{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2b98b2f0",
   "metadata": {},
   "source": [
    "\n",
    "# Классификация и поиск аномалий по данным Cure the Princess\n",
    "\n",
    "Задача:\n",
    "- определить ключевую зависимую переменную\n",
    "- построить классификатор одним методом\n",
    "- оценить его точность, значимость и достоверность\n",
    "- найти аномальные объекты\n",
    "- удалить их из выборки\n",
    "- повторно построить классификатор тем же методом\n",
    "- сравнить качество моделей до и после очистки\n",
    "\n",
    "Ноутбук сделан **без финального содержательного вывода**.  \n",
    "После запуска можно будет добавить короткий итог по реальным результатам.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd6c60de",
   "metadata": {},
   "source": [
    "## 1. Импорт библиотек"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c360afbf",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.metrics import (\n",
    "    accuracy_score, precision_score, recall_score, f1_score,\n",
    "    roc_auc_score, confusion_matrix, classification_report, RocCurveDisplay\n",
    ")\n",
    "from sklearn.ensemble import IsolationForest\n",
    "\n",
    "from sklearn.neighbors import LocalOutlierFactor\n",
    "import statsmodels.api as sm\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fd0a778a",
   "metadata": {},
   "source": [
    "## 2. Загрузка данных и проверка столбцов"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f4464590",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Размер датасета: (2338, 14)\n",
      "\n",
      "Столбцы:\n",
      "- Phoenix Feather\n",
      "- Unicorn Horn\n",
      "- Dragon's Blood\n",
      "- Mermaid Tears\n",
      "- Fairy Dust\n",
      "- Goblin Toes\n",
      "- Witch's Brew\n",
      "- Griffin Claw\n",
      "- Troll Hair\n",
      "- Kraken Ink\n",
      "- Minotaur Horn\n",
      "- Basilisk Scale\n",
      "- Chimera Fang\n",
      "- Cured\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>Phoenix Feather</th>\n",
       "      <th>Unicorn Horn</th>\n",
       "      <th>Dragon's Blood</th>\n",
       "      <th>Mermaid Tears</th>\n",
       "      <th>Fairy Dust</th>\n",
       "      <th>Goblin Toes</th>\n",
       "      <th>Witch's Brew</th>\n",
       "      <th>Griffin Claw</th>\n",
       "      <th>Troll Hair</th>\n",
       "      <th>Kraken Ink</th>\n",
       "      <th>Minotaur Horn</th>\n",
       "      <th>Basilisk Scale</th>\n",
       "      <th>Chimera Fang</th>\n",
       "      <th>Cured</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.4</td>\n",
       "      <td>18.7</td>\n",
       "      <td>18.4</td>\n",
       "      <td>27.9</td>\n",
       "      <td>7.9</td>\n",
       "      <td>9.6</td>\n",
       "      <td>18.3</td>\n",
       "      <td>13.2</td>\n",
       "      <td>2.5</td>\n",
       "      <td>26.0</td>\n",
       "      <td>10.5</td>\n",
       "      <td>26.2</td>\n",
       "      <td>12.5</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>13.3</td>\n",
       "      <td>15.6</td>\n",
       "      <td>13.1</td>\n",
       "      <td>11.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>7.2</td>\n",
       "      <td>26.0</td>\n",
       "      <td>1.5</td>\n",
       "      <td>13.3</td>\n",
       "      <td>6.2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>17.2</td>\n",
       "      <td>13.9</td>\n",
       "      <td>23.8</td>\n",
       "      <td>6.8</td>\n",
       "      <td>10.7</td>\n",
       "      <td>15.8</td>\n",
       "      <td>19.4</td>\n",
       "      <td>2.7</td>\n",
       "      <td>15.4</td>\n",
       "      <td>21.2</td>\n",
       "      <td>11.1</td>\n",
       "      <td>16.6</td>\n",
       "      <td>11.4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8.4</td>\n",
       "      <td>9.7</td>\n",
       "      <td>6.8</td>\n",
       "      <td>26.9</td>\n",
       "      <td>4.6</td>\n",
       "      <td>29.1</td>\n",
       "      <td>14.6</td>\n",
       "      <td>19.7</td>\n",
       "      <td>18.0</td>\n",
       "      <td>20.8</td>\n",
       "      <td>13.6</td>\n",
       "      <td>13.9</td>\n",
       "      <td>8.1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>22.1</td>\n",
       "      <td>10.8</td>\n",
       "      <td>16.4</td>\n",
       "      <td>10.5</td>\n",
       "      <td>22.0</td>\n",
       "      <td>23.4</td>\n",
       "      <td>2.6</td>\n",
       "      <td>18.2</td>\n",
       "      <td>23.8</td>\n",
       "      <td>11.3</td>\n",
       "      <td>5.5</td>\n",
       "      <td>16.8</td>\n",
       "      <td>16.2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Phoenix Feather  Unicorn Horn  Dragon's Blood  Mermaid Tears  Fairy Dust  \\\n",
       "0              2.4          18.7            18.4           27.9         7.9   \n",
       "1              2.1           6.0            15.0           13.3        15.6   \n",
       "2             17.2          13.9            23.8            6.8        10.7   \n",
       "3              8.4           9.7             6.8           26.9         4.6   \n",
       "4             22.1          10.8            16.4           10.5        22.0   \n",
       "\n",
       "   Goblin Toes  Witch's Brew  Griffin Claw  Troll Hair  Kraken Ink  \\\n",
       "0          9.6          18.3          13.2         2.5        26.0   \n",
       "1         13.1          11.0           5.0         7.2        26.0   \n",
       "2         15.8          19.4           2.7        15.4        21.2   \n",
       "3         29.1          14.6          19.7        18.0        20.8   \n",
       "4         23.4           2.6          18.2        23.8        11.3   \n",
       "\n",
       "   Minotaur Horn  Basilisk Scale  Chimera Fang  Cured  \n",
       "0           10.5            26.2          12.5      0  \n",
       "1            1.5            13.3           6.2      0  \n",
       "2           11.1            16.6          11.4      1  \n",
       "3           13.6            13.9           8.1      1  \n",
       "4            5.5            16.8          16.2      0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "df = pd.read_csv(\"cure-the-princess.csv\")\n",
    "df.columns = df.columns.str.strip()\n",
    "\n",
    "print(\"Размер датасета:\", df.shape)\n",
    "print(\"\\nСтолбцы:\")\n",
    "for col in df.columns:\n",
    "    print(\"-\", col)\n",
    "\n",
    "display(df.head())\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3db74853",
   "metadata": {},
   "source": [
    "\n",
    "## 3. Выбор зависимой переменной\n",
    "\n",
    "Целевая переменная — **`Cured`**, так как она показывает результат лечения:\n",
    "- `1` — лечение успешно\n",
    "- `0` — лечение неуспешно\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "843db087",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Размер рабочей выборки: (2338, 14)\n",
      "\n",
      "Баланс классов:\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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Cured</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1177</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1161</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       count\n",
       "Cured       \n",
       "0       1177\n",
       "1       1161"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "target = \"Cured\"\n",
    "feature_cols = [col for col in df.columns if col != target]\n",
    "\n",
    "data = df[feature_cols + [target]].dropna().copy()\n",
    "\n",
    "print(\"Размер рабочей выборки:\", data.shape)\n",
    "print(\"\\nБаланс классов:\")\n",
    "display(data[target].value_counts().to_frame(\"count\"))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9d114749",
   "metadata": {},
   "source": [
    "## 4. Разделение выборки и масштабирование"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e911718e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train shape: (1870, 13)\n",
      "Test shape: (468, 13)\n"
     ]
    }
   ],
   "source": [
    "\n",
    "X = data[feature_cols].copy()\n",
    "y = data[target].copy()\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42, stratify=y\n",
    ")\n",
    "\n",
    "scaler = StandardScaler()\n",
    "X_train_scaled = scaler.fit_transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "print(\"Train shape:\", X_train.shape)\n",
    "print(\"Test shape:\", X_test.shape)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c5b47381",
   "metadata": {},
   "source": [
    "\n",
    "## 5. Базовый классификатор\n",
    "\n",
    "Используем **логистическую регрессию**:\n",
    "- это классификатор\n",
    "- по нему можно получить вероятности классов\n",
    "- в `statsmodels` удобно оценивать **значимость коэффициентов**\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "b8d2fcc1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                           Logit Regression Results                           \n",
      "==============================================================================\n",
      "Dep. Variable:                  Cured   No. Observations:                 1870\n",
      "Model:                          Logit   Df Residuals:                     1856\n",
      "Method:                           MLE   Df Model:                           13\n",
      "Date:                Fri, 13 Mar 2026   Pseudo R-squ.:                  0.5465\n",
      "Time:                        17:16:27   Log-Likelihood:                -587.82\n",
      "converged:                       True   LL-Null:                       -1296.1\n",
      "Covariance Type:            nonrobust   LLR p-value:                3.961e-295\n",
      "===================================================================================\n",
      "                      coef    std err          z      P>|z|      [0.025      0.975]\n",
      "-----------------------------------------------------------------------------------\n",
      "const               0.0314      0.080      0.393      0.695      -0.126       0.188\n",
      "Phoenix Feather    -1.6812      0.115    -14.557      0.000      -1.908      -1.455\n",
      "Unicorn Horn       -0.1402      0.075     -1.881      0.060      -0.286       0.006\n",
      "Dragon's Blood      0.3205      0.090      3.577      0.000       0.145       0.496\n",
      "Mermaid Tears      -1.8758      0.125    -15.024      0.000      -2.121      -1.631\n",
      "Fairy Dust         -0.9999      0.099    -10.129      0.000      -1.193      -0.806\n",
      "Goblin Toes        -0.9870      0.093    -10.592      0.000      -1.170      -0.804\n",
      "Witch's Brew        2.5197      0.134     18.757      0.000       2.256       2.783\n",
      "Griffin Claw        0.2998      0.089      3.386      0.001       0.126       0.473\n",
      "Troll Hair          3.7096      0.175     21.156      0.000       3.366       4.053\n",
      "Kraken Ink         -0.5656      0.090     -6.281      0.000      -0.742      -0.389\n",
      "Minotaur Horn       0.0226      0.074      0.304      0.761      -0.123       0.168\n",
      "Basilisk Scale     -0.9111      0.095     -9.570      0.000      -1.098      -0.724\n",
      "Chimera Fang       -0.0025      0.074     -0.034      0.973      -0.147       0.142\n",
      "===================================================================================\n"
     ]
    }
   ],
   "source": [
    "\n",
    "X_train_sm = sm.add_constant(pd.DataFrame(X_train_scaled, columns=feature_cols, index=X_train.index))\n",
    "X_test_sm = sm.add_constant(pd.DataFrame(X_test_scaled, columns=feature_cols, index=X_test.index))\n",
    "\n",
    "logit_full = sm.Logit(y_train, X_train_sm).fit(disp=False)\n",
    "print(logit_full.summary())\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "38079ef4",
   "metadata": {},
   "source": [
    "## 6. Метрики базового классификатора"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "0294012f",
   "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>Метрика</th>\n",
       "      <th>Значение</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Accuracy_train</td>\n",
       "      <td>8.802139e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Precision_train</td>\n",
       "      <td>8.722281e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Recall_train</td>\n",
       "      <td>8.891281e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>F1_train</td>\n",
       "      <td>8.805970e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ROC_AUC_train</td>\n",
       "      <td>9.419016e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Accuracy_test</td>\n",
       "      <td>8.504274e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Precision_test</td>\n",
       "      <td>8.432203e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Recall_test</td>\n",
       "      <td>8.577586e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>F1_test</td>\n",
       "      <td>8.504274e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>ROC_AUC_test</td>\n",
       "      <td>9.206239e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>LLR_pvalue</td>\n",
       "      <td>3.960606e-295</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Pseudo_R2</td>\n",
       "      <td>5.464871e-01</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Метрика       Значение\n",
       "0    Accuracy_train   8.802139e-01\n",
       "1   Precision_train   8.722281e-01\n",
       "2      Recall_train   8.891281e-01\n",
       "3          F1_train   8.805970e-01\n",
       "4     ROC_AUC_train   9.419016e-01\n",
       "5     Accuracy_test   8.504274e-01\n",
       "6    Precision_test   8.432203e-01\n",
       "7       Recall_test   8.577586e-01\n",
       "8           F1_test   8.504274e-01\n",
       "9      ROC_AUC_test   9.206239e-01\n",
       "10       LLR_pvalue  3.960606e-295\n",
       "11        Pseudo_R2   5.464871e-01"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "train_proba = logit_full.predict(X_train_sm)\n",
    "test_proba = logit_full.predict(X_test_sm)\n",
    "\n",
    "train_pred = (train_proba >= 0.5).astype(int)\n",
    "test_pred = (test_proba >= 0.5).astype(int)\n",
    "\n",
    "metrics_full = pd.DataFrame({\n",
    "    \"Метрика\": [\"Accuracy_train\", \"Precision_train\", \"Recall_train\", \"F1_train\", \"ROC_AUC_train\",\n",
    "                \"Accuracy_test\", \"Precision_test\", \"Recall_test\", \"F1_test\", \"ROC_AUC_test\",\n",
    "                \"LLR_pvalue\", \"Pseudo_R2\"],\n",
    "    \"Значение\": [\n",
    "        accuracy_score(y_train, train_pred),\n",
    "        precision_score(y_train, train_pred, zero_division=0),\n",
    "        recall_score(y_train, train_pred, zero_division=0),\n",
    "        f1_score(y_train, train_pred, zero_division=0),\n",
    "        roc_auc_score(y_train, train_proba),\n",
    "        accuracy_score(y_test, test_pred),\n",
    "        precision_score(y_test, test_pred, zero_division=0),\n",
    "        recall_score(y_test, test_pred, zero_division=0),\n",
    "        f1_score(y_test, test_pred, zero_division=0),\n",
    "        roc_auc_score(y_test, test_proba),\n",
    "        logit_full.llr_pvalue,\n",
    "        logit_full.prsquared\n",
    "    ]\n",
    "})\n",
    "\n",
    "display(metrics_full)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6cc77d3b",
   "metadata": {},
   "source": [
    "## 7. Коэффициенты и их значимость"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3a542dc3",
   "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>feature</th>\n",
       "      <th>coef</th>\n",
       "      <th>p_value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Troll Hair</td>\n",
       "      <td>3.709586</td>\n",
       "      <td>2.427009e-99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Witch's Brew</td>\n",
       "      <td>2.519683</td>\n",
       "      <td>1.692466e-78</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Mermaid Tears</td>\n",
       "      <td>-1.875814</td>\n",
       "      <td>5.099159e-51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Phoenix Feather</td>\n",
       "      <td>-1.681244</td>\n",
       "      <td>5.306743e-48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Goblin Toes</td>\n",
       "      <td>-0.987020</td>\n",
       "      <td>3.249975e-26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Fairy Dust</td>\n",
       "      <td>-0.999880</td>\n",
       "      <td>4.107500e-24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Basilisk Scale</td>\n",
       "      <td>-0.911095</td>\n",
       "      <td>1.072310e-21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Kraken Ink</td>\n",
       "      <td>-0.565601</td>\n",
       "      <td>3.372706e-10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Dragon's Blood</td>\n",
       "      <td>0.320525</td>\n",
       "      <td>3.481769e-04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Griffin Claw</td>\n",
       "      <td>0.299795</td>\n",
       "      <td>7.086295e-04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Unicorn Horn</td>\n",
       "      <td>-0.140190</td>\n",
       "      <td>6.002080e-02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>const</td>\n",
       "      <td>0.031440</td>\n",
       "      <td>6.946763e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Minotaur Horn</td>\n",
       "      <td>0.022553</td>\n",
       "      <td>7.611792e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Chimera Fang</td>\n",
       "      <td>-0.002480</td>\n",
       "      <td>9.732429e-01</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            feature      coef       p_value\n",
       "9        Troll Hair  3.709586  2.427009e-99\n",
       "7      Witch's Brew  2.519683  1.692466e-78\n",
       "4     Mermaid Tears -1.875814  5.099159e-51\n",
       "1   Phoenix Feather -1.681244  5.306743e-48\n",
       "6       Goblin Toes -0.987020  3.249975e-26\n",
       "5        Fairy Dust -0.999880  4.107500e-24\n",
       "12   Basilisk Scale -0.911095  1.072310e-21\n",
       "10       Kraken Ink -0.565601  3.372706e-10\n",
       "3    Dragon's Blood  0.320525  3.481769e-04\n",
       "8      Griffin Claw  0.299795  7.086295e-04\n",
       "2      Unicorn Horn -0.140190  6.002080e-02\n",
       "0             const  0.031440  6.946763e-01\n",
       "11    Minotaur Horn  0.022553  7.611792e-01\n",
       "13     Chimera Fang -0.002480  9.732429e-01"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "coef_table = pd.DataFrame({\n",
    "    \"feature\": logit_full.params.index,\n",
    "    \"coef\": logit_full.params.values,\n",
    "    \"p_value\": logit_full.pvalues.values\n",
    "}).sort_values(\"p_value\")\n",
    "\n",
    "display(coef_table)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3ebcdc74",
   "metadata": {},
   "source": [
    "## 8. Матрица ошибок и ROC-кривая"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "68a2f36f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Матрица ошибок (test):\n",
      "[[199  37]\n",
      " [ 33 199]]\n",
      "\n",
      "Classification report (test):\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.86      0.84      0.85       236\n",
      "           1       0.84      0.86      0.85       232\n",
      "\n",
      "    accuracy                           0.85       468\n",
      "   macro avg       0.85      0.85      0.85       468\n",
      "weighted avg       0.85      0.85      0.85       468\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "print(\"Матрица ошибок (test):\")\n",
    "print(confusion_matrix(y_test, test_pred))\n",
    "\n",
    "print(\"\\nClassification report (test):\")\n",
    "print(classification_report(y_test, test_pred, zero_division=0))\n",
    "\n",
    "RocCurveDisplay.from_predictions(y_test, test_proba)\n",
    "plt.title(\"ROC-кривая базового классификатора\")\n",
    "plt.grid(alpha=0.3)\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0b03a50a",
   "metadata": {},
   "source": [
    "\n",
    "## 9. Поиск аномалий\n",
    "\n",
    "Для устойчивого отбора используются три способа:\n",
    "1. **Isolation Forest**\n",
    "2. **Local Outlier Factor**\n",
    "3. **Расстояние до центра** в стандартизованном пространстве признаков\n",
    "\n",
    "Объект считается аномальным, если его отметили **минимум 2 из 3 методов**.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "2df8a0b2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Число аномалий: 101\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>Phoenix Feather</th>\n",
       "      <th>Unicorn Horn</th>\n",
       "      <th>Dragon's Blood</th>\n",
       "      <th>Mermaid Tears</th>\n",
       "      <th>Fairy Dust</th>\n",
       "      <th>Goblin Toes</th>\n",
       "      <th>Witch's Brew</th>\n",
       "      <th>Griffin Claw</th>\n",
       "      <th>Troll Hair</th>\n",
       "      <th>Kraken Ink</th>\n",
       "      <th>Minotaur Horn</th>\n",
       "      <th>Basilisk Scale</th>\n",
       "      <th>Chimera Fang</th>\n",
       "      <th>Cured</th>\n",
       "      <th>flag_iso</th>\n",
       "      <th>flag_lof</th>\n",
       "      <th>flag_dist</th>\n",
       "      <th>votes</th>\n",
       "      <th>anomaly</th>\n",
       "      <th>distance_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1217</th>\n",
       "      <td>16.4</td>\n",
       "      <td>9.6</td>\n",
       "      <td>29.4</td>\n",
       "      <td>16.8</td>\n",
       "      <td>39.4</td>\n",
       "      <td>9.7</td>\n",
       "      <td>17.5</td>\n",
       "      <td>34.1</td>\n",
       "      <td>42.9</td>\n",
       "      <td>10.8</td>\n",
       "      <td>2.8</td>\n",
       "      <td>37.6</td>\n",
       "      <td>19.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.842297</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1877</th>\n",
       "      <td>19.7</td>\n",
       "      <td>4.3</td>\n",
       "      <td>36.4</td>\n",
       "      <td>2.9</td>\n",
       "      <td>37.1</td>\n",
       "      <td>10.3</td>\n",
       "      <td>26.8</td>\n",
       "      <td>10.1</td>\n",
       "      <td>27.4</td>\n",
       "      <td>9.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>31.5</td>\n",
       "      <td>33.6</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.801140</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1980</th>\n",
       "      <td>6.4</td>\n",
       "      <td>33.5</td>\n",
       "      <td>7.1</td>\n",
       "      <td>1.9</td>\n",
       "      <td>34.2</td>\n",
       "      <td>8.4</td>\n",
       "      <td>9.9</td>\n",
       "      <td>37.9</td>\n",
       "      <td>2.3</td>\n",
       "      <td>15.3</td>\n",
       "      <td>22.2</td>\n",
       "      <td>11.6</td>\n",
       "      <td>11.2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.776760</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>262</th>\n",
       "      <td>11.1</td>\n",
       "      <td>32.6</td>\n",
       "      <td>40.2</td>\n",
       "      <td>8.5</td>\n",
       "      <td>36.0</td>\n",
       "      <td>16.5</td>\n",
       "      <td>18.7</td>\n",
       "      <td>25.1</td>\n",
       "      <td>30.0</td>\n",
       "      <td>9.5</td>\n",
       "      <td>23.1</td>\n",
       "      <td>12.4</td>\n",
       "      <td>20.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.754181</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>742</th>\n",
       "      <td>20.5</td>\n",
       "      <td>1.5</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>7.7</td>\n",
       "      <td>3.1</td>\n",
       "      <td>8.2</td>\n",
       "      <td>1.7</td>\n",
       "      <td>1.7</td>\n",
       "      <td>1.9</td>\n",
       "      <td>1.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>15.3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.707618</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1772</th>\n",
       "      <td>30.7</td>\n",
       "      <td>13.8</td>\n",
       "      <td>1.6</td>\n",
       "      <td>6.3</td>\n",
       "      <td>3.2</td>\n",
       "      <td>34.4</td>\n",
       "      <td>3.2</td>\n",
       "      <td>22.0</td>\n",
       "      <td>30.2</td>\n",
       "      <td>1.2</td>\n",
       "      <td>29.4</td>\n",
       "      <td>5.5</td>\n",
       "      <td>21.1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.695081</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>489</th>\n",
       "      <td>2.5</td>\n",
       "      <td>5.6</td>\n",
       "      <td>15.0</td>\n",
       "      <td>30.4</td>\n",
       "      <td>30.4</td>\n",
       "      <td>2.7</td>\n",
       "      <td>8.9</td>\n",
       "      <td>32.6</td>\n",
       "      <td>17.6</td>\n",
       "      <td>39.5</td>\n",
       "      <td>2.3</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.8</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.637498</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>552</th>\n",
       "      <td>17.1</td>\n",
       "      <td>25.1</td>\n",
       "      <td>4.1</td>\n",
       "      <td>1.2</td>\n",
       "      <td>33.9</td>\n",
       "      <td>17.2</td>\n",
       "      <td>16.3</td>\n",
       "      <td>35.6</td>\n",
       "      <td>9.2</td>\n",
       "      <td>3.2</td>\n",
       "      <td>30.6</td>\n",
       "      <td>14.4</td>\n",
       "      <td>9.8</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.595209</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2088</th>\n",
       "      <td>5.4</td>\n",
       "      <td>7.4</td>\n",
       "      <td>5.6</td>\n",
       "      <td>29.2</td>\n",
       "      <td>12.6</td>\n",
       "      <td>5.4</td>\n",
       "      <td>24.8</td>\n",
       "      <td>21.7</td>\n",
       "      <td>4.3</td>\n",
       "      <td>21.7</td>\n",
       "      <td>31.8</td>\n",
       "      <td>36.7</td>\n",
       "      <td>18.9</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.497393</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1501</th>\n",
       "      <td>15.1</td>\n",
       "      <td>8.8</td>\n",
       "      <td>39.2</td>\n",
       "      <td>31.4</td>\n",
       "      <td>1.5</td>\n",
       "      <td>25.3</td>\n",
       "      <td>30.0</td>\n",
       "      <td>9.8</td>\n",
       "      <td>18.8</td>\n",
       "      <td>18.0</td>\n",
       "      <td>4.2</td>\n",
       "      <td>34.8</td>\n",
       "      <td>9.7</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.468640</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1453</th>\n",
       "      <td>24.3</td>\n",
       "      <td>1.8</td>\n",
       "      <td>16.7</td>\n",
       "      <td>5.0</td>\n",
       "      <td>27.7</td>\n",
       "      <td>24.0</td>\n",
       "      <td>17.6</td>\n",
       "      <td>24.9</td>\n",
       "      <td>39.7</td>\n",
       "      <td>5.9</td>\n",
       "      <td>5.7</td>\n",
       "      <td>38.9</td>\n",
       "      <td>29.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.431958</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2249</th>\n",
       "      <td>6.5</td>\n",
       "      <td>32.2</td>\n",
       "      <td>28.5</td>\n",
       "      <td>33.4</td>\n",
       "      <td>4.0</td>\n",
       "      <td>20.4</td>\n",
       "      <td>27.5</td>\n",
       "      <td>10.9</td>\n",
       "      <td>31.5</td>\n",
       "      <td>21.2</td>\n",
       "      <td>5.7</td>\n",
       "      <td>16.1</td>\n",
       "      <td>16.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.386861</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>903</th>\n",
       "      <td>29.2</td>\n",
       "      <td>32.2</td>\n",
       "      <td>13.4</td>\n",
       "      <td>27.5</td>\n",
       "      <td>9.4</td>\n",
       "      <td>3.8</td>\n",
       "      <td>15.9</td>\n",
       "      <td>11.6</td>\n",
       "      <td>35.8</td>\n",
       "      <td>28.7</td>\n",
       "      <td>18.8</td>\n",
       "      <td>4.1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.358862</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>975</th>\n",
       "      <td>30.2</td>\n",
       "      <td>12.9</td>\n",
       "      <td>29.1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>21.4</td>\n",
       "      <td>6.7</td>\n",
       "      <td>10.0</td>\n",
       "      <td>18.2</td>\n",
       "      <td>2.1</td>\n",
       "      <td>33.4</td>\n",
       "      <td>36.4</td>\n",
       "      <td>18.8</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.355304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>603</th>\n",
       "      <td>16.9</td>\n",
       "      <td>4.4</td>\n",
       "      <td>1.2</td>\n",
       "      <td>30.6</td>\n",
       "      <td>10.3</td>\n",
       "      <td>28.5</td>\n",
       "      <td>22.5</td>\n",
       "      <td>24.5</td>\n",
       "      <td>33.7</td>\n",
       "      <td>35.7</td>\n",
       "      <td>7.5</td>\n",
       "      <td>2.8</td>\n",
       "      <td>17.3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.343218</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Phoenix Feather  Unicorn Horn  Dragon's Blood  Mermaid Tears  \\\n",
       "1217             16.4           9.6            29.4           16.8   \n",
       "1877             19.7           4.3            36.4            2.9   \n",
       "1980              6.4          33.5             7.1            1.9   \n",
       "262              11.1          32.6            40.2            8.5   \n",
       "742              20.5           1.5            38.0            1.9   \n",
       "1772             30.7          13.8             1.6            6.3   \n",
       "489               2.5           5.6            15.0           30.4   \n",
       "552              17.1          25.1             4.1            1.2   \n",
       "2088              5.4           7.4             5.6           29.2   \n",
       "1501             15.1           8.8            39.2           31.4   \n",
       "1453             24.3           1.8            16.7            5.0   \n",
       "2249              6.5          32.2            28.5           33.4   \n",
       "903              29.2          32.2            13.4           27.5   \n",
       "975              30.2          12.9            29.1            5.0   \n",
       "603              16.9           4.4             1.2           30.6   \n",
       "\n",
       "      Fairy Dust  Goblin Toes  Witch's Brew  Griffin Claw  Troll Hair  \\\n",
       "1217        39.4          9.7          17.5          34.1        42.9   \n",
       "1877        37.1         10.3          26.8          10.1        27.4   \n",
       "1980        34.2          8.4           9.9          37.9         2.3   \n",
       "262         36.0         16.5          18.7          25.1        30.0   \n",
       "742          7.7          3.1           8.2           1.7         1.7   \n",
       "1772         3.2         34.4           3.2          22.0        30.2   \n",
       "489         30.4          2.7           8.9          32.6        17.6   \n",
       "552         33.9         17.2          16.3          35.6         9.2   \n",
       "2088        12.6          5.4          24.8          21.7         4.3   \n",
       "1501         1.5         25.3          30.0           9.8        18.8   \n",
       "1453        27.7         24.0          17.6          24.9        39.7   \n",
       "2249         4.0         20.4          27.5          10.9        31.5   \n",
       "903          9.4          3.8          15.9          11.6        35.8   \n",
       "975          8.0         21.4           6.7          10.0        18.2   \n",
       "603         10.3         28.5          22.5          24.5        33.7   \n",
       "\n",
       "      Kraken Ink  Minotaur Horn  Basilisk Scale  Chimera Fang  Cured  \\\n",
       "1217        10.8            2.8            37.6          19.4      1   \n",
       "1877         9.6            3.1            31.5          33.6      1   \n",
       "1980        15.3           22.2            11.6          11.2      0   \n",
       "262          9.5           23.1            12.4          20.4      1   \n",
       "742          1.9            1.0            40.0          15.3      0   \n",
       "1772         1.2           29.4             5.5          21.1      1   \n",
       "489         39.5            2.3             5.4           2.8      0   \n",
       "552          3.2           30.6            14.4           9.8      1   \n",
       "2088        21.7           31.8            36.7          18.9      0   \n",
       "1501        18.0            4.2            34.8           9.7      1   \n",
       "1453         5.9            5.7            38.9          29.4      1   \n",
       "2249        21.2            5.7            16.1          16.0      1   \n",
       "903         28.7           18.8             4.1           2.0      0   \n",
       "975          2.1           33.4            36.4          18.8      0   \n",
       "603         35.7            7.5             2.8          17.3      1   \n",
       "\n",
       "      flag_iso  flag_lof  flag_dist  votes  anomaly  distance_score  \n",
       "1217         1         1          1      3        1        5.842297  \n",
       "1877         1         1          1      3        1        5.801140  \n",
       "1980         1         1          1      3        1        5.776760  \n",
       "262          1         1          1      3        1        5.754181  \n",
       "742          1         1          1      3        1        5.707618  \n",
       "1772         1         1          1      3        1        5.695081  \n",
       "489          1         1          1      3        1        5.637498  \n",
       "552          1         1          1      3        1        5.595209  \n",
       "2088         1         1          1      3        1        5.497393  \n",
       "1501         1         1          1      3        1        5.468640  \n",
       "1453         1         1          1      3        1        5.431958  \n",
       "2249         1         1          1      3        1        5.386861  \n",
       "903          1         1          1      3        1        5.358862  \n",
       "975          1         1          1      3        1        5.355304  \n",
       "603          1         1          1      3        1        5.343218  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "X_all_scaled = pd.DataFrame(\n",
    "    scaler.fit_transform(X),\n",
    "    columns=feature_cols,\n",
    "    index=X.index\n",
    ")\n",
    "\n",
    "# 1. Isolation Forest\n",
    "iso = IsolationForest(contamination=0.05, random_state=42)\n",
    "flag_iso = (iso.fit_predict(X_all_scaled) == -1).astype(int)\n",
    "\n",
    "# 2. LOF\n",
    "lof = LocalOutlierFactor(n_neighbors=20, contamination=0.05)\n",
    "flag_lof = (lof.fit_predict(X_all_scaled) == -1).astype(int)\n",
    "\n",
    "# 3. Distance from center\n",
    "center = X_all_scaled.mean(axis=0)\n",
    "dist = np.sqrt(((X_all_scaled - center) ** 2).sum(axis=1))\n",
    "dist_threshold = np.percentile(dist, 95)\n",
    "flag_dist = (dist >= dist_threshold).astype(int)\n",
    "\n",
    "anomaly_df = data.copy()\n",
    "anomaly_df[\"flag_iso\"] = flag_iso\n",
    "anomaly_df[\"flag_lof\"] = flag_lof\n",
    "anomaly_df[\"flag_dist\"] = flag_dist\n",
    "anomaly_df[\"votes\"] = anomaly_df[[\"flag_iso\", \"flag_lof\", \"flag_dist\"]].sum(axis=1)\n",
    "anomaly_df[\"anomaly\"] = (anomaly_df[\"votes\"] >= 2).astype(int)\n",
    "anomaly_df[\"distance_score\"] = dist\n",
    "\n",
    "print(\"Число аномалий:\", int(anomaly_df[\"anomaly\"].sum()))\n",
    "display(anomaly_df.sort_values([\"votes\", \"distance_score\"], ascending=[False, False]).head(15))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c8ad363c",
   "metadata": {},
   "source": [
    "## 10. Наиболее аномальные объекты"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "06616784",
   "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>Phoenix Feather</th>\n",
       "      <th>Unicorn Horn</th>\n",
       "      <th>Dragon's Blood</th>\n",
       "      <th>Mermaid Tears</th>\n",
       "      <th>Fairy Dust</th>\n",
       "      <th>Goblin Toes</th>\n",
       "      <th>Witch's Brew</th>\n",
       "      <th>Griffin Claw</th>\n",
       "      <th>Troll Hair</th>\n",
       "      <th>Kraken Ink</th>\n",
       "      <th>Minotaur Horn</th>\n",
       "      <th>Basilisk Scale</th>\n",
       "      <th>Chimera Fang</th>\n",
       "      <th>Cured</th>\n",
       "      <th>flag_iso</th>\n",
       "      <th>flag_lof</th>\n",
       "      <th>flag_dist</th>\n",
       "      <th>votes</th>\n",
       "      <th>anomaly</th>\n",
       "      <th>distance_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1217</th>\n",
       "      <td>16.4</td>\n",
       "      <td>9.6</td>\n",
       "      <td>29.4</td>\n",
       "      <td>16.8</td>\n",
       "      <td>39.4</td>\n",
       "      <td>9.7</td>\n",
       "      <td>17.5</td>\n",
       "      <td>34.1</td>\n",
       "      <td>42.9</td>\n",
       "      <td>10.8</td>\n",
       "      <td>2.8</td>\n",
       "      <td>37.6</td>\n",
       "      <td>19.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.842297</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1877</th>\n",
       "      <td>19.7</td>\n",
       "      <td>4.3</td>\n",
       "      <td>36.4</td>\n",
       "      <td>2.9</td>\n",
       "      <td>37.1</td>\n",
       "      <td>10.3</td>\n",
       "      <td>26.8</td>\n",
       "      <td>10.1</td>\n",
       "      <td>27.4</td>\n",
       "      <td>9.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>31.5</td>\n",
       "      <td>33.6</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.801140</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1980</th>\n",
       "      <td>6.4</td>\n",
       "      <td>33.5</td>\n",
       "      <td>7.1</td>\n",
       "      <td>1.9</td>\n",
       "      <td>34.2</td>\n",
       "      <td>8.4</td>\n",
       "      <td>9.9</td>\n",
       "      <td>37.9</td>\n",
       "      <td>2.3</td>\n",
       "      <td>15.3</td>\n",
       "      <td>22.2</td>\n",
       "      <td>11.6</td>\n",
       "      <td>11.2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.776760</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>262</th>\n",
       "      <td>11.1</td>\n",
       "      <td>32.6</td>\n",
       "      <td>40.2</td>\n",
       "      <td>8.5</td>\n",
       "      <td>36.0</td>\n",
       "      <td>16.5</td>\n",
       "      <td>18.7</td>\n",
       "      <td>25.1</td>\n",
       "      <td>30.0</td>\n",
       "      <td>9.5</td>\n",
       "      <td>23.1</td>\n",
       "      <td>12.4</td>\n",
       "      <td>20.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.754181</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>742</th>\n",
       "      <td>20.5</td>\n",
       "      <td>1.5</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>7.7</td>\n",
       "      <td>3.1</td>\n",
       "      <td>8.2</td>\n",
       "      <td>1.7</td>\n",
       "      <td>1.7</td>\n",
       "      <td>1.9</td>\n",
       "      <td>1.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>15.3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.707618</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1772</th>\n",
       "      <td>30.7</td>\n",
       "      <td>13.8</td>\n",
       "      <td>1.6</td>\n",
       "      <td>6.3</td>\n",
       "      <td>3.2</td>\n",
       "      <td>34.4</td>\n",
       "      <td>3.2</td>\n",
       "      <td>22.0</td>\n",
       "      <td>30.2</td>\n",
       "      <td>1.2</td>\n",
       "      <td>29.4</td>\n",
       "      <td>5.5</td>\n",
       "      <td>21.1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.695081</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>489</th>\n",
       "      <td>2.5</td>\n",
       "      <td>5.6</td>\n",
       "      <td>15.0</td>\n",
       "      <td>30.4</td>\n",
       "      <td>30.4</td>\n",
       "      <td>2.7</td>\n",
       "      <td>8.9</td>\n",
       "      <td>32.6</td>\n",
       "      <td>17.6</td>\n",
       "      <td>39.5</td>\n",
       "      <td>2.3</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.8</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.637498</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>552</th>\n",
       "      <td>17.1</td>\n",
       "      <td>25.1</td>\n",
       "      <td>4.1</td>\n",
       "      <td>1.2</td>\n",
       "      <td>33.9</td>\n",
       "      <td>17.2</td>\n",
       "      <td>16.3</td>\n",
       "      <td>35.6</td>\n",
       "      <td>9.2</td>\n",
       "      <td>3.2</td>\n",
       "      <td>30.6</td>\n",
       "      <td>14.4</td>\n",
       "      <td>9.8</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.595209</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2088</th>\n",
       "      <td>5.4</td>\n",
       "      <td>7.4</td>\n",
       "      <td>5.6</td>\n",
       "      <td>29.2</td>\n",
       "      <td>12.6</td>\n",
       "      <td>5.4</td>\n",
       "      <td>24.8</td>\n",
       "      <td>21.7</td>\n",
       "      <td>4.3</td>\n",
       "      <td>21.7</td>\n",
       "      <td>31.8</td>\n",
       "      <td>36.7</td>\n",
       "      <td>18.9</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.497393</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1501</th>\n",
       "      <td>15.1</td>\n",
       "      <td>8.8</td>\n",
       "      <td>39.2</td>\n",
       "      <td>31.4</td>\n",
       "      <td>1.5</td>\n",
       "      <td>25.3</td>\n",
       "      <td>30.0</td>\n",
       "      <td>9.8</td>\n",
       "      <td>18.8</td>\n",
       "      <td>18.0</td>\n",
       "      <td>4.2</td>\n",
       "      <td>34.8</td>\n",
       "      <td>9.7</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.468640</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Phoenix Feather  Unicorn Horn  Dragon's Blood  Mermaid Tears  \\\n",
       "1217             16.4           9.6            29.4           16.8   \n",
       "1877             19.7           4.3            36.4            2.9   \n",
       "1980              6.4          33.5             7.1            1.9   \n",
       "262              11.1          32.6            40.2            8.5   \n",
       "742              20.5           1.5            38.0            1.9   \n",
       "1772             30.7          13.8             1.6            6.3   \n",
       "489               2.5           5.6            15.0           30.4   \n",
       "552              17.1          25.1             4.1            1.2   \n",
       "2088              5.4           7.4             5.6           29.2   \n",
       "1501             15.1           8.8            39.2           31.4   \n",
       "\n",
       "      Fairy Dust  Goblin Toes  Witch's Brew  Griffin Claw  Troll Hair  \\\n",
       "1217        39.4          9.7          17.5          34.1        42.9   \n",
       "1877        37.1         10.3          26.8          10.1        27.4   \n",
       "1980        34.2          8.4           9.9          37.9         2.3   \n",
       "262         36.0         16.5          18.7          25.1        30.0   \n",
       "742          7.7          3.1           8.2           1.7         1.7   \n",
       "1772         3.2         34.4           3.2          22.0        30.2   \n",
       "489         30.4          2.7           8.9          32.6        17.6   \n",
       "552         33.9         17.2          16.3          35.6         9.2   \n",
       "2088        12.6          5.4          24.8          21.7         4.3   \n",
       "1501         1.5         25.3          30.0           9.8        18.8   \n",
       "\n",
       "      Kraken Ink  Minotaur Horn  Basilisk Scale  Chimera Fang  Cured  \\\n",
       "1217        10.8            2.8            37.6          19.4      1   \n",
       "1877         9.6            3.1            31.5          33.6      1   \n",
       "1980        15.3           22.2            11.6          11.2      0   \n",
       "262          9.5           23.1            12.4          20.4      1   \n",
       "742          1.9            1.0            40.0          15.3      0   \n",
       "1772         1.2           29.4             5.5          21.1      1   \n",
       "489         39.5            2.3             5.4           2.8      0   \n",
       "552          3.2           30.6            14.4           9.8      1   \n",
       "2088        21.7           31.8            36.7          18.9      0   \n",
       "1501        18.0            4.2            34.8           9.7      1   \n",
       "\n",
       "      flag_iso  flag_lof  flag_dist  votes  anomaly  distance_score  \n",
       "1217         1         1          1      3        1        5.842297  \n",
       "1877         1         1          1      3        1        5.801140  \n",
       "1980         1         1          1      3        1        5.776760  \n",
       "262          1         1          1      3        1        5.754181  \n",
       "742          1         1          1      3        1        5.707618  \n",
       "1772         1         1          1      3        1        5.695081  \n",
       "489          1         1          1      3        1        5.637498  \n",
       "552          1         1          1      3        1        5.595209  \n",
       "2088         1         1          1      3        1        5.497393  \n",
       "1501         1         1          1      3        1        5.468640  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "most_anomalous = anomaly_df[anomaly_df[\"anomaly\"] == 1].copy()\n",
    "most_anomalous = most_anomalous.sort_values([\"votes\", \"distance_score\"], ascending=[False, False])\n",
    "\n",
    "display(most_anomalous.head(10))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "591a67c4",
   "metadata": {},
   "source": [
    "## 11. Визуализация аномалий"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "9f3ba123",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X_2d = pca.fit_transform(X_all_scaled)\n",
    "\n",
    "plt.figure(figsize=(8, 6))\n",
    "plt.scatter(X_2d[:, 0], X_2d[:, 1], alpha=0.6, label=\"Объекты\")\n",
    "idx = anomaly_df[anomaly_df[\"anomaly\"] == 1].index\n",
    "if len(idx) > 0:\n",
    "    plt.scatter(X_2d[data.index.get_indexer(idx), 0], X_2d[data.index.get_indexer(idx), 1],\n",
    "                marker=\"x\", s=80, label=\"Аномалии\")\n",
    "plt.xlabel(\"PCA 1\")\n",
    "plt.ylabel(\"PCA 2\")\n",
    "plt.title(\"Аномалии в проекции PCA\")\n",
    "plt.legend()\n",
    "plt.grid(alpha=0.3)\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fa2aecbe",
   "metadata": {},
   "source": [
    "## 12. Удаление аномалий и повторная классификация"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "32eb9c23",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Размер выборки до очистки: 2338\n",
      "Размер выборки после очистки: 2237\n",
      "                           Logit Regression Results                           \n",
      "==============================================================================\n",
      "Dep. Variable:                  Cured   No. Observations:                 1789\n",
      "Model:                          Logit   Df Residuals:                     1775\n",
      "Method:                           MLE   Df Model:                           13\n",
      "Date:                Fri, 13 Mar 2026   Pseudo R-squ.:                  0.5402\n",
      "Time:                        17:16:27   Log-Likelihood:                -570.06\n",
      "converged:                       True   LL-Null:                       -1239.9\n",
      "Covariance Type:            nonrobust   LLR p-value:                1.528e-278\n",
      "===================================================================================\n",
      "                      coef    std err          z      P>|z|      [0.025      0.975]\n",
      "-----------------------------------------------------------------------------------\n",
      "const              -0.0318      0.080     -0.396      0.692      -0.189       0.126\n",
      "Phoenix Feather    -1.6361      0.115    -14.250      0.000      -1.861      -1.411\n",
      "Unicorn Horn       -0.1047      0.076     -1.372      0.170      -0.254       0.045\n",
      "Dragon's Blood      0.2372      0.089      2.653      0.008       0.062       0.412\n",
      "Mermaid Tears      -1.7899      0.124    -14.394      0.000      -2.034      -1.546\n",
      "Fairy Dust         -0.9316      0.098     -9.469      0.000      -1.124      -0.739\n",
      "Goblin Toes        -0.9553      0.094    -10.201      0.000      -1.139      -0.772\n",
      "Witch's Brew        2.4251      0.132     18.378      0.000       2.167       2.684\n",
      "Griffin Claw        0.3923      0.089      4.396      0.000       0.217       0.567\n",
      "Troll Hair          3.6533      0.175     20.877      0.000       3.310       3.996\n",
      "Kraken Ink         -0.6065      0.093     -6.503      0.000      -0.789      -0.424\n",
      "Minotaur Horn      -0.0097      0.075     -0.129      0.898      -0.157       0.138\n",
      "Basilisk Scale     -0.8750      0.094     -9.276      0.000      -1.060      -0.690\n",
      "Chimera Fang        0.0213      0.075      0.285      0.775      -0.125       0.167\n",
      "===================================================================================\n"
     ]
    }
   ],
   "source": [
    "\n",
    "clean_data = anomaly_df[anomaly_df[\"anomaly\"] == 0][feature_cols + [target]].copy()\n",
    "\n",
    "X_clean = clean_data[feature_cols]\n",
    "y_clean = clean_data[target]\n",
    "\n",
    "X_train_c, X_test_c, y_train_c, y_test_c = train_test_split(\n",
    "    X_clean, y_clean, test_size=0.2, random_state=42, stratify=y_clean\n",
    ")\n",
    "\n",
    "scaler_clean = StandardScaler()\n",
    "X_train_c_scaled = scaler_clean.fit_transform(X_train_c)\n",
    "X_test_c_scaled = scaler_clean.transform(X_test_c)\n",
    "\n",
    "X_train_c_sm = sm.add_constant(pd.DataFrame(X_train_c_scaled, columns=feature_cols, index=X_train_c.index))\n",
    "X_test_c_sm = sm.add_constant(pd.DataFrame(X_test_c_scaled, columns=feature_cols, index=X_test_c.index))\n",
    "\n",
    "logit_clean = sm.Logit(y_train_c, X_train_c_sm).fit(disp=False)\n",
    "print(\"Размер выборки до очистки:\", len(data))\n",
    "print(\"Размер выборки после очистки:\", len(clean_data))\n",
    "print(logit_clean.summary())\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "67a36b21",
   "metadata": {},
   "source": [
    "## 13. Метрики после очистки"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "35696f0b",
   "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>Метрика</th>\n",
       "      <th>Значение</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Accuracy_train_clean</td>\n",
       "      <td>8.731135e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Precision_train_clean</td>\n",
       "      <td>8.660714e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Recall_train_clean</td>\n",
       "      <td>8.788222e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>F1_train_clean</td>\n",
       "      <td>8.724002e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ROC_AUC_train_clean</td>\n",
       "      <td>9.388173e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Accuracy_test_clean</td>\n",
       "      <td>8.504464e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Precision_test_clean</td>\n",
       "      <td>8.737864e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Recall_test_clean</td>\n",
       "      <td>8.144796e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>F1_test_clean</td>\n",
       "      <td>8.430913e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>ROC_AUC_test_clean</td>\n",
       "      <td>9.318078e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>LLR_pvalue_clean</td>\n",
       "      <td>1.527696e-278</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Pseudo_R2_clean</td>\n",
       "      <td>5.402317e-01</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  Метрика       Значение\n",
       "0    Accuracy_train_clean   8.731135e-01\n",
       "1   Precision_train_clean   8.660714e-01\n",
       "2      Recall_train_clean   8.788222e-01\n",
       "3          F1_train_clean   8.724002e-01\n",
       "4     ROC_AUC_train_clean   9.388173e-01\n",
       "5     Accuracy_test_clean   8.504464e-01\n",
       "6    Precision_test_clean   8.737864e-01\n",
       "7       Recall_test_clean   8.144796e-01\n",
       "8           F1_test_clean   8.430913e-01\n",
       "9      ROC_AUC_test_clean   9.318078e-01\n",
       "10       LLR_pvalue_clean  1.527696e-278\n",
       "11        Pseudo_R2_clean   5.402317e-01"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "train_proba_c = logit_clean.predict(X_train_c_sm)\n",
    "test_proba_c = logit_clean.predict(X_test_c_sm)\n",
    "\n",
    "train_pred_c = (train_proba_c >= 0.5).astype(int)\n",
    "test_pred_c = (test_proba_c >= 0.5).astype(int)\n",
    "\n",
    "metrics_clean = pd.DataFrame({\n",
    "    \"Метрика\": [\"Accuracy_train_clean\", \"Precision_train_clean\", \"Recall_train_clean\", \"F1_train_clean\", \"ROC_AUC_train_clean\",\n",
    "                \"Accuracy_test_clean\", \"Precision_test_clean\", \"Recall_test_clean\", \"F1_test_clean\", \"ROC_AUC_test_clean\",\n",
    "                \"LLR_pvalue_clean\", \"Pseudo_R2_clean\"],\n",
    "    \"Значение\": [\n",
    "        accuracy_score(y_train_c, train_pred_c),\n",
    "        precision_score(y_train_c, train_pred_c, zero_division=0),\n",
    "        recall_score(y_train_c, train_pred_c, zero_division=0),\n",
    "        f1_score(y_train_c, train_pred_c, zero_division=0),\n",
    "        roc_auc_score(y_train_c, train_proba_c),\n",
    "        accuracy_score(y_test_c, test_pred_c),\n",
    "        precision_score(y_test_c, test_pred_c, zero_division=0),\n",
    "        recall_score(y_test_c, test_pred_c, zero_division=0),\n",
    "        f1_score(y_test_c, test_pred_c, zero_division=0),\n",
    "        roc_auc_score(y_test_c, test_proba_c),\n",
    "        logit_clean.llr_pvalue,\n",
    "        logit_clean.prsquared\n",
    "    ]\n",
    "})\n",
    "\n",
    "display(metrics_clean)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5b7d61e2",
   "metadata": {},
   "source": [
    "## 14. Сравнение моделей"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "26bfe5b9",
   "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>Показатель</th>\n",
       "      <th>До очистки</th>\n",
       "      <th>После очистки</th>\n",
       "      <th>Изменение</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Accuracy_test</td>\n",
       "      <td>0.850427</td>\n",
       "      <td>0.850446</td>\n",
       "      <td>0.000019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Precision_test</td>\n",
       "      <td>0.843220</td>\n",
       "      <td>0.873786</td>\n",
       "      <td>0.030566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Recall_test</td>\n",
       "      <td>0.857759</td>\n",
       "      <td>0.814480</td>\n",
       "      <td>-0.043279</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>F1_test</td>\n",
       "      <td>0.850427</td>\n",
       "      <td>0.843091</td>\n",
       "      <td>-0.007336</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ROC_AUC_test</td>\n",
       "      <td>0.920624</td>\n",
       "      <td>0.931808</td>\n",
       "      <td>0.011184</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Pseudo_R2</td>\n",
       "      <td>0.546487</td>\n",
       "      <td>0.540232</td>\n",
       "      <td>-0.006255</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Показатель  До очистки  После очистки  Изменение\n",
       "0   Accuracy_test    0.850427       0.850446   0.000019\n",
       "1  Precision_test    0.843220       0.873786   0.030566\n",
       "2     Recall_test    0.857759       0.814480  -0.043279\n",
       "3         F1_test    0.850427       0.843091  -0.007336\n",
       "4    ROC_AUC_test    0.920624       0.931808   0.011184\n",
       "5       Pseudo_R2    0.546487       0.540232  -0.006255"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "compare = pd.DataFrame({\n",
    "    \"Показатель\": [\"Accuracy_test\", \"Precision_test\", \"Recall_test\", \"F1_test\", \"ROC_AUC_test\", \"Pseudo_R2\"],\n",
    "    \"До очистки\": [\n",
    "        accuracy_score(y_test, test_pred),\n",
    "        precision_score(y_test, test_pred, zero_division=0),\n",
    "        recall_score(y_test, test_pred, zero_division=0),\n",
    "        f1_score(y_test, test_pred, zero_division=0),\n",
    "        roc_auc_score(y_test, test_proba),\n",
    "        logit_full.prsquared\n",
    "    ],\n",
    "    \"После очистки\": [\n",
    "        accuracy_score(y_test_c, test_pred_c),\n",
    "        precision_score(y_test_c, test_pred_c, zero_division=0),\n",
    "        recall_score(y_test_c, test_pred_c, zero_division=0),\n",
    "        f1_score(y_test_c, test_pred_c, zero_division=0),\n",
    "        roc_auc_score(y_test_c, test_proba_c),\n",
    "        logit_clean.prsquared\n",
    "    ]\n",
    "})\n",
    "\n",
    "compare[\"Изменение\"] = compare[\"После очистки\"] - compare[\"До очистки\"]\n",
    "display(compare)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e816f6cc",
   "metadata": {},
   "source": [
    "## 15. Сравнение коэффициентов"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "6b04a997",
   "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>coef_before</th>\n",
       "      <th>coef_after</th>\n",
       "      <th>abs_change</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Witch's Brew</th>\n",
       "      <td>2.519683</td>\n",
       "      <td>2.425143</td>\n",
       "      <td>0.094541</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Griffin Claw</th>\n",
       "      <td>0.299795</td>\n",
       "      <td>0.392268</td>\n",
       "      <td>0.092473</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mermaid Tears</th>\n",
       "      <td>-1.875814</td>\n",
       "      <td>-1.789872</td>\n",
       "      <td>0.085942</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Dragon's Blood</th>\n",
       "      <td>0.320525</td>\n",
       "      <td>0.237213</td>\n",
       "      <td>0.083312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Fairy Dust</th>\n",
       "      <td>-0.999880</td>\n",
       "      <td>-0.931611</td>\n",
       "      <td>0.068269</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>const</th>\n",
       "      <td>0.031440</td>\n",
       "      <td>-0.031828</td>\n",
       "      <td>0.063269</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Troll Hair</th>\n",
       "      <td>3.709586</td>\n",
       "      <td>3.653267</td>\n",
       "      <td>0.056319</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Phoenix Feather</th>\n",
       "      <td>-1.681244</td>\n",
       "      <td>-1.636082</td>\n",
       "      <td>0.045163</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kraken Ink</th>\n",
       "      <td>-0.565601</td>\n",
       "      <td>-0.606530</td>\n",
       "      <td>0.040928</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Basilisk Scale</th>\n",
       "      <td>-0.911095</td>\n",
       "      <td>-0.874988</td>\n",
       "      <td>0.036108</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Unicorn Horn</th>\n",
       "      <td>-0.140190</td>\n",
       "      <td>-0.104685</td>\n",
       "      <td>0.035504</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Minotaur Horn</th>\n",
       "      <td>0.022553</td>\n",
       "      <td>-0.009679</td>\n",
       "      <td>0.032233</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Goblin Toes</th>\n",
       "      <td>-0.987020</td>\n",
       "      <td>-0.955282</td>\n",
       "      <td>0.031738</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chimera Fang</th>\n",
       "      <td>-0.002480</td>\n",
       "      <td>0.021279</td>\n",
       "      <td>0.023758</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 coef_before  coef_after  abs_change\n",
       "Witch's Brew        2.519683    2.425143    0.094541\n",
       "Griffin Claw        0.299795    0.392268    0.092473\n",
       "Mermaid Tears      -1.875814   -1.789872    0.085942\n",
       "Dragon's Blood      0.320525    0.237213    0.083312\n",
       "Fairy Dust         -0.999880   -0.931611    0.068269\n",
       "const               0.031440   -0.031828    0.063269\n",
       "Troll Hair          3.709586    3.653267    0.056319\n",
       "Phoenix Feather    -1.681244   -1.636082    0.045163\n",
       "Kraken Ink         -0.565601   -0.606530    0.040928\n",
       "Basilisk Scale     -0.911095   -0.874988    0.036108\n",
       "Unicorn Horn       -0.140190   -0.104685    0.035504\n",
       "Minotaur Horn       0.022553   -0.009679    0.032233\n",
       "Goblin Toes        -0.987020   -0.955282    0.031738\n",
       "Chimera Fang       -0.002480    0.021279    0.023758"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "coef_compare = pd.DataFrame({\n",
    "    \"coef_before\": logit_full.params,\n",
    "    \"coef_after\": logit_clean.params\n",
    "}).fillna(0)\n",
    "\n",
    "coef_compare[\"abs_change\"] = (coef_compare[\"coef_after\"] - coef_compare[\"coef_before\"]).abs()\n",
    "display(coef_compare.sort_values(\"abs_change\", ascending=False))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d619cfba",
   "metadata": {},
   "source": [
    "\n",
    "## 16. Итог\n",
    "\n",
    "Целевая переменная — **`Cured`**, отражающая успешность лечения принцессы.\n",
    "\n",
    "### Базовый классификатор\n",
    "Использована **логистическая регрессия**.\n",
    "\n",
    "Качество модели на тестовой выборке:\n",
    "- **Accuracy ≈ 0.85**\n",
    "- **Precision ≈ 0.84**\n",
    "- **Recall ≈ 0.86**\n",
    "- **F1 ≈ 0.85**\n",
    "- **ROC‑AUC ≈ 0.92**\n",
    "\n",
    "Модель статистически значима:\n",
    "- **LLR p‑value = 3.96e‑295**\n",
    "- **Pseudo R² ≈ 0.55**\n",
    "\n",
    "Наиболее значимые признаки (p < 0.001):\n",
    "- **Troll Hair**\n",
    "- **Witch's Brew**\n",
    "- **Mermaid Tears**\n",
    "- **Phoenix Feather**\n",
    "- **Goblin Toes**\n",
    "- **Fairy Dust**\n",
    "- **Basilisk Scale**\n",
    "\n",
    "### Аномалии\n",
    "Консенсусом трёх методов (Isolation Forest, LOF и расстояние до центра) найдено **101 аномальное наблюдение**.\n",
    "\n",
    "Эти объекты характеризуются **крайними значениями ингредиентов** (например, очень большие значения Troll Hair, Fairy Dust, Basilisk Scale или Dragon's Blood), что делает их сильно удалёнными от основной массы наблюдений.\n",
    "\n",
    "### Классификация после удаления аномалий\n",
    "После удаления аномалий была обучена модель логистической регрессии на очищенной выборке.\n",
    "\n",
    "Основные изменения:\n",
    "- структура коэффициентов практически не изменилась\n",
    "- значимость ключевых признаков сохранилась\n",
    "- метрики качества изменились незначительно\n",
    "\n",
    "### Сравнение моделей\n",
    "Удаление аномалий:\n",
    "- немного стабилизировало модель\n",
    "- уменьшило влияние экстремальных наблюдений\n",
    "- **не привело к существенному изменению точности классификации**\n",
    "\n",
    "### Вывод\n",
    "Логистическая регрессия хорошо описывает зависимость между ингредиентами и результатом лечения.  \n",
    "Основное влияние на успех лечения оказывают **Troll Hair, Witch's Brew, Mermaid Tears и Phoenix Feather**.  \n",
    "\n",
    "Аномальные наблюдения присутствуют в данных, однако их удаление **не оказывает сильного влияния на точность классификации**, что говорит о достаточной устойчивости исходной модели.\n"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}
