\n",
" | \n",
- " Dashboard: http://4.154.137.246:8787/status\n",
+ " Dashboard: http://20.80.185.4:8787/status\n",
" | \n",
" \n",
" Workers: 4\n",
@@ -885,11 +839,11 @@
" \n",
" \n",
" Scheduler\n",
- " Scheduler-da7b39f6-8d7b-4580-9521-8667cea57940 \n",
+ " Scheduler-9c563196-caf1-4498-aa20-4c4557aa1a47 \n",
" \n",
" \n",
" | \n",
- " Comm: tls://10.5.0.26:8786\n",
+ " Comm: tls://10.5.0.29:8786\n",
" | \n",
" \n",
" Workers: 4\n",
@@ -897,7 +851,7 @@
" | \n",
" \n",
" | \n",
- " Dashboard: http://10.5.0.26:8787/status\n",
+ " Dashboard: http://10.5.0.29:8787/status\n",
" | \n",
" \n",
" Total threads: 4\n",
@@ -905,7 +859,7 @@
" | \n",
" \n",
" | \n",
- " Started: 6 minutes ago\n",
+ " Started: 7 minutes ago\n",
" | \n",
" \n",
" Total memory: 440.42 GiB\n",
@@ -926,12 +880,12 @@
" \n",
" \n",
" \n",
- " Worker: dask-cd718e4c-worker-3cf05f03-0\n",
+ " Worker: dask-e1db89fb-worker-396d96a3-0\n",
" \n",
" \n",
" \n",
" | \n",
- " Comm: tls://10.5.0.28:37831\n",
+ " Comm: tls://10.5.0.30:35833\n",
" | \n",
" \n",
" Total threads: 1\n",
@@ -939,7 +893,7 @@
" | \n",
" \n",
" | \n",
- " Dashboard: http://10.5.0.28:44385/status\n",
+ " Dashboard: http://10.5.0.30:43943/status\n",
" | \n",
" \n",
" Memory: 110.11 GiB\n",
@@ -947,13 +901,13 @@
" | \n",
" \n",
" | \n",
- " Nanny: tls://10.5.0.28:43437\n",
+ " Nanny: tls://10.5.0.30:37243\n",
" | \n",
" | \n",
" \n",
" \n",
" | \n",
- " Local directory: /tmp/dask-scratch-space/worker-laurl35q\n",
+ " Local directory: /tmp/dask-scratch-space/worker-jk35m4vu\n",
" | \n",
" \n",
"\n",
@@ -969,47 +923,6 @@
" \n",
"\n",
" \n",
- " \n",
- " | \n",
- " Tasks executing: \n",
- " | \n",
- " \n",
- " Tasks in memory: \n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Tasks ready: \n",
- " | \n",
- " \n",
- " Tasks in flight: \n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " CPU usage: 0.0%\n",
- " | \n",
- " \n",
- " Last seen: Just now\n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Memory usage: 590.09 MiB\n",
- " | \n",
- " \n",
- " Spilled bytes: 0 B\n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Read bytes: 7.72 kiB\n",
- " | \n",
- " \n",
- " Write bytes: 13.27 kiB\n",
- " | \n",
- " \n",
- " \n",
"\n",
" \n",
" \n",
@@ -1021,12 +934,12 @@
" \n",
" \n",
" \n",
- " Worker: dask-cd718e4c-worker-3cf05f03-1\n",
+ " Worker: dask-e1db89fb-worker-396d96a3-1\n",
" \n",
" \n",
" \n",
" | \n",
- " Comm: tls://10.5.0.28:46499\n",
+ " Comm: tls://10.5.0.30:39857\n",
" | \n",
" \n",
" Total threads: 1\n",
@@ -1034,7 +947,7 @@
" | \n",
" \n",
" | \n",
- " Dashboard: http://10.5.0.28:36329/status\n",
+ " Dashboard: http://10.5.0.30:39981/status\n",
" | \n",
" \n",
" Memory: 110.11 GiB\n",
@@ -1042,13 +955,13 @@
" | \n",
" \n",
" | \n",
- " Nanny: tls://10.5.0.28:42893\n",
+ " Nanny: tls://10.5.0.30:33125\n",
" | \n",
" | \n",
" \n",
" \n",
" | \n",
- " Local directory: /tmp/dask-scratch-space/worker-rz4dg7ou\n",
+ " Local directory: /tmp/dask-scratch-space/worker-gog2yjq8\n",
" | \n",
" \n",
"\n",
@@ -1064,47 +977,6 @@
" \n",
"\n",
" \n",
- " \n",
- " | \n",
- " Tasks executing: \n",
- " | \n",
- " \n",
- " Tasks in memory: \n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Tasks ready: \n",
- " | \n",
- " \n",
- " Tasks in flight: \n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " CPU usage: 2.0%\n",
- " | \n",
- " \n",
- " Last seen: Just now\n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Memory usage: 590.06 MiB\n",
- " | \n",
- " \n",
- " Spilled bytes: 0 B\n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Read bytes: 2.07 kiB\n",
- " | \n",
- " \n",
- " Write bytes: 11.07 kiB\n",
- " | \n",
- " \n",
- " \n",
"\n",
" \n",
" \n",
@@ -1116,12 +988,12 @@
" \n",
" \n",
" \n",
- " Worker: dask-cd718e4c-worker-7b9b2ff2-0\n",
+ " Worker: dask-e1db89fb-worker-f3e80672-0\n",
" \n",
" \n",
" \n",
" | \n",
- " Comm: tls://10.5.0.27:33135\n",
+ " Comm: tls://10.5.0.31:40645\n",
" | \n",
" \n",
" Total threads: 1\n",
@@ -1129,7 +1001,7 @@
" | \n",
" \n",
" | \n",
- " Dashboard: http://10.5.0.27:36693/status\n",
+ " Dashboard: http://10.5.0.31:38957/status\n",
" | \n",
" \n",
" Memory: 110.11 GiB\n",
@@ -1137,13 +1009,13 @@
" | \n",
" \n",
" | \n",
- " Nanny: tls://10.5.0.27:44451\n",
+ " Nanny: tls://10.5.0.31:35155\n",
" | \n",
" | \n",
" \n",
" \n",
" | \n",
- " Local directory: /tmp/dask-scratch-space/worker-rkwt_wd2\n",
+ " Local directory: /tmp/dask-scratch-space/worker-jqle2l9n\n",
" | \n",
" \n",
"\n",
@@ -1159,47 +1031,6 @@
" \n",
"\n",
" \n",
- " \n",
- " | \n",
- " Tasks executing: \n",
- " | \n",
- " \n",
- " Tasks in memory: \n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Tasks ready: \n",
- " | \n",
- " \n",
- " Tasks in flight: \n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " CPU usage: 4.0%\n",
- " | \n",
- " \n",
- " Last seen: Just now\n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Memory usage: 594.46 MiB\n",
- " | \n",
- " \n",
- " Spilled bytes: 0 B\n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Read bytes: 611.7517621464344 B\n",
- " | \n",
- " \n",
- " Write bytes: 3.26 kiB\n",
- " | \n",
- " \n",
- " \n",
"\n",
" \n",
" \n",
@@ -1211,12 +1042,12 @@
" \n",
" \n",
" \n",
- " Worker: dask-cd718e4c-worker-7b9b2ff2-1\n",
+ " Worker: dask-e1db89fb-worker-f3e80672-1\n",
" \n",
" \n",
" \n",
" | \n",
- " Comm: tls://10.5.0.27:36605\n",
+ " Comm: tls://10.5.0.31:42211\n",
" | \n",
" \n",
" Total threads: 1\n",
@@ -1224,7 +1055,7 @@
" | \n",
" \n",
" | \n",
- " Dashboard: http://10.5.0.27:41189/status\n",
+ " Dashboard: http://10.5.0.31:41035/status\n",
" | \n",
" \n",
" Memory: 110.11 GiB\n",
@@ -1232,13 +1063,13 @@
" | \n",
" \n",
" | \n",
- " Nanny: tls://10.5.0.27:35583\n",
+ " Nanny: tls://10.5.0.31:42491\n",
" | \n",
" | \n",
" \n",
" \n",
" | \n",
- " Local directory: /tmp/dask-scratch-space/worker-iclmame3\n",
+ " Local directory: /tmp/dask-scratch-space/worker-vwjtj063\n",
" | \n",
" \n",
"\n",
@@ -1254,47 +1085,6 @@
" \n",
"\n",
" \n",
- " \n",
- " | \n",
- " Tasks executing: \n",
- " | \n",
- " \n",
- " Tasks in memory: \n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Tasks ready: \n",
- " | \n",
- " \n",
- " Tasks in flight: \n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " CPU usage: 2.0%\n",
- " | \n",
- " \n",
- " Last seen: Just now\n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Memory usage: 592.07 MiB\n",
- " | \n",
- " \n",
- " Spilled bytes: 0 B\n",
- " | \n",
- " \n",
- " \n",
- " | \n",
- " Read bytes: 611.8039865679604 B\n",
- " | \n",
- " \n",
- " Write bytes: 3.26 kiB\n",
- " | \n",
- " \n",
- " \n",
"\n",
" \n",
" \n",
@@ -1315,30 +1105,31 @@
" "
],
"text/plain": [
- " "
+ ""
]
},
- "execution_count": 10,
+ "execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
+ "client = Client(cluster)\n",
"client"
]
},
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "'a5edf7b5-fd91-4f6a-abf5-160d4cf9'"
+ "'1a90f19e-b224-4cad-ab48-94ea8cad'"
]
},
- "execution_count": 11,
+ "execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -1349,7 +1140,7 @@
},
{
"cell_type": "code",
- "execution_count": 17,
+ "execution_count": 10,
"metadata": {
"scrolled": true
},
@@ -1357,16 +1148,44 @@
{
"data": {
"text/plain": [
- "'6824de00-5107-4513-8b9c-bcc0d191'"
+ "'1fd09c90-c798-44f8-8a47-a2641d0a'"
]
},
- "execution_count": 17,
+ "execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "client.cluster.workers[1].admin_password"
+ "client.cluster.workers[0].admin_password"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Uncomment if you only have the scheduler with n_workers=0 and want to scale the workers separately.\n",
+ "# %%time\n",
+ "# client.cluster.scale(n_workers)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Wait till all the workers are up. This will wait for `n_workers` number of VMs to be up."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "%%time\n",
+ "client.wait_for_workers(2)"
]
},
{
@@ -1378,192 +1197,192 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "{'address': 'tls://10.5.0.26:8786',\n",
- " 'id': 'Scheduler-da7b39f6-8d7b-4580-9521-8667cea57940',\n",
+ "{'address': 'tls://10.5.0.29:8786',\n",
+ " 'id': 'Scheduler-9c563196-caf1-4498-aa20-4c4557aa1a47',\n",
" 'services': {'dashboard': 8787},\n",
- " 'started': 1695754666.812146,\n",
+ " 'started': 1695797770.0297768,\n",
" 'type': 'Scheduler',\n",
- " 'workers': {'tls://10.5.0.27:33135': {'gpu': {'memory-total': 17179869184,\n",
+ " 'workers': {'tls://10.5.0.30:35833': {'gpu': {'memory-total': 17179869184,\n",
" 'name': 'Tesla V100-PCIE-16GB'},\n",
- " 'host': '10.5.0.27',\n",
- " 'id': 'dask-cd718e4c-worker-7b9b2ff2-0',\n",
- " 'last_seen': 1695755308.5944703,\n",
- " 'local_directory': '/tmp/dask-scratch-space/worker-rkwt_wd2',\n",
+ " 'host': '10.5.0.30',\n",
+ " 'id': 'dask-e1db89fb-worker-396d96a3-0',\n",
+ " 'last_seen': 1695798249.4152472,\n",
+ " 'local_directory': '/tmp/dask-scratch-space/worker-jk35m4vu',\n",
" 'memory_limit': 118225672192,\n",
" 'metrics': {'bandwidth': {'total': 100000000,\n",
" 'types': {},\n",
" 'workers': {}},\n",
- " 'cpu': 2.0,\n",
- " 'digests_total_since_heartbeat': {'latency': 0.004858493804931641,\n",
- " 'tick-duration': 0.500096321105957},\n",
- " 'event_loop_interval': 0.020026397705078126,\n",
+ " 'cpu': 4.0,\n",
+ " 'digests_total_since_heartbeat': {'latency': 0.0039136409759521484,\n",
+ " 'tick-duration': 0.500333309173584},\n",
+ " 'event_loop_interval': 0.019992027282714844,\n",
" 'gpu': {'memory-used': 598867968,\n",
" 'utilization': 0},\n",
" 'gpu_memory_used': 598867968,\n",
" 'gpu_utilization': 0,\n",
" 'host_disk_io': {'read_bps': 0.0,\n",
- " 'write_bps': 16810337.47516862},\n",
- " 'host_net_io': {'read_bps': 613.2082065822599,\n",
- " 'write_bps': 3350.6017039396684},\n",
+ " 'write_bps': 0.0},\n",
+ " 'host_net_io': {'read_bps': 611.5512045867728,\n",
+ " 'write_bps': 3341.5477583956995},\n",
" 'managed_bytes': 0,\n",
- " 'memory': 625156096,\n",
+ " 'memory': 623390720,\n",
" 'num_fds': 86,\n",
" 'rmm': {'rmm-total': 0,\n",
" 'rmm-used': 0},\n",
" 'spilled_bytes': {'disk': 0,\n",
" 'memory': 0},\n",
" 'task_counts': {},\n",
- " 'time': 1695755308.0910525,\n",
+ " 'time': 1695798248.910828,\n",
" 'transfer': {'incoming_bytes': 0,\n",
" 'incoming_count': 0,\n",
" 'incoming_count_total': 0,\n",
" 'outgoing_bytes': 0,\n",
" 'outgoing_count': 0,\n",
" 'outgoing_count_total': 0}},\n",
- " 'name': 'dask-cd718e4c-worker-7b9b2ff2-0',\n",
- " 'nanny': 'tls://10.5.0.27:44451',\n",
+ " 'name': 'dask-e1db89fb-worker-396d96a3-0',\n",
+ " 'nanny': 'tls://10.5.0.30:37243',\n",
" 'nthreads': 1,\n",
" 'resources': {},\n",
- " 'services': {'dashboard': 36693},\n",
+ " 'services': {'dashboard': 43943},\n",
" 'status': 'running',\n",
" 'type': 'Worker'},\n",
- " 'tls://10.5.0.27:36605': {'gpu': {'memory-total': 17179869184,\n",
+ " 'tls://10.5.0.30:39857': {'gpu': {'memory-total': 17179869184,\n",
" 'name': 'Tesla V100-PCIE-16GB'},\n",
- " 'host': '10.5.0.27',\n",
- " 'id': 'dask-cd718e4c-worker-7b9b2ff2-1',\n",
- " 'last_seen': 1695755309.0630434,\n",
- " 'local_directory': '/tmp/dask-scratch-space/worker-iclmame3',\n",
+ " 'host': '10.5.0.30',\n",
+ " 'id': 'dask-e1db89fb-worker-396d96a3-1',\n",
+ " 'last_seen': 1695798249.4130971,\n",
+ " 'local_directory': '/tmp/dask-scratch-space/worker-gog2yjq8',\n",
" 'memory_limit': 118225672192,\n",
" 'metrics': {'bandwidth': {'total': 100000000,\n",
" 'types': {},\n",
" 'workers': {}},\n",
" 'cpu': 2.0,\n",
- " 'digests_total_since_heartbeat': {'latency': 0.0047109127044677734,\n",
- " 'tick-duration': 0.49942922592163086},\n",
- " 'event_loop_interval': 0.020009045600891114,\n",
+ " 'digests_total_since_heartbeat': {'latency': 0.004378795623779297,\n",
+ " 'tick-duration': 0.49997711181640625},\n",
+ " 'event_loop_interval': 0.019992733001708986,\n",
" 'gpu': {'memory-used': 598867968,\n",
" 'utilization': 0},\n",
" 'gpu_memory_used': 598867968,\n",
" 'gpu_utilization': 0,\n",
" 'host_disk_io': {'read_bps': 0.0,\n",
- " 'write_bps': 16774763.127036663},\n",
- " 'host_net_io': {'read_bps': 611.9105239955448,\n",
- " 'write_bps': 3343.5110984331727},\n",
+ " 'write_bps': 0.0},\n",
+ " 'host_net_io': {'read_bps': 612.2709225359564,\n",
+ " 'write_bps': 3345.48033490235},\n",
" 'managed_bytes': 0,\n",
- " 'memory': 621473792,\n",
+ " 'memory': 617656320,\n",
" 'num_fds': 86,\n",
" 'rmm': {'rmm-total': 0,\n",
" 'rmm-used': 0},\n",
" 'spilled_bytes': {'disk': 0,\n",
" 'memory': 0},\n",
" 'task_counts': {},\n",
- " 'time': 1695755308.5604067,\n",
+ " 'time': 1695798248.909559,\n",
" 'transfer': {'incoming_bytes': 0,\n",
" 'incoming_count': 0,\n",
" 'incoming_count_total': 0,\n",
" 'outgoing_bytes': 0,\n",
" 'outgoing_count': 0,\n",
" 'outgoing_count_total': 0}},\n",
- " 'name': 'dask-cd718e4c-worker-7b9b2ff2-1',\n",
- " 'nanny': 'tls://10.5.0.27:35583',\n",
+ " 'name': 'dask-e1db89fb-worker-396d96a3-1',\n",
+ " 'nanny': 'tls://10.5.0.30:33125',\n",
" 'nthreads': 1,\n",
" 'resources': {},\n",
- " 'services': {'dashboard': 41189},\n",
+ " 'services': {'dashboard': 39981},\n",
" 'status': 'running',\n",
" 'type': 'Worker'},\n",
- " 'tls://10.5.0.28:37831': {'gpu': {'memory-total': 17179869184,\n",
+ " 'tls://10.5.0.31:40645': {'gpu': {'memory-total': 17179869184,\n",
" 'name': 'Tesla V100-PCIE-16GB'},\n",
- " 'host': '10.5.0.28',\n",
- " 'id': 'dask-cd718e4c-worker-3cf05f03-0',\n",
- " 'last_seen': 1695755308.6291673,\n",
- " 'local_directory': '/tmp/dask-scratch-space/worker-laurl35q',\n",
- " 'memory_limit': 118225670144,\n",
+ " 'host': '10.5.0.31',\n",
+ " 'id': 'dask-e1db89fb-worker-f3e80672-0',\n",
+ " 'last_seen': 1695798249.7065253,\n",
+ " 'local_directory': '/tmp/dask-scratch-space/worker-jqle2l9n',\n",
+ " 'memory_limit': 118225672192,\n",
" 'metrics': {'bandwidth': {'total': 100000000,\n",
" 'types': {},\n",
" 'workers': {}},\n",
- " 'cpu': 2.0,\n",
- " 'digests_total_since_heartbeat': {'latency': 0.004083871841430664,\n",
- " 'tick-duration': 0.5008234977722168},\n",
- " 'event_loop_interval': 0.020003509521484376,\n",
+ " 'cpu': 4.0,\n",
+ " 'digests_total_since_heartbeat': {'latency': 0.0037021636962890625,\n",
+ " 'tick-duration': 0.4992666244506836},\n",
+ " 'event_loop_interval': 0.020013856887817382,\n",
" 'gpu': {'memory-used': 598867968,\n",
" 'utilization': 0},\n",
" 'gpu_memory_used': 598867968,\n",
" 'gpu_utilization': 0,\n",
" 'host_disk_io': {'read_bps': 0.0,\n",
- " 'write_bps': 8384838.092946665},\n",
- " 'host_net_io': {'read_bps': 611.7249623398017,\n",
- " 'write_bps': 3342.4971798436222},\n",
+ " 'write_bps': 29385631.375439122},\n",
+ " 'host_net_io': {'read_bps': 7885.455761722707,\n",
+ " 'write_bps': 13551.31655225871},\n",
" 'managed_bytes': 0,\n",
- " 'memory': 619945984,\n",
+ " 'memory': 621834240,\n",
" 'num_fds': 86,\n",
" 'rmm': {'rmm-total': 0,\n",
" 'rmm-used': 0},\n",
" 'spilled_bytes': {'disk': 0,\n",
" 'memory': 0},\n",
" 'task_counts': {},\n",
- " 'time': 1695755308.1364117,\n",
+ " 'time': 1695798249.1979365,\n",
" 'transfer': {'incoming_bytes': 0,\n",
" 'incoming_count': 0,\n",
" 'incoming_count_total': 0,\n",
" 'outgoing_bytes': 0,\n",
" 'outgoing_count': 0,\n",
" 'outgoing_count_total': 0}},\n",
- " 'name': 'dask-cd718e4c-worker-3cf05f03-0',\n",
- " 'nanny': 'tls://10.5.0.28:43437',\n",
+ " 'name': 'dask-e1db89fb-worker-f3e80672-0',\n",
+ " 'nanny': 'tls://10.5.0.31:35155',\n",
" 'nthreads': 1,\n",
" 'resources': {},\n",
- " 'services': {'dashboard': 44385},\n",
+ " 'services': {'dashboard': 38957},\n",
" 'status': 'running',\n",
" 'type': 'Worker'},\n",
- " 'tls://10.5.0.28:46499': {'gpu': {'memory-total': 17179869184,\n",
+ " 'tls://10.5.0.31:42211': {'gpu': {'memory-total': 17179869184,\n",
" 'name': 'Tesla V100-PCIE-16GB'},\n",
- " 'host': '10.5.0.28',\n",
- " 'id': 'dask-cd718e4c-worker-3cf05f03-1',\n",
- " 'last_seen': 1695755308.6400685,\n",
- " 'local_directory': '/tmp/dask-scratch-space/worker-rz4dg7ou',\n",
- " 'memory_limit': 118225670144,\n",
+ " 'host': '10.5.0.31',\n",
+ " 'id': 'dask-e1db89fb-worker-f3e80672-1',\n",
+ " 'last_seen': 1695798249.5185316,\n",
+ " 'local_directory': '/tmp/dask-scratch-space/worker-vwjtj063',\n",
+ " 'memory_limit': 118225672192,\n",
" 'metrics': {'bandwidth': {'total': 100000000,\n",
" 'types': {},\n",
" 'workers': {}},\n",
" 'cpu': 2.0,\n",
- " 'digests_total_since_heartbeat': {'latency': 0.0037758350372314453,\n",
- " 'tick-duration': 0.5004556179046631},\n",
- " 'event_loop_interval': 0.020004029273986815,\n",
+ " 'digests_total_since_heartbeat': {'latency': 0.0039021968841552734,\n",
+ " 'tick-duration': 0.4993259906768799},\n",
+ " 'event_loop_interval': 0.019996361732482912,\n",
" 'gpu': {'memory-used': 598867968,\n",
" 'utilization': 0},\n",
" 'gpu_memory_used': 598867968,\n",
" 'gpu_utilization': 0,\n",
" 'host_disk_io': {'read_bps': 0.0,\n",
- " 'write_bps': 8396786.04977224},\n",
- " 'host_net_io': {'read_bps': 612.596638495995,\n",
- " 'write_bps': 3347.2600639389007},\n",
+ " 'write_bps': 33689279.12993749},\n",
+ " 'host_net_io': {'read_bps': 7912.202242801052,\n",
+ " 'write_bps': 13597.280925492661},\n",
" 'managed_bytes': 0,\n",
- " 'memory': 619941888,\n",
+ " 'memory': 625152000,\n",
" 'num_fds': 86,\n",
" 'rmm': {'rmm-total': 0,\n",
" 'rmm-used': 0},\n",
" 'spilled_bytes': {'disk': 0,\n",
" 'memory': 0},\n",
" 'task_counts': {},\n",
- " 'time': 1695755308.1476307,\n",
+ " 'time': 1695798249.0098388,\n",
" 'transfer': {'incoming_bytes': 0,\n",
" 'incoming_count': 0,\n",
" 'incoming_count_total': 0,\n",
" 'outgoing_bytes': 0,\n",
" 'outgoing_count': 0,\n",
" 'outgoing_count_total': 0}},\n",
- " 'name': 'dask-cd718e4c-worker-3cf05f03-1',\n",
- " 'nanny': 'tls://10.5.0.28:42893',\n",
+ " 'name': 'dask-e1db89fb-worker-f3e80672-1',\n",
+ " 'nanny': 'tls://10.5.0.31:42491',\n",
" 'nthreads': 1,\n",
" 'resources': {},\n",
- " 'services': {'dashboard': 36329},\n",
+ " 'services': {'dashboard': 41035},\n",
" 'status': 'running',\n",
" 'type': 'Worker'}}}\n"
]
@@ -1606,19 +1425,19 @@
},
{
"cell_type": "code",
- "execution_count": 14,
+ "execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "{'tls://10.5.0.27:33135': {'status': 'OK'},\n",
- " 'tls://10.5.0.27:36605': {'status': 'OK'},\n",
- " 'tls://10.5.0.28:37831': {'status': 'OK'},\n",
- " 'tls://10.5.0.28:46499': {'status': 'OK'}}"
+ "{'tls://10.5.0.30:35833': {'status': 'OK'},\n",
+ " 'tls://10.5.0.30:39857': {'status': 'OK'},\n",
+ " 'tls://10.5.0.31:40645': {'status': 'OK'},\n",
+ " 'tls://10.5.0.31:42211': {'status': 'OK'}}"
]
},
- "execution_count": 14,
+ "execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
@@ -1666,7 +1485,7 @@
},
{
"cell_type": "code",
- "execution_count": 27,
+ "execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
@@ -1768,24 +1587,8 @@
},
{
"cell_type": "code",
- "execution_count": 28,
- "metadata": {
- "editable": true,
- "slideshow": {
- "slide_type": ""
- },
- "tags": [
- "library/cuml",
- "library/dask-cudf",
- "library/numpy",
- "library/dask",
- "tools/dask-cloudprovider",
- "cloud/azure/azure-vm",
- "dataset/nyc-taxi",
- "data-format/parquet",
- "data-storage/adls"
- ]
- },
+ "execution_count": 14,
+ "metadata": {},
"outputs": [],
"source": [
"def persist_train_infer_split(\n",
@@ -1933,7 +1736,7 @@
},
{
"cell_type": "code",
- "execution_count": 29,
+ "execution_count": 15,
"metadata": {},
"outputs": [
{
@@ -1948,7 +1751,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Wall clock time taken for ETL and persisting : 75.51355690800119 s\n"
+ "Wall clock time taken for ETL and persisting : 76.94258410600014 s\n"
]
}
],
@@ -1967,7 +1770,7 @@
},
{
"cell_type": "code",
- "execution_count": 30,
+ "execution_count": 17,
"metadata": {},
"outputs": [
{
@@ -1976,7 +1779,7 @@
"48817562"
]
},
- "execution_count": 30,
+ "execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
@@ -1994,7 +1797,7 @@
},
{
"cell_type": "code",
- "execution_count": 31,
+ "execution_count": 18,
"metadata": {},
"outputs": [
{
@@ -2135,7 +1938,7 @@
"294464 0.0 "
]
},
- "execution_count": 31,
+ "execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
@@ -2168,7 +1971,7 @@
},
{
"cell_type": "code",
- "execution_count": 32,
+ "execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
@@ -2208,14 +2011,14 @@
},
{
"cell_type": "code",
- "execution_count": 35,
+ "execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Wall clock time taken for this cell : 8.79627256601816 s\n"
+ "Wall clock time taken for this cell : 8.763767230033409 s\n"
]
}
],
@@ -2230,26 +2033,6 @@
"print(f\"Wall clock time taken for this cell : {toc-tic} s\")"
]
},
- {
- "cell_type": "code",
- "execution_count": 36,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- ""
- ]
- },
- "execution_count": 36,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "xgb_gpu_model"
- ]
- },
{
"cell_type": "markdown",
"metadata": {},
@@ -2259,7 +2042,7 @@
},
{
"cell_type": "code",
- "execution_count": 37,
+ "execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
@@ -2291,7 +2074,7 @@
},
{
"cell_type": "code",
- "execution_count": 38,
+ "execution_count": 22,
"metadata": {},
"outputs": [
{
@@ -2300,7 +2083,7 @@
"DoneAndNotDoneFutures(done=set(), not_done=set())"
]
},
- "execution_count": 38,
+ "execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
@@ -2312,45 +2095,14 @@
},
{
"cell_type": "code",
- "execution_count": 39,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "120249 12.0\n",
- "157207 5.0\n",
- "230041 10.5\n",
- "403916 8.5\n",
- "153919 11.5\n",
- " ... \n",
- "52284 7.0\n",
- "488390 5.0\n",
- "320576 19.0\n",
- "270255 15.0\n",
- "587681 6.5\n",
- "Name: fareAmount, Length: 5426301, dtype: float32"
- ]
- },
- "execution_count": 39,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "_y_test"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 40,
+ "execution_count": 23,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Wall clock time taken for xgb.dask.predict : 1.701935115037486 s\n"
+ "Wall clock time taken for xgb.dask.predict : 1.5908975210040808 s\n"
]
}
],
@@ -2379,14 +2131,14 @@
},
{
"cell_type": "code",
- "execution_count": 41,
+ "execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Wall clock time taken for inplace inference : 2.482840881042648 s\n"
+ "Wall clock time taken for inplace inference : 2.646754012966994 s\n"
]
}
],
@@ -2401,7 +2153,7 @@
},
{
"cell_type": "code",
- "execution_count": 42,
+ "execution_count": 25,
"metadata": {
"editable": true,
"slideshow": {
@@ -2415,8 +2167,8 @@
"output_type": "stream",
"text": [
"Calculating MSE\n",
- "Workflow Complete - RMSE: 2.2928023\n",
- "Wall clock time taken for this cell : 0.02508155204122886 s\n"
+ "Workflow Complete - RMSE: 2.2904203\n",
+ "Wall clock time taken for this cell : 0.014574272034224123 s\n"
]
}
],
@@ -2445,7 +2197,7 @@
},
{
"cell_type": "code",
- "execution_count": 43,
+ "execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
@@ -2466,46 +2218,45 @@
},
{
"cell_type": "code",
- "execution_count": 45,
+ "execution_count": 27,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "dict_keys(['tls://10.5.0.27:33135', 'tls://10.5.0.27:36605', 'tls://10.5.0.28:37831', 'tls://10.5.0.28:46499'])\n"
+ "dict_keys(['tls://10.5.0.30:35833', 'tls://10.5.0.30:39857', 'tls://10.5.0.31:40645', 'tls://10.5.0.31:42211'])\n"
]
}
],
"source": [
"workers = client.has_what().keys()\n",
"print(workers)\n",
- "\n",
"n_workers = len(workers)\n",
"n_partitions = n_workers"
]
},
{
"cell_type": "code",
- "execution_count": 107,
+ "execution_count": 30,
"metadata": {},
"outputs": [],
"source": [
- "def checkOrMakeLocalDir():\n",
+ "def unzipFile(zipname):\n",
" worker = get_worker()\n",
+ " import zipfile\n",
" import os\n",
"\n",
- " if not os.path.exists(worker.local_directory):\n",
- " os.makedirs(worker.local_directory)\n",
+ " with zipfile.ZipFile(os.path.join(worker.local_directory, zipname)) as zf:\n",
+ " zf.extractall(worker.local_directory)\n",
"\n",
"\n",
- "def unzipFile(zipname):\n",
+ "def checkOrMakeLocalDir():\n",
" worker = get_worker()\n",
- " import zipfile\n",
" import os\n",
"\n",
- " with zipfile.ZipFile(os.path.join(worker.local_directory, zipname)) as zf:\n",
- " zf.extractall(worker.local_directory)\n",
+ " if not os.path.exists(worker.local_directory):\n",
+ " os.makedirs(worker.local_directory)\n",
"\n",
"\n",
"def workerModelInit(model_file):\n",
@@ -2513,8 +2264,9 @@
" import os\n",
"\n",
" worker = get_worker()\n",
- " filename = os.path.join(worker.local_directory, model_file)\n",
- " worker.data[\"fil_model\"] = ForestInference.load(filename, model_type=\"xgboost\")\n",
+ " worker.data[\"fil_model\"] = ForestInference.load(\n",
+ " filename=os.path.join(worker.local_directory, model_file), model_type=\"xgboost\"\n",
+ " )\n",
"\n",
"\n",
"def predict(input_df):\n",
@@ -2529,20 +2281,16 @@
" zf = zipfile.ZipFile(zip_file_name, mode=\"w\")\n",
" zf.write(f\"./{model_file_name}\")\n",
" zf.close()\n",
- "\n",
" # check to see if local directory present in workers\n",
" # if not present make it\n",
" fut = client.submit(checkOrMakeLocalDir)\n",
" wait(fut)\n",
- "\n",
" # upload the zip file in workers\n",
" fut = client.upload_file(f\"./{zip_file_name}\")\n",
" wait(fut)\n",
- "\n",
" # unzip file in the workers\n",
" fut = client.submit(unzipFile, zip_file_name)\n",
" wait(fut)\n",
- "\n",
" # load model using FIL in workers\n",
" fut = client.submit(workerModelInit, model_file_name)\n",
" wait(fut)"
@@ -2557,15 +2305,15 @@
},
{
"cell_type": "code",
- "execution_count": 108,
+ "execution_count": 31,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "CPU times: user 39.4 ms, sys: 4.61 ms, total: 44.1 ms\n",
- "Wall time: 408 ms\n"
+ "CPU times: user 34 ms, sys: 24.9 ms, total: 58.9 ms\n",
+ "Wall time: 3.64 s\n"
]
}
],
@@ -2583,16 +2331,9 @@
},
{
"cell_type": "code",
- "execution_count": 110,
+ "execution_count": 32,
"metadata": {},
"outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Wall clock time taken for this cell: 0.18047992000356317 s\n"
- ]
- },
{
"name": "stderr",
"output_type": "stream",
@@ -2600,34 +2341,35 @@
"/home/skirui/anaconda3/envs/rapids-23.08/lib/python3.10/site-packages/dask/dataframe/core.py:7047: FutureWarning: Meta is not valid, `map_partitions` and `map_overlap` expects output to be a pandas object. Try passing a pandas object as meta or a dict or tuple representing the (name, dtype) of the columns. In the future the meta you passed will not work.\n",
" warnings.warn(\n"
]
+ },
+ {
+ "ename": "KeyError",
+ "evalue": "'fil_model'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[32], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m tic \u001b[38;5;241m=\u001b[39m timer()\n\u001b[1;32m 2\u001b[0m predictions \u001b[38;5;241m=\u001b[39m X_infer\u001b[38;5;241m.\u001b[39mmap_partitions(predict, meta\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfloat\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;66;03m# this is like MPI reduce\u001b[39;00m\n\u001b[0;32m----> 3\u001b[0m y_pred \u001b[38;5;241m=\u001b[39m \u001b[43mpredictions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcompute\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 4\u001b[0m wait(y_pred)\n\u001b[1;32m 5\u001b[0m toc \u001b[38;5;241m=\u001b[39m timer()\n",
+ "Cell \u001b[0;32mIn[30], line 23\u001b[0m, in \u001b[0;36mpredict\u001b[0;34m()\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpredict\u001b[39m(input_df):\n\u001b[1;32m 21\u001b[0m \u001b[38;5;66;03m# this function will run in each worker and predict \u001b[39;00m\n\u001b[1;32m 22\u001b[0m worker \u001b[38;5;241m=\u001b[39m get_worker()\n\u001b[0;32m---> 23\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m worker\u001b[38;5;241m.\u001b[39mdata[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfil_model\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39mpredict(input_df)\n",
+ "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/dask_cuda/device_host_file.py:269\u001b[0m, in \u001b[0;36m__getitem__\u001b[0;34m()\u001b[0m\n",
+ "\u001b[0;31mKeyError\u001b[0m: 'fil_model'"
+ ]
}
],
"source": [
- "# Submit the predict function to the Dask cluster\n",
- "predict_future = client.submit(predict, X_infer)\n",
- "\n",
- "# Map the predict_future to partitions of X_infer\n",
"tic = timer()\n",
- "predictions = X_infer.map_partitions(lambda df: predict_future, meta=\"float\")\n",
+ "predictions = X_infer.map_partitions(predict, meta=\"float\") # this is like MPI reduce\n",
"y_pred = predictions.compute()\n",
"wait(y_pred)\n",
"toc = timer()\n",
- "print(f\"Wall clock time taken for this cell: {toc - tic} s\")"
+ "print(f\"Wall clock time taken for this cell : {toc-tic} s\")"
]
},
{
"cell_type": "code",
- "execution_count": 111,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "It took 0.18047992000356317 seconds to predict on 5426301 rows using FIL distributedly on each worker\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"rows_csv = X_infer.iloc[:, 0].shape[0].compute()\n",
"print(\n",
@@ -2637,42 +2379,9 @@
},
{
"cell_type": "code",
- "execution_count": 112,
- "metadata": {
- "editable": true,
- "slideshow": {
- "slide_type": ""
- },
- "tags": []
- },
- "outputs": [
- {
- "ename": "ValueError",
- "evalue": "Unsupported dtype object",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn[112], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m tic \u001b[38;5;241m=\u001b[39m timer()\n\u001b[0;32m----> 2\u001b[0m score \u001b[38;5;241m=\u001b[39m \u001b[43mmean_squared_error\u001b[49m\u001b[43m(\u001b[49m\u001b[43my_pred\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m_y_test\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 3\u001b[0m toc \u001b[38;5;241m=\u001b[39m timer()\n\u001b[1;32m 4\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFinal - RMSE: \u001b[39m\u001b[38;5;124m\"\u001b[39m, np\u001b[38;5;241m.\u001b[39msqrt(score))\n",
- "File \u001b[0;32m~/anaconda3/envs/rapids-23.08/lib/python3.10/site-packages/cuml/internals/api_decorators.py:190\u001b[0m, in \u001b[0;36m_make_decorator_function..decorator_function..decorator_closure..wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 188\u001b[0m ret \u001b[38;5;241m=\u001b[39m func(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 189\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 190\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 192\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cm\u001b[38;5;241m.\u001b[39mprocess_return(ret)\n",
- "File \u001b[0;32mregression.pyx:200\u001b[0m, in \u001b[0;36mcuml.metrics.regression.mean_squared_error\u001b[0;34m()\u001b[0m\n",
- "File \u001b[0;32mregression.pyx:111\u001b[0m, in \u001b[0;36mcuml.metrics.regression._prepare_input_reg\u001b[0;34m()\u001b[0m\n",
- "File \u001b[0;32m~/anaconda3/envs/rapids-23.08/lib/python3.10/site-packages/nvtx/nvtx.py:101\u001b[0m, in \u001b[0;36mannotate.__call__..inner\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 98\u001b[0m \u001b[38;5;129m@wraps\u001b[39m(func)\n\u001b[1;32m 99\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minner\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 100\u001b[0m libnvtx_push_range(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mattributes, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdomain\u001b[38;5;241m.\u001b[39mhandle)\n\u001b[0;32m--> 101\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 102\u001b[0m libnvtx_pop_range(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdomain\u001b[38;5;241m.\u001b[39mhandle)\n\u001b[1;32m 103\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\n",
- "File \u001b[0;32m~/anaconda3/envs/rapids-23.08/lib/python3.10/site-packages/cuml/internals/input_utils.py:369\u001b[0m, in \u001b[0;36minput_to_cuml_array\u001b[0;34m(X, order, deepcopy, check_dtype, convert_to_dtype, check_mem_type, convert_to_mem_type, safe_dtype_conversion, check_cols, check_rows, fail_on_order, force_contiguous)\u001b[0m\n\u001b[1;32m 281\u001b[0m \u001b[38;5;129m@nvtx_annotate\u001b[39m(\n\u001b[1;32m 282\u001b[0m message\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcommon.input_utils.input_to_cuml_array\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 283\u001b[0m category\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mutils\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 298\u001b[0m force_contiguous\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 299\u001b[0m ):\n\u001b[1;32m 300\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 301\u001b[0m \u001b[38;5;124;03m Convert input X to CumlArray.\u001b[39;00m\n\u001b[1;32m 302\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 367\u001b[0m \n\u001b[1;32m 368\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 369\u001b[0m arr \u001b[38;5;241m=\u001b[39m \u001b[43mCumlArray\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_input\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 370\u001b[0m \u001b[43m \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 371\u001b[0m \u001b[43m \u001b[49m\u001b[43morder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43morder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 372\u001b[0m \u001b[43m \u001b[49m\u001b[43mdeepcopy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdeepcopy\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 373\u001b[0m \u001b[43m \u001b[49m\u001b[43mcheck_dtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcheck_dtype\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 374\u001b[0m \u001b[43m \u001b[49m\u001b[43mconvert_to_dtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconvert_to_dtype\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 375\u001b[0m \u001b[43m \u001b[49m\u001b[43mcheck_mem_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcheck_mem_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 376\u001b[0m \u001b[43m \u001b[49m\u001b[43mconvert_to_mem_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconvert_to_mem_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 377\u001b[0m \u001b[43m \u001b[49m\u001b[43msafe_dtype_conversion\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msafe_dtype_conversion\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 378\u001b[0m \u001b[43m \u001b[49m\u001b[43mcheck_cols\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcheck_cols\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 379\u001b[0m \u001b[43m \u001b[49m\u001b[43mcheck_rows\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcheck_rows\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 380\u001b[0m \u001b[43m \u001b[49m\u001b[43mfail_on_order\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfail_on_order\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 381\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_contiguous\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_contiguous\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 382\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 383\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 384\u001b[0m shape \u001b[38;5;241m=\u001b[39m arr\u001b[38;5;241m.\u001b[39m__cuda_array_interface__[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mshape\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n",
- "File \u001b[0;32m~/anaconda3/envs/rapids-23.08/lib/python3.10/site-packages/cuml/internals/memory_utils.py:87\u001b[0m, in \u001b[0;36mwith_cupy_rmm..cupy_rmm_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 85\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m GPU_ENABLED:\n\u001b[1;32m 86\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m cupy_using_allocator(rmm_cupy_allocator):\n\u001b[0;32m---> 87\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 88\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m func(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
- "File \u001b[0;32m~/anaconda3/envs/rapids-23.08/lib/python3.10/site-packages/nvtx/nvtx.py:101\u001b[0m, in \u001b[0;36mannotate.__call__..inner\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 98\u001b[0m \u001b[38;5;129m@wraps\u001b[39m(func)\n\u001b[1;32m 99\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minner\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 100\u001b[0m libnvtx_push_range(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mattributes, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdomain\u001b[38;5;241m.\u001b[39mhandle)\n\u001b[0;32m--> 101\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 102\u001b[0m libnvtx_pop_range(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdomain\u001b[38;5;241m.\u001b[39mhandle)\n\u001b[1;32m 103\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\n",
- "File \u001b[0;32m~/anaconda3/envs/rapids-23.08/lib/python3.10/site-packages/cuml/internals/array.py:1117\u001b[0m, in \u001b[0;36mCumlArray.from_input\u001b[0;34m(cls, X, order, deepcopy, check_dtype, convert_to_dtype, check_mem_type, convert_to_mem_type, safe_dtype_conversion, check_cols, check_rows, fail_on_order, force_contiguous)\u001b[0m\n\u001b[1;32m 1109\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[1;32m 1110\u001b[0m (X \u001b[38;5;241m<\u001b[39m target_dtype_range\u001b[38;5;241m.\u001b[39mmin) \u001b[38;5;241m|\u001b[39m (X \u001b[38;5;241m>\u001b[39m target_dtype_range\u001b[38;5;241m.\u001b[39mmax)\n\u001b[1;32m 1111\u001b[0m )\u001b[38;5;241m.\u001b[39many():\n\u001b[1;32m 1112\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\n\u001b[1;32m 1113\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mData type conversion on values outside\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1114\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m representable range of target dtype\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1115\u001b[0m )\n\u001b[1;32m 1116\u001b[0m arr \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mcls\u001b[39m(\n\u001b[0;32m-> 1117\u001b[0m \u001b[43marr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_output\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1118\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_dtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconvert_to_dtype\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1119\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_mem_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconvert_to_mem_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1120\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m 1121\u001b[0m order\u001b[38;5;241m=\u001b[39mrequested_order,\n\u001b[1;32m 1122\u001b[0m index\u001b[38;5;241m=\u001b[39mindex,\n\u001b[1;32m 1123\u001b[0m validate\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m 1124\u001b[0m )\n\u001b[1;32m 1126\u001b[0m make_copy \u001b[38;5;241m=\u001b[39m force_contiguous \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m arr\u001b[38;5;241m.\u001b[39mis_contiguous\n\u001b[1;32m 1128\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[1;32m 1129\u001b[0m \u001b[38;5;129;01mnot\u001b[39;00m fail_on_order \u001b[38;5;129;01mand\u001b[39;00m order \u001b[38;5;241m!=\u001b[39m arr\u001b[38;5;241m.\u001b[39morder \u001b[38;5;129;01mand\u001b[39;00m order \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mK\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1130\u001b[0m ) \u001b[38;5;129;01mor\u001b[39;00m make_copy:\n",
- "File \u001b[0;32m~/anaconda3/envs/rapids-23.08/lib/python3.10/site-packages/cuml/internals/memory_utils.py:87\u001b[0m, in \u001b[0;36mwith_cupy_rmm..cupy_rmm_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 85\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m GPU_ENABLED:\n\u001b[1;32m 86\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m cupy_using_allocator(rmm_cupy_allocator):\n\u001b[0;32m---> 87\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 88\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m func(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
- "File \u001b[0;32m~/anaconda3/envs/rapids-23.08/lib/python3.10/site-packages/nvtx/nvtx.py:101\u001b[0m, in \u001b[0;36mannotate.__call__..inner\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 98\u001b[0m \u001b[38;5;129m@wraps\u001b[39m(func)\n\u001b[1;32m 99\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minner\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 100\u001b[0m libnvtx_push_range(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mattributes, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdomain\u001b[38;5;241m.\u001b[39mhandle)\n\u001b[0;32m--> 101\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 102\u001b[0m libnvtx_pop_range(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdomain\u001b[38;5;241m.\u001b[39mhandle)\n\u001b[1;32m 103\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\n",
- "File \u001b[0;32m~/anaconda3/envs/rapids-23.08/lib/python3.10/site-packages/cuml/internals/array.py:625\u001b[0m, in \u001b[0;36mCumlArray.to_output\u001b[0;34m(self, output_type, output_dtype, output_mem_type)\u001b[0m\n\u001b[1;32m 618\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m np\u001b[38;5;241m.\u001b[39masarray(\n\u001b[1;32m 619\u001b[0m \u001b[38;5;28mself\u001b[39m, dtype\u001b[38;5;241m=\u001b[39moutput_dtype, order\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39morder\n\u001b[1;32m 620\u001b[0m )\n\u001b[1;32m 621\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cp\u001b[38;5;241m.\u001b[39masnumpy(\n\u001b[1;32m 622\u001b[0m cp\u001b[38;5;241m.\u001b[39masarray(\u001b[38;5;28mself\u001b[39m, dtype\u001b[38;5;241m=\u001b[39moutput_dtype, order\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39morder),\n\u001b[1;32m 623\u001b[0m order\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39morder,\n\u001b[1;32m 624\u001b[0m )\n\u001b[0;32m--> 625\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43moutput_mem_type\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mxpy\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43masarray\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 626\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_dtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43morder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43morder\u001b[49m\n\u001b[1;32m 627\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 629\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m output_type \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnumba\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 630\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cuda\u001b[38;5;241m.\u001b[39mas_cuda_array(\n\u001b[1;32m 631\u001b[0m cp\u001b[38;5;241m.\u001b[39masarray(\u001b[38;5;28mself\u001b[39m, dtype\u001b[38;5;241m=\u001b[39moutput_dtype, order\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39morder)\n\u001b[1;32m 632\u001b[0m )\n",
- "File \u001b[0;32m~/anaconda3/envs/rapids-23.08/lib/python3.10/site-packages/cupy/_creation/from_data.py:75\u001b[0m, in \u001b[0;36masarray\u001b[0;34m(a, dtype, order)\u001b[0m\n\u001b[1;32m 49\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21masarray\u001b[39m(a, dtype\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, order\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 50\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Converts an object to array.\u001b[39;00m\n\u001b[1;32m 51\u001b[0m \n\u001b[1;32m 52\u001b[0m \u001b[38;5;124;03m This is equivalent to ``array(a, dtype, copy=False, order=order)``.\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 73\u001b[0m \n\u001b[1;32m 74\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m---> 75\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_core\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marray\u001b[49m\u001b[43m(\u001b[49m\u001b[43ma\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43morder\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32mcupy/_core/core.pyx:2376\u001b[0m, in \u001b[0;36mcupy._core.core.array\u001b[0;34m()\u001b[0m\n",
- "File \u001b[0;32mcupy/_core/core.pyx:2400\u001b[0m, in \u001b[0;36mcupy._core.core.array\u001b[0;34m()\u001b[0m\n",
- "File \u001b[0;32mcupy/_core/core.pyx:2527\u001b[0m, in \u001b[0;36mcupy._core.core._array_default\u001b[0;34m()\u001b[0m\n",
- "\u001b[0;31mValueError\u001b[0m: Unsupported dtype object"
- ]
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"tic = timer()\n",
"score = mean_squared_error(y_pred, _y_test)\n",
@@ -2680,61 +2389,9 @@
"print(\"Final - RMSE: \", np.sqrt(score))"
]
},
- {
- "cell_type": "code",
- "execution_count": 87,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "(dtype('O'), dtype('float32'))"
- ]
- },
- "execution_count": 87,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "y_pred.dtype, _y_test.dtype"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 88,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 | |