{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "acaf201b-0499-4fa8-8bdd-13e2867f59d4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Machine Learning Activity: Feature Selection and Model Comparison (Diabetes dataset)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "779dddbe-b890-4c00-809e-1b4a7a6ef476",
   "metadata": {},
   "outputs": [],
   "source": [
    "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.metrics import accuracy_score, precision_score, recall_score, f1_score, classification_report, confusion_matrix\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "3c6aa060-bb6b-4a55-a93a-a9c6ba5fd60a",
   "metadata": {},
   "outputs": [],
   "source": [
    "RSEED = 42\n",
    "np.random.seed(RSEED)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "024c863e-4206-4532-b7ce-11cf615308d5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape: (768, 10)\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>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": [
    "df = pd.read_csv('diabetes.csv')\n",
    "print(\"Shape:\", df.shape)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8535b10d-0f6f-4877-9a71-b12cb3da3f1e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<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",
      "\n",
      "Missing values per column:\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.info()\n",
    "print(\"\\nMissing values per column:\")\n",
    "print(df.isnull().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "3b08f434-233c-4427-993c-09b769b4365b",
   "metadata": {},
   "outputs": [],
   "source": [
    "cols_with_missing = ['Glucose','BloodPressure','SkinThickness','Insulin','BMI']\n",
    "df[cols_with_missing] = df[cols_with_missing].replace(0, np.nan)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9188a94c-19ed-4152-947e-d47fcb998040",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Missing after replacing zeros:\n",
      "PatientId                     0\n",
      "Pregnancies                   0\n",
      "Glucose                       5\n",
      "BloodPressure                35\n",
      "SkinThickness               227\n",
      "Insulin                     374\n",
      "BMI                          11\n",
      "DiabetesPedigreeFunction      0\n",
      "Age                           0\n",
      "Outcome                       0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(\"Missing after replacing zeros:\")\n",
    "print(df.isnull().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "fec9f5be-087f-4249-a81a-6d35881f3d4e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "After imputation:\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": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df.fillna(df.median())\n",
    "\n",
    "print(\"\\nAfter imputation:\")\n",
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "f792b32d-7a77-4dff-b4da-5e2cda52a728",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Feature columns: ['PatientId', 'Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age']\n",
      "Target distribution:\n",
      " Outcome\n",
      "0    500\n",
      "1    268\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "target_col = 'Outcome'  # standard column in diabetes dataset\n",
    "X = df.drop(columns=[target_col])\n",
    "y = df[target_col]\n",
    "\n",
    "print(\"Feature columns:\", X.columns.tolist())\n",
    "print(\"Target distribution:\\n\", y.value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "3c00769f-9d12-4b90-817d-d86e429be152",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train: (614, 9) Test: (154, 9)\n"
     ]
    }
   ],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=RSEED, stratify=y\n",
    ")\n",
    "print(\"Train:\", X_train.shape, \"Test:\", X_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "928ac1b5-5351-4d9b-8fc7-e2706f71f161",
   "metadata": {},
   "outputs": [],
   "source": [
    "def evaluate_model(model, X_test, y_test, verbose=True):\n",
    "    y_pred = model.predict(X_test)\n",
    "    acc = accuracy_score(y_test, y_pred)\n",
    "    prec = precision_score(y_test, y_pred, zero_division=0)\n",
    "    rec = recall_score(y_test, y_pred, zero_division=0)\n",
    "    f1 = f1_score(y_test, y_pred, zero_division=0)\n",
    "    if verbose:\n",
    "        print(classification_report(y_test, y_pred, zero_division=0))\n",
    "    return {'accuracy': acc, 'precision': prec, 'recall': rec, 'f1': f1, 'y_pred': y_pred}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "8337f942-831c-4d2a-8ec4-2949e437f022",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.77      0.82      0.80       100\n",
      "           1       0.62      0.56      0.59        54\n",
      "\n",
      "    accuracy                           0.73       154\n",
      "   macro avg       0.70      0.69      0.69       154\n",
      "weighted avg       0.72      0.73      0.72       154\n",
      "\n",
      "RF (full) metrics: {'accuracy': 0.7272727272727273, 'precision': 0.625, 'recall': 0.5555555555555556, 'f1': 0.5882352941176471}\n"
     ]
    }
   ],
   "source": [
    "# Cell \n",
    "rf = RandomForestClassifier(n_estimators=200, random_state=RSEED)\n",
    "rf.fit(X_train, y_train)\n",
    "\n",
    "rf_results_full = evaluate_model(rf, X_test, y_test)\n",
    "print(\"RF (full) metrics:\", {k:v for k,v in rf_results_full.items() if k!='y_pred'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "8ff1c078-90fa-44e1-a4f1-92ae86060ed7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Top 5 important features:\n",
      " Glucose                     0.275406\n",
      "BMI                         0.146059\n",
      "DiabetesPedigreeFunction    0.114157\n",
      "Age                         0.109666\n",
      "PatientId                   0.085499\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "feat_importances = pd.Series(rf.feature_importances_, index=X.columns).sort_values(ascending=False)\n",
    "plt.figure(figsize=(8,6))\n",
    "sns.barplot(x=feat_importances, y=feat_importances.index)\n",
    "plt.title(\"Feature Importances - Random Forest (Diabetes)\")\n",
    "plt.xlabel(\"Importance\")\n",
    "plt.ylabel(\"Feature\")\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "print(\"Top 5 important features:\\n\", feat_importances.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "b3e6098d-58c1-4ef8-84ba-1926dd2b65cc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Top 5 features: ['Glucose', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'PatientId']\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.78      0.84      0.81       100\n",
      "           1       0.65      0.56      0.60        54\n",
      "\n",
      "    accuracy                           0.74       154\n",
      "   macro avg       0.71      0.70      0.70       154\n",
      "weighted avg       0.73      0.74      0.73       154\n",
      "\n",
      "RF (top 5) metrics: {'accuracy': 0.7402597402597403, 'precision': 0.6521739130434783, 'recall': 0.5555555555555556, 'f1': 0.6}\n"
     ]
    }
   ],
   "source": [
    "def train_with_top_features(rf_model, X_train, X_test, y_train, y_test, top_n=5):\n",
    "    fi = pd.Series(rf_model.feature_importances_, index=X_train.columns).sort_values(ascending=False)\n",
    "    top_features = fi.head(top_n).index.tolist()\n",
    "    print(f\"Top {top_n} features: {top_features}\")\n",
    "    \n",
    "    X_train_top = X_train[top_features]\n",
    "    X_test_top = X_test[top_features]\n",
    "    \n",
    "    rf_top = RandomForestClassifier(n_estimators=200, random_state=RSEED)\n",
    "    rf_top.fit(X_train_top, y_train)\n",
    "    results = evaluate_model(rf_top, X_test_top, y_test)\n",
    "    return rf_top, top_features, results\n",
    "\n",
    "rf_top5, top5_features, rf_top5_results = train_with_top_features(rf, X_train, X_test, y_train, y_test, top_n=5)\n",
    "print(\"RF (top 5) metrics:\", {k:v for k,v in rf_top5_results.items() if k!='y_pred'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "a74fe80c-9009-4dd7-941b-ae8a9055d05e",
   "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>Model</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>0</th>\n",
       "      <td>RandomForest_Full</td>\n",
       "      <td>0.727273</td>\n",
       "      <td>0.625000</td>\n",
       "      <td>0.555556</td>\n",
       "      <td>0.588235</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>RandomForest_Top5</td>\n",
       "      <td>0.740260</td>\n",
       "      <td>0.652174</td>\n",
       "      <td>0.555556</td>\n",
       "      <td>0.600000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               Model  accuracy  precision    recall        f1\n",
       "0  RandomForest_Full  0.727273   0.625000  0.555556  0.588235\n",
       "1  RandomForest_Top5  0.740260   0.652174  0.555556  0.600000"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cell 11 - Compare Random Forest results (full vs top 5)\n",
    "pd.DataFrame([\n",
    "    {'Model':'RandomForest_Full', **{k:rf_results_full[k] for k in ['accuracy','precision','recall','f1']}},\n",
    "    {'Model':'RandomForest_Top5', **{k:rf_top5_results[k] for k in ['accuracy','precision','recall','f1']}}\n",
    "])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "6642f425-e646-4672-b04a-5a1a693cd907",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PCA retains 8 components (95% variance).\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.76      0.77      0.77       100\n",
      "           1       0.57      0.56      0.56        54\n",
      "\n",
      "    accuracy                           0.69       154\n",
      "   macro avg       0.66      0.66      0.66       154\n",
      "weighted avg       0.69      0.69      0.69       154\n",
      "\n",
      "RF (PCA) metrics: {'accuracy': 0.6948051948051948, 'precision': 0.5660377358490566, 'recall': 0.5555555555555556, 'f1': 0.5607476635514018}\n"
     ]
    }
   ],
   "source": [
    "# Cell 12 - PCA preprocessing\n",
    "scaler = StandardScaler()\n",
    "X_train_scaled = scaler.fit_transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "pca = PCA(n_components=0.95, random_state=RSEED)\n",
    "pca.fit(X_train_scaled)\n",
    "print(f\"PCA retains {pca.n_components_} components (95% variance).\")\n",
    "\n",
    "X_train_pca = pca.transform(X_train_scaled)\n",
    "X_test_pca = pca.transform(X_test_scaled)\n",
    "\n",
    "# Train RF on PCA-transformed features\n",
    "rf_pca = RandomForestClassifier(n_estimators=200, random_state=RSEED)\n",
    "rf_pca.fit(X_train_pca, y_train)\n",
    "rf_pca_results = evaluate_model(rf_pca, X_test_pca, y_test)\n",
    "print(\"RF (PCA) metrics:\", {k:v for k,v in rf_pca_results.items() if k!='y_pred'})\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "6e94fd19-aa95-48fb-8226-9430f0d6ddb9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.75      0.81      0.78       100\n",
      "           1       0.59      0.50      0.54        54\n",
      "\n",
      "    accuracy                           0.70       154\n",
      "   macro avg       0.67      0.66      0.66       154\n",
      "weighted avg       0.69      0.70      0.70       154\n",
      "\n",
      "Logistic Regression metrics: {'accuracy': 0.7012987012987013, 'precision': 0.5869565217391305, 'recall': 0.5, 'f1': 0.54}\n"
     ]
    }
   ],
   "source": [
    "# Cell 13 - Logistic Regression (scaled)\n",
    "logreg = LogisticRegression(max_iter=1000, random_state=RSEED)\n",
    "logreg.fit(X_train_scaled, y_train)\n",
    "logreg_results = evaluate_model(logreg, X_test_scaled, y_test)\n",
    "print(\"Logistic Regression metrics:\", {k:v for k,v in logreg_results.items() if k!='y_pred'})\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "79d408e0-cc3f-461a-a2f6-0b4119aea7f6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.79      0.74      0.76       100\n",
      "           1       0.57      0.63      0.60        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",
      "GaussianNB metrics: {'accuracy': 0.7012987012987013, 'precision': 0.5666666666666667, 'recall': 0.6296296296296297, 'f1': 0.5964912280701755}\n"
     ]
    }
   ],
   "source": [
    "# Cell 14 - Gaussian Naive Bayes\n",
    "gnb = GaussianNB()\n",
    "gnb.fit(X_train_scaled, y_train)\n",
    "gnb_results = evaluate_model(gnb, X_test_scaled, y_test)\n",
    "print(\"GaussianNB metrics:\", {k:v for k,v in gnb_results.items() if k!='y_pred'})\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "aa5783c3-dc5a-47b2-9027-2385f976e0e1",
   "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",
       "    <tr>\n",
       "      <th>Model</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>RandomForest_Full</th>\n",
       "      <td>0.727273</td>\n",
       "      <td>0.625000</td>\n",
       "      <td>0.555556</td>\n",
       "      <td>0.588235</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RandomForest_Top5</th>\n",
       "      <td>0.740260</td>\n",
       "      <td>0.652174</td>\n",
       "      <td>0.555556</td>\n",
       "      <td>0.600000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RandomForest_PCA</th>\n",
       "      <td>0.694805</td>\n",
       "      <td>0.566038</td>\n",
       "      <td>0.555556</td>\n",
       "      <td>0.560748</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LogisticRegression</th>\n",
       "      <td>0.701299</td>\n",
       "      <td>0.586957</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>0.540000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GaussianNB</th>\n",
       "      <td>0.701299</td>\n",
       "      <td>0.566667</td>\n",
       "      <td>0.629630</td>\n",
       "      <td>0.596491</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    accuracy  precision    recall        f1\n",
       "Model                                                      \n",
       "RandomForest_Full   0.727273   0.625000  0.555556  0.588235\n",
       "RandomForest_Top5   0.740260   0.652174  0.555556  0.600000\n",
       "RandomForest_PCA    0.694805   0.566038  0.555556  0.560748\n",
       "LogisticRegression  0.701299   0.586957  0.500000  0.540000\n",
       "GaussianNB          0.701299   0.566667  0.629630  0.596491"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cell 15 - Combine all results\n",
    "results = pd.DataFrame([\n",
    "    {'Model':'RandomForest_Full', **{k:rf_results_full[k] for k in ['accuracy','precision','recall','f1']}},\n",
    "    {'Model':'RandomForest_Top5', **{k:rf_top5_results[k] for k in ['accuracy','precision','recall','f1']}},\n",
    "    {'Model':'RandomForest_PCA', **{k:rf_pca_results[k] for k in ['accuracy','precision','recall','f1']}},\n",
    "    {'Model':'LogisticRegression', **{k:logreg_results[k] for k in ['accuracy','precision','recall','f1']}},\n",
    "    {'Model':'GaussianNB', **{k:gnb_results[k] for k in ['accuracy','precision','recall','f1']}},\n",
    "])\n",
    "\n",
    "results.set_index('Model', inplace=True)\n",
    "results\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "7fadad12-31cd-4b92-bfef-d6aca2341532",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Cell 16 - Visualization of performance\n",
    "plt.figure(figsize=(10,5))\n",
    "sns.barplot(x=results.index, y='accuracy', data=results)\n",
    "plt.title(\"Model Accuracy Comparison\")\n",
    "plt.xticks(rotation=45)\n",
    "plt.show()\n",
    "\n",
    "plt.figure(figsize=(10,5))\n",
    "results[['precision','recall','f1']].plot(kind='bar', figsize=(10,6))\n",
    "plt.title(\"Precision, Recall, F1 Comparison\")\n",
    "plt.xticks(rotation=45)\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "8261e680-5579-4965-9620-23135e710668",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 400x300 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 400x300 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 400x300 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Cell 17 - Plot confusion matrices\n",
    "def plot_confusion(model, X_test, y_test, title):\n",
    "    y_pred = model.predict(X_test)\n",
    "    cm = confusion_matrix(y_test, y_pred)\n",
    "    plt.figure(figsize=(4,3))\n",
    "    sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')\n",
    "    plt.title(title)\n",
    "    plt.xlabel(\"Predicted\")\n",
    "    plt.ylabel(\"Actual\")\n",
    "    plt.show()\n",
    "\n",
    "plot_confusion(rf, X_test, y_test, \"RandomForest (Full)\")\n",
    "plot_confusion(logreg, X_test_scaled, y_test, \"Logistic Regression\")\n",
    "plot_confusion(gnb, X_test_scaled, y_test, \"Naive Bayes\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "e75b18fe-cf0a-4933-9331-c406fa9bb420",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Summary of Findings:\n",
      "- Random Forest performs strongly and provides feature importances for interpretability.\n",
      "- Feature selection (top 5) slightly reduces accuracy but improves simplicity.\n",
      "- PCA reduced dimensionality to 8 components with minimal performance loss.\n",
      "- Logistic Regression provides a good baseline with fewer assumptions.\n",
      "- Naïve Bayes is fastest but may perform slightly worse depending on feature distributions.\n",
      "\n",
      "Conclusion: Random Forest (full) or Logistic Regression are generally strong models for this dataset.\n"
     ]
    }
   ],
   "source": [
    "# Cell 18 - Summary\n",
    "print(\"Summary of Findings:\")\n",
    "print(\"- Random Forest performs strongly and provides feature importances for interpretability.\")\n",
    "print(\"- Feature selection (top 5) slightly reduces accuracy but improves simplicity.\")\n",
    "print(\"- PCA reduced dimensionality to\", pca.n_components_, \"components with minimal performance loss.\")\n",
    "print(\"- Logistic Regression provides a good baseline with fewer assumptions.\")\n",
    "print(\"- Naïve Bayes is fastest but may perform slightly worse depending on feature distributions.\")\n",
    "print(\"\\nConclusion: Random Forest (full) or Logistic Regression are generally strong models for this dataset.\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b653bbb0-7e49-49b8-932f-8b8373b04f1c",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dff8b238-a2b9-4993-84f9-4f326aa61d15",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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
}