{ "cells": [ { "cell_type": "markdown", "id": "c3192ac4", "metadata": {}, "source": [ "# Training a model with Sklearn\n", "In this example we will train a model in Ray AIR using a Sklearn classifier." ] }, { "cell_type": "markdown", "id": "5a4823bf", "metadata": {}, "source": [ "Let's start with installing our dependencies:" ] }, { "cell_type": "code", "execution_count": 1, "id": "88f4bb39", "metadata": { "pycharm": { "name": "#%%\n" } }, "outputs": [], "source": [ "!pip install -qU \"ray[tune]\" sklearn" ] }, { "cell_type": "markdown", "id": "c049c692", "metadata": {}, "source": [ "Then we need some imports:" ] }, { "cell_type": "code", "execution_count": 2, "id": "c02eb5cd", "metadata": {}, "outputs": [], "source": [ "import argparse\n", "import math\n", "from typing import Tuple\n", "\n", "import pandas as pd\n", "\n", "import ray\n", "from ray.data.dataset import Dataset\n", "from ray.train.batch_predictor import BatchPredictor\n", "from ray.train.sklearn import SklearnPredictor\n", "from ray.data.preprocessors import Chain, OrdinalEncoder, StandardScaler\n", "from ray.air.result import Result\n", "from ray.train.sklearn import SklearnTrainer\n", "\n", "\n", "from sklearn.datasets import load_breast_cancer\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.model_selection import train_test_split\n", "\n", "try:\n", " from cuml.ensemble import RandomForestClassifier as cuMLRandomForestClassifier\n", "except ImportError:\n", " cuMLRandomForestClassifier = None" ] }, { "cell_type": "markdown", "id": "52e017f1", "metadata": {}, "source": [ "Next we define a function to load our train, validation, and test datasets." ] }, { "cell_type": "code", "execution_count": 3, "id": "3631ed1e", "metadata": {}, "outputs": [], "source": [ "def prepare_data() -> Tuple[Dataset, Dataset, Dataset]:\n", " data_raw = load_breast_cancer()\n", " dataset_df = pd.DataFrame(data_raw[\"data\"], columns=data_raw[\"feature_names\"])\n", " dataset_df[\"target\"] = data_raw[\"target\"]\n", " # add a random categorical column\n", " num_samples = len(dataset_df)\n", " dataset_df[\"categorical_column\"] = pd.Series(\n", " ([\"A\", \"B\"] * math.ceil(num_samples / 2))[:num_samples]\n", " )\n", " train_df, test_df = train_test_split(dataset_df, test_size=0.3)\n", " train_dataset = ray.data.from_pandas(train_df)\n", " valid_dataset = ray.data.from_pandas(test_df)\n", " test_dataset = ray.data.from_pandas(test_df.drop(\"target\", axis=1))\n", " return train_dataset, valid_dataset, test_dataset" ] }, { "cell_type": "markdown", "id": "8d6c6d17", "metadata": {}, "source": [ "The following function will create a Sklearn trainer, train it, and return the result." ] }, { "cell_type": "code", "execution_count": 4, "id": "0fd39e42", "metadata": {}, "outputs": [], "source": [ "def train_sklearn(num_cpus: int, use_gpu: bool = False) -> Result:\n", " if use_gpu and not cuMLRandomForestClassifier:\n", " raise RuntimeError(\"cuML must be installed for GPU enabled sklearn estimators.\")\n", "\n", " train_dataset, valid_dataset, _ = prepare_data()\n", "\n", " # Scale some random columns\n", " columns_to_scale = [\"mean radius\", \"mean texture\"]\n", " preprocessor = Chain(\n", " OrdinalEncoder([\"categorical_column\"]), StandardScaler(columns=columns_to_scale)\n", " )\n", "\n", " if use_gpu:\n", " trainer_resources = {\"CPU\": 1, \"GPU\": 1}\n", " estimator = cuMLRandomForestClassifier()\n", " else:\n", " trainer_resources = {\"CPU\": num_cpus}\n", " estimator = RandomForestClassifier()\n", "\n", " trainer = SklearnTrainer(\n", " estimator=estimator,\n", " label_column=\"target\",\n", " datasets={\"train\": train_dataset, \"valid\": valid_dataset},\n", " preprocessor=preprocessor,\n", " cv=5,\n", " scaling_config={\n", " \"trainer_resources\": trainer_resources,\n", " },\n", " )\n", " result = trainer.fit()\n", " print(result.metrics)\n", "\n", " return result" ] }, { "cell_type": "markdown", "id": "7a2efb9d", "metadata": {}, "source": [ "Once we have the result, we can do batch inference on the obtained model. Let's define a utility function for this." ] }, { "cell_type": "code", "execution_count": 5, "id": "59eeadd8", "metadata": {}, "outputs": [], "source": [ "def predict_sklearn(result: Result, use_gpu: bool = False):\n", " _, _, test_dataset = prepare_data()\n", "\n", " batch_predictor = BatchPredictor.from_checkpoint(\n", " result.checkpoint, SklearnPredictor\n", " )\n", "\n", " predicted_labels = (\n", " batch_predictor.predict(\n", " test_dataset,\n", " num_gpus_per_worker=int(use_gpu),\n", " )\n", " .map_batches(lambda df: (df > 0.5).astype(int), batch_format=\"pandas\")\n", " .to_pandas(limit=float(\"inf\"))\n", " )\n", " print(f\"PREDICTED LABELS\\n{predicted_labels}\")" ] }, { "cell_type": "markdown", "id": "7d073994", "metadata": {}, "source": [ "Now we can run the training:" ] }, { "cell_type": "code", "execution_count": 6, "id": "43f9170a", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2022-05-19 11:56:26,664\tINFO services.py:1483 -- View the Ray dashboard at \u001B[1m\u001B[32mhttp://127.0.0.1:8266\u001B[39m\u001B[22m\n" ] }, { "data": { "text/html": [ "== Status ==
Current time: 2022-05-19 11:56:51 (running for 00:00:20.56)
Memory usage on this node: 10.1/16.0 GiB
Using FIFO scheduling algorithm.
Resources requested: 0/16 CPUs, 0/0 GPUs, 0.0/4.64 GiB heap, 0.0/2.0 GiB objects
Result logdir: /Users/kai/ray_results/SklearnTrainer_2022-05-19_11-56-29
Number of trials: 1/1 (1 TERMINATED)
\n", "\n", "\n", "\n", "\n", "\n", "\n", "
Trial name status loc iter total time (s) fit_time
SklearnTrainer_564d9_00000TERMINATED127.0.0.1:12221 1 17.1905 2.48662


" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stderr", "output_type": "stream", "text": [ "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:31,837\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=16 --runtime-env-hash=-2010331134\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:34,848\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=17 --runtime-env-hash=-2010331069\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m 2022-05-19 11:56:36,385\tWARNING pool.py:591 -- The 'context' argument is not supported using ray. Please refer to the documentation for how to control ray initialization.\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:37,344\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=19 --runtime-env-hash=-2010331134\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:37,344\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=18 --runtime-env-hash=-2010331134\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:39,843\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=21 --runtime-env-hash=-2010331134\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:39,845\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=20 --runtime-env-hash=-2010331134\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:42,324\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=23 --runtime-env-hash=-2010331134\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:42,324\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=22 --runtime-env-hash=-2010331134\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:44,748\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=24 --runtime-env-hash=-2010331134\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:44,749\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=25 --runtime-env-hash=-2010331134\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:47,193\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=27 --runtime-env-hash=-2010331134\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:47,193\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=26 --runtime-env-hash=-2010331134\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:49,612\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=28 --runtime-env-hash=-2010331134\n", "\u001B[2m\u001B[33m(raylet)\u001B[0m 2022-05-19 11:56:49,612\tINFO context.py:70 -- Exec'ing worker with command: exec /Users/kai/.pyenv/versions/3.7.7/bin/python3.7 /Users/kai/coding/ray/python/ray/workers/default_worker.py --node-ip-address=127.0.0.1 --node-manager-port=55845 --object-store-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/plasma_store --raylet-name=/tmp/ray/session_2022-05-19_11-56-23_998044_12148/sockets/raylet --redis-address=None --storage=None --temp-dir=/tmp/ray --metrics-agent-port=59341 --logging-rotate-bytes=536870912 --logging-rotate-backup-count=5 --gcs-address=127.0.0.1:58305 --redis-password=5241590000000000 --startup-token=29 --runtime-env-hash=-2010331134\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Result for SklearnTrainer_564d9_00000:\n", " cv:\n", " fit_time:\n", " - 2.402121067047119\n", " - 2.312839984893799\n", " - 2.3265390396118164\n", " - 2.325679063796997\n", " - 2.3602960109710693\n", " fit_time_mean: 2.34549503326416\n", " fit_time_std: 0.032384969255539235\n", " score_time:\n", " - 0.10820889472961426\n", " - 0.10829401016235352\n", " - 0.10703587532043457\n", " - 0.10512709617614746\n", " - 0.10840892791748047\n", " score_time_mean: 0.10741496086120605\n", " score_time_std: 0.0012465199424455708\n", " test_score:\n", " - 0.9625\n", " - 0.8875\n", " - 1.0\n", " - 0.9493670886075949\n", " - 0.9240506329113924\n", " test_score_mean: 0.9446835443037976\n", " test_score_std: 0.03766947497186954\n", " date: 2022-05-19_11-56-51\n", " done: false\n", " experiment_id: 200cbc1e2b84434882732d2053ec45c2\n", " fit_time: 2.4866180419921875\n", " hostname: Kais-MacBook-Pro.local\n", " iterations_since_restore: 1\n", " node_ip: 127.0.0.1\n", " pid: 12221\n", " should_checkpoint: true\n", " time_since_restore: 17.19045615196228\n", " time_this_iter_s: 17.19045615196228\n", " time_total_s: 17.19045615196228\n", " timestamp: 1652957811\n", " timesteps_since_restore: 0\n", " training_iteration: 1\n", " trial_id: 564d9_00000\n", " valid:\n", " score_time: 0.10993409156799316\n", " test_score: 0.9473684210526315\n", " warmup_time: 0.0039539337158203125\n", " \n", "Result for SklearnTrainer_564d9_00000:\n", " cv:\n", " fit_time:\n", " - 2.402121067047119\n", " - 2.312839984893799\n", " - 2.3265390396118164\n", " - 2.325679063796997\n", " - 2.3602960109710693\n", " fit_time_mean: 2.34549503326416\n", " fit_time_std: 0.032384969255539235\n", " score_time:\n", " - 0.10820889472961426\n", " - 0.10829401016235352\n", " - 0.10703587532043457\n", " - 0.10512709617614746\n", " - 0.10840892791748047\n", " score_time_mean: 0.10741496086120605\n", " score_time_std: 0.0012465199424455708\n", " test_score:\n", " - 0.9625\n", " - 0.8875\n", " - 1.0\n", " - 0.9493670886075949\n", " - 0.9240506329113924\n", " test_score_mean: 0.9446835443037976\n", " test_score_std: 0.03766947497186954\n", " date: 2022-05-19_11-56-51\n", " done: true\n", " experiment_id: 200cbc1e2b84434882732d2053ec45c2\n", " experiment_tag: '0'\n", " fit_time: 2.4866180419921875\n", " hostname: Kais-MacBook-Pro.local\n", " iterations_since_restore: 1\n", " node_ip: 127.0.0.1\n", " pid: 12221\n", " should_checkpoint: true\n", " time_since_restore: 17.19045615196228\n", " time_this_iter_s: 17.19045615196228\n", " time_total_s: 17.19045615196228\n", " timestamp: 1652957811\n", " timesteps_since_restore: 0\n", " training_iteration: 1\n", " trial_id: 564d9_00000\n", " valid:\n", " score_time: 0.10993409156799316\n", " test_score: 0.9473684210526315\n", " warmup_time: 0.0039539337158203125\n", " \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m /Users/kai/.pyenv/versions/3.7.7/lib/python3.7/site-packages/joblib/externals/loky/backend/resource_tracker.py:320: UserWarning: resource_tracker: There appear to be 6 leaked folder objects to clean up at shutdown\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m (len(rtype_registry), rtype))\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m /Users/kai/.pyenv/versions/3.7.7/lib/python3.7/site-packages/joblib/externals/loky/backend/resource_tracker.py:333: UserWarning: resource_tracker: /var/folders/b2/0_91bd757rz02lrmr920v0gw0000gn/T/joblib_memmapping_folder_12221_5f6216ae1e6a46ba9d419e794af5d6af_23c04cd6260143c0ac6f5dbe654ee805: FileNotFoundError(2, 'No such file or directory')\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m warnings.warn('resource_tracker: %s: %r' % (name, e))\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m /Users/kai/.pyenv/versions/3.7.7/lib/python3.7/site-packages/joblib/externals/loky/backend/resource_tracker.py:333: UserWarning: resource_tracker: /var/folders/b2/0_91bd757rz02lrmr920v0gw0000gn/T/joblib_memmapping_folder_12221_a9bc9a60f53a487e91b551aaace31955_1d562711c03e42ff9f97698134ab33f7: FileNotFoundError(2, 'No such file or directory')\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m warnings.warn('resource_tracker: %s: %r' % (name, e))\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m /Users/kai/.pyenv/versions/3.7.7/lib/python3.7/site-packages/joblib/externals/loky/backend/resource_tracker.py:333: UserWarning: resource_tracker: /var/folders/b2/0_91bd757rz02lrmr920v0gw0000gn/T/joblib_memmapping_folder_12221_4130f87b8a7a41d4bb44d3ff87c47d73_d3df48add59547d89737f42c03172fa5: FileNotFoundError(2, 'No such file or directory')\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m warnings.warn('resource_tracker: %s: %r' % (name, e))\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m /Users/kai/.pyenv/versions/3.7.7/lib/python3.7/site-packages/joblib/externals/loky/backend/resource_tracker.py:333: UserWarning: resource_tracker: /var/folders/b2/0_91bd757rz02lrmr920v0gw0000gn/T/joblib_memmapping_folder_12221_28d4366efda3422c93d8ad3a8d66986e_9d1ab8d6a92146829caf48550752190d: FileNotFoundError(2, 'No such file or directory')\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m warnings.warn('resource_tracker: %s: %r' % (name, e))\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m /Users/kai/.pyenv/versions/3.7.7/lib/python3.7/site-packages/joblib/externals/loky/backend/resource_tracker.py:333: UserWarning: resource_tracker: /var/folders/b2/0_91bd757rz02lrmr920v0gw0000gn/T/joblib_memmapping_folder_12221_4dc9b4c717294776b8162f30cc5eb4fe_068611691a404ca18d46ab1be089bc5a: FileNotFoundError(2, 'No such file or directory')\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m warnings.warn('resource_tracker: %s: %r' % (name, e))\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m /Users/kai/.pyenv/versions/3.7.7/lib/python3.7/site-packages/joblib/externals/loky/backend/resource_tracker.py:333: UserWarning: resource_tracker: /var/folders/b2/0_91bd757rz02lrmr920v0gw0000gn/T/joblib_memmapping_folder_12221_0b60850fd8704b0e83f6c2758d9c1f2a_6ae1cfa0a68741b8b71f28a262bd7f7a: FileNotFoundError(2, 'No such file or directory')\n", "\u001B[2m\u001B[36m(TrainTrainable pid=12221)\u001B[0m warnings.warn('resource_tracker: %s: %r' % (name, e))\n", "2022-05-19 11:56:51,305\tINFO tune.py:753 -- Total run time: 21.67 seconds (20.55 seconds for the tuning loop).\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'valid': {'score_time': 0.10993409156799316, 'test_score': 0.9473684210526315}, 'cv': {'fit_time': array([2.40212107, 2.31283998, 2.32653904, 2.32567906, 2.36029601]), 'score_time': array([0.10820889, 0.10829401, 0.10703588, 0.1051271 , 0.10840893]), 'test_score': array([0.9625 , 0.8875 , 1. , 0.94936709, 0.92405063]), 'fit_time_mean': 2.34549503326416, 'fit_time_std': 0.032384969255539235, 'score_time_mean': 0.10741496086120605, 'score_time_std': 0.0012465199424455708, 'test_score_mean': 0.9446835443037976, 'test_score_std': 0.03766947497186954}, 'fit_time': 2.4866180419921875, 'time_this_iter_s': 17.19045615196228, 'should_checkpoint': True, 'done': True, 'timesteps_total': None, 'episodes_total': None, 'training_iteration': 1, 'trial_id': '564d9_00000', 'experiment_id': '200cbc1e2b84434882732d2053ec45c2', 'date': '2022-05-19_11-56-51', 'timestamp': 1652957811, 'time_total_s': 17.19045615196228, 'pid': 12221, 'hostname': 'Kais-MacBook-Pro.local', 'node_ip': '127.0.0.1', 'config': {}, 'time_since_restore': 17.19045615196228, 'timesteps_since_restore': 0, 'iterations_since_restore': 1, 'warmup_time': 0.0039539337158203125, 'experiment_tag': '0'}\n" ] } ], "source": [ "result = train_sklearn(num_cpus=2, use_gpu=False)" ] }, { "cell_type": "markdown", "id": "0daba603", "metadata": {}, "source": [ "And perform inference on the obtained model:" ] }, { "cell_type": "code", "execution_count": 7, "id": "24b16ede", "metadata": { "pycharm": { "name": "#%%\n" } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Map Progress (1 actors 1 pending): 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:01<00:00, 1.59s/it]\n", "Map_Batches: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 95.33it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "PREDICTED LABELS\n", " predictions\n", "0 1\n", "1 1\n", "2 1\n", "3 1\n", "4 1\n", ".. ...\n", "166 1\n", "167 1\n", "168 0\n", "169 0\n", "170 1\n", "\n", "[171 rows x 1 columns]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n" ] } ], "source": [ "predict_sklearn(result, use_gpu=False)" ] } ], "metadata": { "jupytext": { "cell_metadata_filter": "-all", "main_language": "python", "notebook_metadata_filter": "-all" }, "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.7" } }, "nbformat": 4, "nbformat_minor": 5 }