|
|
{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Logistic regression with scikit-learn: heart disease data set" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Read data " ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/html": [ "<div>\n", "<style scoped>\n", " .dataframe tbody tr th:only-of-type {\n", " vertical-align: middle;\n", " }\n", "\n", " .dataframe tbody tr th {\n", " vertical-align: top;\n", " }\n", "\n", " .dataframe thead th {\n", " text-align: right;\n", " }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", " <thead>\n", " <tr style=\"text-align: right;\">\n", " <th></th>\n", " <th>age</th>\n", " <th>sex</th>\n", " <th>cp</th>\n", " <th>trestbps</th>\n", " <th>chol</th>\n", " <th>fbs</th>\n", " <th>restecg</th>\n", " <th>thalach</th>\n", " <th>exang</th>\n", " <th>oldpeak</th>\n", " <th>slope</th>\n", " <th>ca</th>\n", " <th>thal</th>\n", " <th>target</th>\n", " </tr>\n", " </thead>\n", " <tbody>\n", " <tr>\n", " <th>0</th>\n", " <td>63</td>\n", " <td>1</td>\n", " <td>3</td>\n", " <td>145</td>\n", " <td>233</td>\n", " <td>1</td>\n", " <td>0</td>\n", " <td>150</td>\n", " <td>0</td>\n", " <td>2.3</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>1</td>\n", " <td>1</td>\n", " </tr>\n", " <tr>\n", " <th>1</th>\n", " <td>37</td>\n", " <td>1</td>\n", " <td>2</td>\n", " <td>130</td>\n", " <td>250</td>\n", " <td>0</td>\n", " <td>1</td>\n", " <td>187</td>\n", " <td>0</td>\n", " <td>3.5</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>2</td>\n", " <td>1</td>\n", " </tr>\n", " <tr>\n", " <th>2</th>\n", " <td>41</td>\n", " <td>0</td>\n", " <td>1</td>\n", " <td>130</td>\n", " <td>204</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>172</td>\n", " <td>0</td>\n", " <td>1.4</td>\n", " <td>2</td>\n", " <td>0</td>\n", " <td>2</td>\n", " <td>1</td>\n", " </tr>\n", " <tr>\n", " <th>3</th>\n", " <td>56</td>\n", " <td>1</td>\n", " <td>1</td>\n", " <td>120</td>\n", " <td>236</td>\n", " <td>0</td>\n", " <td>1</td>\n", " <td>178</td>\n", " <td>0</td>\n", " <td>0.8</td>\n", " <td>2</td>\n", " <td>0</td>\n", " <td>2</td>\n", " <td>1</td>\n", " </tr>\n", " <tr>\n", " <th>4</th>\n", " <td>57</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>120</td>\n", " <td>354</td>\n", " <td>0</td>\n", " <td>1</td>\n", " <td>163</td>\n", " <td>1</td>\n", " <td>0.6</td>\n", " <td>2</td>\n", " <td>0</td>\n", " <td>2</td>\n", " <td>1</td>\n", " </tr>\n", " <tr>\n", " <th>...</th>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " <td>...</td>\n", " </tr>\n", " <tr>\n", " <th>298</th>\n", " <td>57</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>140</td>\n", " <td>241</td>\n", " <td>0</td>\n", " <td>1</td>\n", " <td>123</td>\n", " <td>1</td>\n", " <td>0.2</td>\n", " <td>1</td>\n", " <td>0</td>\n", " <td>3</td>\n", " <td>0</td>\n", " </tr>\n", " <tr>\n", " <th>299</th>\n", " <td>45</td>\n", " <td>1</td>\n", " <td>3</td>\n", " <td>110</td>\n", " <td>264</td>\n", " <td>0</td>\n", " <td>1</td>\n", " <td>132</td>\n", " <td>0</td>\n", " <td>1.2</td>\n", " <td>1</td>\n", " <td>0</td>\n", " <td>3</td>\n", " <td>0</td>\n", " </tr>\n", " <tr>\n", " <th>300</th>\n", " <td>68</td>\n", " <td>1</td>\n", " <td>0</td>\n", " <td>144</td>\n", " <td>193</td>\n", " <td>1</td>\n", " <td>1</td>\n", " <td>141</td>\n", " <td>0</td>\n", " <td>3.4</td>\n", " <td>1</td>\n", " <td>2</td>\n", " <td>3</td>\n", " <td>0</td>\n", " </tr>\n", " <tr>\n", " <th>301</th>\n", " <td>57</td>\n", " <td>1</td>\n", " <td>0</td>\n", " <td>130</td>\n", " <td>131</td>\n", " <td>0</td>\n", " <td>1</td>\n", " <td>115</td>\n", " <td>1</td>\n", " <td>1.2</td>\n", " <td>1</td>\n", " <td>1</td>\n", " <td>3</td>\n", " <td>0</td>\n", " </tr>\n", " <tr>\n", " <th>302</th>\n", " <td>57</td>\n", " <td>0</td>\n", " <td>1</td>\n", " <td>130</td>\n", " <td>236</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>174</td>\n", " <td>0</td>\n", " <td>0.0</td>\n", " <td>1</td>\n", " <td>1</td>\n", " <td>2</td>\n", " <td>0</td>\n", " </tr>\n", " </tbody>\n", "</table>\n", "<p>303 rows × 14 columns</p>\n", "</div>" ], "text/plain": [ " age sex cp trestbps chol fbs restecg thalach exang oldpeak \\\n", "0 63 1 3 145 233 1 0 150 0 2.3 \n", "1 37 1 2 130 250 0 1 187 0 3.5 \n", "2 41 0 1 130 204 0 0 172 0 1.4 \n", "3 56 1 1 120 236 0 1 178 0 0.8 \n", "4 57 0 0 120 354 0 1 163 1 0.6 \n", ".. ... ... .. ... ... ... ... ... ... ... \n", "298 57 0 0 140 241 0 1 123 1 0.2 \n", "299 45 1 3 110 264 0 1 132 0 1.2 \n", "300 68 1 0 144 193 1 1 141 0 3.4 \n", "301 57 1 0 130 131 0 1 115 1 1.2 \n", "302 57 0 1 130 236 0 0 174 0 0.0 \n", "\n", " slope ca thal target \n", "0 0 0 1 1 \n", "1 0 0 2 1 \n", "2 2 0 2 1 \n", "3 2 0 2 1 \n", "4 2 0 2 1 \n", ".. ... .. ... ... \n", "298 1 0 3 0 \n", "299 1 0 3 0 \n", "300 1 2 3 0 \n", "301 1 1 3 0 \n", "302 1 1 2 0 \n", "\n", "[303 rows x 14 columns]" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# filename = \"heart.csv\"\n", "filename = \"https://www.physi.uni-heidelberg.de/~reygers/lectures/2021/ml/data/heart.csv\"\n", "df = pd.read_csv(filename)\n", "df" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "y = df['target'].values\n", "X = df[[col for col in df.columns if col!=\"target\"]]" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import train_test_split\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, shuffle=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Fit the model" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/local/home/marks/anaconda3/envs/myML/lib/python3.8/site-packages/sklearn/linear_model/_logistic.py:1173: FutureWarning: `penalty='none'`has been deprecated in 1.2 and will be removed in 1.4. To keep the past behaviour, set `penalty=None`.\n", " warnings.warn(\n" ] }, { "data": { "text/html": [ "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\ ], "text/plain": [ "LogisticRegression(max_iter=5000, penalty='none', tol=1e-05)" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.linear_model import LogisticRegression\n", "lr = LogisticRegression(penalty='none', fit_intercept=True, max_iter=5000, tol=1E-5)\n", "lr.fit(X_train, y_train)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Test predictions on test data set" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " 0 0.82 0.76 0.79 76\n", " 1 0.78 0.83 0.80 76\n", "\n", " accuracy 0.80 152\n", " macro avg 0.80 0.80 0.80 152\n", "weighted avg 0.80 0.80 0.80 152\n", "\n" ] } ], "source": [ "from sklearn.metrics import classification_report\n", "y_pred_lr = lr.predict(X_test)\n", "print(classification_report(y_test, y_pred_lr))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Compare two classifiers using the ROC curve" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "from sklearn.ensemble import RandomForestClassifier\n", "rf = RandomForestClassifier(max_depth=3)\n", "rf.fit(X_train, y_train)\n", "y_pred_rf = rf.predict(X_test)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "image/png": "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 "text/plain": [ "<Figure size 640x480 with 1 Axes>" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from sklearn.metrics import roc_curve\n", "\n", "y_pred_prob_lr = lr.predict_proba(X_test) # predicted probabilities\n", "fpr_lr, tpr_lr, _ = roc_curve(y_test, y_pred_prob_lr[:,1])\n", "\n", "y_pred_prob_rf = rf.predict_proba(X_test) # predicted probabilities\n", "fpr_rf, tpr_rf, _ = roc_curve(y_test, y_pred_prob_rf[:,1])\n", "\n", "plt.plot(tpr_lr, 1-fpr_lr, label=\"log. regression\")\n", "plt.plot(tpr_rf, 1-fpr_rf, label=\"random forest\")\n", "\n", "plt.xlabel('Recall', fontsize=18)\n", "plt.ylabel('Precision', fontsize=18);\n", "plt.legend(fontsize=15)\n", "\n", "plt.savefig(\"03_ml_basics_log_regr_heart_disease.pdf\")" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Area under Curve (AUC) scores: 0.80, 0.80\n" ] } ], "source": [ "from sklearn.metrics import roc_auc_score\n", "auc_lr = roc_auc_score(y_test,y_pred_lr)\n", "auc_rf = roc_auc_score(y_test,y_pred_rf)\n", "print(f\"Area under Curve (AUC) scores: {auc_lr:.2f}, {auc_rf:.2f}\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "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": "3.8.16" } }, "nbformat": 4, "nbformat_minor": 4 }
|