{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "0e8fac55-1f1a-4ea8-b26b-e2465839ef43",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\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.metrics import accuracy_score, precision_score, recall_score, f1_score, classification_report\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "170894c7-25d8-429d-9c12-6b839fea832b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " Dataset loaded successfully!\n",
      "\n",
      "   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  \n",
      "\n",
      "Shape of dataset: (768, 10)\n",
      "\n",
      "Missing values:\n",
      " 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\n"
     ]
    }
   ],
   "source": [
    "df = pd.read_csv('diabetes.csv')\n",
    "print(\" Dataset loaded successfully!\\n\")\n",
    "print(df.head())\n",
    "print(\"\\nShape of dataset:\", df.shape)\n",
    "print(\"\\nMissing values:\\n\", df.isnull().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "1bb24d71-631a-45cc-b094-98dc3a597d90",
   "metadata": {},
   "outputs": [],
   "source": [
    "cols_with_zero = ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI']\n",
    "for col in cols_with_zero:\n",
    "    df[col] = df[col].replace(0, df[col].median())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "c0777b63-1c1b-4b04-b2ea-f9dba091fa60",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Data split completed!\n"
     ]
    }
   ],
   "source": [
    "X = df.drop('Outcome', axis=1)\n",
    "y = df['Outcome']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)\n",
    "print(\"\\nData split completed!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c8441c9d-0e1d-4411-b443-530a46717e2c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Random Forest (All Features) Performance:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.76      0.84      0.80       100\n",
      "           1       0.64      0.52      0.57        54\n",
      "\n",
      "    accuracy                           0.73       154\n",
      "   macro avg       0.70      0.68      0.69       154\n",
      "weighted avg       0.72      0.73      0.72       154\n",
      "\n"
     ]
    }
   ],
   "source": [
    "rf = RandomForestClassifier(random_state=42)\n",
    "rf.fit(X_train, y_train)\n",
    "y_pred_rf = rf.predict(X_test)\n",
    "\n",
    "print(\"\\n Random Forest (All Features) Performance:\")\n",
    "print(classification_report(y_test, y_pred_rf))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e6b3ef5e-8e37-4026-8f98-9d1ac720cd7f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Feature Importance:\n",
      "                     Feature  Importance\n",
      "2                   Glucose    0.286160\n",
      "6                       BMI    0.148742\n",
      "7  DiabetesPedigreeFunction    0.114694\n",
      "8                       Age    0.107017\n",
      "0                 PatientId    0.086523\n",
      "1               Pregnancies    0.075259\n",
      "3             BloodPressure    0.064672\n",
      "5                   Insulin    0.058589\n",
      "4             SkinThickness    0.058345\n"
     ]
    }
   ],
   "source": [
    "importances = rf.feature_importances_\n",
    "feature_names = X.columns\n",
    "feat_imp = pd.DataFrame({'Feature': feature_names, 'Importance': importances})\n",
    "feat_imp = feat_imp.sort_values(by='Importance', ascending=False)\n",
    "\n",
    "print(\"\\n Feature Importance:\\n\", feat_imp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "20fc048f-d9ad-48a3-876c-6a32c39a47aa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,5))\n",
    "sns.barplot(x='Importance', y='Feature', data=feat_imp)\n",
    "plt.title('Feature Importance - Random Forest')\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "95aa2314-483f-4dbf-b8c8-caa5c1082334",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Random Forest (Top 5 Features) Performance:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.79      0.85      0.82       100\n",
      "           1       0.67      0.57      0.62        54\n",
      "\n",
      "    accuracy                           0.75       154\n",
      "   macro avg       0.73      0.71      0.72       154\n",
      "weighted avg       0.75      0.75      0.75       154\n",
      "\n"
     ]
    }
   ],
   "source": [
    "top_features = feat_imp['Feature'].head(5).tolist()\n",
    "X_train_top = X_train[top_features]\n",
    "X_test_top = X_test[top_features]\n",
    "\n",
    "rf_top = RandomForestClassifier(random_state=42)\n",
    "rf_top.fit(X_train_top, y_train)\n",
    "y_pred_rf_top = rf_top.predict(X_test_top)\n",
    "\n",
    "print(\"\\n Random Forest (Top 5 Features) Performance:\")\n",
    "print(classification_report(y_test, y_pred_rf_top))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "1a830f83-9822-4037-95c1-8ebd64aff35a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Random Forest (PCA Reduced) Performance:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.73      0.82      0.77       100\n",
      "           1       0.57      0.44      0.50        54\n",
      "\n",
      "    accuracy                           0.69       154\n",
      "   macro avg       0.65      0.63      0.64       154\n",
      "weighted avg       0.68      0.69      0.68       154\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pca = PCA(n_components=5)\n",
    "X_train_pca = pca.fit_transform(X_train)\n",
    "X_test_pca = pca.transform(X_test)\n",
    "\n",
    "rf_pca = RandomForestClassifier(random_state=42)\n",
    "rf_pca.fit(X_train_pca, y_train)\n",
    "y_pred_rf_pca = rf_pca.predict(X_test_pca)\n",
    "\n",
    "print(\"\\n Random Forest (PCA Reduced) Performance:\")\n",
    "print(classification_report(y_test, y_pred_rf_pca))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "55a1213d-7b68-4fd3-9d98-88e71ee19171",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Logistic Regression Performance:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.76      0.81      0.78       100\n",
      "           1       0.60      0.52      0.55        54\n",
      "\n",
      "    accuracy                           0.71       154\n",
      "   macro avg       0.68      0.66      0.67       154\n",
      "weighted avg       0.70      0.71      0.70       154\n",
      "\n"
     ]
    }
   ],
   "source": [
    "log_reg = LogisticRegression(max_iter=500)\n",
    "log_reg.fit(X_train, y_train)\n",
    "y_pred_lr = log_reg.predict(X_test)\n",
    "\n",
    "print(\"\\n Logistic Regression Performance:\")\n",
    "print(classification_report(y_test, y_pred_lr))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "a6db5f66-2561-4786-ac87-008b352bd555",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Naïve Bayes Performance:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.78      0.75      0.77       100\n",
      "           1       0.57      0.61      0.59        54\n",
      "\n",
      "    accuracy                           0.70       154\n",
      "   macro avg       0.68      0.68      0.68       154\n",
      "weighted avg       0.71      0.70      0.70       154\n",
      "\n"
     ]
    }
   ],
   "source": [
    "nb = GaussianNB()\n",
    "nb.fit(X_train, y_train)\n",
    "y_pred_nb = nb.predict(X_test)\n",
    "\n",
    "print(\"\\n Naïve Bayes Performance:\")\n",
    "print(classification_report(y_test, y_pred_nb))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "aae8fabd-75b0-4885-a544-7b1a388e5869",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "📊 Model Comparison Table:\n",
      "\n",
      "                            Model  Accuracy  Precision    Recall  F1-Score\n",
      "0    Random Forest (All Features)  0.727273   0.636364  0.518519  0.571429\n",
      "1  Random Forest (Top 5 Features)  0.753247   0.673913  0.574074  0.620000\n",
      "2             Random Forest (PCA)  0.688312   0.571429  0.444444  0.500000\n",
      "3             Logistic Regression  0.707792   0.595745  0.518519  0.554455\n",
      "4                     Naive Bayes  0.701299   0.568966  0.611111  0.589286\n"
     ]
    }
   ],
   "source": [
    "def get_metrics(y_true, y_pred, model_name):\n",
    "    return {\n",
    "        'Model': model_name,\n",
    "        'Accuracy': accuracy_score(y_true, y_pred),\n",
    "        'Precision': precision_score(y_true, y_pred),\n",
    "        'Recall': recall_score(y_true, y_pred),\n",
    "        'F1-Score': f1_score(y_true, y_pred)\n",
    "    }\n",
    "\n",
    "results = []\n",
    "results.append(get_metrics(y_test, y_pred_rf, 'Random Forest (All Features)'))\n",
    "results.append(get_metrics(y_test, y_pred_rf_top, 'Random Forest (Top 5 Features)'))\n",
    "results.append(get_metrics(y_test, y_pred_rf_pca, 'Random Forest (PCA)'))\n",
    "results.append(get_metrics(y_test, y_pred_lr, 'Logistic Regression'))\n",
    "results.append(get_metrics(y_test, y_pred_nb, 'Naive Bayes'))\n",
    "\n",
    "results_df = pd.DataFrame(results)\n",
    "print(\"\\n📊 Model Comparison Table:\\n\")\n",
    "print(results_df)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "2db0b13b-fbe6-44e6-819f-6ba926e18d6c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 1000x600 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,6))\n",
    "results_df.set_index('Model')[['Accuracy','Precision','Recall','F1-Score']].plot(kind='bar', figsize=(12,6))\n",
    "plt.title('Model Performance Comparison')\n",
    "plt.ylabel('Score')\n",
    "plt.ylim(0,1)\n",
    "plt.xticks(rotation=45)\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "anaconda-2024.02-py310",
   "language": "python",
   "name": "conda-env-anaconda-2024.02-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": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}