{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "id": "6N9ohvX7-tdE" }, "outputs": [], "source": [ "# Import necessary libraries\n", "import pandas as pd\n", "import numpy as np\n", "from sklearn.model_selection import train_test_split, GridSearchCV\n", "from sklearn.impute import SimpleImputer\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.feature_selection import SelectKBest, f_classif, RFE\n", "from sklearn.metrics import classification_report, accuracy_score\n", "from sklearn.preprocessing import StandardScaler\n", "from xgboost import XGBClassifier" ] }, { "cell_type": "code", "source": [ "from google.colab import files\n", "uploaded = files.upload()\n", "\n", "import pandas as pd\n", "\n", "df = pd.read_csv('healthcare-dataset-stroke-data.csv')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 71 }, "id": "LLlRtq2f_Aqy", "outputId": "8eaed53c-31df-433b-c9fe-d0f5fbc50224" }, "execution_count": 3, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " \n", " Upload widget is only available when the cell has been executed in the\n", " current browser session. Please rerun this cell to enable.\n", " \n", " " ] }, "metadata": {} }, { "output_type": "stream", "name": "stdout", "text": [ "Saving healthcare-dataset-stroke-data.csv to healthcare-dataset-stroke-data.csv\n" ] } ] }, { "cell_type": "code", "source": [ "# Display initial data information\n", "df" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 461 }, "id": "BxoJ0rfO_VM0", "outputId": "6dabafe7-8b00-472e-b29c-6fe8e40a22a0" }, "execution_count": 36, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " id age hypertension heart_disease avg_glucose_level bmi \\\n", "0 9046 67.0 0 1 228.69 36.6 \n", "1 51676 61.0 0 0 202.21 28.1 \n", "2 31112 80.0 0 1 105.92 32.5 \n", "3 60182 49.0 0 0 171.23 34.4 \n", "4 1665 79.0 1 0 174.12 24.0 \n", "... ... ... ... ... ... ... \n", "5105 18234 80.0 1 0 83.75 28.1 \n", "5106 44873 81.0 0 0 125.20 40.0 \n", "5107 19723 35.0 0 0 82.99 30.6 \n", "5108 37544 51.0 0 0 166.29 25.6 \n", "5109 44679 44.0 0 0 85.28 26.2 \n", "\n", " stroke gender_Male gender_Other ever_married_Yes \\\n", "0 1 True False True \n", "1 1 False False True \n", "2 1 True False True \n", "3 1 False False True \n", "4 1 False False True \n", "... ... ... ... ... \n", "5105 0 False False True \n", "5106 0 False False True \n", "5107 0 False False True \n", "5108 0 True False True \n", "5109 0 False False True \n", "\n", " work_type_Never_worked work_type_Private work_type_Self-employed \\\n", "0 False True False \n", "1 False False True \n", "2 False True False \n", "3 False True False \n", "4 False False True \n", "... ... ... ... \n", "5105 False True False \n", "5106 False False True \n", "5107 False False True \n", "5108 False True False \n", "5109 False False False \n", "\n", " work_type_children Residence_type_Urban \\\n", "0 False True \n", "1 False False \n", "2 False False \n", "3 False True \n", "4 False False \n", "... ... ... \n", "5105 False True \n", "5106 False True \n", "5107 False False \n", "5108 False False \n", "5109 False True \n", "\n", " smoking_status_formerly smoked smoking_status_never smoked \\\n", "0 True False \n", "1 False True \n", "2 False True \n", "3 False False \n", "4 False True \n", "... ... ... \n", "5105 False True \n", "5106 False True \n", "5107 False True \n", "5108 True False \n", "5109 False False \n", "\n", " smoking_status_smokes \n", "0 False \n", "1 False \n", "2 False \n", "3 True \n", "4 False \n", "... ... \n", "5105 False \n", "5106 False \n", "5107 False \n", "5108 False \n", "5109 False \n", "\n", "[5110 rows x 18 columns]" ], "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", " \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", " \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", "
idagehypertensionheart_diseaseavg_glucose_levelbmistrokegender_Malegender_Otherever_married_Yeswork_type_Never_workedwork_type_Privatework_type_Self-employedwork_type_childrenResidence_type_Urbansmoking_status_formerly smokedsmoking_status_never smokedsmoking_status_smokes
0904667.001228.6936.61TrueFalseTrueFalseTrueFalseFalseTrueTrueFalseFalse
15167661.000202.2128.11FalseFalseTrueFalseFalseTrueFalseFalseFalseTrueFalse
23111280.001105.9232.51TrueFalseTrueFalseTrueFalseFalseFalseFalseTrueFalse
36018249.000171.2334.41FalseFalseTrueFalseTrueFalseFalseTrueFalseFalseTrue
4166579.010174.1224.01FalseFalseTrueFalseFalseTrueFalseFalseFalseTrueFalse
.........................................................
51051823480.01083.7528.10FalseFalseTrueFalseTrueFalseFalseTrueFalseTrueFalse
51064487381.000125.2040.00FalseFalseTrueFalseFalseTrueFalseTrueFalseTrueFalse
51071972335.00082.9930.60FalseFalseTrueFalseFalseTrueFalseFalseFalseTrueFalse
51083754451.000166.2925.60TrueFalseTrueFalseTrueFalseFalseFalseTrueFalseFalse
51094467944.00085.2826.20FalseFalseTrueFalseFalseFalseFalseTrueFalseFalseFalse
\n", "

5110 rows × 18 columns

\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" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "df", "summary": "{\n \"name\": \"df\",\n \"rows\": 5110,\n \"fields\": [\n {\n \"column\": \"id\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 21161,\n \"min\": 67,\n \"max\": 72940,\n \"num_unique_values\": 5110,\n \"samples\": [\n 40041,\n 55244,\n 70992\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 22.61264672311352,\n \"min\": 0.08,\n \"max\": 82.0,\n \"num_unique_values\": 104,\n \"samples\": [\n 45.0,\n 24.0,\n 33.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"hypertension\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 1,\n \"num_unique_values\": 2,\n \"samples\": [\n 1,\n 0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"heart_disease\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 1,\n \"num_unique_values\": 2,\n \"samples\": [\n 0,\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"avg_glucose_level\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 45.28356015058203,\n \"min\": 55.12,\n \"max\": 271.74,\n \"num_unique_values\": 3979,\n \"samples\": [\n 178.29,\n 156.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"bmi\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 7.699562318787533,\n \"min\": 10.3,\n \"max\": 97.6,\n \"num_unique_values\": 418,\n \"samples\": [\n 49.5,\n 18.5\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"stroke\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 1,\n \"num_unique_values\": 2,\n \"samples\": [\n 0,\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"gender_Male\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n false,\n true\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"gender_Other\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n true,\n false\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ever_married_Yes\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n false,\n true\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"work_type_Never_worked\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n true,\n false\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"work_type_Private\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n false,\n true\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"work_type_Self-employed\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n true,\n false\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"work_type_children\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n true,\n false\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Residence_type_Urban\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n false,\n true\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"smoking_status_formerly smoked\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n false,\n true\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"smoking_status_never smoked\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n true,\n false\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"smoking_status_smokes\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n true,\n false\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 36 } ] }, { "cell_type": "code", "source": [ "# Impute missing numerical values (e.g., BMI) with the median\n", "numerical_features = ['age', 'avg_glucose_level', 'bmi']\n", "imputer = SimpleImputer(strategy='median')\n", "df[numerical_features] = imputer.fit_transform(df[numerical_features])" ], "metadata": { "id": "xSZrnD8-_aeM" }, "execution_count": 5, "outputs": [] }, { "cell_type": "code", "source": [ "# Fill missing categorical values (if any) with the most frequent value\n", "categorical_features = ['smoking_status']\n", "imputer_cat = SimpleImputer(strategy='most_frequent')\n", "df[categorical_features] = imputer_cat.fit_transform(df[categorical_features])" ], "metadata": { "id": "6AWcGOHV_efU" }, "execution_count": 6, "outputs": [] }, { "cell_type": "code", "source": [ "# Confirm no missing values\n", "print(\"\\nMissing values after imputation:\")\n", "print(df.isnull().sum())" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "VgIVpFDz_g4H", "outputId": "0aec95d0-98ee-4247-e9e4-bbc695ca4a0b" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "Missing values after imputation:\n", "id 0\n", "gender 0\n", "age 0\n", "hypertension 0\n", "heart_disease 0\n", "ever_married 0\n", "work_type 0\n", "Residence_type 0\n", "avg_glucose_level 0\n", "bmi 0\n", "smoking_status 0\n", "stroke 0\n", "dtype: int64\n" ] } ] }, { "cell_type": "code", "source": [ "# Encode categorical variables\n", "df = pd.get_dummies(df, columns=['gender', 'ever_married', 'work_type', 'Residence_type', 'smoking_status'], drop_first=True)" ], "metadata": { "id": "LU5X4scl_lOG" }, "execution_count": 8, "outputs": [] }, { "cell_type": "code", "source": [ "# Separate features and target\n", "X = df.drop(columns=['id', 'stroke'])\n", "y = df['stroke']\n", "\n", "# Split the data into training and testing sets\n", "from sklearn.model_selection import train_test_split\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # Adjust test_size and random_state as needed\n", "\n", "# Scale the features\n", "scaler = StandardScaler()\n", "X_train = scaler.fit_transform(X_train)\n", "X_test = scaler.transform(X_test)" ], "metadata": { "id": "LQzJyx8QAKYd" }, "execution_count": 11, "outputs": [] }, { "cell_type": "code", "source": [ "# Step 2: Apply machine learning models with grid search optimization\n", "print(\"\\nApplying Machine Learning Models with Grid Search...\")\n", "rf = RandomForestClassifier(random_state=42)\n", "param_grid_rf = {\n", " 'n_estimators': [100, 200, 300],\n", " 'max_depth': [None, 10, 20],\n", " 'min_samples_split': [2, 5, 10]\n", "}\n", "grid_search_rf = GridSearchCV(rf, param_grid_rf, cv=5, scoring='accuracy', n_jobs=-1)\n", "grid_search_rf.fit(X_train, y_train)\n", "\n", "best_rf = grid_search_rf.best_estimator_\n", "print(f\"Best Random Forest Parameters: {grid_search_rf.best_params_}\")\n", "\n", "# Evaluate the model\n", "y_pred_rf = best_rf.predict(X_test)\n", "print(\"\\nRandom Forest Classification Report:\")\n", "print(classification_report(y_test, y_pred_rf))\n", "\n", "\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "fCLuMHSUAXIU", "outputId": "dbb5359e-cfcb-4dae-b0ed-ebf2c0b90f02" }, "execution_count": 15, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "Applying Machine Learning Models with Grid Search...\n", "Best Random Forest Parameters: {'max_depth': None, 'min_samples_split': 2, 'n_estimators': 100}\n", "\n", "Random Forest Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.94 1.00 0.97 960\n", " 1 0.00 0.00 0.00 62\n", "\n", " accuracy 0.94 1022\n", " macro avg 0.47 0.50 0.48 1022\n", "weighted avg 0.88 0.94 0.91 1022\n", "\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n", "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n", "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n" ] } ] }, { "cell_type": "code", "source": [ "# Apply XGBoost model\n", "xgb = XGBClassifier(random_state=42, use_label_encoder=False, eval_metric='logloss')\n", "param_grid_xgb = {\n", " 'n_estimators': [100, 200],\n", " 'max_depth': [3, 6, 10],\n", " 'learning_rate': [0.01, 0.1, 0.2]\n", "}\n", "grid_search_xgb = GridSearchCV(xgb, param_grid_xgb, cv=5, scoring='accuracy', n_jobs=-1)\n", "grid_search_xgb.fit(X_train, y_train)\n", "\n", "best_xgb = grid_search_xgb.best_estimator_\n", "print(f\"Best XGBoost Parameters: {grid_search_xgb.best_params_}\")\n", "\n", "# Evaluate the model\n", "y_pred_xgb = best_xgb.predict(X_test)\n", "print(\"\\nXGBoost Classification Report:\")\n", "print(classification_report(y_test, y_pred_xgb))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "SYBZFDYBBxE2", "outputId": "4b60d783-a892-4323-8594-8462032d8929" }, "execution_count": 16, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Best XGBoost Parameters: {'learning_rate': 0.01, 'max_depth': 3, 'n_estimators': 100}\n", "\n", "XGBoost Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.94 1.00 0.97 960\n", " 1 0.00 0.00 0.00 62\n", "\n", " accuracy 0.94 1022\n", " macro avg 0.47 0.50 0.48 1022\n", "weighted avg 0.88 0.94 0.91 1022\n", "\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/xgboost/core.py:158: UserWarning: [12:40:12] WARNING: /workspace/src/learner.cc:740: \n", "Parameters: { \"use_label_encoder\" } are not used.\n", "\n", " warnings.warn(smsg, UserWarning)\n", "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n", "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n", "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n" ] } ] }, { "cell_type": "code", "source": [ "\n", "# Step 3: Feature Selection\n", "selector_kbest = SelectKBest(score_func=f_classif, k=10)\n", "X_new_kbest = selector_kbest.fit_transform(X, y)\n", "selected_features_kbest = X.columns[selector_kbest.get_support()]\n", "print(f\"Selected Features using SelectKBest: {list(selected_features_kbest)}\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "vK3_b9HADPwr", "outputId": "fc649610-9f1f-425e-9c77-cd771a1849be" }, "execution_count": 26, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Selected Features using SelectKBest: ['age', 'hypertension', 'heart_disease', 'avg_glucose_level', 'bmi', 'ever_married_Yes', 'work_type_Self-employed', 'work_type_children', 'Residence_type_Urban', 'smoking_status_formerly smoked']\n" ] } ] }, { "cell_type": "code", "source": [ "# Method 2: Recursive Feature Elimination (RFE) with Random Forest\n", "rfe = RFE(estimator=RandomForestClassifier(random_state=42), n_features_to_select=10)\n", "rfe.fit(X, y)\n", "selected_features_rfe = X.columns[rfe.support_]\n", "print(f\"Selected Features using RFE: {list(selected_features_rfe)}\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "EXTQA3DrDWBW", "outputId": "ae19d2a5-9e6c-4963-9902-b091c21fb783" }, "execution_count": 27, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Selected Features using RFE: ['age', 'hypertension', 'heart_disease', 'avg_glucose_level', 'bmi', 'gender_Male', 'work_type_Private', 'Residence_type_Urban', 'smoking_status_formerly smoked', 'smoking_status_never smoked']\n" ] } ] }, { "cell_type": "code", "source": [ "# Step 4: Apply models to selected features and evaluate\n", "print(\"\\nApplying Models to Selected Features...\")\n", "# Train-test split for SelectKBest features\n", "X_kbest_train, X_kbest_test, y_kbest_train, y_kbest_test = train_test_split(\n", " X[selected_features_kbest], y, test_size=0.3, random_state=42, stratify=y)\n", "\n", "\n", "\n", "# Train-test split for RFE features\n", "X_rfe_train, X_rfe_test, y_rfe_train, y_rfe_test = train_test_split(\n", " X[selected_features_rfe], y, test_size=0.3, random_state=42, stratify=y)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "cUBJwzXrDaLX", "outputId": "7e57008b-9722-48c8-e784-6ab7b84a17a7" }, "execution_count": 29, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "Applying Models to Selected Features...\n" ] } ] }, { "cell_type": "code", "source": [ "# Random Forest on SelectKBest features\n", "best_rf.fit(X_kbest_train, y_kbest_train)\n", "y_kbest_pred_rf = best_rf.predict(X_kbest_test)\n", "print(\"\\nRandom Forest on SelectKBest Features:\")\n", "print(classification_report(y_kbest_test, y_kbest_pred_rf))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "5rew-ab0EumC", "outputId": "d94b5e14-ee49-48fd-9bd1-a4c36d00591c" }, "execution_count": 30, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "Random Forest on SelectKBest Features:\n", " precision recall f1-score support\n", "\n", " 0 0.95 1.00 0.97 1458\n", " 1 0.00 0.00 0.00 75\n", "\n", " accuracy 0.95 1533\n", " macro avg 0.48 0.50 0.49 1533\n", "weighted avg 0.90 0.95 0.93 1533\n", "\n" ] } ] }, { "cell_type": "code", "source": [ "# Random Forest on RFE features\n", "best_rf.fit(X_rfe_train, y_rfe_train)\n", "y_rfe_pred_rf = best_rf.predict(X_rfe_test)\n", "print(\"\\nRandom Forest on RFE Features:\")\n", "print(classification_report(y_rfe_test, y_rfe_pred_rf))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "idXO1_NWE3lB", "outputId": "c3500011-74ce-43f9-fb96-6a2538ed3f19" }, "execution_count": 31, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "Random Forest on RFE Features:\n", " precision recall f1-score support\n", "\n", " 0 0.95 1.00 0.97 1458\n", " 1 0.00 0.00 0.00 75\n", "\n", " accuracy 0.95 1533\n", " macro avg 0.48 0.50 0.49 1533\n", "weighted avg 0.90 0.95 0.93 1533\n", "\n" ] } ] }, { "cell_type": "code", "source": [ "# XGBoost on SelectKBest features\n", "best_xgb.fit(X_kbest_train, y_kbest_train)\n", "y_kbest_pred_xgb = best_xgb.predict(X_kbest_test)\n", "print(\"\\nXGBoost on SelectKBest Features:\")\n", "print(classification_report(y_kbest_test, y_kbest_pred_xgb))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "T5R43QdDE5cB", "outputId": "9f80f155-2cef-45fc-eede-82e6d59e9fb2" }, "execution_count": 32, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/xgboost/core.py:158: UserWarning: [12:52:39] WARNING: /workspace/src/learner.cc:740: \n", "Parameters: { \"use_label_encoder\" } are not used.\n", "\n", " warnings.warn(smsg, UserWarning)\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "\n", "XGBoost on SelectKBest Features:\n", " precision recall f1-score support\n", "\n", " 0 0.95 1.00 0.97 1458\n", " 1 0.00 0.00 0.00 75\n", "\n", " accuracy 0.95 1533\n", " macro avg 0.48 0.50 0.49 1533\n", "weighted avg 0.90 0.95 0.93 1533\n", "\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n", "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n", "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n" ] } ] }, { "cell_type": "code", "source": [ "# XGBoost on RFE features\n", "best_xgb.fit(X_rfe_train, y_rfe_train)\n", "y_rfe_pred_xgb = best_xgb.predict(X_rfe_test)\n", "print(\"\\nXGBoost on RFE Features:\")\n", "print(classification_report(y_rfe_test, y_rfe_pred_xgb))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "i_3KsbaQFD2U", "outputId": "4a11bab6-8206-44c7-b9f0-b89d52e42d11" }, "execution_count": 33, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/xgboost/core.py:158: UserWarning: [12:53:04] WARNING: /workspace/src/learner.cc:740: \n", "Parameters: { \"use_label_encoder\" } are not used.\n", "\n", " warnings.warn(smsg, UserWarning)\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "\n", "XGBoost on RFE Features:\n", " precision recall f1-score support\n", "\n", " 0 0.95 1.00 0.97 1458\n", " 1 0.00 0.00 0.00 75\n", "\n", " accuracy 0.95 1533\n", " macro avg 0.48 0.50 0.49 1533\n", "weighted avg 0.90 0.95 0.93 1533\n", "\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n", "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n", "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1531: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n" ] } ] } ] }