From fb035e879079cc5a34a1ca55a50192ce7171273d Mon Sep 17 00:00:00 2001
From: buckl113 <39534448+buckl113@users.noreply.github.com>
Date: Fri, 4 Mar 2022 15:18:00 -0500
Subject: [PATCH] Added compatability with Google Colab
---
Auto-SKLearn_AutoML/Classification.ipynb | 219 +++++++++++++++++++++++
1 file changed, 219 insertions(+)
create mode 100644 Auto-SKLearn_AutoML/Classification.ipynb
diff --git a/Auto-SKLearn_AutoML/Classification.ipynb b/Auto-SKLearn_AutoML/Classification.ipynb
new file mode 100644
index 0000000..17ec558
--- /dev/null
+++ b/Auto-SKLearn_AutoML/Classification.ipynb
@@ -0,0 +1,219 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "name": "Classification.ipynb",
+ "provenance": []
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "source": [
+ "# Classification Using Auto-SKLearn"
+ ],
+ "metadata": {
+ "id": "-I9i52jCjML_"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "[](https://colab.research.google.com/github.com/mcint170/DataTools_Tutorial_Demo/blob/main/Auto-SKLearn_AutoML/Classification.ipynb)"
+ ],
+ "metadata": {
+ "id": "-ZrgwiL9kR_L"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!pip install auto-sklearn"
+ ],
+ "metadata": {
+ "id": "XAjlAHVRenet"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "After running this cell, Click Runtime -> Restart runtime. Then you can run the following cells."
+ ],
+ "metadata": {
+ "id": "yqIcMA8hgZ8W"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# imports\n",
+ "from pprint import pprint\n",
+ "\n",
+ "import sklearn.datasets\n",
+ "import sklearn.metrics\n",
+ "import pickle\n",
+ "\n",
+ "import autosklearn.classification"
+ ],
+ "metadata": {
+ "id": "BXuKNodQe7QZ"
+ },
+ "execution_count": 4,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# split the dataset\n",
+ "X, y = sklearn.datasets.load_breast_cancer(return_X_y=True)\n",
+ "X_train, X_test, y_train, y_test = \\\n",
+ " sklearn.model_selection.train_test_split(X, y, random_state=1)"
+ ],
+ "metadata": {
+ "id": "ExulDsEAfAoO"
+ },
+ "execution_count": 5,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Fit the classifier\n",
+ "automl = autosklearn.classification.AutoSklearnClassifier(\n",
+ " time_left_for_this_task=120,\n",
+ " per_run_time_limit=30,\n",
+ " tmp_folder='/tmp/autosklearn_classification_example_tmp',\n",
+ ")\n",
+ "automl.fit(X_train, y_train, dataset_name='breast_cancer')"
+ ],
+ "metadata": {
+ "id": "-0zi5I38fNMM",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "e732438b-610c-4d82-bd38-b1a5497541c6"
+ },
+ "execution_count": 6,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "AutoSklearnClassifier(per_run_time_limit=30, time_left_for_this_task=120,\n",
+ " tmp_folder='/tmp/autosklearn_classification_example_tmp')"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 6
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Different Models run by autosklearn\n",
+ "print(automl.leaderboard())"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "SxtOkluYiVHe",
+ "outputId": "29e44357-b2cb-404d-a024-cda5bd61b65a"
+ },
+ "execution_count": 7,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ " rank ensemble_weight type cost duration\n",
+ "model_id \n",
+ "7 1 0.10 extra_trees 0.014184 1.502508\n",
+ "2 2 0.02 random_forest 0.028369 2.024807\n",
+ "36 3 0.06 k_nearest_neighbors 0.028369 0.853534\n",
+ "26 4 0.04 extra_trees 0.028369 2.240347\n",
+ "19 5 0.02 extra_trees 0.028369 2.791073\n",
+ "22 6 0.02 gradient_boosting 0.028369 1.149980\n",
+ "3 7 0.14 mlp 0.028369 1.667622\n",
+ "12 8 0.04 gradient_boosting 0.035461 1.240657\n",
+ "17 9 0.02 gradient_boosting 0.035461 1.510491\n",
+ "8 10 0.02 random_forest 0.035461 1.958862\n",
+ "37 11 0.06 gradient_boosting 0.035461 1.585859\n",
+ "5 12 0.04 random_forest 0.035461 2.075770\n",
+ "27 13 0.10 extra_trees 0.042553 1.910083\n",
+ "34 14 0.08 random_forest 0.042553 1.884860\n",
+ "9 15 0.04 extra_trees 0.042553 1.799630\n",
+ "23 16 0.02 mlp 0.049645 2.405247\n",
+ "35 17 0.06 extra_trees 0.056738 1.586217\n",
+ "32 18 0.02 extra_trees 0.063830 1.650489\n",
+ "38 19 0.02 extra_trees 0.063830 2.128083\n",
+ "20 20 0.02 passive_aggressive 0.078014 0.774718\n",
+ "30 21 0.04 adaboost 0.078014 3.121010\n",
+ "29 22 0.02 gaussian_nb 0.141844 1.951357\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Show the different models\n",
+ "pprint(automl.show_models(), indent=4)"
+ ],
+ "metadata": {
+ "id": "25xOtCJ7icgh"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Predict the test labels\n",
+ "predictions = automl.predict(X_test)\n",
+ "print(\"Accuracy score:\", sklearn.metrics.accuracy_score(y_test, predictions))"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "XvbhWaZpidYt",
+ "outputId": "7a153d86-4d3b-474a-f867-8adf7e07318b"
+ },
+ "execution_count": 9,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Accuracy score: 0.9440559440559441\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Export the model with the highest rank\n",
+ "clf = automl.show_models()[7]['sklearn_classifier']\n",
+ "pickle.dump(clf,open('model.pickle','wb'))"
+ ],
+ "metadata": {
+ "id": "iCFcuh9EikR_"
+ },
+ "execution_count": 10,
+ "outputs": []
+ }
+ ]
+}
\ No newline at end of file
--
GitLab