{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Password Strength Classifier Dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import Necessary modules"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Collect Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv(\"data.csv\", on_bad_lines='skip')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "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>password</th>\n",
       "      <th>strength</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>kzde5577</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>kino3434</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>visi7k1yr</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>megzy123</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>lamborghin1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      password  strength\n",
       "0     kzde5577         1\n",
       "1     kino3434         1\n",
       "2    visi7k1yr         1\n",
       "3     megzy123         1\n",
       "4  lamborghin1         1"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Check for duplicates and null values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 669640 entries, 0 to 669639\n",
      "Data columns (total 2 columns):\n",
      " #   Column    Non-Null Count   Dtype \n",
      "---  ------    --------------   ----- \n",
      " 0   password  669639 non-null  object\n",
      " 1   strength  669640 non-null  int64 \n",
      "dtypes: int64(1), object(1)\n",
      "memory usage: 10.2+ MB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "password     True\n",
       "strength    False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.isnull().any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Drop null values\n",
    "data.dropna(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.duplicated().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Divide dataset into features and labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "x=np.array(data.password)\n",
    "y=np.array(data.strength)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Visualise classes count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1008x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(14,7))\n",
    "sns.countplot(x='strength', data=data)\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Use TF-IDF Vectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "def word(inputs):\n",
    "    a= []\n",
    "    for i in inputs:\n",
    "        a.append(i)\n",
    "    return a"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "\n",
    "vect = TfidfVectorizer(tokenizer = word)\n",
    "x_transformed =vect.fit_transform(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "kino3434\n",
      "  (0, 38)\t0.6177740147525559\n",
      "  (0, 37)\t0.5602425115534002\n",
      "  (0, 70)\t0.25649928309246306\n",
      "  (0, 69)\t0.26770311076536885\n",
      "  (0, 64)\t0.2519907735724838\n",
      "  (0, 66)\t0.321756751659985\n"
     ]
    }
   ],
   "source": [
    "print(x[1])\n",
    "print(x_transformed[1])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Split data into training and testing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "x_train,x_test,y_train,y_test=train_test_split(x_transformed,y,test_size=0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.ensemble import AdaBoostClassifier\n",
    "import xgboost as xgb\n",
    "from xgboost import XGBClassifier\n",
    "from sklearn.model_selection import cross_val_score\n",
    "from sklearn.model_selection import ShuffleSplit\n",
    "from sklearn.model_selection import cross_val_score, StratifiedKFold\n",
    "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix, roc_curve, auc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "cv=ShuffleSplit(n_splits=10,test_size=0.2,random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Evaluating AdaBoost Classifier with ShuffleSplit Cross-Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
      "[Parallel(n_jobs=10)]: Done   3 out of  10 | elapsed:  3.2min remaining:  7.5min\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean Accuracy :  0.8329354227527697\n",
      "Standard Deviation Accuracy :  0.002010878226955273\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Done  10 out of  10 | elapsed:  3.4min finished\n"
     ]
    }
   ],
   "source": [
    "AdaBoost = cross_val_score(AdaBoostClassifier(),x_train,y_train,cv=cv,scoring='accuracy', verbose = 2, n_jobs=10)\n",
    "print(\"Mean Accuracy : \", AdaBoost.mean())\n",
    "print(\"Standard Deviation Accuracy : \", AdaBoost.std())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Evaluating XGB Classifier with ShuffleSplit Cross-Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
      "[Parallel(n_jobs=10)]: Done   3 out of  10 | elapsed:   52.0s remaining:  2.0min\n",
      "[Parallel(n_jobs=10)]: Done  10 out of  10 | elapsed:   52.7s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean Accuracy :  0.9797018937308085\n",
      "Standard Deviation Accuracy :  0.0006599760085162088\n"
     ]
    }
   ],
   "source": [
    "XGB = cross_val_score(XGBClassifier(),x_train,y_train,cv=cv,scoring='accuracy', verbose = 2, n_jobs=10)\n",
    "print(\"Mean Accuracy : \", XGB.mean())\n",
    "print(\"Standard Deviation Accuracy : \", XGB.std())\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Evaluating logistic regression with ShuffleSplit Cross-Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
      "[Parallel(n_jobs=10)]: Done   3 out of  10 | elapsed:  1.9min remaining:  4.4min\n",
      "[Parallel(n_jobs=10)]: Done  10 out of  10 | elapsed:  2.1min finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean Accuracy: 0.8196186405084793\n",
      "Standard Deviation Accuracy: 0.0012977626105239754\n"
     ]
    }
   ],
   "source": [
    "logistic_regression = LogisticRegression(max_iter=200)\n",
    "\n",
    "logistic_scores = cross_val_score(logistic_regression, x_train, y_train, cv=cv, scoring='accuracy', verbose=2, n_jobs=10)\n",
    "\n",
    "print(\"Mean Accuracy:\", logistic_scores.mean())\n",
    "print(\"Standard Deviation Accuracy:\", logistic_scores.std())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "cv1 = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Evaluating AdaBoost with Decision Tree Base Estimator Using Stratified K-Fold Cross-Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
      "[Parallel(n_jobs=10)]: Done   3 out of  10 | elapsed:  3.4min remaining:  8.0min\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean Accuracy: 0.8306717586222833\n",
      "Standard Deviation Accuracy: 0.0013117625233690468\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Done  10 out of  10 | elapsed:  3.8min finished\n"
     ]
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier\n",
    "\n",
    "base_estimator = DecisionTreeClassifier(max_depth=1)\n",
    "ada_boost_classifier = AdaBoostClassifier(base_estimator=base_estimator, n_estimators=50, random_state=42)\n",
    "\n",
    "AdaBoost_scores = cross_val_score(ada_boost_classifier, x_train, y_train, cv=cv1, scoring='accuracy', verbose=2, n_jobs=10)\n",
    "\n",
    "print(\"Mean Accuracy:\", AdaBoost_scores.mean())\n",
    "print(\"Standard Deviation Accuracy:\", AdaBoost_scores.std())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Evaluating XGB  with Stratified K-Fold Cross-Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
      "[Parallel(n_jobs=10)]: Done   3 out of  10 | elapsed:  2.4min remaining:  5.7min\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean Accuracy :  0.980056410405737\n",
      "Standard Deviation Accuracy :  0.0006282453595179354\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Done  10 out of  10 | elapsed:  2.6min finished\n"
     ]
    }
   ],
   "source": [
    "cv1 = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)\n",
    "\n",
    "XGB = cross_val_score(XGBClassifier(),x_train,y_train,cv=cv1,scoring='accuracy', verbose = 2, n_jobs=10)\n",
    "print(\"Mean Accuracy : \", XGB.mean())\n",
    "print(\"Standard Deviation Accuracy : \", XGB.std())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Evaluating Logistic Regression with Stratified K-Fold Cross-Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
      "[Parallel(n_jobs=10)]: Done   3 out of  10 | elapsed:  2.5min remaining:  5.9min\n",
      "[Parallel(n_jobs=10)]: Done  10 out of  10 | elapsed:  2.7min finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean Accuracy: 0.8193540949805984\n",
      "Standard Deviation Accuracy: 0.001569340857796851\n"
     ]
    }
   ],
   "source": [
    "logistic_regression = LogisticRegression(max_iter=200)\n",
    "\n",
    "logistic_scores = cross_val_score(logistic_regression, x_train, y_train, cv=cv1, scoring='accuracy', verbose=2, n_jobs=10)\n",
    "\n",
    "print(\"Mean Accuracy:\", logistic_scores.mean())\n",
    "print(\"Standard Deviation Accuracy:\", logistic_scores.std())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\njehm\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:1247: FutureWarning: 'multi_class' was deprecated in version 1.5 and will be removed in 1.7. From then on, it will always use 'multinomial'. Leave it to its default value to avoid this warning.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Logistic Regression:\n",
      "Accuracy: 0.8196642972343349\n",
      "Precision: 0.8027925299466757\n",
      "Recall: 0.8196642972343349\n",
      "F1 Score: 0.8025610723633392\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
      "[Parallel(n_jobs=10)]: Done   3 out of  10 | elapsed:   14.6s remaining:   34.1s\n",
      "[Parallel(n_jobs=10)]: Done  10 out of  10 | elapsed:   19.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Logistic Regression - Mean Accuracy: 0.8188594200010227\n",
      "Logistic Regression - Standard Deviation Accuracy: 0.0011353813395557101\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 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": [
    "# Logistic Regression\n",
    "log_reg = LogisticRegression(max_iter=1000, multi_class='multinomial')\n",
    "\n",
    "# Train the model\n",
    "log_reg.fit(x_train, y_train)\n",
    "y_pred_log_reg = log_reg.predict(x_test)\n",
    "\n",
    "# Calculate metrics\n",
    "accuracy_log_reg = accuracy_score(y_test, y_pred_log_reg)\n",
    "precision_log_reg = precision_score(y_test, y_pred_log_reg, average='weighted')\n",
    "recall_log_reg = recall_score(y_test, y_pred_log_reg, average='weighted')\n",
    "f1_log_reg = f1_score(y_test, y_pred_log_reg, average='weighted')\n",
    "\n",
    "print(\"Logistic Regression:\")\n",
    "print(f\"Accuracy: {accuracy_log_reg}\")\n",
    "print(f\"Precision: {precision_log_reg}\")\n",
    "print(f\"Recall: {recall_log_reg}\")\n",
    "print(f\"F1 Score: {f1_log_reg}\\n\")\n",
    "\n",
    "# Cross-validation\n",
    "cv = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)\n",
    "scores_log_reg = cross_val_score(log_reg, x_train, y_train, cv=cv, scoring='accuracy', verbose=2, n_jobs=10)\n",
    "print(f\"Logistic Regression - Mean Accuracy:\", scores_log_reg.mean())\n",
    "print(f\"Logistic Regression - Standard Deviation Accuracy:\", scores_log_reg.std())\n",
    "\n",
    "# Confusion Matrix\n",
    "cm_log_reg = confusion_matrix(y_test, y_pred_log_reg)\n",
    "sns.heatmap(cm_log_reg, annot=True, fmt='d', cmap='Blues')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('Actual')\n",
    "plt.title('Confusion Matrix - Logistic Regression')\n",
    "plt.show()\n",
    "\n",
    "# ROC Curve\n",
    "if hasattr(log_reg, \"predict_proba\"):\n",
    "    y_score_log_reg = log_reg.predict_proba(x_test)\n",
    "    fpr_log_reg, tpr_log_reg, _ = roc_curve(y_test, y_score_log_reg[:,1], pos_label=log_reg.classes_[1])\n",
    "    roc_auc_log_reg = auc(fpr_log_reg, tpr_log_reg)\n",
    "\n",
    "    plt.figure()\n",
    "    plt.plot(fpr_log_reg, tpr_log_reg, color='darkorange', lw=2, label='ROC curve (area = %0.2f)' % roc_auc_log_reg)\n",
    "    plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')\n",
    "    plt.xlim([0.0, 1.0])\n",
    "    plt.ylim([0.0, 1.05])\n",
    "    plt.xlabel('False Positive Rate')\n",
    "    plt.ylabel('True Positive Rate')\n",
    "    plt.title('ROC Curve - Logistic Regression')\n",
    "    plt.legend(loc=\"lower right\")\n",
    "    plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# AdaBoost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\njehm\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\ensemble\\_weight_boosting.py:527: FutureWarning: The SAMME.R algorithm (the default) is deprecated and will be removed in 1.6. Use the SAMME algorithm to circumvent this warning.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "AdaBoost:\n",
      "Accuracy: 0.8320291499910399\n",
      "Precision: 0.8314213511126545\n",
      "Recall: 0.8320291499910399\n",
      "F1 Score: 0.7910803604483075\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
      "[Parallel(n_jobs=10)]: Done   3 out of  10 | elapsed:  2.2min remaining:  5.0min\n",
      "[Parallel(n_jobs=10)]: Done  10 out of  10 | elapsed:  2.2min finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "AdaBoost - Mean Accuracy: 0.8326037645658989\n",
      "AdaBoost - Standard Deviation Accuracy: 0.0024844962471718066\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 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": [
    "# AdaBoost\n",
    "ada_boost = AdaBoostClassifier()\n",
    "\n",
    "# Train the model\n",
    "ada_boost.fit(x_train, y_train)\n",
    "y_pred_ada_boost = ada_boost.predict(x_test)\n",
    "\n",
    "# Calculate metrics\n",
    "accuracy_ada_boost = accuracy_score(y_test, y_pred_ada_boost)\n",
    "precision_ada_boost = precision_score(y_test, y_pred_ada_boost, average='weighted')\n",
    "recall_ada_boost = recall_score(y_test, y_pred_ada_boost, average='weighted')\n",
    "f1_ada_boost = f1_score(y_test, y_pred_ada_boost, average='weighted')\n",
    "\n",
    "print(\"AdaBoost:\")\n",
    "print(f\"Accuracy: {accuracy_ada_boost}\")\n",
    "print(f\"Precision: {precision_ada_boost}\")\n",
    "print(f\"Recall: {recall_ada_boost}\")\n",
    "print(f\"F1 Score: {f1_ada_boost}\\n\")\n",
    "\n",
    "# Cross-validation\n",
    "scores_ada_boost = cross_val_score(ada_boost, x_train, y_train, cv=cv, scoring='accuracy', verbose=2, n_jobs=10)\n",
    "print(f\"AdaBoost - Mean Accuracy:\", scores_ada_boost.mean())\n",
    "print(f\"AdaBoost - Standard Deviation Accuracy:\", scores_ada_boost.std())\n",
    "\n",
    "# Confusion Matrix\n",
    "cm_ada_boost = confusion_matrix(y_test, y_pred_ada_boost)\n",
    "sns.heatmap(cm_ada_boost, annot=True, fmt='d', cmap='Blues')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('Actual')\n",
    "plt.title('Confusion Matrix - AdaBoost')\n",
    "plt.show()\n",
    "\n",
    "# ROC Curve\n",
    "if hasattr(ada_boost, \"predict_proba\"):\n",
    "    y_score_ada_boost = ada_boost.predict_proba(x_test)\n",
    "    fpr_ada_boost, tpr_ada_boost, _ = roc_curve(y_test, y_score_ada_boost[:,1], pos_label=ada_boost.classes_[1])\n",
    "    roc_auc_ada_boost = auc(fpr_ada_boost, tpr_ada_boost)\n",
    "\n",
    "    plt.figure()\n",
    "    plt.plot(fpr_ada_boost, tpr_ada_boost, color='darkorange', lw=2, label='ROC curve (area = %0.2f)' % roc_auc_ada_boost)\n",
    "    plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')\n",
    "    plt.xlim([0.0, 1.0])\n",
    "    plt.ylim([0.0, 1.05])\n",
    "    plt.xlabel('False Positive Rate')\n",
    "    plt.ylabel('True Positive Rate')\n",
    "    plt.title('ROC Curve - AdaBoost')\n",
    "    plt.legend(loc=\"lower right\")\n",
    "    plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# XGBoost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "XGBoost:\n",
      "Accuracy: 0.9805119168508453\n",
      "Precision: 0.9804456036767737\n",
      "Recall: 0.9805119168508453\n",
      "F1 Score: 0.9804350050572441\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
      "[Parallel(n_jobs=10)]: Done   3 out of  10 | elapsed:   47.1s remaining:  1.8min\n",
      "[Parallel(n_jobs=10)]: Done  10 out of  10 | elapsed:   47.5s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "XGBoost - Mean Accuracy: 0.9803214780779349\n",
      "XGBoost - Standard Deviation Accuracy: 0.0008349919359584393\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 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": [
    "# XGBoost\n",
    "xg_boost = XGBClassifier()\n",
    "\n",
    "# Train the model\n",
    "xg_boost.fit(x_train, y_train)\n",
    "y_pred_xg_boost = xg_boost.predict(x_test)\n",
    "\n",
    "# Calculate metrics\n",
    "accuracy_xg_boost = accuracy_score(y_test, y_pred_xg_boost)\n",
    "precision_xg_boost = precision_score(y_test, y_pred_xg_boost, average='weighted')\n",
    "recall_xg_boost = recall_score(y_test, y_pred_xg_boost, average='weighted')\n",
    "f1_xg_boost = f1_score(y_test, y_pred_xg_boost, average='weighted')\n",
    "\n",
    "print(\"XGBoost:\")\n",
    "print(f\"Accuracy: {accuracy_xg_boost}\")\n",
    "print(f\"Precision: {precision_xg_boost}\")\n",
    "print(f\"Recall: {recall_xg_boost}\")\n",
    "print(f\"F1 Score: {f1_xg_boost}\\n\")\n",
    "\n",
    "# Cross-validation\n",
    "scores_xg_boost = cross_val_score(xg_boost, x_train, y_train, cv=cv, scoring='accuracy', verbose=2, n_jobs=10)\n",
    "print(f\"XGBoost - Mean Accuracy:\", scores_xg_boost.mean())\n",
    "print(f\"XGBoost - Standard Deviation Accuracy:\", scores_xg_boost.std())\n",
    "\n",
    "# Confusion Matrix\n",
    "cm_xg_boost = confusion_matrix(y_test, y_pred_xg_boost)\n",
    "sns.heatmap(cm_xg_boost, annot=True, fmt='d', cmap='Blues')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('Actual')\n",
    "plt.title('Confusion Matrix - XGBoost')\n",
    "plt.show()\n",
    "\n",
    "# ROC Curve\n",
    "if hasattr(xg_boost, \"predict_proba\"):\n",
    "    y_score_xg_boost = xg_boost.predict_proba(x_test)\n",
    "    fpr_xg_boost, tpr_xg_boost, _ = roc_curve(y_test, y_score_xg_boost[:,1], pos_label=xg_boost.classes_[1])\n",
    "    roc_auc_xg_boost = auc(fpr_xg_boost, tpr_xg_boost)\n",
    "\n",
    "    plt.figure()\n",
    "    plt.plot(fpr_xg_boost, tpr_xg_boost, color='darkorange', lw=2, label='ROC curve (area = %0.2f)' % roc_auc_xg_boost)\n",
    "    plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')\n",
    "    plt.xlim([0.0, 1.0])\n",
    "    plt.ylim([0.0, 1.05])\n",
    "    plt.xlabel('False Positive Rate')\n",
    "    plt.ylabel('True Positive Rate')\n",
    "    plt.title('ROC Curve - XGBoost')\n",
    "    plt.legend(loc=\"lower right\")\n",
    "    plt.show()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}