{ "cells": [ { "cell_type": "code", "execution_count": 10, "id": "6aa06cfb-e327-4cd0-b26f-fcea3ed64cb5", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.metrics import ( \n", " accuracy_score,\n", " classification_report,\n", " confusion_matrix,\n", " precision_score,\n", " recall_score,f1_score )\n", "from sklearn.tree import DecisionTreeClassifier\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.metrics import precision_recall_fscore_support\n", "from sklearn.naive_bayes import GaussianNB\n", "from sklearn.svm import SVC" ] }, { "cell_type": "code", "execution_count": 11, "id": "e80746fa-4c33-4ac1-9b1e-3dc74c410e4c", "metadata": {}, "outputs": [ { "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", "
PatientIdPregnanciesGlucoseBloodPressureSkinThicknessInsulinBMIDiabetesPedigreeFunctionAgeOutcome
0161487235033.60.627501
121856629026.60.351310
238183640023.30.672321
3418966239428.10.167210
450137403516843.12.288331
\n", "
" ], "text/plain": [ " 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 " ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.read_csv(\"diabetes.csv\")\n", "df.head()" ] }, { "cell_type": "code", "execution_count": 12, "id": "2c8bfc2a-8034-41cd-bf8a-2cd74490f83f", "metadata": {}, "outputs": [], "source": [ "A = df.drop('Outcome', axis = 1)\n", "b = df['Outcome']" ] }, { "cell_type": "code", "execution_count": 13, "id": "25ce9d41-991b-4228-8b44-b3ebd1753774", "metadata": {}, "outputs": [], "source": [ "X_train, X_test, y_train, y_test = train_test_split(\n", " A,\n", " b,\n", " test_size=0.2,\n", " random_state=101\n", ")" ] }, { "cell_type": "code", "execution_count": 17, "id": "9e90ec4d-7f2a-4927-8de1-35630050a44a", "metadata": {}, "outputs": [], "source": [ "models = {\n", " \"Decision Tree\": DecisionTreeClassifier(random_state=101),\n", " \"Random Forest\": RandomForestClassifier(n_estimators=100, random_state=101),\n", " \"Naive Bayes\": GaussianNB(),\n", " \"SVM (Linear Kernel)\": SVC(kernel=\"linear\"),\n", " \"SVM (RBF Kernel)\": SVC(kernel=\"rbf\")\n", "}" ] }, { "cell_type": "code", "execution_count": 25, "id": "9fc92613-cf7a-4703-8737-160d3a549a5a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training Accuracy: 1.0\n", "Testing Accuracy: 0.7012987012987013\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.77 0.79 0.78 103\n", " 1 0.55 0.53 0.54 51\n", "\n", " accuracy 0.70 154\n", " macro avg 0.66 0.66 0.66 154\n", "weighted avg 0.70 0.70 0.70 154\n", "\n", "Confusion Matrix:\n", "[[81 22]\n", " [24 27]]\n", "Training Accuracy: 1.0\n", "Testing Accuracy: 0.7662337662337663\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.82 0.83 0.83 103\n", " 1 0.65 0.63 0.64 51\n", "\n", " accuracy 0.77 154\n", " macro avg 0.74 0.73 0.73 154\n", "weighted avg 0.76 0.77 0.77 154\n", "\n", "Confusion Matrix:\n", "[[86 17]\n", " [19 32]]\n", "Training Accuracy: 0.750814332247557\n", "Testing Accuracy: 0.7532467532467533\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.82 0.82 0.82 103\n", " 1 0.63 0.63 0.63 51\n", "\n", " accuracy 0.75 154\n", " macro avg 0.72 0.72 0.72 154\n", "weighted avg 0.75 0.75 0.75 154\n", "\n", "Confusion Matrix:\n", "[[84 19]\n", " [19 32]]\n", "Training Accuracy: 0.7736156351791531\n", "Testing Accuracy: 0.7792207792207793\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.82 0.86 0.84 103\n", " 1 0.69 0.61 0.65 51\n", "\n", " accuracy 0.78 154\n", " macro avg 0.75 0.74 0.74 154\n", "weighted avg 0.77 0.78 0.78 154\n", "\n", "Confusion Matrix:\n", "[[89 14]\n", " [20 31]]\n", "Training Accuracy: 0.7182410423452769\n", "Testing Accuracy: 0.7272727272727273\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.73 0.95 0.82 103\n", " 1 0.74 0.27 0.40 51\n", "\n", " accuracy 0.73 154\n", " macro avg 0.73 0.61 0.61 154\n", "weighted avg 0.73 0.73 0.68 154\n", "\n", "Confusion Matrix:\n", "[[98 5]\n", " [37 14]]\n" ] } ], "source": [ "summary = []\n", "\n", "for model_name, clf in models.items():\n", "\n", " clf.fit(X_train, y_train)\n", "\n", " train_pred = clf.predict(X_train)\n", " test_pred = clf.predict(X_test)\n", "\n", " train_acc = accuracy_score(y_train, train_pred)\n", " test_acc = accuracy_score(y_test, test_pred)\n", "\n", " precision, recall, f1, _ = precision_recall_fscore_support(\n", " y_test, test_pred, average=\"weighted\"\n", " )\n", "\n", " summary.append([\n", " model_name,\n", " train_acc,\n", " test_acc,\n", " precision,\n", " recall,\n", " f1\n", " ])\n", " \n", " print(\"Training Accuracy:\", train_acc)\n", " print(\"Testing Accuracy:\", test_acc)\n", "\n", " print(\"\\nClassification Report:\")\n", " print(classification_report(y_test, test_pred))\n", "\n", " print(\"Confusion Matrix:\")\n", " print(confusion_matrix(y_test, test_pred))" ] }, { "cell_type": "code", "execution_count": null, "id": "4654aaca-2ca2-47e1-9db8-f6dd7d720b0a", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "anaconda-2025.12-py312", "language": "python", "name": "conda-env-anaconda-2025.12-py312-py" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.12" } }, "nbformat": 4, "nbformat_minor": 5 }