MII_Salin_Oleg_PIbd-33/lec2.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Загрузка данных в DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 19237 entries, 45654403 to 45813273\n",
      "Data columns (total 17 columns):\n",
      " #   Column           Non-Null Count  Dtype  \n",
      "---  ------           --------------  -----  \n",
      " 0   Price            19237 non-null  int64  \n",
      " 1   Levy             19237 non-null  object \n",
      " 2   Manufacturer     19237 non-null  object \n",
      " 3   Model            19237 non-null  object \n",
      " 4   Prodyear         19237 non-null  int64  \n",
      " 5   Category         19237 non-null  object \n",
      " 6   Leatherinterior  19237 non-null  object \n",
      " 7   Fueltype         19237 non-null  object \n",
      " 8   Engine volume    19237 non-null  object \n",
      " 9   Mileage          19237 non-null  object \n",
      " 10  Cylinders        19237 non-null  float64\n",
      " 11  Gear box type    19237 non-null  object \n",
      " 12  Drive wheels     19237 non-null  object \n",
      " 13  Doors            19237 non-null  object \n",
      " 14  Wheel            19237 non-null  object \n",
      " 15  Color            19237 non-null  object \n",
      " 16  Airbags          19237 non-null  int64  \n",
      "dtypes: float64(1), int64(3), object(13)\n",
      "memory usage: 2.6+ MB\n",
      "(19237, 17)\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>Price</th>\n",
       "      <th>Levy</th>\n",
       "      <th>Manufacturer</th>\n",
       "      <th>Model</th>\n",
       "      <th>Prodyear</th>\n",
       "      <th>Category</th>\n",
       "      <th>Leatherinterior</th>\n",
       "      <th>Fueltype</th>\n",
       "      <th>Engine volume</th>\n",
       "      <th>Mileage</th>\n",
       "      <th>Cylinders</th>\n",
       "      <th>Gear box type</th>\n",
       "      <th>Drive wheels</th>\n",
       "      <th>Doors</th>\n",
       "      <th>Wheel</th>\n",
       "      <th>Color</th>\n",
       "      <th>Airbags</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ID</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>45654403</th>\n",
       "      <td>13328</td>\n",
       "      <td>1399</td>\n",
       "      <td>LEXUS</td>\n",
       "      <td>RX 450</td>\n",
       "      <td>2010</td>\n",
       "      <td>Jeep</td>\n",
       "      <td>1</td>\n",
       "      <td>Hybrid</td>\n",
       "      <td>3.5</td>\n",
       "      <td>186005 km</td>\n",
       "      <td>6.0</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>4x4</td>\n",
       "      <td>04-May</td>\n",
       "      <td>Left wheel</td>\n",
       "      <td>Silver</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44731507</th>\n",
       "      <td>16621</td>\n",
       "      <td>1018</td>\n",
       "      <td>CHEVROLET</td>\n",
       "      <td>Equinox</td>\n",
       "      <td>2011</td>\n",
       "      <td>Jeep</td>\n",
       "      <td>0</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>3</td>\n",
       "      <td>192000 km</td>\n",
       "      <td>6.0</td>\n",
       "      <td>Tiptronic</td>\n",
       "      <td>4x4</td>\n",
       "      <td>04-May</td>\n",
       "      <td>Left wheel</td>\n",
       "      <td>Black</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45774419</th>\n",
       "      <td>8467</td>\n",
       "      <td>-</td>\n",
       "      <td>HONDA</td>\n",
       "      <td>FIT</td>\n",
       "      <td>2006</td>\n",
       "      <td>Hatchback</td>\n",
       "      <td>0</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>1.3</td>\n",
       "      <td>200000 km</td>\n",
       "      <td>4.0</td>\n",
       "      <td>Variator</td>\n",
       "      <td>Front</td>\n",
       "      <td>04-May</td>\n",
       "      <td>Right-hand drive</td>\n",
       "      <td>Black</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45769185</th>\n",
       "      <td>3607</td>\n",
       "      <td>862</td>\n",
       "      <td>FORD</td>\n",
       "      <td>Escape</td>\n",
       "      <td>2011</td>\n",
       "      <td>Jeep</td>\n",
       "      <td>1</td>\n",
       "      <td>Hybrid</td>\n",
       "      <td>2.5</td>\n",
       "      <td>168966 km</td>\n",
       "      <td>4.0</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>4x4</td>\n",
       "      <td>04-May</td>\n",
       "      <td>Left wheel</td>\n",
       "      <td>White</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45809263</th>\n",
       "      <td>11726</td>\n",
       "      <td>446</td>\n",
       "      <td>HONDA</td>\n",
       "      <td>FIT</td>\n",
       "      <td>2014</td>\n",
       "      <td>Hatchback</td>\n",
       "      <td>1</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>1.3</td>\n",
       "      <td>91901 km</td>\n",
       "      <td>4.0</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>Front</td>\n",
       "      <td>04-May</td>\n",
       "      <td>Left wheel</td>\n",
       "      <td>Silver</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Price  Levy Manufacturer    Model  Prodyear   Category  \\\n",
       "ID                                                                 \n",
       "45654403  13328  1399        LEXUS   RX 450      2010       Jeep   \n",
       "44731507  16621  1018    CHEVROLET  Equinox      2011       Jeep   \n",
       "45774419   8467     -        HONDA      FIT      2006  Hatchback   \n",
       "45769185   3607   862         FORD   Escape      2011       Jeep   \n",
       "45809263  11726   446        HONDA      FIT      2014  Hatchback   \n",
       "\n",
       "          Leatherinterior Fueltype Engine volume    Mileage  Cylinders  \\\n",
       "ID                                                                       \n",
       "45654403                1   Hybrid           3.5  186005 km        6.0   \n",
       "44731507                0   Petrol             3  192000 km        6.0   \n",
       "45774419                0   Petrol           1.3  200000 km        4.0   \n",
       "45769185                1   Hybrid           2.5  168966 km        4.0   \n",
       "45809263                1   Petrol           1.3   91901 km        4.0   \n",
       "\n",
       "         Gear box type Drive wheels   Doors             Wheel   Color  Airbags  \n",
       "ID                                                                              \n",
       "45654403     Automatic          4x4  04-May        Left wheel  Silver       12  \n",
       "44731507     Tiptronic          4x4  04-May        Left wheel   Black        8  \n",
       "45774419      Variator        Front  04-May  Right-hand drive   Black        2  \n",
       "45769185     Automatic          4x4  04-May        Left wheel   White        0  \n",
       "45809263     Automatic        Front  04-May        Left wheel  Silver        4  "
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv(\"data/car_price_prediction.csv\", index_col=\"ID\")\n",
    "\n",
    "df.info()\n",
    "\n",
    "df[\"Leatherinterior\"] = df[\"Leatherinterior\"].apply(\n",
    "    lambda x: 1 if x == 'Yes' else 0,\n",
    ")\n",
    "\n",
    "print(df.shape)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Получение сведений о пропущенных данных"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Типы пропущенных данных:\n",
    "- None - представление пустых данных в Python\n",
    "- NaN - представление пустых данных в Pandas\n",
    "- '' - пустая строка"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Price              0\n",
      "Levy               0\n",
      "Manufacturer       0\n",
      "Model              0\n",
      "Prodyear           0\n",
      "Category           0\n",
      "Leatherinterior    0\n",
      "Fueltype           0\n",
      "Engine volume      0\n",
      "Mileage            0\n",
      "Cylinders          0\n",
      "Gear box type      0\n",
      "Drive wheels       0\n",
      "Doors              0\n",
      "Wheel              0\n",
      "Color              0\n",
      "Airbags            0\n",
      "dtype: int64\n",
      "\n",
      "Price              False\n",
      "Levy               False\n",
      "Manufacturer       False\n",
      "Model              False\n",
      "Prodyear           False\n",
      "Category           False\n",
      "Leatherinterior    False\n",
      "Fueltype           False\n",
      "Engine volume      False\n",
      "Mileage            False\n",
      "Cylinders          False\n",
      "Gear box type      False\n",
      "Drive wheels       False\n",
      "Doors              False\n",
      "Wheel              False\n",
      "Color              False\n",
      "Airbags            False\n",
      "dtype: bool\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Количество пустых значений признаков\n",
    "print(df.isnull().sum())\n",
    "\n",
    "print()\n",
    "\n",
    "# Есть ли пустые значения признаков\n",
    "print(df.isnull().any())\n",
    "\n",
    "print()\n",
    "\n",
    "# Процент пустых значений признаков\n",
    "for i in df.columns:\n",
    "    null_rate = df[i].isnull().sum() / len(df) * 100\n",
    "    if null_rate > 0:\n",
    "        print(f\"{i} процент пустых значений: %{null_rate:.2f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Заполнение пропущенных данных\n",
    "\n",
    "https://pythonmldaily.com/posts/pandas-dataframes-search-drop-empty-values\n",
    "\n",
    "https://scales.arabpsychology.com/stats/how-to-fill-nan-values-with-median-in-pandas/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# fillna_df = df.fillna(0)\n",
    "\n",
    "# print(fillna_df.shape)\n",
    "\n",
    "# print(fillna_df.isnull().any())\n",
    "\n",
    "# # Замена пустых данных на 0\n",
    "# df[\"AgeFillNA\"] = df[\"Age\"].fillna(0)\n",
    "\n",
    "# # Замена пустых данных на медиану\n",
    "# df[\"AgeFillMedian\"] = df[\"Age\"].fillna(df[\"Age\"].median())\n",
    "\n",
    "# df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# df[\"AgeCopy\"] = df[\"Age\"]\n",
    "\n",
    "# # Замена данных сразу в DataFrame без копирования\n",
    "# df.fillna({\"AgeCopy\": 0}, inplace=True)\n",
    "\n",
    "# df.tail()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Удаление наблюдений с пропусками"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# dropna_df = df.dropna()\n",
    "\n",
    "# print(dropna_df.shape)\n",
    "\n",
    "# print(fillna_df.isnull().any())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Создание выборок данных\n",
    "\n",
    "Библиотека scikit-learn\n",
    "\n",
    "https://scikit-learn.org/stable/index.html"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<img src=\"assets/lec2-split.png\" width=\"600\" style=\"background-color: white\">"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Функция для создания выборок\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "\n",
    "def split_stratified_into_train_val_test(\n",
    "    df_input,\n",
    "    stratify_colname=\"y\",\n",
    "    frac_train=0.6,\n",
    "    frac_val=0.15,\n",
    "    frac_test=0.25,\n",
    "    random_state=None,\n",
    "):\n",
    "    \"\"\"\n",
    "    Splits a Pandas dataframe into three subsets (train, val, and test)\n",
    "    following fractional ratios provided by the user, where each subset is\n",
    "    stratified by the values in a specific column (that is, each subset has\n",
    "    the same relative frequency of the values in the column). It performs this\n",
    "    splitting by running train_test_split() twice.\n",
    "\n",
    "    Parameters\n",
    "    ----------\n",
    "    df_input : Pandas dataframe\n",
    "        Input dataframe to be split.\n",
    "    stratify_colname : str\n",
    "        The name of the column that will be used for stratification. Usually\n",
    "        this column would be for the label.\n",
    "    frac_train : float\n",
    "    frac_val   : float\n",
    "    frac_test  : float\n",
    "        The ratios with which the dataframe will be split into train, val, and\n",
    "        test data. The values should be expressed as float fractions and should\n",
    "        sum to 1.0.\n",
    "    random_state : int, None, or RandomStateInstance\n",
    "        Value to be passed to train_test_split().\n",
    "\n",
    "    Returns\n",
    "    -------\n",
    "    df_train, df_val, df_test :\n",
    "        Dataframes containing the three splits.\n",
    "    \"\"\"\n",
    "\n",
    "    if frac_train + frac_val + frac_test != 1.0:\n",
    "        raise ValueError(\n",
    "            \"fractions %f, %f, %f do not add up to 1.0\"\n",
    "            % (frac_train, frac_val, frac_test)\n",
    "        )\n",
    "\n",
    "    if stratify_colname not in df_input.columns:\n",
    "        raise ValueError(\"%s is not a column in the dataframe\" % (stratify_colname))\n",
    "\n",
    "    X = df_input  # Contains all columns.\n",
    "    y = df_input[\n",
    "        [stratify_colname]\n",
    "    ]  # Dataframe of just the column on which to stratify.\n",
    "\n",
    "    # Split original dataframe into train and temp dataframes.\n",
    "    df_train, df_temp, y_train, y_temp = train_test_split(\n",
    "        X, y, stratify=y, test_size=(1.0 - frac_train), random_state=random_state\n",
    "    )\n",
    "\n",
    "    # Split the temp dataframe into val and test dataframes.\n",
    "    relative_frac_test = frac_test / (frac_val + frac_test)\n",
    "    df_val, df_test, y_val, y_test = train_test_split(\n",
    "        df_temp,\n",
    "        y_temp,\n",
    "        stratify=y_temp,\n",
    "        test_size=relative_frac_test,\n",
    "        random_state=random_state,\n",
    "    )\n",
    "\n",
    "    assert len(df_input) == len(df_train) + len(df_val) + len(df_test)\n",
    "\n",
    "    return df_train, df_val, df_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Leatherinterior\n",
      "1    13954\n",
      "0     5283\n",
      "Name: count, dtype: int64\n",
      "Обучающая выборка:  (11542, 3)\n",
      "Leatherinterior\n",
      "1    8372\n",
      "0    3170\n",
      "Name: count, dtype: int64\n",
      "Контрольная выборка:  (3847, 3)\n",
      "Leatherinterior\n",
      "1    2791\n",
      "0    1056\n",
      "Name: count, dtype: int64\n",
      "Тестовая выборка:  (3848, 3)\n",
      "Leatherinterior\n",
      "1    2791\n",
      "0    1057\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# Вывод распределения количества наблюдений по меткам (классам)\n",
    "print(df.Leatherinterior.value_counts())\n",
    "\n",
    "data = df[[\"Leatherinterior\", \"Price\", \"Airbags\"]].copy()\n",
    "\n",
    "df_train, df_val, df_test = split_stratified_into_train_val_test(\n",
    "    data,\n",
    "    stratify_colname=\"Leatherinterior\",\n",
    "    frac_train=0.60,\n",
    "    frac_val=0.20,\n",
    "    frac_test=0.20,\n",
    ")\n",
    "\n",
    "print(\"Обучающая выборка: \", df_train.shape)\n",
    "print(df_train.Leatherinterior.value_counts())\n",
    "\n",
    "print(\"Контрольная выборка: \", df_val.shape)\n",
    "print(df_val.Leatherinterior.value_counts())\n",
    "\n",
    "print(\"Тестовая выборка: \", df_test.shape)\n",
    "print(df_test.Leatherinterior.value_counts())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Выборка с избытком (oversampling)\n",
    "\n",
    "https://www.blog.trainindata.com/oversampling-techniques-for-imbalanced-data/\n",
    "\n",
    "https://datacrayon.com/machine-learning/class-imbalance-and-oversampling/\n",
    "\n",
    "Выборка с недостатком (undersampling)\n",
    "\n",
    "https://machinelearningmastery.com/random-oversampling-and-undersampling-for-imbalanced-classification/\n",
    "\n",
    "Библиотека imbalanced-learn\n",
    "\n",
    "https://imbalanced-learn.org/stable/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Обучающая выборка:  (11542, 3)\n",
      "Leatherinterior\n",
      "1    8372\n",
      "0    3170\n",
      "Name: count, dtype: int64\n",
      "Обучающая выборка после oversampling:  (16585, 3)\n",
      "Leatherinterior\n",
      "1    8372\n",
      "0    8213\n",
      "Name: count, dtype: int64\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>Leatherinterior</th>\n",
       "      <th>Price</th>\n",
       "      <th>Airbags</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>12231</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>18817</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>15053</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>470</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>19914</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16580</th>\n",
       "      <td>0</td>\n",
       "      <td>13015</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16581</th>\n",
       "      <td>0</td>\n",
       "      <td>8799</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16582</th>\n",
       "      <td>0</td>\n",
       "      <td>2057</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16583</th>\n",
       "      <td>0</td>\n",
       "      <td>2000</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16584</th>\n",
       "      <td>0</td>\n",
       "      <td>1910</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>16585 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Leatherinterior  Price  Airbags\n",
       "0                    1  12231        8\n",
       "1                    1  18817       10\n",
       "2                    1  15053        4\n",
       "3                    1    470        0\n",
       "4                    1  19914        6\n",
       "...                ...    ...      ...\n",
       "16580                0  13015        4\n",
       "16581                0   8799        2\n",
       "16582                0   2057        2\n",
       "16583                0   2000        2\n",
       "16584                0   1910        1\n",
       "\n",
       "[16585 rows x 3 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from imblearn.over_sampling import ADASYN\n",
    "\n",
    "ada = ADASYN()\n",
    "\n",
    "print(\"Обучающая выборка: \", df_train.shape)\n",
    "print(df_train.Leatherinterior.value_counts())\n",
    "\n",
    "X_resampled, y_resampled = ada.fit_resample(df_train, df_train[\"Leatherinterior\"])  # type: ignore\n",
    "df_train_adasyn = pd.DataFrame(X_resampled)\n",
    "\n",
    "print(\"Обучающая выборка после oversampling: \", df_train_adasyn.shape)\n",
    "print(df_train_adasyn.Leatherinterior.value_counts())\n",
    "\n",
    "df_train_adasyn"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}