{ "cells": [ { "cell_type": "code", "execution_count": 7, "id": "c886cb8a-f2fc-4d82-babf-ea06b1409986", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Dataset shape: (303, 14)\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agesexcptrestbpscholfbsrestecgthalachexangoldpeakslopecathaltarget
063131452331015002.30011
137121302500118703.50021
241011302040017201.42021
356111202360117800.82021
457001203540116310.62021
\n", "
" ], "text/plain": [ " age sex cp trestbps chol fbs restecg thalach exang oldpeak slope \\\n", "0 63 1 3 145 233 1 0 150 0 2.3 0 \n", "1 37 1 2 130 250 0 1 187 0 3.5 0 \n", "2 41 0 1 130 204 0 0 172 0 1.4 2 \n", "3 56 1 1 120 236 0 1 178 0 0.8 2 \n", "4 57 0 0 120 354 0 1 163 1 0.6 2 \n", "\n", " ca thal target \n", "0 0 1 1 \n", "1 0 2 1 \n", "2 0 2 1 \n", "3 0 2 1 \n", "4 0 2 1 " ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import pandas as pd\n", "df = pd.read_csv(\"heart.csv\")\n", "print(\"Dataset shape:\", df.shape)\n", "df.head()" ] }, { "cell_type": "code", "execution_count": 8, "id": "f14009ff-84e5-4e45-b510-ee346408f463", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "age 0\n", "sex 0\n", "cp 0\n", "trestbps 0\n", "chol 0\n", "fbs 0\n", "restecg 0\n", "thalach 0\n", "exang 0\n", "oldpeak 0\n", "slope 0\n", "ca 0\n", "thal 0\n", "target 0\n", "dtype: int64" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 9, "id": "5162ae0f-7a77-4abd-b44f-8f15fd1d9049", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Train: (242, 13)\n", "Test: (61, 13)\n" ] } ], "source": [ "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import StandardScaler\n", "X = df.drop(\"target\", axis=1)\n", "y = df[\"target\"]\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", "scaler = StandardScaler()\n", "X_train = scaler.fit_transform(X_train)\n", "X_test = scaler.transform(X_test)\n", "print(\"Train:\", X_train.shape)\n", "print(\"Test:\", X_test.shape)" ] }, { "cell_type": "code", "execution_count": 10, "id": "f57b9a9f-2f8d-4d85-a5e0-f075865c1057", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "=== Model Performance (Before Feature Selection) ===\n", "\n", "LogReg Best Params: {'C': 1}\n", "Accuracy: 0.8524590163934426\n", " precision recall f1-score support\n", "\n", " 0 0.83 0.86 0.85 29\n", " 1 0.87 0.84 0.86 32\n", "\n", " accuracy 0.85 61\n", " macro avg 0.85 0.85 0.85 61\n", "weighted avg 0.85 0.85 0.85 61\n", "\n", "\n", "RandomForest Best Params: {'max_depth': None, 'n_estimators': 50}\n", "Accuracy: 0.8360655737704918\n", " precision recall f1-score support\n", "\n", " 0 0.83 0.83 0.83 29\n", " 1 0.84 0.84 0.84 32\n", "\n", " accuracy 0.84 61\n", " macro avg 0.84 0.84 0.84 61\n", "weighted avg 0.84 0.84 0.84 61\n", "\n", "\n", "SVM Best Params: {'C': 1, 'kernel': 'rbf'}\n", "Accuracy: 0.8688524590163934\n", " precision recall f1-score support\n", "\n", " 0 0.84 0.90 0.87 29\n", " 1 0.90 0.84 0.87 32\n", "\n", " accuracy 0.87 61\n", " macro avg 0.87 0.87 0.87 61\n", "weighted avg 0.87 0.87 0.87 61\n", "\n" ] } ], "source": [ "from sklearn.linear_model import LogisticRegression\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.svm import SVC\n", "from sklearn.model_selection import GridSearchCV\n", "from sklearn.metrics import accuracy_score, classification_report\n", "models = {\n", " \"LogReg\": (LogisticRegression(max_iter=500), {\"C\":[0.1, 1, 10]}),\n", " \"RandomForest\": (RandomForestClassifier(), {\"n_estimators\":[50,100], \"max_depth\":[None,5,10]}),\n", " \"SVM\": (SVC(), {\"C\":[0.1,1,10], \"kernel\":[\"linear\",\"rbf\"]})\n", "}\n", "print(\"=== Model Performance (Before Feature Selection) ===\")\n", "for name, (model, params) in models.items():\n", " grid = GridSearchCV(model, params, cv=5, scoring=\"accuracy\")\n", " grid.fit(X_train, y_train)\n", " pred = grid.predict(X_test)\n", " print(f\"\\n{name} Best Params: {grid.best_params_}\")\n", " print(\"Accuracy:\", accuracy_score(y_test, pred))\n", " print(classification_report(y_test, pred))" ] }, { "cell_type": "code", "execution_count": 11, "id": "0f8cc49a-d0e6-45e8-a607-c8522a643766", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Chi2 selected features shape: (242, 5)\n", "RFE selected features shape: (242, 5)\n" ] } ], "source": [ "from sklearn.feature_selection import SelectKBest, chi2, RFE\n", "# Chi2 \n", "chi2_selector = SelectKBest(score_func=chi2, k=5)\n", "X_train_chi2 = chi2_selector.fit_transform(abs(X_train), y_train)\n", "X_test_chi2 = chi2_selector.transform(abs(X_test))\n", "print(\"Chi2 selected features shape:\", X_train_chi2.shape)\n", "# RFE ---\n", "rfe = RFE(LogisticRegression(max_iter=500), n_features_to_select=5)\n", "X_train_rfe = rfe.fit_transform(X_train, y_train)\n", "X_test_rfe = rfe.transform(X_test)\n", "print(\"RFE selected features shape:\", X_train_rfe.shape)" ] }, { "cell_type": "code", "execution_count": 13, "id": "351f90d1-8693-440b-9285-a7c5f6d75c8e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", " Performance After Feature Selection (Chi2) \n", "\n", "LogReg Accuracy: 0.7213114754098361\n", "\n", "RandomForest Accuracy: 0.7377049180327869\n", "\n", "SVM Accuracy: 0.7377049180327869\n", "\n", "Performance After Feature Selection (RFE)\n", "\n", "LogReg Accuracy: 0.8688524590163934\n", "\n", "RandomForest Accuracy: 0.8360655737704918\n", "\n", "SVM Accuracy: 0.8688524590163934\n" ] } ], "source": [ "print(\"\\n Performance After Feature Selection (Chi2) \")\n", "for name, (model, params) in models.items():\n", " grid = GridSearchCV(model, params, cv=5, scoring=\"accuracy\")\n", " grid.fit(X_train_chi2, y_train)\n", " pred = grid.predict(X_test_chi2)\n", " print(f\"\\n{name} Accuracy:\", accuracy_score(y_test, pred))\n", "print(\"\\nPerformance After Feature Selection (RFE)\")\n", "for name, (model, params) in models.items():\n", " grid = GridSearchCV(model, params, cv=5, scoring=\"accuracy\")\n", " grid.fit(X_train_rfe, y_train)\n", " pred = grid.predict(X_test_rfe)\n", " print(f\"\\n{name} Accuracy:\", accuracy_score(y_test, pred))" ] }, { "cell_type": "code", "execution_count": 14, "id": "a63be46f-a4de-45cf-a7e2-7bcd9681c313", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Data saved successfully as heart_cleaned.csv\n" ] } ], "source": [ "# حفظ نسخة من البيانات (ما تغيرت كثير)\n", "df.to_csv(\"heart_cleaned.csv\", index=False)\n", "print(\"Data saved successfully as heart_cleaned.csv\")" ] }, { "cell_type": "code", "execution_count": null, "id": "0cce5f44-9ee8-4a08-bdd3-44987c92397c", "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": "3.12.11" } }, "nbformat": 4, "nbformat_minor": 5 }