Merge pull request #14 from usnistgov/develop

Train from folder, and other minor updates.
usnistgov · May 18, 2021 · 43d8027 · 43d8027
2 parents 69c77a2 + a9c1160
commit 43d8027
Show file tree

Hide file tree

Showing 85 changed files with 1,769 additions and 55 deletions.
diff --git a/README.md b/README.md
@@ -3,3 +3,4 @@
 # ALIGNN
 Atomistic Line Graph Neural Network
 
+>>> python alignn/scripts/train_folder.py --root_dir "alignn/examples/sample_data" --config "alignn/examples/sample_data/config_example_regrssion.json"
diff --git a/alignn/__init__.py b/alignn/__init__.py
@@ -1,2 +1,2 @@
 """Version number."""
-__version__ = "2021.5.11"
+__version__ = "2021.5.16"
diff --git a/alignn/config.py b/alignn/config.py
@@ -62,6 +62,7 @@
     "dfpt_piezo_max_dij",
     "gap pbe",
     "e_form",
+    "e_hull",
     "mu_b",
     "bulk modulus",
     "shear modulus",
@@ -81,6 +82,7 @@
     "A",
     "B",
     "C",
+    "target",
 ]
 
 
@@ -90,7 +92,9 @@ class TrainingConfig(BaseSettings):
     version: str = VERSION
 
     # dataset configuration
-    dataset: Literal["dft_3d", "dft_2d", "megnet", "qm9"] = "dft_3d"
+    dataset: Literal[
+        "dft_3d", "dft_2d", "megnet", "qm9", "user_data"
+    ] = "dft_3d"
     target: TARGET_ENUM = "formation_energy_peratom"
     atom_features: Literal["basic", "atomic_number", "cfid", "cgcnn"] = "cgcnn"
     neighbor_strategy: Literal["k-nearest", "voronoi"] = "k-nearest"
@@ -108,7 +112,8 @@ class TrainingConfig(BaseSettings):
     train_ratio: Optional[float] = 0.8
     val_ratio: Optional[float] = 0.1
     test_ratio: Optional[float] = 0.1
-    epochs: int = 200
+    target_multiplication_factor: Optional[float] = None
+    epochs: int = 300
     batch_size: int = 64
     weight_decay: float = 0
     learning_rate: float = 1e-2
@@ -119,7 +124,7 @@ class TrainingConfig(BaseSettings):
     scheduler: Literal["onecycle", "none"] = "onecycle"
     pin_memory: bool = False
     save_dataloader: bool = False
-    write_checkpoint: bool = False
+    write_checkpoint: bool = True
     write_predictions: bool = True
     store_outputs: bool = True
     progress: bool = True
@@ -138,7 +143,8 @@ class TrainingConfig(BaseSettings):
         ALIGNNConfig,
         DenseALIGNNConfig,
         ACGCNNConfig,
-    ] = CGCNNConfig(name="cgcnn")
+    ] = ALIGNNConfig(name="alignn")
+    # ] = CGCNNConfig(name="cgcnn")
 
     @root_validator()
     def set_input_size(cls, values):

diff --git a/alignn/data.py b/alignn/data.py
@@ -174,6 +174,14 @@ def get_torch_dataset(
     df = pd.DataFrame(dataset)
     vals = df[target].values
     print("data range", np.max(vals), np.min(vals))
+
+    f = open("data_range", "w")
+    line = "Max=" + str(np.max(vals)) + "\n"
+    f.write(line)
+    line = "Min=" + str(np.min(vals)) + "\n"
+    f.write(line)
+    f.close()
+
     graphs = load_graphs(
         df,
         name=name,
@@ -197,28 +205,30 @@ def get_torch_dataset(
 
 def get_train_val_loaders(
     dataset: str = "dft_3d",
+    dataset_array=[],
     target: str = "formation_energy_peratom",
-    atom_features: str = "atomic_number",
+    atom_features: str = "cgcnn",
     neighbor_strategy: str = "k-nearest",
     n_train=None,
     n_val=None,
     n_test=None,
     train_ratio=None,
     val_ratio=0.1,
     test_ratio=0.1,
-    batch_size: int = 8,
+    batch_size: int = 5,
     standardize: bool = False,
-    line_graph: bool = False,
+    line_graph: bool = True,
     split_seed: int = 123,
     workers: int = 0,
     pin_memory: bool = True,
-    save_dataloader: bool = True,
+    save_dataloader: bool = False,
     filename: str = "sample",
     id_tag: str = "jid",
     use_canonize: bool = False,
     cutoff: float = 8.0,
     max_neighbors: int = 12,
     classification_threshold: Optional[float] = None,
+    target_multiplication_factor: Optional[float] = None,
 ):
     """Help function to set up Jarvis train and val dataloaders."""
     train_sample = filename + "_train.data"
@@ -254,7 +264,11 @@ def get_train_val_loaders(
         # print("test", len(test_loader.dataset))
     else:
 
-        d = jdata(dataset)
+        if not dataset_array:
+            d = jdata(dataset)
+        else:
+            d = dataset_array
+
         dat = []
         if classification_threshold is not None:
             print(
@@ -267,6 +281,8 @@ def get_train_val_loaders(
             print("Converting target data into 1 and 0.")
         for i in d:
             if i[target] != "na" and not math.isnan(i[target]):
+                if target_multiplication_factor is not None:
+                    i[target] = i[target] * target_multiplication_factor
                 if classification_threshold is not None:
                     if i[target] <= classification_threshold:
                         i[target] = 0
@@ -297,7 +313,7 @@ def get_train_val_loaders(
         ids_train_val_test["id_train"] = [dat[i][id_tag] for i in id_train]
         ids_train_val_test["id_val"] = [dat[i][id_tag] for i in id_val]
         ids_train_val_test["id_test"] = [dat[i][id_tag] for i in id_test]
-        dumpjson(data=ids_train_val_test, filename="ids_train_val_tes.json")
+        dumpjson(data=ids_train_val_test, filename="ids_train_val_test.json")
         dataset_train = [dat[x] for x in id_train]
         dataset_val = [dat[x] for x in id_val]
         dataset_test = [dat[x] for x in id_test]

diff --git a/alignn/examples/sample_data/POSCAR-JVASP-10.vasp b/alignn/examples/sample_data/POSCAR-JVASP-10.vasp
@@ -0,0 +1,11 @@
+System
+1.0
+1.6777483798834445 -2.9059452409270157 -1.1e-15
+1.6777483798834438 2.9059452409270126 -7e-16
+-6.5e-15 -8e-16 6.220805465667012
+V Se
+1 2
+direct
+0.0 0.0 0.0 
+0.6666669999999968 0.3333330000000032 0.7479606991085345 
+0.3333330000000032 0.6666669999999968 0.252039300891465 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-107772.vasp b/alignn/examples/sample_data/POSCAR-JVASP-107772.vasp
@@ -0,0 +1,12 @@
+System
+1.0
+4.376835486482439 0.0086562096165887 7.148251977291244
+2.0211490103296166 3.8822313794698684 7.148251977291244
+0.0142338540946976 0.008656214510917 8.38176620441039
+Bi Sb
+3 1
+direct
+0.11687114695010013 0.11687114695010009 0.11687114695134818 
+0.885057350916569 0.8850573509165686 0.8850573509144881 
+0.3806761740317465 0.3806761740317465 0.3806761740305207 
+0.6173953281015849 0.6173953281015848 0.6173953281036431 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-13526.vasp b/alignn/examples/sample_data/POSCAR-JVASP-13526.vasp
@@ -0,0 +1,24 @@
+System
+1.0
+7.091458561131444 0.0 0.0
+0.0 12.284128695721973 0.0
+-8.862874621478095 0.0 25.0
+Y Br
+4 12
+direct
+0.033346999999999086 0.6240773822144681 0.1871170000000006 
+0.033346999999999086 0.9574286177855293 0.1871170000000006 
+0.5333479999999966 0.12407738221446811 0.1871170000000006 
+0.5333479999999966 0.4574286177855292 0.1871170000000006 
+0.2891270840017781 0.46667191911829303 0.2510176333839372 
+0.2891270840017781 0.11483508088170911 0.2510176333839372 
+0.2613405348547832 0.7907530000000023 0.2510114569972214 
+0.7891270840017786 0.9666709191182953 0.2510176333839372 
+0.7891270840017786 0.6148350808817092 0.2510176333839372 
+0.7613405348547837 0.2907530000000023 0.2510114569972214 
+0.30535446514521963 0.2907530000000023 0.1232235430027774 
+0.2775679159982247 0.9666709191182953 0.123216366616057 
+0.2775679159982247 0.6148350808817092 0.123216366616057 
+0.8053554651452168 0.7907530000000023 0.1232235430027774 
+0.7775679159982244 0.46667191911829303 0.123216366616057 
+0.7775679159982244 0.11483508088170911 0.123216366616057 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-1372.vasp b/alignn/examples/sample_data/POSCAR-JVASP-1372.vasp
@@ -0,0 +1,10 @@
+System
+1.0
+3.5058938597621094 -3.081249e-10 2.0241289627124215
+1.1686312862968669 3.3053879820023613 2.0241289627124215
+-8.715088e-10 -6.162497e-10 4.048256928443838
+Al As
+1 1
+direct
+0.0 0.0 0.0 
+0.24999999999999997 0.25 0.24999999999999997 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-14014.vasp b/alignn/examples/sample_data/POSCAR-JVASP-14014.vasp
@@ -0,0 +1,20 @@
+System
+1.0
+4.157436115454804 -0.0 0.0
+-0.0 7.038494037846648 0.0
+0.0 0.0 7.411178065479046
+Tb Mn Si
+4 4 4
+direct
+0.25 0.5014870121743014 0.1863876024079978 
+0.75 0.49851298782569875 0.8136123975920022 
+0.25 0.0014870121743013 0.3136123975920026 
+0.75 0.9985129878256985 0.6863876024079979 
+0.75 0.8608859093979077 0.06027225572734521 
+0.25 0.1391140906020922 0.939727744272655 
+0.75 0.3608859093979077 0.43972774427265476 
+0.25 0.6391140906020923 0.5602722557273451 
+0.25 0.792634730215007 0.8919146343653592 
+0.75 0.207365269784993 0.10808536563464112 
+0.25 0.2926347302150071 0.6080853656346409 
+0.75 0.707365269784993 0.3919146343653588 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-14441.vasp b/alignn/examples/sample_data/POSCAR-JVASP-14441.vasp
@@ -0,0 +1,11 @@
+System
+1.0
+2.8173501021142346 -0.0 0.0
+-1.4086750510571173 2.439896157530945 0.0
+0.0 0.0 24.551775
+Co O
+1 2
+direct
+0.2690539999999971 0.9290120000000003 0.0926970000000011 
+0.6023870000000002 0.595678999999997 0.1307621356947131 
+0.9357210000000009 0.26234500000000344 0.0546328643052866 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-14873.vasp b/alignn/examples/sample_data/POSCAR-JVASP-14873.vasp
@@ -0,0 +1,15 @@
+System
+1.0
+4.191262576674699 0.0 -0.0
+-0.0 4.191262576674699 0.0
+-0.0 0.0 4.191262576674699
+Sr B
+1 6
+direct
+0.0 0.0 0.0 
+0.2028453684309125 0.5 0.5 
+0.5 0.5 0.7971546315690875 
+0.5 0.5 0.2028453684309125 
+0.5 0.2028453684309125 0.5 
+0.5 0.7971546315690875 0.5 
+0.7971546315690875 0.5 0.5 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-15345.vasp b/alignn/examples/sample_data/POSCAR-JVASP-15345.vasp
@@ -0,0 +1,12 @@
+System
+1.0
+3.5666343258756448 0.0 0.0
+0.0 3.60492483256326 -1.0516480500920402
+0.0 0.0043800721536433 3.7551864245512623
+Y Co C
+1 1 2
+direct
+0.0 0.9970518040927455 0.00294819590736377 
+0.5 0.6150401254054609 0.3849598745944179 
+0.5 0.15192770422861318 0.5440196337270639 
+0.5 0.4559803662731792 0.8480722957711558 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-1996.vasp b/alignn/examples/sample_data/POSCAR-JVASP-1996.vasp
@@ -0,0 +1,10 @@
+System
+1.0
+3.93712543178282 0.0 2.273100275741533
+1.3123751439276066 3.7119571065192623 2.273100275741533
+0.0 0.0 4.546200551483066
+Na I
+1 1
+direct
+0.0 0.0 0.0 
+0.5 0.5 0.5 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-21210.vasp b/alignn/examples/sample_data/POSCAR-JVASP-21210.vasp
@@ -0,0 +1,9 @@
+System
+1.0
+1.6712283e-08 -2.508029669761222 3.5458136263853106
+-2.172017276374766 1.254014874098203 3.545813646368687
+-2.17201803290572 -1.254014795663004 -3.5458136064019246
+Xe
+1
+direct
+0.0 0.0 0.0 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-22556.vasp b/alignn/examples/sample_data/POSCAR-JVASP-22556.vasp
@@ -0,0 +1,13 @@
+System
+1.0
+3.790914410660539 -0.0 0.0
+0.0 3.790914410660539 0.0
+-0.0 -0.0 3.790914410660539
+Sr Fe O
+1 1 3
+direct
+0.4999990000000025 0.4999990000000025 0.4999990000000025 
+0.0 0.0 0.0 
+0.4999990000000025 0.0 0.0 
+0.0 0.4999990000000025 0.0 
+0.0 0.0 0.4999990000000025 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-27901.vasp b/alignn/examples/sample_data/POSCAR-JVASP-27901.vasp
@@ -0,0 +1,14 @@
+System
+1.0
+3.4878362323679837 3.6597344e-09 0.0
+-1.7439186098402102 3.020554822453009 0.0
+0.0 0.0 25.743165
+Sc H Cl
+2 2 2
+direct
+0.6666669999999968 0.3333330000000032 0.45082619084199527 
+0.33333300000000327 0.6666669999999969 0.5491738091580051 
+0.6666669999999968 0.3333330000000032 0.5287351839124973 
+0.33333300000000327 0.6666669999999969 0.47126481608750276 
+0.0 0.0 0.3881804432720387 
+0.0 0.0 0.6118195567279613 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-28397.vasp b/alignn/examples/sample_data/POSCAR-JVASP-28397.vasp
@@ -0,0 +1,16 @@
+System
+1.0
+0.0 -3.9587610833154616 0.0
+-6.655928089533787 0.0 0.0
+0.0 0.0 -23.94045079597872
+Si S
+4 4
+direct
+0.0 0.0 0.5217263648738928 
+0.0 0.5 0.5217263648738928 
+0.5 0.0 0.4661843287970869 
+0.5 0.5 0.4661843287970869 
+0.0524900550457348 0.7500000000000001 0.5792751627500841 
+0.9475099449542649 0.25 0.5792751627500841 
+0.4474867899417421 0.7500000000000001 0.40863414357892813 
+0.5525132100582582 0.25 0.40863414357892813 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-28565.vasp b/alignn/examples/sample_data/POSCAR-JVASP-28565.vasp
@@ -0,0 +1,17 @@
+System
+1.0
+3.3542337275744103 0.0 0.0
+-1.6771168637872051 2.904850045503021 0.0002624763854255
+0.0 0.0027191662067697 29.227006366170723
+Te Mo W Se S
+2 2 1 2 2
+direct
+0.3332869375319439 0.6665748750638851 0.40880470960271253 
+0.3334050587801155 0.6668121175602401 0.2788667649202174 
+0.3335186248083656 0.6670362496167267 0.11458088390572692 
+0.6666801663591748 0.33335933271835083 0.3438741864905265 
+0.3331138284834239 0.6662286569668452 0.5825261819744669 
+0.6664959135073409 0.3329918270146898 0.5252624785410095 
+0.6664002633646019 0.3327995267292049 0.639695963563112 
+0.6669034856871763 0.33380597137434753 0.06276093238425431 
+0.6667957214778616 0.3335914429557147 0.1664678986179713 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-28634.vasp b/alignn/examples/sample_data/POSCAR-JVASP-28634.vasp
@@ -0,0 +1,20 @@
+System
+1.0
+3.2250494729190726 2.216578e-10 2.163e-13
+-1.6125242360333125 2.7929740932668943 -8.4754501616e-06
+6.6135e-12 -9.7386036979e-05 34.14068378844537
+Mo W Se S
+1 3 2 6
+direct
+0.33331504683701274 0.6666300936741254 0.0934536896030271 
+0.33331656497272827 0.6666341299456554 0.47208556491119213 
+0.6666698924990063 0.33333978499784117 0.28247993950367123 
+0.6666991220003533 0.3333972440007849 0.6548932577640771 
+0.33334341592455036 0.6666888318491291 0.3328984548376194 
+0.33332779768550075 0.6666565953711356 0.2320623862553914 
+0.33337390316228616 0.6667488063245635 0.7006769649140224 
+0.6666482437297062 0.33329648745935525 0.0479187308537724 
+0.6666490346540366 0.33329706930798436 0.4262562969343839 
+0.6666480620607286 0.33329512412140816 0.1390473399063092 
+0.6666512247313715 0.33330144946262313 0.5179005541158488 
+0.33335669174272836 0.6667143834853922 0.6090748204006833 
diff --git a/alignn/examples/sample_data/POSCAR-JVASP-28704.vasp b/alignn/examples/sample_data/POSCAR-JVASP-28704.vasp
@@ -0,0 +1,20 @@
+System
+1.0
+3.292134155794691 0.0 0.0
+-1.6460670778973454 2.8510786681143565 -3.615752048e-06
+0.0 -0.0001768206441563 34.978246270650075
+Mo W Se S
+3 1 6 2
+direct
+0.3333192249247229 0.6666384498494459 0.0966675137812058 
+0.6666558392026922 0.3333126784053811 0.2791091321598709 
+0.6666926464398288 0.3333852928796507 0.6584266681105794 
+0.3333321581155246 0.666664316231042 0.468712621722382 
+0.3333230348691514 0.6666470697383001 0.3273013286877133 
+0.3333590853838843 0.6667201707677635 0.7065686651425439 
+0.6666558450522622 0.3333116901045159 0.4202334807678751 
+0.6666765519168195 0.3333521038336415 0.5171906710959798 
+0.3333210915930135 0.6666421831860199 0.23092332016136433 
+0.3333560781404684 0.6667131562809414 0.6102231914914819 
+0.6666426939013361 0.33328538780266426 0.0528105185440566 
+0.6666647504603075 0.33332850092061717 0.1405808883349591
Original file line number	Diff line number	Diff line change
Expand Up		@@ -3,3 +3,4 @@
		# ALIGNN
		Atomistic Line Graph Neural Network

		>>> python alignn/scripts/train_folder.py --root_dir "alignn/examples/sample_data" --config "alignn/examples/sample_data/config_example_regrssion.json"