{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Данные успешно загружены.\n",
      "Выбраны релевантные столбцы для Дании.\n",
      "Пропущенные значения обработаны (удалены строки с NaN).\n",
      "Сформированы массивы 24x3 (часы x признаки).\n",
      "Создан DataFrame с массивами и метками сезонов.\n",
      "Выполнено кодирование меток.\n",
      "Данные разделены на обучающий, валидационный и тестовый наборы.\n",
      "Выполнено масштабирование данных.\n",
      "Данные успешно сохранены в processed_data.npz\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler, LabelEncoder\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "def task1_preprocessing() -> None:\n",
    "    \"\"\"\n",
    "    Выполняет EDA и предобработку данных для прогнозирования сезонности на основе данных о потреблении энергии в Дании.\n",
    "    \"\"\"\n",
    "    # 1. Загрузка данных\n",
    "    try:\n",
    "        data = pd.read_csv(\"dataset/opsd_raw.csv\", parse_dates=[\"utc_timestamp\"])\n",
    "        print(\"Данные успешно загружены.\")\n",
    "    except FileNotFoundError:\n",
    "        print(\"Ошибка: Файл dataset/opsd_raw.csv не найден.\")\n",
    "        return\n",
    "    \n",
    "    # 2. Выбор релевантных столбцов для Дании\n",
    "    cols = [\n",
    "        \"utc_timestamp\",\n",
    "        \"DK_load_actual_entsoe_transparency\",\n",
    "        \"DK_wind_generation_actual\", \n",
    "        \"DK_solar_generation_actual\"\n",
    "    ]\n",
    "\n",
    "    # Проверка наличия столбцов в данных\n",
    "    missing_cols = [col for col in cols if col not in data.columns]\n",
    "    if missing_cols:\n",
    "        print(f\"Ошибка: Отсутствуют столбцы {missing_cols} в данных.\")\n",
    "        return\n",
    "    \n",
    "    data = data[cols].copy()\n",
    "    data.columns = [\"timestamp\", \"load\", \"wind\", \"solar\"]\n",
    "    print(\"Выбраны релевантные столбцы для Дании.\")\n",
    "    \n",
    "    # 3. Обработка пропущенных значений:\n",
    "    # Удаляем строки, где есть хоть одно пропущенное значение\n",
    "    data.dropna(inplace=True)\n",
    "    print(\"Пропущенные значения обработаны (удалены строки с NaN).\")\n",
    "\n",
    "    # 4. Формирование массивов 24x3 (часы × признаки)\n",
    "    data.set_index(\"timestamp\", inplace=True)\n",
    "    \n",
    "    # Группируем по дням и оставляем только дни с ровно 24 записями\n",
    "    daily_data = data.groupby(data.index.date).apply(\n",
    "        lambda x: x[[\"load\", \"wind\", \"solar\"]].values.T\n",
    "        if len(x) == 24 else None\n",
    "    )\n",
    "    daily_data = daily_data.dropna()\n",
    "    print(\"Сформированы массивы 24x3 (часы x признаки).\")\n",
    "    \n",
    "    # Преобразуем индексы в формат datetime для дальнейшей работы\n",
    "    daily_data.index = pd.to_datetime(daily_data.index)\n",
    "    \n",
    "    # 5. Создание DataFrame с массивами и метками сезонов\n",
    "    df = pd.DataFrame({\n",
    "        \"timestamp\": daily_data.index,\n",
    "        \"data\": daily_data.values,\n",
    "        \"season\": daily_data.index.map(lambda x: get_season(x.month))\n",
    "    })\n",
    "    print(\"Создан DataFrame с массивами и метками сезонов.\")\n",
    "    \n",
    "    # 6. Разделение данных\n",
    "    X = np.stack(df[\"data\"].values)\n",
    "    y = df[\"season\"].values\n",
    "    \n",
    "    # Check for NaNs *before* train-test split\n",
    "    if np.isnan(X).any() or not np.isfinite(X).all():\n",
    "        print(\"Ошибка: X содержит NaN или бесконечные значения перед train-test split.\")\n",
    "        return\n",
    "    \n",
    "    # Encode labels\n",
    "    label_encoder = LabelEncoder()\n",
    "    y_encoded = label_encoder.fit_transform(y)\n",
    "    print(\"Выполнено кодирование меток.\")\n",
    "    \n",
    "    X_train, X_temp, y_train, y_temp = train_test_split(\n",
    "        X, y_encoded, test_size=0.3, stratify=y_encoded, random_state=42\n",
    "    )\n",
    "    X_val, X_test, y_val, y_test = train_test_split(\n",
    "        X_temp, y_temp, test_size=0.5, stratify=y_temp, random_state=42\n",
    "    )\n",
    "    print(\"Данные разделены на обучающий, валидационный и тестовый наборы.\")\n",
    "    \n",
    "    # 7. Масштабирование\n",
    "    scaler = StandardScaler()\n",
    "    # Проверяем, что массивы не содержат NaN перед масштабированием\n",
    "    if np.isnan(X_train).any() or not np.isfinite(X_train).all():\n",
    "        print(\"Ошибка: X_train содержит NaN или бесконечные значения перед масштабированием.\")\n",
    "        return\n",
    "    X_train_reshaped = X_train.reshape(-1, 3)\n",
    "    X_train_scaled = scaler.fit_transform(X_train_reshaped).reshape(X_train.shape)\n",
    "    \n",
    "    if np.isnan(X_val).any() or not np.isfinite(X_val).all():\n",
    "        print(\"Ошибка: X_val содержит NaN или бесконечные значения перед масштабированием.\")\n",
    "        return\n",
    "    X_val_reshaped = X_val.reshape(-1, 3)\n",
    "    X_val_scaled = scaler.transform(X_val_reshaped).reshape(X_val.shape)\n",
    "    \n",
    "    if np.isnan(X_test).any() or not np.isfinite(X_test).all():\n",
    "        print(\"Ошибка: X_test содержит NaN или бесконечные значения перед масштабированием.\")\n",
    "        return\n",
    "    X_test_reshaped = X_test.reshape(-1, 3)\n",
    "    X_test_scaled = scaler.transform(X_test_reshaped).reshape(X_test.shape)\n",
    "    print(\"Выполнено масштабирование данных.\")\n",
    "    \n",
    "    # 8. Сохранение данных\n",
    "    try:\n",
    "        np.savez(\"processed_data.npz\",\n",
    "                X_train=X_train_scaled,\n",
    "                X_val=X_val_scaled,\n",
    "                X_test=X_test_scaled,\n",
    "                y_train=y_train,\n",
    "                y_val=y_val,\n",
    "                y_test=y_test,\n",
    "                classes=label_encoder.classes_,\n",
    "                allow_pickle=True)\n",
    "        print(\"Данные успешно сохранены в processed_data.npz\")\n",
    "    except Exception as e:\n",
    "        print(f\"Ошибка при сохранении данных: {e}\")\n",
    "        return\n",
    "    \n",
    "    # 9. Визуализация\n",
    "    plot_sample_profiles(df)\n",
    "\n",
    "def get_season(month: int) -> str:\n",
    "    if month in [12, 1, 2]: return \"winter\"\n",
    "    if month in [3, 4, 5]: return \"spring\"\n",
    "    if month in [6, 7, 8]: return \"summer\"\n",
    "    return \"autumn\"\n",
    "\n",
    "def plot_sample_profiles(df: pd.DataFrame) -> None:\n",
    "    plt.figure(figsize=(12, 6))\n",
    "    for season in [\"winter\", \"spring\", \"summer\", \"autumn\"]:\n",
    "        try:\n",
    "            # Get the first day's data for the given season\n",
    "            season_data = df[df[\"season\"] == season].iloc[0][\"data\"]\n",
    "            # Plotting only the 'load' data\n",
    "            plt.plot(season_data[0], label=f\"{season} load\")\n",
    "        except IndexError:\n",
    "            print(f\"Предупреждение: Нет данных для сезона {season} для построения графика.\")\n",
    "    plt.title(\"Суточные профили потребления энергии по сезонам\")\n",
    "    plt.xlabel(\"Час дня (0-23)\")\n",
    "    plt.ylabel(\"Мощность (МВт)\")\n",
    "    plt.legend()\n",
    "    plt.grid(True)\n",
    "    plt.savefig(\"load_profiles.png\")\n",
    "    plt.show()\n",
    "\n",
    "# Запуск preprocessing\n",
    "task1_preprocessing()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Запуск GridSearchCV...\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "/var/data/python/lib/python3.12/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Лучшие параметры: <bound method BaseEstimator.get_params of MLPClassifier(activation='tanh', hidden_layer_sizes=(50,), max_iter=500,\n",
      "              random_state=42)>\n",
      "Точность (Accuracy): 0.7587\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "      autumn       0.76      0.70      0.73        73\n",
      "      spring       0.84      0.59      0.70        83\n",
      "      summer       0.72      0.92      0.81        83\n",
      "      winter       0.74      0.83      0.78        76\n",
      "\n",
      "    accuracy                           0.76       315\n",
      "   macro avg       0.77      0.76      0.75       315\n",
      "weighted avg       0.77      0.76      0.75       315\n",
      "\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "from sklearn.model_selection import train_test_split, GridSearchCV\n",
    "from sklearn.metrics import accuracy_score, classification_report\n",
    "import warnings\n",
    "\n",
    "def task2_mlp():\n",
    "    \"\"\"\n",
    "    Строит и обучает многослойный перцептрон (MLP) для классификации сезонов.\n",
    "    \"\"\"\n",
    "    warnings.filterwarnings(\"ignore\")\n",
    "    # 1. Загрузка данных\n",
    "    try:\n",
    "        data = np.load(\"processed_data.npz\", allow_pickle=True)\n",
    "        X_train, X_val, X_test = data[\"X_train\"], data[\"X_val\"], data[\"X_test\"]\n",
    "        y_train, y_val, y_test = data[\"y_train\"], data[\"y_val\"], data[\"y_test\"]\n",
    "        classes = data[\"classes\"]\n",
    "    except FileNotFoundError:\n",
    "        print(\"Ошибка: Файл processed_data.npz не найден. Запустите task1_preprocessing() перед выполнением этой задачи.\")\n",
    "        return\n",
    "\n",
    "    # 2. Определение модели\n",
    "    mlp = MLPClassifier(max_iter=500, random_state=42)\n",
    "\n",
    "    # 3. Настройка гиперпараметров с использованием GridSearchCV\n",
    "    param_grid = {\n",
    "        \"hidden_layer_sizes\": [(50,), (100,), (50, 50), (100, 100)],\n",
    "        \"activation\": [\"relu\", \"tanh\"],\n",
    "        \"solver\": [\"adam\", \"sgd\"],\n",
    "        \"alpha\": [0.0001, 0.001],\n",
    "    }\n",
    "    grid_search = GridSearchCV(mlp, param_grid, cv=5, scoring=\"accuracy\", n_jobs=-1)\n",
    "\n",
    "    print(\"Запуск GridSearchCV...\")\n",
    "    grid_search.fit(X_train.reshape(X_train.shape[0], -1), y_train)\n",
    "\n",
    "    # 4. Лучшая модель и её параметры\n",
    "    best_model = grid_search.best_estimator_\n",
    "    print(\"Лучшие параметры:\", best_model.get_params)\n",
    "\n",
    "    # 5. Оценка модели на тестовом наборе\n",
    "    y_pred = best_model.predict(X_test.reshape(X_test.shape[0], -1))\n",
    "\n",
    "    accuracy = accuracy_score(y_test, y_pred)\n",
    "    print(f\"Точность (Accuracy): {accuracy:.4f}\")\n",
    "    print(classification_report(y_test, y_pred, target_names=classes))\n",
    "\n",
    "# Запуск обучения MLP\n",
    "task2_mlp()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/50\n"
     ]
    },
    {
     "ename": "ValueError",
     "evalue": "Exception encountered when calling Sequential.call().\n\n\u001b[1mInput 0 of layer \"conv1d_24\" is incompatible with the layer: expected axis -1 of input shape to have value 3, but received input with shape (None, 3, 24)\u001b[0m\n\nArguments received by Sequential.call():\n  • inputs=tf.Tensor(shape=(None, 3, 24), dtype=float32)\n  • training=True\n  • mask=None",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mValueError\u001b[39m                                Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[81]\u001b[39m\u001b[32m, line 76\u001b[39m\n\u001b[32m     73\u001b[39m     model.save(\u001b[33m\"\u001b[39m\u001b[33m1d_cnn_model.h5\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m     75\u001b[39m \u001b[38;5;66;03m# Запуск обучения 1D CNN\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m76\u001b[39m \u001b[43mtask3_1d_cnn\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[81]\u001b[39m\u001b[32m, line 56\u001b[39m, in \u001b[36mtask3_1d_cnn\u001b[39m\u001b[34m()\u001b[39m\n\u001b[32m     47\u001b[39m model.compile(optimizer=Adam(learning_rate=\u001b[32m0.001\u001b[39m),\n\u001b[32m     48\u001b[39m               loss=\u001b[33m'\u001b[39m\u001b[33mcategorical_crossentropy\u001b[39m\u001b[33m'\u001b[39m,\n\u001b[32m     49\u001b[39m               metrics=[\u001b[33m'\u001b[39m\u001b[33maccuracy\u001b[39m\u001b[33m'\u001b[39m])\n\u001b[32m     51\u001b[39m \u001b[38;5;66;03m# X_train = np.transpose(X_train, (0, 2, 1))\u001b[39;00m\n\u001b[32m     52\u001b[39m \u001b[38;5;66;03m# X_val = np.transpose(X_val, (0, 2, 1))\u001b[39;00m\n\u001b[32m     53\u001b[39m \u001b[38;5;66;03m# X_test = np.transpose(X_test, (0, 2, 1))\u001b[39;00m\n\u001b[32m     54\u001b[39m \n\u001b[32m     55\u001b[39m \u001b[38;5;66;03m# Обучение модели\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m56\u001b[39m history = \u001b[43mmodel\u001b[49m\u001b[43m.\u001b[49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_train\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m     57\u001b[39m \u001b[43m                    \u001b[49m\u001b[43mvalidation_data\u001b[49m\u001b[43m=\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_val\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m     58\u001b[39m \u001b[43m                    \u001b[49m\u001b[43mepochs\u001b[49m\u001b[43m=\u001b[49m\u001b[32;43m50\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m     59\u001b[39m \u001b[43m                    \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[43m=\u001b[49m\u001b[32;43m32\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m     60\u001b[39m \u001b[43m                    \u001b[49m\u001b[43mverbose\u001b[49m\u001b[43m=\u001b[49m\u001b[32;43m1\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[32m     62\u001b[39m \u001b[38;5;66;03m# Оценка модели на тестовом наборе\u001b[39;00m\n\u001b[32m     63\u001b[39m y_pred = model.predict(X_test)\n",
      "\u001b[36mFile \u001b[39m\u001b[32m/var/data/python/lib/python3.12/site-packages/keras/src/utils/traceback_utils.py:122\u001b[39m, in \u001b[36mfilter_traceback.<locals>.error_handler\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m    119\u001b[39m     filtered_tb = _process_traceback_frames(e.__traceback__)\n\u001b[32m    120\u001b[39m     \u001b[38;5;66;03m# To get the full stack trace, call:\u001b[39;00m\n\u001b[32m    121\u001b[39m     \u001b[38;5;66;03m# `keras.config.disable_traceback_filtering()`\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m122\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m e.with_traceback(filtered_tb) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m    123\u001b[39m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[32m    124\u001b[39m     \u001b[38;5;28;01mdel\u001b[39;00m filtered_tb\n",
      "\u001b[36mFile \u001b[39m\u001b[32m/var/data/python/lib/python3.12/site-packages/keras/src/layers/input_spec.py:227\u001b[39m, in \u001b[36massert_input_compatibility\u001b[39m\u001b[34m(input_spec, inputs, layer_name)\u001b[39m\n\u001b[32m    222\u001b[39m     \u001b[38;5;28;01mfor\u001b[39;00m axis, value \u001b[38;5;129;01min\u001b[39;00m spec.axes.items():\n\u001b[32m    223\u001b[39m         \u001b[38;5;28;01mif\u001b[39;00m value \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m shape[axis] \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m {\n\u001b[32m    224\u001b[39m             value,\n\u001b[32m    225\u001b[39m             \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[32m    226\u001b[39m         }:\n\u001b[32m--> \u001b[39m\u001b[32m227\u001b[39m             \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[32m    228\u001b[39m                 \u001b[33mf\u001b[39m\u001b[33m'\u001b[39m\u001b[33mInput \u001b[39m\u001b[38;5;132;01m{\u001b[39;00minput_index\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m of layer \u001b[39m\u001b[33m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mlayer_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\u001b[33m is \u001b[39m\u001b[33m'\u001b[39m\n\u001b[32m    229\u001b[39m                 \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mincompatible with the layer: expected axis \u001b[39m\u001b[38;5;132;01m{\u001b[39;00maxis\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m \u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m    230\u001b[39m                 \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mof input shape to have value \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mvalue\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m, \u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m    231\u001b[39m                 \u001b[33m\"\u001b[39m\u001b[33mbut received input with \u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m    232\u001b[39m                 \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mshape \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mshape\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\n\u001b[32m    233\u001b[39m             )\n\u001b[32m    234\u001b[39m \u001b[38;5;66;03m# Check shape.\u001b[39;00m\n\u001b[32m    235\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m spec.shape \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
      "\u001b[31mValueError\u001b[39m: Exception encountered when calling Sequential.call().\n\n\u001b[1mInput 0 of layer \"conv1d_24\" is incompatible with the layer: expected axis -1 of input shape to have value 3, but received input with shape (None, 3, 24)\u001b[0m\n\nArguments received by Sequential.call():\n  • inputs=tf.Tensor(shape=(None, 3, 24), dtype=float32)\n  • training=True\n  • mask=None"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler, LabelEncoder\n",
    "import matplotlib.pyplot as plt\n",
    "import tensorflow as tf\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Conv1D, MaxPooling1D, Flatten, Dense, Dropout\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "from tensorflow.keras.utils import to_categorical\n",
    "from sklearn.metrics import accuracy_score, classification_report\n",
    "\n",
    "def task3_1d_cnn():\n",
    "    \"\"\"\n",
    "    Строит и обучает одномерную сверточную нейронную сеть (1D CNN) для классификации сезонов.\n",
    "    \"\"\"\n",
    "    # Загрузка предобработанных данных\n",
    "    try:\n",
    "        data = np.load(\"processed_data.npz\", allow_pickle=True)\n",
    "        X_train, X_val, X_test = data[\"X_train\"], data[\"X_val\"], data[\"X_test\"]\n",
    "        y_train, y_val, y_test = data[\"y_train\"], data[\"y_val\"], data[\"y_test\"]\n",
    "        classes = data[\"classes\"]\n",
    "    except FileNotFoundError:\n",
    "        print(\"Ошибка: Файл processed_data.npz не найден. Запустите task1_preprocessing() перед выполнением этой задачи.\")\n",
    "        return\n",
    "    \n",
    "    num_classes = len(classes)\n",
    "    y_train = to_categorical(y_train, num_classes)\n",
    "    y_val = to_categorical(y_val, num_classes)\n",
    "    y_test = to_categorical(y_test, num_classes)\n",
    "\n",
    "    # strategy = tf.distribute.get_strategy()\n",
    "    # with strategy.scope():\n",
    "\n",
    "    # Построение модели 1D CNN\n",
    "    model = Sequential([\n",
    "        tf.keras.layers.Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(24, 3)), # Corrected input shape\n",
    "        tf.keras.layers.MaxPooling1D(pool_size=2),\n",
    "        tf.keras.layers.Conv1D(filters=32, kernel_size=3, activation='relu'),\n",
    "        tf.keras.layers.MaxPooling1D(pool_size=2),\n",
    "        tf.keras.layers.Flatten(),\n",
    "        tf.keras.layers.Dense(64, activation='relu'),\n",
    "        tf.keras.layers.Dropout(0.5),\n",
    "        tf.keras.layers.Dense(num_classes, activation='softmax')\n",
    "    ])\n",
    "    # Компиляция модели\n",
    "    model.compile(optimizer=Adam(learning_rate=0.001),\n",
    "                  loss='categorical_crossentropy',\n",
    "                  metrics=['accuracy'])\n",
    "\n",
    "    # X_train = np.transpose(X_train, (0, 2, 1))\n",
    "    # X_val = np.transpose(X_val, (0, 2, 1))\n",
    "    # X_test = np.transpose(X_test, (0, 2, 1))\n",
    "\n",
    "    # Обучение модели\n",
    "    history = model.fit(X_train, y_train,\n",
    "                        validation_data=(X_val, y_val),\n",
    "                        epochs=50,\n",
    "                        batch_size=32,\n",
    "                        verbose=1)\n",
    "\n",
    "    # Оценка модели на тестовом наборе\n",
    "    y_pred = model.predict(X_test)\n",
    "    y_pred_classes = np.argmax(y_pred, axis=1)\n",
    "    y_test_classes = np.argmax(y_test, axis=1)\n",
    "\n",
    "    # Вычисление метрик\n",
    "    accuracy = accuracy_score(y_test_classes, y_pred_classes)\n",
    "    print(f\"Точность (Accuracy): {accuracy:.4f}\")\n",
    "    print(classification_report(y_test_classes, y_pred_classes, target_names=classes))\n",
    "\n",
    "    # Сохранение модели\n",
    "    model.save(\"1d_cnn_model.h5\")\n",
    "\n",
    "# Запуск обучения 1D CNN\n",
    "task3_1d_cnn()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}