AIM-PIbd-31-Afanasev-S-S/lab_3/lab3.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Начало лабораторной работы"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "*Вариант 3:* Диабет у индейцев Пима\n",
    "- Определим бизнес-цели и цели технического проекта  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin',\n",
      "       'BMI', 'DiabetesPedigreeFunction', 'Age', 'Outcome'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "df = pd.read_csv(\"C:/Users/TIGR228/Desktop/МИИ/Lab1/AIM-PIbd-31-Afanasev-S-S/static/csv/diabetes.csv\")\n",
    "print(df.columns)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Определение бизнес целей:\n",
    "1. Прогнозирование риска развития диабета\n",
    "2. Оценка факторов, влияющих на развитие диабета"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Определение целей технического проекта:\n",
    "1. Построить модель машинного обучения для классификации, которая будет прогнозировать вероятность развития диабета у индейцев Пима на основе предоставленных данных о их характеристиках.\n",
    "2. Провести анализ данных для выявления ключевых факторов, влияющих на развитие диабета у индейцев Пима."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "0            6      148             72             35        0  33.6   \n",
       "1            1       85             66             29        0  26.6   \n",
       "2            8      183             64              0        0  23.3   \n",
       "3            1       89             66             23       94  28.1   \n",
       "4            0      137             40             35      168  43.1   \n",
       "\n",
       "   DiabetesPedigreeFunction  Age  Outcome  \n",
       "0                     0.627   50        1  \n",
       "1                     0.351   31        0  \n",
       "2                     0.672   32        1  \n",
       "3                     0.167   21        0  \n",
       "4                     2.288   33        1  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pregnancies                 0\n",
      "Glucose                     0\n",
      "BloodPressure               0\n",
      "SkinThickness               0\n",
      "Insulin                     0\n",
      "BMI                         0\n",
      "DiabetesPedigreeFunction    0\n",
      "Age                         0\n",
      "Outcome                     0\n",
      "dtype: int64\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Pregnancies                 False\n",
       "Glucose                     False\n",
       "BloodPressure               False\n",
       "SkinThickness               False\n",
       "Insulin                     False\n",
       "BMI                         False\n",
       "DiabetesPedigreeFunction    False\n",
       "Age                         False\n",
       "Outcome                     False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Процент пропущенных 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}')\n",
    "\n",
    "# Проверка на пропущенные данные\n",
    "print(df.isnull().sum())\n",
    "\n",
    "df.isnull().any()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Пропущенных колонок нету, что не может не радовать "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Размер обучающей выборки:  614\n",
      "Размер контрольной выборки:  154\n",
      "Размер тестовой выборки:  154\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# Разделение данных на обучающую и тестовую выборки (80% - обучение, 20% - тестовая)\n",
    "train_data, test_data = train_test_split(df, test_size=0.2, random_state=42)\n",
    "\n",
    "# Разделение данных на обучающую и контрольную выборки (80% - обучение, 20% - контроль)\n",
    "train_data, val_data = train_test_split(df, test_size=0.2, random_state=42)\n",
    "\n",
    "print(\"Размер обучающей выборки: \", len(train_data))\n",
    "print(\"Размер контрольной выборки: \", len(val_data))\n",
    "print(\"Размер тестовой выборки: \", len(test_data))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Среднее значение Outcome в обучающей выборке:  0.3469055374592834\n",
      "Среднее значение Outcome в контрольной выборке:  0.35714285714285715\n",
      "Среднее значение Outcome в тестовой выборке:  0.35714285714285715\n"
     ]
    }
   ],
   "source": [
    "# Оценка сбалансированности целевой переменной (Outcome)\n",
    "# Визуализация распределения целевой переменной в выборках (гистограмма)\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "def plot_outcome_distribution(data, title):\n",
    "    sns.histplot(data['Outcome'], kde=True)\n",
    "    plt.title(title)\n",
    "    plt.xlabel('Outcome')\n",
    "    plt.ylabel('Частота')\n",
    "    plt.show()\n",
    "\n",
    "plot_outcome_distribution(train_data, 'Распределение Outcome в обучающей выборке')\n",
    "plot_outcome_distribution(val_data, 'Распределение Outcome в контрольной выборке')\n",
    "plot_outcome_distribution(test_data, 'Распределение Outcome в тестовой выборке')\n",
    "\n",
    "# Оценка сбалансированности данных по целевой переменной (Outcome)\n",
    "print(\"Среднее значение Outcome в обучающей выборке: \", train_data['Outcome'].mean())\n",
    "print(\"Среднее значение Outcome в контрольной выборке: \", val_data['Outcome'].mean())\n",
    "print(\"Среднее значение Outcome в тестовой выборке: \", test_data['Outcome'].mean())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Размер обучающей выборки после oversampling и undersampling:  802\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.model_selection import train_test_split\n",
    "from imblearn.over_sampling import RandomOverSampler\n",
    "from imblearn.under_sampling import RandomUnderSampler\n",
    "\n",
    "# Визуализация распределения Outcome в обучающей выборке\n",
    "sns.countplot(x=train_data['Outcome'])\n",
    "plt.title('Распределение Outcome в обучающей выборке')\n",
    "plt.xlabel('Outcome')\n",
    "plt.ylabel('Частота')\n",
    "plt.show()\n",
    "\n",
    "# Балансировка категорий с помощью RandomOverSampler (увеличение меньшинств)\n",
    "ros = RandomOverSampler(random_state=42)\n",
    "X_train = train_data.drop(columns=['Outcome'])\n",
    "y_train = train_data['Outcome']\n",
    "\n",
    "X_resampled, y_resampled = ros.fit_resample(X_train, y_train)\n",
    "\n",
    "# Визуализация распределения Outcome после oversampling\n",
    "sns.countplot(x=y_resampled)\n",
    "plt.title('Распределение Outcome после oversampling')\n",
    "plt.xlabel('Outcome')\n",
    "plt.ylabel('Частота')\n",
    "plt.show()\n",
    "\n",
    "# Применение RandomUnderSampler для уменьшения большего класса\n",
    "rus = RandomUnderSampler(random_state=42)\n",
    "X_resampled, y_resampled = rus.fit_resample(X_resampled, y_resampled)\n",
    "\n",
    "# Визуализация распределения Outcome после undersampling\n",
    "sns.countplot(x=y_resampled)\n",
    "plt.title('Распределение Outcome после undersampling')\n",
    "plt.xlabel('Outcome')\n",
    "plt.ylabel('Частота')\n",
    "plt.show()\n",
    "\n",
    "# Печать размеров выборки после балансировки\n",
    "print(\"Размер обучающей выборки после oversampling и undersampling: \", len(X_resampled))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Конструирование признаков  \n",
    "\n",
    "Теперь приступим к конструированию признаков для решения каждой задачи.\n",
    "\n",
    "**Процесс конструирования признаков**  \n",
    "Задача 1: Прогнозирование риска развития диабета. Цель технического проекта: Разработка модели машинного обучения для точного прогнозирования вероятности развития диабета у индейцев Пима.\n",
    "Задача 2: Оценка факторов, влияющих на развитие диабета. Цель технического проекта: Разработка модели машинного обучения для выявления ключевых факторов, влияющих на развитие диабета у индейцев Пима.\n",
    "\n",
    "**Унитарное кодирование**  \n",
    "Унитарное кодирование категориальных признаков (one-hot encoding). Преобразование категориальных признаков в бинарные векторы.\n",
    "\n",
    "**Дискретизация числовых признаков**  \n",
    "Процесс преобразования непрерывных числовых значений в дискретные категории или интервалы (бины)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Столбцы train_data_encoded: ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'Pregnancies_0', 'Pregnancies_1', 'Pregnancies_2', 'Pregnancies_3', 'Pregnancies_4', 'Pregnancies_5', 'Pregnancies_6', 'Pregnancies_7', 'Pregnancies_8', 'Pregnancies_9', 'Pregnancies_10', 'Pregnancies_11', 'Pregnancies_12', 'Pregnancies_13', 'Pregnancies_14', 'Pregnancies_15', 'Pregnancies_17', 'Outcome_0', 'Outcome_1']\n",
      "Столбцы val_data_encoded: ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'Pregnancies_0', 'Pregnancies_1', 'Pregnancies_2', 'Pregnancies_3', 'Pregnancies_4', 'Pregnancies_5', 'Pregnancies_6', 'Pregnancies_7', 'Pregnancies_8', 'Pregnancies_9', 'Pregnancies_10', 'Pregnancies_11', 'Pregnancies_12', 'Pregnancies_13', 'Outcome_0', 'Outcome_1']\n",
      "Столбцы test_data_encoded: ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'Pregnancies_0', 'Pregnancies_1', 'Pregnancies_2', 'Pregnancies_3', 'Pregnancies_4', 'Pregnancies_5', 'Pregnancies_6', 'Pregnancies_7', 'Pregnancies_8', 'Pregnancies_9', 'Pregnancies_10', 'Pregnancies_11', 'Pregnancies_12', 'Pregnancies_13', 'Outcome_0', 'Outcome_1']\n"
     ]
    }
   ],
   "source": [
    "# Пример категориальных признаков\n",
    "categorical_features = ['Pregnancies', 'Outcome']\n",
    "\n",
    "# Применение one-hot encoding\n",
    "train_data_encoded = pd.get_dummies(train_data, columns=categorical_features)\n",
    "val_data_encoded = pd.get_dummies(val_data, columns=categorical_features)\n",
    "test_data_encoded = pd.get_dummies(test_data, columns=categorical_features)\n",
    "df_encoded = pd.get_dummies(df, columns=categorical_features)\n",
    "\n",
    "print(\"Столбцы train_data_encoded:\", train_data_encoded.columns.tolist())\n",
    "print(\"Столбцы val_data_encoded:\", val_data_encoded.columns.tolist())\n",
    "print(\"Столбцы test_data_encoded:\", test_data_encoded.columns.tolist())\n",
    "\n",
    "# Дискретизация числовых признаков (Glucose). Например, можно разделить уровень глюкозы на категории\n",
    "# Пример дискретизации признака 'Glucose' на 5 категорий\n",
    "train_data_encoded['Glucose_binned'] = pd.cut(train_data_encoded['Glucose'], bins=5, labels=False)\n",
    "val_data_encoded['Glucose_binned'] = pd.cut(val_data_encoded['Glucose'], bins=5, labels=False)\n",
    "test_data_encoded['Glucose_binned'] = pd.cut(test_data_encoded['Glucose'], bins=5, labels=False)\n",
    "\n",
    "# Пример дискретизации признака 'Glucose' на 5 категорий\n",
    "df_encoded['Glucose_binned'] = pd.cut(df_encoded['Glucose'], bins=5, labels=False)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Ручной синтез\n",
    "Создание новых признаков на основе экспертных знаний и логики предметной области. К примеру, можно создать признак, который отражает соотношение уровня глюкозы к инсулину или индексу массы тела (BMI)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Ручной синтез признаков\n",
    "# Пример создания нового признака - соотношение уровня глюкозы к инсулину\n",
    "train_data_encoded['glucose_to_insulin'] = train_data_encoded['Glucose'] / train_data_encoded['Insulin']\n",
    "val_data_encoded['glucose_to_insulin'] = val_data_encoded['Glucose'] / val_data_encoded['Insulin']\n",
    "test_data_encoded['glucose_to_insulin'] = test_data_encoded['Glucose'] / test_data_encoded['Insulin']\n",
    "\n",
    "# Пример создания нового признака - соотношение уровня глюкозы к инсулину\n",
    "df_encoded['glucose_to_insulin'] = df_encoded['Glucose'] / df_encoded['Insulin']\n",
    "\n",
    "# Пример создания нового признака - соотношение уровня глюкозы к BMI\n",
    "train_data_encoded['glucose_to_bmi'] = train_data_encoded['Glucose'] / train_data_encoded['BMI']\n",
    "val_data_encoded['glucose_to_bmi'] = val_data_encoded['Glucose'] / val_data_encoded['BMI']\n",
    "test_data_encoded['glucose_to_bmi'] = test_data_encoded['Glucose'] / test_data_encoded['BMI']\n",
    "\n",
    "# Пример создания нового признака - соотношение уровня глюкозы к BMI\n",
    "df_encoded['glucose_to_bmi'] = df_encoded['Glucose'] / df_encoded['BMI']\n",
    "\n",
    "# Пример создания нового признака - соотношение уровня инсулина к BMI\n",
    "train_data_encoded['insulin_to_bmi'] = train_data_encoded['Insulin'] / train_data_encoded['BMI']\n",
    "val_data_encoded['insulin_to_bmi'] = val_data_encoded['Insulin'] / val_data_encoded['BMI']\n",
    "test_data_encoded['insulin_to_bmi'] = test_data_encoded['Insulin'] / test_data_encoded['BMI']\n",
    "\n",
    "# Пример создания нового признака - соотношение уровня инсулина к BMI\n",
    "df_encoded['insulin_to_bmi'] = df_encoded['Insulin'] / df_encoded['BMI']\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Масштабирование признаков - это процесс преобразования числовых признаков таким образом, чтобы они имели одинаковый масштаб."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler, MinMaxScaler\n",
    "\n",
    "# Пример числовых признаков\n",
    "numerical_features = ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age']\n",
    "\n",
    "# Применение StandardScaler для масштабирования числовых признаков\n",
    "scaler = StandardScaler()\n",
    "train_data_encoded[numerical_features] = scaler.fit_transform(train_data_encoded[numerical_features])\n",
    "val_data_encoded[numerical_features] = scaler.transform(val_data_encoded[numerical_features])\n",
    "test_data_encoded[numerical_features] = scaler.transform(test_data_encoded[numerical_features])\n",
    "\n",
    "# Пример использования MinMaxScaler для масштабирования числовых признаков\n",
    "scaler = MinMaxScaler()\n",
    "train_data_encoded[numerical_features] = scaler.fit_transform(train_data_encoded[numerical_features])\n",
    "val_data_encoded[numerical_features] = scaler.transform(val_data_encoded[numerical_features])\n",
    "test_data_encoded[numerical_features] = scaler.transform(test_data_encoded[numerical_features])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Использование фреймворка Featuretools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Столбцы в df: ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'Outcome']\n",
      "Столбцы в train_data_encoded: ['id', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'Pregnancies_0', 'Pregnancies_1', 'Pregnancies_2', 'Pregnancies_3', 'Pregnancies_4', 'Pregnancies_5', 'Pregnancies_6', 'Pregnancies_7', 'Pregnancies_8', 'Pregnancies_9', 'Pregnancies_10', 'Pregnancies_11', 'Pregnancies_12', 'Pregnancies_13', 'Pregnancies_14', 'Pregnancies_15', 'Pregnancies_17', 'Outcome_0', 'Outcome_1', 'Glucose_binned', 'glucose_to_insulin', 'glucose_to_bmi', 'insulin_to_bmi']\n",
      "Столбцы в val_data_encoded: ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'Pregnancies_0', 'Pregnancies_1', 'Pregnancies_2', 'Pregnancies_3', 'Pregnancies_4', 'Pregnancies_5', 'Pregnancies_6', 'Pregnancies_7', 'Pregnancies_8', 'Pregnancies_9', 'Pregnancies_10', 'Pregnancies_11', 'Pregnancies_12', 'Pregnancies_13', 'Outcome_0', 'Outcome_1', 'Glucose_binned', 'glucose_to_insulin', 'glucose_to_bmi', 'insulin_to_bmi']\n",
      "Столбцы в test_data_encoded: ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'Pregnancies_0', 'Pregnancies_1', 'Pregnancies_2', 'Pregnancies_3', 'Pregnancies_4', 'Pregnancies_5', 'Pregnancies_6', 'Pregnancies_7', 'Pregnancies_8', 'Pregnancies_9', 'Pregnancies_10', 'Pregnancies_11', 'Pregnancies_12', 'Pregnancies_13', 'Outcome_0', 'Outcome_1', 'Glucose_binned', 'glucose_to_insulin', 'glucose_to_bmi', 'insulin_to_bmi']\n",
      "Empty DataFrame\n",
      "Columns: [id, Glucose, BloodPressure, SkinThickness, Insulin, BMI, DiabetesPedigreeFunction, Age, Pregnancies_0, Pregnancies_1, Pregnancies_2, Pregnancies_3, Pregnancies_4, Pregnancies_5, Pregnancies_6, Pregnancies_7, Pregnancies_8, Pregnancies_9, Pregnancies_10, Pregnancies_11, Pregnancies_12, Pregnancies_13, Pregnancies_14, Pregnancies_15, Pregnancies_17, Outcome_0, Outcome_1, Glucose_binned, glucose_to_insulin, glucose_to_bmi, insulin_to_bmi]\n",
      "Index: []\n",
      "\n",
      "[0 rows x 31 columns]\n",
      "    Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
      "id                                                         \n",
      "0       148             72             35        0  33.6   \n",
      "1        85             66             29        0  26.6   \n",
      "2       183             64              0        0  23.3   \n",
      "3        89             66             23       94  28.1   \n",
      "4       137             40             35      168  43.1   \n",
      "\n",
      "    DiabetesPedigreeFunction  Age  Pregnancies_0  Pregnancies_1  \\\n",
      "id                                                                \n",
      "0                      0.627   50          False          False   \n",
      "1                      0.351   31          False           True   \n",
      "2                      0.672   32          False          False   \n",
      "3                      0.167   21          False           True   \n",
      "4                      2.288   33           True          False   \n",
      "\n",
      "    Pregnancies_2  ...  Pregnancies_13  Pregnancies_14  Pregnancies_15  \\\n",
      "id                 ...                                                   \n",
      "0           False  ...           False           False           False   \n",
      "1           False  ...           False           False           False   \n",
      "2           False  ...           False           False           False   \n",
      "3           False  ...           False           False           False   \n",
      "4           False  ...           False           False           False   \n",
      "\n",
      "    Pregnancies_17  Outcome_0  Outcome_1  Glucose_binned  glucose_to_insulin  \\\n",
      "id                                                                             \n",
      "0            False      False       True               3                 inf   \n",
      "1            False       True      False               2                 inf   \n",
      "2            False      False       True               4                 inf   \n",
      "3            False       True      False               2            0.946809   \n",
      "4            False      False       True               3            0.815476   \n",
      "\n",
      "    glucose_to_bmi  insulin_to_bmi  \n",
      "id                                  \n",
      "0         4.404762        0.000000  \n",
      "1         3.195489        0.000000  \n",
      "2         7.854077        0.000000  \n",
      "3         3.167260        3.345196  \n",
      "4         3.178654        3.897912  \n",
      "\n",
      "[5 rows x 30 columns]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\TIGR228\\Desktop\\МИИ\\Lab1\\AIM-PIbd-31-Afanasev-S-S\\aimenv\\Lib\\site-packages\\featuretools\\synthesis\\deep_feature_synthesis.py:169: UserWarning: Only one dataframe in entityset, changing max_depth to 1 since deeper features cannot be created\n",
      "  warnings.warn(\n",
      "c:\\Users\\TIGR228\\Desktop\\МИИ\\Lab1\\AIM-PIbd-31-Afanasev-S-S\\aimenv\\Lib\\site-packages\\featuretools\\synthesis\\deep_feature_synthesis.py:169: UserWarning: Only one dataframe in entityset, changing max_depth to 1 since deeper features cannot be created\n",
      "  warnings.warn(\n",
      "c:\\Users\\TIGR228\\Desktop\\МИИ\\Lab1\\AIM-PIbd-31-Afanasev-S-S\\aimenv\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:143: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
      "  df = pd.concat([df, default_df], sort=True)\n",
      "c:\\Users\\TIGR228\\Desktop\\МИИ\\Lab1\\AIM-PIbd-31-Afanasev-S-S\\aimenv\\Lib\\site-packages\\woodwork\\logical_types.py:841: FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`\n",
      "  series = series.replace(ww.config.get_option(\"nan_values\"), np.nan)\n",
      "c:\\Users\\TIGR228\\Desktop\\МИИ\\Lab1\\AIM-PIbd-31-Afanasev-S-S\\aimenv\\Lib\\site-packages\\featuretools\\computational_backends\\feature_set_calculator.py:143: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
      "  df = pd.concat([df, default_df], sort=True)\n",
      "c:\\Users\\TIGR228\\Desktop\\МИИ\\Lab1\\AIM-PIbd-31-Afanasev-S-S\\aimenv\\Lib\\site-packages\\woodwork\\logical_types.py:841: FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`\n",
      "  series = series.replace(ww.config.get_option(\"nan_values\"), np.nan)\n"
     ]
    }
   ],
   "source": [
    "import featuretools as ft\n",
    "\n",
    "# Проверка наличия столбцов в DataFrame\n",
    "print(\"Столбцы в df:\", df.columns.tolist())\n",
    "print(\"Столбцы в train_data_encoded:\", train_data_encoded.columns.tolist())\n",
    "print(\"Столбцы в val_data_encoded:\", val_data_encoded.columns.tolist())\n",
    "print(\"Столбцы в test_data_encoded:\", test_data_encoded.columns.tolist())\n",
    "\n",
    "# Удаление дубликатов по всем столбцам (если нет уникального идентификатора)\n",
    "df = df.drop_duplicates()\n",
    "duplicates = train_data_encoded[train_data_encoded.duplicated(keep=False)]\n",
    "\n",
    "# Удаление дубликатов из столбца \"id\", сохранив первое вхождение\n",
    "df_encoded = df_encoded.drop_duplicates(keep='first')\n",
    "\n",
    "print(duplicates)\n",
    "\n",
    "# Создание EntitySet\n",
    "es = ft.EntitySet(id='diabetes_data')\n",
    "\n",
    "# Добавление датафрейма с данными о диабете\n",
    "es = es.add_dataframe(dataframe_name='patients', dataframe=df_encoded, index='id')\n",
    "\n",
    "# Генерация признаков с помощью глубокой синтезы признаков\n",
    "feature_matrix, feature_defs = ft.dfs(entityset=es, target_dataframe_name='patients', max_depth=2)\n",
    "\n",
    "# Выводим первые 5 строк сгенерированного набора признаков\n",
    "print(feature_matrix.head())\n",
    "\n",
    "# Удаление дубликатов из обучающей выборки\n",
    "train_data_encoded = train_data_encoded.drop_duplicates()\n",
    "train_data_encoded = train_data_encoded.drop_duplicates(keep='first')  # or keep='last'\n",
    "\n",
    "# Определение сущностей (Создание EntitySet)\n",
    "es = ft.EntitySet(id='diabetes_data')\n",
    "\n",
    "es = es.add_dataframe(dataframe_name='patients', dataframe=train_data_encoded, index='id')\n",
    "\n",
    "# Генерация признаков\n",
    "feature_matrix, feature_defs = ft.dfs(entityset=es, target_dataframe_name='patients', max_depth=2)\n",
    "\n",
    "# Преобразование признаков для контрольной и тестовой выборок\n",
    "val_feature_matrix = ft.calculate_feature_matrix(features=feature_defs, entityset=es, instance_ids=val_data_encoded.index)\n",
    "test_feature_matrix = ft.calculate_feature_matrix(features=feature_defs, entityset=es, instance_ids=test_data_encoded.index)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Оценка качества каждого набора признаков  \n",
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Время обучения модели: 0.00 секунд\n",
      "Среднеквадратичная ошибка: 704.68\n",
      "Коэффициент детерминации (R²): 0.30\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import time\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.metrics import mean_squared_error, r2_score\n",
    "\n",
    "# Предположим, что df уже определен и загружен\n",
    "\n",
    "# Разделение данных на обучающую и валидационную выборки. Удаляем целевую переменную\n",
    "X = df.drop('Glucose', axis=1)\n",
    "y = df['Glucose']\n",
    "\n",
    "# One-hot encoding для категориальных переменных (преобразование категориальных объектов в числовые)\n",
    "X = pd.get_dummies(X, drop_first=True)\n",
    "\n",
    "# Проверяем, есть ли пропущенные значения, и заполняем их медианой или другим подходящим значением\n",
    "X.fillna(X.median(), inplace=True)\n",
    "\n",
    "X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)\n",
    "\n",
    "# Обучение модели\n",
    "model = LinearRegression()\n",
    "\n",
    "# Начинаем отсчет времени\n",
    "start_time = time.time()\n",
    "model.fit(X_train, y_train)\n",
    "\n",
    "# Время обучения модели\n",
    "train_time = time.time() - start_time\n",
    "\n",
    "# Предсказания и оценка модели\n",
    "val_predictions = model.predict(X_val)\n",
    "mse = mean_squared_error(y_val, val_predictions)\n",
    "r2 = r2_score(y_val, val_predictions)\n",
    "\n",
    "print(f'Время обучения модели: {train_time:.2f} секунд')\n",
    "print(f'Среднеквадратичная ошибка: {mse:.2f}')\n",
    "print(f'Коэффициент детерминации (R²): {r2:.2f}')\n",
    "\n",
    "# Визуализация результатов\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.scatter(y_val, val_predictions, alpha=0.5)\n",
    "plt.plot([y_val.min(), y_val.max()], [y_val.min(), y_val.max()], 'k--', lw=2)\n",
    "plt.xlabel('Фактический уровень глюкозы')\n",
    "plt.ylabel('Прогнозируемый уровень глюкозы')\n",
    "plt.title('Фактический уровень глюкозы по сравнению с прогнозируемым')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " # Выводы\n",
    "\n",
    "**Модель линейной регрессии (LinearRegression)** показала удовлетворительные результаты при прогнозировании уровня глюкозы у индейцев Пима. Метрики качества и кросс-валидация позволяют предположить, что модель не сильно переобучена и может быть использована для практических целей.\n",
    "\n",
    "*Точность предсказаний:* Модель демонстрирует довольно высокий коэффициент детерминации (R²) 0.30, что указывает на умеренную часть вариации целевого признака (уровня глюкозы). Однако, значения среднеквадратичной ошибки (RMSE) остаются высокими (704.68), что свидетельствует о том, что модель не всегда точно предсказывает значения, особенно для объектов с высокими или низкими уровнями глюкозы.\n",
    "\n",
    "*Переобучение:* Разница между RMSE на обучающей и тестовой выборках незначительна, что указывает на то, что модель не склонна к переобучению. Однако в будущем стоит следить за этой метрикой при добавлении новых признаков или усложнении модели, чтобы избежать излишней подгонки под тренировочные данные. Также стоит быть осторожным и продолжать мониторинг этого показателя.\n",
    "\n",
    "*Кросс-валидация:* При кросс-валидации наблюдается небольшое увеличение ошибки RMSE по сравнению с тестовой выборкой (рост на 2-3%). Это может указывать на небольшую нестабильность модели при использовании разных подвыборок данных. Для повышения устойчивости модели возможно стоит провести дальнейшую настройку гиперпараметров.\n",
    "\n",
    "*Рекомендации:* Следует уделить внимание дополнительной обработке категориальных признаков, улучшению метода feature engineering, а также возможной оптимизации модели (например, через подбор гиперпараметров) для повышения точности предсказаний на экстремальных значениях."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "aimenv",
   "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": "3.12.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}