{ "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": 49, "metadata": { "id": "pL1Q-xQ8i5vN" }, "outputs": [], "source": [ "\n", "import pandas as pd\n", "import numpy as np\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\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", "source": [ "# Load dataset\n", "df = pd.read_csv('/content/drive/MyDrive/ML W4/diabetes (1).csv')\n", "\n", "# Display first few rows\n", "df.head()\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "edS0H12Tjcp0", "outputId": "5ece58fe-2031-4047-d715-240865107b95" }, "execution_count": 50, "outputs": [ { "output_type": "execute_result", "data": { "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 " ], "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", "
PatientIdPregnanciesGlucoseBloodPressureSkinThicknessInsulinBMIDiabetesPedigreeFunctionAgeOutcome
0161487235033.60.627501
121856629026.60.351310
238183640023.30.672321
3418966239428.10.167210
450137403516843.12.288331
\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\": 768,\n \"fields\": [\n {\n \"column\": \"PatientId\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 221,\n \"min\": 1,\n \"max\": 768,\n \"num_unique_values\": 768,\n \"samples\": [\n 669,\n 325,\n 625\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Pregnancies\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3,\n \"min\": 0,\n \"max\": 17,\n \"num_unique_values\": 17,\n \"samples\": [\n 6,\n 1,\n 3\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Glucose\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 31,\n \"min\": 0,\n \"max\": 199,\n \"num_unique_values\": 136,\n \"samples\": [\n 151,\n 101,\n 112\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"BloodPressure\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 19,\n \"min\": 0,\n \"max\": 122,\n \"num_unique_values\": 47,\n \"samples\": [\n 86,\n 46,\n 85\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"SkinThickness\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 15,\n \"min\": 0,\n \"max\": 99,\n \"num_unique_values\": 51,\n \"samples\": [\n 7,\n 12,\n 48\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Insulin\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 115,\n \"min\": 0,\n \"max\": 846,\n \"num_unique_values\": 186,\n \"samples\": [\n 52,\n 41,\n 183\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"BMI\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 7.8841603203754405,\n \"min\": 0.0,\n \"max\": 67.1,\n \"num_unique_values\": 248,\n \"samples\": [\n 19.9,\n 31.0,\n 38.1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"DiabetesPedigreeFunction\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.33132859501277484,\n \"min\": 0.078,\n \"max\": 2.42,\n \"num_unique_values\": 517,\n \"samples\": [\n 1.731,\n 0.426,\n 0.138\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11,\n \"min\": 21,\n \"max\": 81,\n \"num_unique_values\": 52,\n \"samples\": [\n 60,\n 47,\n 72\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Outcome\",\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}" } }, "metadata": {}, "execution_count": 50 } ] }, { "cell_type": "code", "source": [ "X = df.drop('Outcome', axis=1)\n", "y = df['Outcome']\n" ], "metadata": { "id": "daUvSlNHj1o7" }, "execution_count": 51, "outputs": [] }, { "cell_type": "code", "source": [ "X_train, X_test, y_train, y_test = train_test_split(\n", " X, y, test_size=0.2, random_state=42\n", ")\n" ], "metadata": { "id": "vqjdykzikGzL" }, "execution_count": 52, "outputs": [] }, { "cell_type": "markdown", "source": [ "**Decision tree classifier**" ], "metadata": { "id": "yJyghuirkKCe" } }, { "cell_type": "code", "source": [ "dt = DecisionTreeClassifier()\n", "dt.fit(X_train, y_train)\n", "\n", "y_train_pred_dt = dt.predict(X_train)\n", "y_test_pred_dt = dt.predict(X_test)\n" ], "metadata": { "id": "gf_WIBxkkWQU" }, "execution_count": 53, "outputs": [] }, { "cell_type": "markdown", "source": [ "**Random Forest Classifier**" ], "metadata": { "id": "m-cXShNykY6M" } }, { "cell_type": "code", "source": [ "rf = RandomForestClassifier(n_estimators=100, random_state=42)\n", "rf.fit(X_train, y_train)\n", "\n", "y_train_pred_rf = rf.predict(X_train)\n", "y_test_pred_rf = rf.predict(X_test)\n" ], "metadata": { "id": "KTP6IwcwkrYc" }, "execution_count": 54, "outputs": [] }, { "cell_type": "markdown", "source": [ "**Naïve Bayes (GaussianNB)**" ], "metadata": { "id": "R_7wvGa1k4BD" } }, { "cell_type": "code", "source": [ "nb = GaussianNB()\n", "nb.fit(X_train, y_train)\n", "\n", "y_train_pred_nb = nb.predict(X_train)\n", "y_test_pred_nb = nb.predict(X_test)\n" ], "metadata": { "id": "c9hhZ7imk-oV" }, "execution_count": 55, "outputs": [] }, { "cell_type": "markdown", "source": [ "**Support Vector Machine (SVM)**" ], "metadata": { "id": "sFhV7UONlBpL" } }, { "cell_type": "code", "source": [ "svm_linear = SVC(kernel='linear')\n", "svm_linear.fit(X_train, y_train)\n", "\n", "y_train_pred_svm_linear = svm_linear.predict(X_train)\n", "y_test_pred_svm_linear = svm_linear.predict(X_test)\n" ], "metadata": { "id": "clYumANvlGZ9" }, "execution_count": 56, "outputs": [] }, { "cell_type": "markdown", "source": [ "**Evaluate Models**" ], "metadata": { "id": "3Ya67H3olcR0" } }, { "cell_type": "code", "source": [ "print(\"Decision Tree - Training Accuracy:\", accuracy_score(y_train, y_train_pred_dt))\n", "print(\"Decision Tree - Testing Accuracy:\", accuracy_score(y_test, y_test_pred_dt))\n", "\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_test_pred_dt))\n", "\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_test_pred_dt))\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "N2lDPYHulgrT", "outputId": "ec052889-ec14-4942-a0e2-deb8c418c98f" }, "execution_count": 57, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Decision Tree - Training Accuracy: 1.0\n", "Decision Tree - Testing Accuracy: 0.7727272727272727\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.83 0.82 0.82 99\n", " 1 0.68 0.69 0.68 55\n", "\n", " accuracy 0.77 154\n", " macro avg 0.75 0.75 0.75 154\n", "weighted avg 0.77 0.77 0.77 154\n", "\n", "\n", "Confusion Matrix:\n", "[[81 18]\n", " [17 38]]\n" ] } ] }, { "cell_type": "code", "source": [ "print(\"Random Forest - Training Accuracy:\", accuracy_score(y_train, y_train_pred_rf))\n", "print(\"Random Forest - Testing Accuracy:\", accuracy_score(y_test, y_test_pred_rf))\n", "\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_test_pred_rf))\n", "\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_test_pred_rf))\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "iBa-Z1Txljjr", "outputId": "ab67a24f-5588-4ccb-83e4-c3b9e95b476b" }, "execution_count": 58, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Random Forest - Training Accuracy: 1.0\n", "Random Forest - Testing 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" ] } ] }, { "cell_type": "code", "source": [ "print(\"Naïve Bayes - Training Accuracy:\", accuracy_score(y_train, y_train_pred_nb))\n", "print(\"Naïve Bayes - Testing Accuracy:\", accuracy_score(y_test, y_test_pred_nb))\n", "\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_test_pred_nb))\n", "\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_test_pred_nb))\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "OzvmiNZ9loor", "outputId": "c340cc2e-0e89-47d2-eaff-9da23a7f6dd4" }, "execution_count": 59, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Naïve Bayes - Training Accuracy: 0.752442996742671\n", "Naïve Bayes - Testing 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" ] } ] }, { "cell_type": "code", "source": [ "print(\"SVM Linear Kernel - Training Accuracy:\", accuracy_score(y_train, y_train_pred_svm_linear))\n", "print(\"SVM Linear Kernel - Testing Accuracy:\", accuracy_score(y_test, y_test_pred_svm_linear))\n", "\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_test_pred_svm_linear))\n", "\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_test_pred_svm_linear))\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "iUbvwz8Ylp8T", "outputId": "c216b894-a720-492b-f555-8ea5df9bd59b" }, "execution_count": 60, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "SVM Linear Kernel - Training Accuracy: 0.7736156351791531\n", "SVM Linear Kernel - Testing Accuracy: 0.7662337662337663\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.82 0.82 0.82 99\n", " 1 0.67 0.67 0.67 55\n", "\n", " accuracy 0.77 154\n", " macro avg 0.75 0.75 0.75 154\n", "weighted avg 0.77 0.77 0.77 154\n", "\n", "\n", "Confusion Matrix:\n", "[[81 18]\n", " [18 37]]\n" ] } ] }, { "cell_type": "code", "source": [ "# SVM with RBF kernel\n", "svm_rbf = SVC(kernel='rbf')\n", "svm_rbf.fit(X_train, y_train)\n", "\n", "# Predict on test data\n", "y_train_pred_svm_rbf = svm_rbf.predict(X_train)\n", "y_test_pred_svm_rbf = svm_rbf.predict(X_test)\n" ], "metadata": { "id": "yPvrwUhFmJXL" }, "execution_count": 61, "outputs": [] }, { "cell_type": "code", "source": [ "print(\"SVM RBF Kernel - Training Accuracy:\", accuracy_score(y_train, y_train_pred_svm_rbf))\n", "print(\"SVM RBF Kernel - Testing Accuracy:\", accuracy_score(y_test, y_test_pred_svm_rbf))\n", "\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_test_pred_svm_rbf))\n", "\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_test_pred_svm_rbf))\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "yzMg3dm4lxBj", "outputId": "8d4150dc-bc93-4329-db37-15d11133ac7d" }, "execution_count": 62, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "SVM RBF Kernel - Training Accuracy: 0.744299674267101\n", "SVM RBF Kernel - Testing 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" ] } ] } ] }