Arlind Kadra: Merge pull request #173 from ravinkohli/fix-fit_pipeline

Author: Github Actions

refactor_development_regularization_cocktails/_downloads/0b35eb5fea161bb1ba2c30e6b7323b44/example_single_configuration.ipynb

@@ -0,0 +1,54 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "%matplotlib inline"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "\n# Fit a single configuration\n*Auto-PyTorch* searches for the best combination of machine learning algorithms\nand their hyper-parameter configuration for a given task.\n\nThis example shows how one can fit one of these pipelines, both, with a user defined\nconfiguration, and a randomly sampled one form the configuration space.\nThe pipelines that Auto-PyTorch fits are compatible with Scikit-Learn API. You can\nget further documentation about Scikit-Learn models here: <https://scikit-learn.org/stable/getting_started.html`>_\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "import os\nimport tempfile as tmp\nimport warnings\n\nos.environ['JOBLIB_TEMP_FOLDER'] = tmp.gettempdir()\nos.environ['OMP_NUM_THREADS'] = '1'\nos.environ['OPENBLAS_NUM_THREADS'] = '1'\nos.environ['MKL_NUM_THREADS'] = '1'\n\nwarnings.simplefilter(action='ignore', category=UserWarning)\nwarnings.simplefilter(action='ignore', category=FutureWarning)\n\nimport sklearn.datasets\nimport sklearn.metrics\n\nfrom autoPyTorch.api.tabular_classification import TabularClassificationTask\nfrom autoPyTorch.datasets.resampling_strategy import HoldoutValTypes\n\n\nif __name__ == '__main__':\n    ############################################################################\n    # Data Loading\n    # ============\n\n    X, y = sklearn.datasets.fetch_openml(data_id=3, return_X_y=True, as_frame=True)\n    X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(\n        X, y, test_size=0.5, random_state=3\n    )\n\n    ############################################################################\n    # Define an estimator\n    # ============================\n\n    # Search for a good configuration\n    estimator = TabularClassificationTask(\n        resampling_strategy=HoldoutValTypes.holdout_validation,\n        resampling_strategy_args={'val_share': 0.33}\n    )\n\n    ############################################################################\n    # Get a random configuration of the pipeline for current dataset\n    # ===============================================================\n\n    dataset = estimator.get_dataset(X_train=X_train,\n                                    y_train=y_train,\n                                    X_test=X_test,\n                                    y_test=y_test)\n    configuration = estimator.get_search_space(dataset).get_default_configuration()\n\n    ###########################################################################\n    # Fit the configuration\n    # ==================================\n\n    pipeline, run_info, run_value, dataset = estimator.fit_pipeline(X_train=X_train, y_train=y_train,\n                                                                    dataset_name='kr-vs-kp',\n                                                                    X_test=X_test, y_test=y_test,\n                                                                    disable_file_output=False,\n                                                                    configuration=configuration\n                                                                    )\n\n    # This object complies with Scikit-Learn Pipeline API.\n    # https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html\n    print(pipeline.named_steps)\n\n    # The fit_pipeline command also returns a named tuple with the pipeline constraints\n    print(run_info)\n\n    # The fit_pipeline command also returns a named tuple with train/test performance\n    print(run_value)\n\n    print(\"Passed Configuration:\", pipeline.config)\n    print(\"Network:\", pipeline.named_steps['network'].network)"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "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": "3.8.9"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

refactor_development_regularization_cocktails/_downloads/2f0f54a9831653ac5c12ee0e06324a62/basics_tabular_jupyter.zip

@@ -0,0 +1,85 @@
+# -*- encoding: utf-8 -*-
+"""
+==========================
+Fit a single configuration
+==========================
+*Auto-PyTorch* searches for the best combination of machine learning algorithms
+and their hyper-parameter configuration for a given task.
+
+This example shows how one can fit one of these pipelines, both, with a user defined
+configuration, and a randomly sampled one form the configuration space.
+The pipelines that Auto-PyTorch fits are compatible with Scikit-Learn API. You can
+get further documentation about Scikit-Learn models here: <https://scikit-learn.org/stable/getting_started.html`>_
+"""
+import os
+import tempfile as tmp
+import warnings
+
+os.environ['JOBLIB_TEMP_FOLDER'] = tmp.gettempdir()
+os.environ['OMP_NUM_THREADS'] = '1'
+os.environ['OPENBLAS_NUM_THREADS'] = '1'
+os.environ['MKL_NUM_THREADS'] = '1'
+
+warnings.simplefilter(action='ignore', category=UserWarning)
+warnings.simplefilter(action='ignore', category=FutureWarning)
+
+import sklearn.datasets
+import sklearn.metrics
+
+from autoPyTorch.api.tabular_classification import TabularClassificationTask
+from autoPyTorch.datasets.resampling_strategy import HoldoutValTypes
+
+
+if __name__ == '__main__':
+    ############################################################################
+    # Data Loading
+    # ============
+
+    X, y = sklearn.datasets.fetch_openml(data_id=3, return_X_y=True, as_frame=True)
+    X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(
+        X, y, test_size=0.5, random_state=3
+    )
+
+    ############################################################################
+    # Define an estimator
+    # ============================
+
+    # Search for a good configuration
+    estimator = TabularClassificationTask(
+        resampling_strategy=HoldoutValTypes.holdout_validation,
+        resampling_strategy_args={'val_share': 0.33}
+    )
+
+    ############################################################################
+    # Get a random configuration of the pipeline for current dataset
+    # ===============================================================
+
+    dataset = estimator.get_dataset(X_train=X_train,
+                                    y_train=y_train,
+                                    X_test=X_test,
+                                    y_test=y_test)
+    configuration = estimator.get_search_space(dataset).get_default_configuration()
+
+    ###########################################################################
+    # Fit the configuration
+    # ==================================
+
+    pipeline, run_info, run_value, dataset = estimator.fit_pipeline(X_train=X_train, y_train=y_train,
+                                                                    dataset_name='kr-vs-kp',
+                                                                    X_test=X_test, y_test=y_test,
+                                                                    disable_file_output=False,
+                                                                    configuration=configuration
+                                                                    )
+
+    # This object complies with Scikit-Learn Pipeline API.
+    # https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html
+    print(pipeline.named_steps)
+
+    # The fit_pipeline command also returns a named tuple with the pipeline constraints
+    print(run_info)
+
+    # The fit_pipeline command also returns a named tuple with train/test performance
+    print(run_value)
+
+    print("Passed Configuration:", pipeline.config)
+    print("Network:", pipeline.named_steps['network'].network)