{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "b0b3d976-4364-4dd6-be0b-92029da02a1b", "metadata": {}, "outputs": [], "source": [ "#import libraries\n", "import pandas as pd\n", "import numpy as np\n", "\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.naive_bayes import GaussianNB\n", "from sklearn.decomposition import PCA\n", "from sklearn.preprocessing import StandardScaler\n", "\n", "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\n" ] }, { "cell_type": "code", "execution_count": 2, "id": "3cf136e0-2e7b-4c62-a5de-f4c034f4db34", "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": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#load dataset\n", "# Load Diabetes dataset\n", "df = pd.read_csv(\"diabetes.csv\")\n", "\n", "# Display first rows\n", "df.head()\n" ] }, { "cell_type": "code", "execution_count": 3, "id": "bf5ab28d-361b-4a6f-bb82-10bbc86662bc", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 768 entries, 0 to 767\n", "Data columns (total 10 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 PatientId 768 non-null int64 \n", " 1 Pregnancies 768 non-null int64 \n", " 2 Glucose 768 non-null int64 \n", " 3 BloodPressure 768 non-null int64 \n", " 4 SkinThickness 768 non-null int64 \n", " 5 Insulin 768 non-null int64 \n", " 6 BMI 768 non-null float64\n", " 7 DiabetesPedigreeFunction 768 non-null float64\n", " 8 Age 768 non-null int64 \n", " 9 Outcome 768 non-null int64 \n", "dtypes: float64(2), int64(8)\n", "memory usage: 60.1 KB\n" ] } ], "source": [ "# Check basic information\n", "df.info()\n" ] }, { "cell_type": "code", "execution_count": 4, "id": "61943fd3-c3bc-4b75-9df5-0eb08957af4c", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "PatientId 0\n", "Pregnancies 0\n", "Glucose 0\n", "BloodPressure 0\n", "SkinThickness 0\n", "Insulin 0\n", "BMI 0\n", "DiabetesPedigreeFunction 0\n", "Age 0\n", "Outcome 0\n", "dtype: int64" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Check missing values\n", "df.isnull().sum()\n" ] }, { "cell_type": "code", "execution_count": 5, "id": "05c484b5-d485-46da-82b7-faa35d9b7b43", "metadata": {}, "outputs": [], "source": [ "#split features and target\n", "\n", "X = df.drop(\"Outcome\", axis=1)\n", "y = df[\"Outcome\"]\n" ] }, { "cell_type": "code", "execution_count": 7, "id": "650fa64e-3488-4779-8000-b31cb75298b5", "metadata": {}, "outputs": [], "source": [ "#train-test split\n", "X_train, X_test, y_train, y_test = train_test_split(\n", " X, y, test_size=0.2, random_state=42\n", ")\n" ] }, { "cell_type": "code", "execution_count": 9, "id": "896494cb-6075-4a65-8d13-6896cec394fa", "metadata": {}, "outputs": [], "source": [ "#PART 1: Random Forest Classifier\n", "#Random Forest\n", "\n", "rf = RandomForestClassifier(random_state=42)\n", "rf.fit(X_train, y_train)\n", "\n", "y_pred_rf = rf.predict(X_test)\n" ] }, { "cell_type": "code", "execution_count": 10, "id": "867b37c2-8ed9-4d32-a675-f094159fc1e9", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'Accuracy': 0.7532467532467533,\n", " 'Precision': 0.6440677966101694,\n", " 'Recall': 0.6909090909090909,\n", " 'F1-score': 0.6666666666666665}" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rf_results = {\n", " \"Accuracy\": accuracy_score(y_test, y_pred_rf),\n", " \"Precision\": precision_score(y_test, y_pred_rf),\n", " \"Recall\": recall_score(y_test, y_pred_rf),\n", " \"F1-score\": f1_score(y_test, y_pred_rf)\n", "}\n", "\n", "rf_results\n" ] }, { "cell_type": "code", "execution_count": 11, "id": "debcd430-0caa-435f-8782-e0c24628c486", "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", "
FeatureImportance
2Glucose0.267089
6BMI0.153334
8Age0.129185
7DiabetesPedigreeFunction0.102934
0PatientId0.090048
3BloodPressure0.075748
1Pregnancies0.065340
5Insulin0.060622
4SkinThickness0.055700
\n", "
" ], "text/plain": [ " 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" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#Manual Feature Selection using Feature Importance\n", "# Get feature importances\n", "importances = rf.feature_importances_\n", "\n", "feature_importance_df = pd.DataFrame({\n", " \"Feature\": X.columns,\n", " \"Importance\": importances\n", "}).sort_values(by=\"Importance\", ascending=False)\n", "\n", "feature_importance_df\n" ] }, { "cell_type": "code", "execution_count": 13, "id": "87165ef9-b106-4ec7-a75f-ce4bbcd17d33", "metadata": {}, "outputs": [], "source": [ "top_features = feature_importance_df[\"Feature\"].head(5).values\n", "\n", "X_train_top = X_train[top_features]\n", "X_test_top = X_test[top_features]\n" ] }, { "cell_type": "code", "execution_count": 14, "id": "c361f9f2-5b81-4a6f-bf02-3e4394c8c752", "metadata": {}, "outputs": [], "source": [ "rf_top = RandomForestClassifier(random_state=42)\n", "rf_top.fit(X_train_top, y_train)\n", "\n", "y_pred_rf_top = rf_top.predict(X_test_top)\n" ] }, { "cell_type": "code", "execution_count": 15, "id": "13a2d9ad-1288-49b9-a5b4-5631ddfaaf1c", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'Accuracy': 0.7727272727272727,\n", " 'Precision': 0.6785714285714286,\n", " 'Recall': 0.6909090909090909,\n", " 'F1-score': 0.6846846846846847}" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rf_top_results = {\n", " \"Accuracy\": accuracy_score(y_test, y_pred_rf_top),\n", " \"Precision\": precision_score(y_test, y_pred_rf_top),\n", " \"Recall\": recall_score(y_test, y_pred_rf_top),\n", " \"F1-score\": f1_score(y_test, y_pred_rf_top)\n", "}\n", "\n", "rf_top_results\n" ] }, { "cell_type": "code", "execution_count": 16, "id": "d2df04dd-dee5-45eb-aa6c-ba3f788391d6", "metadata": {}, "outputs": [], "source": [ "#Feature Selection using PCA\n", "#Standardize Data\n", "scaler = StandardScaler()\n", "X_scaled = scaler.fit_transform(X)\n" ] }, { "cell_type": "code", "execution_count": 17, "id": "717f9507-96c0-43c5-98f4-66fe859da6bb", "metadata": {}, "outputs": [], "source": [ "#Apply PCA\n", "pca = PCA(n_components=5)\n", "X_pca = pca.fit_transform(X_scaled)\n" ] }, { "cell_type": "code", "execution_count": 18, "id": "f0311870-b352-45a7-819b-271389faf3e2", "metadata": {}, "outputs": [], "source": [ "X_train_pca, X_test_pca, y_train_pca, y_test_pca = train_test_split(\n", " X_pca, y, test_size=0.2, random_state=42\n", ")\n" ] }, { "cell_type": "code", "execution_count": 19, "id": "e89ac73e-feea-4afd-9b5b-11de7f42cbe6", "metadata": {}, "outputs": [], "source": [ "rf_pca = RandomForestClassifier(random_state=42)\n", "rf_pca.fit(X_train_pca, y_train_pca)\n", "\n", "y_pred_rf_pca = rf_pca.predict(X_test_pca)\n" ] }, { "cell_type": "code", "execution_count": 20, "id": "1d178683-990b-43ae-835e-34e519fc3bac", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'Accuracy': 0.6688311688311688,\n", " 'Precision': 0.54,\n", " 'Recall': 0.4909090909090909,\n", " 'F1-score': 0.5142857142857142}" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rf_pca_results = {\n", " \"Accuracy\": accuracy_score(y_test_pca, y_pred_rf_pca),\n", " \"Precision\": precision_score(y_test_pca, y_pred_rf_pca),\n", " \"Recall\": recall_score(y_test_pca, y_pred_rf_pca),\n", " \"F1-score\": f1_score(y_test_pca, y_pred_rf_pca)\n", "}\n", "\n", "rf_pca_results\n" ] }, { "cell_type": "code", "execution_count": 21, "id": "7fad4bfe-6388-4b6c-966d-385cdd03cae5", "metadata": {}, "outputs": [], "source": [ "#PART 2: Comparing with Other Classifiers\n", "#Logistic Regression\n", "lr = LogisticRegression(max_iter=1000)\n", "lr.fit(X_train, y_train)\n", "\n", "y_pred_lr = lr.predict(X_test)\n" ] }, { "cell_type": "code", "execution_count": 22, "id": "afb395e6-9038-48fd-b9ea-a3bf4ff484a3", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'Accuracy': 0.7532467532467533,\n", " 'Precision': 0.6491228070175439,\n", " 'Recall': 0.6727272727272727,\n", " 'F1-score': 0.6607142857142858}" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "lr_results = {\n", " \"Accuracy\": accuracy_score(y_test, y_pred_lr),\n", " \"Precision\": precision_score(y_test, y_pred_lr),\n", " \"Recall\": recall_score(y_test, y_pred_lr),\n", " \"F1-score\": f1_score(y_test, y_pred_lr)\n", "}\n", "\n", "lr_results\n" ] }, { "cell_type": "code", "execution_count": 23, "id": "78d3066d-6929-473e-aa46-4876dbce112c", "metadata": {}, "outputs": [], "source": [ "#Naive Bayes\n", "nb = GaussianNB()\n", "nb.fit(X_train, y_train)\n", "\n", "y_pred_nb = nb.predict(X_test)\n" ] }, { "cell_type": "code", "execution_count": 24, "id": "f0db597e-3721-4db9-a95d-55b84d87d794", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'Accuracy': 0.7597402597402597,\n", " 'Precision': 0.65,\n", " 'Recall': 0.7090909090909091,\n", " 'F1-score': 0.6782608695652174}" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "nb_results = {\n", " \"Accuracy\": accuracy_score(y_test, y_pred_nb),\n", " \"Precision\": precision_score(y_test, y_pred_nb),\n", " \"Recall\": recall_score(y_test, y_pred_nb),\n", " \"F1-score\": f1_score(y_test, y_pred_nb)\n", "}\n", "\n", "nb_results\n" ] }, { "cell_type": "code", "execution_count": 26, "id": "695fd3ad-e932-4a4b-a244-4c33ed8fd679", "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", "
ModelAccuracyPrecisionRecallF1-score
0Random Forest (Original)0.7532470.6440680.6909090.666667
1Random Forest (Top Features)0.7727270.6785710.6909090.684685
2Random Forest (PCA)0.6688310.5400000.4909090.514286
3Logistic Regression0.7532470.6491230.6727270.660714
4Naïve Bayes0.7597400.6500000.7090910.678261
\n", "
" ], "text/plain": [ " 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) 0.668831 0.540000 0.490909 0.514286\n", "3 Logistic Regression 0.753247 0.649123 0.672727 0.660714\n", "4 Naïve Bayes 0.759740 0.650000 0.709091 0.678261" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#Final Model Comparison Table\n", "results_df = pd.DataFrame({\n", " \"Model\": [\n", " \"Random Forest (Original)\",\n", " \"Random Forest (Top Features)\",\n", " \"Random Forest (PCA)\",\n", " \"Logistic Regression\",\n", " \"Naïve Bayes\"\n", " ],\n", " \"Accuracy\": [\n", " rf_results[\"Accuracy\"],\n", " rf_top_results[\"Accuracy\"],\n", " rf_pca_results[\"Accuracy\"],\n", " lr_results[\"Accuracy\"],\n", " nb_results[\"Accuracy\"]\n", " ],\n", " \"Precision\": [\n", " rf_results[\"Precision\"],\n", " rf_top_results[\"Precision\"],\n", " rf_pca_results[\"Precision\"],\n", " lr_results[\"Precision\"],\n", " nb_results[\"Precision\"]\n", " ],\n", " \"Recall\": [\n", " rf_results[\"Recall\"],\n", " rf_top_results[\"Recall\"],\n", " rf_pca_results[\"Recall\"],\n", " lr_results[\"Recall\"],\n", " nb_results[\"Recall\"]\n", " ],\n", " \"F1-score\": [\n", " rf_results[\"F1-score\"],\n", " rf_top_results[\"F1-score\"],\n", " rf_pca_results[\"F1-score\"],\n", " lr_results[\"F1-score\"],\n", " nb_results[\"F1-score\"]\n", " ]\n", "})\n", "\n", "results_df\n" ] }, { "cell_type": "code", "execution_count": null, "id": "e26b2a93-bd7d-4a5c-b425-a025f4b88edd", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "anaconda-panel-2023.05-py310", "language": "python", "name": "conda-env-anaconda-panel-2023.05-py310-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": "3.11.5" } }, "nbformat": 4, "nbformat_minor": 5 }