{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "406a1ecf-338a-4c4e-af17-f1a5f93f5faf",
   "metadata": {},
   "source": [
    "# Diabetes: Feature Selection & Model Comparison\n",
    "**Objectives**\n",
    "- Train Random Forest on diabetes.csv\n",
    "- Manual feature selection using Random Forest importance\n",
    "- PCA dimensionality reduction\n",
    "- Train Logistic Regression and GaussianNB\n",
    "- Evaluate all models with accuracy, precision, recall, F1-score\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a9fbca66-cb82-457b-b135-05914b8eb8b9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Requirements (run in your environment if needed)\n",
    "# pip install pandas numpy scikit-learn matplotlib seaborn\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e84ad112-afc8-49de-99cc-4f5d67b62c57",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Imports and global config\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score\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",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, classification_report, confusion_matrix\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "RANDOM_STATE = 42\n",
    "np.random.seed(RANDOM_STATE)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "a87b7b66-38cc-48fd-8752-b3fcac58c90a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PatientId</th>\n",
       "      <th>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "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": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 1) Load dataset\n",
    "# Update path if needed\n",
    "df = pd.read_csv('diabetes.csv')\n",
    "df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "b5c11351-368a-45e8-8625-42cc448169d8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(768, 10)\n",
      "<class 'pandas.core.frame.DataFrame'>\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"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>PatientId</th>\n",
       "      <td>768.0</td>\n",
       "      <td>384.500000</td>\n",
       "      <td>221.846794</td>\n",
       "      <td>1.000</td>\n",
       "      <td>192.75000</td>\n",
       "      <td>384.5000</td>\n",
       "      <td>576.25000</td>\n",
       "      <td>768.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Pregnancies</th>\n",
       "      <td>768.0</td>\n",
       "      <td>3.845052</td>\n",
       "      <td>3.369578</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1.00000</td>\n",
       "      <td>3.0000</td>\n",
       "      <td>6.00000</td>\n",
       "      <td>17.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Glucose</th>\n",
       "      <td>768.0</td>\n",
       "      <td>120.894531</td>\n",
       "      <td>31.972618</td>\n",
       "      <td>0.000</td>\n",
       "      <td>99.00000</td>\n",
       "      <td>117.0000</td>\n",
       "      <td>140.25000</td>\n",
       "      <td>199.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BloodPressure</th>\n",
       "      <td>768.0</td>\n",
       "      <td>69.105469</td>\n",
       "      <td>19.355807</td>\n",
       "      <td>0.000</td>\n",
       "      <td>62.00000</td>\n",
       "      <td>72.0000</td>\n",
       "      <td>80.00000</td>\n",
       "      <td>122.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SkinThickness</th>\n",
       "      <td>768.0</td>\n",
       "      <td>20.536458</td>\n",
       "      <td>15.952218</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>23.0000</td>\n",
       "      <td>32.00000</td>\n",
       "      <td>99.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Insulin</th>\n",
       "      <td>768.0</td>\n",
       "      <td>79.799479</td>\n",
       "      <td>115.244002</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>30.5000</td>\n",
       "      <td>127.25000</td>\n",
       "      <td>846.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BMI</th>\n",
       "      <td>768.0</td>\n",
       "      <td>31.992578</td>\n",
       "      <td>7.884160</td>\n",
       "      <td>0.000</td>\n",
       "      <td>27.30000</td>\n",
       "      <td>32.0000</td>\n",
       "      <td>36.60000</td>\n",
       "      <td>67.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <td>768.0</td>\n",
       "      <td>0.471876</td>\n",
       "      <td>0.331329</td>\n",
       "      <td>0.078</td>\n",
       "      <td>0.24375</td>\n",
       "      <td>0.3725</td>\n",
       "      <td>0.62625</td>\n",
       "      <td>2.42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>768.0</td>\n",
       "      <td>33.240885</td>\n",
       "      <td>11.760232</td>\n",
       "      <td>21.000</td>\n",
       "      <td>24.00000</td>\n",
       "      <td>29.0000</td>\n",
       "      <td>41.00000</td>\n",
       "      <td>81.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Outcome</th>\n",
       "      <td>768.0</td>\n",
       "      <td>0.348958</td>\n",
       "      <td>0.476951</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1.00000</td>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          count        mean         std     min        25%  \\\n",
       "PatientId                 768.0  384.500000  221.846794   1.000  192.75000   \n",
       "Pregnancies               768.0    3.845052    3.369578   0.000    1.00000   \n",
       "Glucose                   768.0  120.894531   31.972618   0.000   99.00000   \n",
       "BloodPressure             768.0   69.105469   19.355807   0.000   62.00000   \n",
       "SkinThickness             768.0   20.536458   15.952218   0.000    0.00000   \n",
       "Insulin                   768.0   79.799479  115.244002   0.000    0.00000   \n",
       "BMI                       768.0   31.992578    7.884160   0.000   27.30000   \n",
       "DiabetesPedigreeFunction  768.0    0.471876    0.331329   0.078    0.24375   \n",
       "Age                       768.0   33.240885   11.760232  21.000   24.00000   \n",
       "Outcome                   768.0    0.348958    0.476951   0.000    0.00000   \n",
       "\n",
       "                               50%        75%     max  \n",
       "PatientId                 384.5000  576.25000  768.00  \n",
       "Pregnancies                 3.0000    6.00000   17.00  \n",
       "Glucose                   117.0000  140.25000  199.00  \n",
       "BloodPressure              72.0000   80.00000  122.00  \n",
       "SkinThickness              23.0000   32.00000   99.00  \n",
       "Insulin                    30.5000  127.25000  846.00  \n",
       "BMI                        32.0000   36.60000   67.10  \n",
       "DiabetesPedigreeFunction    0.3725    0.62625    2.42  \n",
       "Age                        29.0000   41.00000   81.00  \n",
       "Outcome                     0.0000    1.00000    1.00  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Quick dataset info\n",
    "print(df.shape)\n",
    "df.info()\n",
    "df.describe().T\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "029b0eb4-9344-4234-ac25-ca7a1b07cdfc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Glucose            5\n",
       "BloodPressure     35\n",
       "SkinThickness    227\n",
       "Insulin          374\n",
       "BMI               11\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Typical Diabetes dataset columns (Pima Indians Diabetes):\n",
    "# ['Pregnancies','Glucose','BloodPressure','SkinThickness','Insulin','BMI','DiabetesPedigreeFunction','Age','Outcome']\n",
    "# Check for missing values coded as zeros (common issue for some columns)\n",
    "zero_as_missing_cols = ['Glucose','BloodPressure','SkinThickness','Insulin','BMI']\n",
    "(df[zero_as_missing_cols] == 0).sum()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d3f5e7f8-b01f-485a-8935-a894607bffdd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Filled missing in Glucose with median=117.0\n",
      "Filled missing in BloodPressure with median=72.0\n",
      "Filled missing in SkinThickness with median=29.0\n",
      "Filled missing in Insulin with median=125.0\n",
      "Filled missing in BMI with median=32.3\n"
     ]
    },
    {
     "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": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 2) Preprocessing:\n",
    "# Replace zeros in medically impossible columns with NaN, then impute (median)\n",
    "df_clean = df.copy()\n",
    "for col in zero_as_missing_cols:\n",
    "    df_clean[col] = df_clean[col].replace(0, np.nan)\n",
    "\n",
    "# Impute with median (robust for skew)\n",
    "for col in zero_as_missing_cols:\n",
    "    med = df_clean[col].median()\n",
    "    df_clean[col] = df_clean[col].fillna(med)\n",
    "    print(f'Filled missing in {col} with median={med}')\n",
    "    \n",
    "# Confirm no remaining missing\n",
    "df_clean.isna().sum()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "15da9456-99a7-4473-ba53-1d8134d48778",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((768, 9),\n",
       " (768,),\n",
       " Outcome\n",
       " 0    500\n",
       " 1    268\n",
       " Name: count, dtype: int64)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Feature / target split\n",
    "X = df_clean.drop(columns=['Outcome'])\n",
    "y = df_clean['Outcome']\n",
    "X.shape, y.shape, y.value_counts()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d4ceffed-40c4-4bcf-8c6d-feb2decc91c0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(576, 9) (192, 9) Outcome\n",
      "0    0.651042\n",
      "1    0.348958\n",
      "Name: proportion, dtype: float64 Outcome\n",
      "0    0.651042\n",
      "1    0.348958\n",
      "Name: proportion, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "# Train/test split (stratify to keep class balance)\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.25, random_state=RANDOM_STATE, stratify=y)\n",
    "\n",
    "print(X_train.shape, X_test.shape, y_train.value_counts(normalize=True), y_test.value_counts(normalize=True))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e72287d6-5af1-4d59-9550-86b08a26712e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'accuracy': 0.7447916666666666,\n",
       " 'precision': 0.68,\n",
       " 'recall': 0.5074626865671642,\n",
       " 'f1': 0.5811965811965812}"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 3) Baseline Random Forest (no scaling required but we will keep consistent pipeline)\n",
    "rf = RandomForestClassifier(n_estimators=200, random_state=RANDOM_STATE)\n",
    "rf.fit(X_train, y_train)\n",
    "\n",
    "# Predictions\n",
    "y_pred_rf = rf.predict(X_test)\n",
    "\n",
    "# Evaluate\n",
    "def eval_metrics(y_true, y_pred, pos_label=1):\n",
    "    return {\n",
    "        'accuracy': accuracy_score(y_true, y_pred),\n",
    "        'precision': precision_score(y_true, y_pred, zero_division=0),\n",
    "        'recall': recall_score(y_true, y_pred, zero_division=0),\n",
    "        'f1': f1_score(y_true, y_pred, zero_division=0)\n",
    "    }\n",
    "\n",
    "baseline_metrics = eval_metrics(y_test, y_pred_rf)\n",
    "baseline_metrics\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "6ec2790e-2280-4f7d-964e-0d08f9a63c98",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Random Forest - classification report\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.77      0.87      0.82       125\n",
      "           1       0.68      0.51      0.58        67\n",
      "\n",
      "    accuracy                           0.74       192\n",
      "   macro avg       0.72      0.69      0.70       192\n",
      "weighted avg       0.74      0.74      0.73       192\n",
      "\n",
      "Confusion Matrix:\n",
      "[[109  16]\n",
      " [ 33  34]]\n"
     ]
    }
   ],
   "source": [
    "# Print classification report and confusion matrix\n",
    "print('Random Forest - classification report')\n",
    "print(classification_report(y_test, y_pred_rf))\n",
    "print('Confusion Matrix:')\n",
    "print(confusion_matrix(y_test, y_pred_rf))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "cf162bed-2b27-4db6-b7d9-3104aadb3f10",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Glucose                     0.281562\n",
       "BMI                         0.143892\n",
       "Age                         0.111680\n",
       "DiabetesPedigreeFunction    0.107287\n",
       "PatientId                   0.088247\n",
       "Insulin                     0.077022\n",
       "Pregnancies                 0.067935\n",
       "BloodPressure               0.064632\n",
       "SkinThickness               0.057744\n",
       "dtype: float64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Feature importances from Random Forest\n",
    "feat_importances = pd.Series(rf.feature_importances_, index=X.columns).sort_values(ascending=False)\n",
    "feat_importances\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "1dd6e8f5-9071-4171-817c-5dcd6c0ab7f3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot feature importances\n",
    "plt.figure(figsize=(8,5))\n",
    "sns.barplot(x=feat_importances.values, y=feat_importances.index)\n",
    "plt.title('Random Forest Feature Importances')\n",
    "plt.xlabel('Importance')\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "c1b0a632-ab0b-4a8d-ab83-bf640d60867b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Top features: ['Glucose', 'BMI', 'Age', 'DiabetesPedigreeFunction', 'PatientId']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'accuracy': 0.7604166666666666,\n",
       " 'precision': 0.6909090909090909,\n",
       " 'recall': 0.5671641791044776,\n",
       " 'f1': 0.6229508196721312}"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 4) Manual selection: pick top N features (e.g., top 5)\n",
    "N = 5\n",
    "topN = feat_importances.head(N).index.tolist()\n",
    "print('Top features:', topN)\n",
    "\n",
    "X_train_top = X_train[topN]\n",
    "X_test_top = X_test[topN]\n",
    "\n",
    "rf_top = RandomForestClassifier(n_estimators=200, random_state=RANDOM_STATE)\n",
    "rf_top.fit(X_train_top, y_train)\n",
    "y_pred_rf_top = rf_top.predict(X_test_top)\n",
    "metrics_rf_top = eval_metrics(y_test, y_pred_rf_top)\n",
    "metrics_rf_top\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "f8314ed6-9a5d-4717-9c51-3f2ee29938dc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>accuracy</th>\n",
       "      <th>precision</th>\n",
       "      <th>recall</th>\n",
       "      <th>f1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>RF_all_features</th>\n",
       "      <td>0.744792</td>\n",
       "      <td>0.680000</td>\n",
       "      <td>0.507463</td>\n",
       "      <td>0.581197</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RF_top_5</th>\n",
       "      <td>0.760417</td>\n",
       "      <td>0.690909</td>\n",
       "      <td>0.567164</td>\n",
       "      <td>0.622951</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 accuracy  precision    recall        f1\n",
       "RF_all_features  0.744792   0.680000  0.507463  0.581197\n",
       "RF_top_5         0.760417   0.690909  0.567164  0.622951"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Compare baseline vs top-N metrics\n",
    "pd.DataFrame([baseline_metrics, metrics_rf_top], index=['RF_all_features','RF_top_'+str(N)])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "c7dd7cc1-abda-4e6e-99fc-b03bdb615e97",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Original feature count: 9\n",
      "PCA components retained: 8\n",
      "Explained variance ratio (sum): 0.9565689073382125\n"
     ]
    }
   ],
   "source": [
    "# 5) PCA for dimensionality reduction\n",
    "# Standardize features first (PCA is sensitive to scale).\n",
    "scaler = StandardScaler()\n",
    "X_train_scaled = scaler.fit_transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "# PCA retaining 95% variance (alternate: specify n_components)\n",
    "pca = PCA(n_components=0.95, random_state=RANDOM_STATE)\n",
    "X_train_pca = pca.fit_transform(X_train_scaled)\n",
    "X_test_pca = pca.transform(X_test_scaled)\n",
    "\n",
    "print('Original feature count:', X_train.shape[1])\n",
    "print('PCA components retained:', X_train_pca.shape[1])\n",
    "print('Explained variance ratio (sum):', pca.explained_variance_ratio_.sum())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "dc936158-06c8-474e-b91a-8d5d0d01bd7f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot explained variance by component\n",
    "plt.figure(figsize=(8,4))\n",
    "explained = pca.explained_variance_ratio_\n",
    "plt.plot(np.cumsum(explained), marker='o')\n",
    "plt.xlabel('Number of components')\n",
    "plt.ylabel('Cumulative explained variance')\n",
    "plt.title('PCA cumulative explained variance (after scaling)')\n",
    "plt.grid(True)\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "d53e32b1-282e-4604-b986-50e2c4690c74",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'accuracy': 0.703125,\n",
       " 'precision': 0.5757575757575758,\n",
       " 'recall': 0.5671641791044776,\n",
       " 'f1': 0.5714285714285714}"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Train Random Forest on PCA features\n",
    "rf_pca = RandomForestClassifier(n_estimators=200, random_state=RANDOM_STATE)\n",
    "rf_pca.fit(X_train_pca, y_train)\n",
    "y_pred_rf_pca = rf_pca.predict(X_test_pca)\n",
    "metrics_rf_pca = eval_metrics(y_test, y_pred_rf_pca)\n",
    "metrics_rf_pca\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "22d11eae-0a7d-4303-b650-6435fc21796f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "({'accuracy': 0.7239583333333334,\n",
       "  'precision': 0.6296296296296297,\n",
       "  'recall': 0.5074626865671642,\n",
       "  'f1': 0.5619834710743802},\n",
       " {'accuracy': 0.71875,\n",
       "  'precision': 0.5942028985507246,\n",
       "  'recall': 0.6119402985074627,\n",
       "  'f1': 0.6029411764705882})"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 6) Logistic Regression and Gaussian Naive Bayes\n",
    "# For these, use scaled features (not raw)\n",
    "# Logistic Regression\n",
    "lr = LogisticRegression(max_iter=1000, random_state=RANDOM_STATE)\n",
    "lr.fit(X_train_scaled, y_train)\n",
    "y_pred_lr = lr.predict(X_test_scaled)\n",
    "metrics_lr = eval_metrics(y_test, y_pred_lr)\n",
    "\n",
    "# GaussianNB (works fine with scaled or unscaled; we'll use scaled)\n",
    "gnb = GaussianNB()\n",
    "gnb.fit(X_train_scaled, y_train)\n",
    "y_pred_gnb = gnb.predict(X_test_scaled)\n",
    "metrics_gnb = eval_metrics(y_test, y_pred_gnb)\n",
    "\n",
    "metrics_lr, metrics_gnb\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "33184c9f-efc4-4f83-9b25-74188eeb1478",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'accuracy': 0.7239583333333334,\n",
       " 'precision': 0.6296296296296297,\n",
       " 'recall': 0.5074626865671642,\n",
       " 'f1': 0.5619834710743802}"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 7) Logistic Regression on top-N features (scaled) for fairness\n",
    "scaler_top = StandardScaler()\n",
    "X_train_top_scaled = scaler_top.fit_transform(X_train_top)\n",
    "X_test_top_scaled = scaler_top.transform(X_test_top)\n",
    "\n",
    "lr_top = LogisticRegression(max_iter=1000, random_state=RANDOM_STATE)\n",
    "lr_top.fit(X_train_top_scaled, y_train)\n",
    "y_pred_lr_top = lr_top.predict(X_test_top_scaled)\n",
    "metrics_lr_top = eval_metrics(y_test, y_pred_lr_top)\n",
    "metrics_lr_top\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "343ff11c-a911-45c4-8ac1-068571b36b5a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>accuracy</th>\n",
       "      <th>precision</th>\n",
       "      <th>recall</th>\n",
       "      <th>f1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>RandomForest_all</th>\n",
       "      <td>0.744792</td>\n",
       "      <td>0.680000</td>\n",
       "      <td>0.507463</td>\n",
       "      <td>0.581197</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RandomForest_top5</th>\n",
       "      <td>0.760417</td>\n",
       "      <td>0.690909</td>\n",
       "      <td>0.567164</td>\n",
       "      <td>0.622951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RandomForest_PCA</th>\n",
       "      <td>0.703125</td>\n",
       "      <td>0.575758</td>\n",
       "      <td>0.567164</td>\n",
       "      <td>0.571429</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LogisticRegression_scaled</th>\n",
       "      <td>0.723958</td>\n",
       "      <td>0.629630</td>\n",
       "      <td>0.507463</td>\n",
       "      <td>0.561983</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LogisticRegression_top5</th>\n",
       "      <td>0.723958</td>\n",
       "      <td>0.629630</td>\n",
       "      <td>0.507463</td>\n",
       "      <td>0.561983</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GaussianNB_scaled</th>\n",
       "      <td>0.718750</td>\n",
       "      <td>0.594203</td>\n",
       "      <td>0.611940</td>\n",
       "      <td>0.602941</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                           accuracy  precision    recall        f1\n",
       "RandomForest_all           0.744792   0.680000  0.507463  0.581197\n",
       "RandomForest_top5          0.760417   0.690909  0.567164  0.622951\n",
       "RandomForest_PCA           0.703125   0.575758  0.567164  0.571429\n",
       "LogisticRegression_scaled  0.723958   0.629630  0.507463  0.561983\n",
       "LogisticRegression_top5    0.723958   0.629630  0.507463  0.561983\n",
       "GaussianNB_scaled          0.718750   0.594203  0.611940  0.602941"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 8) Compile results into single DataFrame for comparison\n",
    "results = pd.DataFrame({\n",
    "    'RandomForest_all': baseline_metrics,\n",
    "    'RandomForest_top'+str(N): metrics_rf_top,\n",
    "    'RandomForest_PCA': metrics_rf_pca,\n",
    "    'LogisticRegression_scaled': metrics_lr,\n",
    "    'LogisticRegression_top'+str(N): metrics_lr_top,\n",
    "    'GaussianNB_scaled': metrics_gnb\n",
    "}).T\n",
    "\n",
    "results = results[['accuracy','precision','recall','f1']]\n",
    "results\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "0fca78e6-1021-4334-a197-835456ade92b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 1000x500 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 9) Visual comparison of metrics\n",
    "plt.figure(figsize=(10,5))\n",
    "results[['accuracy','precision','recall','f1']].plot(kind='bar', rot=45)\n",
    "plt.title('Model comparison (Diabetes dataset)')\n",
    "plt.ylabel('Score')\n",
    "plt.ylim(0,1)\n",
    "plt.legend(loc='lower right')\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "f1623295-f3ac-4389-a50f-655d8863e195",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x800 with 5 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 10) Additional: Confusion matrices for top-performing models\n",
    "from sklearn.metrics import ConfusionMatrixDisplay\n",
    "\n",
    "best_models = {\n",
    "    'RandomForest_all': (rf, X_test),\n",
    "    'RandomForest_top'+str(N): (rf_top, X_test_top),\n",
    "    'RandomForest_PCA': (rf_pca, X_test_pca),\n",
    "    'LogisticRegression_scaled': (lr, X_test_scaled),\n",
    "    'GaussianNB_scaled': (gnb, X_test_scaled)\n",
    "}\n",
    "\n",
    "plt.figure(figsize=(12,8))\n",
    "i = 1\n",
    "for name, (model, Xs) in best_models.items():\n",
    "    plt.subplot(2,3,i); i+=1\n",
    "    ypred = model.predict(Xs)\n",
    "    cm = confusion_matrix(y_test, ypred)\n",
    "    disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=[0,1])\n",
    "    disp.plot(ax=plt.gca(), cmap='Blues', colorbar=False)\n",
    "    plt.title(name)\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "6f0c347e-008d-46d5-9d65-06c345cbb4ed",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saved results to diabetes_model_comparison_results.csv\n"
     ]
    }
   ],
   "source": [
    "# 12) Optional: Save results and key models (if you want)\n",
    "results.to_csv('diabetes_model_comparison_results.csv', index=True)\n",
    "print('Saved results to diabetes_model_comparison_results.csv')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "6e744d59-3171-408f-a397-c88487b6cd4f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Original shape: (768, 9)\n",
      "Transformed shape: (768, 8)\n",
      "Explained variance ratio per component:\n",
      " [0.23272686 0.19238799 0.11685063 0.11026015 0.09600764 0.08454347\n",
      " 0.07582451 0.04646464]\n",
      "Cumulative explained variance: [0.23272686 0.42511485 0.54196548 0.65222563 0.74823327 0.83277674\n",
      " 0.90860124 0.95506589]\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        PC1       PC2       PC3       PC4       PC5       PC6       PC7  \\\n",
      "0  1.046728  1.269606  1.130755 -1.334317  0.012106 -0.009166  0.318796   \n",
      "1 -1.141976 -0.701207  0.470395 -1.783299 -0.241092  0.260830 -0.446386   \n",
      "2 -0.418800  1.630649  2.375920 -0.174482 -0.422483 -1.031545 -0.088903   \n",
      "3 -1.135571 -1.239020  0.420686 -1.567982 -1.081183  0.198028 -0.459859   \n",
      "4  2.336899 -2.143166  3.920360 -0.548185  3.543514 -0.599708  1.058117   \n",
      "\n",
      "        PC8  \n",
      "0  0.925265  \n",
      "1  0.840074  \n",
      "2 -1.084740  \n",
      "3  0.068978  \n",
      "4  0.622043  \n"
     ]
    }
   ],
   "source": [
    "# PCA using sklearn.decomposition.PCA\n",
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.decomposition import PCA\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Example: load your dataset\n",
    "# Replace with your actual data file or DataFrame\n",
    "df = pd.read_csv(\"diabetes.csv\")\n",
    "\n",
    "# Separate features and target (if applicable)\n",
    "X = df.drop(columns=['Outcome'], errors='ignore')\n",
    "\n",
    "# 1. Standardize the data (important before PCA)\n",
    "scaler = StandardScaler()\n",
    "X_scaled = scaler.fit_transform(X)\n",
    "\n",
    "# 2. Apply PCA\n",
    "# You can specify number of components or explained variance threshold\n",
    "pca = PCA(n_components=0.95, random_state=42)   # retain 95% of variance\n",
    "X_pca = pca.fit_transform(X_scaled)\n",
    "\n",
    "# 3. Display results\n",
    "print(\"Original shape:\", X.shape)\n",
    "print(\"Transformed shape:\", X_pca.shape)\n",
    "print(\"Explained variance ratio per component:\\n\", pca.explained_variance_ratio_)\n",
    "print(\"Cumulative explained variance:\", np.cumsum(pca.explained_variance_ratio_))\n",
    "\n",
    "# 4. Visualize explained variance\n",
    "plt.figure(figsize=(8,5))\n",
    "plt.plot(np.cumsum(pca.explained_variance_ratio_), marker='o')\n",
    "plt.xlabel('Number of Principal Components')\n",
    "plt.ylabel('Cumulative Explained Variance')\n",
    "plt.title('PCA Explained Variance')\n",
    "plt.grid(True)\n",
    "plt.show()\n",
    "\n",
    "# Optional: create a new DataFrame with principal components\n",
    "pca_df = pd.DataFrame(X_pca, columns=[f'PC{i+1}' for i in range(X_pca.shape[1])])\n",
    "print(pca_df.head())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c5497191-7999-48ad-99c6-244424e89a93",
   "metadata": {},
   "outputs": [],
   "source": [
    "0"
   ]
  }
 ],
 "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
}