{ "cells": [ { "cell_type": "code", "execution_count": 26, "id": "af8f6ab9-9164-4e15-9335-be58cc5764b7", "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.naive_bayes import GaussianNB\n", "from sklearn.svm import SVC" ] }, { "cell_type": "code", "execution_count": 27, "id": "649016af-e94c-4317-8ef0-a8fa3e335c21", "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": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.read_csv(\"diabetes.csv\")\n", "df.head()" ] }, { "cell_type": "code", "execution_count": 28, "id": "700c3ec4-bbb9-422d-9d3b-7e9c83a0be6f", "metadata": {}, "outputs": [], "source": [ "x = df.drop('Outcome', axis = 1)\n", "y = df['Outcome']" ] }, { "cell_type": "code", "execution_count": 29, "id": "267f1ab0-3cd7-4810-9cbf-1d911cc42411", "metadata": {}, "outputs": [], "source": [ "x_train, x_test , y_train, y_test = train_test_split (\n", " x,y, test_size = 0.2, random_state = 42 \n", ")" ] }, { "cell_type": "code", "execution_count": 11, "id": "b111ed3f-e558-438a-bca4-6ce4d5df3db9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training Accuracy: 1.0\n", "Test Accuracy: 0.7402597402597403\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.80 0.79 0.80 99\n", " 1 0.63 0.65 0.64 55\n", "\n", " accuracy 0.74 154\n", " macro avg 0.72 0.72 0.72 154\n", "weighted avg 0.74 0.74 0.74 154\n", "\n", "\n", "Confusion Matrix:\n", "[[78 21]\n", " [19 36]]\n" ] } ], "source": [ "# function to Decision Tree\n", "dt = DecisionTreeClassifier()\n", "dt.fit(x_train, y_train)\n", "\n", "y_train_pred = dt.predict(x_train)/\n", "y_test_pred = dt.predict(x_test)\n", "\n", "print(\"Training Accuracy:\", accuracy_score(y_train, y_train_pred))\n", "print(\"Test Accuracy:\", accuracy_score(y_test, y_test_pred))\n", "\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_test_pred))\n", "\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_test_pred))" ] }, { "cell_type": "code", "execution_count": 17, "id": "4047de72-8459-45bf-a015-64295abbf42a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training Accuracy: 1.0\n", "Test Accuracy: 0.7532467532467533\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.82 0.79 0.80 99\n", " 1 0.64 0.69 0.67 55\n", "\n", " accuracy 0.75 154\n", " macro avg 0.73 0.74 0.74 154\n", "weighted avg 0.76 0.75 0.76 154\n", "\n", "\n", "Confusion Matrix:\n", "[[78 21]\n", " [17 38]]\n" ] } ], "source": [ "# function to Random forest\n", "dt = RandomForestClassifier(n_estimators=100,\n", " random_state=42)\n", "dt.fit(x_train, y_train)\n", "\n", "y_train_pred = dt.predict(x_train)\n", "y_test_pred = dt.predict(x_test)\n", "\n", "print(\"Training Accuracy:\", accuracy_score(y_train, y_train_pred))\n", "print(\"Test Accuracy:\", accuracy_score(y_test, y_test_pred))\n", "\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_test_pred))\n", "\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_test_pred))" ] }, { "cell_type": "code", "execution_count": 30, "id": "20cc8194-aad7-4f07-8213-98ad39ce607e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training Accuracy: 0.752442996742671\n", "Test Accuracy: 0.7597402597402597\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.83 0.79 0.81 99\n", " 1 0.65 0.71 0.68 55\n", "\n", " accuracy 0.76 154\n", " macro avg 0.74 0.75 0.74 154\n", "weighted avg 0.77 0.76 0.76 154\n", "\n", "\n", "Confusion Matrix:\n", "[[78 21]\n", " [16 39]]\n" ] } ], "source": [ "# function to Gaussian \n", "dt = GaussianNB()\n", "dt.fit(x_train, y_train)\n", "\n", "y_train_pred = dt.predict(x_train)\n", "y_test_pred = dt.predict(x_test)\n", "\n", "print(\"Training Accuracy:\", accuracy_score(y_train, y_train_pred))\n", "print(\"Test Accuracy:\", accuracy_score(y_test, y_test_pred))\n", "\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_test_pred))\n", "\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_test_pred))" ] }, { "cell_type": "code", "execution_count": 21, "id": "fcfba2af-a550-4b35-936b-5c0dbf48a27a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training Accuracy: 0.7736156351791531\n", "Test Accuracy: 0.7597402597402597\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.81 0.82 0.81 99\n", " 1 0.67 0.65 0.66 55\n", "\n", " accuracy 0.76 154\n", " macro avg 0.74 0.74 0.74 154\n", "weighted avg 0.76 0.76 0.76 154\n", "\n", "\n", "Confusion Matrix:\n", "[[81 18]\n", " [19 36]]\n" ] } ], "source": [ "# function to SVC Linear\n", "dt = SVC(kernel='linear')\n", "dt.fit(x_train, y_train)\n", "\n", "y_train_pred = dt.predict(x_train)\n", "y_test_pred = dt.predict(x_test)\n", "\n", "print(\"Training Accuracy:\", accuracy_score(y_train, y_train_pred))\n", "print(\"Test Accuracy:\", accuracy_score(y_test, y_test_pred))\n", "\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_test_pred))\n", "\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_test_pred))" ] }, { "cell_type": "code", "execution_count": 22, "id": "42b70672-f4d9-4fde-b16b-1476446f4890", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training Accuracy: 0.744299674267101\n", "Test Accuracy: 0.7467532467532467\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.75 0.92 0.82 99\n", " 1 0.75 0.44 0.55 55\n", "\n", " accuracy 0.75 154\n", " macro avg 0.75 0.68 0.69 154\n", "weighted avg 0.75 0.75 0.73 154\n", "\n", "\n", "Confusion Matrix:\n", "[[91 8]\n", " [31 24]]\n" ] } ], "source": [ "# function to SVC Rbf\n", "dt = SVC(kernel='rbf')\n", "dt.fit(x_train, y_train)\n", "\n", "y_train_pred = dt.predict(x_train)\n", "y_test_pred = dt.predict(x_test)\n", "\n", "print(\"Training Accuracy:\", accuracy_score(y_train, y_train_pred))\n", "print(\"Test Accuracy:\", accuracy_score(y_test, y_test_pred))\n", "\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_test_pred))\n", "\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_test_pred))" ] }, { "cell_type": "code", "execution_count": null, "id": "73a171e0-fbc3-4951-8d65-58fa67b2220f", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "8d49d827-83e6-4df2-97d5-6d562b6b3556", "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 }