{ "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": { "collapsed": true, "id": "273zC8GGEb_J", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "da2519d9-8b98-42a5-c324-1b420af8117e" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ " PatientId Pregnancies Glucose BloodPressure SkinThickness Insulin \\\n", "0 1 6 148 72 35 0 \n", "1 2 1 85 66 29 0 \n", "2 3 8 183 64 0 0 \n", "3 4 1 89 66 23 94 \n", "4 5 0 137 40 35 168 \n", "\n", " BMI DiabetesPedigreeFunction Age Outcome \n", "0 33.6 0.627 50 1 \n", "1 26.6 0.351 31 0 \n", "2 23.3 0.672 32 1 \n", "3 28.1 0.167 21 0 \n", "4 43.1 2.288 33 1 \n", "\n", "Feature Importance:\n", " Feature Importance\n", "2 Glucose 0.267089\n", "6 BMI 0.153334\n", "8 Age 0.129185\n", "7 DiabetesPedigreeFunction 0.102934\n", "0 PatientId 0.090048\n", "3 BloodPressure 0.075748\n", "1 Pregnancies 0.065340\n", "5 Insulin 0.060622\n", "4 SkinThickness 0.055700\n", "\n", "Model Comparison Results:\n", " Model Accuracy Precision Recall F1 Score\n", "0 Random Forest (Original) 0.753247 0.644068 0.690909 0.666667\n", "1 Random Forest (Top Features) 0.772727 0.678571 0.690909 0.684685\n", "2 Random Forest (PCA) 0.701299 0.591837 0.527273 0.557692\n", "3 Logistic Regression 0.733766 0.645833 0.563636 0.601942\n", "4 Naive Bayes 0.772727 0.717391 0.600000 0.653465\n" ] } ], "source": [ "# ===============================\n", "# Feature Selection & Model Comparison\n", "# ===============================\n", "\n", "import pandas as pd\n", "import numpy as np\n", "\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\n", "\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.decomposition import PCA\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.naive_bayes import GaussianNB\n", "\n", "# ===============================\n", "# Load Dataset\n", "# ===============================\n", "df = pd.read_csv('/content/diabetes (1).csv')\n", "print(df.head())\n", "\n", "# ===============================\n", "# Handle Missing Values\n", "# ===============================\n", "df.fillna(df.mean(), inplace=True)\n", "\n", "# ===============================\n", "# Split Features and Target\n", "# ===============================\n", "X = df.drop('Outcome', axis=1)\n", "y = df['Outcome']\n", "\n", "# ===============================\n", "# Train-Test Split (Original Data)\n", "# ===============================\n", "X_train, X_test, y_train, y_test = train_test_split(\n", " X, y, test_size=0.2, random_state=42\n", ")\n", "\n", "# ===============================\n", "# Random Forest - Original Features\n", "# ===============================\n", "rf = RandomForestClassifier(random_state=42)\n", "rf.fit(X_train, y_train)\n", "y_pred_rf = rf.predict(X_test)\n", "\n", "rf_acc = accuracy_score(y_test, y_pred_rf)\n", "rf_prec = precision_score(y_test, y_pred_rf)\n", "rf_rec = recall_score(y_test, y_pred_rf)\n", "rf_f1 = f1_score(y_test, y_pred_rf)\n", "\n", "# ===============================\n", "# Feature Importance & Selection\n", "# ===============================\n", "feature_importance = pd.DataFrame({\n", " 'Feature': X.columns,\n", " 'Importance': rf.feature_importances_\n", "}).sort_values(by='Importance', ascending=False)\n", "\n", "top_features = feature_importance['Feature'][:5]\n", "X_top = X[top_features]\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(\n", " X_top, y, test_size=0.2, random_state=42\n", ")\n", "\n", "rf_top = RandomForestClassifier(random_state=42)\n", "rf_top.fit(X_train, y_train)\n", "y_pred_top = rf_top.predict(X_test)\n", "\n", "rf_top_acc = accuracy_score(y_test, y_pred_top)\n", "rf_top_prec = precision_score(y_test, y_pred_top)\n", "rf_top_rec = recall_score(y_test, y_pred_top)\n", "rf_top_f1 = f1_score(y_test, y_pred_top)\n", "\n", "# ===============================\n", "# PCA Feature Reduction\n", "# ===============================\n", "scaler = StandardScaler()\n", "X_scaled = scaler.fit_transform(X)\n", "\n", "pca = PCA(n_components=5)\n", "X_pca = pca.fit_transform(X_scaled)\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(\n", " X_pca, y, test_size=0.2, random_state=42\n", ")\n", "\n", "rf_pca = RandomForestClassifier(random_state=42)\n", "rf_pca.fit(X_train, y_train)\n", "y_pred_pca = rf_pca.predict(X_test)\n", "\n", "rf_pca_acc = accuracy_score(y_test, y_pred_pca)\n", "rf_pca_prec = precision_score(y_test, y_pred_pca)\n", "rf_pca_rec = recall_score(y_test, y_pred_pca)\n", "rf_pca_f1 = f1_score(y_test, y_pred_pca)\n", "\n", "# ===============================\n", "# Logistic Regression\n", "# ===============================\n", "lr = LogisticRegression(max_iter=1000)\n", "lr.fit(X_train, y_train)\n", "y_pred_lr = lr.predict(X_test)\n", "\n", "lr_acc = accuracy_score(y_test, y_pred_lr)\n", "lr_prec = precision_score(y_test, y_pred_lr)\n", "lr_rec = recall_score(y_test, y_pred_lr)\n", "lr_f1 = f1_score(y_test, y_pred_lr)\n", "\n", "# ===============================\n", "# Naive Bayes\n", "# ===============================\n", "nb = GaussianNB()\n", "nb.fit(X_train, y_train)\n", "y_pred_nb = nb.predict(X_test)\n", "\n", "nb_acc = accuracy_score(y_test, y_pred_nb)\n", "nb_prec = precision_score(y_test, y_pred_nb)\n", "nb_rec = recall_score(y_test, y_pred_nb)\n", "nb_f1 = f1_score(y_test, y_pred_nb)\n", "\n", "# ===============================\n", "# Results Comparison\n", "# ===============================\n", "results = pd.DataFrame({\n", " 'Model': [\n", " 'Random Forest (Original)',\n", " 'Random Forest (Top Features)',\n", " 'Random Forest (PCA)',\n", " 'Logistic Regression',\n", " 'Naive Bayes'\n", " ],\n", " 'Accuracy': [\n", " rf_acc,\n", " rf_top_acc,\n", " rf_pca_acc,\n", " lr_acc,\n", " nb_acc\n", " ],\n", " 'Precision': [\n", " rf_prec,\n", " rf_top_prec,\n", " rf_pca_prec,\n", " lr_prec,\n", " nb_prec\n", " ],\n", " 'Recall': [\n", " rf_rec,\n", " rf_top_rec,\n", " rf_pca_rec,\n", " lr_rec,\n", " nb_rec\n", " ],\n", " 'F1 Score': [\n", " rf_f1,\n", " rf_top_f1,\n", " rf_pca_f1,\n", " lr_f1,\n", " nb_f1\n", " ]\n", "})\n", "\n", "print(\"\\nFeature Importance:\")\n", "print(feature_importance)\n", "\n", "print(\"\\nModel Comparison Results:\")\n", "print(results)" ] }, { "cell_type": "markdown", "source": [ "The analysis shows that glucose level is the most important factor in predicting diabetes, followed by BMI, age, and family history. This matches medical knowledge, as high blood sugar, obesity, and increasing age increase the risk of diabetes. Other features such as blood pressure, pregnancies, insulin, and skin thickness have less impact on the prediction.\n", "\n", "Among all models, the Random Forest model using selected top features performed the best, giving higher accuracy and balanced precision and recall. Models like Logistic Regression and Naive Bayes showed reasonable results but were less reliable for identifying all diabetic cases. The PCA-based model performed the worst, as it removed important information. Overall, Random Forest with important features is the most suitable model for this dataset." ], "metadata": { "id": "65XkIobEfVIx" } } ] }