{ "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": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "oKnyyIujGia-", "outputId": "080d965b-ba5b-4ea3-ea68-6b67e7f15b0d" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Dataset shape: (768, 10)\n", "\n", "Columns: ['PatientId', 'Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'Outcome']\n", "\n", "Target distribution:\n", " Outcome\n", "0 0.651042\n", "1 0.348958\n", "Name: proportion, dtype: float64\n", "\n", "Decision Tree\n", "---------------------------------------------\n", "\n", "Classification Report (Test set):\n", " precision recall f1-score support\n", "\n", " 0 0.75 0.77 0.76 100\n", " 1 0.56 0.54 0.55 54\n", "\n", " accuracy 0.69 154\n", " macro avg 0.66 0.65 0.65 154\n", "weighted avg 0.69 0.69 0.69 154\n", "\n", "Confusion Matrix (Test set):\n", "[[77 23]\n", " [25 29]]\n", "Training Accuracy : 1.0000\n", "Test Accuracy : 0.6883\n", "Precision (1) : 0.5577\n", "Recall (1) : 0.5370\n", "F1-score (1) : 0.5472\n", "\n", "Random Forest\n", "---------------------------------------------\n", "\n", "Classification Report (Test set):\n", " precision recall f1-score support\n", "\n", " 0 0.79 0.82 0.80 100\n", " 1 0.64 0.59 0.62 54\n", "\n", " accuracy 0.74 154\n", " macro avg 0.71 0.71 0.71 154\n", "weighted avg 0.74 0.74 0.74 154\n", "\n", "Confusion Matrix (Test set):\n", "[[82 18]\n", " [22 32]]\n", "Training Accuracy : 1.0000\n", "Test Accuracy : 0.7403\n", "Precision (1) : 0.6400\n", "Recall (1) : 0.5926\n", "F1-score (1) : 0.6154\n", "\n", "Naive Bayes\n", "---------------------------------------------\n", "\n", "Classification Report (Test set):\n", " precision recall f1-score support\n", "\n", " 0 0.79 0.76 0.78 100\n", " 1 0.59 0.63 0.61 54\n", "\n", " accuracy 0.71 154\n", " macro avg 0.69 0.69 0.69 154\n", "weighted avg 0.72 0.71 0.72 154\n", "\n", "Confusion Matrix (Test set):\n", "[[76 24]\n", " [20 34]]\n", "Training Accuracy : 0.7752\n", "Test Accuracy : 0.7143\n", "Precision (1) : 0.5862\n", "Recall (1) : 0.6296\n", "F1-score (1) : 0.6071\n", "\n", "SVM (Linear)\n", "---------------------------------------------\n", "\n", "Classification Report (Test set):\n", " precision recall f1-score support\n", "\n", " 0 0.75 0.83 0.79 100\n", " 1 0.61 0.50 0.55 54\n", "\n", " accuracy 0.71 154\n", " macro avg 0.68 0.67 0.67 154\n", "weighted avg 0.71 0.71 0.71 154\n", "\n", "Confusion Matrix (Test set):\n", "[[83 17]\n", " [27 27]]\n", "Training Accuracy : 0.7948\n", "Test Accuracy : 0.7143\n", "Precision (1) : 0.6136\n", "Recall (1) : 0.5000\n", "F1-score (1) : 0.5510\n", "\n", "SVM (RBF)\n", "---------------------------------------------\n", "\n", "Classification Report (Test set):\n", " precision recall f1-score support\n", "\n", " 0 0.70 0.87 0.77 100\n", " 1 0.55 0.30 0.39 54\n", "\n", " accuracy 0.67 154\n", " macro avg 0.62 0.58 0.58 154\n", "weighted avg 0.65 0.67 0.64 154\n", "\n", "Confusion Matrix (Test set):\n", "[[87 13]\n", " [38 16]]\n", "Training Accuracy : 0.7443\n", "Test Accuracy : 0.6688\n", "Precision (1) : 0.5517\n", "Recall (1) : 0.2963\n", "F1-score (1) : 0.3855\n" ] } ], "source": [ "# ==============================\n", "# Step 1: Import Libraries\n", "# ==============================\n", "import pandas as pd\n", "import numpy as np\n", "\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n", "\n", "from sklearn.tree import DecisionTreeClassifier\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.naive_bayes import GaussianNB\n", "from sklearn.svm import SVC\n", "\n", "\n", "# ==============================\n", "# Step 2: Load Dataset\n", "# ==============================\n", "df = pd.read_csv(\"/content/diabetes.csv\")\n", "\n", "print(\"Dataset shape:\", df.shape)\n", "print(\"\\nColumns:\", df.columns.tolist())\n", "print(\"\\nTarget distribution:\\n\", df['Outcome'].value_counts(normalize=True))\n", "\n", "\n", "# ==============================\n", "# Step 3: Prepare Data\n", "# ==============================\n", "X = df.drop(\"Outcome\", axis=1)\n", "y = df[\"Outcome\"]\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(\n", " X, y,\n", " test_size=0.20,\n", " random_state=42,\n", " stratify=y\n", ")\n", "\n", "\n", "# ==============================\n", "# Step 4: Evaluation Function\n", "# (Diabetes class = 1)\n", "# ==============================\n", "def evaluate_model_diabetes(model, model_name):\n", " model.fit(X_train, y_train)\n", "\n", " y_train_pred = model.predict(X_train)\n", " y_test_pred = model.predict(X_test)\n", "\n", " train_acc = accuracy_score(y_train, y_train_pred)\n", " test_acc = accuracy_score(y_test, y_test_pred)\n", "\n", " print(f\"\\n{model_name}\")\n", " print(\"-\" * 45)\n", "\n", " print(\"\\nClassification Report (Test set):\")\n", " print(classification_report(y_test, y_test_pred))\n", "\n", " print(\"Confusion Matrix (Test set):\")\n", " print(confusion_matrix(y_test, y_test_pred))\n", "\n", " report = classification_report(y_test, y_test_pred, output_dict=True)\n", "\n", " precision = report['1']['precision']\n", " recall = report['1']['recall']\n", " f1 = report['1']['f1-score']\n", "\n", " print(f\"Training Accuracy : {train_acc:.4f}\")\n", " print(f\"Test Accuracy : {test_acc:.4f}\")\n", " print(f\"Precision (1) : {precision:.4f}\")\n", " print(f\"Recall (1) : {recall:.4f}\")\n", " print(f\"F1-score (1) : {f1:.4f}\")\n", "\n", "\n", "# ==============================\n", "# Step 5: Train & Evaluate Models\n", "# ==============================\n", "\n", "# Decision Tree\n", "evaluate_model_diabetes(\n", " DecisionTreeClassifier(random_state=42),\n", " \"Decision Tree\"\n", ")\n", "\n", "# Random Forest\n", "evaluate_model_diabetes(\n", " RandomForestClassifier(n_estimators=100, random_state=42),\n", " \"Random Forest\"\n", ")\n", "\n", "# Naive Bayes\n", "evaluate_model_diabetes(\n", " GaussianNB(),\n", " \"Naive Bayes\"\n", ")\n", "\n", "# SVM (Linear)\n", "evaluate_model_diabetes(\n", " SVC(kernel='linear'),\n", " \"SVM (Linear)\"\n", ")\n", "\n", "# SVM (RBF)\n", "evaluate_model_diabetes(\n", " SVC(kernel='rbf'),\n", " \"SVM (RBF)\"\n", ")\n" ] } ] }