row5_col8" class="data row5 col8" >0.23</td>
-      <td id="T_0e66b_row5_col9" class="data row5 col9" >0.82</td>
-    </tr>
-    <tr>
-      <th id="T_0e66b_level0_row6" class="row_heading level0 row6" >97%</th>
-      <td id="T_0e66b_row6_col0" class="data row6 col0" >1.39</td>
-      <td id="T_0e66b_row6_col1" class="data row6 col1" >1.29</td>
-      <td id="T_0e66b_row6_col2" class="data row6 col2" >0.91</td>
-      <td id="T_0e66b_row6_col3" class="data row6 col3" >0.11</td>
-      <td id="T_0e66b_row6_col4" class="data row6 col4" >2.83</td>
-      <td id="T_0e66b_row6_col5" class="data row6 col5" >0.09</td>
-      <td id="T_0e66b_row6_col6" class="data row6 col6" >1.00</td>
-      <td id="T_0e66b_row6_col7" class="data row6 col7" >0.22</td>
-      <td id="T_0e66b_row6_col8" class="data row6 col8" >0.41</td>
-      <td id="T_0e66b_row6_col9" class="data row6 col9" >2.75</td>
+      <th id="T_9a101_level0_row0" class="row_heading level0 row0" >3%</th>
+      <td id="T_9a101_row0_col0" class="data row0 col0" >0.00</td>
+      <td id="T_9a101_row0_col1" class="data row0 col1" >0.00</td>
+      <td id="T_9a101_row0_col2" class="data row0 col2" >0.00</td>
+      <td id="T_9a101_row0_col3" class="data row0 col3" >0.00</td>
+      <td id="T_9a101_row0_col4" class="data row0 col4" >0.00</td>
+      <td id="T_9a101_row0_col5" class="data row0 col5" >0.00</td>
+      <td id="T_9a101_row0_col6" class="data row0 col6" >0.00</td>
+      <td id="T_9a101_row0_col7" class="data row0 col7" >0.00</td>
+      <td id="T_9a101_row0_col8" class="data row0 col8" >0.00</td>
+      <td id="T_9a101_row0_col9" class="data row0 col9" >0.00</td>
+    </tr>
+    <tr>
+      <th id="T_9a101_level0_row1" class="row_heading level0 row1" >25%</th>
+      <td id="T_9a101_row1_col0" class="data row1 col0" >0.00</td>
+      <td id="T_9a101_row1_col1" class="data row1 col1" >0.05</td>
+      <td id="T_9a101_row1_col2" class="data row1 col2" >0.03</td>
+      <td id="T_9a101_row1_col3" class="data row1 col3" >0.00</td>
+      <td id="T_9a101_row1_col4" class="data row1 col4" >0.05</td>
+      <td id="T_9a101_row1_col5" class="data row1 col5" >0.00</td>
+      <td id="T_9a101_row1_col6" class="data row1 col6" >0.01</td>
+      <td id="T_9a101_row1_col7" class="data row1 col7" >0.00</td>
+      <td id="T_9a101_row1_col8" class="data row1 col8" >0.04</td>
+      <td id="T_9a101_row1_col9" class="data row1 col9" >0.00</td>
+    </tr>
+    <tr>
+      <th id="T_9a101_level0_row2" class="row_heading level0 row2" >48%</th>
+      <td id="T_9a101_row2_col0" class="data row2 col0" >0.08</td>
+      <td id="T_9a101_row2_col1" class="data row2 col1" >0.46</td>
+      <td id="T_9a101_row2_col2" class="data row2 col2" >0.35</td>
+      <td id="T_9a101_row2_col3" class="data row2 col3" >0.03</td>
+      <td id="T_9a101_row2_col4" class="data row2 col4" >0.16</td>
+      <td id="T_9a101_row2_col5" class="data row2 col5" >0.00</td>
+      <td id="T_9a101_row2_col6" class="data row2 col6" >0.32</td>
+      <td id="T_9a101_row2_col7" class="data row2 col7" >0.04</td>
+      <td id="T_9a101_row2_col8" class="data row2 col8" >0.11</td>
+      <td id="T_9a101_row2_col9" class="data row2 col9" >0.68</td>
+    </tr>
+    <tr>
+      <th id="T_9a101_level0_row3" class="row_heading level0 row3" >50%</th>
+      <td id="T_9a101_row3_col0" class="data row3 col0" >0.12</td>
+      <td id="T_9a101_row3_col1" class="data row3 col1" >0.47</td>
+      <td id="T_9a101_row3_col2" class="data row3 col2" >0.39</td>
+      <td id="T_9a101_row3_col3" class="data row3 col3" >0.04</td>
+      <td id="T_9a101_row3_col4" class="data row3 col4" >0.16</td>
+      <td id="T_9a101_row3_col5" class="data row3 col5" >0.01</td>
+      <td id="T_9a101_row3_col6" class="data row3 col6" >0.32</td>
+      <td id="T_9a101_row3_col7" class="data row3 col7" >0.04</td>
+      <td id="T_9a101_row3_col8" class="data row3 col8" >0.11</td>
+      <td id="T_9a101_row3_col9" class="data row3 col9" >0.74</td>
+    </tr>
+    <tr>
+      <th id="T_9a101_level0_row4" class="row_heading level0 row4" >52%</th>
+      <td id="T_9a101_row4_col0" class="data row4 col0" >0.22</td>
+      <td id="T_9a101_row4_col1" class="data row4 col1" >0.48</td>
+      <td id="T_9a101_row4_col2" class="data row4 col2" >0.43</td>
+      <td id="T_9a101_row4_col3" class="data row4 col3" >0.04</td>
+      <td id="T_9a101_row4_col4" class="data row4 col4" >0.22</td>
+      <td id="T_9a101_row4_col5" class="data row4 col5" >0.02</td>
+      <td id="T_9a101_row4_col6" class="data row4 col6" >0.34</td>
+      <td id="T_9a101_row4_col7" class="data row4 col7" >0.05</td>
+      <td id="T_9a101_row4_col8" class="data row4 col8" >0.12</td>
+      <td id="T_9a101_row4_col9" class="data row4 col9" >0.74</td>
+    </tr>
+    <tr>
+      <th id="T_9a101_level0_row5" class="row_heading level0 row5" >75%</th>
+      <td id="T_9a101_row5_col0" class="data row5 col0" >0.68</td>
+      <td id="T_9a101_row5_col1" class="data row5 col1" >0.93</td>
+      <td id="T_9a101_row5_col2" class="data row5 col2" >0.57</td>
+      <td id="T_9a101_row5_col3" class="data row5 col3" >0.08</td>
+      <td id="T_9a101_row5_col4" class="data row5 col4" >0.33</td>
+      <td id="T_9a101_row5_col5" class="data row5 col5" >0.05</td>
+      <td id="T_9a101_row5_col6" class="data row5 col6" >0.52</td>
+      <td id="T_9a101_row5_col7" class="data row5 col7" >0.08</td>
+      <td id="T_9a101_row5_col8" class="data row5 col8" >0.23</td>
+      <td id="T_9a101_row5_col9" class="data row5 col9" >1.24</td>
+    </tr>
+    <tr>
+      <th id="T_9a101_level0_row6" class="row_heading level0 row6" >97%</th>
+      <td id="T_9a101_row6_col0" class="data row6 col0" >1.46</td>
+      <td id="T_9a101_row6_col1" class="data row6 col1" >1.47</td>
+      <td id="T_9a101_row6_col2" class="data row6 col2" >1.21</td>
+      <td id="T_9a101_row6_col3" class="data row6 col3" >0.11</td>
+      <td id="T_9a101_row6_col4" class="data row6 col4" >0.64</td>
+      <td id="T_9a101_row6_col5" class="data row6 col5" >5.58</td>
+      <td id="T_9a101_row6_col6" class="data row6 col6" >1.11</td>
+      <td id="T_9a101_row6_col7" class="data row6 col7" >0.20</td>
+      <td id="T_9a101_row6_col8" class="data row6 col8" >0.50</td>
+      <td id="T_9a101_row6_col9" class="data row6 col9" >5.05</td>
     </tr>
   </tbody>
 </table>
@@ -1252,87 +949,28 @@ <h3><span class="section-number">3.3.1. </span>Predicted values using empirical
 <div class="section" id="estimates-from-participants">
 <h3><span class="section-number">3.3.2. </span>Estimates from participants<a class="headerlink" href="#estimates-from-participants" title="Permalink to this heading">#</a></h3>
 <p>After a classroom discusion and review of the previous years results (but not the predicted results) the participants made an estimate of how many they expect to find of each item of interest.</p>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">length_p</span> <span class="o">=</span> <span class="mf">49.3</span>
-
-<span class="n">estimated_p</span> <span class="o">=</span><span class="p">[</span>
-    <span class="p">[</span><span class="mf">.16</span><span class="p">,</span> <span class="mf">1.12</span><span class="p">,</span> <span class="mf">.54</span><span class="p">,</span> <span class="mf">.05</span><span class="p">,</span> <span class="mf">.30</span><span class="p">,</span> <span class="mf">.08</span><span class="p">,</span> <span class="mf">.39</span><span class="p">,</span> <span class="mf">.04</span><span class="p">,</span> <span class="mf">.31</span><span class="p">,</span> <span class="mf">1.34</span><span class="p">],</span>
-    <span class="p">[</span><span class="mi">6</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mf">.6</span><span class="p">,</span> <span class="mf">.1</span><span class="p">,</span> <span class="mf">.4</span><span class="p">,</span> <span class="mf">.03</span><span class="p">,</span> <span class="mf">.8</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mf">1.34</span><span class="p">],</span>
-    <span class="p">[</span><span class="mf">.4</span><span class="p">,</span> <span class="mf">1.5</span><span class="p">,</span> <span class="mf">.3</span><span class="p">,</span> <span class="mf">.1</span><span class="p">,</span> <span class="mf">1.1</span><span class="p">,</span> <span class="mf">.01</span><span class="p">,</span> <span class="mf">.5</span><span class="p">,</span> <span class="mf">.2</span><span class="p">,</span> <span class="mf">.4</span><span class="p">,</span> <span class="mi">2</span><span class="p">]</span>    
-<span class="p">]</span>
-
-<span class="k">def</span> <span class="nf">make_rows</span><span class="p">(</span><span class="n">estimated</span><span class="p">,</span> <span class="n">objects</span><span class="p">):</span>
-    <span class="n">rows</span> <span class="o">=</span> <span class="p">[]</span>
-    <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">estimated</span><span class="p">:</span>
-        <span class="n">row</span> <span class="o">=</span> <span class="p">{</span><span class="n">objects</span><span class="p">[</span><span class="n">i</span><span class="p">]:</span> <span class="n">x</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span><span class="n">x</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">row</span><span class="p">)}</span>
-        <span class="n">rows</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">row</span><span class="p">)</span>
-    <span class="k">return</span> <span class="n">rows</span>
-
-<span class="n">found_p</span> <span class="o">=</span> <span class="p">[</span><span class="mi">4</span><span class="p">,</span> <span class="mi">51</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">12</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">12</span><span class="p">,</span> <span class="mi">266</span><span class="p">]</span>
-<span class="n">found_pm</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="o">/</span><span class="n">length_p</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">found_p</span><span class="p">]</span>
-
-<span class="n">pierrette_rows</span> <span class="o">=</span> <span class="n">make_rows</span><span class="p">(</span><span class="n">estimated_p</span><span class="p">,</span> <span class="n">objects</span><span class="p">)</span>
-<span class="n">pierrette</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">pierrette_rows</span><span class="p">)</span>
-</pre></div>
-</div>
-</div>
-</div>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">found_pel</span> <span class="o">=</span> <span class="p">[</span><span class="mi">4</span><span class="p">,</span> <span class="mi">51</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">12</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">12</span><span class="p">,</span> <span class="mi">266</span><span class="p">]</span>
-<span class="n">found_pelm</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="o">/</span><span class="n">length_p</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">found_p</span><span class="p">]</span>
-</pre></div>
-</div>
-</div>
-</div>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">estimated_td</span> <span class="o">=</span> <span class="p">[</span>
-    <span class="p">[</span><span class="mf">.16</span><span class="p">,</span> <span class="mf">1.12</span><span class="p">,</span> <span class="mf">.54</span><span class="p">,</span> <span class="mf">.05</span><span class="p">,</span> <span class="mf">.30</span><span class="p">,</span> <span class="mf">.08</span><span class="p">,</span> <span class="mf">.39</span><span class="p">,</span> <span class="mf">.04</span><span class="p">,</span> <span class="mf">.31</span><span class="p">,</span> <span class="mf">1.34</span><span class="p">],</span>
-    <span class="p">[</span><span class="mf">.15</span><span class="p">,</span> <span class="mf">.57</span><span class="p">,</span><span class="mf">.24</span><span class="p">,</span><span class="mf">.08</span><span class="p">,</span><span class="mf">.05</span><span class="p">,</span><span class="mf">.05</span><span class="p">,</span><span class="mf">.16</span><span class="p">,</span><span class="mf">.1</span><span class="p">,</span><span class="mf">.14</span><span class="p">,</span> <span class="mf">.22</span><span class="p">],</span>
-    <span class="p">[</span><span class="mf">.05</span><span class="p">,</span> <span class="mf">.8</span><span class="p">,</span> <span class="mf">.2</span><span class="p">,</span> <span class="mf">.02</span><span class="p">,</span> <span class="mf">.15</span><span class="p">,</span> <span class="mf">.04</span><span class="p">,</span> <span class="mf">.3</span><span class="p">,</span> <span class="mf">.01</span><span class="p">,</span> <span class="mf">.25</span><span class="p">,</span> <span class="mf">1.2</span><span class="p">],</span>
-    <span class="p">[</span><span class="mf">.1</span><span class="p">,</span><span class="mf">.35</span><span class="p">,</span><span class="mf">.15</span><span class="p">,</span><span class="mf">.03</span><span class="p">,</span> <span class="mf">.05</span><span class="p">,</span> <span class="mf">.01</span><span class="p">,</span> <span class="mf">.06</span><span class="p">,</span> <span class="mf">.1</span><span class="p">,</span> <span class="mf">.15</span><span class="p">,</span> <span class="mf">.5</span><span class="p">],</span>
-    <span class="p">[</span><span class="mf">.07</span><span class="p">,</span> <span class="mf">.15</span><span class="p">,</span> <span class="mf">.05</span><span class="p">,</span> <span class="mf">.02</span><span class="p">,</span> <span class="mf">.01</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mf">.04</span><span class="p">,</span> <span class="mf">.01</span><span class="p">,</span> <span class="mf">.08</span><span class="p">,</span> <span class="mf">.12</span><span class="p">],</span>
-    <span class="p">[</span><span class="mf">.15</span><span class="p">,</span> <span class="mf">.5</span><span class="p">,</span> <span class="mf">.3</span><span class="p">,</span> <span class="mf">.03</span><span class="p">,</span> <span class="mf">.01</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mf">.05</span><span class="p">,</span> <span class="mf">.05</span><span class="p">,</span> <span class="mf">.2</span><span class="p">,</span> <span class="mf">.2</span><span class="p">]</span>
-<span class="p">]</span>
-
-<span class="n">length_td</span><span class="o">=</span><span class="mf">16.5</span>
-
-<span class="n">found_td</span> <span class="o">=</span> <span class="p">[</span><span class="mi">11</span><span class="p">,</span> <span class="mi">60</span><span class="p">,</span> <span class="mi">9</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span><span class="mi">13</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">179</span><span class="p">]</span>
-<span class="n">found_tdm</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">x</span><span class="o">/</span><span class="n">length_td</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">found_td</span><span class="p">])</span>
-
-<span class="n">tiger_duck_rows</span> <span class="o">=</span> <span class="n">make_rows</span><span class="p">(</span><span class="n">estimated_td</span><span class="p">,</span> <span class="n">objects</span><span class="p">)</span>
-<span class="n">tiger_duck</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">tiger_duck_rows</span><span class="p">)</span>
-
-<span class="n">found</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">([</span><span class="n">found_tdm</span><span class="p">,</span> <span class="n">found_pm</span><span class="p">],</span> <span class="n">columns</span><span class="o">=</span><span class="n">objects</span><span class="p">)</span>
-<span class="n">fmelted</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">melt</span><span class="p">(</span><span class="n">found</span><span class="p">,</span> <span class="n">value_vars</span><span class="o">=</span><span class="n">found</span><span class="o">.</span><span class="n">columns</span><span class="p">)</span>
-<span class="n">fmelted</span><span class="p">[</span><span class="s2">&quot;source&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="s2">&quot;found&quot;</span>
-
-<span class="n">combined</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">([</span><span class="n">tiger_duck</span><span class="p">,</span> <span class="n">pierrette</span><span class="p">])</span>
-<span class="n">caption</span> <span class="o">=</span> <span class="s2">&quot;Table 5: The estimated amount in pcs/meter for each object that the participants expected to find.&quot;</span>
-<span class="n">combined</span><span class="o">.</span><span class="n">reset_index</span><span class="p">(</span><span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">drop</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-<span class="n">combined</span><span class="o">.</span><span class="n">style</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">precision</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">set_table_styles</span><span class="p">(</span><span class="n">table_large_font</span><span class="p">)</span><span class="o">.</span><span class="n">set_caption</span><span class="p">(</span><span class="n">caption</span><span class="p">)</span>
-</pre></div>
+<div class="cell tag_remove-input docutils container">
 </div>
+<div class="cell tag_remove-input docutils container">
 </div>
+<div class="cell tag_remove-input docutils container">
 <div class="cell_output docutils container">
 <div class="output text_html"><style type="text/css">
-#T_ac8e3 tr:nth-child(even) {
+#T_abf7a tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_ac8e3 tr:nth-child(odd) {
+#T_abf7a tr:nth-child(odd) {
   background: #FFF;
 }
-#T_ac8e3 tr {
+#T_abf7a tr {
   font-size: 14px;
   padding: 12px;
 }
-#T_ac8e3 th:nth-child(1) {
+#T_abf7a th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_ac8e3 caption {
+#T_abf7a caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -1340,140 +978,140 @@ <h3><span class="section-number">3.3.2. </span>Estimates from participants<a cla
   margin-top: 10px;
 }
 </style>
-<table id="T_ac8e3">
+<table id="T_abf7a">
   <caption>Table 5: The estimated amount in pcs/meter for each object that the participants expected to find.</caption>
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_ac8e3_level0_col0" class="col_heading level0 col0" >G112</th>
-      <th id="T_ac8e3_level0_col1" class="col_heading level0 col1" >G27</th>
-      <th id="T_ac8e3_level0_col2" class="col_heading level0 col2" >G30</th>
-      <th id="T_ac8e3_level0_col3" class="col_heading level0 col3" >G32</th>
-      <th id="T_ac8e3_level0_col4" class="col_heading level0 col4" >G67</th>
-      <th id="T_ac8e3_level0_col5" class="col_heading level0 col5" >G70</th>
-      <th id="T_ac8e3_level0_col6" class="col_heading level0 col6" >G95</th>
-      <th id="T_ac8e3_level0_col7" class="col_heading level0 col7" >G96</th>
-      <th id="T_ac8e3_level0_col8" class="col_heading level0 col8" >Gcaps</th>
-      <th id="T_ac8e3_level0_col9" class="col_heading level0 col9" >Gfrags</th>
+      <th id="T_abf7a_level0_col0" class="col_heading level0 col0" >G112</th>
+      <th id="T_abf7a_level0_col1" class="col_heading level0 col1" >G27</th>
+      <th id="T_abf7a_level0_col2" class="col_heading level0 col2" >G30</th>
+      <th id="T_abf7a_level0_col3" class="col_heading level0 col3" >G32</th>
+      <th id="T_abf7a_level0_col4" class="col_heading level0 col4" >G67</th>
+      <th id="T_abf7a_level0_col5" class="col_heading level0 col5" >G70</th>
+      <th id="T_abf7a_level0_col6" class="col_heading level0 col6" >G95</th>
+      <th id="T_abf7a_level0_col7" class="col_heading level0 col7" >G96</th>
+      <th id="T_abf7a_level0_col8" class="col_heading level0 col8" >Gcaps</th>
+      <th id="T_abf7a_level0_col9" class="col_heading level0 col9" >Gfrags</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_ac8e3_level0_row0" class="row_heading level0 row0" >0</th>
-      <td id="T_ac8e3_row0_col0" class="data row0 col0" >0.16</td>
-      <td id="T_ac8e3_row0_col1" class="data row0 col1" >1.12</td>
-      <td id="T_ac8e3_row0_col2" class="data row0 col2" >0.54</td>
-      <td id="T_ac8e3_row0_col3" class="data row0 col3" >0.05</td>
-      <td id="T_ac8e3_row0_col4" class="data row0 col4" >0.30</td>
-      <td id="T_ac8e3_row0_col5" class="data row0 col5" >0.08</td>
-      <td id="T_ac8e3_row0_col6" class="data row0 col6" >0.39</td>
-      <td id="T_ac8e3_row0_col7" class="data row0 col7" >0.04</td>
-      <td id="T_ac8e3_row0_col8" class="data row0 col8" >0.31</td>
-      <td id="T_ac8e3_row0_col9" class="data row0 col9" >1.34</td>
-    </tr>
-    <tr>
-      <th id="T_ac8e3_level0_row1" class="row_heading level0 row1" >1</th>
-      <td id="T_ac8e3_row1_col0" class="data row1 col0" >0.15</td>
-      <td id="T_ac8e3_row1_col1" class="data row1 col1" >0.57</td>
-      <td id="T_ac8e3_row1_col2" class="data row1 col2" >0.24</td>
-      <td id="T_ac8e3_row1_col3" class="data row1 col3" >0.08</td>
-      <td id="T_ac8e3_row1_col4" class="data row1 col4" >0.05</td>
-      <td id="T_ac8e3_row1_col5" class="data row1 col5" >0.05</td>
-      <td id="T_ac8e3_row1_col6" class="data row1 col6" >0.16</td>
-      <td id="T_ac8e3_row1_col7" class="data row1 col7" >0.10</td>
-      <td id="T_ac8e3_row1_col8" class="data row1 col8" >0.14</td>
-      <td id="T_ac8e3_row1_col9" class="data row1 col9" >0.22</td>
-    </tr>
-    <tr>
-      <th id="T_ac8e3_level0_row2" class="row_heading level0 row2" >2</th>
-      <td id="T_ac8e3_row2_col0" class="data row2 col0" >0.05</td>
-      <td id="T_ac8e3_row2_col1" class="data row2 col1" >0.80</td>
-      <td id="T_ac8e3_row2_col2" class="data row2 col2" >0.20</td>
-      <td id="T_ac8e3_row2_col3" class="data row2 col3" >0.02</td>
-      <td id="T_ac8e3_row2_col4" class="data row2 col4" >0.15</td>
-      <td id="T_ac8e3_row2_col5" class="data row2 col5" >0.04</td>
-      <td id="T_ac8e3_row2_col6" class="data row2 col6" >0.30</td>
-      <td id="T_ac8e3_row2_col7" class="data row2 col7" >0.01</td>
-      <td id="T_ac8e3_row2_col8" class="data row2 col8" >0.25</td>
-      <td id="T_ac8e3_row2_col9" class="data row2 col9" >1.20</td>
-    </tr>
-    <tr>
-      <th id="T_ac8e3_level0_row3" class="row_heading level0 row3" >3</th>
-      <td id="T_ac8e3_row3_col0" class="data row3 col0" >0.10</td>
-      <td id="T_ac8e3_row3_col1" class="data row3 col1" >0.35</td>
-      <td id="T_ac8e3_row3_col2" class="data row3 col2" >0.15</td>
-      <td id="T_ac8e3_row3_col3" class="data row3 col3" >0.03</td>
-      <td id="T_ac8e3_row3_col4" class="data row3 col4" >0.05</td>
-      <td id="T_ac8e3_row3_col5" class="data row3 col5" >0.01</td>
-      <td id="T_ac8e3_row3_col6" class="data row3 col6" >0.06</td>
-      <td id="T_ac8e3_row3_col7" class="data row3 col7" >0.10</td>
-      <td id="T_ac8e3_row3_col8" class="data row3 col8" >0.15</td>
-      <td id="T_ac8e3_row3_col9" class="data row3 col9" >0.50</td>
-    </tr>
-    <tr>
-      <th id="T_ac8e3_level0_row4" class="row_heading level0 row4" >4</th>
-      <td id="T_ac8e3_row4_col0" class="data row4 col0" >0.07</td>
-      <td id="T_ac8e3_row4_col1" class="data row4 col1" >0.15</td>
-      <td id="T_ac8e3_row4_col2" class="data row4 col2" >0.05</td>
-      <td id="T_ac8e3_row4_col3" class="data row4 col3" >0.02</td>
-      <td id="T_ac8e3_row4_col4" class="data row4 col4" >0.01</td>
-      <td id="T_ac8e3_row4_col5" class="data row4 col5" >0.00</td>
-      <td id="T_ac8e3_row4_col6" class="data row4 col6" >0.04</td>
-      <td id="T_ac8e3_row4_col7" class="data row4 col7" >0.01</td>
-      <td id="T_ac8e3_row4_col8" class="data row4 col8" >0.08</td>
-      <td id="T_ac8e3_row4_col9" class="data row4 col9" >0.12</td>
-    </tr>
-    <tr>
-      <th id="T_ac8e3_level0_row5" class="row_heading level0 row5" >5</th>
-      <td id="T_ac8e3_row5_col0" class="data row5 col0" >0.15</td>
-      <td id="T_ac8e3_row5_col1" class="data row5 col1" >0.50</td>
-      <td id="T_ac8e3_row5_col2" class="data row5 col2" >0.30</td>
-      <td id="T_ac8e3_row5_col3" class="data row5 col3" >0.03</td>
-      <td id="T_ac8e3_row5_col4" class="data row5 col4" >0.01</td>
-      <td id="T_ac8e3_row5_col5" class="data row5 col5" >0.00</td>
-      <td id="T_ac8e3_row5_col6" class="data row5 col6" >0.05</td>
-      <td id="T_ac8e3_row5_col7" class="data row5 col7" >0.05</td>
-      <td id="T_ac8e3_row5_col8" class="data row5 col8" >0.20</td>
-      <td id="T_ac8e3_row5_col9" class="data row5 col9" >0.20</td>
-    </tr>
-    <tr>
-      <th id="T_ac8e3_level0_row6" class="row_heading level0 row6" >6</th>
-      <td id="T_ac8e3_row6_col0" class="data row6 col0" >0.16</td>
-      <td id="T_ac8e3_row6_col1" class="data row6 col1" >1.12</td>
-      <td id="T_ac8e3_row6_col2" class="data row6 col2" >0.54</td>
-      <td id="T_ac8e3_row6_col3" class="data row6 col3" >0.05</td>
-      <td id="T_ac8e3_row6_col4" class="data row6 col4" >0.30</td>
-      <td id="T_ac8e3_row6_col5" class="data row6 col5" >0.08</td>
-      <td id="T_ac8e3_row6_col6" class="data row6 col6" >0.39</td>
-      <td id="T_ac8e3_row6_col7" class="data row6 col7" >0.04</td>
-      <td id="T_ac8e3_row6_col8" class="data row6 col8" >0.31</td>
-      <td id="T_ac8e3_row6_col9" class="data row6 col9" >1.34</td>
-    </tr>
-    <tr>
-      <th id="T_ac8e3_level0_row7" class="row_heading level0 row7" >7</th>
-      <td id="T_ac8e3_row7_col0" class="data row7 col0" >6.00</td>
-      <td id="T_ac8e3_row7_col1" class="data row7 col1" >3.00</td>
-      <td id="T_ac8e3_row7_col2" class="data row7 col2" >0.60</td>
-      <td id="T_ac8e3_row7_col3" class="data row7 col3" >0.10</td>
-      <td id="T_ac8e3_row7_col4" class="data row7 col4" >0.40</td>
-      <td id="T_ac8e3_row7_col5" class="data row7 col5" >0.03</td>
-      <td id="T_ac8e3_row7_col6" class="data row7 col6" >0.80</td>
-      <td id="T_ac8e3_row7_col7" class="data row7 col7" >1.00</td>
-      <td id="T_ac8e3_row7_col8" class="data row7 col8" >2.00</td>
-      <td id="T_ac8e3_row7_col9" class="data row7 col9" >1.34</td>
-    </tr>
-    <tr>
-      <th id="T_ac8e3_level0_row8" class="row_heading level0 row8" >8</th>
-      <td id="T_ac8e3_row8_col0" class="data row8 col0" >0.40</td>
-      <td id="T_ac8e3_row8_col1" class="data row8 col1" >1.50</td>
-      <td id="T_ac8e3_row8_col2" class="data row8 col2" >0.30</td>
-      <td id="T_ac8e3_row8_col3" class="data row8 col3" >0.10</td>
-      <td id="T_ac8e3_row8_col4" class="data row8 col4" >1.10</td>
-      <td id="T_ac8e3_row8_col5" class="data row8 col5" >0.01</td>
-      <td id="T_ac8e3_row8_col6" class="data row8 col6" >0.50</td>
-      <td id="T_ac8e3_row8_col7" class="data row8 col7" >0.20</td>
-      <td id="T_ac8e3_row8_col8" class="data row8 col8" >0.40</td>
-      <td id="T_ac8e3_row8_col9" class="data row8 col9" >2.00</td>
+      <th id="T_abf7a_level0_row0" class="row_heading level0 row0" >0</th>
+      <td id="T_abf7a_row0_col0" class="data row0 col0" >0.16</td>
+      <td id="T_abf7a_row0_col1" class="data row0 col1" >1.12</td>
+      <td id="T_abf7a_row0_col2" class="data row0 col2" >0.54</td>
+      <td id="T_abf7a_row0_col3" class="data row0 col3" >0.05</td>
+      <td id="T_abf7a_row0_col4" class="data row0 col4" >0.30</td>
+      <td id="T_abf7a_row0_col5" class="data row0 col5" >0.08</td>
+      <td id="T_abf7a_row0_col6" class="data row0 col6" >0.39</td>
+      <td id="T_abf7a_row0_col7" class="data row0 col7" >0.04</td>
+      <td id="T_abf7a_row0_col8" class="data row0 col8" >0.31</td>
+      <td id="T_abf7a_row0_col9" class="data row0 col9" >1.34</td>
+    </tr>
+    <tr>
+      <th id="T_abf7a_level0_row1" class="row_heading level0 row1" >1</th>
+      <td id="T_abf7a_row1_col0" class="data row1 col0" >0.15</td>
+      <td id="T_abf7a_row1_col1" class="data row1 col1" >0.57</td>
+      <td id="T_abf7a_row1_col2" class="data row1 col2" >0.24</td>
+      <td id="T_abf7a_row1_col3" class="data row1 col3" >0.08</td>
+      <td id="T_abf7a_row1_col4" class="data row1 col4" >0.05</td>
+      <td id="T_abf7a_row1_col5" class="data row1 col5" >0.05</td>
+      <td id="T_abf7a_row1_col6" class="data row1 col6" >0.16</td>
+      <td id="T_abf7a_row1_col7" class="data row1 col7" >0.10</td>
+      <td id="T_abf7a_row1_col8" class="data row1 col8" >0.14</td>
+      <td id="T_abf7a_row1_col9" class="data row1 col9" >0.22</td>
+    </tr>
+    <tr>
+      <th id="T_abf7a_level0_row2" class="row_heading level0 row2" >2</th>
+      <td id="T_abf7a_row2_col0" class="data row2 col0" >0.05</td>
+      <td id="T_abf7a_row2_col1" class="data row2 col1" >0.80</td>
+      <td id="T_abf7a_row2_col2" class="data row2 col2" >0.20</td>
+      <td id="T_abf7a_row2_col3" class="data row2 col3" >0.02</td>
+      <td id="T_abf7a_row2_col4" class="data row2 col4" >0.15</td>
+      <td id="T_abf7a_row2_col5" class="data row2 col5" >0.04</td>
+      <td id="T_abf7a_row2_col6" class="data row2 col6" >0.30</td>
+      <td id="T_abf7a_row2_col7" class="data row2 col7" >0.01</td>
+      <td id="T_abf7a_row2_col8" class="data row2 col8" >0.25</td>
+      <td id="T_abf7a_row2_col9" class="data row2 col9" >1.20</td>
+    </tr>
+    <tr>
+      <th id="T_abf7a_level0_row3" class="row_heading level0 row3" >3</th>
+      <td id="T_abf7a_row3_col0" class="data row3 col0" >0.10</td>
+      <td id="T_abf7a_row3_col1" class="data row3 col1" >0.35</td>
+      <td id="T_abf7a_row3_col2" class="data row3 col2" >0.15</td>
+      <td id="T_abf7a_row3_col3" class="data row3 col3" >0.03</td>
+      <td id="T_abf7a_row3_col4" class="data row3 col4" >0.05</td>
+      <td id="T_abf7a_row3_col5" class="data row3 col5" >0.01</td>
+      <td id="T_abf7a_row3_col6" class="data row3 col6" >0.06</td>
+      <td id="T_abf7a_row3_col7" class="data row3 col7" >0.10</td>
+      <td id="T_abf7a_row3_col8" class="data row3 col8" >0.15</td>
+      <td id="T_abf7a_row3_col9" class="data row3 col9" >0.50</td>
+    </tr>
+    <tr>
+      <th id="T_abf7a_level0_row4" class="row_heading level0 row4" >4</th>
+      <td id="T_abf7a_row4_col0" class="data row4 col0" >0.07</td>
+      <td id="T_abf7a_row4_col1" class="data row4 col1" >0.15</td>
+      <td id="T_abf7a_row4_col2" class="data row4 col2" >0.05</td>
+      <td id="T_abf7a_row4_col3" class="data row4 col3" >0.02</td>
+      <td id="T_abf7a_row4_col4" class="data row4 col4" >0.01</td>
+      <td id="T_abf7a_row4_col5" class="data row4 col5" >0.00</td>
+      <td id="T_abf7a_row4_col6" class="data row4 col6" >0.04</td>
+      <td id="T_abf7a_row4_col7" class="data row4 col7" >0.01</td>
+      <td id="T_abf7a_row4_col8" class="data row4 col8" >0.08</td>
+      <td id="T_abf7a_row4_col9" class="data row4 col9" >0.12</td>
+    </tr>
+    <tr>
+      <th id="T_abf7a_level0_row5" class="row_heading level0 row5" >5</th>
+      <td id="T_abf7a_row5_col0" class="data row5 col0" >0.15</td>
+      <td id="T_abf7a_row5_col1" class="data row5 col1" >0.50</td>
+      <td id="T_abf7a_row5_col2" class="data row5 col2" >0.30</td>
+      <td id="T_abf7a_row5_col3" class="data row5 col3" >0.03</td>
+      <td id="T_abf7a_row5_col4" class="data row5 col4" >0.01</td>
+      <td id="T_abf7a_row5_col5" class="data row5 col5" >0.00</td>
+      <td id="T_abf7a_row5_col6" class="data row5 col6" >0.05</td>
+      <td id="T_abf7a_row5_col7" class="data row5 col7" >0.05</td>
+      <td id="T_abf7a_row5_col8" class="data row5 col8" >0.20</td>
+      <td id="T_abf7a_row5_col9" class="data row5 col9" >0.20</td>
+    </tr>
+    <tr>
+      <th id="T_abf7a_level0_row6" class="row_heading level0 row6" >6</th>
+      <td id="T_abf7a_row6_col0" class="data row6 col0" >0.16</td>
+      <td id="T_abf7a_row6_col1" class="data row6 col1" >1.12</td>
+      <td id="T_abf7a_row6_col2" class="data row6 col2" >0.54</td>
+      <td id="T_abf7a_row6_col3" class="data row6 col3" >0.05</td>
+      <td id="T_abf7a_row6_col4" class="data row6 col4" >0.30</td>
+      <td id="T_abf7a_row6_col5" class="data row6 col5" >0.08</td>
+      <td id="T_abf7a_row6_col6" class="data row6 col6" >0.39</td>
+      <td id="T_abf7a_row6_col7" class="data row6 col7" >0.04</td>
+      <td id="T_abf7a_row6_col8" class="data row6 col8" >0.31</td>
+      <td id="T_abf7a_row6_col9" class="data row6 col9" >1.34</td>
+    </tr>
+    <tr>
+      <th id="T_abf7a_level0_row7" class="row_heading level0 row7" >7</th>
+      <td id="T_abf7a_row7_col0" class="data row7 col0" >6.00</td>
+      <td id="T_abf7a_row7_col1" class="data row7 col1" >3.00</td>
+      <td id="T_abf7a_row7_col2" class="data row7 col2" >0.60</td>
+      <td id="T_abf7a_row7_col3" class="data row7 col3" >0.10</td>
+      <td id="T_abf7a_row7_col4" class="data row7 col4" >0.40</td>
+      <td id="T_abf7a_row7_col5" class="data row7 col5" >0.03</td>
+      <td id="T_abf7a_row7_col6" class="data row7 col6" >0.80</td>
+      <td id="T_abf7a_row7_col7" class="data row7 col7" >1.00</td>
+      <td id="T_abf7a_row7_col8" class="data row7 col8" >2.00</td>
+      <td id="T_abf7a_row7_col9" class="data row7 col9" >1.34</td>
+    </tr>
+    <tr>
+      <th id="T_abf7a_level0_row8" class="row_heading level0 row8" >8</th>
+      <td id="T_abf7a_row8_col0" class="data row8 col0" >0.40</td>
+      <td id="T_abf7a_row8_col1" class="data row8 col1" >1.50</td>
+      <td id="T_abf7a_row8_col2" class="data row8 col2" >0.30</td>
+      <td id="T_abf7a_row8_col3" class="data row8 col3" >0.10</td>
+      <td id="T_abf7a_row8_col4" class="data row8 col4" >1.10</td>
+      <td id="T_abf7a_row8_col5" class="data row8 col5" >0.01</td>
+      <td id="T_abf7a_row8_col6" class="data row8 col6" >0.50</td>
+      <td id="T_abf7a_row8_col7" class="data row8 col7" >0.20</td>
+      <td id="T_abf7a_row8_col8" class="data row8 col8" >0.40</td>
+      <td id="T_abf7a_row8_col9" class="data row8 col9" >2.00</td>
     </tr>
   </tbody>
 </table>
@@ -1484,35 +1122,24 @@ <h3><span class="section-number">3.3.2. </span>Estimates from participants<a cla
 <div class="section" id="survey-results-october-5-2023-saint-sulpice">
 <h2><span class="section-number">3.4. </span>Survey results October 5, 2023 Saint Sulpice<a class="headerlink" href="#survey-results-october-5-2023-saint-sulpice" title="Permalink to this heading">#</a></h2>
 <p>After the particpants completed the forms, surveys were conducted at three beaches within the city limits of Saint Sulpice. Only the forms for two beaches were returned.</p>
-<div class="cell docutils container">
-<div class="cell_input docutils container">
-<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">caption</span><span class="o">=</span><span class="s2">&quot;Table 6: The survey results of the objects of interest on October 5, 2023 in pieces per meter&quot;</span>
-<span class="n">found_display</span> <span class="o">=</span> <span class="n">found</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-<span class="n">found_display</span><span class="o">.</span><span class="n">loc</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;beach&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="s2">&quot;tiger-duck-beach&quot;</span>
-<span class="n">found_display</span><span class="o">.</span><span class="n">loc</span><span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="s2">&quot;beach&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="s2">&quot;parc-des-pierrettes&quot;</span>
-<span class="n">found_display</span><span class="o">.</span><span class="n">set_index</span><span class="p">(</span><span class="s2">&quot;beach&quot;</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">drop</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-<span class="n">found_display</span><span class="o">.</span><span class="n">index</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="kc">None</span>
-<span class="n">found_display</span><span class="o">.</span><span class="n">style</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">precision</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">set_table_styles</span><span class="p">(</span><span class="n">table_large_font</span><span class="p">)</span><span class="o">.</span><span class="n">set_caption</span><span class="p">(</span><span class="n">caption</span><span class="p">)</span>
-</pre></div>
-</div>
-</div>
+<div class="cell tag_remove-input docutils container">
 <div class="cell_output docutils container">
 <div class="output text_html"><style type="text/css">
-#T_208b1 tr:nth-child(even) {
+#T_b354f tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_208b1 tr:nth-child(odd) {
+#T_b354f tr:nth-child(odd) {
   background: #FFF;
 }
-#T_208b1 tr {
+#T_b354f tr {
   font-size: 14px;
   padding: 12px;
 }
-#T_208b1 th:nth-child(1) {
+#T_b354f th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_208b1 caption {
+#T_b354f caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -1520,49 +1147,49 @@ <h2><span class="section-number">3.4. </span>Survey results October 5, 2023 Sain
   margin-top: 10px;
 }
 </style>
-<table id="T_208b1">
+<table id="T_b354f">
   <caption>Table 6: The survey results of the objects of interest on October 5, 2023 in pieces per meter</caption>
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_208b1_level0_col0" class="col_heading level0 col0" >G112</th>
-      <th id="T_208b1_level0_col1" class="col_heading level0 col1" >G27</th>
-      <th id="T_208b1_level0_col2" class="col_heading level0 col2" >G30</th>
-      <th id="T_208b1_level0_col3" class="col_heading level0 col3" >G32</th>
-      <th id="T_208b1_level0_col4" class="col_heading level0 col4" >G67</th>
-      <th id="T_208b1_level0_col5" class="col_heading level0 col5" >G70</th>
-      <th id="T_208b1_level0_col6" class="col_heading level0 col6" >G95</th>
-      <th id="T_208b1_level0_col7" class="col_heading level0 col7" >G96</th>
-      <th id="T_208b1_level0_col8" class="col_heading level0 col8" >Gcaps</th>
-      <th id="T_208b1_level0_col9" class="col_heading level0 col9" >Gfrags</th>
+      <th id="T_b354f_level0_col0" class="col_heading level0 col0" >G112</th>
+      <th id="T_b354f_level0_col1" class="col_heading level0 col1" >G27</th>
+      <th id="T_b354f_level0_col2" class="col_heading level0 col2" >G30</th>
+      <th id="T_b354f_level0_col3" class="col_heading level0 col3" >G32</th>
+      <th id="T_b354f_level0_col4" class="col_heading level0 col4" >G67</th>
+      <th id="T_b354f_level0_col5" class="col_heading level0 col5" >G70</th>
+      <th id="T_b354f_level0_col6" class="col_heading level0 col6" >G95</th>
+      <th id="T_b354f_level0_col7" class="col_heading level0 col7" >G96</th>
+      <th id="T_b354f_level0_col8" class="col_heading level0 col8" >Gcaps</th>
+      <th id="T_b354f_level0_col9" class="col_heading level0 col9" >Gfrags</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_208b1_level0_row0" class="row_heading level0 row0" >tiger-duck-beach</th>
-      <td id="T_208b1_row0_col0" class="data row0 col0" >0.67</td>
-      <td id="T_208b1_row0_col1" class="data row0 col1" >3.64</td>
-      <td id="T_208b1_row0_col2" class="data row0 col2" >0.55</td>
-      <td id="T_208b1_row0_col3" class="data row0 col3" >0.18</td>
-      <td id="T_208b1_row0_col4" class="data row0 col4" >0.00</td>
-      <td id="T_208b1_row0_col5" class="data row0 col5" >0.00</td>
-      <td id="T_208b1_row0_col6" class="data row0 col6" >0.79</td>
-      <td id="T_208b1_row0_col7" class="data row0 col7" >0.06</td>
-      <td id="T_208b1_row0_col8" class="data row0 col8" >0.18</td>
-      <td id="T_208b1_row0_col9" class="data row0 col9" >10.85</td>
-    </tr>
-    <tr>
-      <th id="T_208b1_level0_row1" class="row_heading level0 row1" >parc-des-pierrettes</th>
-      <td id="T_208b1_row1_col0" class="data row1 col0" >0.08</td>
-      <td id="T_208b1_row1_col1" class="data row1 col1" >1.03</td>
-      <td id="T_208b1_row1_col2" class="data row1 col2" >0.14</td>
-      <td id="T_208b1_row1_col3" class="data row1 col3" >0.04</td>
-      <td id="T_208b1_row1_col4" class="data row1 col4" >0.00</td>
-      <td id="T_208b1_row1_col5" class="data row1 col5" >0.00</td>
-      <td id="T_208b1_row1_col6" class="data row1 col6" >0.24</td>
-      <td id="T_208b1_row1_col7" class="data row1 col7" >0.02</td>
-      <td id="T_208b1_row1_col8" class="data row1 col8" >0.24</td>
-      <td id="T_208b1_row1_col9" class="data row1 col9" >5.40</td>
+      <th id="T_b354f_level0_row0" class="row_heading level0 row0" >tiger-duck-beach</th>
+      <td id="T_b354f_row0_col0" class="data row0 col0" >0.67</td>
+      <td id="T_b354f_row0_col1" class="data row0 col1" >3.64</td>
+      <td id="T_b354f_row0_col2" class="data row0 col2" >0.55</td>
+      <td id="T_b354f_row0_col3" class="data row0 col3" >0.18</td>
+      <td id="T_b354f_row0_col4" class="data row0 col4" >0.00</td>
+      <td id="T_b354f_row0_col5" class="data row0 col5" >0.00</td>
+      <td id="T_b354f_row0_col6" class="data row0 col6" >0.79</td>
+      <td id="T_b354f_row0_col7" class="data row0 col7" >0.06</td>
+      <td id="T_b354f_row0_col8" class="data row0 col8" >0.18</td>
+      <td id="T_b354f_row0_col9" class="data row0 col9" >10.85</td>
+    </tr>
+    <tr>
+      <th id="T_b354f_level0_row1" class="row_heading level0 row1" >parc-des-pierrettes</th>
+      <td id="T_b354f_row1_col0" class="data row1 col0" >0.08</td>
+      <td id="T_b354f_row1_col1" class="data row1 col1" >1.03</td>
+      <td id="T_b354f_row1_col2" class="data row1 col2" >0.14</td>
+      <td id="T_b354f_row1_col3" class="data row1 col3" >0.04</td>
+      <td id="T_b354f_row1_col4" class="data row1 col4" >0.00</td>
+      <td id="T_b354f_row1_col5" class="data row1 col5" >0.00</td>
+      <td id="T_b354f_row1_col6" class="data row1 col6" >0.24</td>
+      <td id="T_b354f_row1_col7" class="data row1 col7" >0.02</td>
+      <td id="T_b354f_row1_col8" class="data row1 col8" >0.24</td>
+      <td id="T_b354f_row1_col9" class="data row1 col9" >5.40</td>
     </tr>
   </tbody>
 </table>
@@ -1575,21 +1202,21 @@ <h2><span class="section-number">3.5. </span>Survey results October 5, 2023 Sain
 <div class="cell tag_remove-input docutils container">
 <div class="cell_output docutils container">
 <div class="output text_html"><style type="text/css">
-#T_46124 tr:nth-child(even) {
+#T_075e0 tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_46124 tr:nth-child(odd) {
+#T_075e0 tr:nth-child(odd) {
   background: #FFF;
 }
-#T_46124 tr {
+#T_075e0 tr {
   font-size: 14px;
   padding: 12px;
 }
-#T_46124 th:nth-child(1) {
+#T_075e0 th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_46124 caption {
+#T_075e0 caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -1597,49 +1224,49 @@ <h2><span class="section-number">3.5. </span>Survey results October 5, 2023 Sain
   margin-top: 10px;
 }
 </style>
-<table id="T_46124">
+<table id="T_075e0">
   <caption>Table 6: The survey results of the objects of interest on October 5, 2023 in pieces per meter</caption>
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_46124_level0_col0" class="col_heading level0 col0" >G112</th>
-      <th id="T_46124_level0_col1" class="col_heading level0 col1" >G27</th>
-      <th id="T_46124_level0_col2" class="col_heading level0 col2" >G30</th>
-      <th id="T_46124_level0_col3" class="col_heading level0 col3" >G32</th>
-      <th id="T_46124_level0_col4" class="col_heading level0 col4" >G67</th>
-      <th id="T_46124_level0_col5" class="col_heading level0 col5" >G70</th>
-      <th id="T_46124_level0_col6" class="col_heading level0 col6" >G95</th>
-      <th id="T_46124_level0_col7" class="col_heading level0 col7" >G96</th>
-      <th id="T_46124_level0_col8" class="col_heading level0 col8" >Gcaps</th>
-      <th id="T_46124_level0_col9" class="col_heading level0 col9" >Gfrags</th>
+      <th id="T_075e0_level0_col0" class="col_heading level0 col0" >G112</th>
+      <th id="T_075e0_level0_col1" class="col_heading level0 col1" >G27</th>
+      <th id="T_075e0_level0_col2" class="col_heading level0 col2" >G30</th>
+      <th id="T_075e0_level0_col3" class="col_heading level0 col3" >G32</th>
+      <th id="T_075e0_level0_col4" class="col_heading level0 col4" >G67</th>
+      <th id="T_075e0_level0_col5" class="col_heading level0 col5" >G70</th>
+      <th id="T_075e0_level0_col6" class="col_heading level0 col6" >G95</th>
+      <th id="T_075e0_level0_col7" class="col_heading level0 col7" >G96</th>
+      <th id="T_075e0_level0_col8" class="col_heading level0 col8" >Gcaps</th>
+      <th id="T_075e0_level0_col9" class="col_heading level0 col9" >Gfrags</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_46124_level0_row0" class="row_heading level0 row0" >tiger-duck-beach</th>
-      <td id="T_46124_row0_col0" class="data row0 col0" >0.67</td>
-      <td id="T_46124_row0_col1" class="data row0 col1" >3.64</td>
-      <td id="T_46124_row0_col2" class="data row0 col2" >0.55</td>
-      <td id="T_46124_row0_col3" class="data row0 col3" >0.18</td>
-      <td id="T_46124_row0_col4" class="data row0 col4" >0.00</td>
-      <td id="T_46124_row0_col5" class="data row0 col5" >0.00</td>
-      <td id="T_46124_row0_col6" class="data row0 col6" >0.79</td>
-      <td id="T_46124_row0_col7" class="data row0 col7" >0.06</td>
-      <td id="T_46124_row0_col8" class="data row0 col8" >0.18</td>
-      <td id="T_46124_row0_col9" class="data row0 col9" >10.85</td>
-    </tr>
-    <tr>
-      <th id="T_46124_level0_row1" class="row_heading level0 row1" >parc-des-pierrettes</th>
-      <td id="T_46124_row1_col0" class="data row1 col0" >0.08</td>
-      <td id="T_46124_row1_col1" class="data row1 col1" >1.03</td>
-      <td id="T_46124_row1_col2" class="data row1 col2" >0.14</td>
-      <td id="T_46124_row1_col3" class="data row1 col3" >0.04</td>
-      <td id="T_46124_row1_col4" class="data row1 col4" >0.00</td>
-      <td id="T_46124_row1_col5" class="data row1 col5" >0.00</td>
-      <td id="T_46124_row1_col6" class="data row1 col6" >0.24</td>
-      <td id="T_46124_row1_col7" class="data row1 col7" >0.02</td>
-      <td id="T_46124_row1_col8" class="data row1 col8" >0.24</td>
-      <td id="T_46124_row1_col9" class="data row1 col9" >5.40</td>
+      <th id="T_075e0_level0_row0" class="row_heading level0 row0" >tiger-duck-beach</th>
+      <td id="T_075e0_row0_col0" class="data row0 col0" >0.67</td>
+      <td id="T_075e0_row0_col1" class="data row0 col1" >3.64</td>
+      <td id="T_075e0_row0_col2" class="data row0 col2" >0.55</td>
+      <td id="T_075e0_row0_col3" class="data row0 col3" >0.18</td>
+      <td id="T_075e0_row0_col4" class="data row0 col4" >0.00</td>
+      <td id="T_075e0_row0_col5" class="data row0 col5" >0.00</td>
+      <td id="T_075e0_row0_col6" class="data row0 col6" >0.79</td>
+      <td id="T_075e0_row0_col7" class="data row0 col7" >0.06</td>
+      <td id="T_075e0_row0_col8" class="data row0 col8" >0.18</td>
+      <td id="T_075e0_row0_col9" class="data row0 col9" >10.85</td>
+    </tr>
+    <tr>
+      <th id="T_075e0_level0_row1" class="row_heading level0 row1" >parc-des-pierrettes</th>
+      <td id="T_075e0_row1_col0" class="data row1 col0" >0.08</td>
+      <td id="T_075e0_row1_col1" class="data row1 col1" >1.03</td>
+      <td id="T_075e0_row1_col2" class="data row1 col2" >0.14</td>
+      <td id="T_075e0_row1_col3" class="data row1 col3" >0.04</td>
+      <td id="T_075e0_row1_col4" class="data row1 col4" >0.00</td>
+      <td id="T_075e0_row1_col5" class="data row1 col5" >0.00</td>
+      <td id="T_075e0_row1_col6" class="data row1 col6" >0.24</td>
+      <td id="T_075e0_row1_col7" class="data row1 col7" >0.02</td>
+      <td id="T_075e0_row1_col8" class="data row1 col8" >0.24</td>
+      <td id="T_075e0_row1_col9" class="data row1 col9" >5.40</td>
     </tr>
   </tbody>
 </table>
@@ -1657,7 +1284,7 @@ <h2><span class="section-number">3.6. </span>Results: Estimated, found and predi
 </tr>
 </thead>
 <tbody>
-<tr class="row-even"><td class="text-center"><p><img alt="_images/5f56302bedbd28c12ef38d5cf2f3c7abb0bd6ee7496fb1c9f71718a65c2dfa91.png" src="_images/5f56302bedbd28c12ef38d5cf2f3c7abb0bd6ee7496fb1c9f71718a65c2dfa91.png" /></p></td>
+<tr class="row-even"><td class="text-center"><p><img alt="_images/3b10867ba4b3bf65b1dee903696e5accfa2c51ba007dd2cfe381a0658d975cc4.png" src="_images/3b10867ba4b3bf65b1dee903696e5accfa2c51ba007dd2cfe381a0658d975cc4.png" /></p></td>
 </tr>
 <tr class="row-odd"><td class="text-center"><p>Figure 3: <em>The Estimated, observed and predicted results for the objects of interest, Saint Sulpice October 5, 2023</em></p></td>
 </tr>
@@ -1682,7 +1309,7 @@ <h2><span class="section-number">3.6. </span>Results: Estimated, found and predi
 </tr>
 </thead>
 <tbody>
-<tr class="row-even"><td class="text-center"><p><img alt="_images/a17b221991c8fe26eb7f6c3320065aff20d9460441e62fe8c1e0623ccdeb4808.png" src="_images/a17b221991c8fe26eb7f6c3320065aff20d9460441e62fe8c1e0623ccdeb4808.png" /></p></td>
+<tr class="row-even"><td class="text-center"><p><img alt="_images/44661da8d7b6632d7323190eded41307ef7514e245c37c044cb00987aa2adae3.png" src="_images/44661da8d7b6632d7323190eded41307ef7514e245c37c044cb00987aa2adae3.png" /></p></td>
 </tr>
 <tr class="row-odd"><td class="text-center"><p>Figure 4: <em>The root of the squared difference between observed estimated and predicted, Saint Sulpice October 5, 2023</em></p></td>
 </tr>
@@ -1691,21 +1318,21 @@ <h2><span class="section-number">3.6. </span>Results: Estimated, found and predi
 <div class="cell tag_remove-input docutils container">
 <div class="cell_output docutils container">
 <div class="output text_html"><style type="text/css">
-#T_a043f tr:nth-child(even) {
+#T_565a7 tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_a043f tr:nth-child(odd) {
+#T_565a7 tr:nth-child(odd) {
   background: #FFF;
 }
-#T_a043f tr {
+#T_565a7 tr {
   font-size: 14px;
   padding: 12px;
 }
-#T_a043f th:nth-child(1) {
+#T_565a7 th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_a043f caption {
+#T_565a7 caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -1713,69 +1340,69 @@ <h2><span class="section-number">3.6. </span>Results: Estimated, found and predi
   margin-top: 10px;
 }
 </style>
-<table id="T_a043f">
+<table id="T_565a7">
   <caption>Table 7: The average difference between what was found and the estimates of the participants and what was predicted using the empirical Bayes method</caption>
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_a043f_level0_col0" class="col_heading level0 col0" colspan="2">average</th>
+      <th id="T_565a7_level0_col0" class="col_heading level0 col0" colspan="2">average</th>
     </tr>
     <tr>
       <th class="index_name level1" >source</th>
-      <th id="T_a043f_level1_col0" class="col_heading level1 col0" >difference² of estimated</th>
-      <th id="T_a043f_level1_col1" class="col_heading level1 col1" >difference² of predicted</th>
+      <th id="T_565a7_level1_col0" class="col_heading level1 col0" >difference² of estimated</th>
+      <th id="T_565a7_level1_col1" class="col_heading level1 col1" >difference² of predicted</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_a043f_level0_row0" class="row_heading level0 row0" >G112</th>
-      <td id="T_a043f_row0_col0" class="data row0 col0" >1.07</td>
-      <td id="T_a043f_row0_col1" class="data row0 col1" >0.29</td>
+      <th id="T_565a7_level0_row0" class="row_heading level0 row0" >G112</th>
+      <td id="T_565a7_row0_col0" class="data row0 col0" >1.07</td>
+      <td id="T_565a7_row0_col1" class="data row0 col1" >0.29</td>
     </tr>
     <tr>
-      <th id="T_a043f_level0_row1" class="row_heading level0 row1" >G27</th>
-      <td id="T_a043f_row1_col0" class="data row1 col0" >2.32</td>
-      <td id="T_a043f_row1_col1" class="data row1 col1" >1.89</td>
+      <th id="T_565a7_level0_row1" class="row_heading level0 row1" >G27</th>
+      <td id="T_565a7_row1_col0" class="data row1 col0" >2.32</td>
+      <td id="T_565a7_row1_col1" class="data row1 col1" >1.87</td>
     </tr>
     <tr>
-      <th id="T_a043f_level0_row2" class="row_heading level0 row2" >G30</th>
-      <td id="T_a043f_row2_col0" class="data row2 col0" >0.31</td>
-      <td id="T_a043f_row2_col1" class="data row2 col1" >0.21</td>
+      <th id="T_565a7_level0_row2" class="row_heading level0 row2" >G30</th>
+      <td id="T_565a7_row2_col0" class="data row2 col0" >0.31</td>
+      <td id="T_565a7_row2_col1" class="data row2 col1" >0.20</td>
     </tr>
     <tr>
-      <th id="T_a043f_level0_row3" class="row_heading level0 row3" >G32</th>
-      <td id="T_a043f_row3_col0" class="data row3 col0" >0.11</td>
-      <td id="T_a043f_row3_col1" class="data row3 col1" >0.07</td>
+      <th id="T_565a7_level0_row3" class="row_heading level0 row3" >G32</th>
+      <td id="T_565a7_row3_col0" class="data row3 col0" >0.11</td>
+      <td id="T_565a7_row3_col1" class="data row3 col1" >0.07</td>
     </tr>
     <tr>
-      <th id="T_a043f_level0_row4" class="row_heading level0 row4" >G67</th>
-      <td id="T_a043f_row4_col0" class="data row4 col0" >0.26</td>
-      <td id="T_a043f_row4_col1" class="data row4 col1" >0.16</td>
+      <th id="T_565a7_level0_row4" class="row_heading level0 row4" >G67</th>
+      <td id="T_565a7_row4_col0" class="data row4 col0" >0.26</td>
+      <td id="T_565a7_row4_col1" class="data row4 col1" >0.16</td>
     </tr>
     <tr>
-      <th id="T_a043f_level0_row5" class="row_heading level0 row5" >G70</th>
-      <td id="T_a043f_row5_col0" class="data row5 col0" >0.03</td>
-      <td id="T_a043f_row5_col1" class="data row5 col1" >0.00</td>
+      <th id="T_565a7_level0_row5" class="row_heading level0 row5" >G70</th>
+      <td id="T_565a7_row5_col0" class="data row5 col0" >0.03</td>
+      <td id="T_565a7_row5_col1" class="data row5 col1" >0.01</td>
     </tr>
     <tr>
-      <th id="T_a043f_level0_row6" class="row_heading level0 row6" >G95</th>
-      <td id="T_a043f_row6_col0" class="data row6 col0" >0.52</td>
-      <td id="T_a043f_row6_col1" class="data row6 col1" >0.27</td>
+      <th id="T_565a7_level0_row6" class="row_heading level0 row6" >G95</th>
+      <td id="T_565a7_row6_col0" class="data row6 col0" >0.52</td>
+      <td id="T_565a7_row6_col1" class="data row6 col1" >0.27</td>
     </tr>
     <tr>
-      <th id="T_a043f_level0_row7" class="row_heading level0 row7" >G96</th>
-      <td id="T_a043f_row7_col0" class="data row7 col0" >0.15</td>
-      <td id="T_a043f_row7_col1" class="data row7 col1" >0.05</td>
+      <th id="T_565a7_level0_row7" class="row_heading level0 row7" >G96</th>
+      <td id="T_565a7_row7_col0" class="data row7 col0" >0.15</td>
+      <td id="T_565a7_row7_col1" class="data row7 col1" >0.02</td>
     </tr>
     <tr>
-      <th id="T_a043f_level0_row8" class="row_heading level0 row8" >Gcaps</th>
-      <td id="T_a043f_row8_col0" class="data row8 col0" >0.26</td>
-      <td id="T_a043f_row8_col1" class="data row8 col1" >0.07</td>
+      <th id="T_565a7_level0_row8" class="row_heading level0 row8" >Gcaps</th>
+      <td id="T_565a7_row8_col0" class="data row8 col0" >0.26</td>
+      <td id="T_565a7_row8_col1" class="data row8 col1" >0.10</td>
     </tr>
     <tr>
-      <th id="T_a043f_level0_row9" class="row_heading level0 row9" >Gfrags</th>
-      <td id="T_a043f_row9_col0" class="data row9 col0" >8.11</td>
-      <td id="T_a043f_row9_col1" class="data row9 col1" >7.71</td>
+      <th id="T_565a7_level0_row9" class="row_heading level0 row9" >Gfrags</th>
+      <td id="T_565a7_row9_col0" class="data row9 col0" >8.11</td>
+      <td id="T_565a7_row9_col1" class="data row9 col1" >7.38</td>
     </tr>
   </tbody>
 </table>
@@ -1804,21 +1431,21 @@ <h3><span class="section-number">3.9.1. </span>The accuracy of the predictions i
 <div class="cell tag_remove-input docutils container">
 <div class="cell_output docutils container">
 <div class="output text_html"><style type="text/css">
-#T_368fb tr:nth-child(even) {
+#T_5cefd tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_368fb tr:nth-child(odd) {
+#T_5cefd tr:nth-child(odd) {
   background: #FFF;
 }
-#T_368fb tr {
+#T_5cefd tr {
   font-size: 14px;
   padding: 12px;
 }
-#T_368fb th:nth-child(1) {
+#T_5cefd th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_368fb caption {
+#T_5cefd caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -1826,136 +1453,136 @@ <h3><span class="section-number">3.9.1. </span>The accuracy of the predictions i
   margin-top: 10px;
 }
 </style>
-<table id="T_368fb">
+<table id="T_5cefd">
   <caption>Table 8: Whether the observed value fell within the predicted interval</caption>
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_368fb_level0_col0" class="col_heading level0 col0" >object</th>
-      <th id="T_368fb_level0_col1" class="col_heading level0 col1" >within 96% HDI</th>
-      <th id="T_368fb_level0_col2" class="col_heading level0 col2" >within 50% HDI</th>
+      <th id="T_5cefd_level0_col0" class="col_heading level0 col0" >object</th>
+      <th id="T_5cefd_level0_col1" class="col_heading level0 col1" >within 96% HDI</th>
+      <th id="T_5cefd_level0_col2" class="col_heading level0 col2" >within 50% HDI</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_368fb_level0_row0" class="row_heading level0 row0" >0</th>
-      <td id="T_368fb_row0_col0" class="data row0 col0" >G112</td>
-      <td id="T_368fb_row0_col1" class="data row0 col1" >True</td>
-      <td id="T_368fb_row0_col2" class="data row0 col2" >False</td>
+      <th id="T_5cefd_level0_row0" class="row_heading level0 row0" >0</th>
+      <td id="T_5cefd_row0_col0" class="data row0 col0" >G112</td>
+      <td id="T_5cefd_row0_col1" class="data row0 col1" >True</td>
+      <td id="T_5cefd_row0_col2" class="data row0 col2" >True</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row1" class="row_heading level0 row1" >1</th>
-      <td id="T_368fb_row1_col0" class="data row1 col0" >G27</td>
-      <td id="T_368fb_row1_col1" class="data row1 col1" >False</td>
-      <td id="T_368fb_row1_col2" class="data row1 col2" >False</td>
+      <th id="T_5cefd_level0_row1" class="row_heading level0 row1" >1</th>
+      <td id="T_5cefd_row1_col0" class="data row1 col0" >G27</td>
+      <td id="T_5cefd_row1_col1" class="data row1 col1" >False</td>
+      <td id="T_5cefd_row1_col2" class="data row1 col2" >False</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row2" class="row_heading level0 row2" >2</th>
-      <td id="T_368fb_row2_col0" class="data row2 col0" >G30</td>
-      <td id="T_368fb_row2_col1" class="data row2 col1" >True</td>
-      <td id="T_368fb_row2_col2" class="data row2 col2" >False</td>
+      <th id="T_5cefd_level0_row2" class="row_heading level0 row2" >2</th>
+      <td id="T_5cefd_row2_col0" class="data row2 col0" >G30</td>
+      <td id="T_5cefd_row2_col1" class="data row2 col1" >True</td>
+      <td id="T_5cefd_row2_col2" class="data row2 col2" >True</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row3" class="row_heading level0 row3" >3</th>
-      <td id="T_368fb_row3_col0" class="data row3 col0" >G32</td>
-      <td id="T_368fb_row3_col1" class="data row3 col1" >False</td>
-      <td id="T_368fb_row3_col2" class="data row3 col2" >False</td>
+      <th id="T_5cefd_level0_row3" class="row_heading level0 row3" >3</th>
+      <td id="T_5cefd_row3_col0" class="data row3 col0" >G32</td>
+      <td id="T_5cefd_row3_col1" class="data row3 col1" >False</td>
+      <td id="T_5cefd_row3_col2" class="data row3 col2" >False</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row4" class="row_heading level0 row4" >4</th>
-      <td id="T_368fb_row4_col0" class="data row4 col0" >G67</td>
-      <td id="T_368fb_row4_col1" class="data row4 col1" >True</td>
-      <td id="T_368fb_row4_col2" class="data row4 col2" >False</td>
+      <th id="T_5cefd_level0_row4" class="row_heading level0 row4" >4</th>
+      <td id="T_5cefd_row4_col0" class="data row4 col0" >G67</td>
+      <td id="T_5cefd_row4_col1" class="data row4 col1" >True</td>
+      <td id="T_5cefd_row4_col2" class="data row4 col2" >False</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row5" class="row_heading level0 row5" >5</th>
-      <td id="T_368fb_row5_col0" class="data row5 col0" >G70</td>
-      <td id="T_368fb_row5_col1" class="data row5 col1" >True</td>
-      <td id="T_368fb_row5_col2" class="data row5 col2" >False</td>
+      <th id="T_5cefd_level0_row5" class="row_heading level0 row5" >5</th>
+      <td id="T_5cefd_row5_col0" class="data row5 col0" >G70</td>
+      <td id="T_5cefd_row5_col1" class="data row5 col1" >True</td>
+      <td id="T_5cefd_row5_col2" class="data row5 col2" >False</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row6" class="row_heading level0 row6" >6</th>
-      <td id="T_368fb_row6_col0" class="data row6 col0" >G95</td>
-      <td id="T_368fb_row6_col1" class="data row6 col1" >True</td>
-      <td id="T_368fb_row6_col2" class="data row6 col2" >False</td>
+      <th id="T_5cefd_level0_row6" class="row_heading level0 row6" >6</th>
+      <td id="T_5cefd_row6_col0" class="data row6 col0" >G95</td>
+      <td id="T_5cefd_row6_col1" class="data row6 col1" >True</td>
+      <td id="T_5cefd_row6_col2" class="data row6 col2" >False</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row7" class="row_heading level0 row7" >7</th>
-      <td id="T_368fb_row7_col0" class="data row7 col0" >G96</td>
-      <td id="T_368fb_row7_col1" class="data row7 col1" >True</td>
-      <td id="T_368fb_row7_col2" class="data row7 col2" >True</td>
+      <th id="T_5cefd_level0_row7" class="row_heading level0 row7" >7</th>
+      <td id="T_5cefd_row7_col0" class="data row7 col0" >G96</td>
+      <td id="T_5cefd_row7_col1" class="data row7 col1" >True</td>
+      <td id="T_5cefd_row7_col2" class="data row7 col2" >True</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row8" class="row_heading level0 row8" >8</th>
-      <td id="T_368fb_row8_col0" class="data row8 col0" >Gcaps</td>
-      <td id="T_368fb_row8_col1" class="data row8 col1" >True</td>
-      <td id="T_368fb_row8_col2" class="data row8 col2" >True</td>
+      <th id="T_5cefd_level0_row8" class="row_heading level0 row8" >8</th>
+      <td id="T_5cefd_row8_col0" class="data row8 col0" >Gcaps</td>
+      <td id="T_5cefd_row8_col1" class="data row8 col1" >True</td>
+      <td id="T_5cefd_row8_col2" class="data row8 col2" >True</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row9" class="row_heading level0 row9" >9</th>
-      <td id="T_368fb_row9_col0" class="data row9 col0" >Gfrags</td>
-      <td id="T_368fb_row9_col1" class="data row9 col1" >False</td>
-      <td id="T_368fb_row9_col2" class="data row9 col2" >False</td>
+      <th id="T_5cefd_level0_row9" class="row_heading level0 row9" >9</th>
+      <td id="T_5cefd_row9_col0" class="data row9 col0" >Gfrags</td>
+      <td id="T_5cefd_row9_col1" class="data row9 col1" >False</td>
+      <td id="T_5cefd_row9_col2" class="data row9 col2" >False</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row10" class="row_heading level0 row10" >0</th>
-      <td id="T_368fb_row10_col0" class="data row10 col0" >G112</td>
-      <td id="T_368fb_row10_col1" class="data row10 col1" >True</td>
-      <td id="T_368fb_row10_col2" class="data row10 col2" >True</td>
+      <th id="T_5cefd_level0_row10" class="row_heading level0 row10" >0</th>
+      <td id="T_5cefd_row10_col0" class="data row10 col0" >G112</td>
+      <td id="T_5cefd_row10_col1" class="data row10 col1" >True</td>
+      <td id="T_5cefd_row10_col2" class="data row10 col2" >True</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row11" class="row_heading level0 row11" >1</th>
-      <td id="T_368fb_row11_col0" class="data row11 col0" >G27</td>
-      <td id="T_368fb_row11_col1" class="data row11 col1" >True</td>
-      <td id="T_368fb_row11_col2" class="data row11 col2" >False</td>
+      <th id="T_5cefd_level0_row11" class="row_heading level0 row11" >1</th>
+      <td id="T_5cefd_row11_col0" class="data row11 col0" >G27</td>
+      <td id="T_5cefd_row11_col1" class="data row11 col1" >True</td>
+      <td id="T_5cefd_row11_col2" class="data row11 col2" >False</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row12" class="row_heading level0 row12" >2</th>
-      <td id="T_368fb_row12_col0" class="data row12 col0" >G30</td>
-      <td id="T_368fb_row12_col1" class="data row12 col1" >True</td>
-      <td id="T_368fb_row12_col2" class="data row12 col2" >True</td>
+      <th id="T_5cefd_level0_row12" class="row_heading level0 row12" >2</th>
+      <td id="T_5cefd_row12_col0" class="data row12 col0" >G30</td>
+      <td id="T_5cefd_row12_col1" class="data row12 col1" >True</td>
+      <td id="T_5cefd_row12_col2" class="data row12 col2" >True</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row13" class="row_heading level0 row13" >3</th>
-      <td id="T_368fb_row13_col0" class="data row13 col0" >G32</td>
-      <td id="T_368fb_row13_col1" class="data row13 col1" >True</td>
-      <td id="T_368fb_row13_col2" class="data row13 col2" >True</td>
+      <th id="T_5cefd_level0_row13" class="row_heading level0 row13" >3</th>
+      <td id="T_5cefd_row13_col0" class="data row13 col0" >G32</td>
+      <td id="T_5cefd_row13_col1" class="data row13 col1" >True</td>
+      <td id="T_5cefd_row13_col2" class="data row13 col2" >True</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row14" class="row_heading level0 row14" >4</th>
-      <td id="T_368fb_row14_col0" class="data row14 col0" >G67</td>
-      <td id="T_368fb_row14_col1" class="data row14 col1" >True</td>
-      <td id="T_368fb_row14_col2" class="data row14 col2" >False</td>
+      <th id="T_5cefd_level0_row14" class="row_heading level0 row14" >4</th>
+      <td id="T_5cefd_row14_col0" class="data row14 col0" >G67</td>
+      <td id="T_5cefd_row14_col1" class="data row14 col1" >True</td>
+      <td id="T_5cefd_row14_col2" class="data row14 col2" >False</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row15" class="row_heading level0 row15" >5</th>
-      <td id="T_368fb_row15_col0" class="data row15 col0" >G70</td>
-      <td id="T_368fb_row15_col1" class="data row15 col1" >True</td>
-      <td id="T_368fb_row15_col2" class="data row15 col2" >False</td>
+      <th id="T_5cefd_level0_row15" class="row_heading level0 row15" >5</th>
+      <td id="T_5cefd_row15_col0" class="data row15 col0" >G70</td>
+      <td id="T_5cefd_row15_col1" class="data row15 col1" >True</td>
+      <td id="T_5cefd_row15_col2" class="data row15 col2" >False</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row16" class="row_heading level0 row16" >6</th>
-      <td id="T_368fb_row16_col0" class="data row16 col0" >G95</td>
-      <td id="T_368fb_row16_col1" class="data row16 col1" >True</td>
-      <td id="T_368fb_row16_col2" class="data row16 col2" >True</td>
+      <th id="T_5cefd_level0_row16" class="row_heading level0 row16" >6</th>
+      <td id="T_5cefd_row16_col0" class="data row16 col0" >G95</td>
+      <td id="T_5cefd_row16_col1" class="data row16 col1" >True</td>
+      <td id="T_5cefd_row16_col2" class="data row16 col2" >True</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row17" class="row_heading level0 row17" >7</th>
-      <td id="T_368fb_row17_col0" class="data row17 col0" >G96</td>
-      <td id="T_368fb_row17_col1" class="data row17 col1" >True</td>
-      <td id="T_368fb_row17_col2" class="data row17 col2" >True</td>
+      <th id="T_5cefd_level0_row17" class="row_heading level0 row17" >7</th>
+      <td id="T_5cefd_row17_col0" class="data row17 col0" >G96</td>
+      <td id="T_5cefd_row17_col1" class="data row17 col1" >True</td>
+      <td id="T_5cefd_row17_col2" class="data row17 col2" >True</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row18" class="row_heading level0 row18" >8</th>
-      <td id="T_368fb_row18_col0" class="data row18 col0" >Gcaps</td>
-      <td id="T_368fb_row18_col1" class="data row18 col1" >True</td>
-      <td id="T_368fb_row18_col2" class="data row18 col2" >False</td>
+      <th id="T_5cefd_level0_row18" class="row_heading level0 row18" >8</th>
+      <td id="T_5cefd_row18_col0" class="data row18 col0" >Gcaps</td>
+      <td id="T_5cefd_row18_col1" class="data row18 col1" >True</td>
+      <td id="T_5cefd_row18_col2" class="data row18 col2" >False</td>
     </tr>
     <tr>
-      <th id="T_368fb_level0_row19" class="row_heading level0 row19" >9</th>
-      <td id="T_368fb_row19_col0" class="data row19 col0" >Gfrags</td>
-      <td id="T_368fb_row19_col1" class="data row19 col1" >False</td>
-      <td id="T_368fb_row19_col2" class="data row19 col2" >False</td>
+      <th id="T_5cefd_level0_row19" class="row_heading level0 row19" >9</th>
+      <td id="T_5cefd_row19_col0" class="data row19 col0" >Gfrags</td>
+      <td id="T_5cefd_row19_col1" class="data row19 col1" >False</td>
+      <td id="T_5cefd_row19_col2" class="data row19 col2" >False</td>
     </tr>
   </tbody>
 </table>
@@ -1964,7 +1591,7 @@ <h3><span class="section-number">3.9.1. </span>The accuracy of the predictions i
 <div class="cell tag_remove-input docutils container">
 <div class="cell_output docutils container">
 <div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>within 96% HDI    0.80
-within 50% HDI    0.35
+within 50% HDI    0.45
 dtype: float64
 </pre></div>
 </div>
@@ -1973,7 +1600,7 @@ <h3><span class="section-number">3.9.1. </span>The accuracy of the predictions i
 <div class="cell tag_remove-input docutils container">
 <div class="cell_output docutils container">
 <div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>within 96% HDI    16
-within 50% HDI     7
+within 50% HDI     9
 dtype: int64
 </pre></div>
 </div>
@@ -1989,12 +1616,12 @@ <h3><span class="section-number">3.9.1. </span>The accuracy of the predictions i
 <div class="cell_output docutils container">
 <div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Git repo: https://github.com/hammerdirt-analyst/solid-waste-team.git
 
-Git branch: review
+Git branch: main
 
 pandas    : 2.0.3
+numpy     : 1.25.2
 matplotlib: 3.7.1
 seaborn   : 0.12.2
-numpy     : 1.25.2
 </pre></div>
 </div>
 </div>
diff --git a/docs/plastic_shotgun_wadding.html b/docs/plastic_shotgun_wadding.html
index f4adc3d..cc86e6c 100644
--- a/docs/plastic_shotgun_wadding.html
+++ b/docs/plastic_shotgun_wadding.html
@@ -359,20 +359,20 @@ <h2><span class="section-number">4.1. </span>Characteristics and weight of sampl
 <div class="sd-row sd-row-cols-1 sd-row-cols-xs-1 sd-row-cols-sm-1 sd-row-cols-md-1 sd-row-cols-lg-1 docutils">
 <div class="sd-col sd-d-flex-column docutils">
 <p><span class="output text_html"><style type="text/css">
-#T_c1fc0 tr:nth-child(even) {
+#T_09e96 tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_c1fc0 tr:nth-child(odd) {
+#T_09e96 tr:nth-child(odd) {
   background: #FFF;
 }
-#T_c1fc0 tr {
+#T_09e96 tr {
   font-size: 14px;
 }
-#T_c1fc0 th:nth-child(1) {
+#T_09e96 th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_c1fc0 caption {
+#T_09e96 caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -380,64 +380,64 @@ <h2><span class="section-number">4.1. </span>Characteristics and weight of sampl
   margin-top: 10px;
 }
 </style>
-<table id="T_c1fc0">
+<table id="T_09e96">
   <caption>Percent of samples collected with the designated land-use feature and category.</caption>
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_c1fc0_level0_col0" class="col_heading level0 col0" >orchards</th>
-      <th id="T_c1fc0_level0_col1" class="col_heading level0 col1" >vineyards</th>
-      <th id="T_c1fc0_level0_col2" class="col_heading level0 col2" >buildings</th>
-      <th id="T_c1fc0_level0_col3" class="col_heading level0 col3" >forest</th>
-      <th id="T_c1fc0_level0_col4" class="col_heading level0 col4" >undefined</th>
-      <th id="T_c1fc0_level0_col5" class="col_heading level0 col5" >public_services</th>
+      <th id="T_09e96_level0_col0" class="col_heading level0 col0" >orchards</th>
+      <th id="T_09e96_level0_col1" class="col_heading level0 col1" >vineyards</th>
+      <th id="T_09e96_level0_col2" class="col_heading level0 col2" >buildings</th>
+      <th id="T_09e96_level0_col3" class="col_heading level0 col3" >forest</th>
+      <th id="T_09e96_level0_col4" class="col_heading level0 col4" >undefined</th>
+      <th id="T_09e96_level0_col5" class="col_heading level0 col5" >public_services</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_c1fc0_level0_row0" class="row_heading level0 row0" >1</th>
-      <td id="T_c1fc0_row0_col0" class="data row0 col0" >91%</td>
-      <td id="T_c1fc0_row0_col1" class="data row0 col1" >92%</td>
-      <td id="T_c1fc0_row0_col2" class="data row0 col2" >11%</td>
-      <td id="T_c1fc0_row0_col3" class="data row0 col3" >72%</td>
-      <td id="T_c1fc0_row0_col4" class="data row0 col4" >63%</td>
-      <td id="T_c1fc0_row0_col5" class="data row0 col5" >68%</td>
-    </tr>
-    <tr>
-      <th id="T_c1fc0_level0_row1" class="row_heading level0 row1" >2</th>
-      <td id="T_c1fc0_row1_col0" class="data row1 col0" >6%</td>
-      <td id="T_c1fc0_row1_col1" class="data row1 col1" >7%</td>
-      <td id="T_c1fc0_row1_col2" class="data row1 col2" >6%</td>
-      <td id="T_c1fc0_row1_col3" class="data row1 col3" >14%</td>
-      <td id="T_c1fc0_row1_col4" class="data row1 col4" >25%</td>
-      <td id="T_c1fc0_row1_col5" class="data row1 col5" >7%</td>
-    </tr>
-    <tr>
-      <th id="T_c1fc0_level0_row2" class="row_heading level0 row2" >3</th>
-      <td id="T_c1fc0_row2_col0" class="data row2 col0" >0%</td>
-      <td id="T_c1fc0_row2_col1" class="data row2 col1" >0%</td>
-      <td id="T_c1fc0_row2_col2" class="data row2 col2" >1%</td>
-      <td id="T_c1fc0_row2_col3" class="data row2 col3" >0%</td>
-      <td id="T_c1fc0_row2_col4" class="data row2 col4" >1%</td>
-      <td id="T_c1fc0_row2_col5" class="data row2 col5" >7%</td>
-    </tr>
-    <tr>
-      <th id="T_c1fc0_level0_row3" class="row_heading level0 row3" >4</th>
-      <td id="T_c1fc0_row3_col0" class="data row3 col0" >1%</td>
-      <td id="T_c1fc0_row3_col1" class="data row3 col1" >0%</td>
-      <td id="T_c1fc0_row3_col2" class="data row3 col2" >20%</td>
-      <td id="T_c1fc0_row3_col3" class="data row3 col3" >9%</td>
-      <td id="T_c1fc0_row3_col4" class="data row3 col4" >2%</td>
-      <td id="T_c1fc0_row3_col5" class="data row3 col5" >8%</td>
-    </tr>
-    <tr>
-      <th id="T_c1fc0_level0_row4" class="row_heading level0 row4" >5</th>
-      <td id="T_c1fc0_row4_col0" class="data row4 col0" >1%</td>
-      <td id="T_c1fc0_row4_col1" class="data row4 col1" >1%</td>
-      <td id="T_c1fc0_row4_col2" class="data row4 col2" >62%</td>
-      <td id="T_c1fc0_row4_col3" class="data row4 col3" >5%</td>
-      <td id="T_c1fc0_row4_col4" class="data row4 col4" >9%</td>
-      <td id="T_c1fc0_row4_col5" class="data row4 col5" >10%</td>
+      <th id="T_09e96_level0_row0" class="row_heading level0 row0" >1</th>
+      <td id="T_09e96_row0_col0" class="data row0 col0" >91%</td>
+      <td id="T_09e96_row0_col1" class="data row0 col1" >92%</td>
+      <td id="T_09e96_row0_col2" class="data row0 col2" >11%</td>
+      <td id="T_09e96_row0_col3" class="data row0 col3" >72%</td>
+      <td id="T_09e96_row0_col4" class="data row0 col4" >63%</td>
+      <td id="T_09e96_row0_col5" class="data row0 col5" >68%</td>
+    </tr>
+    <tr>
+      <th id="T_09e96_level0_row1" class="row_heading level0 row1" >2</th>
+      <td id="T_09e96_row1_col0" class="data row1 col0" >6%</td>
+      <td id="T_09e96_row1_col1" class="data row1 col1" >7%</td>
+      <td id="T_09e96_row1_col2" class="data row1 col2" >6%</td>
+      <td id="T_09e96_row1_col3" class="data row1 col3" >14%</td>
+      <td id="T_09e96_row1_col4" class="data row1 col4" >25%</td>
+      <td id="T_09e96_row1_col5" class="data row1 col5" >7%</td>
+    </tr>
+    <tr>
+      <th id="T_09e96_level0_row2" class="row_heading level0 row2" >3</th>
+      <td id="T_09e96_row2_col0" class="data row2 col0" >0%</td>
+      <td id="T_09e96_row2_col1" class="data row2 col1" >0%</td>
+      <td id="T_09e96_row2_col2" class="data row2 col2" >1%</td>
+      <td id="T_09e96_row2_col3" class="data row2 col3" >0%</td>
+      <td id="T_09e96_row2_col4" class="data row2 col4" >1%</td>
+      <td id="T_09e96_row2_col5" class="data row2 col5" >7%</td>
+    </tr>
+    <tr>
+      <th id="T_09e96_level0_row3" class="row_heading level0 row3" >4</th>
+      <td id="T_09e96_row3_col0" class="data row3 col0" >1%</td>
+      <td id="T_09e96_row3_col1" class="data row3 col1" >0%</td>
+      <td id="T_09e96_row3_col2" class="data row3 col2" >20%</td>
+      <td id="T_09e96_row3_col3" class="data row3 col3" >9%</td>
+      <td id="T_09e96_row3_col4" class="data row3 col4" >2%</td>
+      <td id="T_09e96_row3_col5" class="data row3 col5" >8%</td>
+    </tr>
+    <tr>
+      <th id="T_09e96_level0_row4" class="row_heading level0 row4" >5</th>
+      <td id="T_09e96_row4_col0" class="data row4 col0" >1%</td>
+      <td id="T_09e96_row4_col1" class="data row4 col1" >1%</td>
+      <td id="T_09e96_row4_col2" class="data row4 col2" >62%</td>
+      <td id="T_09e96_row4_col3" class="data row4 col3" >5%</td>
+      <td id="T_09e96_row4_col4" class="data row4 col4" >9%</td>
+      <td id="T_09e96_row4_col5" class="data row4 col5" >10%</td>
     </tr>
   </tbody>
 </table>
@@ -445,20 +445,20 @@ <h2><span class="section-number">4.1. </span>Characteristics and weight of sampl
 </div>
 <div class="sd-col sd-d-flex-column docutils">
 <p><span class="output text_html"><style type="text/css">
-#T_c091a tr:nth-child(even) {
+#T_1cbf2 tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_c091a tr:nth-child(odd) {
+#T_1cbf2 tr:nth-child(odd) {
   background: #FFF;
 }
-#T_c091a tr {
+#T_1cbf2 tr {
   font-size: 14px;
 }
-#T_c091a th:nth-child(1) {
+#T_1cbf2 th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_c091a caption {
+#T_1cbf2 caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -466,64 +466,64 @@ <h2><span class="section-number">4.1. </span>Characteristics and weight of sampl
   margin-top: 10px;
 }
 </style>
-<table id="T_c091a">
+<table id="T_1cbf2">
   <caption>The average number of shotgun shells per linear meter of shoreline by feature and category.</caption>
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_c091a_level0_col0" class="col_heading level0 col0" >buildings</th>
-      <th id="T_c091a_level0_col1" class="col_heading level0 col1" >forest</th>
-      <th id="T_c091a_level0_col2" class="col_heading level0 col2" >orchards</th>
-      <th id="T_c091a_level0_col3" class="col_heading level0 col3" >public_services</th>
-      <th id="T_c091a_level0_col4" class="col_heading level0 col4" >undefined</th>
-      <th id="T_c091a_level0_col5" class="col_heading level0 col5" >vineyards</th>
+      <th id="T_1cbf2_level0_col0" class="col_heading level0 col0" >buildings</th>
+      <th id="T_1cbf2_level0_col1" class="col_heading level0 col1" >forest</th>
+      <th id="T_1cbf2_level0_col2" class="col_heading level0 col2" >orchards</th>
+      <th id="T_1cbf2_level0_col3" class="col_heading level0 col3" >public_services</th>
+      <th id="T_1cbf2_level0_col4" class="col_heading level0 col4" >undefined</th>
+      <th id="T_1cbf2_level0_col5" class="col_heading level0 col5" >vineyards</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_c091a_level0_row0" class="row_heading level0 row0" >1</th>
-      <td id="T_c091a_row0_col0" class="data row0 col0" >0.03</td>
-      <td id="T_c091a_row0_col1" class="data row0 col1" >0.08</td>
-      <td id="T_c091a_row0_col2" class="data row0 col2" >0.11</td>
-      <td id="T_c091a_row0_col3" class="data row0 col3" >0.13</td>
-      <td id="T_c091a_row0_col4" class="data row0 col4" >0.09</td>
-      <td id="T_c091a_row0_col5" class="data row0 col5" >0.10</td>
-    </tr>
-    <tr>
-      <th id="T_c091a_level0_row1" class="row_heading level0 row1" >2</th>
-      <td id="T_c091a_row1_col0" class="data row1 col0" >0.59</td>
-      <td id="T_c091a_row1_col1" class="data row1 col1" >0.06</td>
-      <td id="T_c091a_row1_col2" class="data row1 col2" >0.01</td>
-      <td id="T_c091a_row1_col3" class="data row1 col3" >0.12</td>
-      <td id="T_c091a_row1_col4" class="data row1 col4" >0.18</td>
-      <td id="T_c091a_row1_col5" class="data row1 col5" >0.08</td>
-    </tr>
-    <tr>
-      <th id="T_c091a_level0_row2" class="row_heading level0 row2" >3</th>
-      <td id="T_c091a_row2_col0" class="data row2 col0" >0.00</td>
-      <td id="T_c091a_row2_col1" class="data row2 col1" >-</td>
-      <td id="T_c091a_row2_col2" class="data row2 col2" >0.00</td>
-      <td id="T_c091a_row2_col3" class="data row2 col3" >0.01</td>
-      <td id="T_c091a_row2_col4" class="data row2 col4" >0.08</td>
-      <td id="T_c091a_row2_col5" class="data row2 col5" >-</td>
-    </tr>
-    <tr>
-      <th id="T_c091a_level0_row3" class="row_heading level0 row3" >4</th>
-      <td id="T_c091a_row3_col0" class="data row3 col0" >0.04</td>
-      <td id="T_c091a_row3_col1" class="data row3 col1" >0.00</td>
-      <td id="T_c091a_row3_col2" class="data row3 col2" >0.01</td>
-      <td id="T_c091a_row3_col3" class="data row3 col3" >0.03</td>
-      <td id="T_c091a_row3_col4" class="data row3 col4" >0.09</td>
-      <td id="T_c091a_row3_col5" class="data row3 col5" >0.00</td>
-    </tr>
-    <tr>
-      <th id="T_c091a_level0_row4" class="row_heading level0 row4" >5</th>
-      <td id="T_c091a_row4_col0" class="data row4 col0" >0.09</td>
-      <td id="T_c091a_row4_col1" class="data row4 col1" >0.68</td>
-      <td id="T_c091a_row4_col2" class="data row4 col2" >0.14</td>
-      <td id="T_c091a_row4_col3" class="data row4 col3" >0.03</td>
-      <td id="T_c091a_row4_col4" class="data row4 col4" >0.00</td>
-      <td id="T_c091a_row4_col5" class="data row4 col5" >0.12</td>
+      <th id="T_1cbf2_level0_row0" class="row_heading level0 row0" >1</th>
+      <td id="T_1cbf2_row0_col0" class="data row0 col0" >0.03</td>
+      <td id="T_1cbf2_row0_col1" class="data row0 col1" >0.08</td>
+      <td id="T_1cbf2_row0_col2" class="data row0 col2" >0.11</td>
+      <td id="T_1cbf2_row0_col3" class="data row0 col3" >0.13</td>
+      <td id="T_1cbf2_row0_col4" class="data row0 col4" >0.09</td>
+      <td id="T_1cbf2_row0_col5" class="data row0 col5" >0.10</td>
+    </tr>
+    <tr>
+      <th id="T_1cbf2_level0_row1" class="row_heading level0 row1" >2</th>
+      <td id="T_1cbf2_row1_col0" class="data row1 col0" >0.59</td>
+      <td id="T_1cbf2_row1_col1" class="data row1 col1" >0.06</td>
+      <td id="T_1cbf2_row1_col2" class="data row1 col2" >0.01</td>
+      <td id="T_1cbf2_row1_col3" class="data row1 col3" >0.12</td>
+      <td id="T_1cbf2_row1_col4" class="data row1 col4" >0.18</td>
+      <td id="T_1cbf2_row1_col5" class="data row1 col5" >0.08</td>
+    </tr>
+    <tr>
+      <th id="T_1cbf2_level0_row2" class="row_heading level0 row2" >3</th>
+      <td id="T_1cbf2_row2_col0" class="data row2 col0" >0.00</td>
+      <td id="T_1cbf2_row2_col1" class="data row2 col1" >-</td>
+      <td id="T_1cbf2_row2_col2" class="data row2 col2" >0.00</td>
+      <td id="T_1cbf2_row2_col3" class="data row2 col3" >0.01</td>
+      <td id="T_1cbf2_row2_col4" class="data row2 col4" >0.08</td>
+      <td id="T_1cbf2_row2_col5" class="data row2 col5" >-</td>
+    </tr>
+    <tr>
+      <th id="T_1cbf2_level0_row3" class="row_heading level0 row3" >4</th>
+      <td id="T_1cbf2_row3_col0" class="data row3 col0" >0.04</td>
+      <td id="T_1cbf2_row3_col1" class="data row3 col1" >0.00</td>
+      <td id="T_1cbf2_row3_col2" class="data row3 col2" >0.01</td>
+      <td id="T_1cbf2_row3_col3" class="data row3 col3" >0.03</td>
+      <td id="T_1cbf2_row3_col4" class="data row3 col4" >0.09</td>
+      <td id="T_1cbf2_row3_col5" class="data row3 col5" >0.00</td>
+    </tr>
+    <tr>
+      <th id="T_1cbf2_level0_row4" class="row_heading level0 row4" >5</th>
+      <td id="T_1cbf2_row4_col0" class="data row4 col0" >0.09</td>
+      <td id="T_1cbf2_row4_col1" class="data row4 col1" >0.68</td>
+      <td id="T_1cbf2_row4_col2" class="data row4 col2" >0.14</td>
+      <td id="T_1cbf2_row4_col3" class="data row4 col3" >0.03</td>
+      <td id="T_1cbf2_row4_col4" class="data row4 col4" >0.00</td>
+      <td id="T_1cbf2_row4_col5" class="data row4 col5" >0.12</td>
     </tr>
   </tbody>
 </table>
@@ -559,20 +559,20 @@ <h2><span class="section-number">4.2. </span>Regional results<a class="headerlin
 <div class="sd-row sd-row-cols-1 sd-row-cols-xs-1 sd-row-cols-sm-1 sd-row-cols-md-1 sd-row-cols-lg-1 docutils">
 <div class="sd-col sd-d-flex-column docutils">
 <p><span class="output text_html"><style type="text/css">
-#T_620b2 tr:nth-child(even) {
+#T_94f7e tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_620b2 tr:nth-child(odd) {
+#T_94f7e tr:nth-child(odd) {
   background: #FFF;
 }
-#T_620b2 tr {
+#T_94f7e tr {
   font-size: 14px;
 }
-#T_620b2 th:nth-child(1) {
+#T_94f7e th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_620b2 caption {
+#T_94f7e caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -580,54 +580,54 @@ <h2><span class="section-number">4.2. </span>Regional results<a class="headerlin
   margin-top: 10px;
 }
 </style>
-<table id="T_620b2">
+<table id="T_94f7e">
   <caption>The distribution of the number of shotgun wadding found per meter of shoreline</caption>
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_620b2_level0_col0" class="col_heading level0 col0" >nsamples</th>
-      <th id="T_620b2_level0_col1" class="col_heading level0 col1" >mean</th>
-      <th id="T_620b2_level0_col2" class="col_heading level0 col2" >std</th>
-      <th id="T_620b2_level0_col3" class="col_heading level0 col3" >min</th>
-      <th id="T_620b2_level0_col4" class="col_heading level0 col4" >25%</th>
-      <th id="T_620b2_level0_col5" class="col_heading level0 col5" >50%</th>
-      <th id="T_620b2_level0_col6" class="col_heading level0 col6" >75%</th>
-      <th id="T_620b2_level0_col7" class="col_heading level0 col7" >max</th>
+      <th id="T_94f7e_level0_col0" class="col_heading level0 col0" >nsamples</th>
+      <th id="T_94f7e_level0_col1" class="col_heading level0 col1" >mean</th>
+      <th id="T_94f7e_level0_col2" class="col_heading level0 col2" >std</th>
+      <th id="T_94f7e_level0_col3" class="col_heading level0 col3" >min</th>
+      <th id="T_94f7e_level0_col4" class="col_heading level0 col4" >25%</th>
+      <th id="T_94f7e_level0_col5" class="col_heading level0 col5" >50%</th>
+      <th id="T_94f7e_level0_col6" class="col_heading level0 col6" >75%</th>
+      <th id="T_94f7e_level0_col7" class="col_heading level0 col7" >max</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_620b2_level0_row0" class="row_heading level0 row0" >Grand lac</th>
-      <td id="T_620b2_row0_col0" class="data row0 col0" >58.00</td>
-      <td id="T_620b2_row0_col1" class="data row0 col1" >0.03</td>
-      <td id="T_620b2_row0_col2" class="data row0 col2" >0.05</td>
-      <td id="T_620b2_row0_col3" class="data row0 col3" >0.00</td>
-      <td id="T_620b2_row0_col4" class="data row0 col4" >0.00</td>
-      <td id="T_620b2_row0_col5" class="data row0 col5" >0.00</td>
-      <td id="T_620b2_row0_col6" class="data row0 col6" >0.03</td>
-      <td id="T_620b2_row0_col7" class="data row0 col7" >0.22</td>
-    </tr>
-    <tr>
-      <th id="T_620b2_level0_row1" class="row_heading level0 row1" >Haut lac</th>
-      <td id="T_620b2_row1_col0" class="data row1 col0" >137.00</td>
-      <td id="T_620b2_row1_col1" class="data row1 col1" >0.17</td>
-      <td id="T_620b2_row1_col2" class="data row1 col2" >0.31</td>
-      <td id="T_620b2_row1_col3" class="data row1 col3" >0.00</td>
-      <td id="T_620b2_row1_col4" class="data row1 col4" >0.00</td>
-      <td id="T_620b2_row1_col5" class="data row1 col5" >0.05</td>
-      <td id="T_620b2_row1_col6" class="data row1 col6" >0.17</td>
-      <td id="T_620b2_row1_col7" class="data row1 col7" >1.64</td>
-    </tr>
-    <tr>
-      <th id="T_620b2_level0_row2" class="row_heading level0 row2" >Petit lac</th>
-      <td id="T_620b2_row2_col0" class="data row2 col0" >55.00</td>
-      <td id="T_620b2_row2_col1" class="data row2 col1" >0.02</td>
-      <td id="T_620b2_row2_col2" class="data row2 col2" >0.05</td>
-      <td id="T_620b2_row2_col3" class="data row2 col3" >0.00</td>
-      <td id="T_620b2_row2_col4" class="data row2 col4" >0.00</td>
-      <td id="T_620b2_row2_col5" class="data row2 col5" >0.00</td>
-      <td id="T_620b2_row2_col6" class="data row2 col6" >0.01</td>
-      <td id="T_620b2_row2_col7" class="data row2 col7" >0.30</td>
+      <th id="T_94f7e_level0_row0" class="row_heading level0 row0" >Grand lac</th>
+      <td id="T_94f7e_row0_col0" class="data row0 col0" >58.00</td>
+      <td id="T_94f7e_row0_col1" class="data row0 col1" >0.03</td>
+      <td id="T_94f7e_row0_col2" class="data row0 col2" >0.05</td>
+      <td id="T_94f7e_row0_col3" class="data row0 col3" >0.00</td>
+      <td id="T_94f7e_row0_col4" class="data row0 col4" >0.00</td>
+      <td id="T_94f7e_row0_col5" class="data row0 col5" >0.00</td>
+      <td id="T_94f7e_row0_col6" class="data row0 col6" >0.03</td>
+      <td id="T_94f7e_row0_col7" class="data row0 col7" >0.22</td>
+    </tr>
+    <tr>
+      <th id="T_94f7e_level0_row1" class="row_heading level0 row1" >Haut lac</th>
+      <td id="T_94f7e_row1_col0" class="data row1 col0" >137.00</td>
+      <td id="T_94f7e_row1_col1" class="data row1 col1" >0.17</td>
+      <td id="T_94f7e_row1_col2" class="data row1 col2" >0.31</td>
+      <td id="T_94f7e_row1_col3" class="data row1 col3" >0.00</td>
+      <td id="T_94f7e_row1_col4" class="data row1 col4" >0.00</td>
+      <td id="T_94f7e_row1_col5" class="data row1 col5" >0.05</td>
+      <td id="T_94f7e_row1_col6" class="data row1 col6" >0.17</td>
+      <td id="T_94f7e_row1_col7" class="data row1 col7" >1.64</td>
+    </tr>
+    <tr>
+      <th id="T_94f7e_level0_row2" class="row_heading level0 row2" >Petit lac</th>
+      <td id="T_94f7e_row2_col0" class="data row2 col0" >55.00</td>
+      <td id="T_94f7e_row2_col1" class="data row2 col1" >0.02</td>
+      <td id="T_94f7e_row2_col2" class="data row2 col2" >0.05</td>
+      <td id="T_94f7e_row2_col3" class="data row2 col3" >0.00</td>
+      <td id="T_94f7e_row2_col4" class="data row2 col4" >0.00</td>
+      <td id="T_94f7e_row2_col5" class="data row2 col5" >0.00</td>
+      <td id="T_94f7e_row2_col6" class="data row2 col6" >0.01</td>
+      <td id="T_94f7e_row2_col7" class="data row2 col7" >0.30</td>
     </tr>
   </tbody>
 </table>
@@ -652,20 +652,20 @@ <h2><span class="section-number">4.3. </span>Municipal results<a class="headerli
 <div class="cell tag_remove-input docutils container">
 <div class="cell_output docutils container">
 <div class="output text_html"><style type="text/css">
-#T_75ad1 tr:nth-child(even) {
+#T_92448 tr:nth-child(even) {
   background-color: rgba(139, 69, 19, 0.08);
 }
-#T_75ad1 tr:nth-child(odd) {
+#T_92448 tr:nth-child(odd) {
   background: #FFF;
 }
-#T_75ad1 tr {
+#T_92448 tr {
   font-size: 14px;
 }
-#T_75ad1 th:nth-child(1) {
+#T_92448 th:nth-child(1) {
   background-color: #FFF;
   text-align: right;
 }
-#T_75ad1 caption {
+#T_92448 caption {
   font-size: 14px;
   font-style: italic;
   caption-side: bottom;
@@ -673,94 +673,100 @@ <h2><span class="section-number">4.3. </span>Municipal results<a class="headerli
   margin-top: 10px;
 }
 </style>
-<table id="T_75ad1">
+<table id="T_92448">
   <thead>
     <tr>
       <th class="blank level0" >&nbsp;</th>
-      <th id="T_75ad1_level0_col0" class="col_heading level0 col0" >pcs/m</th>
-      <th id="T_75ad1_level0_col1" class="col_heading level0 col1" >nsamples</th>
+      <th id="T_92448_level0_col0" class="col_heading level0 col0" >pcs/m</th>
+      <th id="T_92448_level0_col1" class="col_heading level0 col1" >nsamples</th>
     </tr>
   </thead>
   <tbody>
     <tr>
-      <th id="T_75ad1_level0_row0" class="row_heading level0 row0" >Saint-Gingolph</th>
-      <td id="T_75ad1_row0_col0" class="data row0 col0" >0.68</td>
-      <td id="T_75ad1_row0_col1" class="data row0 col1" >13</td>
+      <th id="T_92448_level0_row0" class="row_heading level0 row0" >Saint-Gingolph</th>
+      <td id="T_92448_row0_col0" class="data row0 col0" >0.68</td>
+      <td id="T_92448_row0_col1" class="data row0 col1" >13</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row1" class="row_heading level0 row1" >Allaman</th>
-      <td id="T_75ad1_row1_col0" class="data row1 col0" >0.14</td>
-      <td id="T_75ad1_row1_col1" class="data row1 col1" >3</td>
+      <th id="T_92448_level0_row1" class="row_heading level0 row1" >Allaman</th>
+      <td id="T_92448_row1_col0" class="data row1 col0" >0.14</td>
+      <td id="T_92448_row1_col1" class="data row1 col1" >3</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row2" class="row_heading level0 row2" >Bourg-en-Lavaux</th>
-      <td id="T_75ad1_row2_col0" class="data row2 col0" >0.12</td>
-      <td id="T_75ad1_row2_col1" class="data row2 col1" >2</td>
+      <th id="T_92448_level0_row2" class="row_heading level0 row2" >Bourg-en-Lavaux</th>
+      <td id="T_92448_row2_col0" class="data row2 col0" >0.12</td>
+      <td id="T_92448_row2_col1" class="data row2 col1" >2</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row3" class="row_heading level0 row3" >La Tour-de-Peilz</th>
-      <td id="T_75ad1_row3_col0" class="data row3 col0" >0.12</td>
-      <td id="T_75ad1_row3_col1" class="data row3 col1" >25</td>
+      <th id="T_92448_level0_row3" class="row_heading level0 row3" >La Tour-de-Peilz</th>
+      <td id="T_92448_row3_col0" class="data row3 col0" >0.12</td>
+      <td id="T_92448_row3_col1" class="data row3 col1" >25</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row4" class="row_heading level0 row4" >Montreux</th>
-      <td id="T_75ad1_row4_col0" class="data row4 col0" >0.11</td>
-      <td id="T_75ad1_row4_col1" class="data row4 col1" >53</td>
+      <th id="T_92448_level0_row4" class="row_heading level0 row4" >Montreux</th>
+      <td id="T_92448_row4_col0" class="data row4 col0" >0.11</td>
+      <td id="T_92448_row4_col1" class="data row4 col1" >53</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row5" class="row_heading level0 row5" >Vevey</th>
-      <td id="T_75ad1_row5_col0" class="data row5 col0" >0.11</td>
-      <td id="T_75ad1_row5_col1" class="data row5 col1" >44</td>
+      <th id="T_92448_level0_row5" class="row_heading level0 row5" >Vevey</th>
+      <td id="T_92448_row5_col0" class="data row5 col0" >0.11</td>
+      <td id="T_92448_row5_col1" class="data row5 col1" >44</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row6" class="row_heading level0 row6" >Saint-Sulpice (VD)</th>
-      <td id="T_75ad1_row6_col0" class="data row6 col0" >0.06</td>
-      <td id="T_75ad1_row6_col1" class="data row6 col1" >15</td>
+      <th id="T_92448_level0_row6" class="row_heading level0 row6" >Saint-Sulpice (VD)</th>
+      <td id="T_92448_row6_col0" class="data row6 col0" >0.06</td>
+      <td id="T_92448_row6_col1" class="data row6 col1" >15</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row7" class="row_heading level0 row7" >Versoix</th>
-      <td id="T_75ad1_row7_col0" class="data row7 col0" >0.05</td>
-      <td id="T_75ad1_row7_col1" class="data row7 col1" >4</td>
+      <th id="T_92448_level0_row7" class="row_heading level0 row7" >Versoix</th>
+      <td id="T_92448_row7_col0" class="data row7 col0" >0.05</td>
+      <td id="T_92448_row7_col1" class="data row7 col1" >4</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row8" class="row_heading level0 row8" >Genève</th>
-      <td id="T_75ad1_row8_col0" class="data row8 col0" >0.03</td>
-      <td id="T_75ad1_row8_col1" class="data row8 col1" >29</td>
+      <th id="T_92448_level0_row8" class="row_heading level0 row8" >Genève</th>
+      <td id="T_92448_row8_col0" class="data row8 col0" >0.03</td>
+      <td id="T_92448_row8_col1" class="data row8 col1" >29</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row9" class="row_heading level0 row9" >Préverenges</th>
-      <td id="T_75ad1_row9_col0" class="data row9 col0" >0.01</td>
-      <td id="T_75ad1_row9_col1" class="data row9 col1" >15</td>
+      <th id="T_92448_level0_row9" class="row_heading level0 row9" >Préverenges</th>
+      <td id="T_92448_row9_col0" class="data row9 col0" >0.01</td>
+      <td id="T_92448_row9_col1" class="data row9 col1" >15</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row10" class="row_heading level0 row10" >Tolochenaz</th>
-      <td id="T_75ad1_row10_col0" class="data row10 col0" >0.01</td>
-      <td id="T_75ad1_row10_col1" class="data row10 col1" >3</td>
+      <th id="T_92448_level0_row10" class="row_heading level0 row10" >Tolochenaz</th>
+      <td id="T_92448_row10_col0" class="data row10 col0" >0.01</td>
+      <td id="T_92448_row10_col1" class="data row10 col1" >3</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row11" class="row_heading level0 row11" >Lausanne</th>
-      <td id="T_75ad1_row11_col0" class="data row11 col0" >0.01</td>
-      <td id="T_75ad1_row11_col1" class="data row11 col1" >20</td>
+      <th id="T_92448_level0_row11" class="row_heading level0 row11" >Lausanne</th>
+      <td id="T_92448_row11_col0" class="data row11 col0" >0.01</td>
+      <td id="T_92448_row11_col1" class="data row11 col1" >20</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row12" class="row_heading level0 row12" >Gland</th>
-      <td id="T_75ad1_row12_col0" class="data row12 col0" >0.00</td>
-      <td id="T_75ad1_row12_col1" class="data row12 col1" >22</td>
+      <th id="T_92448_level0_row12" class="row_heading level0 row12" >Gland</th>
+      <td id="T_92448_row12_col0" class="data row12 col0" >0.00</td>
+      <td id="T_92448_row12_col1" class="data row12 col1" >22</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row13" class="row_heading level0 row13" >Morges</th>
-      <td id="T_75ad1_row13_col0" class="data row13 col0" >0.00</td>
-      <td id="T_75ad1_row13_col1" class="data row13 col1" >1</td>
+      <th id="T_92448_level0_row13" class="row_heading level0 row13" >Morges</th>
+      <td id="T_92448_row13_col0" class="data row13 col0" >0.00</td>
+      <td id="T_92448_row13_col1" class="data row13 col1" >1</td>
     </tr>
     <tr>
-      <th id="T_75ad1_level0_row14" class="row_heading level0 row14" >Rolle</th>
-      <td id="T_75ad1_row14_col0" class="data row14 col0" >0.00</td>
-      <td id="T_75ad1_row14_col1" class="data row14 col1" >1</td>
+      <th id="T_92448_level0_row14" class="row_heading level0 row14" >Rolle</th>
+      <td id="T_92448_row14_col0" class="data row14 col0" >0.00</td>
+      <td id="T_92448_row14_col1" class="data row14 col1" >1</td>
     </tr>
   </tbody>
 </table>
 </div></div>
 </div>
+<div class="cell tag_remove-input docutils container">
+<div class="cell_output docutils container">
+<p>This script updated 21/03/2024 in Biel, CH</p>
+<p>❤️ <strong>what you do everyday:</strong> <em>analyst at hammerdirt</em></p>
+</div>
+</div>
 </div>
 </div>
 
diff --git a/docs/searchindex.js b/docs/searchindex.js
index cfbbeac..0fd0a39 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"docnames": ["grid_approximation", "grids_2023", "plastic_shotgun_wadding", "summary_2015_2021", "titlepage"], "filenames": ["grid_approximation.ipynb", "grids_2023.ipynb", "plastic_shotgun_wadding.ipynb", "summary_2015_2021.ipynb", "titlepage.md"], "titles": ["<span class=\"section-number\">2. </span>Empirical Bayes: grid approximations", "<span class=\"section-number\">3. </span>Testing 2023 predictions", "<span class=\"section-number\">4. </span>Plastic shotgun shell wadding", "<span class=\"section-number\">1. </span>Results 2015 - 2021", "The solid waste experience"], "terms": {"note": [0, 1, 3], "colleagu": 0, "concern": [0, 1], "feder": [0, 2, 3], "report": [0, 1, 2, 3], "subset": [0, 1], "gather": [0, 1], "sinc": [0, 3, 4], "puplic": 0, "iqaasl": [0, 2], "decemb": 0, "ha": [0, 1, 2, 3, 4], "been": [0, 1, 3, 4], "addtion": 0, "collect": [0, 1, 2, 3], "event": 0, "lac": [0, 1, 2, 3], "l\u00e9man": [0, 1, 2, 3], "swe": [0, 3], "team": [0, 1, 3], "associ": [0, 2, 3], "sauvegard": [0, 3], "du": [0, 3], "asl": [0, 3], "complet": [0, 1], "100": [0, 1, 2, 4], "beach": [0, 1, 2, 3, 4], "litter": [0, 1, 2, 3, 4], "work": [0, 3], "gener": [0, 1, 3, 4], "guidanc": [0, 1], "big": 0, "pictur": 0, "common": [0, 3], "sens": 0, "consid": [0, 1, 2, 3, 4], "reason": [0, 1, 3], "minimum": 0, "amount": [0, 1], "trash": [0, 1, 4], "ground": [0, 2], "time": [0, 1, 2], "shorelin": [0, 1, 2, 3], "point": 0, "where": [0, 1, 2, 3], "abandon": 0, "enter": 0, "water": [0, 2, 3, 4], "get": [0, 4], "deposit": 0, "It": [0, 1, 2, 3], "necessari": 0, "whole": 0, "There": [0, 1, 2, 3], "mani": [0, 1], "sourc": [0, 1, 3], "varianc": [0, 3], "have": [0, 1, 2, 3, 4], "treat": 0, "densiti": [0, 1, 2, 4], "between": [0, 1, 2], "sampl": [0, 1, 3, 4], "group": [0, 1], "covari": 0, "topograph": [0, 1, 2], "featur": [0, 2], "differ": [0, 1, 2, 3], "locat": [0, 1, 2, 3, 4], "detect": 0, "abil": 0, "appear": [0, 1, 3], "item": [0, 1, 3], "same": [0, 1, 2, 3], "code": [0, 1, 3], "due": [0, 1, 2], "effect": [0, 1, 2], "decomposit": 0, "surveyor": 0, "volunt": [0, 1], "level": [0, 2, 3], "experi": 0, "physic": [0, 3], "limit": [0, 1, 4], "actual": [0, 1], "count": [0, 1, 3], "much": [0, 1, 3], "like": [0, 1], "find": [0, 2], "most": [0, 2, 3], "honest": [0, 1], "can": [0, 1, 2, 3, 4], "deriv": [0, 1, 2], "well": [0, 1, 3], "perform": [0, 2], "over": [0, 4], "part": [0, 1, 2, 3], "here": [0, 1, 2, 3], "assess": [0, 3, 4], "fit": 0, "process": [0, 1, 4], "clear": [0, 1], "For": [0, 1, 2, 3, 4], "exampl": [0, 1], "when": [0, 1, 2, 3], "health": [0, 1], "alongsid": 0, "bath": 0, "qualiti": 0, "eu": [0, 1, 3, 4], "adopt": 0, "principl": [0, 1, 4], "precaut": [0, 1, 4], "suggest": [0, 1, 3], "threshold": [0, 1, 3], "wa": [0, 3], "set": [0, 1, 3, 4], "20": [0, 1, 2, 3, 4], "piec": [0, 1, 3, 4], "meter": [0, 1, 2, 3, 4], "stakehold": 0, "impact": 0, "despit": 0, "section": [0, 1, 3], "one": [0, 1, 3], "see": [0, 1, 2], "greatest": 0, "rang": [0, 2, 3], "iqr": [0, 3], "howev": [0, 1, 3], "still": [0, 1], "close": [0, 1, 3], "other": [0, 1, 2, 3, 4], "indic": [0, 1], "yet": [0, 1], "found": [0, 2, 4], "maximum": [0, 3], "some": [0, 1, 3], "consensu": 0, "might": [0, 1], "paramet": [0, 3], "consider": 0, "effort": [0, 4], "put": [0, 1], "explor": 0, "posit": 0, "among": 0, "Near": [0, 1, 2], "far": [0, 1, 2], "certain": 0, "mai": [0, 1, 3], "construct": [0, 1, 2, 3], "model": [0, 1, 3, 4], "hypothesi": 0, "predict": [0, 4], "municip": [0, 1, 3, 4], "strategi": [0, 1], "consist": [0, 1, 2], "1": [0, 1, 2, 3], "context": [0, 2], "which": [0, 1, 3], "were": [0, 1, 2, 3], "becaus": [0, 1, 2, 3], "2": [0, 1, 2, 3], "3": [0, 1, 2, 3], "benefit": 0, "uncertainti": 0, "about": [0, 1], "base": [0, 1, 3, 4], "spread": 0, "statist": [0, 2], "geograph": 0, "student": [0, 3, 4], "demonstr": [0, 1, 4], "import": [0, 3], "small": [0, 1, 2], "action": 0, "On": [0, 1], "own": 0, "thei": [0, 1, 2, 3, 4], "sai": 0, "relat": 0, "combin": [0, 1, 3], "observ": [0, 2, 3, 4], "better": 0, "idea": 0, "specif": [0, 1, 2], "saint": [0, 2, 4], "sulpic": [0, 2, 4], "six": [0, 1, 3], "year": [0, 1], "period": [0, 1, 3], "newest": 0, "seven": [0, 1, 3], "after": [0, 1, 2], "first": [0, 1, 3], "record": [0, 1, 3, 4], "could": [0, 1, 3], "interpret": [0, 2, 4], "begin": 0, "new": [0, 1], "start": [0, 1, 4], "januari": 0, "joint": 0, "center": [0, 2, 3], "jrc": 0, "prefer": 0, "40": [0, 1, 3], "each": [0, 1, 3], "being": 0, "monitor": [0, 1], "met": 0, "baselin": [0, 3], "establish": [0, 1, 4], "250": [0, 2, 4], "38": [0, 2, 3], "initi": [0, 1], "therefor": [0, 1], "describ": [0, 1, 3], "previous": [0, 1, 3], "would": [0, 1, 3], "appropri": 0, "ani": [0, 1, 2], "singl": 0, "more": [0, 1, 2, 3], "than": [0, 1, 3], "enough": 0, "invest": 0, "made": [0, 1], "either": [0, 1], "prevent": [0, 1, 4], "remov": [0, 1], "public": [0, 1, 2, 4], "space": [0, 2, 4], "intent": 0, "reduc": [0, 4], "environ": 0, "help": [0, 2, 3], "evalu": 0, "return": [0, 1], "roi": 0, "project": 0, "provid": [0, 1, 2], "insight": [0, 3], "did": 0, "net": 0, "declin": [0, 3], "particularli": 0, "doe": [0, 2], "municp": 0, "compar": [0, 1, 3], "rest": 0, "area": [0, 1, 2, 3], "need": [0, 1], "must": [0, 4], "produc": [0, 1], "directli": 0, "immediatlei": 0, "requir": [0, 2], "check": 0, "integr": 0, "anoth": 0, "basic": [0, 2], "calcul": 0, "simpl": [0, 1], "possibl": [0, 1, 3], "By": 0, "mean": [0, 1, 2, 3], "text": [0, 3], "book": [0, 3], "similar": [0, 1], "maturit\u00e9": 0, "calculu": 0, "execut": 0, "sheet": [0, 1, 3], "scalabl": 0, "path": 0, "backend": 0, "server": 0, "oper": 0, "output": [0, 3], "format": [0, 1, 2, 3], "take": [0, 3, 4], "ml": 0, "discard": [0, 1], "disregard": 0, "highli": 0, "discourag": 0, "per": [0, 1, 2, 3, 4], "A": [0, 2], "float": 0, "0": [0, 1, 2, 3], "9": [0, 1, 2, 3], "99": [0, 1, 3], "repres": [0, 1, 3, 4], "999": 0, "everi": [0, 2], "individu": [0, 1, 4], "rare": 0, "exceed": 0, "connect": 0, "categori": [0, 1, 2], "contain": [0, 3], "materi": [0, 3], "type": [0, 1, 2, 3], "intend": 0, "defin": [0, 1, 2, 3], "orgin": 0, "frequenc": 0, "number": [0, 1, 2, 3, 4], "k": [0, 1], "divid": [0, 2], "taken": 0, "n": [0, 1], "bound": 0, "hex": 0, "hexagon": 0, "inscrib": 0, "circl": 0, "r": [0, 1], "1500": 0, "m": [0, 1, 2, 3], "dry": [0, 2], "portion": [0, 1], "cover": 0, "within": [0, 1, 2, 3], "occupi": 0, "op": 0, "avail": [0, 3], "least": [0, 1, 3], "superimpos": 0, "10": [0, 1, 2, 3], "pick": 0, "up": [0, 2], "indentifi": [0, 1], "them": 0, "theta": 0, "under": [0, 1, 3], "yield": 0, "exchang": 0, "bodi": [0, 2], "follow": [0, 1, 2, 3], "two": [0, 1, 2, 3, 4], "recov": 0, "assum": [0, 2], "activ": [0, 2, 3], "adjac": 0, "four": [0, 1], "three": [0, 1, 2, 3], "local": 0, "contribut": 0, "mix": 0, "accur": [0, 1], "misidentifi": 0, "Not": 0, "all": [0, 1, 2, 3], "inaccuraci": 0, "entri": 0, "through": [0, 2, 3], "6": [0, 1, 2, 3], "present": [0, 1, 3], "inculd": 0, "french": 0, "side": [0, 3], "becasu": 0, "done": [0, 1], "swiss": 0, "geo": 0, "admin": 0, "To": 0, "includ": [0, 2, 3], "region": [0, 1, 3, 4], "authorit": 0, "expert": 0, "map": [0, 1, 2, 3], "layer": 0, "franc": 0, "correspond": [0, 3], "befor": [0, 1], "31": [0, 1, 2, 3], "s": [0, 1, 2, 3], "further": [0, 1, 3], "request": 0, "identifi": [0, 1, 3], "switzerland": [0, 1, 3], "protocol": [0, 1, 3], "guid": 0, "marin": [0, 1], "european": [0, 1], "sea": [0, 1], "delimit": 0, "length": 0, "surfac": [0, 2], "border": 0, "standard": [0, 1, 2], "encourag": 0, "criteria": 0, "exclus": 0, "5": [0, 2, 3], "18": [0, 1, 2, 3], "width": [0, 2, 3], "line": [0, 1, 2, 3], "high": [0, 3], "mark": 0, "itself": 0, "purpos": [0, 1], "studi": 0, "onli": [0, 1, 2, 3], "valid": [0, 1], "impos": 0, "varieti": 0, "organ": [0, 3], "In": [0, 1, 3, 4], "campaign": 0, "mcbp": 0, "2016": [0, 1, 3, 4], "primarili": [0, 3], "south": [0, 2], "peopl": [0, 1], "resid": [0, 3], "know": [0, 1], "haut": [0, 2, 3], "come": [0, 2], "riviera": 0, "agglomerm": 0, "vevei": [0, 2], "la": [0, 2], "tour": [0, 2], "de": [0, 1, 2], "peilz": [0, 2], "montreux": [0, 2], "second": 0, "slr": [0, 3], "2017": [0, 3], "2018": [0, 3], "wwf": 0, "extend": [0, 1], "gland": [0, 2], "lausann": [0, 2], "last": [0, 3], "2020": [0, 3], "major": [0, 3], "monthli": 0, "fix": 0, "ad": [0, 1, 4], "spontan": 0, "food": [0, 1, 3], "tobacco": 0, "unclear": 0, "pandem": 0, "restrict": 0, "v": 0, "plastock": 0, "run": 0, "conduct": [0, 1, 3], "95": [0, 2, 3], "liter": 0, "25": [0, 1, 2, 3], "analyz": 0, "partnership": 0, "manag": [0, 3, 4], "determin": [0, 1, 3], "suitabl": 0, "off": 0, "nation": [0, 2, 3], "identif": [0, 1], "dimens": 0, "averag": [0, 1, 2], "longer": 0, "69": [0, 1, 3], "48": [0, 1, 3], "wider": 0, "430": 0, "m\u00b2": 0, "209": 0, "245": 0, "4": [0, 1, 2, 3, 4], "column": [0, 1, 3], "loc_dat": [0, 1, 3], "date": [0, 1, 2, 3], "dai": [0, 1, 3], "doi": [0, 1], "pc": [0, 1, 2, 3], "230": [0, 4], "384": 0, "onc": [0, 2], "paint": 0, "brush": 0, "g166": 0, "87": [0, 3], "cigarett": [0, 1, 3], "end": [0, 1, 3], "g27": [0, 1, 3], "15": [0, 1, 2, 3], "abund": 0, "account": [0, 1, 3], "75": [0, 1, 2, 3], "tabl": [0, 1, 3], "except": [0, 1], "elimin": 0, "explain": [0, 1], "nurdl": [0, 1], "inject": 0, "mold": 0, "pellet": [0, 1], "focuss": 0, "select": 0, "AND": [0, 1], "less": [0, 2, 3], "often": 0, "relativelei": 0, "easi": [0, 1, 4], "furthermor": 0, "also": [0, 3], "encount": 0, "variou": [0, 2], "state": 0, "place": [0, 1], "correct": 0, "immedi": 0, "recogniz": 0, "otherwis": 0, "degrad": 0, "objest": 0, "challeng": 0, "wether": 0, "bottl": [0, 1, 3], "cap": 0, "beverag": 0, "chemic": [0, 3], "difficult": [0, 1], "label": [0, 1, 3], "erod": 0, "origin": [0, 1, 3], "aggreg": [0, 1], "gfoam": [0, 1, 3], "expand": [0, 1, 3], "polystyren": [0, 1, 3], "g81": 0, "g82": 0, "g83": 0, "gfrag": [0, 1, 3], "g78": 0, "g79": 0, "g80": 0, "g75": 0, "g76": 0, "g77": 0, "gcap": [0, 1, 3], "lid": [0, 1, 3], "ring": 0, "g21": 0, "g23": 0, "g24": 0, "sup": 0, "dispos": [0, 2], "fish": 0, "gear": 0, "16": [0, 1, 3], "These": 0, "case": [0, 3], "hygien": 0, "ph": 0, "spatial": 0, "diffus": 0, "toilet": 0, "treatment": 0, "facil": 0, "g95": [0, 1, 3], "cotton": [0, 1, 3], "swab": [0, 1, 3], "500": [0, 1, 2], "g30": [0, 1, 3], "snack": [0, 1, 3], "wrapper": [0, 1, 3], "drink": [0, 3], "g10": [0, 1], "g25": 0, "cigartett": 0, "g35": 0, "straw": 0, "stirrer": 0, "g31": 0, "lollypop": 0, "stick": [0, 1, 3], "g32": [0, 1], "toi": [0, 1], "parti": [0, 1], "favor": [0, 1], "g33": 0, "industri": [0, 1, 3, 4], "profession": 0, "ip": 0, "transport": 0, "g67": [0, 1, 3], "g89": [0, 1, 3], "unknown": [0, 1], "unk": 0, "recreat": [0, 3], "sport": [0, 2], "rc": 0, "illeg": 0, "discharg": 0, "firearm": 0, "lakeshor": 0, "g70": [0, 1], "shotgun": [0, 1], "shell": 0, "wai": [0, 1, 2, 4], "look": [0, 1], "framework": 0, "ensur": [0, 2], "pathwai": 0, "manner": 0, "nor": 0, "analysi": [0, 3], "those": [0, 1], "easili": 0, "leverag": 0, "occur": [0, 1], "domain": 0, "figur": [0, 1, 3], "remark": [0, 1], "22": [0, 1, 2, 3], "nbsp": [0, 1, 2, 3], "weight": [0, 1], "78": [0, 1], "263": [0, 1], "73": [0, 1, 3], "62": [0, 2, 3], "34": [0, 1, 3], "35": [0, 1, 3], "25th": [0, 1, 3], "percentil": [0, 1, 3], "63": [0, 2, 3], "75th": [0, 1, 3], "citi": [0, 1, 2], "municipalitit": [0, 1], "21": [0, 1, 3], "19": [0, 1, 3], "23": [0, 1, 2, 3], "59": [0, 2, 3], "839": 0, "13": [0, 1, 2, 3], "804": 0, "inquir": 0, "entir": 0, "neg": [0, 3], "binomi": [0, 3], "distribut": [0, 1, 2], "river": [0, 1], "bassin": 0, "particular": [0, 1], "shape": 0, "solv": 0, "interv": [0, 1, 3], "01": [0, 1, 2, 3], "our": [0, 1, 4], "trend": [0, 3], "conservationist": [0, 1], "wildlif": [0, 2], "biologist": [0, 1], "both": [0, 1, 3], "field": [0, 2], "rich": [0, 4], "histori": 0, "citizen": 0, "scienc": [0, 1], "program": 0, "summar": 0, "bird": 0, "ag": 0, "surviv": 0, "tick": 0, "magnitud": [0, 1, 3], "variabl": 0, "error": 0, "appli": [0, 1, 3], "best": 0, "classifi": 0, "bayesian": 0, "filter": [0, 1, 3], "smooth": 0, "classic": 0, "infer": 0, "share": [0, 1], "davidson": 0, "pillon": 0, "hacker": 0, "doubl": [0, 4], "formul": 0, "dur": 0, "basi": 0, "again": 0, "rigor": 0, "analyt": 0, "understood": 0, "build": [0, 2], "probabilist": 0, "exist": 0, "seri": 0, "theorem": 0, "condtion": 0, "make": [0, 1, 2, 3, 4], "long": [0, 1], "quantifi": 0, "underli": 0, "relationship": [0, 2], "realtionship": 0, "notat": 0, "b": 0, "p": [0, 3], "machin": 0, "learn": 0, "proababl": 0, "propos": [0, 1], "demand": 0, "whether": [0, 1], "binari": 0, "therfor": 0, "think": [0, 1], "rule": [0, 3], "introduct": 0, "introduc": 0, "conjug": 0, "rel": [0, 3], "1000": 0, "real": 0, "hierarch": [0, 1], "awai": 0, "without": 0, "overhead": 0, "develop": [0, 1], "full": 0, "compromis": 0, "wikepedia": [0, 2], "formal": [0, 1], "let": 0, "align": [0, 3], "frac": 0, "lt": 0, "tag": 0, "10pt": 0, "final": 0, "evid": [0, 2], "prime": 0, "11pt": 0, "posterior": [0, 1], "likelihood": [0, 1, 4], "7": [0, 1, 2, 3], "tell": [0, 1], "sum": [0, 1, 3], "complement": 0, "y": [0, 1, 3], "ge": 0, "x": [0, 1, 3], "assign": 0, "cari": 0, "out": [0, 3], "math": [0, 3], "gamma": 0, "n_": 0, "pr": 0, "beta": [0, 1], "8": [0, 1, 2, 3], "12pt": 0, "choos": [0, 1], "c": 0, "int_": 0, "i": [0, 1, 3], "d": [0, 1], "11": [0, 1, 2, 3], "recogn": 0, "write": 0, "abov": [0, 3], "solut": [0, 4], "sim": 0, "12": [0, 1, 2, 3], "subject": 0, "subjecitv": 0, "bia": 0, "caus": 0, "carri": 0, "omit": 0, "instead": 0, "reli": 0, "configur": 0, "spearman": [0, 1], "rho": 0, "distanc": [0, 3], "compon": 0, "captur": 0, "closest": 0, "denomin": [0, 1], "smilar": 0, "even": [0, 3], "explicit": 0, "basin": [0, 2], "scale": [0, 1], "lowest": [0, 3], "rank": [0, 1], "infrastructur": 0, "benfici": 0, "satisfi": 0, "testabl": 0, "though": [0, 1], "exactli": [0, 2], "moment": 0, "give": 0, "accru": 0, "elsewher": 0, "remain": [0, 1, 3], "choic": [0, 1], "statement": [0, 1, 3], "refer": [0, 1, 3], "multipl": [0, 3], "gelman": 0, "whch": 0, "you": [0, 1, 3], "anyth": 0, "equal": 0, "50": [0, 1, 2, 3], "form": [0, 1, 2], "coefici": 0, "analag": 0, "problem": 0, "angl": 0, "slight": 0, "handl": [0, 3], "respect": [0, 3], "notabl": 0, "infrastrutur": 0, "separ": [0, 1, 3], "detail": [0, 1, 2, 3], "descript": [0, 2, 3], "issu": 0, "themselv": 0, "system": [0, 1], "control": 0, "varaibl": 0, "certainli": 0, "assembl": 0, "illustr": 0, "depth": 0, "earli": 0, "version": 0, "swisstlmregio": 0, "extract": [0, 2], "boundari": 0, "polygon": 0, "landcov": 0, "product": [0, 3], "vector": 0, "overlai": [0, 1], "techniqu": [0, 1], "qgi": [0, 1], "3000m": 0, "circumcscrib": 0, "1500m": 0, "undefin": [0, 2], "built": 0, "urban": [0, 3], "wood": [0, 2, 3], "park": 0, "harvest": 0, "tree": 0, "vineyard": [0, 2], "agricultur": 0, "orchard": [0, 2], "predefin": 0, "labl": 0, "freizeitar": 0, "nutzungsar": 0, "hospit": [0, 2], "cemeteri": 0, "histor": [0, 2], "site": 0, "inciner": 0, "plant": 0, "As": [0, 2, 3], "ratio": 0, "meters\u00b2": 0, "thu": [0, 3], "size": [0, 1, 3], "attract": [0, 3], "school": [0, 2], "powerpl": 0, "street": 0, "road": 0, "polylin": 0, "tlm": 0, "strass": 0, "polyin": 0, "merg": [0, 1], "disolv": 0, "command": 0, "coeffici": [0, 1], "covarainc": 0, "__combin": 0, "daili": [0, 3], "total__": 0, "list": [0, 1, 4], "2024": [0, 1], "reduct": [0, 3], "minim": 0, "readili": 0, "veri": [0, 1], "unkown": 0, "85": [0, 1, 3], "42": [0, 1, 3], "94": [0, 1, 3], "86": [0, 1, 3], "53": [0, 2, 3], "45": [0, 1, 3], "46": [0, 1, 3], "43": [0, 3], "noth": 0, "hypothesis": 0, "lend": 0, "support": [0, 2, 3], "52": [0, 1, 3], "56": [0, 3], "41": [0, 1], "246": 0, "36": [0, 3], "24": [0, 1, 3], "29": [0, 1, 2, 3], "08": [0, 1, 2, 3], "visitor": 0, "tobaco": 0, "notic": 0, "commun": 0, "39": [0, 1, 3], "72": [0, 2, 3], "82": [0, 1, 3], "66": [0, 1, 3], "27": [0, 1, 3], "With": 0, "lower": [0, 3], "improv": [0, 1], "comparison": 0, "main": [0, 3], "focu": 0, "anti": 0, "low": 0, "mistaken": 0, "ident": 0, "fact": 0, "rose": 0, "usual": 0, "inexperienc": 0, "tend": [0, 1], "differenti": [0, 1], "sever": 0, "profesion": 0, "conduit": 0, "pvc": 0, "ab": 0, "concret": 0, "stop": 0, "saftei": 0, "barrier": 0, "pallett": 0, "heavi": 0, "guag": 0, "pheromon": 0, "bait": 0, "unawar": [0, 1], "sale": 0, "ban": 0, "tampon": [0, 1], "lack": [0, 1], "percent": [0, 2, 3], "58": [0, 2], "00": [0, 1, 2, 3], "06": [0, 1, 2, 3], "14": [0, 1, 2, 3], "57": [0, 1, 3], "49": [0, 1, 3], "90": [0, 3], "30": [0, 1, 2, 3], "91": [0, 1, 2], "legend": [0, 1, 3], "greater": [0, 3], "potenti": [0, 3], "show": [0, 3], "came": 0, "hisotr": 0, "around": 0, "why": [0, 1], "anticip": 0, "presenc": [0, 1], "hydrolog": 0, "mechan": 0, "function": [0, 1], "flat": 0, "curv": 0, "comprehens": 0, "hdi": [0, 1], "80": [0, 1, 3], "script": [0, 1, 3, 4], "updat": [0, 1, 3], "03": [0, 1, 2], "biel": [0, 1, 3], "ch": [0, 1, 3, 4], "everydai": [0, 1, 3], "analyst": [0, 1, 3, 4], "hammerdirt": [0, 1, 3, 4], "git": [0, 1, 3], "repo": [0, 1, 3], "http": [0, 1, 3], "github": [0, 1, 3], "com": [0, 1, 3], "solid": [0, 3], "wast": [0, 3], "branch": [0, 1, 3], "review": [0, 1, 4], "panda": [0, 1, 3], "seaborn": [0, 1, 3], "matplotlib": [0, 1, 3], "numpi": [0, 1, 3], "thi": [1, 2, 3, 4], "seventh": 1, "epfl": 1, "maritim": 1, "measur": [1, 3, 4], "decad": 1, "good": [1, 4], "environment": 1, "stand": 1, "we": [1, 2, 4], "2015": [1, 2], "obviou": 1, "prof": 1, "ludwig": 1, "interest": [1, 3, 4], "realiz": 1, "flow": [1, 3], "lake": [1, 2, 3, 4], "ocean": 1, "while": [1, 4], "rais": 1, "plastic": [1, 3, 4], "diminsh": 1, "biodivers": 1, "ar": [1, 2, 3, 4], "prudent": 1, "contact": 1, "quantiti": [1, 3], "object": [1, 2, 3, 4], "numer": [1, 2], "inform": [1, 4], "condit": 1, "term": 1, "attribut": [1, 2, 3], "correl": [1, 2], "quickli": 1, "specfic": 1, "accumul": [1, 3], "wrote": 1, "an": [1, 2, 3, 4], "articl": 1, "how": [1, 2, 3], "becom": 1, "accid": 1, "creat": 1, "increas": 1, "chanc": 1, "lifecycl": 1, "evad": 1, "recoveri": 1, "resourc": [1, 3, 4], "emploi": 1, "chang": 1, "behavior": 1, "lifcycl": 1, "approri": 1, "servic": [1, 2], "dedic": 1, "inappropri": 1, "indiffer": 1, "reliant": 1, "orntithologist": 1, "botanist": 1, "data": [1, 2, 3, 4], "answer": 1, "336": 1, "000": [1, 4], "145km": 1, "shore": [1, 3, 4], "geneva": [1, 2, 3, 4], "although": 1, "stretch": 1, "coastlin": 1, "anywher": 1, "world": 1, "opinion": 1, "5th": 1, "philosoph": 1, "realiti": 1, "hard": 1, "distinct": 1, "228": 1, "search": 1, "OR": 1, "74": [1, 3], "ssp": 1, "head": 1, "slug": [1, 2, 3], "water_name_slug": 1, "29392": 1, "parc": 1, "pierrett": [1, 3], "vd": [1, 2, 3], "leman": [1, 3], "287": 1, "train": 1, "g1": 1, "29393": 1, "02": [1, 2, 3], "29394": 1, "g100": [1, 3], "79": 1, "29395": 1, "g101": 1, "29396": 1, "g102": 1, "fail": 1, "rate": 1, "total": [1, 2], "g112": [1, 3], "2686": 1, "16458": 1, "candi": [1, 3], "54": [1, 2, 3], "6767": 1, "05": [1, 2, 3], "606": 1, "3356": 1, "cartridg": 1, "1030": 1, "1970": 1, "51": 1, "bud": [1, 3], "4777": 1, "04": [1, 2], "g96": 1, "sanitari": 1, "pad": [1, 3], "panti": 1, "liner": 1, "applic": 1, "373": 1, "3953": 1, "84": [1, 3], "12871": 1, "81": 1, "fragment": [1, 3], "17479": 1, "93": [1, 3], "download": 1, "goal": 1, "todai": 1, "excercis": 1, "your": 1, "current": [1, 4], "understand": 1, "consult": 1, "200": 1, "100m": 1, "red": [1, 3], "ink": 1, "name": [1, 3], "At": [1, 3], "do": [1, 3], "document": [1, 3, 4], "access": 1, "narrat": 1, "screencast": 1, "someth": 1, "class": 1, "who": 1, "python": 1, "annaconda": 1, "reult": 1, "plage": 1, "p\u00e9lican": 1, "cours": 1, "allow": 1, "skill": 1, "creativ": 1, "fairli": 1, "given": [1, 3], "2021": [1, 2], "summ_data": 1, "cbd": 1, "copi": [1, 3], "lambda": [1, 3], "use_groups_i": 1, "ug": 1, "abbrev_use_g": 1, "person": 1, "consumpt": 1, "pd": [1, 3], "to_datetim": [1, 3], "sd_x": 1, "groupbi": [1, 3], "as_index": [1, 3], "fals": [1, 3], "agg": [1, 3], "sd_x_sp": 1, "trg": 1, "tst": 1, "trg_c": 1, "tst_c": 1, "nuniqu": [1, 3], "trg_lc": 1, "tst_lc": 1, "trg_q": 1, "tst_q": 1, "data_magnitud": 1, "cities_set": 1, "n_ind_citi": 1, "len": 1, "caption": [1, 3], "f": [1, 3], "data_summ_q": 1, "datafram": 1, "index": [1, 3], "astyp": [1, 3], "int": [1, 3], "style": [1, 3], "formatt": 1, "set_table_styl": [1, 3], "table_large_font": 1, "set_capt": [1, 3], "indexslic": 1, "glue": [1, 3], "summ": 1, "q3": 1, "displai": [1, 3], "the_99th_percentil": 1, "np": [1, 3], "quantil": [1, 3], "px": 1, "plt": [1, 3], "rcparam": 1, "dpi": 1, "pixel": 1, "inch": 1, "fig": [1, 3], "ax": [1, 3], "subplot": [1, 3], "figsiz": [1, 3], "600": 1, "sn": [1, 3], "scatterplot": [1, 3], "color": [1, 3], "dodgerblu": [1, 3], "alpha": [1, 3], "magenta": [1, 3], "set_ylim": [1, 3], "loc": [1, 3], "upper": [1, 2, 3], "left": [1, 2, 3], "set_xlabel": [1, 3], "testing_training_chrono_2": 1, "testing_training_doy_2": 1, "testing_v": 1, "training_v": 1, "train_quantil": 1, "some_qu": 1, "test_quantil": 1, "training_testing_summari": 1, "training_testing_compar": 1, "sum_tabl": 1, "0f": 1, "summary_2": 1, "median": [1, 2, 3], "47": 1, "28": [1, 3], "623": 1, "703": 1, "def": [1, 3], "sampler_from_multinomi": 1, "norm": 1, "xrang": 1, "nsampl": [1, 2], "random": 1, "default_rng": 1, "norm_nuniqu": 1, "multinomi": 1, "pval": 1, "ft": 1, "axi": [1, 3], "asum": 1, "enumer": [1, 3], "els": [1, 3], "samp": 1, "period_piec": 1, "date_mask": 1, "period_on": 1, "pone_pc": 1, "pcs_m": 1, "period_k_and_n": 1, "add_on": 1, "pone_k": 1, "pone_notk": 1, "dist": 1, "mulitpli": 1, "uninform": 1, "prior": [1, 4], "pone_k_n_minus_k": 1, "arrai": 1, "period_beta": 1, "current_possible_prior_loc": 1, "landus": 1, "moa": 1, "magnitude_of_attribut": 1, "possible_loc": 1, "isin": [1, 3], "prior_loc": 1, "make_expect": 1, "lh_tupl": 1, "prior_tupl": 1, "re": 1, "print": 1, "arang": 1, "betai": 1, "success": 1, "abeta": 1, "append": [1, 3], "an_xrang": 1, "comb_lu_agg": 1, "read_csv": [1, 3], "u_comb_lu_cover_street_riv": 1, "csv": [1, 3], "lu_scal": 1, "pivot": [1, 3], "fillna": [1, 3], "lu_magnitud": 1, "lu_bin": 1, "bin": 1, "not_thes": 1, "amphion": 1, "anthi": 1, "excenevex": 1, "lugrin": 1, "meilleri": [1, 2], "disdil": 1, "tougu": 1, "merge_loc": 1, "cbdu": 1, "left_on": 1, "right_index": 1, "true": [1, 3], "many_to_on": 1, "outer": 1, "attribute_column": 1, "geroel": 1, "stause": 1, "sumpf": 1, "stadtzentr": 1, "fel": 1, "work_column": 1, "renam": [1, 3], "inplac": [1, 3], "chapter": 1, "index_rang": 1, "uninformed_tupl": 1, "g_resa": 1, "g_resadt": 1, "posterior_df": 1, "code_index": 1, "city_index": 1, "attribute_index": 1, "this_cod": 1, "this_attribut": 1, "this_citi": 1, "coi": [1, 3], "prior_data": 1, "lh_data": 1, "lh_locat": 1, "land": [1, 2], "lac_leman_region": 1, "lh_region": 1, "alabel": 1, "retirev": 1, "regional_loc": 1, "retriev": 1, "land_use_data_of_interest": 1, "pass": [1, 3], "prior_arg": 1, "uninformed_prior": 1, "grid": [1, 4], "approxim": [1, 3, 4], "grid_prior": 1, "beta_prior": 1, "prior_k_n": 1, "prior_df": 1, "prior_distribut": 1, "posterior_arg": 1, "2022": 1, "un_inform": 1, "informed_prior": 1, "beta_p": 1, "lh_pc": 1, "posterior_distribut": 1, "prior_quant": 1, "post_quant": 1, "frame": 1, "normal": 1, "post_df": 1, "make_results_df": 1, "post": 1, "source_norm": 1, "ip_n": 1, "un_n": 1, "sim_2024": 1, "sim_quant": 1, "pred_quant": 1, "probabl": [1, 3], "precis": [1, 3], "32": [1, 3], "09": [1, 2, 3], "17": [1, 2, 3], "97": [1, 3], "83": [1, 3], "recal": [1, 3], "characterist": [1, 4], "classroom": 1, "discus": 1, "length_p": 1, "estimated_p": 1, "make_row": 1, "row": 1, "found_p": 1, "266": 1, "found_pm": 1, "pierrette_row": 1, "found_pel": 1, "found_pelm": 1, "estimated_td": 1, "07": [1, 3], "length_td": 1, "found_td": 1, "60": [1, 3], "179": 1, "found_tdm": 1, "tiger_duck_row": 1, "tiger_duck": 1, "fmelt": 1, "melt": 1, "value_var": 1, "concat": 1, "reset_index": 1, "drop": [1, 3], "particp": 1, "found_displai": 1, "tiger": [1, 3], "duck": [1, 3], "set_index": [1, 3], "none": [1, 2, 3], "67": 1, "64": [1, 2], "55": [1, 2], "underestim": 1, "cumul": 1, "closer": 1, "oserv": 1, "fell": 1, "96": 1, "Of": [1, 3], "root": 1, "squar": 1, "difference\u00b2": 1, "89": [1, 3], "26": [1, 3], "71": 1, "reflect": 1, "neither": 1, "third": [1, 3], "shown": [1, 3], "foam": [1, 3], "constraint": 1, "unidentifi": [1, 3], "certainti": 1, "paritcip": 1, "simpli": 1, "question": 1, "serv": 1, "correctli": 1, "past": 1, "conclud": 1, "dtype": 1, "float64": 1, "int64": 1, "summari": 2, "commonli": 2, "us": [2, 3, 4], "modern": 2, "its": 2, "durabl": 2, "cushion": 2, "shot": 2, "move": 2, "down": 2, "barrel": 2, "stai": 2, "proper": 2, "seal": 2, "maxim": 2, "energi": 2, "transfer": 2, "upon": [2, 3], "fire": 2, "cup": 2, "design": 2, "depend": [2, 3], "desir": 2, "behind": 2, "shoot": 2, "improperli": 2, "eventu": 2, "wash": 2, "pose": 2, "risk": 2, "ingest": 2, "entangl": 2, "essenti": 2, "from": [2, 3, 4], "949": 2, "uniqu": [2, 3], "The": [2, 3], "what": [2, 3], "archeaologist": 2, "anthropologist": 2, "assumpt": 2, "undertak": 2, "excav": 2, "discuss": 2, "strong": 2, "isol": 2, "survei": 2, "forest": 2, "etc": 2, "grow": 2, "grape": 2, "wine": 2, "valu": [2, 3], "public_servic": 2, "92": [2, 3], "68": [2, 3], "linear": [2, 4], "sediment": 2, "tecton": 2, "fold": 2, "glacial": 2, "eros": 2, "eastern": 2, "rh\u00f4ne": 2, "estuari": 2, "rivaz": 2, "grand": [2, 3], "larg": 2, "largest": 2, "deepest": 2, "petit": 2, "west": 2, "narrow": 2, "deep": 2, "yvoir": 2, "promenthoux": 2, "next": 2, "prangin": 2, "exit": 2, "brief": [2, 3], "geographi": 2, "std": [2, 3], "min": [2, 3], "max": [2, 3], "137": 2, "nummber": 2, "morg": 2, "roll": [2, 3], "descend": 2, "order": [2, 3], "gingolph": 2, "allaman": 2, "bourg": 2, "en": 2, "lavaux": 2, "44": 2, "versoix": [2, 3], "gen\u00e8v": 2, "pr\u00e9vereng": 2, "tolochenaz": 2, "msfd": 3, "mlwguidanc": 3, "novemb": 3, "accord": 3, "www": 3, "plagespropr": 3, "visibl": 3, "along": 3, "edg": 3, "terrain": 3, "strand": 3, "nearest": 3, "structur": 3, "pour": 3, "le": 3, "ecol": 3, "polytechniqu": 3, "intern": 3, "genev": 3, "preciou": 3, "open": 3, "notebook": 3, "repositori": 3, "load_ext": 3, "watermark": 3, "os": 3, "datetim": 3, "dt": 3, "packag": 3, "scipi": 3, "stat": 3, "statsmodel": 3, "empirical_distribut": 3, "ecdf": 3, "percentileofscor": 3, "chart": 3, "mpl": 3, "pyplot": 3, "mdate": 3, "ticker": 3, "gridspec": 3, "ipython": 3, "html": 3, "markdown": 3, "md": 3, "myst_nb": 3, "blank_capt": 3, "survey_data": 3, "u_pstk_iqaasl_al": 3, "g216": 3, "dfcode": 3, "u_cod": 3, "dfbeach": 3, "u_beach": 3, "decript": 3, "group_map": 3, "groupnam": 3, "st": 3, "fd": 3, "werr": 3, "respons": 3, "t_name": 3, "eint": 3, "hd": 3, "teams_y1_4": 3, "prevereng": 3, "babi": 3, "lacleman_vidy_santi": 3, "lacleman_gland_lecoanet": 3, "lacleman_gland_kubela": 3, "teams_y5_6": 3, "maladair": 3, "vidi": 3, "ruin": 3, "ii": 3, "rocki": 3, "n_hd_y_1_4": 3, "n_hd_y_5_6": 3, "hd_y_1_4": 3, "hd_y_5_5": 3, "css": 3, "header_row": 3, "selector": 3, "th": 3, "nth": 3, "child": 3, "prop": 3, "background": 3, "fff": 3, "right": 3, "even_row": 3, "tr": 3, "rgba": 3, "139": 3, "odd_row": 3, "odd": 3, "table_font": 3, "font": 3, "12px": 3, "table_data": 3, "td": 3, "6px": 3, "table_capt": 3, "14px": 3, "ital": 3, "bottom": 3, "margin": 3, "10px": 3, "table_css_styl": 3, "start_dat": 3, "end_dat": 3, "year_on": 3, "year_two": 3, "year_thre": 3, "year_four": 3, "2019": 3, "year_fiv": 3, "year_six": 3, "year_nam": 3, "yx": 3, "assign_a_survey_period": 3, "start_end": 3, "slice": 3, "these_arg": 3, "asamp": 3, "to_csv": 3, "table_1": 3, "33": 3, "aqti": 3, "table_2": 3, "28007": 3, "2721": 3, "30728": 3, "1490": 3, "10188": 3, "2526": 3, "1006": 3, "15210": 3, "2164": 3, "203": 3, "1591": 3, "1534": 3, "5492": 3, "306": 3, "2719": 3, "167": 3, "9582": 3, "4701": 3, "1536": 3, "18705": 3, "556": 3, "6130": 3, "2072": 3, "971": 3, "9749": 3, "qs": 3, "aq": 3, "table_3": 3, "t": 3, "318": 3, "350": 3, "129": 3, "127": 3, "443": 3, "previou": 3, "termin": 3, "below": 3, "fall": 3, "a_l": 3, "a_l_summari": 3, "var": 3, "dispers": 3, "round": 3, "table_4": 3, "77": 3, "98": 3, "88": 3, "249": 3, "145": 3, "101": 3, "prohibit": 3, "poisson": 3, "decis": [3, 4], "outlier": 3, "eubaselein": 3, "iq": 3, "to_numpi": 3, "twenty_f": 3, "seventy_f": 3, "figure_1": 3, "histplot": 3, "hue": 3, "zorder": 3, "stack": 3, "vline": 3, "ymin": 3, "ymax": 3, "linestyl": 3, "dash": 3, "linewidth": 3, "fill_between": 3, "y1": 3, "y2": 3, "h": 3, "l": 3, "get_legend_handles_label": 3, "hs": 3, "nl": 3, "frameon": 3, "set_ylabel": 3, "fontsiz": 3, "tight_layout": 3, "figure_2": 3, "a_locd": 3, "figure_3": 3, "ylimit": 3, "dayloc": 3, "tick_param": 3, "fancybox": 3, "facecolor": 3, "white": 3, "edgecolor": 3, "framealpha": 3, "get_fram": 3, "set_linewidth": 3, "267": 3, "figure_4": 3, "boxprop": 3, "boxplot": 3, "showflier": 3, "stripplot": 3, "jitter": 3, "axis_limit": 3, "99th": 3, "highest": 3, "77pc": 3, "regular": 3, "occurr": 3, "publish": 3, "guidelin": 3, "eubaselin": 3, "set_styl": 3, "whitegrid": 3, "set_xlim": 3, "somdata": 3, "lower25": 3, "upper25": 3, "dashdot": 3, "lineplot": 3, "n_handl": 3, "n_label": 3, "bbox_to_anchor": 3, "titl": 3, "innerquartil": 3, "cluster": 3, "saddlebrown": 3, "iqrs_by_group": 3, "black": 3, "aproxim": 3, "had": 3, "p_total_yoi": 3, "table_6": 3, "g200": 3, "70": [3, 4], "ten_yoi": 3, "lake_top_ten": 3, "p_yoi": 3, "sort_valu": 3, "ascend": 3, "table_7": 3, "6298": 3, "1442": 3, "536": 3, "2318": 3, "1271": 3, "6152": 3, "4068": 3, "579": 3, "2392": 3, "777": 3, "3985": 3, "1243": 3, "1151": 3, "65": 3, "2923": 3, "1297": 3, "1913": 3, "1119": 3, "509": 3, "1069": 3, "668": 3, "1498": 3, "1174": 3, "362": 3, "754": 3, "358": 3, "1421": 3, "686": 3, "236": 3, "640": 3, "410": 3, "1246": 3, "713": 3, "174": 3, "658": 3, "542": 3, "1234": 3, "533": 3, "183": 3, "261": 3, "293": 3, "524": 3, "247": 3, "190": 3, "366": 3, "248": 3, "1091": 3, "296": 3, "24271": 3, "11225": 3, "3920": 3, "217": 3, "12472": 3, "6160": 3, "mention": 3, "short": 3, "walk": 3, "residenti": 3, "neighborhood": 3, "ps": 3, "pp": 3, "If": 3, "diff": 3, "dif": 3, "693": 3, "2028": 3, "258": 3, "748": 3, "160": 3, "464": 3, "326": 3, "sort": 3, "input": 3, "databas": 3, "mlw": 3, "classif": 3, "appendix": 3, "segment": 3, "scrutin": 3, "seen": 3, "compos": 3, "cloth": 3, "glass": 3, "metal": 3, "paper": 3, "76": 3, "rubber": 3, "via": 3, "categoris": 3, "al": 3, "predominantli": 3, "polymer": 3, "volum": 3, "season": 3, "fluctuat": 3, "direct": 3, "affect": 3, "instanc": 3, "somewhat": 3, "shelter": 3, "higher": 3, "debri": 3, "mostli": 3, "parallel": 3, "quantit": 3, "gain": 3, "healthi": 3, "code_summari": 3, "fdsp": 3, "code_d": 3, "mat_d": 3, "c_sum": 3, "each_beach": 3, "boi": 3, "tten": 3, "mat": 3, "274": 3, "737": 3, "351": 3, "475": 3, "289": 3, "341": 3, "279": 3, "343": 3, "252": 3, "142": 3, "349": 3, "325": 3, "334": 3, "tape": 3, "mask": 3, "duct": 3, "pack": 3, "178": 3, "medic": 3, "tube": 3, "tdata": 3, "matdata": 3, "gdata": 3, "sharei": 3, "plot": 3, "bar": 3, "colormap": 3, "tab10": 3, "labelbottom": 3, "labels": 3, "ls": 3, "new_label": 3, "ncol": 3, "set_titl": 3, "ylabel": 3, "capit": 3, "333": 3, "175": 3, "195": 3, "113": 3, "169": 3, "117": 3, "155": 3, "insul": 3, "polyurethan": 3, "broken": 3, "moder": 3, "dens": 3, "circumst": 3, "2023": [3, 4], "octob": 4, "colect": 4, "Their": 4, "result": 4, "manuscript": 4, "peer": 4, "mass": 4, "That": 4, "300": 4, "catalog": 4, "empir": 4, "bay": 4, "approach": 4, "avoid": 4, "util": 4, "appilc": 4, "envrironment": 4, "chosen": 4, "beacus": 4, "independ": 4, "anthropolgist": 4, "should": 4, "delight": 4, "toxic": 4, "perist": 4, "topic": 4, "seem": 4, "shake": 4, "regard": 4, "opt": 4, "recomend": 4, "tool": 4, "aid": 4, "evidenv": 4, "replic": 4, "unfund": 4, "author": 4, "roger": 4, "erismann": 4, "bhavish": 4, "patel": 4, "content": 4, "conata": 4}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"empir": [0, 1], "bay": [0, 1], "grid": 0, "approxim": 0, "If": 0, "we": 0, "ar": 0, "us": [0, 1], "data": 0, "estim": [0, 1], "environment": 0, "condit": [0, 2], "respons": 0, "should": 0, "answer": 0, "question": 0, "research": 0, "practic": 0, "applic": 0, "constraint": 0, "definit": 0, "assumpt": 0, "test": [0, 1], "train": 0, "object": 0, "interest": 0, "The": [0, 1, 4], "summari": [0, 1, 3], "method": [0, 1], "probabl": 0, "prior": 0, "inform": 0, "uninform": 0, "measur": 0, "land": 0, "attribut": 0, "result": [0, 1, 2, 3], "lake": 0, "geneva": 0, "given": 0, "from": [0, 1], "2022": 0, "Is": 0, "an": 0, "increas": 0, "decreas": 0, "chang": 0, "expect": [0, 1], "survei": [0, 1, 3], "consolid": 0, "2015": [0, 3], "2021": [0, 3], "previou": [0, 1], "total": [0, 3], "median": 0, "valu": [0, 1], "what": [0, 1], "chanc": 0, "exce": 0, "thi": 0, "fragment": 0, "plastic": [0, 2], "person": 0, "consumpt": 0, "how": 0, "do": 0, "go": 0, "forward": 0, "discuss": [0, 1], "conclus": [0, 1], "next": [0, 1], "step": [0, 1], "2023": 1, "predict": 1, "solid": [1, 4], "wast": [1, 4], "experi": [1, 4], "observ": 1, "interpret": 1, "A": 1, "uniqu": 1, "problem": 1, "solut": 1, "asess": 1, "environ": 1, "reduc": 1, "dimension": 1, "find": 1, "most": 1, "common": 1, "assess": 1, "semest": 1, "project": 1, "saint": [1, 3], "sulpic": [1, 3], "particip": 1, "octob": 1, "5": 1, "found": 1, "annex": 1, "accuraci": 1, "relat": 1, "wa": 1, "shotgun": 2, "shell": 2, "wad": 2, "characterist": 2, "weight": 2, "sampl": 2, "region": 2, "municip": 2, "variat": 3, "trash": 3, "over": 3, "time": 3, "year": 3, "statist": 3, "cumul": 3, "distribut": 3, "comparison": 3, "between": 3, "group": 3, "composit": 3, "site": 3, "specif": 3, "plage": 3, "de": 3, "parc": 3, "pierett": 3, "top": 3, "ten": 3, "purpos": 4, "financi": 4, "disclosur": 4}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 6, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx": 56}})
\ No newline at end of file
+Search.setIndex({"docnames": ["grid_approximation", "grids_2023", "plastic_shotgun_wadding", "summary_2015_2021", "titlepage"], "filenames": ["grid_approximation.ipynb", "grids_2023.ipynb", "plastic_shotgun_wadding.ipynb", "summary_2015_2021.ipynb", "titlepage.md"], "titles": ["<span class=\"section-number\">2. </span>Empirical Bayes: grid approximations", "<span class=\"section-number\">3. </span>Testing 2023 predictions", "<span class=\"section-number\">4. </span>Plastic shotgun shell wadding", "<span class=\"section-number\">1. </span>Results 2015 - 2021", "The solid waste experience"], "terms": {"note": [0, 1, 3], "colleagu": 0, "concern": [0, 1], "feder": [0, 2, 3], "report": [0, 1, 2, 3], "subset": 0, "gather": [0, 1], "sinc": [0, 3, 4], "puplic": 0, "iqaasl": [0, 2], "decemb": 0, "ha": [0, 1, 2, 3, 4], "been": [0, 1, 3, 4], "addtion": 0, "collect": [0, 1, 2, 3], "event": 0, "lac": [0, 1, 2, 3], "l\u00e9man": [0, 2, 3], "swe": [0, 3], "team": [0, 1, 3], "associ": [0, 2, 3], "sauvegard": [0, 3], "du": [0, 3], "asl": [0, 3], "complet": [0, 1], "100": [0, 1, 2, 4], "beach": [0, 1, 2, 3, 4], "litter": [0, 1, 2, 3, 4], "work": [0, 3], "gener": [0, 1, 3, 4], "guidanc": [0, 1], "big": 0, "pictur": 0, "common": [0, 3], "sens": 0, "consid": [0, 1, 2, 3, 4], "reason": [0, 1, 3], "minimum": 0, "amount": [0, 1], "trash": [0, 1, 4], "ground": [0, 2], "time": [0, 1, 2], "shorelin": [0, 1, 2, 3], "point": 0, "where": [0, 1, 2, 3], "abandon": 0, "enter": 0, "water": [0, 2, 3, 4], "get": [0, 4], "deposit": 0, "It": [0, 1, 2, 3], "necessari": 0, "whole": 0, "There": [0, 1, 2, 3], "mani": [0, 1], "sourc": [0, 1, 3], "varianc": [0, 3], "have": [0, 1, 2, 3, 4], "treat": 0, "densiti": [0, 1, 2, 4], "between": [0, 1, 2], "sampl": [0, 1, 3, 4], "group": [0, 1], "covari": 0, "topograph": [0, 1, 2], "featur": [0, 2], "differ": [0, 1, 2, 3], "locat": [0, 1, 2, 3, 4], "detect": 0, "abil": 0, "appear": [0, 1, 3], "item": [0, 1, 3], "same": [0, 1, 2, 3], "code": [0, 1, 3], "due": [0, 1, 2], "effect": [0, 1, 2], "decomposit": 0, "surveyor": 0, "volunt": [0, 1], "level": [0, 2, 3], "experi": 0, "physic": [0, 3], "limit": [0, 1, 4], "actual": [0, 1], "count": [0, 1, 3], "much": [0, 1, 3], "like": [0, 1], "find": [0, 2], "most": [0, 2, 3], "honest": [0, 1], "can": [0, 1, 2, 3, 4], "deriv": [0, 1, 2], "well": [0, 1, 3], "perform": [0, 2], "over": [0, 4], "part": [0, 1, 2, 3], "here": [0, 1, 2, 3], "assess": [0, 3, 4], "fit": 0, "process": [0, 1, 4], "clear": [0, 1], "For": [0, 1, 2, 3, 4], "exampl": [0, 1], "when": [0, 1, 2, 3], "health": [0, 1], "alongsid": 0, "bath": 0, "qualiti": 0, "eu": [0, 1, 3, 4], "adopt": 0, "principl": [0, 1, 4], "precaut": [0, 1, 4], "suggest": [0, 1, 3], "threshold": [0, 1, 3], "wa": [0, 3], "set": [0, 3, 4], "20": [0, 1, 2, 3, 4], "piec": [0, 1, 3, 4], "meter": [0, 1, 2, 3, 4], "stakehold": 0, "impact": 0, "despit": 0, "section": [0, 1, 3], "one": [0, 1, 3], "see": [0, 1, 2], "greatest": 0, "rang": [0, 2, 3], "iqr": [0, 3], "howev": [0, 1, 3], "still": [0, 1], "close": [0, 1, 3], "other": [0, 1, 2, 3, 4], "indic": [0, 1], "yet": [0, 1], "found": [0, 2, 4], "maximum": [0, 3], "some": [0, 1, 3], "consensu": 0, "might": [0, 1], "paramet": [0, 3], "consider": 0, "effort": [0, 4], "put": [0, 1], "explor": 0, "posit": 0, "among": 0, "Near": [0, 1, 2], "far": [0, 1, 2], "certain": 0, "mai": [0, 1, 3], "construct": [0, 1, 2, 3], "model": [0, 1, 3, 4], "hypothesi": 0, "predict": [0, 4], "municip": [0, 3, 4], "strategi": [0, 1], "consist": [0, 1, 2], "1": [0, 1, 2, 3], "context": [0, 2], "which": [0, 1, 3], "were": [0, 1, 2, 3], "becaus": [0, 1, 2, 3], "2": [0, 1, 2, 3], "3": [0, 1, 2, 3], "benefit": 0, "uncertainti": 0, "about": [0, 1], "base": [0, 1, 3, 4], "spread": 0, "statist": [0, 2], "geograph": 0, "student": [0, 3, 4], "demonstr": [0, 1, 4], "import": [0, 3], "small": [0, 1, 2], "action": 0, "On": [0, 1], "own": 0, "thei": [0, 1, 2, 3, 4], "sai": 0, "relat": 0, "combin": [0, 3], "observ": [0, 2, 3, 4], "better": 0, "idea": 0, "specif": [0, 1, 2], "saint": [0, 2, 4], "sulpic": [0, 2, 4], "six": [0, 1, 3], "year": [0, 1], "period": [0, 1, 3], "newest": 0, "seven": [0, 1, 3], "after": [0, 1, 2], "first": [0, 1, 3], "record": [0, 1, 3, 4], "could": [0, 1, 3], "interpret": [0, 2, 4], "begin": 0, "new": [0, 1], "start": [0, 1, 4], "januari": 0, "joint": 0, "center": [0, 2, 3], "jrc": 0, "prefer": 0, "40": [0, 1, 3], "each": [0, 1, 3], "being": 0, "monitor": [0, 1], "met": 0, "baselin": [0, 3], "establish": [0, 1, 4], "250": [0, 2, 4], "38": [0, 1, 2, 3], "initi": [0, 1], "therefor": [0, 1], "describ": [0, 1, 3], "previous": [0, 1, 3], "would": [0, 1, 3], "appropri": 0, "ani": [0, 2], "singl": 0, "more": [0, 1, 2, 3], "than": [0, 1, 3], "enough": 0, "invest": 0, "made": [0, 1], "either": [0, 1], "prevent": [0, 1, 4], "remov": 0, "public": [0, 1, 2, 4], "space": [0, 2, 4], "intent": 0, "reduc": [0, 4], "environ": 0, "help": [0, 2, 3], "evalu": 0, "return": [0, 1], "roi": 0, "project": 0, "provid": [0, 1, 2], "insight": [0, 3], "did": 0, "net": 0, "declin": [0, 3], "particularli": 0, "doe": [0, 2], "municp": 0, "compar": [0, 1, 3], "rest": 0, "area": [0, 1, 2, 3], "need": [0, 1], "must": [0, 4], "produc": [0, 1], "directli": 0, "immediatlei": 0, "requir": [0, 2], "check": 0, "integr": 0, "anoth": 0, "basic": [0, 2], "calcul": 0, "simpl": [0, 1], "possibl": [0, 1, 3], "By": 0, "mean": [0, 2, 3], "text": [0, 3], "book": [0, 3], "similar": [0, 1], "maturit\u00e9": 0, "calculu": 0, "execut": 0, "sheet": [0, 1, 3], "scalabl": 0, "path": 0, "backend": 0, "server": 0, "oper": 0, "output": [0, 3], "format": [0, 2, 3], "take": [0, 3, 4], "ml": 0, "discard": [0, 1], "disregard": 0, "highli": 0, "discourag": 0, "per": [0, 1, 2, 3, 4], "A": [0, 2], "float": 0, "0": [0, 1, 2, 3], "9": [0, 1, 2, 3], "99": [0, 3], "repres": [0, 1, 3, 4], "999": 0, "everi": [0, 2], "individu": [0, 1, 4], "rare": 0, "exceed": 0, "connect": 0, "categori": [0, 1, 2], "contain": [0, 3], "materi": [0, 3], "type": [0, 1, 2, 3], "intend": 0, "defin": [0, 1, 2, 3], "orgin": 0, "frequenc": 0, "number": [0, 1, 2, 3, 4], "k": 0, "divid": [0, 2], "taken": 0, "n": 0, "bound": 0, "hex": 0, "hexagon": 0, "inscrib": 0, "circl": 0, "r": [0, 1], "1500": 0, "m": [0, 1, 2, 3], "dry": [0, 2], "portion": [0, 1], "cover": 0, "within": [0, 1, 2, 3], "occupi": 0, "op": 0, "avail": [0, 3], "least": [0, 1, 3], "superimpos": 0, "10": [0, 1, 2, 3], "pick": 0, "up": [0, 2], "indentifi": 0, "them": 0, "theta": 0, "under": [0, 1, 3], "yield": 0, "exchang": 0, "bodi": [0, 2], "follow": [0, 1, 2, 3], "two": [0, 1, 2, 3, 4], "recov": 0, "assum": [0, 2], "activ": [0, 2, 3], "adjac": 0, "four": [0, 1], "three": [0, 1, 2, 3], "local": 0, "contribut": 0, "mix": 0, "accur": [0, 1], "misidentifi": 0, "Not": 0, "all": [0, 1, 2, 3], "inaccuraci": 0, "entri": 0, "through": [0, 2, 3], "6": [0, 1, 2, 3], "present": [0, 1, 3], "inculd": 0, "french": 0, "side": [0, 3], "becasu": 0, "done": [0, 1], "swiss": 0, "geo": 0, "admin": 0, "To": 0, "includ": [0, 2, 3], "region": [0, 1, 3, 4], "authorit": 0, "expert": 0, "map": [0, 1, 2, 3], "layer": 0, "franc": 0, "correspond": [0, 3], "befor": [0, 1], "31": [0, 1, 2, 3], "s": [0, 2, 3], "further": [0, 1, 3], "request": 0, "identifi": [0, 1, 3], "switzerland": [0, 1, 3], "protocol": [0, 1, 3], "guid": 0, "marin": [0, 1], "european": [0, 1], "sea": [0, 1], "delimit": 0, "length": 0, "surfac": [0, 2], "border": 0, "standard": [0, 1, 2], "encourag": 0, "criteria": 0, "exclus": 0, "5": [0, 2, 3], "18": [0, 1, 2, 3], "width": [0, 2, 3], "line": [0, 1, 2, 3], "high": [0, 3], "mark": 0, "itself": 0, "purpos": [0, 1], "studi": 0, "onli": [0, 1, 2, 3], "valid": 0, "impos": 0, "varieti": 0, "organ": [0, 3], "In": [0, 1, 3, 4], "campaign": 0, "mcbp": 0, "2016": [0, 1, 3, 4], "primarili": [0, 3], "south": [0, 2], "peopl": [0, 1], "resid": [0, 3], "know": [0, 1], "haut": [0, 2, 3], "come": [0, 2], "riviera": 0, "agglomerm": 0, "vevei": [0, 2], "la": [0, 2], "tour": [0, 2], "de": [0, 1, 2], "peilz": [0, 2], "montreux": [0, 2], "second": 0, "slr": [0, 3], "2017": [0, 3], "2018": [0, 3], "wwf": 0, "extend": 0, "gland": [0, 2], "lausann": [0, 2], "last": [0, 3], "2020": [0, 3], "major": [0, 3], "monthli": 0, "fix": 0, "ad": [0, 1, 4], "spontan": 0, "food": [0, 1, 3], "tobacco": 0, "unclear": 0, "pandem": 0, "restrict": 0, "v": 0, "plastock": 0, "run": 0, "conduct": [0, 1, 3], "95": [0, 2, 3], "liter": 0, "25": [0, 1, 2, 3], "analyz": 0, "partnership": 0, "manag": [0, 3, 4], "determin": [0, 1, 3], "suitabl": 0, "off": 0, "nation": [0, 2, 3], "identif": [0, 1], "dimens": 0, "averag": [0, 1, 2], "longer": 0, "69": [0, 1, 3], "48": [0, 1, 3], "wider": 0, "430": 0, "m\u00b2": 0, "209": 0, "245": 0, "4": [0, 1, 2, 3, 4], "column": [0, 3], "loc_dat": [0, 1, 3], "date": [0, 1, 2, 3], "dai": [0, 3], "doi": [0, 1], "pc": [0, 1, 2, 3], "230": [0, 4], "384": 0, "onc": [0, 2], "paint": 0, "brush": 0, "g166": 0, "87": [0, 1, 3], "cigarett": [0, 1, 3], "end": [0, 1, 3], "g27": [0, 1, 3], "15": [0, 1, 2, 3], "abund": 0, "account": [0, 1, 3], "75": [0, 1, 2, 3], "tabl": [0, 1, 3], "except": [0, 1], "elimin": 0, "explain": [0, 1], "nurdl": [0, 1], "inject": 0, "mold": 0, "pellet": [0, 1], "focuss": 0, "select": 0, "AND": [0, 1], "less": [0, 2, 3], "often": 0, "relativelei": 0, "easi": [0, 1, 4], "furthermor": 0, "also": [0, 3], "encount": 0, "variou": [0, 2], "state": 0, "place": [0, 1], "correct": 0, "immedi": 0, "recogniz": 0, "otherwis": 0, "degrad": 0, "objest": 0, "challeng": 0, "wether": 0, "bottl": [0, 1, 3], "cap": 0, "beverag": 0, "chemic": [0, 3], "difficult": [0, 1], "label": [0, 3], "erod": 0, "origin": [0, 1, 3], "aggreg": [0, 1], "gfoam": [0, 1, 3], "expand": [0, 1, 3], "polystyren": [0, 1, 3], "g81": 0, "g82": 0, "g83": 0, "gfrag": [0, 1, 3], "g78": 0, "g79": 0, "g80": 0, "g75": 0, "g76": 0, "g77": 0, "gcap": [0, 1, 3], "lid": [0, 1, 3], "ring": 0, "g21": 0, "g23": 0, "g24": 0, "sup": 0, "dispos": [0, 2], "fish": 0, "gear": 0, "16": [0, 1, 3], "These": 0, "case": [0, 3], "hygien": 0, "ph": 0, "spatial": 0, "diffus": 0, "toilet": 0, "treatment": 0, "facil": 0, "g95": [0, 1, 3], "cotton": [0, 1, 3], "swab": [0, 1, 3], "500": [0, 2], "g30": [0, 1, 3], "snack": [0, 1, 3], "wrapper": [0, 1, 3], "drink": [0, 3], "g10": [0, 1], "g25": 0, "cigartett": 0, "g35": 0, "straw": 0, "stirrer": 0, "g31": 0, "lollypop": 0, "stick": [0, 1, 3], "g32": [0, 1], "toi": [0, 1], "parti": [0, 1], "favor": [0, 1], "g33": 0, "industri": [0, 1, 3, 4], "profession": 0, "ip": 0, "transport": 0, "g67": [0, 1, 3], "g89": [0, 1, 3], "unknown": [0, 1], "unk": 0, "recreat": [0, 3], "sport": [0, 2], "rc": 0, "illeg": 0, "discharg": 0, "firearm": 0, "lakeshor": 0, "g70": [0, 1], "shotgun": [0, 1], "shell": 0, "wai": [0, 1, 2, 4], "look": [0, 1], "framework": 0, "ensur": [0, 2], "pathwai": 0, "manner": 0, "nor": 0, "analysi": [0, 3], "those": [0, 1], "easili": 0, "leverag": 0, "occur": [0, 1], "domain": 0, "figur": [0, 1, 3], "remark": [0, 1], "22": [0, 1, 2, 3], "nbsp": [0, 1, 2, 3], "weight": [0, 1], "78": [0, 1], "263": [0, 1], "73": [0, 1, 3], "62": [0, 2, 3], "34": [0, 1, 3], "35": [0, 1, 3], "25th": [0, 1, 3], "percentil": [0, 1, 3], "63": [0, 2, 3], "75th": [0, 1, 3], "citi": [0, 1, 2], "municipalitit": [0, 1], "21": [0, 1, 2, 3], "19": [0, 1, 3], "23": [0, 1, 2, 3], "59": [0, 2, 3], "839": 0, "13": [0, 1, 2, 3], "804": 0, "inquir": 0, "entir": 0, "neg": [0, 3], "binomi": [0, 3], "distribut": [0, 1, 2], "river": [0, 1], "bassin": 0, "particular": [0, 1], "shape": 0, "solv": 0, "interv": [0, 1, 3], "01": [0, 1, 2, 3], "our": [0, 1, 4], "trend": [0, 3], "conservationist": [0, 1], "wildlif": [0, 2], "biologist": [0, 1], "both": [0, 1, 3], "field": [0, 2], "rich": [0, 4], "histori": 0, "citizen": 0, "scienc": [0, 1], "program": 0, "summar": 0, "bird": 0, "ag": 0, "surviv": 0, "tick": 0, "magnitud": [0, 3], "variabl": 0, "error": 0, "appli": [0, 3], "best": 0, "classifi": 0, "bayesian": 0, "filter": [0, 1, 3], "smooth": 0, "classic": 0, "infer": 0, "share": [0, 1], "davidson": 0, "pillon": 0, "hacker": 0, "doubl": [0, 4], "formul": 0, "dur": 0, "basi": 0, "again": 0, "rigor": 0, "analyt": 0, "understood": 0, "build": [0, 2], "probabilist": 0, "exist": 0, "seri": 0, "theorem": 0, "condtion": 0, "make": [0, 1, 2, 3, 4], "long": [0, 1], "quantifi": 0, "underli": 0, "relationship": [0, 2], "realtionship": 0, "notat": 0, "b": 0, "p": [0, 3], "machin": 0, "learn": 0, "proababl": 0, "propos": [0, 1], "demand": 0, "whether": [0, 1], "binari": 0, "therfor": 0, "think": [0, 1], "rule": [0, 3], "introduct": 0, "introduc": 0, "conjug": 0, "rel": [0, 3], "1000": 0, "real": 0, "hierarch": [0, 1], "awai": 0, "without": 0, "overhead": 0, "develop": [0, 1], "full": 0, "compromis": 0, "wikepedia": [0, 2], "formal": [0, 1], "let": 0, "align": [0, 3], "frac": 0, "lt": 0, "tag": 0, "10pt": 0, "final": 0, "evid": [0, 2], "prime": 0, "11pt": 0, "posterior": 0, "likelihood": [0, 4], "7": [0, 1, 2, 3], "tell": [0, 1], "sum": [0, 3], "complement": 0, "y": [0, 3], "ge": 0, "x": [0, 3], "assign": 0, "cari": 0, "out": [0, 3], "math": [0, 3], "gamma": 0, "n_": 0, "pr": 0, "beta": 0, "8": [0, 1, 2, 3], "12pt": 0, "choos": [0, 1], "c": 0, "int_": 0, "i": [0, 3], "d": 0, "11": [0, 1, 2, 3], "recogn": 0, "write": 0, "abov": [0, 3], "solut": [0, 4], "sim": 0, "12": [0, 1, 2, 3], "subject": 0, "subjecitv": 0, "bia": 0, "caus": 0, "carri": 0, "omit": 0, "instead": 0, "reli": 0, "configur": 0, "spearman": [0, 1], "rho": 0, "distanc": [0, 3], "compon": 0, "captur": 0, "closest": 0, "denomin": 0, "smilar": 0, "even": [0, 3], "explicit": 0, "basin": [0, 2], "scale": 0, "lowest": [0, 3], "rank": [0, 1], "infrastructur": 0, "benfici": 0, "satisfi": 0, "testabl": 0, "though": [0, 1], "exactli": [0, 2], "moment": 0, "give": 0, "accru": 0, "elsewher": 0, "remain": [0, 1, 3], "choic": 0, "statement": [0, 1, 3], "refer": [0, 1, 3], "multipl": [0, 3], "gelman": 0, "whch": 0, "you": [0, 1, 2, 3], "anyth": 0, "equal": 0, "50": [0, 1, 2, 3], "form": [0, 1, 2], "coefici": 0, "analag": 0, "problem": 0, "angl": 0, "slight": 0, "handl": [0, 3], "respect": [0, 3], "notabl": 0, "infrastrutur": 0, "separ": [0, 1, 3], "detail": [0, 1, 2, 3], "descript": [0, 2, 3], "issu": 0, "themselv": 0, "system": [0, 1], "control": 0, "varaibl": 0, "certainli": 0, "assembl": 0, "illustr": 0, "depth": 0, "earli": 0, "version": 0, "swisstlmregio": 0, "extract": [0, 2], "boundari": 0, "polygon": 0, "landcov": 0, "product": [0, 3], "vector": 0, "overlai": [0, 1], "techniqu": [0, 1], "qgi": [0, 1], "3000m": 0, "circumcscrib": 0, "1500m": 0, "undefin": [0, 2], "built": 0, "urban": [0, 3], "wood": [0, 2, 3], "park": 0, "harvest": 0, "tree": 0, "vineyard": [0, 2], "agricultur": 0, "orchard": [0, 2], "predefin": 0, "labl": 0, "freizeitar": 0, "nutzungsar": 0, "hospit": [0, 2], "cemeteri": 0, "histor": [0, 2], "site": 0, "inciner": 0, "plant": 0, "As": [0, 2, 3], "ratio": 0, "meters\u00b2": 0, "thu": [0, 3], "size": [0, 3], "attract": [0, 3], "school": [0, 2], "powerpl": 0, "street": 0, "road": 0, "polylin": 0, "tlm": 0, "strass": 0, "polyin": 0, "merg": 0, "disolv": 0, "command": 0, "coeffici": [0, 1], "covarainc": 0, "__combin": 0, "daili": [0, 3], "total__": 0, "list": [0, 4], "2024": [0, 1, 2], "reduct": [0, 3], "minim": 0, "readili": 0, "veri": [0, 1], "unkown": 0, "85": [0, 1, 3], "42": [0, 3], "94": [0, 1, 3], "86": [0, 1, 3], "53": [0, 2, 3], "45": [0, 1, 3], "46": [0, 1, 3], "43": [0, 1, 3], "noth": 0, "hypothesis": 0, "lend": 0, "support": [0, 2, 3], "52": [0, 1, 3], "56": [0, 3], "41": 0, "246": 0, "36": [0, 3], "24": [0, 1, 3], "29": [0, 1, 2, 3], "08": [0, 1, 2, 3], "visitor": 0, "tobaco": 0, "notic": 0, "commun": 0, "39": [0, 1, 3], "72": [0, 2, 3], "82": [0, 3], "66": [0, 1, 3], "27": [0, 1, 3], "With": 0, "lower": [0, 3], "improv": [0, 1], "comparison": 0, "main": [0, 1, 3], "focu": 0, "anti": 0, "low": 0, "mistaken": 0, "ident": 0, "fact": 0, "rose": 0, "usual": 0, "inexperienc": 0, "tend": [0, 1], "differenti": [0, 1], "sever": 0, "profesion": 0, "conduit": 0, "pvc": 0, "ab": 0, "concret": 0, "stop": 0, "saftei": 0, "barrier": 0, "pallett": 0, "heavi": 0, "guag": 0, "pheromon": 0, "bait": 0, "unawar": [0, 1], "sale": 0, "ban": 0, "tampon": [0, 1], "lack": [0, 1], "percent": [0, 2, 3], "58": [0, 1, 2], "00": [0, 1, 2, 3], "06": [0, 1, 2, 3], "14": [0, 1, 2, 3], "57": [0, 1, 3], "49": [0, 3], "90": [0, 3], "30": [0, 1, 2, 3], "91": [0, 2], "legend": [0, 3], "greater": [0, 3], "potenti": [0, 3], "show": [0, 3], "came": 0, "hisotr": 0, "around": 0, "why": [0, 1], "anticip": 0, "presenc": [0, 1], "hydrolog": 0, "mechan": 0, "function": 0, "flat": 0, "curv": 0, "comprehens": 0, "hdi": [0, 1], "80": [0, 1, 3], "script": [0, 1, 2, 3, 4], "updat": [0, 1, 2, 3], "03": [0, 1, 2], "biel": [0, 1, 2, 3], "ch": [0, 1, 2, 3, 4], "everydai": [0, 1, 2, 3], "analyst": [0, 1, 2, 3, 4], "hammerdirt": [0, 1, 2, 3, 4], "git": [0, 1, 3], "repo": [0, 1, 3], "http": [0, 1, 3], "github": [0, 1, 3], "com": [0, 1, 3], "solid": [0, 3], "wast": [0, 3], "branch": [0, 1, 3], "review": [0, 1, 4], "panda": [0, 1, 3], "seaborn": [0, 1, 3], "matplotlib": [0, 1, 3], "numpi": [0, 1, 3], "thi": [1, 2, 3, 4], "seventh": 1, "epfl": 1, "maritim": 1, "measur": [1, 3, 4], "decad": 1, "good": [1, 4], "environment": 1, "stand": 1, "we": [1, 2, 4], "2015": [1, 2], "obviou": 1, "prof": 1, "ludwig": 1, "interest": [1, 3, 4], "realiz": 1, "flow": [1, 3], "lake": [1, 2, 3, 4], "ocean": 1, "while": [1, 4], "rais": 1, "plastic": [1, 3, 4], "diminsh": 1, "biodivers": 1, "ar": [1, 2, 3, 4], "prudent": 1, "contact": 1, "quantiti": [1, 3], "object": [1, 2, 3, 4], "numer": [1, 2], "inform": [1, 4], "condit": 1, "term": 1, "attribut": [1, 2, 3], "correl": [1, 2], "quickli": 1, "specfic": 1, "accumul": [1, 3], "wrote": 1, "an": [1, 2, 3, 4], "articl": 1, "how": [1, 2, 3], "becom": 1, "accid": 1, "creat": 1, "increas": 1, "chanc": 1, "lifecycl": 1, "evad": 1, "recoveri": 1, "resourc": [1, 3, 4], "emploi": 1, "chang": 1, "behavior": 1, "lifcycl": 1, "approri": 1, "servic": [1, 2], "dedic": 1, "inappropri": 1, "indiffer": 1, "reliant": 1, "orntithologist": 1, "botanist": 1, "data": [1, 2, 3, 4], "answer": 1, "336": 1, "000": [1, 4], "145km": 1, "shore": [1, 3, 4], "geneva": [1, 2, 3, 4], "although": 1, "stretch": 1, "coastlin": 1, "anywher": 1, "world": 1, "opinion": 1, "5th": 1, "philosoph": 1, "realiti": 1, "hard": 1, "distinct": 1, "228": 1, "search": 1, "OR": 1, "74": [1, 3], "ssp": 1, "head": 1, "slug": [1, 2, 3], "water_name_slug": 1, "29392": 1, "parc": 1, "pierrett": [1, 3], "vd": [1, 2, 3], "leman": [1, 3], "287": 1, "train": 1, "g1": 1, "29393": 1, "02": [1, 2, 3], "29394": 1, "g100": [1, 3], "79": 1, "29395": 1, "g101": 1, "29396": 1, "g102": 1, "fail": 1, "rate": 1, "total": [1, 2], "g112": [1, 3], "2686": 1, "16458": 1, "candi": [1, 3], "54": [1, 2, 3], "6767": 1, "05": [1, 2, 3], "606": 1, "3356": 1, "cartridg": 1, "1030": 1, "1970": 1, "51": 1, "bud": [1, 3], "4777": 1, "04": [1, 2], "g96": 1, "sanitari": 1, "pad": [1, 3], "panti": 1, "liner": 1, "applic": 1, "373": 1, "3953": 1, "84": [1, 3], "12871": 1, "81": 1, "fragment": [1, 3], "17479": 1, "93": [1, 3], "download": 1, "goal": 1, "todai": 1, "excercis": 1, "your": 1, "current": [1, 4], "understand": 1, "consult": 1, "200": 1, "100m": 1, "red": [1, 3], "ink": 1, "name": [1, 3], "At": [1, 3], "do": [1, 2, 3], "document": [1, 3, 4], "access": 1, "narrat": 1, "screencast": 1, "someth": 1, "class": 1, "who": 1, "python": 1, "annaconda": 1, "reult": 1, "plage": 1, "p\u00e9lican": 1, "cours": 1, "allow": 1, "skill": 1, "creativ": 1, "fairli": 1, "given": [1, 3], "2021": [1, 2], "median": [1, 2, 3], "47": 1, "28": [1, 3], "623": 1, "703": 1, "chapter": 1, "probabl": [1, 3], "32": [1, 3], "68": [1, 2, 3], "33": [1, 3], "97": [1, 3], "64": [1, 2], "recal": [1, 3], "land": [1, 2], "characterist": [1, 4], "classroom": 1, "discus": 1, "07": [1, 3], "60": [1, 3], "particp": 1, "tiger": [1, 3], "duck": [1, 3], "67": 1, "55": [1, 2], "underestim": 1, "cumul": 1, "closer": 1, "17": [1, 2, 3], "oserv": 1, "fell": 1, "96": 1, "Of": [1, 3], "root": 1, "squar": 1, "difference\u00b2": 1, "26": [1, 3], "reflect": 1, "neither": 1, "third": [1, 3], "shown": [1, 3], "foam": [1, 3], "constraint": 1, "unidentifi": [1, 3], "precis": [1, 3], "certainti": 1, "paritcip": 1, "simpli": 1, "question": 1, "serv": 1, "correctli": 1, "past": 1, "conclud": 1, "true": [1, 3], "fals": [1, 3], "dtype": 1, "float64": 1, "int64": 1, "summari": 2, "commonli": 2, "us": [2, 3, 4], "modern": 2, "its": 2, "durabl": 2, "cushion": 2, "shot": 2, "move": 2, "down": 2, "barrel": 2, "stai": 2, "proper": 2, "seal": 2, "maxim": 2, "energi": 2, "transfer": 2, "upon": [2, 3], "fire": 2, "cup": 2, "design": 2, "depend": [2, 3], "desir": 2, "left": [2, 3], "behind": 2, "shoot": 2, "improperli": 2, "eventu": 2, "wash": 2, "pose": 2, "risk": 2, "ingest": 2, "entangl": 2, "essenti": 2, "from": [2, 3, 4], "949": 2, "uniqu": [2, 3], "The": [2, 3], "what": [2, 3], "archeaologist": 2, "anthropologist": 2, "assumpt": 2, "undertak": 2, "excav": 2, "discuss": 2, "strong": 2, "isol": 2, "survei": 2, "forest": 2, "etc": 2, "grow": 2, "grape": 2, "wine": 2, "valu": [2, 3], "public_servic": 2, "92": [2, 3], "linear": [2, 4], "09": [2, 3], "sediment": 2, "tecton": 2, "fold": 2, "glacial": 2, "eros": 2, "upper": [2, 3], "eastern": 2, "rh\u00f4ne": 2, "estuari": 2, "meilleri": 2, "rivaz": 2, "grand": [2, 3], "larg": 2, "largest": 2, "deepest": 2, "petit": 2, "west": 2, "narrow": 2, "deep": 2, "yvoir": 2, "promenthoux": 2, "next": 2, "prangin": 2, "exit": 2, "brief": [2, 3], "geographi": 2, "nsampl": 2, "std": [2, 3], "min": [2, 3], "max": [2, 3], "137": 2, "nummber": 2, "none": [2, 3], "morg": 2, "roll": [2, 3], "descend": 2, "order": [2, 3], "gingolph": 2, "allaman": 2, "bourg": 2, "en": 2, "lavaux": 2, "44": 2, "versoix": [2, 3], "gen\u00e8v": 2, "pr\u00e9vereng": 2, "tolochenaz": 2, "msfd": 3, "mlwguidanc": 3, "novemb": 3, "accord": 3, "www": 3, "plagespropr": 3, "visibl": 3, "along": 3, "edg": 3, "terrain": 3, "strand": 3, "nearest": 3, "structur": 3, "pour": 3, "le": 3, "ecol": 3, "polytechniqu": 3, "intern": 3, "genev": 3, "preciou": 3, "open": 3, "notebook": 3, "repositori": 3, "load_ext": 3, "watermark": 3, "os": 3, "datetim": 3, "dt": 3, "packag": 3, "pd": 3, "np": 3, "scipi": 3, "stat": 3, "statsmodel": 3, "empirical_distribut": 3, "ecdf": 3, "percentileofscor": 3, "chart": 3, "mpl": 3, "pyplot": 3, "plt": 3, "mdate": 3, "ticker": 3, "sn": 3, "gridspec": 3, "ipython": 3, "displai": 3, "html": 3, "markdown": 3, "md": 3, "myst_nb": 3, "glue": 3, "blank_capt": 3, "survey_data": 3, "read_csv": 3, "u_pstk_iqaasl_al": 3, "csv": 3, "to_datetim": 3, "g216": 3, "copi": 3, "dfcode": 3, "u_cod": 3, "dfbeach": 3, "u_beach": 3, "decript": 3, "set_index": 3, "inplac": 3, "group_map": 3, "groupnam": 3, "lambda": 3, "loc": 3, "st": 3, "coi": 3, "fd": 3, "werr": 3, "respons": 3, "t_name": 3, "eint": 3, "hd": 3, "teams_y1_4": 3, "prevereng": 3, "babi": 3, "lacleman_vidy_santi": 3, "lacleman_gland_lecoanet": 3, "lacleman_gland_kubela": 3, "teams_y5_6": 3, "maladair": 3, "vidi": 3, "ruin": 3, "ii": 3, "rocki": 3, "n_hd_y_1_4": 3, "n_hd_y_5_6": 3, "hd_y_1_4": 3, "hd_y_5_5": 3, "css": 3, "header_row": 3, "selector": 3, "th": 3, "nth": 3, "child": 3, "prop": 3, "f": 3, "background": 3, "color": 3, "fff": 3, "right": 3, "even_row": 3, "tr": 3, "rgba": 3, "139": 3, "odd_row": 3, "odd": 3, "table_font": 3, "font": 3, "12px": 3, "table_data": 3, "td": 3, "6px": 3, "table_capt": 3, "caption": 3, "14px": 3, "style": 3, "ital": 3, "bottom": 3, "margin": 3, "10px": 3, "table_css_styl": 3, "start_dat": 3, "end_dat": 3, "year_on": 3, "year_two": 3, "year_thre": 3, "year_four": 3, "2019": 3, "year_fiv": 3, "year_six": 3, "year_nam": 3, "yx": 3, "def": 3, "assign_a_survey_period": 3, "start_end": 3, "slice": 3, "these_arg": 3, "isin": 3, "enumer": 3, "groupbi": 3, "as_index": 3, "agg": 3, "nuniqu": 3, "asamp": 3, "pivot": 3, "index": 3, "fillna": 3, "astyp": 3, "int": 3, "axi": 3, "to_csv": 3, "table_1": 3, "set_capt": 3, "set_table_styl": 3, "aqti": 3, "table_2": 3, "28007": 3, "2721": 3, "30728": 3, "1490": 3, "10188": 3, "2526": 3, "1006": 3, "15210": 3, "2164": 3, "203": 3, "1591": 3, "1534": 3, "5492": 3, "306": 3, "2719": 3, "167": 3, "9582": 3, "4701": 3, "1536": 3, "18705": 3, "556": 3, "6130": 3, "2072": 3, "971": 3, "9749": 3, "qs": 3, "aq": 3, "table_3": 3, "t": 3, "renam": 3, "drop": 3, "318": 3, "83": 3, "350": 3, "129": 3, "127": 3, "443": 3, "previou": 3, "termin": 3, "below": 3, "fall": 3, "a_l": 3, "a_l_summari": 3, "var": 3, "dispers": 3, "round": 3, "table_4": 3, "77": 3, "98": 3, "88": 3, "249": 3, "145": 3, "101": 3, "prohibit": 3, "poisson": 3, "decis": [3, 4], "outlier": 3, "eubaselein": 3, "fig": 3, "ax": 3, "subplot": 3, "figsiz": 3, "iq": 3, "to_numpi": 3, "twenty_f": 3, "seventy_f": 3, "figure_1": 3, "histplot": 3, "hue": 3, "zorder": 3, "stack": 3, "vline": 3, "ymin": 3, "ymax": 3, "linestyl": 3, "dash": 3, "dodgerblu": 3, "linewidth": 3, "fill_between": 3, "y1": 3, "y2": 3, "alpha": 3, "h": 3, "l": 3, "get_legend_handles_label": 3, "hs": 3, "nl": 3, "frameon": 3, "set_ylabel": 3, "fontsiz": 3, "set_xlabel": 3, "tight_layout": 3, "figure_2": 3, "a_locd": 3, "figure_3": 3, "ylimit": 3, "scatterplot": 3, "dayloc": 3, "tick_param": 3, "set_ylim": 3, "fancybox": 3, "facecolor": 3, "white": 3, "edgecolor": 3, "framealpha": 3, "get_fram": 3, "set_linewidth": 3, "267": 3, "figure_4": 3, "boxprop": 3, "boxplot": 3, "showflier": 3, "stripplot": 3, "jitter": 3, "quantil": 3, "axis_limit": 3, "99th": 3, "highest": 3, "77pc": 3, "regular": 3, "occurr": 3, "publish": 3, "guidelin": 3, "eubaselin": 3, "set_styl": 3, "whitegrid": 3, "set_xlim": 3, "somdata": 3, "lower25": 3, "upper25": 3, "dashdot": 3, "lineplot": 3, "els": 3, "pass": 3, "n_handl": 3, "n_label": 3, "bbox_to_anchor": 3, "titl": 3, "innerquartil": 3, "cluster": 3, "magenta": 3, "saddlebrown": 3, "iqrs_by_group": 3, "append": 3, "black": 3, "aproxim": 3, "had": 3, "p_total_yoi": 3, "table_6": 3, "g200": 3, "70": [3, 4], "ten_yoi": 3, "lake_top_ten": 3, "p_yoi": 3, "sort_valu": 3, "ascend": 3, "table_7": 3, "6298": 3, "1442": 3, "536": 3, "2318": 3, "1271": 3, "6152": 3, "4068": 3, "579": 3, "2392": 3, "777": 3, "3985": 3, "1243": 3, "1151": 3, "65": 3, "2923": 3, "1297": 3, "1913": 3, "1119": 3, "509": 3, "1069": 3, "668": 3, "1498": 3, "1174": 3, "362": 3, "754": 3, "358": 3, "1421": 3, "686": 3, "236": 3, "640": 3, "410": 3, "1246": 3, "713": 3, "174": 3, "658": 3, "542": 3, "1234": 3, "533": 3, "183": 3, "261": 3, "293": 3, "524": 3, "247": 3, "190": 3, "366": 3, "248": 3, "1091": 3, "296": 3, "24271": 3, "11225": 3, "3920": 3, "217": 3, "12472": 3, "6160": 3, "mention": 3, "short": 3, "walk": 3, "residenti": 3, "neighborhood": 3, "ps": 3, "pp": 3, "If": 3, "diff": 3, "dif": 3, "693": 3, "2028": 3, "258": 3, "748": 3, "160": 3, "464": 3, "326": 3, "sort": 3, "input": 3, "databas": 3, "mlw": 3, "classif": 3, "appendix": 3, "segment": 3, "scrutin": 3, "seen": 3, "compos": 3, "approxim": [3, 4], "cloth": 3, "glass": 3, "89": 3, "metal": 3, "paper": 3, "76": 3, "rubber": 3, "via": 3, "categoris": 3, "al": 3, "predominantli": 3, "polymer": 3, "volum": 3, "season": 3, "fluctuat": 3, "direct": 3, "affect": 3, "instanc": 3, "somewhat": 3, "shelter": 3, "higher": 3, "debri": 3, "mostli": 3, "parallel": 3, "quantit": 3, "gain": 3, "healthi": 3, "code_summari": 3, "fdsp": 3, "code_d": 3, "mat_d": 3, "c_sum": 3, "each_beach": 3, "boi": 3, "tten": 3, "mat": 3, "274": 3, "737": 3, "351": 3, "475": 3, "289": 3, "341": 3, "279": 3, "343": 3, "252": 3, "142": 3, "349": 3, "325": 3, "334": 3, "tape": 3, "mask": 3, "duct": 3, "pack": 3, "178": 3, "medic": 3, "tube": 3, "tdata": 3, "matdata": 3, "gdata": 3, "sharei": 3, "plot": 3, "bar": 3, "colormap": 3, "tab10": 3, "labelbottom": 3, "labels": 3, "ls": 3, "new_label": 3, "ncol": 3, "set_titl": 3, "ylabel": 3, "capit": 3, "333": 3, "175": 3, "195": 3, "113": 3, "169": 3, "117": 3, "155": 3, "insul": 3, "polyurethan": 3, "broken": 3, "moder": 3, "dens": 3, "circumst": 3, "2023": [3, 4], "octob": 4, "colect": 4, "Their": 4, "result": 4, "manuscript": 4, "peer": 4, "mass": 4, "That": 4, "300": 4, "catalog": 4, "empir": 4, "bay": 4, "approach": 4, "avoid": 4, "prior": 4, "grid": 4, "util": 4, "appilc": 4, "envrironment": 4, "chosen": 4, "beacus": 4, "independ": 4, "anthropolgist": 4, "should": 4, "delight": 4, "toxic": 4, "perist": 4, "topic": 4, "seem": 4, "shake": 4, "regard": 4, "opt": 4, "recomend": 4, "tool": 4, "aid": 4, "evidenv": 4, "replic": 4, "unfund": 4, "author": 4, "roger": 4, "erismann": 4, "bhavish": 4, "patel": 4, "content": 4, "conata": 4}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"empir": [0, 1], "bay": [0, 1], "grid": 0, "approxim": 0, "If": 0, "we": 0, "ar": 0, "us": [0, 1], "data": 0, "estim": [0, 1], "environment": 0, "condit": [0, 2], "respons": 0, "should": 0, "answer": 0, "question": 0, "research": 0, "practic": 0, "applic": 0, "constraint": 0, "definit": 0, "assumpt": 0, "test": [0, 1], "train": 0, "object": 0, "interest": 0, "The": [0, 1, 4], "summari": [0, 1, 3], "method": [0, 1], "probabl": 0, "prior": 0, "inform": 0, "uninform": 0, "measur": 0, "land": 0, "attribut": 0, "result": [0, 1, 2, 3], "lake": 0, "geneva": 0, "given": 0, "from": [0, 1], "2022": 0, "Is": 0, "an": 0, "increas": 0, "decreas": 0, "chang": 0, "expect": [0, 1], "survei": [0, 1, 3], "consolid": 0, "2015": [0, 3], "2021": [0, 3], "previou": [0, 1], "total": [0, 3], "median": 0, "valu": [0, 1], "what": [0, 1], "chanc": 0, "exce": 0, "thi": 0, "fragment": 0, "plastic": [0, 2], "person": 0, "consumpt": 0, "how": 0, "do": 0, "go": 0, "forward": 0, "discuss": [0, 1], "conclus": [0, 1], "next": [0, 1], "step": [0, 1], "2023": 1, "predict": 1, "solid": [1, 4], "wast": [1, 4], "experi": [1, 4], "observ": 1, "interpret": 1, "A": 1, "uniqu": 1, "problem": 1, "solut": 1, "asess": 1, "environ": 1, "reduc": 1, "dimension": 1, "find": 1, "most": 1, "common": 1, "assess": 1, "semest": 1, "project": 1, "saint": [1, 3], "sulpic": [1, 3], "particip": 1, "octob": 1, "5": 1, "found": 1, "annex": 1, "accuraci": 1, "relat": 1, "wa": 1, "shotgun": 2, "shell": 2, "wad": 2, "characterist": 2, "weight": 2, "sampl": 2, "region": 2, "municip": 2, "variat": 3, "trash": 3, "over": 3, "time": 3, "year": 3, "statist": 3, "cumul": 3, "distribut": 3, "comparison": 3, "between": 3, "group": 3, "composit": 3, "site": 3, "specif": 3, "plage": 3, "de": 3, "parc": 3, "pierett": 3, "top": 3, "ten": 3, "purpos": 4, "financi": 4, "disclosur": 4}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 6, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx": 56}})
\ No newline at end of file
diff --git a/grids_2023.ipynb b/grids_2023.ipynb
index 62b2e8b..7047ecf 100644
--- a/grids_2023.ipynb
+++ b/grids_2023.ipynb
@@ -496,21 +496,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_d0aab tr:nth-child(even) {\n",
+       "#T_556fc tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_d0aab tr:nth-child(odd) {\n",
+       "#T_556fc tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_d0aab tr {\n",
+       "#T_556fc tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_d0aab th:nth-child(1) {\n",
+       "#T_556fc th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_d0aab caption {\n",
+       "#T_556fc caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -518,16 +518,16 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_d0aab\">\n",
+       "<table id=\"T_556fc\">\n",
        "  <caption>Table 1: The objects of interest. The average pcs/m per sample for each object. The fail rate is the % of all samples that the object appeared in.</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank\" >&nbsp;</th>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_d0aab_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
-       "      <th id=\"T_d0aab_level0_col1\" class=\"col_heading level0 col1\" >quantity</th>\n",
-       "      <th id=\"T_d0aab_level0_col2\" class=\"col_heading level0 col2\" >fail rate</th>\n",
-       "      <th id=\"T_d0aab_level0_col3\" class=\"col_heading level0 col3\" >% of total</th>\n",
+       "      <th id=\"T_556fc_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
+       "      <th id=\"T_556fc_level0_col1\" class=\"col_heading level0 col1\" >quantity</th>\n",
+       "      <th id=\"T_556fc_level0_col2\" class=\"col_heading level0 col2\" >fail rate</th>\n",
+       "      <th id=\"T_556fc_level0_col3\" class=\"col_heading level0 col3\" >% of total</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th class=\"index_name level0\" >code</th>\n",
@@ -540,106 +540,106 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
-       "      <th id=\"T_d0aab_level1_row0\" class=\"row_heading level1 row0\" >Industrial pellets (nurdles)</th>\n",
-       "      <td id=\"T_d0aab_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
-       "      <td id=\"T_d0aab_row0_col1\" class=\"data row0 col1\" >2686</td>\n",
-       "      <td id=\"T_d0aab_row0_col2\" class=\"data row0 col2\" >0.22</td>\n",
-       "      <td id=\"T_d0aab_row0_col3\" class=\"data row0 col3\" >0.02</td>\n",
+       "      <th id=\"T_556fc_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
+       "      <th id=\"T_556fc_level1_row0\" class=\"row_heading level1 row0\" >Industrial pellets (nurdles)</th>\n",
+       "      <td id=\"T_556fc_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
+       "      <td id=\"T_556fc_row0_col1\" class=\"data row0 col1\" >2686</td>\n",
+       "      <td id=\"T_556fc_row0_col2\" class=\"data row0 col2\" >0.22</td>\n",
+       "      <td id=\"T_556fc_row0_col3\" class=\"data row0 col3\" >0.02</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
-       "      <th id=\"T_d0aab_level1_row1\" class=\"row_heading level1 row1\" >Cigarette filters</th>\n",
-       "      <td id=\"T_d0aab_row1_col0\" class=\"data row1 col0\" >1.12</td>\n",
-       "      <td id=\"T_d0aab_row1_col1\" class=\"data row1 col1\" >16458</td>\n",
-       "      <td id=\"T_d0aab_row1_col2\" class=\"data row1 col2\" >0.85</td>\n",
-       "      <td id=\"T_d0aab_row1_col3\" class=\"data row1 col3\" >0.15</td>\n",
+       "      <th id=\"T_556fc_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
+       "      <th id=\"T_556fc_level1_row1\" class=\"row_heading level1 row1\" >Cigarette filters</th>\n",
+       "      <td id=\"T_556fc_row1_col0\" class=\"data row1 col0\" >1.12</td>\n",
+       "      <td id=\"T_556fc_row1_col1\" class=\"data row1 col1\" >16458</td>\n",
+       "      <td id=\"T_556fc_row1_col2\" class=\"data row1 col2\" >0.85</td>\n",
+       "      <td id=\"T_556fc_row1_col3\" class=\"data row1 col3\" >0.15</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
-       "      <th id=\"T_d0aab_level1_row2\" class=\"row_heading level1 row2\" >Food wrappers; candy, snacks</th>\n",
-       "      <td id=\"T_d0aab_row2_col0\" class=\"data row2 col0\" >0.54</td>\n",
-       "      <td id=\"T_d0aab_row2_col1\" class=\"data row2 col1\" >6767</td>\n",
-       "      <td id=\"T_d0aab_row2_col2\" class=\"data row2 col2\" >0.86</td>\n",
-       "      <td id=\"T_d0aab_row2_col3\" class=\"data row2 col3\" >0.06</td>\n",
+       "      <th id=\"T_556fc_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
+       "      <th id=\"T_556fc_level1_row2\" class=\"row_heading level1 row2\" >Food wrappers; candy, snacks</th>\n",
+       "      <td id=\"T_556fc_row2_col0\" class=\"data row2 col0\" >0.54</td>\n",
+       "      <td id=\"T_556fc_row2_col1\" class=\"data row2 col1\" >6767</td>\n",
+       "      <td id=\"T_556fc_row2_col2\" class=\"data row2 col2\" >0.86</td>\n",
+       "      <td id=\"T_556fc_row2_col3\" class=\"data row2 col3\" >0.06</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
-       "      <th id=\"T_d0aab_level1_row3\" class=\"row_heading level1 row3\" >Toys and party favors</th>\n",
-       "      <td id=\"T_d0aab_row3_col0\" class=\"data row3 col0\" >0.05</td>\n",
-       "      <td id=\"T_d0aab_row3_col1\" class=\"data row3 col1\" >606</td>\n",
-       "      <td id=\"T_d0aab_row3_col2\" class=\"data row3 col2\" >0.48</td>\n",
-       "      <td id=\"T_d0aab_row3_col3\" class=\"data row3 col3\" >0.01</td>\n",
+       "      <th id=\"T_556fc_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
+       "      <th id=\"T_556fc_level1_row3\" class=\"row_heading level1 row3\" >Toys and party favors</th>\n",
+       "      <td id=\"T_556fc_row3_col0\" class=\"data row3 col0\" >0.05</td>\n",
+       "      <td id=\"T_556fc_row3_col1\" class=\"data row3 col1\" >606</td>\n",
+       "      <td id=\"T_556fc_row3_col2\" class=\"data row3 col2\" >0.48</td>\n",
+       "      <td id=\"T_556fc_row3_col3\" class=\"data row3 col3\" >0.01</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
-       "      <th id=\"T_d0aab_level1_row4\" class=\"row_heading level1 row4\" >Industrial sheeting</th>\n",
-       "      <td id=\"T_d0aab_row4_col0\" class=\"data row4 col0\" >0.30</td>\n",
-       "      <td id=\"T_d0aab_row4_col1\" class=\"data row4 col1\" >3356</td>\n",
-       "      <td id=\"T_d0aab_row4_col2\" class=\"data row4 col2\" >0.57</td>\n",
-       "      <td id=\"T_d0aab_row4_col3\" class=\"data row4 col3\" >0.03</td>\n",
+       "      <th id=\"T_556fc_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
+       "      <th id=\"T_556fc_level1_row4\" class=\"row_heading level1 row4\" >Industrial sheeting</th>\n",
+       "      <td id=\"T_556fc_row4_col0\" class=\"data row4 col0\" >0.30</td>\n",
+       "      <td id=\"T_556fc_row4_col1\" class=\"data row4 col1\" >3356</td>\n",
+       "      <td id=\"T_556fc_row4_col2\" class=\"data row4 col2\" >0.57</td>\n",
+       "      <td id=\"T_556fc_row4_col3\" class=\"data row4 col3\" >0.03</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
-       "      <th id=\"T_d0aab_level1_row5\" class=\"row_heading level1 row5\" >Shotgun cartridges</th>\n",
-       "      <td id=\"T_d0aab_row5_col0\" class=\"data row5 col0\" >0.08</td>\n",
-       "      <td id=\"T_d0aab_row5_col1\" class=\"data row5 col1\" >1030</td>\n",
-       "      <td id=\"T_d0aab_row5_col2\" class=\"data row5 col2\" >0.48</td>\n",
-       "      <td id=\"T_d0aab_row5_col3\" class=\"data row5 col3\" >0.01</td>\n",
+       "      <th id=\"T_556fc_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
+       "      <th id=\"T_556fc_level1_row5\" class=\"row_heading level1 row5\" >Shotgun cartridges</th>\n",
+       "      <td id=\"T_556fc_row5_col0\" class=\"data row5 col0\" >0.08</td>\n",
+       "      <td id=\"T_556fc_row5_col1\" class=\"data row5 col1\" >1030</td>\n",
+       "      <td id=\"T_556fc_row5_col2\" class=\"data row5 col2\" >0.48</td>\n",
+       "      <td id=\"T_556fc_row5_col3\" class=\"data row5 col3\" >0.01</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row6\" class=\"row_heading level0 row6\" >G89</th>\n",
-       "      <th id=\"T_d0aab_level1_row6\" class=\"row_heading level1 row6\" >Plastic construction waste</th>\n",
-       "      <td id=\"T_d0aab_row6_col0\" class=\"data row6 col0\" >0.14</td>\n",
-       "      <td id=\"T_d0aab_row6_col1\" class=\"data row6 col1\" >1970</td>\n",
-       "      <td id=\"T_d0aab_row6_col2\" class=\"data row6 col2\" >0.51</td>\n",
-       "      <td id=\"T_d0aab_row6_col3\" class=\"data row6 col3\" >0.02</td>\n",
+       "      <th id=\"T_556fc_level0_row6\" class=\"row_heading level0 row6\" >G89</th>\n",
+       "      <th id=\"T_556fc_level1_row6\" class=\"row_heading level1 row6\" >Plastic construction waste</th>\n",
+       "      <td id=\"T_556fc_row6_col0\" class=\"data row6 col0\" >0.14</td>\n",
+       "      <td id=\"T_556fc_row6_col1\" class=\"data row6 col1\" >1970</td>\n",
+       "      <td id=\"T_556fc_row6_col2\" class=\"data row6 col2\" >0.51</td>\n",
+       "      <td id=\"T_556fc_row6_col3\" class=\"data row6 col3\" >0.02</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row7\" class=\"row_heading level0 row7\" >G95</th>\n",
-       "      <th id=\"T_d0aab_level1_row7\" class=\"row_heading level1 row7\" >Cotton bud/swab sticks</th>\n",
-       "      <td id=\"T_d0aab_row7_col0\" class=\"data row7 col0\" >0.39</td>\n",
-       "      <td id=\"T_d0aab_row7_col1\" class=\"data row7 col1\" >4777</td>\n",
-       "      <td id=\"T_d0aab_row7_col2\" class=\"data row7 col2\" >0.74</td>\n",
-       "      <td id=\"T_d0aab_row7_col3\" class=\"data row7 col3\" >0.04</td>\n",
+       "      <th id=\"T_556fc_level0_row7\" class=\"row_heading level0 row7\" >G95</th>\n",
+       "      <th id=\"T_556fc_level1_row7\" class=\"row_heading level1 row7\" >Cotton bud/swab sticks</th>\n",
+       "      <td id=\"T_556fc_row7_col0\" class=\"data row7 col0\" >0.39</td>\n",
+       "      <td id=\"T_556fc_row7_col1\" class=\"data row7 col1\" >4777</td>\n",
+       "      <td id=\"T_556fc_row7_col2\" class=\"data row7 col2\" >0.74</td>\n",
+       "      <td id=\"T_556fc_row7_col3\" class=\"data row7 col3\" >0.04</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row8\" class=\"row_heading level0 row8\" >G96</th>\n",
-       "      <th id=\"T_d0aab_level1_row8\" class=\"row_heading level1 row8\" >Sanitary pads /panty liners/tampons and applicators</th>\n",
-       "      <td id=\"T_d0aab_row8_col0\" class=\"data row8 col0\" >0.04</td>\n",
-       "      <td id=\"T_d0aab_row8_col1\" class=\"data row8 col1\" >373</td>\n",
-       "      <td id=\"T_d0aab_row8_col2\" class=\"data row8 col2\" >0.29</td>\n",
-       "      <td id=\"T_d0aab_row8_col3\" class=\"data row8 col3\" >0.00</td>\n",
+       "      <th id=\"T_556fc_level0_row8\" class=\"row_heading level0 row8\" >G96</th>\n",
+       "      <th id=\"T_556fc_level1_row8\" class=\"row_heading level1 row8\" >Sanitary pads /panty liners/tampons and applicators</th>\n",
+       "      <td id=\"T_556fc_row8_col0\" class=\"data row8 col0\" >0.04</td>\n",
+       "      <td id=\"T_556fc_row8_col1\" class=\"data row8 col1\" >373</td>\n",
+       "      <td id=\"T_556fc_row8_col2\" class=\"data row8 col2\" >0.29</td>\n",
+       "      <td id=\"T_556fc_row8_col3\" class=\"data row8 col3\" >0.00</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row9\" class=\"row_heading level0 row9\" >Gcaps</th>\n",
-       "      <th id=\"T_d0aab_level1_row9\" class=\"row_heading level1 row9\" >Plastic bottle lids</th>\n",
-       "      <td id=\"T_d0aab_row9_col0\" class=\"data row9 col0\" >0.31</td>\n",
-       "      <td id=\"T_d0aab_row9_col1\" class=\"data row9 col1\" >3953</td>\n",
-       "      <td id=\"T_d0aab_row9_col2\" class=\"data row9 col2\" >0.84</td>\n",
-       "      <td id=\"T_d0aab_row9_col3\" class=\"data row9 col3\" >0.04</td>\n",
+       "      <th id=\"T_556fc_level0_row9\" class=\"row_heading level0 row9\" >Gcaps</th>\n",
+       "      <th id=\"T_556fc_level1_row9\" class=\"row_heading level1 row9\" >Plastic bottle lids</th>\n",
+       "      <td id=\"T_556fc_row9_col0\" class=\"data row9 col0\" >0.31</td>\n",
+       "      <td id=\"T_556fc_row9_col1\" class=\"data row9 col1\" >3953</td>\n",
+       "      <td id=\"T_556fc_row9_col2\" class=\"data row9 col2\" >0.84</td>\n",
+       "      <td id=\"T_556fc_row9_col3\" class=\"data row9 col3\" >0.04</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row10\" class=\"row_heading level0 row10\" >Gfoam</th>\n",
-       "      <th id=\"T_d0aab_level1_row10\" class=\"row_heading level1 row10\" >Expanded polystyrene</th>\n",
-       "      <td id=\"T_d0aab_row10_col0\" class=\"data row10 col0\" >1.02</td>\n",
-       "      <td id=\"T_d0aab_row10_col1\" class=\"data row10 col1\" >12871</td>\n",
-       "      <td id=\"T_d0aab_row10_col2\" class=\"data row10 col2\" >0.81</td>\n",
-       "      <td id=\"T_d0aab_row10_col3\" class=\"data row10 col3\" >0.12</td>\n",
+       "      <th id=\"T_556fc_level0_row10\" class=\"row_heading level0 row10\" >Gfoam</th>\n",
+       "      <th id=\"T_556fc_level1_row10\" class=\"row_heading level1 row10\" >Expanded polystyrene</th>\n",
+       "      <td id=\"T_556fc_row10_col0\" class=\"data row10 col0\" >1.02</td>\n",
+       "      <td id=\"T_556fc_row10_col1\" class=\"data row10 col1\" >12871</td>\n",
+       "      <td id=\"T_556fc_row10_col2\" class=\"data row10 col2\" >0.81</td>\n",
+       "      <td id=\"T_556fc_row10_col3\" class=\"data row10 col3\" >0.12</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_d0aab_level0_row11\" class=\"row_heading level0 row11\" >Gfrags</th>\n",
-       "      <th id=\"T_d0aab_level1_row11\" class=\"row_heading level1 row11\" >Fragmented plastics</th>\n",
-       "      <td id=\"T_d0aab_row11_col0\" class=\"data row11 col0\" >1.34</td>\n",
-       "      <td id=\"T_d0aab_row11_col1\" class=\"data row11 col1\" >17479</td>\n",
-       "      <td id=\"T_d0aab_row11_col2\" class=\"data row11 col2\" >0.93</td>\n",
-       "      <td id=\"T_d0aab_row11_col3\" class=\"data row11 col3\" >0.16</td>\n",
+       "      <th id=\"T_556fc_level0_row11\" class=\"row_heading level0 row11\" >Gfrags</th>\n",
+       "      <th id=\"T_556fc_level1_row11\" class=\"row_heading level1 row11\" >Fragmented plastics</th>\n",
+       "      <td id=\"T_556fc_row11_col0\" class=\"data row11 col0\" >1.34</td>\n",
+       "      <td id=\"T_556fc_row11_col1\" class=\"data row11 col1\" >17479</td>\n",
+       "      <td id=\"T_556fc_row11_col2\" class=\"data row11 col2\" >0.93</td>\n",
+       "      <td id=\"T_556fc_row11_col3\" class=\"data row11 col3\" >0.16</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f602427b50>"
+       "<pandas.io.formats.style.Styler at 0x7c6c3ed037f0>"
       ]
      },
      "execution_count": 6,
@@ -759,18 +759,25 @@
    "execution_count": 7,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_91665 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_91665 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_91665 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_91665 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_91665 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_91665\">\n  <caption>The number of different locations and cities for the data. Note that there are 31 different municipalitites in all.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_91665_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_91665_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_91665_level0_row0\" class=\"row_heading level0 row0\" >Number of cities</th>\n      <td id=\"T_91665_row0_col0\" class=\"data row0 col0\" >21</td>\n      <td id=\"T_91665_row0_col1\" class=\"data row0 col1\" >19</td>\n    </tr>\n    <tr>\n      <th id=\"T_91665_level0_row1\" class=\"row_heading level0 row1\" >Number of locations</th>\n      <td id=\"T_91665_row1_col0\" class=\"data row1 col0\" >48</td>\n      <td id=\"T_91665_row1_col1\" class=\"data row1 col1\" >23</td>\n    </tr>\n    <tr>\n      <th id=\"T_91665_level0_row2\" class=\"row_heading level0 row2\" >Total objects</th>\n      <td id=\"T_91665_row2_col0\" class=\"data row2 col0\" >57,623</td>\n      <td id=\"T_91665_row2_col1\" class=\"data row2 col1\" >14,703</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x76f602293490>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_540d8 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_540d8 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_540d8 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_540d8 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_540d8 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_540d8\">\n  <caption>The number of different locations and cities for the data. Note that there are 31 different municipalitites in all.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_540d8_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_540d8_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_540d8_level0_row0\" class=\"row_heading level0 row0\" >Number of cities</th>\n      <td id=\"T_540d8_row0_col0\" class=\"data row0 col0\" >21</td>\n      <td id=\"T_540d8_row0_col1\" class=\"data row0 col1\" >19</td>\n    </tr>\n    <tr>\n      <th id=\"T_540d8_level0_row1\" class=\"row_heading level0 row1\" >Number of locations</th>\n      <td id=\"T_540d8_row1_col0\" class=\"data row1 col0\" >48</td>\n      <td id=\"T_540d8_row1_col1\" class=\"data row1 col1\" >23</td>\n    </tr>\n    <tr>\n      <th id=\"T_540d8_level0_row2\" class=\"row_heading level0 row2\" >Total objects</th>\n      <td id=\"T_540d8_row2_col0\" class=\"data row2 col0\" >57,623</td>\n      <td id=\"T_540d8_row2_col1\" class=\"data row2 col1\" >14,703</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7c6c3ec92fa0>"
      },
      "metadata": {
       "scrapbook": {
@@ -832,7 +839,9 @@
     "slideshow": {
      "slide_type": ""
     },
-    "tags": []
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
@@ -870,12 +879,19 @@
    "execution_count": 9,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
@@ -909,18 +925,25 @@
    "execution_count": 10,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_4afd1 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_4afd1 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_4afd1 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_4afd1 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_4afd1 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_4afd1\">\n  <caption>The observed values from the training and testing data. Remark that the testing data is only 22% of all the data. This is because we are only in the first year of a six year sampling period</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_4afd1_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_4afd1_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_4afd1_level0_row0\" class=\"row_heading level0 row0\" >weight all samples</th>\n      <td id=\"T_4afd1_row0_col0\" class=\"data row0 col0\" >0.78</td>\n      <td id=\"T_4afd1_row0_col1\" class=\"data row0 col1\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row1\" class=\"row_heading level0 row1\" >Number of samples</th>\n      <td id=\"T_4afd1_row1_col0\" class=\"data row1 col0\" >263</td>\n      <td id=\"T_4afd1_row1_col1\" class=\"data row1 col1\" >73</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row2\" class=\"row_heading level0 row2\" >Median</th>\n      <td id=\"T_4afd1_row2_col0\" class=\"data row2 col0\" >3.47</td>\n      <td id=\"T_4afd1_row2_col1\" class=\"data row2 col1\" >2.28</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row3\" class=\"row_heading level0 row3\" >Average</th>\n      <td id=\"T_4afd1_row3_col0\" class=\"data row3 col0\" >6.13</td>\n      <td id=\"T_4afd1_row3_col1\" class=\"data row3 col1\" >3.25</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row4\" class=\"row_heading level0 row4\" >25th percentile</th>\n      <td id=\"T_4afd1_row4_col0\" class=\"data row4 col0\" >1.52</td>\n      <td id=\"T_4afd1_row4_col1\" class=\"data row4 col1\" >0.78</td>\n    </tr>\n    <tr>\n      <th id=\"T_4afd1_level0_row5\" class=\"row_heading level0 row5\" >75th percentile</th>\n      <td id=\"T_4afd1_row5_col0\" class=\"data row5 col0\" >6.69</td>\n      <td id=\"T_4afd1_row5_col1\" class=\"data row5 col1\" >4.31</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x76f65a0b9dc0>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_59f14 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_59f14 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_59f14 tr {\n  font-size: 14px;\n  padding: 12px;\n}\n#T_59f14 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_59f14 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_59f14\">\n  <caption>The observed values from the training and testing data. Remark that the testing data is only 22% of all the data. This is because we are only in the first year of a six year sampling period</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_59f14_level0_col0\" class=\"col_heading level0 col0\" >before may 2021</th>\n      <th id=\"T_59f14_level0_col1\" class=\"col_heading level0 col1\" >after may 2021</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_59f14_level0_row0\" class=\"row_heading level0 row0\" >weight all samples</th>\n      <td id=\"T_59f14_row0_col0\" class=\"data row0 col0\" >0.78</td>\n      <td id=\"T_59f14_row0_col1\" class=\"data row0 col1\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row1\" class=\"row_heading level0 row1\" >Number of samples</th>\n      <td id=\"T_59f14_row1_col0\" class=\"data row1 col0\" >263</td>\n      <td id=\"T_59f14_row1_col1\" class=\"data row1 col1\" >73</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row2\" class=\"row_heading level0 row2\" >Median</th>\n      <td id=\"T_59f14_row2_col0\" class=\"data row2 col0\" >3.47</td>\n      <td id=\"T_59f14_row2_col1\" class=\"data row2 col1\" >2.28</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row3\" class=\"row_heading level0 row3\" >Average</th>\n      <td id=\"T_59f14_row3_col0\" class=\"data row3 col0\" >6.13</td>\n      <td id=\"T_59f14_row3_col1\" class=\"data row3 col1\" >3.25</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row4\" class=\"row_heading level0 row4\" >25th percentile</th>\n      <td id=\"T_59f14_row4_col0\" class=\"data row4 col0\" >1.52</td>\n      <td id=\"T_59f14_row4_col1\" class=\"data row4 col1\" >0.78</td>\n    </tr>\n    <tr>\n      <th id=\"T_59f14_level0_row5\" class=\"row_heading level0 row5\" >75th percentile</th>\n      <td id=\"T_59f14_row5_col0\" class=\"data row5 col0\" >6.69</td>\n      <td id=\"T_59f14_row5_col1\" class=\"data row5 col1\" >4.31</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7c6bfdf61a00>"
      },
      "metadata": {
       "scrapbook": {
@@ -974,12 +997,19 @@
    "execution_count": 11,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1079,12 +1109,19 @@
    "execution_count": 12,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1096,12 +1133,19 @@
    "execution_count": 13,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1172,12 +1216,19 @@
    "execution_count": 14,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1272,33 +1323,40 @@
    "execution_count": 15,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_0e66b tr:nth-child(even) {\n",
+       "#T_9a101 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_0e66b tr:nth-child(odd) {\n",
+       "#T_9a101 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_0e66b tr {\n",
+       "#T_9a101 tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_0e66b th:nth-child(1) {\n",
+       "#T_9a101 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_0e66b caption {\n",
+       "#T_9a101 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1306,120 +1364,120 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_0e66b\">\n",
+       "<table id=\"T_9a101\">\n",
        "  <caption>Table 4: The 94% probability interval of the objects of interest for Saint Sulpice. The median value is used for the predictions</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_0e66b_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_0e66b_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_0e66b_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_0e66b_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_0e66b_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_0e66b_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_0e66b_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_0e66b_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_0e66b_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_0e66b_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_9a101_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_9a101_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_9a101_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_9a101_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_9a101_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_9a101_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_9a101_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_9a101_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_9a101_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_9a101_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row0\" class=\"row_heading level0 row0\" >3%</th>\n",
-       "      <td id=\"T_0e66b_row0_col0\" class=\"data row0 col0\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col1\" class=\"data row0 col1\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col2\" class=\"data row0 col2\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col6\" class=\"data row0 col6\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col7\" class=\"data row0 col7\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col8\" class=\"data row0 col8\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row0_col9\" class=\"data row0 col9\" >0.00</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row1\" class=\"row_heading level0 row1\" >25%</th>\n",
-       "      <td id=\"T_0e66b_row1_col0\" class=\"data row1 col0\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col2\" class=\"data row1 col2\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col3\" class=\"data row1 col3\" >0.01</td>\n",
-       "      <td id=\"T_0e66b_row1_col4\" class=\"data row1 col4\" >0.01</td>\n",
-       "      <td id=\"T_0e66b_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col6\" class=\"data row1 col6\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row1_col7\" class=\"data row1 col7\" >0.01</td>\n",
-       "      <td id=\"T_0e66b_row1_col8\" class=\"data row1 col8\" >0.03</td>\n",
-       "      <td id=\"T_0e66b_row1_col9\" class=\"data row1 col9\" >0.00</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row2\" class=\"row_heading level0 row2\" >48%</th>\n",
-       "      <td id=\"T_0e66b_row2_col0\" class=\"data row2 col0\" >0.03</td>\n",
-       "      <td id=\"T_0e66b_row2_col1\" class=\"data row2 col1\" >0.42</td>\n",
-       "      <td id=\"T_0e66b_row2_col2\" class=\"data row2 col2\" >0.13</td>\n",
-       "      <td id=\"T_0e66b_row2_col3\" class=\"data row2 col3\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row2_col4\" class=\"data row2 col4\" >0.14</td>\n",
-       "      <td id=\"T_0e66b_row2_col5\" class=\"data row2 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row2_col6\" class=\"data row2 col6\" >0.30</td>\n",
-       "      <td id=\"T_0e66b_row2_col7\" class=\"data row2 col7\" >0.08</td>\n",
-       "      <td id=\"T_0e66b_row2_col8\" class=\"data row2 col8\" >0.12</td>\n",
-       "      <td id=\"T_0e66b_row2_col9\" class=\"data row2 col9\" >0.35</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row3\" class=\"row_heading level0 row3\" >50%</th>\n",
-       "      <td id=\"T_0e66b_row3_col0\" class=\"data row3 col0\" >0.08</td>\n",
-       "      <td id=\"T_0e66b_row3_col1\" class=\"data row3 col1\" >0.45</td>\n",
-       "      <td id=\"T_0e66b_row3_col2\" class=\"data row3 col2\" >0.13</td>\n",
-       "      <td id=\"T_0e66b_row3_col3\" class=\"data row3 col3\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row3_col4\" class=\"data row3 col4\" >0.16</td>\n",
-       "      <td id=\"T_0e66b_row3_col5\" class=\"data row3 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row3_col6\" class=\"data row3 col6\" >0.32</td>\n",
-       "      <td id=\"T_0e66b_row3_col7\" class=\"data row3 col7\" >0.09</td>\n",
-       "      <td id=\"T_0e66b_row3_col8\" class=\"data row3 col8\" >0.14</td>\n",
-       "      <td id=\"T_0e66b_row3_col9\" class=\"data row3 col9\" >0.41</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row4\" class=\"row_heading level0 row4\" >52%</th>\n",
-       "      <td id=\"T_0e66b_row4_col0\" class=\"data row4 col0\" >0.10</td>\n",
-       "      <td id=\"T_0e66b_row4_col1\" class=\"data row4 col1\" >0.46</td>\n",
-       "      <td id=\"T_0e66b_row4_col2\" class=\"data row4 col2\" >0.13</td>\n",
-       "      <td id=\"T_0e66b_row4_col3\" class=\"data row4 col3\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row4_col4\" class=\"data row4 col4\" >0.17</td>\n",
-       "      <td id=\"T_0e66b_row4_col5\" class=\"data row4 col5\" >0.00</td>\n",
-       "      <td id=\"T_0e66b_row4_col6\" class=\"data row4 col6\" >0.34</td>\n",
-       "      <td id=\"T_0e66b_row4_col7\" class=\"data row4 col7\" >0.09</td>\n",
-       "      <td id=\"T_0e66b_row4_col8\" class=\"data row4 col8\" >0.14</td>\n",
-       "      <td id=\"T_0e66b_row4_col9\" class=\"data row4 col9\" >0.50</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row5\" class=\"row_heading level0 row5\" >75%</th>\n",
-       "      <td id=\"T_0e66b_row5_col0\" class=\"data row5 col0\" >0.54</td>\n",
-       "      <td id=\"T_0e66b_row5_col1\" class=\"data row5 col1\" >0.66</td>\n",
-       "      <td id=\"T_0e66b_row5_col2\" class=\"data row5 col2\" >0.48</td>\n",
-       "      <td id=\"T_0e66b_row5_col3\" class=\"data row5 col3\" >0.06</td>\n",
-       "      <td id=\"T_0e66b_row5_col4\" class=\"data row5 col4\" >0.31</td>\n",
-       "      <td id=\"T_0e66b_row5_col5\" class=\"data row5 col5\" >0.04</td>\n",
-       "      <td id=\"T_0e66b_row5_col6\" class=\"data row5 col6\" >0.52</td>\n",
-       "      <td id=\"T_0e66b_row5_col7\" class=\"data row5 col7\" >0.12</td>\n",
-       "      <td id=\"T_0e66b_row5_col8\" class=\"data row5 col8\" >0.23</td>\n",
-       "      <td id=\"T_0e66b_row5_col9\" class=\"data row5 col9\" >0.82</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_0e66b_level0_row6\" class=\"row_heading level0 row6\" >97%</th>\n",
-       "      <td id=\"T_0e66b_row6_col0\" class=\"data row6 col0\" >1.39</td>\n",
-       "      <td id=\"T_0e66b_row6_col1\" class=\"data row6 col1\" >1.29</td>\n",
-       "      <td id=\"T_0e66b_row6_col2\" class=\"data row6 col2\" >0.91</td>\n",
-       "      <td id=\"T_0e66b_row6_col3\" class=\"data row6 col3\" >0.11</td>\n",
-       "      <td id=\"T_0e66b_row6_col4\" class=\"data row6 col4\" >2.83</td>\n",
-       "      <td id=\"T_0e66b_row6_col5\" class=\"data row6 col5\" >0.09</td>\n",
-       "      <td id=\"T_0e66b_row6_col6\" class=\"data row6 col6\" >1.00</td>\n",
-       "      <td id=\"T_0e66b_row6_col7\" class=\"data row6 col7\" >0.22</td>\n",
-       "      <td id=\"T_0e66b_row6_col8\" class=\"data row6 col8\" >0.41</td>\n",
-       "      <td id=\"T_0e66b_row6_col9\" class=\"data row6 col9\" >2.75</td>\n",
+       "      <th id=\"T_9a101_level0_row0\" class=\"row_heading level0 row0\" >3%</th>\n",
+       "      <td id=\"T_9a101_row0_col0\" class=\"data row0 col0\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col1\" class=\"data row0 col1\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col2\" class=\"data row0 col2\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col6\" class=\"data row0 col6\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col7\" class=\"data row0 col7\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col8\" class=\"data row0 col8\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row0_col9\" class=\"data row0 col9\" >0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row1\" class=\"row_heading level0 row1\" >25%</th>\n",
+       "      <td id=\"T_9a101_row1_col0\" class=\"data row1 col0\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col1\" class=\"data row1 col1\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row1_col2\" class=\"data row1 col2\" >0.03</td>\n",
+       "      <td id=\"T_9a101_row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col4\" class=\"data row1 col4\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col6\" class=\"data row1 col6\" >0.01</td>\n",
+       "      <td id=\"T_9a101_row1_col7\" class=\"data row1 col7\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row1_col8\" class=\"data row1 col8\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row1_col9\" class=\"data row1 col9\" >0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row2\" class=\"row_heading level0 row2\" >48%</th>\n",
+       "      <td id=\"T_9a101_row2_col0\" class=\"data row2 col0\" >0.08</td>\n",
+       "      <td id=\"T_9a101_row2_col1\" class=\"data row2 col1\" >0.46</td>\n",
+       "      <td id=\"T_9a101_row2_col2\" class=\"data row2 col2\" >0.35</td>\n",
+       "      <td id=\"T_9a101_row2_col3\" class=\"data row2 col3\" >0.03</td>\n",
+       "      <td id=\"T_9a101_row2_col4\" class=\"data row2 col4\" >0.16</td>\n",
+       "      <td id=\"T_9a101_row2_col5\" class=\"data row2 col5\" >0.00</td>\n",
+       "      <td id=\"T_9a101_row2_col6\" class=\"data row2 col6\" >0.32</td>\n",
+       "      <td id=\"T_9a101_row2_col7\" class=\"data row2 col7\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row2_col8\" class=\"data row2 col8\" >0.11</td>\n",
+       "      <td id=\"T_9a101_row2_col9\" class=\"data row2 col9\" >0.68</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row3\" class=\"row_heading level0 row3\" >50%</th>\n",
+       "      <td id=\"T_9a101_row3_col0\" class=\"data row3 col0\" >0.12</td>\n",
+       "      <td id=\"T_9a101_row3_col1\" class=\"data row3 col1\" >0.47</td>\n",
+       "      <td id=\"T_9a101_row3_col2\" class=\"data row3 col2\" >0.39</td>\n",
+       "      <td id=\"T_9a101_row3_col3\" class=\"data row3 col3\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row3_col4\" class=\"data row3 col4\" >0.16</td>\n",
+       "      <td id=\"T_9a101_row3_col5\" class=\"data row3 col5\" >0.01</td>\n",
+       "      <td id=\"T_9a101_row3_col6\" class=\"data row3 col6\" >0.32</td>\n",
+       "      <td id=\"T_9a101_row3_col7\" class=\"data row3 col7\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row3_col8\" class=\"data row3 col8\" >0.11</td>\n",
+       "      <td id=\"T_9a101_row3_col9\" class=\"data row3 col9\" >0.74</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row4\" class=\"row_heading level0 row4\" >52%</th>\n",
+       "      <td id=\"T_9a101_row4_col0\" class=\"data row4 col0\" >0.22</td>\n",
+       "      <td id=\"T_9a101_row4_col1\" class=\"data row4 col1\" >0.48</td>\n",
+       "      <td id=\"T_9a101_row4_col2\" class=\"data row4 col2\" >0.43</td>\n",
+       "      <td id=\"T_9a101_row4_col3\" class=\"data row4 col3\" >0.04</td>\n",
+       "      <td id=\"T_9a101_row4_col4\" class=\"data row4 col4\" >0.22</td>\n",
+       "      <td id=\"T_9a101_row4_col5\" class=\"data row4 col5\" >0.02</td>\n",
+       "      <td id=\"T_9a101_row4_col6\" class=\"data row4 col6\" >0.34</td>\n",
+       "      <td id=\"T_9a101_row4_col7\" class=\"data row4 col7\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row4_col8\" class=\"data row4 col8\" >0.12</td>\n",
+       "      <td id=\"T_9a101_row4_col9\" class=\"data row4 col9\" >0.74</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row5\" class=\"row_heading level0 row5\" >75%</th>\n",
+       "      <td id=\"T_9a101_row5_col0\" class=\"data row5 col0\" >0.68</td>\n",
+       "      <td id=\"T_9a101_row5_col1\" class=\"data row5 col1\" >0.93</td>\n",
+       "      <td id=\"T_9a101_row5_col2\" class=\"data row5 col2\" >0.57</td>\n",
+       "      <td id=\"T_9a101_row5_col3\" class=\"data row5 col3\" >0.08</td>\n",
+       "      <td id=\"T_9a101_row5_col4\" class=\"data row5 col4\" >0.33</td>\n",
+       "      <td id=\"T_9a101_row5_col5\" class=\"data row5 col5\" >0.05</td>\n",
+       "      <td id=\"T_9a101_row5_col6\" class=\"data row5 col6\" >0.52</td>\n",
+       "      <td id=\"T_9a101_row5_col7\" class=\"data row5 col7\" >0.08</td>\n",
+       "      <td id=\"T_9a101_row5_col8\" class=\"data row5 col8\" >0.23</td>\n",
+       "      <td id=\"T_9a101_row5_col9\" class=\"data row5 col9\" >1.24</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_9a101_level0_row6\" class=\"row_heading level0 row6\" >97%</th>\n",
+       "      <td id=\"T_9a101_row6_col0\" class=\"data row6 col0\" >1.46</td>\n",
+       "      <td id=\"T_9a101_row6_col1\" class=\"data row6 col1\" >1.47</td>\n",
+       "      <td id=\"T_9a101_row6_col2\" class=\"data row6 col2\" >1.21</td>\n",
+       "      <td id=\"T_9a101_row6_col3\" class=\"data row6 col3\" >0.11</td>\n",
+       "      <td id=\"T_9a101_row6_col4\" class=\"data row6 col4\" >0.64</td>\n",
+       "      <td id=\"T_9a101_row6_col5\" class=\"data row6 col5\" >5.58</td>\n",
+       "      <td id=\"T_9a101_row6_col6\" class=\"data row6 col6\" >1.11</td>\n",
+       "      <td id=\"T_9a101_row6_col7\" class=\"data row6 col7\" >0.20</td>\n",
+       "      <td id=\"T_9a101_row6_col8\" class=\"data row6 col8\" >0.50</td>\n",
+       "      <td id=\"T_9a101_row6_col9\" class=\"data row6 col9\" >5.05</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5cff55910>"
+       "<pandas.io.formats.style.Styler at 0x7c6c3ec29580>"
       ]
      },
      "execution_count": 15,
@@ -1471,12 +1529,19 @@
    "execution_count": 16,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1507,12 +1572,19 @@
    "execution_count": 17,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [],
    "source": [
@@ -1525,33 +1597,40 @@
    "execution_count": 18,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_ac8e3 tr:nth-child(even) {\n",
+       "#T_abf7a tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_ac8e3 tr:nth-child(odd) {\n",
+       "#T_abf7a tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_ac8e3 tr {\n",
+       "#T_abf7a tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_ac8e3 th:nth-child(1) {\n",
+       "#T_abf7a th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_ac8e3 caption {\n",
+       "#T_abf7a caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1559,146 +1638,146 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_ac8e3\">\n",
+       "<table id=\"T_abf7a\">\n",
        "  <caption>Table 5: The estimated amount in pcs/meter for each object that the participants expected to find.</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_ac8e3_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_ac8e3_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_ac8e3_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_ac8e3_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_ac8e3_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_ac8e3_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_ac8e3_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_ac8e3_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_ac8e3_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_ac8e3_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_abf7a_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_abf7a_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_abf7a_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_abf7a_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_abf7a_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_abf7a_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_abf7a_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_abf7a_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_abf7a_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_abf7a_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
-       "      <td id=\"T_ac8e3_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
-       "      <td id=\"T_ac8e3_row0_col1\" class=\"data row0 col1\" >1.12</td>\n",
-       "      <td id=\"T_ac8e3_row0_col2\" class=\"data row0 col2\" >0.54</td>\n",
-       "      <td id=\"T_ac8e3_row0_col3\" class=\"data row0 col3\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row0_col4\" class=\"data row0 col4\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row0_col5\" class=\"data row0 col5\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row0_col6\" class=\"data row0 col6\" >0.39</td>\n",
-       "      <td id=\"T_ac8e3_row0_col7\" class=\"data row0 col7\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row0_col8\" class=\"data row0 col8\" >0.31</td>\n",
-       "      <td id=\"T_ac8e3_row0_col9\" class=\"data row0 col9\" >1.34</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
-       "      <td id=\"T_ac8e3_row1_col0\" class=\"data row1 col0\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row1_col1\" class=\"data row1 col1\" >0.57</td>\n",
-       "      <td id=\"T_ac8e3_row1_col2\" class=\"data row1 col2\" >0.24</td>\n",
-       "      <td id=\"T_ac8e3_row1_col3\" class=\"data row1 col3\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row1_col4\" class=\"data row1 col4\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row1_col5\" class=\"data row1 col5\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row1_col6\" class=\"data row1 col6\" >0.16</td>\n",
-       "      <td id=\"T_ac8e3_row1_col7\" class=\"data row1 col7\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row1_col8\" class=\"data row1 col8\" >0.14</td>\n",
-       "      <td id=\"T_ac8e3_row1_col9\" class=\"data row1 col9\" >0.22</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
-       "      <td id=\"T_ac8e3_row2_col0\" class=\"data row2 col0\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row2_col1\" class=\"data row2 col1\" >0.80</td>\n",
-       "      <td id=\"T_ac8e3_row2_col2\" class=\"data row2 col2\" >0.20</td>\n",
-       "      <td id=\"T_ac8e3_row2_col3\" class=\"data row2 col3\" >0.02</td>\n",
-       "      <td id=\"T_ac8e3_row2_col4\" class=\"data row2 col4\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row2_col5\" class=\"data row2 col5\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row2_col6\" class=\"data row2 col6\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row2_col7\" class=\"data row2 col7\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row2_col8\" class=\"data row2 col8\" >0.25</td>\n",
-       "      <td id=\"T_ac8e3_row2_col9\" class=\"data row2 col9\" >1.20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
-       "      <td id=\"T_ac8e3_row3_col0\" class=\"data row3 col0\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row3_col1\" class=\"data row3 col1\" >0.35</td>\n",
-       "      <td id=\"T_ac8e3_row3_col2\" class=\"data row3 col2\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row3_col3\" class=\"data row3 col3\" >0.03</td>\n",
-       "      <td id=\"T_ac8e3_row3_col4\" class=\"data row3 col4\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row3_col5\" class=\"data row3 col5\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row3_col6\" class=\"data row3 col6\" >0.06</td>\n",
-       "      <td id=\"T_ac8e3_row3_col7\" class=\"data row3 col7\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row3_col8\" class=\"data row3 col8\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row3_col9\" class=\"data row3 col9\" >0.50</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
-       "      <td id=\"T_ac8e3_row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
-       "      <td id=\"T_ac8e3_row4_col1\" class=\"data row4 col1\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row4_col2\" class=\"data row4 col2\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row4_col3\" class=\"data row4 col3\" >0.02</td>\n",
-       "      <td id=\"T_ac8e3_row4_col4\" class=\"data row4 col4\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row4_col5\" class=\"data row4 col5\" >0.00</td>\n",
-       "      <td id=\"T_ac8e3_row4_col6\" class=\"data row4 col6\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row4_col7\" class=\"data row4 col7\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row4_col8\" class=\"data row4 col8\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row4_col9\" class=\"data row4 col9\" >0.12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
-       "      <td id=\"T_ac8e3_row5_col0\" class=\"data row5 col0\" >0.15</td>\n",
-       "      <td id=\"T_ac8e3_row5_col1\" class=\"data row5 col1\" >0.50</td>\n",
-       "      <td id=\"T_ac8e3_row5_col2\" class=\"data row5 col2\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row5_col3\" class=\"data row5 col3\" >0.03</td>\n",
-       "      <td id=\"T_ac8e3_row5_col4\" class=\"data row5 col4\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row5_col5\" class=\"data row5 col5\" >0.00</td>\n",
-       "      <td id=\"T_ac8e3_row5_col6\" class=\"data row5 col6\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row5_col7\" class=\"data row5 col7\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row5_col8\" class=\"data row5 col8\" >0.20</td>\n",
-       "      <td id=\"T_ac8e3_row5_col9\" class=\"data row5 col9\" >0.20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
-       "      <td id=\"T_ac8e3_row6_col0\" class=\"data row6 col0\" >0.16</td>\n",
-       "      <td id=\"T_ac8e3_row6_col1\" class=\"data row6 col1\" >1.12</td>\n",
-       "      <td id=\"T_ac8e3_row6_col2\" class=\"data row6 col2\" >0.54</td>\n",
-       "      <td id=\"T_ac8e3_row6_col3\" class=\"data row6 col3\" >0.05</td>\n",
-       "      <td id=\"T_ac8e3_row6_col4\" class=\"data row6 col4\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row6_col5\" class=\"data row6 col5\" >0.08</td>\n",
-       "      <td id=\"T_ac8e3_row6_col6\" class=\"data row6 col6\" >0.39</td>\n",
-       "      <td id=\"T_ac8e3_row6_col7\" class=\"data row6 col7\" >0.04</td>\n",
-       "      <td id=\"T_ac8e3_row6_col8\" class=\"data row6 col8\" >0.31</td>\n",
-       "      <td id=\"T_ac8e3_row6_col9\" class=\"data row6 col9\" >1.34</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
-       "      <td id=\"T_ac8e3_row7_col0\" class=\"data row7 col0\" >6.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col1\" class=\"data row7 col1\" >3.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col2\" class=\"data row7 col2\" >0.60</td>\n",
-       "      <td id=\"T_ac8e3_row7_col3\" class=\"data row7 col3\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row7_col4\" class=\"data row7 col4\" >0.40</td>\n",
-       "      <td id=\"T_ac8e3_row7_col5\" class=\"data row7 col5\" >0.03</td>\n",
-       "      <td id=\"T_ac8e3_row7_col6\" class=\"data row7 col6\" >0.80</td>\n",
-       "      <td id=\"T_ac8e3_row7_col7\" class=\"data row7 col7\" >1.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col8\" class=\"data row7 col8\" >2.00</td>\n",
-       "      <td id=\"T_ac8e3_row7_col9\" class=\"data row7 col9\" >1.34</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_ac8e3_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
-       "      <td id=\"T_ac8e3_row8_col0\" class=\"data row8 col0\" >0.40</td>\n",
-       "      <td id=\"T_ac8e3_row8_col1\" class=\"data row8 col1\" >1.50</td>\n",
-       "      <td id=\"T_ac8e3_row8_col2\" class=\"data row8 col2\" >0.30</td>\n",
-       "      <td id=\"T_ac8e3_row8_col3\" class=\"data row8 col3\" >0.10</td>\n",
-       "      <td id=\"T_ac8e3_row8_col4\" class=\"data row8 col4\" >1.10</td>\n",
-       "      <td id=\"T_ac8e3_row8_col5\" class=\"data row8 col5\" >0.01</td>\n",
-       "      <td id=\"T_ac8e3_row8_col6\" class=\"data row8 col6\" >0.50</td>\n",
-       "      <td id=\"T_ac8e3_row8_col7\" class=\"data row8 col7\" >0.20</td>\n",
-       "      <td id=\"T_ac8e3_row8_col8\" class=\"data row8 col8\" >0.40</td>\n",
-       "      <td id=\"T_ac8e3_row8_col9\" class=\"data row8 col9\" >2.00</td>\n",
+       "      <th id=\"T_abf7a_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
+       "      <td id=\"T_abf7a_row0_col0\" class=\"data row0 col0\" >0.16</td>\n",
+       "      <td id=\"T_abf7a_row0_col1\" class=\"data row0 col1\" >1.12</td>\n",
+       "      <td id=\"T_abf7a_row0_col2\" class=\"data row0 col2\" >0.54</td>\n",
+       "      <td id=\"T_abf7a_row0_col3\" class=\"data row0 col3\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row0_col4\" class=\"data row0 col4\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row0_col5\" class=\"data row0 col5\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row0_col6\" class=\"data row0 col6\" >0.39</td>\n",
+       "      <td id=\"T_abf7a_row0_col7\" class=\"data row0 col7\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row0_col8\" class=\"data row0 col8\" >0.31</td>\n",
+       "      <td id=\"T_abf7a_row0_col9\" class=\"data row0 col9\" >1.34</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
+       "      <td id=\"T_abf7a_row1_col0\" class=\"data row1 col0\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row1_col1\" class=\"data row1 col1\" >0.57</td>\n",
+       "      <td id=\"T_abf7a_row1_col2\" class=\"data row1 col2\" >0.24</td>\n",
+       "      <td id=\"T_abf7a_row1_col3\" class=\"data row1 col3\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row1_col4\" class=\"data row1 col4\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row1_col5\" class=\"data row1 col5\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row1_col6\" class=\"data row1 col6\" >0.16</td>\n",
+       "      <td id=\"T_abf7a_row1_col7\" class=\"data row1 col7\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row1_col8\" class=\"data row1 col8\" >0.14</td>\n",
+       "      <td id=\"T_abf7a_row1_col9\" class=\"data row1 col9\" >0.22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
+       "      <td id=\"T_abf7a_row2_col0\" class=\"data row2 col0\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row2_col1\" class=\"data row2 col1\" >0.80</td>\n",
+       "      <td id=\"T_abf7a_row2_col2\" class=\"data row2 col2\" >0.20</td>\n",
+       "      <td id=\"T_abf7a_row2_col3\" class=\"data row2 col3\" >0.02</td>\n",
+       "      <td id=\"T_abf7a_row2_col4\" class=\"data row2 col4\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row2_col5\" class=\"data row2 col5\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row2_col6\" class=\"data row2 col6\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row2_col7\" class=\"data row2 col7\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row2_col8\" class=\"data row2 col8\" >0.25</td>\n",
+       "      <td id=\"T_abf7a_row2_col9\" class=\"data row2 col9\" >1.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
+       "      <td id=\"T_abf7a_row3_col0\" class=\"data row3 col0\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row3_col1\" class=\"data row3 col1\" >0.35</td>\n",
+       "      <td id=\"T_abf7a_row3_col2\" class=\"data row3 col2\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row3_col3\" class=\"data row3 col3\" >0.03</td>\n",
+       "      <td id=\"T_abf7a_row3_col4\" class=\"data row3 col4\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row3_col5\" class=\"data row3 col5\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row3_col6\" class=\"data row3 col6\" >0.06</td>\n",
+       "      <td id=\"T_abf7a_row3_col7\" class=\"data row3 col7\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row3_col8\" class=\"data row3 col8\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row3_col9\" class=\"data row3 col9\" >0.50</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
+       "      <td id=\"T_abf7a_row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
+       "      <td id=\"T_abf7a_row4_col1\" class=\"data row4 col1\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row4_col2\" class=\"data row4 col2\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row4_col3\" class=\"data row4 col3\" >0.02</td>\n",
+       "      <td id=\"T_abf7a_row4_col4\" class=\"data row4 col4\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row4_col5\" class=\"data row4 col5\" >0.00</td>\n",
+       "      <td id=\"T_abf7a_row4_col6\" class=\"data row4 col6\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row4_col7\" class=\"data row4 col7\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row4_col8\" class=\"data row4 col8\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row4_col9\" class=\"data row4 col9\" >0.12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
+       "      <td id=\"T_abf7a_row5_col0\" class=\"data row5 col0\" >0.15</td>\n",
+       "      <td id=\"T_abf7a_row5_col1\" class=\"data row5 col1\" >0.50</td>\n",
+       "      <td id=\"T_abf7a_row5_col2\" class=\"data row5 col2\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row5_col3\" class=\"data row5 col3\" >0.03</td>\n",
+       "      <td id=\"T_abf7a_row5_col4\" class=\"data row5 col4\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row5_col5\" class=\"data row5 col5\" >0.00</td>\n",
+       "      <td id=\"T_abf7a_row5_col6\" class=\"data row5 col6\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row5_col7\" class=\"data row5 col7\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row5_col8\" class=\"data row5 col8\" >0.20</td>\n",
+       "      <td id=\"T_abf7a_row5_col9\" class=\"data row5 col9\" >0.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
+       "      <td id=\"T_abf7a_row6_col0\" class=\"data row6 col0\" >0.16</td>\n",
+       "      <td id=\"T_abf7a_row6_col1\" class=\"data row6 col1\" >1.12</td>\n",
+       "      <td id=\"T_abf7a_row6_col2\" class=\"data row6 col2\" >0.54</td>\n",
+       "      <td id=\"T_abf7a_row6_col3\" class=\"data row6 col3\" >0.05</td>\n",
+       "      <td id=\"T_abf7a_row6_col4\" class=\"data row6 col4\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row6_col5\" class=\"data row6 col5\" >0.08</td>\n",
+       "      <td id=\"T_abf7a_row6_col6\" class=\"data row6 col6\" >0.39</td>\n",
+       "      <td id=\"T_abf7a_row6_col7\" class=\"data row6 col7\" >0.04</td>\n",
+       "      <td id=\"T_abf7a_row6_col8\" class=\"data row6 col8\" >0.31</td>\n",
+       "      <td id=\"T_abf7a_row6_col9\" class=\"data row6 col9\" >1.34</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
+       "      <td id=\"T_abf7a_row7_col0\" class=\"data row7 col0\" >6.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col1\" class=\"data row7 col1\" >3.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col2\" class=\"data row7 col2\" >0.60</td>\n",
+       "      <td id=\"T_abf7a_row7_col3\" class=\"data row7 col3\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row7_col4\" class=\"data row7 col4\" >0.40</td>\n",
+       "      <td id=\"T_abf7a_row7_col5\" class=\"data row7 col5\" >0.03</td>\n",
+       "      <td id=\"T_abf7a_row7_col6\" class=\"data row7 col6\" >0.80</td>\n",
+       "      <td id=\"T_abf7a_row7_col7\" class=\"data row7 col7\" >1.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col8\" class=\"data row7 col8\" >2.00</td>\n",
+       "      <td id=\"T_abf7a_row7_col9\" class=\"data row7 col9\" >1.34</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_abf7a_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
+       "      <td id=\"T_abf7a_row8_col0\" class=\"data row8 col0\" >0.40</td>\n",
+       "      <td id=\"T_abf7a_row8_col1\" class=\"data row8 col1\" >1.50</td>\n",
+       "      <td id=\"T_abf7a_row8_col2\" class=\"data row8 col2\" >0.30</td>\n",
+       "      <td id=\"T_abf7a_row8_col3\" class=\"data row8 col3\" >0.10</td>\n",
+       "      <td id=\"T_abf7a_row8_col4\" class=\"data row8 col4\" >1.10</td>\n",
+       "      <td id=\"T_abf7a_row8_col5\" class=\"data row8 col5\" >0.01</td>\n",
+       "      <td id=\"T_abf7a_row8_col6\" class=\"data row8 col6\" >0.50</td>\n",
+       "      <td id=\"T_abf7a_row8_col7\" class=\"data row8 col7\" >0.20</td>\n",
+       "      <td id=\"T_abf7a_row8_col8\" class=\"data row8 col8\" >0.40</td>\n",
+       "      <td id=\"T_abf7a_row8_col9\" class=\"data row8 col9\" >2.00</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c13c8700>"
+       "<pandas.io.formats.style.Styler at 0x7c6c098db280>"
       ]
      },
      "execution_count": 18,
@@ -1756,33 +1835,40 @@
    "execution_count": 19,
    "metadata": {
     "collapsed": false,
+    "editable": true,
     "jupyter": {
      "outputs_hidden": false
     },
     "pycharm": {
      "name": "#%%\n"
-    }
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
    },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_208b1 tr:nth-child(even) {\n",
+       "#T_b354f tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_208b1 tr:nth-child(odd) {\n",
+       "#T_b354f tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_208b1 tr {\n",
+       "#T_b354f tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_208b1 th:nth-child(1) {\n",
+       "#T_b354f th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_208b1 caption {\n",
+       "#T_b354f caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1790,55 +1876,55 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_208b1\">\n",
+       "<table id=\"T_b354f\">\n",
        "  <caption>Table 6: The survey results of the objects of interest on October 5, 2023 in pieces per meter</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_208b1_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_208b1_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_208b1_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_208b1_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_208b1_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_208b1_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_208b1_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_208b1_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_208b1_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_208b1_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_b354f_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_b354f_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_b354f_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_b354f_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_b354f_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_b354f_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_b354f_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_b354f_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_b354f_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_b354f_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_208b1_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
-       "      <td id=\"T_208b1_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
-       "      <td id=\"T_208b1_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
-       "      <td id=\"T_208b1_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
-       "      <td id=\"T_208b1_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
-       "      <td id=\"T_208b1_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
-       "      <td id=\"T_208b1_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
-       "      <td id=\"T_208b1_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
-       "      <td id=\"T_208b1_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_208b1_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
-       "      <td id=\"T_208b1_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
-       "      <td id=\"T_208b1_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
-       "      <td id=\"T_208b1_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
-       "      <td id=\"T_208b1_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
-       "      <td id=\"T_208b1_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
-       "      <td id=\"T_208b1_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
-       "      <td id=\"T_208b1_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
-       "      <td id=\"T_208b1_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
-       "      <td id=\"T_208b1_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
+       "      <th id=\"T_b354f_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
+       "      <td id=\"T_b354f_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
+       "      <td id=\"T_b354f_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
+       "      <td id=\"T_b354f_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
+       "      <td id=\"T_b354f_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
+       "      <td id=\"T_b354f_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
+       "      <td id=\"T_b354f_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
+       "      <td id=\"T_b354f_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
+       "      <td id=\"T_b354f_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_b354f_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
+       "      <td id=\"T_b354f_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
+       "      <td id=\"T_b354f_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
+       "      <td id=\"T_b354f_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
+       "      <td id=\"T_b354f_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
+       "      <td id=\"T_b354f_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
+       "      <td id=\"T_b354f_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
+       "      <td id=\"T_b354f_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
+       "      <td id=\"T_b354f_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
+       "      <td id=\"T_b354f_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c16359d0>"
+       "<pandas.io.formats.style.Styler at 0x7c6bfdd33850>"
       ]
      },
      "execution_count": 19,
@@ -1894,21 +1980,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_46124 tr:nth-child(even) {\n",
+       "#T_075e0 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_46124 tr:nth-child(odd) {\n",
+       "#T_075e0 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_46124 tr {\n",
+       "#T_075e0 tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_46124 th:nth-child(1) {\n",
+       "#T_075e0 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_46124 caption {\n",
+       "#T_075e0 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -1916,55 +2002,55 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_46124\">\n",
+       "<table id=\"T_075e0\">\n",
        "  <caption>Table 6: The survey results of the objects of interest on October 5, 2023 in pieces per meter</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_46124_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
-       "      <th id=\"T_46124_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
-       "      <th id=\"T_46124_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
-       "      <th id=\"T_46124_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
-       "      <th id=\"T_46124_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
-       "      <th id=\"T_46124_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
-       "      <th id=\"T_46124_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
-       "      <th id=\"T_46124_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
-       "      <th id=\"T_46124_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
-       "      <th id=\"T_46124_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
+       "      <th id=\"T_075e0_level0_col0\" class=\"col_heading level0 col0\" >G112</th>\n",
+       "      <th id=\"T_075e0_level0_col1\" class=\"col_heading level0 col1\" >G27</th>\n",
+       "      <th id=\"T_075e0_level0_col2\" class=\"col_heading level0 col2\" >G30</th>\n",
+       "      <th id=\"T_075e0_level0_col3\" class=\"col_heading level0 col3\" >G32</th>\n",
+       "      <th id=\"T_075e0_level0_col4\" class=\"col_heading level0 col4\" >G67</th>\n",
+       "      <th id=\"T_075e0_level0_col5\" class=\"col_heading level0 col5\" >G70</th>\n",
+       "      <th id=\"T_075e0_level0_col6\" class=\"col_heading level0 col6\" >G95</th>\n",
+       "      <th id=\"T_075e0_level0_col7\" class=\"col_heading level0 col7\" >G96</th>\n",
+       "      <th id=\"T_075e0_level0_col8\" class=\"col_heading level0 col8\" >Gcaps</th>\n",
+       "      <th id=\"T_075e0_level0_col9\" class=\"col_heading level0 col9\" >Gfrags</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_46124_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
-       "      <td id=\"T_46124_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
-       "      <td id=\"T_46124_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
-       "      <td id=\"T_46124_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
-       "      <td id=\"T_46124_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
-       "      <td id=\"T_46124_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
-       "      <td id=\"T_46124_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
-       "      <td id=\"T_46124_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
-       "      <td id=\"T_46124_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
-       "      <td id=\"T_46124_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
-       "      <td id=\"T_46124_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_46124_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
-       "      <td id=\"T_46124_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
-       "      <td id=\"T_46124_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
-       "      <td id=\"T_46124_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
-       "      <td id=\"T_46124_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
-       "      <td id=\"T_46124_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
-       "      <td id=\"T_46124_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
-       "      <td id=\"T_46124_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
-       "      <td id=\"T_46124_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
-       "      <td id=\"T_46124_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
-       "      <td id=\"T_46124_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
+       "      <th id=\"T_075e0_level0_row0\" class=\"row_heading level0 row0\" >tiger-duck-beach</th>\n",
+       "      <td id=\"T_075e0_row0_col0\" class=\"data row0 col0\" >0.67</td>\n",
+       "      <td id=\"T_075e0_row0_col1\" class=\"data row0 col1\" >3.64</td>\n",
+       "      <td id=\"T_075e0_row0_col2\" class=\"data row0 col2\" >0.55</td>\n",
+       "      <td id=\"T_075e0_row0_col3\" class=\"data row0 col3\" >0.18</td>\n",
+       "      <td id=\"T_075e0_row0_col4\" class=\"data row0 col4\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row0_col5\" class=\"data row0 col5\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row0_col6\" class=\"data row0 col6\" >0.79</td>\n",
+       "      <td id=\"T_075e0_row0_col7\" class=\"data row0 col7\" >0.06</td>\n",
+       "      <td id=\"T_075e0_row0_col8\" class=\"data row0 col8\" >0.18</td>\n",
+       "      <td id=\"T_075e0_row0_col9\" class=\"data row0 col9\" >10.85</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_075e0_level0_row1\" class=\"row_heading level0 row1\" >parc-des-pierrettes</th>\n",
+       "      <td id=\"T_075e0_row1_col0\" class=\"data row1 col0\" >0.08</td>\n",
+       "      <td id=\"T_075e0_row1_col1\" class=\"data row1 col1\" >1.03</td>\n",
+       "      <td id=\"T_075e0_row1_col2\" class=\"data row1 col2\" >0.14</td>\n",
+       "      <td id=\"T_075e0_row1_col3\" class=\"data row1 col3\" >0.04</td>\n",
+       "      <td id=\"T_075e0_row1_col4\" class=\"data row1 col4\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
+       "      <td id=\"T_075e0_row1_col6\" class=\"data row1 col6\" >0.24</td>\n",
+       "      <td id=\"T_075e0_row1_col7\" class=\"data row1 col7\" >0.02</td>\n",
+       "      <td id=\"T_075e0_row1_col8\" class=\"data row1 col8\" >0.24</td>\n",
+       "      <td id=\"T_075e0_row1_col9\" class=\"data row1 col9\" >5.40</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c0e1c910>"
+       "<pandas.io.formats.style.Styler at 0x7c6bfd855ac0>"
       ]
      },
      "execution_count": 20,
@@ -2018,7 +2104,7 @@
    "outputs": [
     {
      "data": {
-      "application/papermill.record/image/png": "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",
+      "application/papermill.record/image/png": "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",
       "application/papermill.record/text/plain": "<Figure size 640x480 with 1 Axes>"
      },
      "metadata": {
@@ -2165,20 +2251,6 @@
     "p_diff_predicted[\"source\"] = \"difference² of predicted\""
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "editable": true,
-    "pycharm": {
-     "name": "#%% md\n"
-    },
-    "slideshow": {
-     "slide_type": ""
-    },
-    "tags": []
-   },
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": 24,
@@ -2197,7 +2269,7 @@
    "outputs": [
     {
      "data": {
-      "application/papermill.record/image/png": "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",
+      "application/papermill.record/image/png": "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",
       "application/papermill.record/text/plain": "<Figure size 640x480 with 1 Axes>"
      },
      "metadata": {
@@ -2262,21 +2334,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_a043f tr:nth-child(even) {\n",
+       "#T_565a7 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_a043f tr:nth-child(odd) {\n",
+       "#T_565a7 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_a043f tr {\n",
+       "#T_565a7 tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_a043f th:nth-child(1) {\n",
+       "#T_565a7 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_a043f caption {\n",
+       "#T_565a7 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -2284,75 +2356,75 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_a043f\">\n",
+       "<table id=\"T_565a7\">\n",
        "  <caption>Table 7: The average difference between what was found and the estimates of the participants and what was predicted using the empirical Bayes method</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_a043f_level0_col0\" class=\"col_heading level0 col0\" colspan=\"2\">average</th>\n",
+       "      <th id=\"T_565a7_level0_col0\" class=\"col_heading level0 col0\" colspan=\"2\">average</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th class=\"index_name level1\" >source</th>\n",
-       "      <th id=\"T_a043f_level1_col0\" class=\"col_heading level1 col0\" >difference² of estimated</th>\n",
-       "      <th id=\"T_a043f_level1_col1\" class=\"col_heading level1 col1\" >difference² of predicted</th>\n",
+       "      <th id=\"T_565a7_level1_col0\" class=\"col_heading level1 col0\" >difference² of estimated</th>\n",
+       "      <th id=\"T_565a7_level1_col1\" class=\"col_heading level1 col1\" >difference² of predicted</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
-       "      <td id=\"T_a043f_row0_col0\" class=\"data row0 col0\" >1.07</td>\n",
-       "      <td id=\"T_a043f_row0_col1\" class=\"data row0 col1\" >0.29</td>\n",
+       "      <th id=\"T_565a7_level0_row0\" class=\"row_heading level0 row0\" >G112</th>\n",
+       "      <td id=\"T_565a7_row0_col0\" class=\"data row0 col0\" >1.07</td>\n",
+       "      <td id=\"T_565a7_row0_col1\" class=\"data row0 col1\" >0.29</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
-       "      <td id=\"T_a043f_row1_col0\" class=\"data row1 col0\" >2.32</td>\n",
-       "      <td id=\"T_a043f_row1_col1\" class=\"data row1 col1\" >1.89</td>\n",
+       "      <th id=\"T_565a7_level0_row1\" class=\"row_heading level0 row1\" >G27</th>\n",
+       "      <td id=\"T_565a7_row1_col0\" class=\"data row1 col0\" >2.32</td>\n",
+       "      <td id=\"T_565a7_row1_col1\" class=\"data row1 col1\" >1.87</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
-       "      <td id=\"T_a043f_row2_col0\" class=\"data row2 col0\" >0.31</td>\n",
-       "      <td id=\"T_a043f_row2_col1\" class=\"data row2 col1\" >0.21</td>\n",
+       "      <th id=\"T_565a7_level0_row2\" class=\"row_heading level0 row2\" >G30</th>\n",
+       "      <td id=\"T_565a7_row2_col0\" class=\"data row2 col0\" >0.31</td>\n",
+       "      <td id=\"T_565a7_row2_col1\" class=\"data row2 col1\" >0.20</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
-       "      <td id=\"T_a043f_row3_col0\" class=\"data row3 col0\" >0.11</td>\n",
-       "      <td id=\"T_a043f_row3_col1\" class=\"data row3 col1\" >0.07</td>\n",
+       "      <th id=\"T_565a7_level0_row3\" class=\"row_heading level0 row3\" >G32</th>\n",
+       "      <td id=\"T_565a7_row3_col0\" class=\"data row3 col0\" >0.11</td>\n",
+       "      <td id=\"T_565a7_row3_col1\" class=\"data row3 col1\" >0.07</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
-       "      <td id=\"T_a043f_row4_col0\" class=\"data row4 col0\" >0.26</td>\n",
-       "      <td id=\"T_a043f_row4_col1\" class=\"data row4 col1\" >0.16</td>\n",
+       "      <th id=\"T_565a7_level0_row4\" class=\"row_heading level0 row4\" >G67</th>\n",
+       "      <td id=\"T_565a7_row4_col0\" class=\"data row4 col0\" >0.26</td>\n",
+       "      <td id=\"T_565a7_row4_col1\" class=\"data row4 col1\" >0.16</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
-       "      <td id=\"T_a043f_row5_col0\" class=\"data row5 col0\" >0.03</td>\n",
-       "      <td id=\"T_a043f_row5_col1\" class=\"data row5 col1\" >0.00</td>\n",
+       "      <th id=\"T_565a7_level0_row5\" class=\"row_heading level0 row5\" >G70</th>\n",
+       "      <td id=\"T_565a7_row5_col0\" class=\"data row5 col0\" >0.03</td>\n",
+       "      <td id=\"T_565a7_row5_col1\" class=\"data row5 col1\" >0.01</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row6\" class=\"row_heading level0 row6\" >G95</th>\n",
-       "      <td id=\"T_a043f_row6_col0\" class=\"data row6 col0\" >0.52</td>\n",
-       "      <td id=\"T_a043f_row6_col1\" class=\"data row6 col1\" >0.27</td>\n",
+       "      <th id=\"T_565a7_level0_row6\" class=\"row_heading level0 row6\" >G95</th>\n",
+       "      <td id=\"T_565a7_row6_col0\" class=\"data row6 col0\" >0.52</td>\n",
+       "      <td id=\"T_565a7_row6_col1\" class=\"data row6 col1\" >0.27</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row7\" class=\"row_heading level0 row7\" >G96</th>\n",
-       "      <td id=\"T_a043f_row7_col0\" class=\"data row7 col0\" >0.15</td>\n",
-       "      <td id=\"T_a043f_row7_col1\" class=\"data row7 col1\" >0.05</td>\n",
+       "      <th id=\"T_565a7_level0_row7\" class=\"row_heading level0 row7\" >G96</th>\n",
+       "      <td id=\"T_565a7_row7_col0\" class=\"data row7 col0\" >0.15</td>\n",
+       "      <td id=\"T_565a7_row7_col1\" class=\"data row7 col1\" >0.02</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row8\" class=\"row_heading level0 row8\" >Gcaps</th>\n",
-       "      <td id=\"T_a043f_row8_col0\" class=\"data row8 col0\" >0.26</td>\n",
-       "      <td id=\"T_a043f_row8_col1\" class=\"data row8 col1\" >0.07</td>\n",
+       "      <th id=\"T_565a7_level0_row8\" class=\"row_heading level0 row8\" >Gcaps</th>\n",
+       "      <td id=\"T_565a7_row8_col0\" class=\"data row8 col0\" >0.26</td>\n",
+       "      <td id=\"T_565a7_row8_col1\" class=\"data row8 col1\" >0.10</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_a043f_level0_row9\" class=\"row_heading level0 row9\" >Gfrags</th>\n",
-       "      <td id=\"T_a043f_row9_col0\" class=\"data row9 col0\" >8.11</td>\n",
-       "      <td id=\"T_a043f_row9_col1\" class=\"data row9 col1\" >7.71</td>\n",
+       "      <th id=\"T_565a7_level0_row9\" class=\"row_heading level0 row9\" >Gfrags</th>\n",
+       "      <td id=\"T_565a7_row9_col0\" class=\"data row9 col0\" >8.11</td>\n",
+       "      <td id=\"T_565a7_row9_col1\" class=\"data row9 col1\" >7.38</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5cced1e20>"
+       "<pandas.io.formats.style.Styler at 0x7c6c0c679be0>"
       ]
      },
      "execution_count": 25,
@@ -2495,21 +2567,21 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_368fb tr:nth-child(even) {\n",
+       "#T_5cefd tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_368fb tr:nth-child(odd) {\n",
+       "#T_5cefd tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_368fb tr {\n",
+       "#T_5cefd tr {\n",
        "  font-size: 14px;\n",
        "  padding: 12px;\n",
        "}\n",
-       "#T_368fb th:nth-child(1) {\n",
+       "#T_5cefd th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_368fb caption {\n",
+       "#T_5cefd caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -2517,142 +2589,142 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_368fb\">\n",
+       "<table id=\"T_5cefd\">\n",
        "  <caption>Table 8: Whether the observed value fell within the predicted interval</caption>\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_368fb_level0_col0\" class=\"col_heading level0 col0\" >object</th>\n",
-       "      <th id=\"T_368fb_level0_col1\" class=\"col_heading level0 col1\" >within 96% HDI</th>\n",
-       "      <th id=\"T_368fb_level0_col2\" class=\"col_heading level0 col2\" >within 50% HDI</th>\n",
+       "      <th id=\"T_5cefd_level0_col0\" class=\"col_heading level0 col0\" >object</th>\n",
+       "      <th id=\"T_5cefd_level0_col1\" class=\"col_heading level0 col1\" >within 96% HDI</th>\n",
+       "      <th id=\"T_5cefd_level0_col2\" class=\"col_heading level0 col2\" >within 50% HDI</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
-       "      <td id=\"T_368fb_row0_col0\" class=\"data row0 col0\" >G112</td>\n",
-       "      <td id=\"T_368fb_row0_col1\" class=\"data row0 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row0_col2\" class=\"data row0 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
+       "      <td id=\"T_5cefd_row0_col0\" class=\"data row0 col0\" >G112</td>\n",
+       "      <td id=\"T_5cefd_row0_col1\" class=\"data row0 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row0_col2\" class=\"data row0 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
-       "      <td id=\"T_368fb_row1_col0\" class=\"data row1 col0\" >G27</td>\n",
-       "      <td id=\"T_368fb_row1_col1\" class=\"data row1 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row1_col2\" class=\"data row1 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
+       "      <td id=\"T_5cefd_row1_col0\" class=\"data row1 col0\" >G27</td>\n",
+       "      <td id=\"T_5cefd_row1_col1\" class=\"data row1 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row1_col2\" class=\"data row1 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
-       "      <td id=\"T_368fb_row2_col0\" class=\"data row2 col0\" >G30</td>\n",
-       "      <td id=\"T_368fb_row2_col1\" class=\"data row2 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row2_col2\" class=\"data row2 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
+       "      <td id=\"T_5cefd_row2_col0\" class=\"data row2 col0\" >G30</td>\n",
+       "      <td id=\"T_5cefd_row2_col1\" class=\"data row2 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row2_col2\" class=\"data row2 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
-       "      <td id=\"T_368fb_row3_col0\" class=\"data row3 col0\" >G32</td>\n",
-       "      <td id=\"T_368fb_row3_col1\" class=\"data row3 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row3_col2\" class=\"data row3 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
+       "      <td id=\"T_5cefd_row3_col0\" class=\"data row3 col0\" >G32</td>\n",
+       "      <td id=\"T_5cefd_row3_col1\" class=\"data row3 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row3_col2\" class=\"data row3 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
-       "      <td id=\"T_368fb_row4_col0\" class=\"data row4 col0\" >G67</td>\n",
-       "      <td id=\"T_368fb_row4_col1\" class=\"data row4 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row4_col2\" class=\"data row4 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
+       "      <td id=\"T_5cefd_row4_col0\" class=\"data row4 col0\" >G67</td>\n",
+       "      <td id=\"T_5cefd_row4_col1\" class=\"data row4 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row4_col2\" class=\"data row4 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
-       "      <td id=\"T_368fb_row5_col0\" class=\"data row5 col0\" >G70</td>\n",
-       "      <td id=\"T_368fb_row5_col1\" class=\"data row5 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row5_col2\" class=\"data row5 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
+       "      <td id=\"T_5cefd_row5_col0\" class=\"data row5 col0\" >G70</td>\n",
+       "      <td id=\"T_5cefd_row5_col1\" class=\"data row5 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row5_col2\" class=\"data row5 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
-       "      <td id=\"T_368fb_row6_col0\" class=\"data row6 col0\" >G95</td>\n",
-       "      <td id=\"T_368fb_row6_col1\" class=\"data row6 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row6_col2\" class=\"data row6 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
+       "      <td id=\"T_5cefd_row6_col0\" class=\"data row6 col0\" >G95</td>\n",
+       "      <td id=\"T_5cefd_row6_col1\" class=\"data row6 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row6_col2\" class=\"data row6 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
-       "      <td id=\"T_368fb_row7_col0\" class=\"data row7 col0\" >G96</td>\n",
-       "      <td id=\"T_368fb_row7_col1\" class=\"data row7 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row7_col2\" class=\"data row7 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
+       "      <td id=\"T_5cefd_row7_col0\" class=\"data row7 col0\" >G96</td>\n",
+       "      <td id=\"T_5cefd_row7_col1\" class=\"data row7 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row7_col2\" class=\"data row7 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
-       "      <td id=\"T_368fb_row8_col0\" class=\"data row8 col0\" >Gcaps</td>\n",
-       "      <td id=\"T_368fb_row8_col1\" class=\"data row8 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row8_col2\" class=\"data row8 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
+       "      <td id=\"T_5cefd_row8_col0\" class=\"data row8 col0\" >Gcaps</td>\n",
+       "      <td id=\"T_5cefd_row8_col1\" class=\"data row8 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row8_col2\" class=\"data row8 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
-       "      <td id=\"T_368fb_row9_col0\" class=\"data row9 col0\" >Gfrags</td>\n",
-       "      <td id=\"T_368fb_row9_col1\" class=\"data row9 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row9_col2\" class=\"data row9 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
+       "      <td id=\"T_5cefd_row9_col0\" class=\"data row9 col0\" >Gfrags</td>\n",
+       "      <td id=\"T_5cefd_row9_col1\" class=\"data row9 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row9_col2\" class=\"data row9 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row10\" class=\"row_heading level0 row10\" >0</th>\n",
-       "      <td id=\"T_368fb_row10_col0\" class=\"data row10 col0\" >G112</td>\n",
-       "      <td id=\"T_368fb_row10_col1\" class=\"data row10 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row10_col2\" class=\"data row10 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row10\" class=\"row_heading level0 row10\" >0</th>\n",
+       "      <td id=\"T_5cefd_row10_col0\" class=\"data row10 col0\" >G112</td>\n",
+       "      <td id=\"T_5cefd_row10_col1\" class=\"data row10 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row10_col2\" class=\"data row10 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row11\" class=\"row_heading level0 row11\" >1</th>\n",
-       "      <td id=\"T_368fb_row11_col0\" class=\"data row11 col0\" >G27</td>\n",
-       "      <td id=\"T_368fb_row11_col1\" class=\"data row11 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row11_col2\" class=\"data row11 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row11\" class=\"row_heading level0 row11\" >1</th>\n",
+       "      <td id=\"T_5cefd_row11_col0\" class=\"data row11 col0\" >G27</td>\n",
+       "      <td id=\"T_5cefd_row11_col1\" class=\"data row11 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row11_col2\" class=\"data row11 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row12\" class=\"row_heading level0 row12\" >2</th>\n",
-       "      <td id=\"T_368fb_row12_col0\" class=\"data row12 col0\" >G30</td>\n",
-       "      <td id=\"T_368fb_row12_col1\" class=\"data row12 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row12_col2\" class=\"data row12 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row12\" class=\"row_heading level0 row12\" >2</th>\n",
+       "      <td id=\"T_5cefd_row12_col0\" class=\"data row12 col0\" >G30</td>\n",
+       "      <td id=\"T_5cefd_row12_col1\" class=\"data row12 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row12_col2\" class=\"data row12 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row13\" class=\"row_heading level0 row13\" >3</th>\n",
-       "      <td id=\"T_368fb_row13_col0\" class=\"data row13 col0\" >G32</td>\n",
-       "      <td id=\"T_368fb_row13_col1\" class=\"data row13 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row13_col2\" class=\"data row13 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row13\" class=\"row_heading level0 row13\" >3</th>\n",
+       "      <td id=\"T_5cefd_row13_col0\" class=\"data row13 col0\" >G32</td>\n",
+       "      <td id=\"T_5cefd_row13_col1\" class=\"data row13 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row13_col2\" class=\"data row13 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row14\" class=\"row_heading level0 row14\" >4</th>\n",
-       "      <td id=\"T_368fb_row14_col0\" class=\"data row14 col0\" >G67</td>\n",
-       "      <td id=\"T_368fb_row14_col1\" class=\"data row14 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row14_col2\" class=\"data row14 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row14\" class=\"row_heading level0 row14\" >4</th>\n",
+       "      <td id=\"T_5cefd_row14_col0\" class=\"data row14 col0\" >G67</td>\n",
+       "      <td id=\"T_5cefd_row14_col1\" class=\"data row14 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row14_col2\" class=\"data row14 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row15\" class=\"row_heading level0 row15\" >5</th>\n",
-       "      <td id=\"T_368fb_row15_col0\" class=\"data row15 col0\" >G70</td>\n",
-       "      <td id=\"T_368fb_row15_col1\" class=\"data row15 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row15_col2\" class=\"data row15 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row15\" class=\"row_heading level0 row15\" >5</th>\n",
+       "      <td id=\"T_5cefd_row15_col0\" class=\"data row15 col0\" >G70</td>\n",
+       "      <td id=\"T_5cefd_row15_col1\" class=\"data row15 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row15_col2\" class=\"data row15 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row16\" class=\"row_heading level0 row16\" >6</th>\n",
-       "      <td id=\"T_368fb_row16_col0\" class=\"data row16 col0\" >G95</td>\n",
-       "      <td id=\"T_368fb_row16_col1\" class=\"data row16 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row16_col2\" class=\"data row16 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row16\" class=\"row_heading level0 row16\" >6</th>\n",
+       "      <td id=\"T_5cefd_row16_col0\" class=\"data row16 col0\" >G95</td>\n",
+       "      <td id=\"T_5cefd_row16_col1\" class=\"data row16 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row16_col2\" class=\"data row16 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row17\" class=\"row_heading level0 row17\" >7</th>\n",
-       "      <td id=\"T_368fb_row17_col0\" class=\"data row17 col0\" >G96</td>\n",
-       "      <td id=\"T_368fb_row17_col1\" class=\"data row17 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row17_col2\" class=\"data row17 col2\" >True</td>\n",
+       "      <th id=\"T_5cefd_level0_row17\" class=\"row_heading level0 row17\" >7</th>\n",
+       "      <td id=\"T_5cefd_row17_col0\" class=\"data row17 col0\" >G96</td>\n",
+       "      <td id=\"T_5cefd_row17_col1\" class=\"data row17 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row17_col2\" class=\"data row17 col2\" >True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row18\" class=\"row_heading level0 row18\" >8</th>\n",
-       "      <td id=\"T_368fb_row18_col0\" class=\"data row18 col0\" >Gcaps</td>\n",
-       "      <td id=\"T_368fb_row18_col1\" class=\"data row18 col1\" >True</td>\n",
-       "      <td id=\"T_368fb_row18_col2\" class=\"data row18 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row18\" class=\"row_heading level0 row18\" >8</th>\n",
+       "      <td id=\"T_5cefd_row18_col0\" class=\"data row18 col0\" >Gcaps</td>\n",
+       "      <td id=\"T_5cefd_row18_col1\" class=\"data row18 col1\" >True</td>\n",
+       "      <td id=\"T_5cefd_row18_col2\" class=\"data row18 col2\" >False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_368fb_level0_row19\" class=\"row_heading level0 row19\" >9</th>\n",
-       "      <td id=\"T_368fb_row19_col0\" class=\"data row19 col0\" >Gfrags</td>\n",
-       "      <td id=\"T_368fb_row19_col1\" class=\"data row19 col1\" >False</td>\n",
-       "      <td id=\"T_368fb_row19_col2\" class=\"data row19 col2\" >False</td>\n",
+       "      <th id=\"T_5cefd_level0_row19\" class=\"row_heading level0 row19\" >9</th>\n",
+       "      <td id=\"T_5cefd_row19_col0\" class=\"data row19 col0\" >Gfrags</td>\n",
+       "      <td id=\"T_5cefd_row19_col1\" class=\"data row19 col1\" >False</td>\n",
+       "      <td id=\"T_5cefd_row19_col2\" class=\"data row19 col2\" >False</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x76f5c07e21f0>"
+       "<pandas.io.formats.style.Styler at 0x7c6bfcfdc5e0>"
       ]
      },
      "execution_count": 27,
@@ -2685,7 +2757,7 @@
      "data": {
       "text/plain": [
        "within 96% HDI    0.80\n",
-       "within 50% HDI    0.35\n",
+       "within 50% HDI    0.45\n",
        "dtype: float64"
       ]
      },
@@ -2719,7 +2791,7 @@
      "data": {
       "text/plain": [
        "within 96% HDI    16\n",
-       "within 50% HDI     7\n",
+       "within 50% HDI     9\n",
        "dtype: int64"
       ]
      },
@@ -2802,12 +2874,12 @@
      "text": [
       "Git repo: https://github.com/hammerdirt-analyst/solid-waste-team.git\n",
       "\n",
-      "Git branch: review\n",
+      "Git branch: main\n",
       "\n",
       "pandas    : 2.0.3\n",
+      "numpy     : 1.25.2\n",
       "matplotlib: 3.7.1\n",
       "seaborn   : 0.12.2\n",
-      "numpy     : 1.25.2\n",
       "\n"
      ]
     }
diff --git a/plastic_shotgun_wadding.ipynb b/plastic_shotgun_wadding.ipynb
index d590d80..d7a79bb 100644
--- a/plastic_shotgun_wadding.ipynb
+++ b/plastic_shotgun_wadding.ipynb
@@ -216,8 +216,8 @@
    "outputs": [
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_c1fc0 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_c1fc0 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_c1fc0 tr {\n  font-size: 14px;\n}\n#T_c1fc0 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_c1fc0 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_c1fc0\">\n  <caption>Percent of samples collected with the designated land-use feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_c1fc0_level0_col0\" class=\"col_heading level0 col0\" >orchards</th>\n      <th id=\"T_c1fc0_level0_col1\" class=\"col_heading level0 col1\" >vineyards</th>\n      <th id=\"T_c1fc0_level0_col2\" class=\"col_heading level0 col2\" >buildings</th>\n      <th id=\"T_c1fc0_level0_col3\" class=\"col_heading level0 col3\" >forest</th>\n      <th id=\"T_c1fc0_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_c1fc0_level0_col5\" class=\"col_heading level0 col5\" >public_services</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_c1fc0_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_c1fc0_row0_col0\" class=\"data row0 col0\" >91%</td>\n      <td id=\"T_c1fc0_row0_col1\" class=\"data row0 col1\" >92%</td>\n      <td id=\"T_c1fc0_row0_col2\" class=\"data row0 col2\" >11%</td>\n      <td id=\"T_c1fc0_row0_col3\" class=\"data row0 col3\" >72%</td>\n      <td id=\"T_c1fc0_row0_col4\" class=\"data row0 col4\" >63%</td>\n      <td id=\"T_c1fc0_row0_col5\" class=\"data row0 col5\" >68%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_c1fc0_row1_col0\" class=\"data row1 col0\" >6%</td>\n      <td id=\"T_c1fc0_row1_col1\" class=\"data row1 col1\" >7%</td>\n      <td id=\"T_c1fc0_row1_col2\" class=\"data row1 col2\" >6%</td>\n      <td id=\"T_c1fc0_row1_col3\" class=\"data row1 col3\" >14%</td>\n      <td id=\"T_c1fc0_row1_col4\" class=\"data row1 col4\" >25%</td>\n      <td id=\"T_c1fc0_row1_col5\" class=\"data row1 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_c1fc0_row2_col0\" class=\"data row2 col0\" >0%</td>\n      <td id=\"T_c1fc0_row2_col1\" class=\"data row2 col1\" >0%</td>\n      <td id=\"T_c1fc0_row2_col2\" class=\"data row2 col2\" >1%</td>\n      <td id=\"T_c1fc0_row2_col3\" class=\"data row2 col3\" >0%</td>\n      <td id=\"T_c1fc0_row2_col4\" class=\"data row2 col4\" >1%</td>\n      <td id=\"T_c1fc0_row2_col5\" class=\"data row2 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_c1fc0_row3_col0\" class=\"data row3 col0\" >1%</td>\n      <td id=\"T_c1fc0_row3_col1\" class=\"data row3 col1\" >0%</td>\n      <td id=\"T_c1fc0_row3_col2\" class=\"data row3 col2\" >20%</td>\n      <td id=\"T_c1fc0_row3_col3\" class=\"data row3 col3\" >9%</td>\n      <td id=\"T_c1fc0_row3_col4\" class=\"data row3 col4\" >2%</td>\n      <td id=\"T_c1fc0_row3_col5\" class=\"data row3 col5\" >8%</td>\n    </tr>\n    <tr>\n      <th id=\"T_c1fc0_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_c1fc0_row4_col0\" class=\"data row4 col0\" >1%</td>\n      <td id=\"T_c1fc0_row4_col1\" class=\"data row4 col1\" >1%</td>\n      <td id=\"T_c1fc0_row4_col2\" class=\"data row4 col2\" >62%</td>\n      <td id=\"T_c1fc0_row4_col3\" class=\"data row4 col3\" >5%</td>\n      <td id=\"T_c1fc0_row4_col4\" class=\"data row4 col4\" >9%</td>\n      <td id=\"T_c1fc0_row4_col5\" class=\"data row4 col5\" >10%</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7896dc878ca0>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_09e96 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_09e96 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_09e96 tr {\n  font-size: 14px;\n}\n#T_09e96 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_09e96 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_09e96\">\n  <caption>Percent of samples collected with the designated land-use feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_09e96_level0_col0\" class=\"col_heading level0 col0\" >orchards</th>\n      <th id=\"T_09e96_level0_col1\" class=\"col_heading level0 col1\" >vineyards</th>\n      <th id=\"T_09e96_level0_col2\" class=\"col_heading level0 col2\" >buildings</th>\n      <th id=\"T_09e96_level0_col3\" class=\"col_heading level0 col3\" >forest</th>\n      <th id=\"T_09e96_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_09e96_level0_col5\" class=\"col_heading level0 col5\" >public_services</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_09e96_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_09e96_row0_col0\" class=\"data row0 col0\" >91%</td>\n      <td id=\"T_09e96_row0_col1\" class=\"data row0 col1\" >92%</td>\n      <td id=\"T_09e96_row0_col2\" class=\"data row0 col2\" >11%</td>\n      <td id=\"T_09e96_row0_col3\" class=\"data row0 col3\" >72%</td>\n      <td id=\"T_09e96_row0_col4\" class=\"data row0 col4\" >63%</td>\n      <td id=\"T_09e96_row0_col5\" class=\"data row0 col5\" >68%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_09e96_row1_col0\" class=\"data row1 col0\" >6%</td>\n      <td id=\"T_09e96_row1_col1\" class=\"data row1 col1\" >7%</td>\n      <td id=\"T_09e96_row1_col2\" class=\"data row1 col2\" >6%</td>\n      <td id=\"T_09e96_row1_col3\" class=\"data row1 col3\" >14%</td>\n      <td id=\"T_09e96_row1_col4\" class=\"data row1 col4\" >25%</td>\n      <td id=\"T_09e96_row1_col5\" class=\"data row1 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_09e96_row2_col0\" class=\"data row2 col0\" >0%</td>\n      <td id=\"T_09e96_row2_col1\" class=\"data row2 col1\" >0%</td>\n      <td id=\"T_09e96_row2_col2\" class=\"data row2 col2\" >1%</td>\n      <td id=\"T_09e96_row2_col3\" class=\"data row2 col3\" >0%</td>\n      <td id=\"T_09e96_row2_col4\" class=\"data row2 col4\" >1%</td>\n      <td id=\"T_09e96_row2_col5\" class=\"data row2 col5\" >7%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_09e96_row3_col0\" class=\"data row3 col0\" >1%</td>\n      <td id=\"T_09e96_row3_col1\" class=\"data row3 col1\" >0%</td>\n      <td id=\"T_09e96_row3_col2\" class=\"data row3 col2\" >20%</td>\n      <td id=\"T_09e96_row3_col3\" class=\"data row3 col3\" >9%</td>\n      <td id=\"T_09e96_row3_col4\" class=\"data row3 col4\" >2%</td>\n      <td id=\"T_09e96_row3_col5\" class=\"data row3 col5\" >8%</td>\n    </tr>\n    <tr>\n      <th id=\"T_09e96_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_09e96_row4_col0\" class=\"data row4 col0\" >1%</td>\n      <td id=\"T_09e96_row4_col1\" class=\"data row4 col1\" >1%</td>\n      <td id=\"T_09e96_row4_col2\" class=\"data row4 col2\" >62%</td>\n      <td id=\"T_09e96_row4_col3\" class=\"data row4 col3\" >5%</td>\n      <td id=\"T_09e96_row4_col4\" class=\"data row4 col4\" >9%</td>\n      <td id=\"T_09e96_row4_col5\" class=\"data row4 col5\" >10%</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7a2c78fa07f0>"
      },
      "metadata": {
       "scrapbook": {
@@ -289,8 +289,8 @@
    "outputs": [
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_c091a tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_c091a tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_c091a tr {\n  font-size: 14px;\n}\n#T_c091a th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_c091a caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_c091a\">\n  <caption>The average number of shotgun shells per linear meter of shoreline by feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_c091a_level0_col0\" class=\"col_heading level0 col0\" >buildings</th>\n      <th id=\"T_c091a_level0_col1\" class=\"col_heading level0 col1\" >forest</th>\n      <th id=\"T_c091a_level0_col2\" class=\"col_heading level0 col2\" >orchards</th>\n      <th id=\"T_c091a_level0_col3\" class=\"col_heading level0 col3\" >public_services</th>\n      <th id=\"T_c091a_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_c091a_level0_col5\" class=\"col_heading level0 col5\" >vineyards</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_c091a_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_c091a_row0_col0\" class=\"data row0 col0\" >0.03</td>\n      <td id=\"T_c091a_row0_col1\" class=\"data row0 col1\" >0.08</td>\n      <td id=\"T_c091a_row0_col2\" class=\"data row0 col2\" >0.11</td>\n      <td id=\"T_c091a_row0_col3\" class=\"data row0 col3\" >0.13</td>\n      <td id=\"T_c091a_row0_col4\" class=\"data row0 col4\" >0.09</td>\n      <td id=\"T_c091a_row0_col5\" class=\"data row0 col5\" >0.10</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_c091a_row1_col0\" class=\"data row1 col0\" >0.59</td>\n      <td id=\"T_c091a_row1_col1\" class=\"data row1 col1\" >0.06</td>\n      <td id=\"T_c091a_row1_col2\" class=\"data row1 col2\" >0.01</td>\n      <td id=\"T_c091a_row1_col3\" class=\"data row1 col3\" >0.12</td>\n      <td id=\"T_c091a_row1_col4\" class=\"data row1 col4\" >0.18</td>\n      <td id=\"T_c091a_row1_col5\" class=\"data row1 col5\" >0.08</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_c091a_row2_col0\" class=\"data row2 col0\" >0.00</td>\n      <td id=\"T_c091a_row2_col1\" class=\"data row2 col1\" >-</td>\n      <td id=\"T_c091a_row2_col2\" class=\"data row2 col2\" >0.00</td>\n      <td id=\"T_c091a_row2_col3\" class=\"data row2 col3\" >0.01</td>\n      <td id=\"T_c091a_row2_col4\" class=\"data row2 col4\" >0.08</td>\n      <td id=\"T_c091a_row2_col5\" class=\"data row2 col5\" >-</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_c091a_row3_col0\" class=\"data row3 col0\" >0.04</td>\n      <td id=\"T_c091a_row3_col1\" class=\"data row3 col1\" >0.00</td>\n      <td id=\"T_c091a_row3_col2\" class=\"data row3 col2\" >0.01</td>\n      <td id=\"T_c091a_row3_col3\" class=\"data row3 col3\" >0.03</td>\n      <td id=\"T_c091a_row3_col4\" class=\"data row3 col4\" >0.09</td>\n      <td id=\"T_c091a_row3_col5\" class=\"data row3 col5\" >0.00</td>\n    </tr>\n    <tr>\n      <th id=\"T_c091a_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_c091a_row4_col0\" class=\"data row4 col0\" >0.09</td>\n      <td id=\"T_c091a_row4_col1\" class=\"data row4 col1\" >0.68</td>\n      <td id=\"T_c091a_row4_col2\" class=\"data row4 col2\" >0.14</td>\n      <td id=\"T_c091a_row4_col3\" class=\"data row4 col3\" >0.03</td>\n      <td id=\"T_c091a_row4_col4\" class=\"data row4 col4\" >0.00</td>\n      <td id=\"T_c091a_row4_col5\" class=\"data row4 col5\" >0.12</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7896dca60c10>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_1cbf2 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_1cbf2 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_1cbf2 tr {\n  font-size: 14px;\n}\n#T_1cbf2 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_1cbf2 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_1cbf2\">\n  <caption>The average number of shotgun shells per linear meter of shoreline by feature and category.</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_1cbf2_level0_col0\" class=\"col_heading level0 col0\" >buildings</th>\n      <th id=\"T_1cbf2_level0_col1\" class=\"col_heading level0 col1\" >forest</th>\n      <th id=\"T_1cbf2_level0_col2\" class=\"col_heading level0 col2\" >orchards</th>\n      <th id=\"T_1cbf2_level0_col3\" class=\"col_heading level0 col3\" >public_services</th>\n      <th id=\"T_1cbf2_level0_col4\" class=\"col_heading level0 col4\" >undefined</th>\n      <th id=\"T_1cbf2_level0_col5\" class=\"col_heading level0 col5\" >vineyards</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_1cbf2_level0_row0\" class=\"row_heading level0 row0\" >1</th>\n      <td id=\"T_1cbf2_row0_col0\" class=\"data row0 col0\" >0.03</td>\n      <td id=\"T_1cbf2_row0_col1\" class=\"data row0 col1\" >0.08</td>\n      <td id=\"T_1cbf2_row0_col2\" class=\"data row0 col2\" >0.11</td>\n      <td id=\"T_1cbf2_row0_col3\" class=\"data row0 col3\" >0.13</td>\n      <td id=\"T_1cbf2_row0_col4\" class=\"data row0 col4\" >0.09</td>\n      <td id=\"T_1cbf2_row0_col5\" class=\"data row0 col5\" >0.10</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row1\" class=\"row_heading level0 row1\" >2</th>\n      <td id=\"T_1cbf2_row1_col0\" class=\"data row1 col0\" >0.59</td>\n      <td id=\"T_1cbf2_row1_col1\" class=\"data row1 col1\" >0.06</td>\n      <td id=\"T_1cbf2_row1_col2\" class=\"data row1 col2\" >0.01</td>\n      <td id=\"T_1cbf2_row1_col3\" class=\"data row1 col3\" >0.12</td>\n      <td id=\"T_1cbf2_row1_col4\" class=\"data row1 col4\" >0.18</td>\n      <td id=\"T_1cbf2_row1_col5\" class=\"data row1 col5\" >0.08</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row2\" class=\"row_heading level0 row2\" >3</th>\n      <td id=\"T_1cbf2_row2_col0\" class=\"data row2 col0\" >0.00</td>\n      <td id=\"T_1cbf2_row2_col1\" class=\"data row2 col1\" >-</td>\n      <td id=\"T_1cbf2_row2_col2\" class=\"data row2 col2\" >0.00</td>\n      <td id=\"T_1cbf2_row2_col3\" class=\"data row2 col3\" >0.01</td>\n      <td id=\"T_1cbf2_row2_col4\" class=\"data row2 col4\" >0.08</td>\n      <td id=\"T_1cbf2_row2_col5\" class=\"data row2 col5\" >-</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row3\" class=\"row_heading level0 row3\" >4</th>\n      <td id=\"T_1cbf2_row3_col0\" class=\"data row3 col0\" >0.04</td>\n      <td id=\"T_1cbf2_row3_col1\" class=\"data row3 col1\" >0.00</td>\n      <td id=\"T_1cbf2_row3_col2\" class=\"data row3 col2\" >0.01</td>\n      <td id=\"T_1cbf2_row3_col3\" class=\"data row3 col3\" >0.03</td>\n      <td id=\"T_1cbf2_row3_col4\" class=\"data row3 col4\" >0.09</td>\n      <td id=\"T_1cbf2_row3_col5\" class=\"data row3 col5\" >0.00</td>\n    </tr>\n    <tr>\n      <th id=\"T_1cbf2_level0_row4\" class=\"row_heading level0 row4\" >5</th>\n      <td id=\"T_1cbf2_row4_col0\" class=\"data row4 col0\" >0.09</td>\n      <td id=\"T_1cbf2_row4_col1\" class=\"data row4 col1\" >0.68</td>\n      <td id=\"T_1cbf2_row4_col2\" class=\"data row4 col2\" >0.14</td>\n      <td id=\"T_1cbf2_row4_col3\" class=\"data row4 col3\" >0.03</td>\n      <td id=\"T_1cbf2_row4_col4\" class=\"data row4 col4\" >0.00</td>\n      <td id=\"T_1cbf2_row4_col5\" class=\"data row4 col5\" >0.12</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7a2cc40c9220>"
      },
      "metadata": {
       "scrapbook": {
@@ -462,8 +462,8 @@
    "outputs": [
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_8ea89 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_8ea89 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_8ea89 tr {\n  font-size: 14px;\n}\n#T_8ea89 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_8ea89 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_8ea89\">\n  <caption>The distribution of the total number of plastic shotgun wadding found per sample for each region</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_8ea89_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_8ea89_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_8ea89_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_8ea89_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_8ea89_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_8ea89_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_8ea89_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_8ea89_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_8ea89_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_8ea89_row0_col0\" class=\"data row0 col0\" >58</td>\n      <td id=\"T_8ea89_row0_col1\" class=\"data row0 col1\" >1</td>\n      <td id=\"T_8ea89_row0_col2\" class=\"data row0 col2\" >2</td>\n      <td id=\"T_8ea89_row0_col3\" class=\"data row0 col3\" >0</td>\n      <td id=\"T_8ea89_row0_col4\" class=\"data row0 col4\" >0</td>\n      <td id=\"T_8ea89_row0_col5\" class=\"data row0 col5\" >0</td>\n      <td id=\"T_8ea89_row0_col6\" class=\"data row0 col6\" >1</td>\n      <td id=\"T_8ea89_row0_col7\" class=\"data row0 col7\" >8</td>\n    </tr>\n    <tr>\n      <th id=\"T_8ea89_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_8ea89_row1_col0\" class=\"data row1 col0\" >137</td>\n      <td id=\"T_8ea89_row1_col1\" class=\"data row1 col1\" >6</td>\n      <td id=\"T_8ea89_row1_col2\" class=\"data row1 col2\" >10</td>\n      <td id=\"T_8ea89_row1_col3\" class=\"data row1 col3\" >0</td>\n      <td id=\"T_8ea89_row1_col4\" class=\"data row1 col4\" >0</td>\n      <td id=\"T_8ea89_row1_col5\" class=\"data row1 col5\" >2</td>\n      <td id=\"T_8ea89_row1_col6\" class=\"data row1 col6\" >7</td>\n      <td id=\"T_8ea89_row1_col7\" class=\"data row1 col7\" >51</td>\n    </tr>\n    <tr>\n      <th id=\"T_8ea89_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_8ea89_row2_col0\" class=\"data row2 col0\" >55</td>\n      <td id=\"T_8ea89_row2_col1\" class=\"data row2 col1\" >1</td>\n      <td id=\"T_8ea89_row2_col2\" class=\"data row2 col2\" >4</td>\n      <td id=\"T_8ea89_row2_col3\" class=\"data row2 col3\" >0</td>\n      <td id=\"T_8ea89_row2_col4\" class=\"data row2 col4\" >0</td>\n      <td id=\"T_8ea89_row2_col5\" class=\"data row2 col5\" >0</td>\n      <td id=\"T_8ea89_row2_col6\" class=\"data row2 col6\" >0</td>\n      <td id=\"T_8ea89_row2_col7\" class=\"data row2 col7\" >22</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7896dca95d60>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_59bce tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_59bce tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_59bce tr {\n  font-size: 14px;\n}\n#T_59bce th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_59bce caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_59bce\">\n  <caption>The distribution of the total number of plastic shotgun wadding found per sample for each region</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_59bce_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_59bce_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_59bce_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_59bce_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_59bce_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_59bce_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_59bce_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_59bce_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_59bce_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_59bce_row0_col0\" class=\"data row0 col0\" >58</td>\n      <td id=\"T_59bce_row0_col1\" class=\"data row0 col1\" >1</td>\n      <td id=\"T_59bce_row0_col2\" class=\"data row0 col2\" >2</td>\n      <td id=\"T_59bce_row0_col3\" class=\"data row0 col3\" >0</td>\n      <td id=\"T_59bce_row0_col4\" class=\"data row0 col4\" >0</td>\n      <td id=\"T_59bce_row0_col5\" class=\"data row0 col5\" >0</td>\n      <td id=\"T_59bce_row0_col6\" class=\"data row0 col6\" >1</td>\n      <td id=\"T_59bce_row0_col7\" class=\"data row0 col7\" >8</td>\n    </tr>\n    <tr>\n      <th id=\"T_59bce_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_59bce_row1_col0\" class=\"data row1 col0\" >137</td>\n      <td id=\"T_59bce_row1_col1\" class=\"data row1 col1\" >6</td>\n      <td id=\"T_59bce_row1_col2\" class=\"data row1 col2\" >10</td>\n      <td id=\"T_59bce_row1_col3\" class=\"data row1 col3\" >0</td>\n      <td id=\"T_59bce_row1_col4\" class=\"data row1 col4\" >0</td>\n      <td id=\"T_59bce_row1_col5\" class=\"data row1 col5\" >2</td>\n      <td id=\"T_59bce_row1_col6\" class=\"data row1 col6\" >7</td>\n      <td id=\"T_59bce_row1_col7\" class=\"data row1 col7\" >51</td>\n    </tr>\n    <tr>\n      <th id=\"T_59bce_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_59bce_row2_col0\" class=\"data row2 col0\" >55</td>\n      <td id=\"T_59bce_row2_col1\" class=\"data row2 col1\" >1</td>\n      <td id=\"T_59bce_row2_col2\" class=\"data row2 col2\" >4</td>\n      <td id=\"T_59bce_row2_col3\" class=\"data row2 col3\" >0</td>\n      <td id=\"T_59bce_row2_col4\" class=\"data row2 col4\" >0</td>\n      <td id=\"T_59bce_row2_col5\" class=\"data row2 col5\" >0</td>\n      <td id=\"T_59bce_row2_col6\" class=\"data row2 col6\" >0</td>\n      <td id=\"T_59bce_row2_col7\" class=\"data row2 col7\" >22</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7a2c708dd2e0>"
      },
      "metadata": {
       "scrapbook": {
@@ -475,8 +475,8 @@
     },
     {
      "data": {
-      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_620b2 tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_620b2 tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_620b2 tr {\n  font-size: 14px;\n}\n#T_620b2 th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_620b2 caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_620b2\">\n  <caption>The distribution of the number of shotgun wadding found per meter of shoreline</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_620b2_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_620b2_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_620b2_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_620b2_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_620b2_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_620b2_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_620b2_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_620b2_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_620b2_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_620b2_row0_col0\" class=\"data row0 col0\" >58.00</td>\n      <td id=\"T_620b2_row0_col1\" class=\"data row0 col1\" >0.03</td>\n      <td id=\"T_620b2_row0_col2\" class=\"data row0 col2\" >0.05</td>\n      <td id=\"T_620b2_row0_col3\" class=\"data row0 col3\" >0.00</td>\n      <td id=\"T_620b2_row0_col4\" class=\"data row0 col4\" >0.00</td>\n      <td id=\"T_620b2_row0_col5\" class=\"data row0 col5\" >0.00</td>\n      <td id=\"T_620b2_row0_col6\" class=\"data row0 col6\" >0.03</td>\n      <td id=\"T_620b2_row0_col7\" class=\"data row0 col7\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_620b2_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_620b2_row1_col0\" class=\"data row1 col0\" >137.00</td>\n      <td id=\"T_620b2_row1_col1\" class=\"data row1 col1\" >0.17</td>\n      <td id=\"T_620b2_row1_col2\" class=\"data row1 col2\" >0.31</td>\n      <td id=\"T_620b2_row1_col3\" class=\"data row1 col3\" >0.00</td>\n      <td id=\"T_620b2_row1_col4\" class=\"data row1 col4\" >0.00</td>\n      <td id=\"T_620b2_row1_col5\" class=\"data row1 col5\" >0.05</td>\n      <td id=\"T_620b2_row1_col6\" class=\"data row1 col6\" >0.17</td>\n      <td id=\"T_620b2_row1_col7\" class=\"data row1 col7\" >1.64</td>\n    </tr>\n    <tr>\n      <th id=\"T_620b2_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_620b2_row2_col0\" class=\"data row2 col0\" >55.00</td>\n      <td id=\"T_620b2_row2_col1\" class=\"data row2 col1\" >0.02</td>\n      <td id=\"T_620b2_row2_col2\" class=\"data row2 col2\" >0.05</td>\n      <td id=\"T_620b2_row2_col3\" class=\"data row2 col3\" >0.00</td>\n      <td id=\"T_620b2_row2_col4\" class=\"data row2 col4\" >0.00</td>\n      <td id=\"T_620b2_row2_col5\" class=\"data row2 col5\" >0.00</td>\n      <td id=\"T_620b2_row2_col6\" class=\"data row2 col6\" >0.01</td>\n      <td id=\"T_620b2_row2_col7\" class=\"data row2 col7\" >0.30</td>\n    </tr>\n  </tbody>\n</table>\n",
-      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7896afba5880>"
+      "application/papermill.record/text/html": "<style type=\"text/css\">\n#T_94f7e tr:nth-child(even) {\n  background-color: rgba(139, 69, 19, 0.08);\n}\n#T_94f7e tr:nth-child(odd) {\n  background: #FFF;\n}\n#T_94f7e tr {\n  font-size: 14px;\n}\n#T_94f7e th:nth-child(1) {\n  background-color: #FFF;\n  text-align: right;\n}\n#T_94f7e caption {\n  font-size: 14px;\n  font-style: italic;\n  caption-side: bottom;\n  text-align: left;\n  margin-top: 10px;\n}\n</style>\n<table id=\"T_94f7e\">\n  <caption>The distribution of the number of shotgun wadding found per meter of shoreline</caption>\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_94f7e_level0_col0\" class=\"col_heading level0 col0\" >nsamples</th>\n      <th id=\"T_94f7e_level0_col1\" class=\"col_heading level0 col1\" >mean</th>\n      <th id=\"T_94f7e_level0_col2\" class=\"col_heading level0 col2\" >std</th>\n      <th id=\"T_94f7e_level0_col3\" class=\"col_heading level0 col3\" >min</th>\n      <th id=\"T_94f7e_level0_col4\" class=\"col_heading level0 col4\" >25%</th>\n      <th id=\"T_94f7e_level0_col5\" class=\"col_heading level0 col5\" >50%</th>\n      <th id=\"T_94f7e_level0_col6\" class=\"col_heading level0 col6\" >75%</th>\n      <th id=\"T_94f7e_level0_col7\" class=\"col_heading level0 col7\" >max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_94f7e_level0_row0\" class=\"row_heading level0 row0\" >Grand lac</th>\n      <td id=\"T_94f7e_row0_col0\" class=\"data row0 col0\" >58.00</td>\n      <td id=\"T_94f7e_row0_col1\" class=\"data row0 col1\" >0.03</td>\n      <td id=\"T_94f7e_row0_col2\" class=\"data row0 col2\" >0.05</td>\n      <td id=\"T_94f7e_row0_col3\" class=\"data row0 col3\" >0.00</td>\n      <td id=\"T_94f7e_row0_col4\" class=\"data row0 col4\" >0.00</td>\n      <td id=\"T_94f7e_row0_col5\" class=\"data row0 col5\" >0.00</td>\n      <td id=\"T_94f7e_row0_col6\" class=\"data row0 col6\" >0.03</td>\n      <td id=\"T_94f7e_row0_col7\" class=\"data row0 col7\" >0.22</td>\n    </tr>\n    <tr>\n      <th id=\"T_94f7e_level0_row1\" class=\"row_heading level0 row1\" >Haut lac</th>\n      <td id=\"T_94f7e_row1_col0\" class=\"data row1 col0\" >137.00</td>\n      <td id=\"T_94f7e_row1_col1\" class=\"data row1 col1\" >0.17</td>\n      <td id=\"T_94f7e_row1_col2\" class=\"data row1 col2\" >0.31</td>\n      <td id=\"T_94f7e_row1_col3\" class=\"data row1 col3\" >0.00</td>\n      <td id=\"T_94f7e_row1_col4\" class=\"data row1 col4\" >0.00</td>\n      <td id=\"T_94f7e_row1_col5\" class=\"data row1 col5\" >0.05</td>\n      <td id=\"T_94f7e_row1_col6\" class=\"data row1 col6\" >0.17</td>\n      <td id=\"T_94f7e_row1_col7\" class=\"data row1 col7\" >1.64</td>\n    </tr>\n    <tr>\n      <th id=\"T_94f7e_level0_row2\" class=\"row_heading level0 row2\" >Petit lac</th>\n      <td id=\"T_94f7e_row2_col0\" class=\"data row2 col0\" >55.00</td>\n      <td id=\"T_94f7e_row2_col1\" class=\"data row2 col1\" >0.02</td>\n      <td id=\"T_94f7e_row2_col2\" class=\"data row2 col2\" >0.05</td>\n      <td id=\"T_94f7e_row2_col3\" class=\"data row2 col3\" >0.00</td>\n      <td id=\"T_94f7e_row2_col4\" class=\"data row2 col4\" >0.00</td>\n      <td id=\"T_94f7e_row2_col5\" class=\"data row2 col5\" >0.00</td>\n      <td id=\"T_94f7e_row2_col6\" class=\"data row2 col6\" >0.01</td>\n      <td id=\"T_94f7e_row2_col7\" class=\"data row2 col7\" >0.30</td>\n    </tr>\n  </tbody>\n</table>\n",
+      "application/papermill.record/text/plain": "<pandas.io.formats.style.Styler at 0x7a2cc40878b0>"
      },
      "metadata": {
       "scrapbook": {
@@ -612,20 +612,20 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_75ad1 tr:nth-child(even) {\n",
+       "#T_92448 tr:nth-child(even) {\n",
        "  background-color: rgba(139, 69, 19, 0.08);\n",
        "}\n",
-       "#T_75ad1 tr:nth-child(odd) {\n",
+       "#T_92448 tr:nth-child(odd) {\n",
        "  background: #FFF;\n",
        "}\n",
-       "#T_75ad1 tr {\n",
+       "#T_92448 tr {\n",
        "  font-size: 14px;\n",
        "}\n",
-       "#T_75ad1 th:nth-child(1) {\n",
+       "#T_92448 th:nth-child(1) {\n",
        "  background-color: #FFF;\n",
        "  text-align: right;\n",
        "}\n",
-       "#T_75ad1 caption {\n",
+       "#T_92448 caption {\n",
        "  font-size: 14px;\n",
        "  font-style: italic;\n",
        "  caption-side: bottom;\n",
@@ -633,95 +633,95 @@
        "  margin-top: 10px;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_75ad1\">\n",
+       "<table id=\"T_92448\">\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_75ad1_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
-       "      <th id=\"T_75ad1_level0_col1\" class=\"col_heading level0 col1\" >nsamples</th>\n",
+       "      <th id=\"T_92448_level0_col0\" class=\"col_heading level0 col0\" >pcs/m</th>\n",
+       "      <th id=\"T_92448_level0_col1\" class=\"col_heading level0 col1\" >nsamples</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row0\" class=\"row_heading level0 row0\" >Saint-Gingolph</th>\n",
-       "      <td id=\"T_75ad1_row0_col0\" class=\"data row0 col0\" >0.68</td>\n",
-       "      <td id=\"T_75ad1_row0_col1\" class=\"data row0 col1\" >13</td>\n",
+       "      <th id=\"T_92448_level0_row0\" class=\"row_heading level0 row0\" >Saint-Gingolph</th>\n",
+       "      <td id=\"T_92448_row0_col0\" class=\"data row0 col0\" >0.68</td>\n",
+       "      <td id=\"T_92448_row0_col1\" class=\"data row0 col1\" >13</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row1\" class=\"row_heading level0 row1\" >Allaman</th>\n",
-       "      <td id=\"T_75ad1_row1_col0\" class=\"data row1 col0\" >0.14</td>\n",
-       "      <td id=\"T_75ad1_row1_col1\" class=\"data row1 col1\" >3</td>\n",
+       "      <th id=\"T_92448_level0_row1\" class=\"row_heading level0 row1\" >Allaman</th>\n",
+       "      <td id=\"T_92448_row1_col0\" class=\"data row1 col0\" >0.14</td>\n",
+       "      <td id=\"T_92448_row1_col1\" class=\"data row1 col1\" >3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row2\" class=\"row_heading level0 row2\" >Bourg-en-Lavaux</th>\n",
-       "      <td id=\"T_75ad1_row2_col0\" class=\"data row2 col0\" >0.12</td>\n",
-       "      <td id=\"T_75ad1_row2_col1\" class=\"data row2 col1\" >2</td>\n",
+       "      <th id=\"T_92448_level0_row2\" class=\"row_heading level0 row2\" >Bourg-en-Lavaux</th>\n",
+       "      <td id=\"T_92448_row2_col0\" class=\"data row2 col0\" >0.12</td>\n",
+       "      <td id=\"T_92448_row2_col1\" class=\"data row2 col1\" >2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row3\" class=\"row_heading level0 row3\" >La Tour-de-Peilz</th>\n",
-       "      <td id=\"T_75ad1_row3_col0\" class=\"data row3 col0\" >0.12</td>\n",
-       "      <td id=\"T_75ad1_row3_col1\" class=\"data row3 col1\" >25</td>\n",
+       "      <th id=\"T_92448_level0_row3\" class=\"row_heading level0 row3\" >La Tour-de-Peilz</th>\n",
+       "      <td id=\"T_92448_row3_col0\" class=\"data row3 col0\" >0.12</td>\n",
+       "      <td id=\"T_92448_row3_col1\" class=\"data row3 col1\" >25</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row4\" class=\"row_heading level0 row4\" >Montreux</th>\n",
-       "      <td id=\"T_75ad1_row4_col0\" class=\"data row4 col0\" >0.11</td>\n",
-       "      <td id=\"T_75ad1_row4_col1\" class=\"data row4 col1\" >53</td>\n",
+       "      <th id=\"T_92448_level0_row4\" class=\"row_heading level0 row4\" >Montreux</th>\n",
+       "      <td id=\"T_92448_row4_col0\" class=\"data row4 col0\" >0.11</td>\n",
+       "      <td id=\"T_92448_row4_col1\" class=\"data row4 col1\" >53</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row5\" class=\"row_heading level0 row5\" >Vevey</th>\n",
-       "      <td id=\"T_75ad1_row5_col0\" class=\"data row5 col0\" >0.11</td>\n",
-       "      <td id=\"T_75ad1_row5_col1\" class=\"data row5 col1\" >44</td>\n",
+       "      <th id=\"T_92448_level0_row5\" class=\"row_heading level0 row5\" >Vevey</th>\n",
+       "      <td id=\"T_92448_row5_col0\" class=\"data row5 col0\" >0.11</td>\n",
+       "      <td id=\"T_92448_row5_col1\" class=\"data row5 col1\" >44</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row6\" class=\"row_heading level0 row6\" >Saint-Sulpice (VD)</th>\n",
-       "      <td id=\"T_75ad1_row6_col0\" class=\"data row6 col0\" >0.06</td>\n",
-       "      <td id=\"T_75ad1_row6_col1\" class=\"data row6 col1\" >15</td>\n",
+       "      <th id=\"T_92448_level0_row6\" class=\"row_heading level0 row6\" >Saint-Sulpice (VD)</th>\n",
+       "      <td id=\"T_92448_row6_col0\" class=\"data row6 col0\" >0.06</td>\n",
+       "      <td id=\"T_92448_row6_col1\" class=\"data row6 col1\" >15</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row7\" class=\"row_heading level0 row7\" >Versoix</th>\n",
-       "      <td id=\"T_75ad1_row7_col0\" class=\"data row7 col0\" >0.05</td>\n",
-       "      <td id=\"T_75ad1_row7_col1\" class=\"data row7 col1\" >4</td>\n",
+       "      <th id=\"T_92448_level0_row7\" class=\"row_heading level0 row7\" >Versoix</th>\n",
+       "      <td id=\"T_92448_row7_col0\" class=\"data row7 col0\" >0.05</td>\n",
+       "      <td id=\"T_92448_row7_col1\" class=\"data row7 col1\" >4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row8\" class=\"row_heading level0 row8\" >Genève</th>\n",
-       "      <td id=\"T_75ad1_row8_col0\" class=\"data row8 col0\" >0.03</td>\n",
-       "      <td id=\"T_75ad1_row8_col1\" class=\"data row8 col1\" >29</td>\n",
+       "      <th id=\"T_92448_level0_row8\" class=\"row_heading level0 row8\" >Genève</th>\n",
+       "      <td id=\"T_92448_row8_col0\" class=\"data row8 col0\" >0.03</td>\n",
+       "      <td id=\"T_92448_row8_col1\" class=\"data row8 col1\" >29</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row9\" class=\"row_heading level0 row9\" >Préverenges</th>\n",
-       "      <td id=\"T_75ad1_row9_col0\" class=\"data row9 col0\" >0.01</td>\n",
-       "      <td id=\"T_75ad1_row9_col1\" class=\"data row9 col1\" >15</td>\n",
+       "      <th id=\"T_92448_level0_row9\" class=\"row_heading level0 row9\" >Préverenges</th>\n",
+       "      <td id=\"T_92448_row9_col0\" class=\"data row9 col0\" >0.01</td>\n",
+       "      <td id=\"T_92448_row9_col1\" class=\"data row9 col1\" >15</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row10\" class=\"row_heading level0 row10\" >Tolochenaz</th>\n",
-       "      <td id=\"T_75ad1_row10_col0\" class=\"data row10 col0\" >0.01</td>\n",
-       "      <td id=\"T_75ad1_row10_col1\" class=\"data row10 col1\" >3</td>\n",
+       "      <th id=\"T_92448_level0_row10\" class=\"row_heading level0 row10\" >Tolochenaz</th>\n",
+       "      <td id=\"T_92448_row10_col0\" class=\"data row10 col0\" >0.01</td>\n",
+       "      <td id=\"T_92448_row10_col1\" class=\"data row10 col1\" >3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row11\" class=\"row_heading level0 row11\" >Lausanne</th>\n",
-       "      <td id=\"T_75ad1_row11_col0\" class=\"data row11 col0\" >0.01</td>\n",
-       "      <td id=\"T_75ad1_row11_col1\" class=\"data row11 col1\" >20</td>\n",
+       "      <th id=\"T_92448_level0_row11\" class=\"row_heading level0 row11\" >Lausanne</th>\n",
+       "      <td id=\"T_92448_row11_col0\" class=\"data row11 col0\" >0.01</td>\n",
+       "      <td id=\"T_92448_row11_col1\" class=\"data row11 col1\" >20</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row12\" class=\"row_heading level0 row12\" >Gland</th>\n",
-       "      <td id=\"T_75ad1_row12_col0\" class=\"data row12 col0\" >0.00</td>\n",
-       "      <td id=\"T_75ad1_row12_col1\" class=\"data row12 col1\" >22</td>\n",
+       "      <th id=\"T_92448_level0_row12\" class=\"row_heading level0 row12\" >Gland</th>\n",
+       "      <td id=\"T_92448_row12_col0\" class=\"data row12 col0\" >0.00</td>\n",
+       "      <td id=\"T_92448_row12_col1\" class=\"data row12 col1\" >22</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row13\" class=\"row_heading level0 row13\" >Morges</th>\n",
-       "      <td id=\"T_75ad1_row13_col0\" class=\"data row13 col0\" >0.00</td>\n",
-       "      <td id=\"T_75ad1_row13_col1\" class=\"data row13 col1\" >1</td>\n",
+       "      <th id=\"T_92448_level0_row13\" class=\"row_heading level0 row13\" >Morges</th>\n",
+       "      <td id=\"T_92448_row13_col0\" class=\"data row13 col0\" >0.00</td>\n",
+       "      <td id=\"T_92448_row13_col1\" class=\"data row13 col1\" >1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th id=\"T_75ad1_level0_row14\" class=\"row_heading level0 row14\" >Rolle</th>\n",
-       "      <td id=\"T_75ad1_row14_col0\" class=\"data row14 col0\" >0.00</td>\n",
-       "      <td id=\"T_75ad1_row14_col1\" class=\"data row14 col1\" >1</td>\n",
+       "      <th id=\"T_92448_level0_row14\" class=\"row_heading level0 row14\" >Rolle</th>\n",
+       "      <td id=\"T_92448_row14_col0\" class=\"data row14 col0\" >0.00</td>\n",
+       "      <td id=\"T_92448_row14_col1\" class=\"data row14 col1\" >1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x7896afd57f40>"
+       "<pandas.io.formats.style.Styler at 0x7a2c708f6250>"
       ]
      },
      "metadata": {
@@ -743,6 +743,71 @@
     "cp = cpm.style.set_table_styles(table_css_styles).format(precision=2)\n",
     "glue('city_rankings', cp, display=True)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "989efbdc-f400-4894-8424-a5c4856595ca",
+   "metadata": {
+    "editable": true,
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": [
+     "remove-input"
+    ]
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "\n",
+       "\n",
+       "This script updated 21/03/2024 in Biel, CH\n",
+       "\n",
+       "❤️ __what you do everyday:__ *analyst at hammerdirt*\n"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import datetime as dt\n",
+    "from IPython.display import Markdown as md\n",
+    "today = dt.datetime.now().date().strftime(\"%d/%m/%Y\")\n",
+    "where = \"Biel, CH\"\n",
+    "\n",
+    "my_block = f\"\"\"\n",
+    "\n",
+    "This script updated {today} in {where}\n",
+    "\n",
+    "\\u2764\\ufe0f __what you do everyday:__ *analyst at hammerdirt*\n",
+    "\"\"\"\n",
+    "\n",
+    "md(my_block)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11d8473e-9271-4828-b1fc-ecbcf2f28765",
+   "metadata": {
+    "editable": true,
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {