3185 lines
1.6 MiB
Plaintext
3185 lines
1.6 MiB
Plaintext
|
{
|
|||
|
|
"cells": [
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### 1. Датасет: Диабет у индейцев Пима\n",
|
|||
|
|
"https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database\n",
|
|||
|
|
"##### О наборе данных: \n",
|
|||
|
|
"Этот набор данных был получен из Национального института диабета, болезней органов пищеварения и почек. Цель набора данных - диагностически предсказать, есть ли у пациента сахарный диабет, на основе определенных диагностических измерений, включенных в набор данных. На выбор этих образцов из более обширной базы данных было наложено несколько ограничений. В частности, все пациенты были женщинами в возрасте не менее 21 года, родом из племени пима.\n",
|
|||
|
|
"##### Таким образом:\n",
|
|||
|
|
"* Объект наблюдения - женщины племени пима, возрастом от 21 года.\n",
|
|||
|
|
"* Атрибуты: Pregnancies, Glucose, BloodPressure, SkinThickness, Insulin, BMI, DiabetesPedigreeFunction, Age, Outcome.\n",
|
|||
|
|
"* Проблемная область: Предсказание диабета у пациента на основе измерений."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 43,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Количество колонок: 9\n",
|
|||
|
|
"Колонки: Pregnancies, Glucose, BloodPressure, SkinThickness, Insulin, BMI, DiabetesPedigreeFunction, Age, Outcome\n",
|
|||
|
|
"\n",
|
|||
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
|||
|
|
"RangeIndex: 768 entries, 0 to 767\n",
|
|||
|
|
"Data columns (total 9 columns):\n",
|
|||
|
|
" # Column Non-Null Count Dtype \n",
|
|||
|
|
"--- ------ -------------- ----- \n",
|
|||
|
|
" 0 Pregnancies 768 non-null int64 \n",
|
|||
|
|
" 1 Glucose 768 non-null int64 \n",
|
|||
|
|
" 2 BloodPressure 768 non-null int64 \n",
|
|||
|
|
" 3 SkinThickness 768 non-null int64 \n",
|
|||
|
|
" 4 Insulin 768 non-null int64 \n",
|
|||
|
|
" 5 BMI 768 non-null float64\n",
|
|||
|
|
" 6 DiabetesPedigreeFunction 768 non-null float64\n",
|
|||
|
|
" 7 Age 768 non-null int64 \n",
|
|||
|
|
" 8 Outcome 768 non-null int64 \n",
|
|||
|
|
"dtypes: float64(2), int64(7)\n",
|
|||
|
|
"memory usage: 54.1 KB\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>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": 43,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"import pandas as pd\n",
|
|||
|
|
"df = pd.read_csv(\".//static//csv//diabetes.csv\", sep=\",\")\n",
|
|||
|
|
"print('Количество колонок: ' + str(df.columns.size)) \n",
|
|||
|
|
"print('Колонки: ' + ', '.join(df.columns)+'\\n')\n",
|
|||
|
|
"\n",
|
|||
|
|
"df.info()\n",
|
|||
|
|
"df.head()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Получение сведений о пропущенных данных\n",
|
|||
|
|
"Типы пропущенных данных:\n",
|
|||
|
|
"\n",
|
|||
|
|
"- None - представление пустых данных в Python\n",
|
|||
|
|
"- NaN - представление пустых данных в Pandas\n",
|
|||
|
|
"- '' - пустая строка"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 44,
|
|||
|
|
"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",
|
|||
|
|
"\n",
|
|||
|
|
"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\n",
|
|||
|
|
"\n",
|
|||
|
|
"Pregnancies процент пустых значений: %0.00\n",
|
|||
|
|
"Glucose процент пустых значений: %0.00\n",
|
|||
|
|
"BloodPressure процент пустых значений: %0.00\n",
|
|||
|
|
"SkinThickness процент пустых значений: %0.00\n",
|
|||
|
|
"Insulin процент пустых значений: %0.00\n",
|
|||
|
|
"BMI процент пустых значений: %0.00\n",
|
|||
|
|
"DiabetesPedigreeFunction процент пустых значений: %0.00\n",
|
|||
|
|
"Age процент пустых значений: %0.00\n",
|
|||
|
|
"Outcome процент пустых значений: %0.00\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"# Количество пустых значений признаков\n",
|
|||
|
|
"print(df.isnull().sum())\n",
|
|||
|
|
"print()\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Есть ли пустые значения признаков\n",
|
|||
|
|
"print(df.isnull().any())\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",
|
|||
|
|
" print(f\"{i} процент пустых значений: %{null_rate:.2f}\")"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"##### Проверим выбросы и устраним их:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 45,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Колонка Pregnancies:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 4\n",
|
|||
|
|
" Минимальное значение: 0.0\n",
|
|||
|
|
" Максимальное значение: 13.5\n",
|
|||
|
|
" 1-й квартиль (Q1): 1.0\n",
|
|||
|
|
" 3-й квартиль (Q3): 6.0\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка Glucose:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 5\n",
|
|||
|
|
" Минимальное значение: 37.125\n",
|
|||
|
|
" Максимальное значение: 199.0\n",
|
|||
|
|
" 1-й квартиль (Q1): 99.0\n",
|
|||
|
|
" 3-й квартиль (Q3): 140.25\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка BloodPressure:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 45\n",
|
|||
|
|
" Минимальное значение: 35.0\n",
|
|||
|
|
" Максимальное значение: 107.0\n",
|
|||
|
|
" 1-й квартиль (Q1): 62.0\n",
|
|||
|
|
" 3-й квартиль (Q3): 80.0\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка SkinThickness:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 1\n",
|
|||
|
|
" Минимальное значение: 0.0\n",
|
|||
|
|
" Максимальное значение: 80.0\n",
|
|||
|
|
" 1-й квартиль (Q1): 0.0\n",
|
|||
|
|
" 3-й квартиль (Q3): 32.0\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка Insulin:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 34\n",
|
|||
|
|
" Минимальное значение: 0.0\n",
|
|||
|
|
" Максимальное значение: 318.125\n",
|
|||
|
|
" 1-й квартиль (Q1): 0.0\n",
|
|||
|
|
" 3-й квартиль (Q3): 127.25\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка BMI:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 19\n",
|
|||
|
|
" Минимальное значение: 13.35\n",
|
|||
|
|
" Максимальное значение: 50.550000000000004\n",
|
|||
|
|
" 1-й квартиль (Q1): 27.3\n",
|
|||
|
|
" 3-й квартиль (Q3): 36.6\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка DiabetesPedigreeFunction:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 29\n",
|
|||
|
|
" Минимальное значение: 0.078\n",
|
|||
|
|
" Максимальное значение: 1.2\n",
|
|||
|
|
" 1-й квартиль (Q1): 0.24375\n",
|
|||
|
|
" 3-й квартиль (Q3): 0.62625\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка Age:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 9\n",
|
|||
|
|
" Минимальное значение: 21.0\n",
|
|||
|
|
" Максимальное значение: 66.5\n",
|
|||
|
|
" 1-й квартиль (Q1): 24.0\n",
|
|||
|
|
" 3-й квартиль (Q3): 41.0\n",
|
|||
|
|
"\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"numeric_columns = ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age']\n",
|
|||
|
|
"for column in numeric_columns:\n",
|
|||
|
|
" if pd.api.types.is_numeric_dtype(df[column]): # Проверяем, является ли колонка числовой\n",
|
|||
|
|
" q1 = df[column].quantile(0.25) # Находим 1-й квартиль (Q1)\n",
|
|||
|
|
" q3 = df[column].quantile(0.75) # Находим 3-й квартиль (Q3)\n",
|
|||
|
|
" iqr = q3 - q1 # Вычисляем межквартильный размах (IQR)\n",
|
|||
|
|
"\n",
|
|||
|
|
" # Определяем границы для выбросов\n",
|
|||
|
|
" lower_bound = q1 - 1.5 * iqr # Нижняя граница\n",
|
|||
|
|
" upper_bound = q3 + 1.5 * iqr # Верхняя граница\n",
|
|||
|
|
"\n",
|
|||
|
|
" # Подсчитываем количество выбросов\n",
|
|||
|
|
" outliers = df[(df[column] < lower_bound) | (df[column] > upper_bound)]\n",
|
|||
|
|
" outlier_count = outliers.shape[0]\n",
|
|||
|
|
"\n",
|
|||
|
|
" # Устраняем выбросы: заменяем значения ниже нижней границы на саму нижнюю границу, а выше верхней — на верхнюю\n",
|
|||
|
|
" df[column] = df[column].apply(lambda x: lower_bound if x < lower_bound else upper_bound if x > upper_bound else x)\n",
|
|||
|
|
"\n",
|
|||
|
|
" print(f\"Колонка {column}:\")\n",
|
|||
|
|
" print(f\" Есть выбросы: {'Да' if outlier_count > 0 else 'Нет'}\")\n",
|
|||
|
|
" print(f\" Количество выбросов: {outlier_count}\")\n",
|
|||
|
|
" print(f\" Минимальное значение: {df[column].min()}\")\n",
|
|||
|
|
" print(f\" Максимальное значение: {df[column].max()}\")\n",
|
|||
|
|
" print(f\" 1-й квартиль (Q1): {q1}\")\n",
|
|||
|
|
" print(f\" 3-й квартиль (Q3): {q3}\\n\")"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Постараемся выявить зависимости Outcome от остальных колонок:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 47,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"import matplotlib.pyplot as plt\n",
|
|||
|
|
" # Создание диаграмм зависимости\n",
|
|||
|
|
"for column in numeric_columns:\n",
|
|||
|
|
" plt.figure(figsize=(8, 6)) # Установка размера графика\n",
|
|||
|
|
" if pd.api.types.is_numeric_dtype(df[column]): # Проверяем, является ли колонка числовой\n",
|
|||
|
|
" # Проверяем, содержит ли колонка только два уникальных значения (0 и 1)\n",
|
|||
|
|
" if df[column].nunique() == 2 and set(df[column].unique()).issubset({0, 1}):\n",
|
|||
|
|
" # Если да, то строим столбчатую диаграмму\n",
|
|||
|
|
" counts = df[column].value_counts() # Считаем количество повторений каждого значения\n",
|
|||
|
|
" counts.plot(kind='bar') # Создаем столбчатую диаграмму\n",
|
|||
|
|
" plt.title(f'Количество значений для {column}')\n",
|
|||
|
|
" plt.xlabel(column)\n",
|
|||
|
|
" plt.ylabel('Количество повторений')\n",
|
|||
|
|
" else:\n",
|
|||
|
|
" # Если колонка числовая, создаем диаграмму рассеяния\n",
|
|||
|
|
" plt.scatter(df['Outcome'], df[column], alpha=0.5) # Создаем диаграмму рассеяния\n",
|
|||
|
|
" plt.title(f'Зависимость {column} от Outcome')\n",
|
|||
|
|
" plt.xlabel('Outcome (0 = нет, 1 = да)')\n",
|
|||
|
|
" plt.ylabel(column)\n",
|
|||
|
|
" plt.xticks([0, 1]) # Установка меток по оси X\n",
|
|||
|
|
" plt.grid() # Добавление сетки для удобства восприятия\n",
|
|||
|
|
" else:\n",
|
|||
|
|
" # Если колонка не числовая, строим столбчатую диаграмму\n",
|
|||
|
|
" counts = df[column].value_counts() # Считаем количество повторений каждого значения\n",
|
|||
|
|
" counts.plot(kind='bar') # Создаем столбчатую диаграмму\n",
|
|||
|
|
" plt.title(f'Количество значений для {column}')\n",
|
|||
|
|
" plt.xlabel(column)\n",
|
|||
|
|
" plt.ylabel('Количество повторений')\n",
|
|||
|
|
"\n",
|
|||
|
|
" plt.show() # Отображение графика"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Разобьем наш набор на выборки относительно параметра Outcome:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 34,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"# Функция для создания выборок\n",
|
|||
|
|
"from sklearn.model_selection import train_test_split\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",
|
|||
|
|
" 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": 35,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Outcome\n",
|
|||
|
|
"0 500\n",
|
|||
|
|
"1 268\n",
|
|||
|
|
"Name: count, dtype: int64\n",
|
|||
|
|
"\n",
|
|||
|
|
"Обучающая выборка: (460, 9)\n",
|
|||
|
|
"Outcome\n",
|
|||
|
|
"0 299\n",
|
|||
|
|
"1 161\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Контрольная выборка: (154, 9)\n",
|
|||
|
|
"Outcome\n",
|
|||
|
|
"0 101\n",
|
|||
|
|
"1 53\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Тестовая выборка: (154, 9)\n",
|
|||
|
|
"Outcome\n",
|
|||
|
|
"0 100\n",
|
|||
|
|
"1 54\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"# Вывод распределения количества наблюдений по меткам (классам)\n",
|
|||
|
|
"print(df.Outcome.value_counts())\n",
|
|||
|
|
"print()\n",
|
|||
|
|
"\n",
|
|||
|
|
"data = df.copy()\n",
|
|||
|
|
"\n",
|
|||
|
|
"df_train, df_val, df_test = split_stratified_into_train_val_test(\n",
|
|||
|
|
" data, stratify_colname=\"Outcome\", frac_train=0.60, frac_val=0.20, frac_test=0.20\n",
|
|||
|
|
")\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(\"Обучающая выборка: \", df_train.shape)\n",
|
|||
|
|
"print(df_train.Outcome.value_counts())\n",
|
|||
|
|
"counts = df_train['Outcome'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))# Установка размера графика\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)# Построение круговой диаграммы\n",
|
|||
|
|
"plt.title('Распределение классов Outcome в обучающей выборке')# Добавление заголовка\n",
|
|||
|
|
"plt.show()# Отображение графика\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(\"Контрольная выборка: \", df_val.shape)\n",
|
|||
|
|
"print(df_val.Outcome.value_counts())\n",
|
|||
|
|
"counts = df_val['Outcome'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов Outcome в контрольной выборке')\n",
|
|||
|
|
"plt.show()\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(\"Тестовая выборка: \", df_test.shape)\n",
|
|||
|
|
"print(df_test.Outcome.value_counts())\n",
|
|||
|
|
"counts = df_test['Outcome'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов Outcome в тестовой выборке')\n",
|
|||
|
|
"plt.show()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Сбалансируем распределение:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"1. Балансировка данных оверсемплингом. Это метод, увеличивающий число наблюдений в меньшинственном классе для достижения более равномерного распределения классов."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 39,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Обучающая выборка: (460, 9)\n",
|
|||
|
|
"Outcome\n",
|
|||
|
|
"0 299\n",
|
|||
|
|
"1 161\n",
|
|||
|
|
"Name: count, dtype: int64\n",
|
|||
|
|
"Обучающая выборка после oversampling: (594, 9)\n",
|
|||
|
|
"Outcome\n",
|
|||
|
|
"0 299\n",
|
|||
|
|
"1 295\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"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>3.000000</td>\n",
|
|||
|
|
" <td>124.000000</td>\n",
|
|||
|
|
" <td>80.000000</td>\n",
|
|||
|
|
" <td>33.000000</td>\n",
|
|||
|
|
" <td>130.000000</td>\n",
|
|||
|
|
" <td>33.200000</td>\n",
|
|||
|
|
" <td>0.305000</td>\n",
|
|||
|
|
" <td>26.000000</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>1</th>\n",
|
|||
|
|
" <td>1.000000</td>\n",
|
|||
|
|
" <td>80.000000</td>\n",
|
|||
|
|
" <td>74.000000</td>\n",
|
|||
|
|
" <td>11.000000</td>\n",
|
|||
|
|
" <td>60.000000</td>\n",
|
|||
|
|
" <td>30.000000</td>\n",
|
|||
|
|
" <td>0.527000</td>\n",
|
|||
|
|
" <td>22.000000</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>2</th>\n",
|
|||
|
|
" <td>4.000000</td>\n",
|
|||
|
|
" <td>90.000000</td>\n",
|
|||
|
|
" <td>88.000000</td>\n",
|
|||
|
|
" <td>47.000000</td>\n",
|
|||
|
|
" <td>54.000000</td>\n",
|
|||
|
|
" <td>37.700000</td>\n",
|
|||
|
|
" <td>0.362000</td>\n",
|
|||
|
|
" <td>29.000000</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>3</th>\n",
|
|||
|
|
" <td>1.000000</td>\n",
|
|||
|
|
" <td>100.000000</td>\n",
|
|||
|
|
" <td>66.000000</td>\n",
|
|||
|
|
" <td>15.000000</td>\n",
|
|||
|
|
" <td>56.000000</td>\n",
|
|||
|
|
" <td>23.600000</td>\n",
|
|||
|
|
" <td>0.666000</td>\n",
|
|||
|
|
" <td>26.000000</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>4</th>\n",
|
|||
|
|
" <td>3.000000</td>\n",
|
|||
|
|
" <td>139.000000</td>\n",
|
|||
|
|
" <td>54.000000</td>\n",
|
|||
|
|
" <td>0.000000</td>\n",
|
|||
|
|
" <td>0.000000</td>\n",
|
|||
|
|
" <td>25.600000</td>\n",
|
|||
|
|
" <td>0.402000</td>\n",
|
|||
|
|
" <td>22.000000</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>...</th>\n",
|
|||
|
|
" <td>...</td>\n",
|
|||
|
|
" <td>...</td>\n",
|
|||
|
|
" <td>...</td>\n",
|
|||
|
|
" <td>...</td>\n",
|
|||
|
|
" <td>...</td>\n",
|
|||
|
|
" <td>...</td>\n",
|
|||
|
|
" <td>...</td>\n",
|
|||
|
|
" <td>...</td>\n",
|
|||
|
|
" <td>...</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>589</th>\n",
|
|||
|
|
" <td>5.532765</td>\n",
|
|||
|
|
" <td>123.754039</td>\n",
|
|||
|
|
" <td>78.778726</td>\n",
|
|||
|
|
" <td>30.922127</td>\n",
|
|||
|
|
" <td>0.000000</td>\n",
|
|||
|
|
" <td>27.981576</td>\n",
|
|||
|
|
" <td>0.587583</td>\n",
|
|||
|
|
" <td>48.143402</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>590</th>\n",
|
|||
|
|
" <td>0.324393</td>\n",
|
|||
|
|
" <td>122.297574</td>\n",
|
|||
|
|
" <td>60.809705</td>\n",
|
|||
|
|
" <td>33.243934</td>\n",
|
|||
|
|
" <td>165.648787</td>\n",
|
|||
|
|
" <td>33.975607</td>\n",
|
|||
|
|
" <td>0.449215</td>\n",
|
|||
|
|
" <td>31.378033</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>591</th>\n",
|
|||
|
|
" <td>0.462644</td>\n",
|
|||
|
|
" <td>159.918100</td>\n",
|
|||
|
|
" <td>76.693967</td>\n",
|
|||
|
|
" <td>35.537356</td>\n",
|
|||
|
|
" <td>0.000000</td>\n",
|
|||
|
|
" <td>48.316162</td>\n",
|
|||
|
|
" <td>0.385976</td>\n",
|
|||
|
|
" <td>27.272272</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>592</th>\n",
|
|||
|
|
" <td>1.033191</td>\n",
|
|||
|
|
" <td>128.066382</td>\n",
|
|||
|
|
" <td>97.977873</td>\n",
|
|||
|
|
" <td>40.977873</td>\n",
|
|||
|
|
" <td>57.919788</td>\n",
|
|||
|
|
" <td>31.985617</td>\n",
|
|||
|
|
" <td>1.198703</td>\n",
|
|||
|
|
" <td>33.027659</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>593</th>\n",
|
|||
|
|
" <td>1.655930</td>\n",
|
|||
|
|
" <td>132.147291</td>\n",
|
|||
|
|
" <td>100.556954</td>\n",
|
|||
|
|
" <td>28.590337</td>\n",
|
|||
|
|
" <td>140.655930</td>\n",
|
|||
|
|
" <td>33.423133</td>\n",
|
|||
|
|
" <td>0.270142</td>\n",
|
|||
|
|
" <td>45.196779</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </tbody>\n",
|
|||
|
|
"</table>\n",
|
|||
|
|
"<p>594 rows × 9 columns</p>\n",
|
|||
|
|
"</div>"
|
|||
|
|
],
|
|||
|
|
"text/plain": [
|
|||
|
|
" Pregnancies Glucose BloodPressure SkinThickness Insulin \\\n",
|
|||
|
|
"0 3.000000 124.000000 80.000000 33.000000 130.000000 \n",
|
|||
|
|
"1 1.000000 80.000000 74.000000 11.000000 60.000000 \n",
|
|||
|
|
"2 4.000000 90.000000 88.000000 47.000000 54.000000 \n",
|
|||
|
|
"3 1.000000 100.000000 66.000000 15.000000 56.000000 \n",
|
|||
|
|
"4 3.000000 139.000000 54.000000 0.000000 0.000000 \n",
|
|||
|
|
".. ... ... ... ... ... \n",
|
|||
|
|
"589 5.532765 123.754039 78.778726 30.922127 0.000000 \n",
|
|||
|
|
"590 0.324393 122.297574 60.809705 33.243934 165.648787 \n",
|
|||
|
|
"591 0.462644 159.918100 76.693967 35.537356 0.000000 \n",
|
|||
|
|
"592 1.033191 128.066382 97.977873 40.977873 57.919788 \n",
|
|||
|
|
"593 1.655930 132.147291 100.556954 28.590337 140.655930 \n",
|
|||
|
|
"\n",
|
|||
|
|
" BMI DiabetesPedigreeFunction Age Outcome \n",
|
|||
|
|
"0 33.200000 0.305000 26.000000 0 \n",
|
|||
|
|
"1 30.000000 0.527000 22.000000 0 \n",
|
|||
|
|
"2 37.700000 0.362000 29.000000 0 \n",
|
|||
|
|
"3 23.600000 0.666000 26.000000 0 \n",
|
|||
|
|
"4 25.600000 0.402000 22.000000 1 \n",
|
|||
|
|
".. ... ... ... ... \n",
|
|||
|
|
"589 27.981576 0.587583 48.143402 1 \n",
|
|||
|
|
"590 33.975607 0.449215 31.378033 1 \n",
|
|||
|
|
"591 48.316162 0.385976 27.272272 1 \n",
|
|||
|
|
"592 31.985617 1.198703 33.027659 1 \n",
|
|||
|
|
"593 33.423133 0.270142 45.196779 1 \n",
|
|||
|
|
"\n",
|
|||
|
|
"[594 rows x 9 columns]"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 39,
|
|||
|
|
"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.Outcome.value_counts())\n",
|
|||
|
|
"\n",
|
|||
|
|
"X_resampled, y_resampled = ada.fit_resample(df_train, df_train[\"Outcome\"])\n",
|
|||
|
|
"df_train_adasyn = pd.DataFrame(X_resampled)\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(\"Обучающая выборка после oversampling: \", df_train_adasyn.shape)\n",
|
|||
|
|
"print(df_train_adasyn.Outcome.value_counts())\n",
|
|||
|
|
"\n",
|
|||
|
|
"counts = df_train_adasyn['Outcome'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов Outcome в тренировочной выборке после ADASYN')\n",
|
|||
|
|
"plt.show()\n",
|
|||
|
|
"\n",
|
|||
|
|
"df_train_adasyn"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"2. Балансировка данных андерсемплингом. Этот метод помогает сбалансировать выборку, уменьшая количество экземпляров класса большинства, чтобы привести его в соответствие с классом меньшинства."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 41,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Обучающая выборка после undersampling: (322, 9)\n",
|
|||
|
|
"Outcome\n",
|
|||
|
|
"0 161\n",
|
|||
|
|
"1 161\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"from imblearn.under_sampling import RandomUnderSampler\n",
|
|||
|
|
"\n",
|
|||
|
|
"rus = RandomUnderSampler()# Создание экземпляра RandomUnderSampler\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Применение RandomUnderSampler\n",
|
|||
|
|
"X_resampled, y_resampled = rus.fit_resample(df_train.drop(columns=['Outcome']), df_train['Outcome'])\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Создание нового DataFrame\n",
|
|||
|
|
"df_train_undersampled = pd.DataFrame(X_resampled)\n",
|
|||
|
|
"df_train_undersampled['Outcome'] = y_resampled # Добавление целевой переменной\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Вывод информации о новой выборке\n",
|
|||
|
|
"print(\"Обучающая выборка после undersampling: \", df_train_undersampled.shape)\n",
|
|||
|
|
"print(df_train_undersampled['Outcome'].value_counts())\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Визуализация распределения классов\n",
|
|||
|
|
"counts = df_train_undersampled['Outcome'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов Outcome в тренировочной выборке после Undersampling')\n",
|
|||
|
|
"plt.show()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### 2. Датасет: Данные по инсультам\n",
|
|||
|
|
"https://www.kaggle.com/datasets/fedesoriano/stroke-prediction-dataset\n",
|
|||
|
|
"##### О наборе данных: \n",
|
|||
|
|
"По данным Всемирной организации здравоохранения (ВОЗ), инсульт является второй по значимости причиной смертности во всем мире, на его долю приходится примерно 11% от общего числа смертей.\n",
|
|||
|
|
"Этот набор данных используется для прогнозирования вероятности инсульта у пациента на основе входных параметров, таких как пол, возраст, различные заболевания и статус курильщика. Каждая строка в данных содержит соответствующую информацию о пациенте.\n",
|
|||
|
|
"\n",
|
|||
|
|
"Атрибуты:\n",
|
|||
|
|
"1) id: уникальный идентификатор\n",
|
|||
|
|
"2) gender: \"Male\", \"Female\" или \"Other\"\n",
|
|||
|
|
"3) age: возраст пациента\n",
|
|||
|
|
"4) hypertension: 0, если у пациента нет артериальной гипертензии, 1, если у пациента есть артериальная гипертензия\n",
|
|||
|
|
"5) heart_disease: 0, если у пациента нет сердечных заболеваний, 1, если у пациента есть сердечные заболевания\n",
|
|||
|
|
"6) ever_married: \"No\" или \"Yes\"\n",
|
|||
|
|
"7) work_type: \"children\", \"Govt_jov\", \"Never_worked\", \"Private\" or \"Self-employed\"\n",
|
|||
|
|
"8) Residence_type: \"Rural\" or \"Urban\"\n",
|
|||
|
|
"9) avg_glucose_level: средний уровень глюкозы в крови\n",
|
|||
|
|
"10) bmi: индекс массы тела\n",
|
|||
|
|
"11) smoking_status: \"formerly smoked\", \"never smoked\", \"smokes\" или \"Unknown\"*\n",
|
|||
|
|
"12) stroke: 1, если у пациента был инсульт, или 0, если нет.\n",
|
|||
|
|
"##### Таким образом:\n",
|
|||
|
|
"* Объект наблюдения - Реальные пациенты.\n",
|
|||
|
|
"* Атрибуты: id, gender, age, hypertension, heart_disease, ever_married, work_type, Residence_type, avg_glucose_level, bmi, smoking_status, stroke.\n",
|
|||
|
|
"* Проблемная область: Прогнозирование вероятности инсульта у пациента."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 34,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Количество колонок: 12\n",
|
|||
|
|
"Колонки: id, gender, age, hypertension, heart_disease, ever_married, work_type, Residence_type, avg_glucose_level, bmi, smoking_status, stroke\n",
|
|||
|
|
"\n",
|
|||
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
|||
|
|
"RangeIndex: 5110 entries, 0 to 5109\n",
|
|||
|
|
"Data columns (total 12 columns):\n",
|
|||
|
|
" # Column Non-Null Count Dtype \n",
|
|||
|
|
"--- ------ -------------- ----- \n",
|
|||
|
|
" 0 id 5110 non-null int64 \n",
|
|||
|
|
" 1 gender 5110 non-null object \n",
|
|||
|
|
" 2 age 5110 non-null float64\n",
|
|||
|
|
" 3 hypertension 5110 non-null int64 \n",
|
|||
|
|
" 4 heart_disease 5110 non-null int64 \n",
|
|||
|
|
" 5 ever_married 5110 non-null object \n",
|
|||
|
|
" 6 work_type 5110 non-null object \n",
|
|||
|
|
" 7 Residence_type 5110 non-null object \n",
|
|||
|
|
" 8 avg_glucose_level 5110 non-null float64\n",
|
|||
|
|
" 9 bmi 4909 non-null float64\n",
|
|||
|
|
" 10 smoking_status 5110 non-null object \n",
|
|||
|
|
" 11 stroke 5110 non-null int64 \n",
|
|||
|
|
"dtypes: float64(3), int64(4), object(5)\n",
|
|||
|
|
"memory usage: 479.2+ KB\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>id</th>\n",
|
|||
|
|
" <th>gender</th>\n",
|
|||
|
|
" <th>age</th>\n",
|
|||
|
|
" <th>hypertension</th>\n",
|
|||
|
|
" <th>heart_disease</th>\n",
|
|||
|
|
" <th>ever_married</th>\n",
|
|||
|
|
" <th>work_type</th>\n",
|
|||
|
|
" <th>Residence_type</th>\n",
|
|||
|
|
" <th>avg_glucose_level</th>\n",
|
|||
|
|
" <th>bmi</th>\n",
|
|||
|
|
" <th>smoking_status</th>\n",
|
|||
|
|
" <th>stroke</th>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </thead>\n",
|
|||
|
|
" <tbody>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>0</th>\n",
|
|||
|
|
" <td>9046</td>\n",
|
|||
|
|
" <td>Male</td>\n",
|
|||
|
|
" <td>67.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Private</td>\n",
|
|||
|
|
" <td>Urban</td>\n",
|
|||
|
|
" <td>228.69</td>\n",
|
|||
|
|
" <td>36.6</td>\n",
|
|||
|
|
" <td>formerly smoked</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>1</th>\n",
|
|||
|
|
" <td>51676</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>61.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Self-employed</td>\n",
|
|||
|
|
" <td>Rural</td>\n",
|
|||
|
|
" <td>202.21</td>\n",
|
|||
|
|
" <td>NaN</td>\n",
|
|||
|
|
" <td>never smoked</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>2</th>\n",
|
|||
|
|
" <td>31112</td>\n",
|
|||
|
|
" <td>Male</td>\n",
|
|||
|
|
" <td>80.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Private</td>\n",
|
|||
|
|
" <td>Rural</td>\n",
|
|||
|
|
" <td>105.92</td>\n",
|
|||
|
|
" <td>32.5</td>\n",
|
|||
|
|
" <td>never smoked</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>3</th>\n",
|
|||
|
|
" <td>60182</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>49.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Private</td>\n",
|
|||
|
|
" <td>Urban</td>\n",
|
|||
|
|
" <td>171.23</td>\n",
|
|||
|
|
" <td>34.4</td>\n",
|
|||
|
|
" <td>smokes</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>4</th>\n",
|
|||
|
|
" <td>1665</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>79.0</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Self-employed</td>\n",
|
|||
|
|
" <td>Rural</td>\n",
|
|||
|
|
" <td>174.12</td>\n",
|
|||
|
|
" <td>24.0</td>\n",
|
|||
|
|
" <td>never smoked</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </tbody>\n",
|
|||
|
|
"</table>\n",
|
|||
|
|
"</div>"
|
|||
|
|
],
|
|||
|
|
"text/plain": [
|
|||
|
|
" id gender age hypertension heart_disease ever_married \\\n",
|
|||
|
|
"0 9046 Male 67.0 0 1 Yes \n",
|
|||
|
|
"1 51676 Female 61.0 0 0 Yes \n",
|
|||
|
|
"2 31112 Male 80.0 0 1 Yes \n",
|
|||
|
|
"3 60182 Female 49.0 0 0 Yes \n",
|
|||
|
|
"4 1665 Female 79.0 1 0 Yes \n",
|
|||
|
|
"\n",
|
|||
|
|
" work_type Residence_type avg_glucose_level bmi smoking_status \\\n",
|
|||
|
|
"0 Private Urban 228.69 36.6 formerly smoked \n",
|
|||
|
|
"1 Self-employed Rural 202.21 NaN never smoked \n",
|
|||
|
|
"2 Private Rural 105.92 32.5 never smoked \n",
|
|||
|
|
"3 Private Urban 171.23 34.4 smokes \n",
|
|||
|
|
"4 Self-employed Rural 174.12 24.0 never smoked \n",
|
|||
|
|
"\n",
|
|||
|
|
" stroke \n",
|
|||
|
|
"0 1 \n",
|
|||
|
|
"1 1 \n",
|
|||
|
|
"2 1 \n",
|
|||
|
|
"3 1 \n",
|
|||
|
|
"4 1 "
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 34,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"import pandas as pd\n",
|
|||
|
|
"df = pd.read_csv(\".//static//csv//stroke.csv\", sep=\",\")\n",
|
|||
|
|
"print('Количество колонок: ' + str(df.columns.size)) \n",
|
|||
|
|
"print('Колонки: ' + ', '.join(df.columns)+'\\n')\n",
|
|||
|
|
"\n",
|
|||
|
|
"df.info()\n",
|
|||
|
|
"df.head()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Получение сведений о пропущенных данных\n",
|
|||
|
|
"Типы пропущенных данных:\n",
|
|||
|
|
"\n",
|
|||
|
|
"- None - представление пустых данных в Python\n",
|
|||
|
|
"- NaN - представление пустых данных в Pandas\n",
|
|||
|
|
"- '' - пустая строка"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 6,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"id 0\n",
|
|||
|
|
"gender 0\n",
|
|||
|
|
"age 0\n",
|
|||
|
|
"hypertension 0\n",
|
|||
|
|
"heart_disease 0\n",
|
|||
|
|
"ever_married 0\n",
|
|||
|
|
"work_type 0\n",
|
|||
|
|
"Residence_type 0\n",
|
|||
|
|
"avg_glucose_level 0\n",
|
|||
|
|
"bmi 201\n",
|
|||
|
|
"smoking_status 0\n",
|
|||
|
|
"stroke 0\n",
|
|||
|
|
"dtype: int64\n",
|
|||
|
|
"\n",
|
|||
|
|
"id False\n",
|
|||
|
|
"gender False\n",
|
|||
|
|
"age False\n",
|
|||
|
|
"hypertension False\n",
|
|||
|
|
"heart_disease False\n",
|
|||
|
|
"ever_married False\n",
|
|||
|
|
"work_type False\n",
|
|||
|
|
"Residence_type False\n",
|
|||
|
|
"avg_glucose_level False\n",
|
|||
|
|
"bmi True\n",
|
|||
|
|
"smoking_status False\n",
|
|||
|
|
"stroke False\n",
|
|||
|
|
"dtype: bool\n",
|
|||
|
|
"\n",
|
|||
|
|
"id процент пустых значений: %0.00\n",
|
|||
|
|
"gender процент пустых значений: %0.00\n",
|
|||
|
|
"age процент пустых значений: %0.00\n",
|
|||
|
|
"hypertension процент пустых значений: %0.00\n",
|
|||
|
|
"heart_disease процент пустых значений: %0.00\n",
|
|||
|
|
"ever_married процент пустых значений: %0.00\n",
|
|||
|
|
"work_type процент пустых значений: %0.00\n",
|
|||
|
|
"Residence_type процент пустых значений: %0.00\n",
|
|||
|
|
"avg_glucose_level процент пустых значений: %0.00\n",
|
|||
|
|
"bmi процент пустых значений: %3.93\n",
|
|||
|
|
"smoking_status процент пустых значений: %0.00\n",
|
|||
|
|
"stroke процент пустых значений: %0.00\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"# Количество пустых значений признаков\n",
|
|||
|
|
"print(df.isnull().sum())\n",
|
|||
|
|
"print()\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Есть ли пустые значения признаков\n",
|
|||
|
|
"print(df.isnull().any())\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",
|
|||
|
|
" print(f\"{i} процент пустых значений: %{null_rate:.2f}\")"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"##### Пропущенные данные существуют. Необходимо заполнить пропуски медианными значениями.\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"Заполнение пропущенных данных:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 7,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"(5110, 12)\n",
|
|||
|
|
"id False\n",
|
|||
|
|
"gender False\n",
|
|||
|
|
"age False\n",
|
|||
|
|
"hypertension False\n",
|
|||
|
|
"heart_disease False\n",
|
|||
|
|
"ever_married False\n",
|
|||
|
|
"work_type False\n",
|
|||
|
|
"Residence_type False\n",
|
|||
|
|
"avg_glucose_level False\n",
|
|||
|
|
"bmi False\n",
|
|||
|
|
"smoking_status False\n",
|
|||
|
|
"stroke False\n",
|
|||
|
|
"dtype: bool\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>id</th>\n",
|
|||
|
|
" <th>gender</th>\n",
|
|||
|
|
" <th>age</th>\n",
|
|||
|
|
" <th>hypertension</th>\n",
|
|||
|
|
" <th>heart_disease</th>\n",
|
|||
|
|
" <th>ever_married</th>\n",
|
|||
|
|
" <th>work_type</th>\n",
|
|||
|
|
" <th>Residence_type</th>\n",
|
|||
|
|
" <th>avg_glucose_level</th>\n",
|
|||
|
|
" <th>bmi</th>\n",
|
|||
|
|
" <th>smoking_status</th>\n",
|
|||
|
|
" <th>stroke</th>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </thead>\n",
|
|||
|
|
" <tbody>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5105</th>\n",
|
|||
|
|
" <td>18234</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>80.0</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Private</td>\n",
|
|||
|
|
" <td>Urban</td>\n",
|
|||
|
|
" <td>83.75</td>\n",
|
|||
|
|
" <td>27.7</td>\n",
|
|||
|
|
" <td>never smoked</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5106</th>\n",
|
|||
|
|
" <td>44873</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>81.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Self-employed</td>\n",
|
|||
|
|
" <td>Urban</td>\n",
|
|||
|
|
" <td>125.20</td>\n",
|
|||
|
|
" <td>40.0</td>\n",
|
|||
|
|
" <td>never smoked</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5107</th>\n",
|
|||
|
|
" <td>19723</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>35.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Self-employed</td>\n",
|
|||
|
|
" <td>Rural</td>\n",
|
|||
|
|
" <td>82.99</td>\n",
|
|||
|
|
" <td>30.6</td>\n",
|
|||
|
|
" <td>never smoked</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5108</th>\n",
|
|||
|
|
" <td>37544</td>\n",
|
|||
|
|
" <td>Male</td>\n",
|
|||
|
|
" <td>51.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Private</td>\n",
|
|||
|
|
" <td>Rural</td>\n",
|
|||
|
|
" <td>166.29</td>\n",
|
|||
|
|
" <td>25.6</td>\n",
|
|||
|
|
" <td>formerly smoked</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5109</th>\n",
|
|||
|
|
" <td>44679</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>44.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Govt_job</td>\n",
|
|||
|
|
" <td>Urban</td>\n",
|
|||
|
|
" <td>85.28</td>\n",
|
|||
|
|
" <td>26.2</td>\n",
|
|||
|
|
" <td>Unknown</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </tbody>\n",
|
|||
|
|
"</table>\n",
|
|||
|
|
"</div>"
|
|||
|
|
],
|
|||
|
|
"text/plain": [
|
|||
|
|
" id gender age hypertension heart_disease ever_married \\\n",
|
|||
|
|
"5105 18234 Female 80.0 1 0 Yes \n",
|
|||
|
|
"5106 44873 Female 81.0 0 0 Yes \n",
|
|||
|
|
"5107 19723 Female 35.0 0 0 Yes \n",
|
|||
|
|
"5108 37544 Male 51.0 0 0 Yes \n",
|
|||
|
|
"5109 44679 Female 44.0 0 0 Yes \n",
|
|||
|
|
"\n",
|
|||
|
|
" work_type Residence_type avg_glucose_level bmi smoking_status \\\n",
|
|||
|
|
"5105 Private Urban 83.75 27.7 never smoked \n",
|
|||
|
|
"5106 Self-employed Urban 125.20 40.0 never smoked \n",
|
|||
|
|
"5107 Self-employed Rural 82.99 30.6 never smoked \n",
|
|||
|
|
"5108 Private Rural 166.29 25.6 formerly smoked \n",
|
|||
|
|
"5109 Govt_job Urban 85.28 26.2 Unknown \n",
|
|||
|
|
"\n",
|
|||
|
|
" stroke \n",
|
|||
|
|
"5105 0 \n",
|
|||
|
|
"5106 0 \n",
|
|||
|
|
"5107 0 \n",
|
|||
|
|
"5108 0 \n",
|
|||
|
|
"5109 0 "
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 7,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"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[\"bmi\"] = df[\"bmi\"].fillna(0)\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Вычисляем медиану для колонки \"bmi\"\n",
|
|||
|
|
"median_bmi = df[\"bmi\"].median()\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Заменяем значения 0 на медиану\n",
|
|||
|
|
"df.loc[df[\"bmi\"] == 0, \"bmi\"] = median_bmi\n",
|
|||
|
|
"\n",
|
|||
|
|
"df.tail()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"Удалим наблюдения с пропусками:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 8,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"(5110, 12)\n",
|
|||
|
|
"id False\n",
|
|||
|
|
"gender False\n",
|
|||
|
|
"age False\n",
|
|||
|
|
"hypertension False\n",
|
|||
|
|
"heart_disease False\n",
|
|||
|
|
"ever_married False\n",
|
|||
|
|
"work_type False\n",
|
|||
|
|
"Residence_type False\n",
|
|||
|
|
"avg_glucose_level False\n",
|
|||
|
|
"bmi False\n",
|
|||
|
|
"smoking_status False\n",
|
|||
|
|
"stroke False\n",
|
|||
|
|
"dtype: bool\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>id</th>\n",
|
|||
|
|
" <th>gender</th>\n",
|
|||
|
|
" <th>age</th>\n",
|
|||
|
|
" <th>hypertension</th>\n",
|
|||
|
|
" <th>heart_disease</th>\n",
|
|||
|
|
" <th>ever_married</th>\n",
|
|||
|
|
" <th>work_type</th>\n",
|
|||
|
|
" <th>Residence_type</th>\n",
|
|||
|
|
" <th>avg_glucose_level</th>\n",
|
|||
|
|
" <th>bmi</th>\n",
|
|||
|
|
" <th>smoking_status</th>\n",
|
|||
|
|
" <th>stroke</th>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </thead>\n",
|
|||
|
|
" <tbody>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5105</th>\n",
|
|||
|
|
" <td>18234</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>80.0</td>\n",
|
|||
|
|
" <td>1</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Private</td>\n",
|
|||
|
|
" <td>Urban</td>\n",
|
|||
|
|
" <td>83.75</td>\n",
|
|||
|
|
" <td>27.7</td>\n",
|
|||
|
|
" <td>never smoked</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5106</th>\n",
|
|||
|
|
" <td>44873</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>81.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Self-employed</td>\n",
|
|||
|
|
" <td>Urban</td>\n",
|
|||
|
|
" <td>125.20</td>\n",
|
|||
|
|
" <td>40.0</td>\n",
|
|||
|
|
" <td>never smoked</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5107</th>\n",
|
|||
|
|
" <td>19723</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>35.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Self-employed</td>\n",
|
|||
|
|
" <td>Rural</td>\n",
|
|||
|
|
" <td>82.99</td>\n",
|
|||
|
|
" <td>30.6</td>\n",
|
|||
|
|
" <td>never smoked</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5108</th>\n",
|
|||
|
|
" <td>37544</td>\n",
|
|||
|
|
" <td>Male</td>\n",
|
|||
|
|
" <td>51.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Private</td>\n",
|
|||
|
|
" <td>Rural</td>\n",
|
|||
|
|
" <td>166.29</td>\n",
|
|||
|
|
" <td>25.6</td>\n",
|
|||
|
|
" <td>formerly smoked</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>5109</th>\n",
|
|||
|
|
" <td>44679</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>44.0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Govt_job</td>\n",
|
|||
|
|
" <td>Urban</td>\n",
|
|||
|
|
" <td>85.28</td>\n",
|
|||
|
|
" <td>26.2</td>\n",
|
|||
|
|
" <td>Unknown</td>\n",
|
|||
|
|
" <td>0</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </tbody>\n",
|
|||
|
|
"</table>\n",
|
|||
|
|
"</div>"
|
|||
|
|
],
|
|||
|
|
"text/plain": [
|
|||
|
|
" id gender age hypertension heart_disease ever_married \\\n",
|
|||
|
|
"5105 18234 Female 80.0 1 0 Yes \n",
|
|||
|
|
"5106 44873 Female 81.0 0 0 Yes \n",
|
|||
|
|
"5107 19723 Female 35.0 0 0 Yes \n",
|
|||
|
|
"5108 37544 Male 51.0 0 0 Yes \n",
|
|||
|
|
"5109 44679 Female 44.0 0 0 Yes \n",
|
|||
|
|
"\n",
|
|||
|
|
" work_type Residence_type avg_glucose_level bmi smoking_status \\\n",
|
|||
|
|
"5105 Private Urban 83.75 27.7 never smoked \n",
|
|||
|
|
"5106 Self-employed Urban 125.20 40.0 never smoked \n",
|
|||
|
|
"5107 Self-employed Rural 82.99 30.6 never smoked \n",
|
|||
|
|
"5108 Private Rural 166.29 25.6 formerly smoked \n",
|
|||
|
|
"5109 Govt_job Urban 85.28 26.2 Unknown \n",
|
|||
|
|
"\n",
|
|||
|
|
" stroke \n",
|
|||
|
|
"5105 0 \n",
|
|||
|
|
"5106 0 \n",
|
|||
|
|
"5107 0 \n",
|
|||
|
|
"5108 0 \n",
|
|||
|
|
"5109 0 "
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 8,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"dropna_df = df.dropna()\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(dropna_df.shape)\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(fillna_df.isnull().any())\n",
|
|||
|
|
"df.tail()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"##### Проверим выбросы и усредним их:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 36,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Колонка age:\n",
|
|||
|
|
" Есть выбросы: Нет\n",
|
|||
|
|
" Количество выбросов: 0\n",
|
|||
|
|
" Минимальное значение: 0.08\n",
|
|||
|
|
" Максимальное значение: 82.0\n",
|
|||
|
|
" 1-й квартиль (Q1): 25.0\n",
|
|||
|
|
" 3-й квартиль (Q3): 61.0\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка avg_glucose_level:\n",
|
|||
|
|
" Есть выбросы: Нет\n",
|
|||
|
|
" Количество выбросов: 0\n",
|
|||
|
|
" Минимальное значение: 55.12\n",
|
|||
|
|
" Максимальное значение: 169.35750000000002\n",
|
|||
|
|
" 1-й квартиль (Q1): 77.245\n",
|
|||
|
|
" 3-й квартиль (Q3): 114.09\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка bmi:\n",
|
|||
|
|
" Есть выбросы: Нет\n",
|
|||
|
|
" Количество выбросов: 0\n",
|
|||
|
|
" Минимальное значение: 10.3\n",
|
|||
|
|
" Максимальное значение: 47.5\n",
|
|||
|
|
" 1-й квартиль (Q1): 23.5\n",
|
|||
|
|
" 3-й квартиль (Q3): 33.1\n",
|
|||
|
|
"\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"numeric_columns = ['age', 'avg_glucose_level', 'bmi']\n",
|
|||
|
|
"for column in numeric_columns:\n",
|
|||
|
|
" if pd.api.types.is_numeric_dtype(df[column]): # Проверяем, является ли колонка числовой\n",
|
|||
|
|
" q1 = df[column].quantile(0.25) # Находим 1-й квартиль (Q1)\n",
|
|||
|
|
" q3 = df[column].quantile(0.75) # Находим 3-й квартиль (Q3)\n",
|
|||
|
|
" iqr = q3 - q1 # Вычисляем межквартильный размах (IQR)\n",
|
|||
|
|
"\n",
|
|||
|
|
" # Определяем границы для выбросов\n",
|
|||
|
|
" lower_bound = q1 - 1.5 * iqr # Нижняя граница\n",
|
|||
|
|
" upper_bound = q3 + 1.5 * iqr # Верхняя граница\n",
|
|||
|
|
"\n",
|
|||
|
|
" # Подсчитываем количество выбросов\n",
|
|||
|
|
" outliers = df[(df[column] < lower_bound) | (df[column] > upper_bound)]\n",
|
|||
|
|
" outlier_count = outliers.shape[0]\n",
|
|||
|
|
"\n",
|
|||
|
|
" print(f\"Колонка {column}:\")\n",
|
|||
|
|
" print(f\" Есть выбросы: {'Да' if outlier_count > 0 else 'Нет'}\")\n",
|
|||
|
|
" print(f\" Количество выбросов: {outlier_count}\")\n",
|
|||
|
|
" print(f\" Минимальное значение: {df[column].min()}\")\n",
|
|||
|
|
" print(f\" Максимальное значение: {df[column].max()}\")\n",
|
|||
|
|
" print(f\" 1-й квартиль (Q1): {q1}\")\n",
|
|||
|
|
" print(f\" 3-й квартиль (Q3): {q3}\\n\")\n",
|
|||
|
|
"\n",
|
|||
|
|
" # Устраняем выбросы: заменяем значения ниже нижней границы на саму нижнюю границу, а выше верхней — на верхнюю\n",
|
|||
|
|
" df[column] = df[column].apply(lambda x: lower_bound if x < lower_bound else upper_bound if x > upper_bound else x)\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Постараемся выявить зависимости Stroke от остальных колонок:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Разобьем наш набор на выборки относительно параметра Stroke:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 39,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"import matplotlib.pyplot as plt\n",
|
|||
|
|
"# Список колонок для построения графиков\n",
|
|||
|
|
"columns = ['gender', 'age', 'hypertension', 'heart_disease', 'ever_married',\n",
|
|||
|
|
" 'work_type', 'Residence_type', 'avg_glucose_level', 'bmi',\n",
|
|||
|
|
" 'smoking_status']\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Создание диаграмм зависимости\n",
|
|||
|
|
"for column in columns:\n",
|
|||
|
|
" plt.figure(figsize=(8, 6)) # Установка размера графика\n",
|
|||
|
|
" if pd.api.types.is_numeric_dtype(df[column]): # Проверяем, является ли колонка числовой\n",
|
|||
|
|
" # Проверяем, содержит ли колонка только два уникальных значения (0 и 1)\n",
|
|||
|
|
" if df[column].nunique() == 2 and set(df[column].unique()).issubset({0, 1}):\n",
|
|||
|
|
" # Если да, то строим столбчатую диаграмму\n",
|
|||
|
|
" counts = df[column].value_counts() # Считаем количество повторений каждого значения\n",
|
|||
|
|
" counts.plot(kind='bar') # Создаем столбчатую диаграмму\n",
|
|||
|
|
" plt.title(f'Количество значений для {column}')\n",
|
|||
|
|
" plt.xlabel(column)\n",
|
|||
|
|
" plt.ylabel('Количество повторений')\n",
|
|||
|
|
" else:\n",
|
|||
|
|
" # Если колонка числовая, создаем диаграмму рассеяния\n",
|
|||
|
|
" plt.scatter(df['stroke'], df[column], alpha=0.5) # Создаем диаграмму рассеяния\n",
|
|||
|
|
" plt.title(f'Зависимость {column} от stroke')\n",
|
|||
|
|
" plt.xlabel('stroke (0 = нет, 1 = да)')\n",
|
|||
|
|
" plt.ylabel(column)\n",
|
|||
|
|
" plt.xticks([0, 1]) # Установка меток по оси X\n",
|
|||
|
|
" plt.grid() # Добавление сетки для удобства восприятия\n",
|
|||
|
|
" else:\n",
|
|||
|
|
" # Если колонка не числовая, строим столбчатую диаграмму\n",
|
|||
|
|
" counts = df[column].value_counts() # Считаем количество повторений каждого значения\n",
|
|||
|
|
" counts.plot(kind='bar') # Создаем столбчатую диаграмму\n",
|
|||
|
|
" plt.title(f'Количество значений для {column}')\n",
|
|||
|
|
" plt.xlabel(column)\n",
|
|||
|
|
" plt.ylabel('Количество повторений')\n",
|
|||
|
|
"\n",
|
|||
|
|
" plt.show() # Отображение графика"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 15,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"# Функция для создания выборок\n",
|
|||
|
|
"from sklearn.model_selection import train_test_split\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",
|
|||
|
|
" 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": 17,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"stroke\n",
|
|||
|
|
"0 4861\n",
|
|||
|
|
"1 249\n",
|
|||
|
|
"Name: count, dtype: int64\n",
|
|||
|
|
"\n",
|
|||
|
|
"Обучающая выборка: (3066, 12)\n",
|
|||
|
|
"stroke\n",
|
|||
|
|
"0 2917\n",
|
|||
|
|
"1 149\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Контрольная выборка: (1022, 12)\n",
|
|||
|
|
"stroke\n",
|
|||
|
|
"0 972\n",
|
|||
|
|
"1 50\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Тестовая выборка: (1022, 12)\n",
|
|||
|
|
"stroke\n",
|
|||
|
|
"0 972\n",
|
|||
|
|
"1 50\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"# Вывод распределения количества наблюдений по меткам (классам)\n",
|
|||
|
|
"print(df.stroke.value_counts())\n",
|
|||
|
|
"print()\n",
|
|||
|
|
"\n",
|
|||
|
|
"data = df.copy()\n",
|
|||
|
|
"\n",
|
|||
|
|
"df_train, df_val, df_test = split_stratified_into_train_val_test(\n",
|
|||
|
|
" data, stratify_colname=\"stroke\", frac_train=0.60, frac_val=0.20, frac_test=0.20\n",
|
|||
|
|
")\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(\"Обучающая выборка: \", df_train.shape)\n",
|
|||
|
|
"print(df_train.stroke.value_counts())\n",
|
|||
|
|
"counts = df_train['stroke'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))# Установка размера графика\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)# Построение круговой диаграммы\n",
|
|||
|
|
"plt.title('Распределение классов stroke в обучающей выборке')# Добавление заголовка\n",
|
|||
|
|
"plt.show()# Отображение графика\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(\"Контрольная выборка: \", df_val.shape)\n",
|
|||
|
|
"print(df_val.stroke.value_counts())\n",
|
|||
|
|
"counts = df_val['stroke'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов stroke в контрольной выборке')\n",
|
|||
|
|
"plt.show()\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(\"Тестовая выборка: \", df_test.shape)\n",
|
|||
|
|
"print(df_test.stroke.value_counts())\n",
|
|||
|
|
"counts = df_test['stroke'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов stroke в тестовой выборке')\n",
|
|||
|
|
"plt.show()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Сбалансируем распределение:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"1. Балансировка данных оверсемплингом. Это метод, увеличивающий число наблюдений в меньшинственном классе для достижения более равномерного распределения классов."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 23,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Обучающая выборка после oversampling: (5808, 18)\n",
|
|||
|
|
"stroke\n",
|
|||
|
|
"0 2917\n",
|
|||
|
|
"1 2891\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 600x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"from imblearn.over_sampling import ADASYN\n",
|
|||
|
|
"from sklearn.compose import ColumnTransformer\n",
|
|||
|
|
"from sklearn.preprocessing import OneHotEncoder\n",
|
|||
|
|
"\n",
|
|||
|
|
"categorical_features = ['gender', 'ever_married', 'work_type', 'Residence_type'] # Ваши категориальные признаки\n",
|
|||
|
|
"numeric_features = ['age', 'hypertension', 'heart_disease', 'avg_glucose_level', 'bmi'] # Ваши числовые признаки\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Создание пайплайна для обработки категориальных данных\n",
|
|||
|
|
"preprocessor = ColumnTransformer(\n",
|
|||
|
|
" transformers=[\n",
|
|||
|
|
" ('cat', OneHotEncoder(), categorical_features), # OneHotEncoder для категориальных данных\n",
|
|||
|
|
" ('num', 'passthrough', numeric_features) # Оставляем числовые колонки без изменений\n",
|
|||
|
|
" ]\n",
|
|||
|
|
")\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Создание экземпляра ADASYN\n",
|
|||
|
|
"ada = ADASYN()\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Преобразование данных с помощью пайплайна\n",
|
|||
|
|
"X = preprocessor.fit_transform(df_train.drop(columns=['stroke']))\n",
|
|||
|
|
"y = df_train['stroke']\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Применение ADASYN\n",
|
|||
|
|
"X_resampled, y_resampled = ada.fit_resample(X, y)\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Создание нового DataFrame\n",
|
|||
|
|
"df_train_adasyn = pd.DataFrame(X_resampled)\n",
|
|||
|
|
"# Восстанавливаем названия столбцов для DataFrame\n",
|
|||
|
|
"ohe_columns = preprocessor.named_transformers_['cat'].get_feature_names_out(categorical_features)\n",
|
|||
|
|
"new_column_names = list(ohe_columns) + numeric_features\n",
|
|||
|
|
"df_train_adasyn.columns = new_column_names\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Добавление целевой переменной\n",
|
|||
|
|
"df_train_adasyn['stroke'] = y_resampled\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Вывод информации о новой выборке\n",
|
|||
|
|
"print(\"Обучающая выборка после oversampling: \", df_train_adasyn.shape)\n",
|
|||
|
|
"print(df_train_adasyn['stroke'].value_counts())\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Визуализация\n",
|
|||
|
|
"counts = df_train_adasyn['stroke'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(6, 6))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов Stroke в тренировочной выборке после ADASYN')\n",
|
|||
|
|
"plt.show()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"2. Балансировка данных андерсемплингом. Этот метод помогает сбалансировать выборку, уменьшая количество экземпляров класса большинства, чтобы привести его в соответствие с классом меньшинства."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 24,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Обучающая выборка после undersampling: (298, 12)\n",
|
|||
|
|
"stroke\n",
|
|||
|
|
"0 149\n",
|
|||
|
|
"1 149\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"from imblearn.under_sampling import RandomUnderSampler\n",
|
|||
|
|
"\n",
|
|||
|
|
"rus = RandomUnderSampler()# Создание экземпляра RandomUnderSampler\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Применение RandomUnderSampler\n",
|
|||
|
|
"X_resampled, y_resampled = rus.fit_resample(df_train.drop(columns=['stroke']), df_train['stroke'])\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Создание нового DataFrame\n",
|
|||
|
|
"df_train_undersampled = pd.DataFrame(X_resampled)\n",
|
|||
|
|
"df_train_undersampled['stroke'] = y_resampled # Добавление целевой переменной\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Вывод информации о новой выборке\n",
|
|||
|
|
"print(\"Обучающая выборка после undersampling: \", df_train_undersampled.shape)\n",
|
|||
|
|
"print(df_train_undersampled['stroke'].value_counts())\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Визуализация распределения классов\n",
|
|||
|
|
"counts = df_train_undersampled['stroke'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов stroke в тренировочной выборке после Undersampling')\n",
|
|||
|
|
"plt.show()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### 3. Датасет: Набор данных для анализа и прогнозирования сердечного приступа\n",
|
|||
|
|
"https://www.kaggle.com/datasets/kamilpytlak/personal-key-indicators-of-heart-disease\n",
|
|||
|
|
"##### О наборе данных: \n",
|
|||
|
|
"По данным CDC, болезни сердца являются основной причиной смерти представителей большинства рас в США (афроамериканцев, американских индейцев и коренных жителей Аляски, а также белых). Около половины всех американцев (47%) имеют по крайней мере 1 из 3 основных факторов риска сердечно-сосудистых заболеваний: высокое кровяное давление, высокий уровень холестерина и курение. Другие ключевые показатели включают сахарный диабет, ожирение (высокий ИМТ), недостаточную физическую активность или чрезмерное употребление алкоголя. Выявление и профилактика факторов, оказывающих наибольшее влияние на сердечно-сосудистые заболевания, очень важны в здравоохранении. В свою очередь, достижения в области вычислительной техники позволяют применять методы машинного обучения для выявления \"закономерностей\" в данных, которые позволяют предсказать состояние пациента.\n",
|
|||
|
|
"\n",
|
|||
|
|
"##### Таким образом:\n",
|
|||
|
|
"* Объект наблюдения - представители большинства рас в США\n",
|
|||
|
|
"* Атрибуты: HeartDisease, BMI, Smoking, AlcoholDrinking, Stroke, PhysicalHealth(как много дней за месяц вы чувствовали себя плохо), MentalHealth(как много дней за месяц вы чувствовали себя ментально плохо), DiffWalking, Sex, AgeCategory, Race, Diabetic, PhysicalActivity, GenHealth, SleepTime, Asthma, KidneyDisease, SkinCancer.\n",
|
|||
|
|
"* Проблемная область: прогнозирование сердечного приступа у человека."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 48,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Количество колонок: 18\n",
|
|||
|
|
"Колонки: HeartDisease, BMI, Smoking, AlcoholDrinking, Stroke, PhysicalHealth, MentalHealth, DiffWalking, Sex, AgeCategory, Race, Diabetic, PhysicalActivity, GenHealth, SleepTime, Asthma, KidneyDisease, SkinCancer\n",
|
|||
|
|
"\n",
|
|||
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
|||
|
|
"RangeIndex: 319795 entries, 0 to 319794\n",
|
|||
|
|
"Data columns (total 18 columns):\n",
|
|||
|
|
" # Column Non-Null Count Dtype \n",
|
|||
|
|
"--- ------ -------------- ----- \n",
|
|||
|
|
" 0 HeartDisease 319795 non-null object \n",
|
|||
|
|
" 1 BMI 319795 non-null float64\n",
|
|||
|
|
" 2 Smoking 319795 non-null object \n",
|
|||
|
|
" 3 AlcoholDrinking 319795 non-null object \n",
|
|||
|
|
" 4 Stroke 319795 non-null object \n",
|
|||
|
|
" 5 PhysicalHealth 319795 non-null float64\n",
|
|||
|
|
" 6 MentalHealth 319795 non-null float64\n",
|
|||
|
|
" 7 DiffWalking 319795 non-null object \n",
|
|||
|
|
" 8 Sex 319795 non-null object \n",
|
|||
|
|
" 9 AgeCategory 319795 non-null object \n",
|
|||
|
|
" 10 Race 319795 non-null object \n",
|
|||
|
|
" 11 Diabetic 319795 non-null object \n",
|
|||
|
|
" 12 PhysicalActivity 319795 non-null object \n",
|
|||
|
|
" 13 GenHealth 319795 non-null object \n",
|
|||
|
|
" 14 SleepTime 319795 non-null float64\n",
|
|||
|
|
" 15 Asthma 319795 non-null object \n",
|
|||
|
|
" 16 KidneyDisease 319795 non-null object \n",
|
|||
|
|
" 17 SkinCancer 319795 non-null object \n",
|
|||
|
|
"dtypes: float64(4), object(14)\n",
|
|||
|
|
"memory usage: 43.9+ MB\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>HeartDisease</th>\n",
|
|||
|
|
" <th>BMI</th>\n",
|
|||
|
|
" <th>Smoking</th>\n",
|
|||
|
|
" <th>AlcoholDrinking</th>\n",
|
|||
|
|
" <th>Stroke</th>\n",
|
|||
|
|
" <th>PhysicalHealth</th>\n",
|
|||
|
|
" <th>MentalHealth</th>\n",
|
|||
|
|
" <th>DiffWalking</th>\n",
|
|||
|
|
" <th>Sex</th>\n",
|
|||
|
|
" <th>AgeCategory</th>\n",
|
|||
|
|
" <th>Race</th>\n",
|
|||
|
|
" <th>Diabetic</th>\n",
|
|||
|
|
" <th>PhysicalActivity</th>\n",
|
|||
|
|
" <th>GenHealth</th>\n",
|
|||
|
|
" <th>SleepTime</th>\n",
|
|||
|
|
" <th>Asthma</th>\n",
|
|||
|
|
" <th>KidneyDisease</th>\n",
|
|||
|
|
" <th>SkinCancer</th>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </thead>\n",
|
|||
|
|
" <tbody>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>0</th>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>16.60</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>3.0</td>\n",
|
|||
|
|
" <td>30.0</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>55-59</td>\n",
|
|||
|
|
" <td>White</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Very good</td>\n",
|
|||
|
|
" <td>5.0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>1</th>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>20.34</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>0.0</td>\n",
|
|||
|
|
" <td>0.0</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>80 or older</td>\n",
|
|||
|
|
" <td>White</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Very good</td>\n",
|
|||
|
|
" <td>7.0</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>2</th>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>26.58</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>20.0</td>\n",
|
|||
|
|
" <td>30.0</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>Male</td>\n",
|
|||
|
|
" <td>65-69</td>\n",
|
|||
|
|
" <td>White</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Fair</td>\n",
|
|||
|
|
" <td>8.0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>3</th>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>24.21</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>0.0</td>\n",
|
|||
|
|
" <td>0.0</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>75-79</td>\n",
|
|||
|
|
" <td>White</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>Good</td>\n",
|
|||
|
|
" <td>6.0</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" <tr>\n",
|
|||
|
|
" <th>4</th>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>23.71</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>28.0</td>\n",
|
|||
|
|
" <td>0.0</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Female</td>\n",
|
|||
|
|
" <td>40-44</td>\n",
|
|||
|
|
" <td>White</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>Yes</td>\n",
|
|||
|
|
" <td>Very good</td>\n",
|
|||
|
|
" <td>8.0</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" <td>No</td>\n",
|
|||
|
|
" </tr>\n",
|
|||
|
|
" </tbody>\n",
|
|||
|
|
"</table>\n",
|
|||
|
|
"</div>"
|
|||
|
|
],
|
|||
|
|
"text/plain": [
|
|||
|
|
" HeartDisease BMI Smoking AlcoholDrinking Stroke PhysicalHealth \\\n",
|
|||
|
|
"0 No 16.60 Yes No No 3.0 \n",
|
|||
|
|
"1 No 20.34 No No Yes 0.0 \n",
|
|||
|
|
"2 No 26.58 Yes No No 20.0 \n",
|
|||
|
|
"3 No 24.21 No No No 0.0 \n",
|
|||
|
|
"4 No 23.71 No No No 28.0 \n",
|
|||
|
|
"\n",
|
|||
|
|
" MentalHealth DiffWalking Sex AgeCategory Race Diabetic \\\n",
|
|||
|
|
"0 30.0 No Female 55-59 White Yes \n",
|
|||
|
|
"1 0.0 No Female 80 or older White No \n",
|
|||
|
|
"2 30.0 No Male 65-69 White Yes \n",
|
|||
|
|
"3 0.0 No Female 75-79 White No \n",
|
|||
|
|
"4 0.0 Yes Female 40-44 White No \n",
|
|||
|
|
"\n",
|
|||
|
|
" PhysicalActivity GenHealth SleepTime Asthma KidneyDisease SkinCancer \n",
|
|||
|
|
"0 Yes Very good 5.0 Yes No Yes \n",
|
|||
|
|
"1 Yes Very good 7.0 No No No \n",
|
|||
|
|
"2 Yes Fair 8.0 Yes No No \n",
|
|||
|
|
"3 No Good 6.0 No No Yes \n",
|
|||
|
|
"4 Yes Very good 8.0 No No No "
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 48,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"import pandas as pd\n",
|
|||
|
|
"df = pd.read_csv(\".//static//csv//heart.csv\", sep=\",\")\n",
|
|||
|
|
"print('Количество колонок: ' + str(df.columns.size)) \n",
|
|||
|
|
"print('Колонки: ' + ', '.join(df.columns)+'\\n')\n",
|
|||
|
|
"\n",
|
|||
|
|
"df.info()\n",
|
|||
|
|
"df.head()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Получение сведений о пропущенных данных\n",
|
|||
|
|
"Типы пропущенных данных:\n",
|
|||
|
|
"\n",
|
|||
|
|
"- None - представление пустых данных в Python\n",
|
|||
|
|
"- NaN - представление пустых данных в Pandas\n",
|
|||
|
|
"- '' - пустая строка"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 28,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"HeartDisease 0\n",
|
|||
|
|
"BMI 0\n",
|
|||
|
|
"Smoking 0\n",
|
|||
|
|
"AlcoholDrinking 0\n",
|
|||
|
|
"Stroke 0\n",
|
|||
|
|
"PhysicalHealth 0\n",
|
|||
|
|
"MentalHealth 0\n",
|
|||
|
|
"DiffWalking 0\n",
|
|||
|
|
"Sex 0\n",
|
|||
|
|
"AgeCategory 0\n",
|
|||
|
|
"Race 0\n",
|
|||
|
|
"Diabetic 0\n",
|
|||
|
|
"PhysicalActivity 0\n",
|
|||
|
|
"GenHealth 0\n",
|
|||
|
|
"SleepTime 0\n",
|
|||
|
|
"Asthma 0\n",
|
|||
|
|
"KidneyDisease 0\n",
|
|||
|
|
"SkinCancer 0\n",
|
|||
|
|
"dtype: int64\n",
|
|||
|
|
"\n",
|
|||
|
|
"HeartDisease False\n",
|
|||
|
|
"BMI False\n",
|
|||
|
|
"Smoking False\n",
|
|||
|
|
"AlcoholDrinking False\n",
|
|||
|
|
"Stroke False\n",
|
|||
|
|
"PhysicalHealth False\n",
|
|||
|
|
"MentalHealth False\n",
|
|||
|
|
"DiffWalking False\n",
|
|||
|
|
"Sex False\n",
|
|||
|
|
"AgeCategory False\n",
|
|||
|
|
"Race False\n",
|
|||
|
|
"Diabetic False\n",
|
|||
|
|
"PhysicalActivity False\n",
|
|||
|
|
"GenHealth False\n",
|
|||
|
|
"SleepTime False\n",
|
|||
|
|
"Asthma False\n",
|
|||
|
|
"KidneyDisease False\n",
|
|||
|
|
"SkinCancer False\n",
|
|||
|
|
"dtype: bool\n",
|
|||
|
|
"\n",
|
|||
|
|
"HeartDisease процент пустых значений: %0.00\n",
|
|||
|
|
"BMI процент пустых значений: %0.00\n",
|
|||
|
|
"Smoking процент пустых значений: %0.00\n",
|
|||
|
|
"AlcoholDrinking процент пустых значений: %0.00\n",
|
|||
|
|
"Stroke процент пустых значений: %0.00\n",
|
|||
|
|
"PhysicalHealth процент пустых значений: %0.00\n",
|
|||
|
|
"MentalHealth процент пустых значений: %0.00\n",
|
|||
|
|
"DiffWalking процент пустых значений: %0.00\n",
|
|||
|
|
"Sex процент пустых значений: %0.00\n",
|
|||
|
|
"AgeCategory процент пустых значений: %0.00\n",
|
|||
|
|
"Race процент пустых значений: %0.00\n",
|
|||
|
|
"Diabetic процент пустых значений: %0.00\n",
|
|||
|
|
"PhysicalActivity процент пустых значений: %0.00\n",
|
|||
|
|
"GenHealth процент пустых значений: %0.00\n",
|
|||
|
|
"SleepTime процент пустых значений: %0.00\n",
|
|||
|
|
"Asthma процент пустых значений: %0.00\n",
|
|||
|
|
"KidneyDisease процент пустых значений: %0.00\n",
|
|||
|
|
"SkinCancer процент пустых значений: %0.00\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"# Количество пустых значений признаков\n",
|
|||
|
|
"print(df.isnull().sum())\n",
|
|||
|
|
"print()\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Есть ли пустые значения признаков\n",
|
|||
|
|
"print(df.isnull().any())\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",
|
|||
|
|
" print(f\"{i} процент пустых значений: %{null_rate:.2f}\")"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"##### Пропущенные данные отсутствуют.\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"##### Проверим выбросы и усредним их:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 49,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Колонка BMI:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 10396\n",
|
|||
|
|
" Минимальное значение: 12.02\n",
|
|||
|
|
" Максимальное значение: 94.85\n",
|
|||
|
|
" 1-й квартиль (Q1): 24.03\n",
|
|||
|
|
" 3-й квартиль (Q3): 31.42\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка PhysicalHealth:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 47146\n",
|
|||
|
|
" Минимальное значение: 0.0\n",
|
|||
|
|
" Максимальное значение: 30.0\n",
|
|||
|
|
" 1-й квартиль (Q1): 0.0\n",
|
|||
|
|
" 3-й квартиль (Q3): 2.0\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка MentalHealth:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 51576\n",
|
|||
|
|
" Минимальное значение: 0.0\n",
|
|||
|
|
" Максимальное значение: 30.0\n",
|
|||
|
|
" 1-й квартиль (Q1): 0.0\n",
|
|||
|
|
" 3-й квартиль (Q3): 3.0\n",
|
|||
|
|
"\n",
|
|||
|
|
"Колонка SleepTime:\n",
|
|||
|
|
" Есть выбросы: Да\n",
|
|||
|
|
" Количество выбросов: 4543\n",
|
|||
|
|
" Минимальное значение: 1.0\n",
|
|||
|
|
" Максимальное значение: 24.0\n",
|
|||
|
|
" 1-й квартиль (Q1): 6.0\n",
|
|||
|
|
" 3-й квартиль (Q3): 8.0\n",
|
|||
|
|
"\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"numeric_columns = ['BMI', 'PhysicalHealth', 'MentalHealth', 'AgeCategory', 'SleepTime']\n",
|
|||
|
|
"for column in numeric_columns:\n",
|
|||
|
|
" if pd.api.types.is_numeric_dtype(df[column]): # Проверяем, является ли колонка числовой\n",
|
|||
|
|
" q1 = df[column].quantile(0.25) # Находим 1-й квартиль (Q1)\n",
|
|||
|
|
" q3 = df[column].quantile(0.75) # Находим 3-й квартиль (Q3)\n",
|
|||
|
|
" iqr = q3 - q1 # Вычисляем межквартильный размах (IQR)\n",
|
|||
|
|
"\n",
|
|||
|
|
" # Определяем границы для выбросов\n",
|
|||
|
|
" lower_bound = q1 - 1.5 * iqr # Нижняя граница\n",
|
|||
|
|
" upper_bound = q3 + 1.5 * iqr # Верхняя граница\n",
|
|||
|
|
"\n",
|
|||
|
|
" # Подсчитываем количество выбросов\n",
|
|||
|
|
" outliers = df[(df[column] < lower_bound) | (df[column] > upper_bound)]\n",
|
|||
|
|
" outlier_count = outliers.shape[0]\n",
|
|||
|
|
"\n",
|
|||
|
|
" print(f\"Колонка {column}:\")\n",
|
|||
|
|
" print(f\" Есть выбросы: {'Да' if outlier_count > 0 else 'Нет'}\")\n",
|
|||
|
|
" print(f\" Количество выбросов: {outlier_count}\")\n",
|
|||
|
|
" print(f\" Минимальное значение: {df[column].min()}\")\n",
|
|||
|
|
" print(f\" Максимальное значение: {df[column].max()}\")\n",
|
|||
|
|
" print(f\" 1-й квартиль (Q1): {q1}\")\n",
|
|||
|
|
" print(f\" 3-й квартиль (Q3): {q3}\\n\")\n",
|
|||
|
|
"\n",
|
|||
|
|
" # Устраняем выбросы: заменяем значения ниже нижней границы на саму нижнюю границу, а выше верхней — на верхнюю\n",
|
|||
|
|
" df[column] = df[column].apply(lambda x: lower_bound if x < lower_bound else upper_bound if x > upper_bound else x)\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Постараемся выявить зависимости HeartDisease от остальных колонок:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Разобьем наш набор на выборки относительно параметра HeartDisease:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 52,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAtQAAAIxCAYAAABtpC/BAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAABTjUlEQVR4nO3deXyM5/7/8fdEEgmxxBZLtfaISqzZWmu06qBO0VKKnh5aVaWoWmorpVQJSlVTlNjbRrXVHvotPbaSiKW0Yhe1JtYE2WV+f/hljmlCM7kTk8jr+XjkwdzXdV/zmZkw77nmuu/bZDabzQIAAACQIw72LgAAAAAoyAjUAAAAgAEEagAAAMAAAjUAAABgAIEaAAAAMIBADQAAABhAoAYAAAAMIFADAAAABhCoAQAAAAMI1ACy1Lt3b/Xu3dtqW2RkpDp16qR69erpq6++slNleFiFhoaqf//+unTpkg4fPqymTZvq6tWr9i7rb/Xu3Vuenp6Wn7p166pRo0bq0qWLQkNDlZaWZtU/KChIo0aNstzetWuXnnnmGdWvX1/9+vXTzZs39frrr6tBgwby9fWVv7+/Bg0alOl+Fy1aJE9PT/Xr1y9T2+LFi+Xp6akLFy5k6zHcXdPZs2fl6emptWvX3vcx//X/B6Awc7R3AQAKhitXruj111/X448/bnkjB3JTly5d9M0336hZs2YymUwaMGCAypQpY++ysqVevXqaMGGCJOn27duKi4vT1q1bNXXqVEVGRmr27NlycLgzhzVv3jy5ublZ9p0+fbrS09MVEhKismXLat26dfrll180fvx41a5dW6tXr1ZERESm+9y2bZtKly6t3bt3Kzk5WUWLFrW07d69WzVq1FClSpXy5PFmPFYAdxCoAWTLF198oaSkJE2fPl0eHh72LgcPITc3N4WFhen06dNyc3NT+fLl7V1Strm5ualhw4ZW24KCglSjRg1NmTJF69evV6dOnSTdCd93u379unx9ffXEE09Ikv7v//5PktSzZ0+ZTCadPn1aP/zwg86cOaOqVatKkhITE7Vnzx4NGjRIM2fOVEREhJo3by5JMpvN2rt3r5599tk8e7y1atXKs7GBgoglHwD+1rVr17Ry5Uo9++yzmcJ0dHS0Bg8erCeffFINGzZU7969tWfPHqs+QUFBVl+JZ/wEBQVZ9bn7a3BJGjZsmDw9PRUeHn7Pr6FHjRplNY4kffXVV+rQoYPq16+vVq1aae7cubp9+7ZVny1btujFF19Uw4YN1axZM40fP17x8fEKDw/PslZPT0/LV9x3P566devK19dXgwYN0rVr1yzj37hxQ1OnTtVTTz0lb29vdezYUV9//fXfPtc//vij2rdvr4YNG6pLly6KjIy0tM2dOzfLbwY8PT01d+5cy+3Dhw/rzTffVEBAgB5//HE1b95ckydPVlJSUpb97zX2zz//rC5dusjb21tPPvmkJk+erISEBJvqyXg+w8PDLe1XrlxR06ZNs3z9HRwcVL16dZUvX97q9b+fF198McvX6+79Mmq9X7/4+Hi9++67atas2X3HskWvXr3k4eGh1atXZ3qsGb/T586d07p16yy/YxnPXd26dTVq1CgFBgZKktW/q/DwcKWmpur5559X1apVtX37dkvbsWPHdP36dUtAv3r1qiZOnKjWrVurfv368vPz08CBA3X27NlsPQaz2azRo0fLx8fHcj9/XfLh6empFStWaMyYMfLz81OjRo301ltv6fLly1ZjLVq0SG3atJGPj49efPFFbd682dDzC+QXzFADuCez2awLFy5o8uTJSktLU//+/a3ajx8/rm7duqlatWoaO3asnJycFBoaqpdfflmLFy+Wn5+fpW/Lli31xhtvWG7Pnz9fx48fv+d9R0ZG6ocffrC55s8++0yzZs1Sr169NHr0aEVFRWnu3Lm6cOGCPvjgA0nSL7/8ogEDBqhNmzaaPXu2rl+/runTp+vcuXOaM2eO1qxZI+lOMP/6668tt+/+mj7j8aSmpurEiROaPn26pkyZohkzZigpKUk9e/bUlStXNHjwYFWpUkU///yzxowZo8uXL+v111/PsvYDBw5o+PDheu655zRu3DgtX75cr7/+ujZs2KBy5cpl6/HHxsbqpZdeUsOGDTVt2jQ5Oztr69at+uKLL1ShQgW99tpr2Rrn+++/1/Dhw/Xss89qyJAhOnfunGbNmqXjx4/riy++kMlkytY4WZk5c6Zu3LihkiVL3rOPLa9/cnKyBg0apGbNmkmS/vjjD02aNCnLvhmvZVb9pk2bpg0bNmjkyJGqWbOmHB0d7ztWdjg4OCgwMFA//PCD0tLS5Oj4v7fdChUqaM2aNXrzzTdVr149vfHGG3JxcdGyZcssv3dlypTRI488oqpVq2rv3r167rnnJEnbt29XvXr1VKZMGTVr1kzbtm3T6NGjJd1Z7uHk5CR/f3+ZzWb1799fcXFxGj58uMqVK6cjR45o9uzZmjBhghYtWvS3j2Hy5Mlav369PvnkE8tznJVZs2bp6aefVnBwsM6cOaOpU6eqSJEiCg4OlnRnqcsnn3yivn37KiAgQNu2bdOQIUNy/NwC+QmBGsA97d69W61atZKTk5M+//xzVatWzap93rx5cnZ2VmhoqCVstmrVSh07dtT06dOtZmTLlClj9ZX4/dbGpqena/LkyXr88cf1xx9/SJKKFCkiSZlmmu9248YNzZ8/X927d9fYsWMlSc2aNVPp0qU1duxYvfLKK6pdu7bmzp0rLy8vzZs3zxIMnZ2dNWfOHCUlJVnq3LZtmyRl+ir/r4/H19dXv/76q6XWtWvX6ujRo1q9erUaNWokSWrevLnS0tI0f/58vfjiiypdunSmMS9evKhnnnlGkydPloODg8qVK6eOHTtq//79euqpp+75uO929OhReXl5ac6cOZbX5IknntCOHTsUHh6u1157TQ4ODpkOlLub2WzWjBkz1Lx5c82YMcOyvVq1avrXv/6lLVu2qFWrVtmq568OHjyob7/9Vl5eXoqPj8+yT1av//0kJCSodu3altcjOTn5nn3vfi3/2u/AgQNq1qyZunfvfs8+OVGuXDmlpqbq+vXrVh+MnJ2d1bBhQzk7O1v9PlWsWDFTrYGBgdq3b5/l9rZt29SuXTtJd37HV61apfPnz6ty5cqKjIxUgwYNVLx4ccXExMjV1VUjR45U06ZNJUn+/v76888/rT5c3MvMmTO1Zs0azZs3Ty1atLhv3zp16mjq1KmW2wcOHNCGDRsk3XmNPv/8c7300ksaPny4pe7ExMRs1QHkdyz5AHBP9erV07Rp01SqVCmNHj0601fEERERat26tdXMraOjozp06KDff/9dt27dytH9rl69WpcuXdLAgQMt20qXLq0iRYro4sWL99xv3759SkpKUlBQkNLS0iw/GUsLduzYoaSkJB06dEhPPfWU1Sxr+/bttXHjxmzPBJvNZqWlpSklJUUHDhzQnj17VL9+fUl3npcqVapYwnSGTp06KTk5Wb/99luWY7Zt21azZs2SyWRSQkKC/vOf/1iWQNzt7sf212DcrFkzLV++XEWLFtXx48e1adMmffrpp7p69apSUlIkSWXLllVMTMw9H9vJkyd18eLFTM+jr6+v3NzctGPHjmzX89fnbPLkyXr++edVt27de/bL6vW/n5iYmPvOdmeXt7e3IiIitHPnTt24cUNpaWlKT083PK7ZbJYkQ7P6gYGBOnbsmOLj43XmzBlFR0dbZosDAgLk6OioX3/9VdKd2f2M5R4eHh4KDQ1VkyZNdPbsWe3YsUPLli3T3r17Lb8P97JixQqFhISoQ4cO2foA9dcPnhUrVlRiYqIkaf/+/UpKSrJ8CMjQsWPH7Dx8IN9jhhrAPbm5ualz586qUaOGevTooSFDhmjNmjWW2eK4uLgsA2i5cuVkNpt18+ZNFS9e3Kb7vH79uubMmaMRI0ZYBXVXV1f5+/tr9erVat68uWrVqqXDhw/r2LFjVvtKuueyhtjYWMXFxclsNqts2bI21fVX69at07p166zqy1jKERcXl+UBdRnP1b1mZjNs2rTJEiZbtmy
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 800x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"import matplotlib.pyplot as plt\n",
|
|||
|
|
"# Список колонок для построения графиков\n",
|
|||
|
|
"columns = ['BMI', 'Smoking', 'AlcoholDrinking', 'Stroke',\n",
|
|||
|
|
" 'PhysicalHealth', 'MentalHealth', 'DiffWalking', 'Sex',\n",
|
|||
|
|
" 'AgeCategory', 'Race', 'Diabetic', 'PhysicalActivity', 'GenHealth', 'SleepTime', 'Asthma', 'KidneyDisease', 'SkinCancer']\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Создание диаграмм зависимости\n",
|
|||
|
|
"for column in columns:\n",
|
|||
|
|
" plt.figure(figsize=(8, 6)) # Установка размера графика\n",
|
|||
|
|
" if pd.api.types.is_numeric_dtype(df[column]): # Проверяем, является ли колонка числовой\n",
|
|||
|
|
" # Проверяем, содержит ли колонка только два уникальных значения (0 и 1)\n",
|
|||
|
|
" if df[column].nunique() == 2 and set(df[column].unique()).issubset({0, 1}):\n",
|
|||
|
|
" # Если да, то строим столбчатую диаграмму\n",
|
|||
|
|
" counts = df[column].value_counts() # Считаем количество повторений каждого значения\n",
|
|||
|
|
" counts.plot(kind='bar') # Создаем столбчатую диаграмму\n",
|
|||
|
|
" plt.title(f'Количество значений для {column}')\n",
|
|||
|
|
" plt.xlabel(column)\n",
|
|||
|
|
" plt.ylabel('Количество повторений')\n",
|
|||
|
|
" else:\n",
|
|||
|
|
" # Если колонка числовая, создаем диаграмму рассеяния\n",
|
|||
|
|
" plt.scatter(df['HeartDisease'], df[column], alpha=0.5) # Создаем диаграмму рассеяния\n",
|
|||
|
|
" plt.title(f'Зависимость HeartDisease от {column}')\n",
|
|||
|
|
" plt.xlabel('HeartDisease (0 = нет, 1 = да)')\n",
|
|||
|
|
" plt.ylabel(column)\n",
|
|||
|
|
" plt.xticks([0, 1]) # Установка меток по оси X\n",
|
|||
|
|
" plt.grid() # Добавление сетки для удобства восприятия\n",
|
|||
|
|
" else:\n",
|
|||
|
|
" # Если колонка не числовая, строим столбчатую диаграмму\n",
|
|||
|
|
" counts = df[column].value_counts() # Считаем количество повторений каждого значения\n",
|
|||
|
|
" counts.plot(kind='bar') # Создаем столбчатую диаграмму\n",
|
|||
|
|
" plt.title(f'Количество значений для {column}')\n",
|
|||
|
|
" plt.xlabel(column)\n",
|
|||
|
|
" plt.ylabel('Количество повторений')\n",
|
|||
|
|
"\n",
|
|||
|
|
" plt.show() # Отображение графика"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 53,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"# Функция для создания выборок\n",
|
|||
|
|
"from sklearn.model_selection import train_test_split\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",
|
|||
|
|
" 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": 54,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"HeartDisease\n",
|
|||
|
|
"No 292422\n",
|
|||
|
|
"Yes 27373\n",
|
|||
|
|
"Name: count, dtype: int64\n",
|
|||
|
|
"\n",
|
|||
|
|
"Обучающая выборка: (191877, 18)\n",
|
|||
|
|
"HeartDisease\n",
|
|||
|
|
"No 175453\n",
|
|||
|
|
"Yes 16424\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Контрольная выборка: (63959, 18)\n",
|
|||
|
|
"HeartDisease\n",
|
|||
|
|
"No 58484\n",
|
|||
|
|
"Yes 5475\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Тестовая выборка: (63959, 18)\n",
|
|||
|
|
"HeartDisease\n",
|
|||
|
|
"No 58485\n",
|
|||
|
|
"Yes 5474\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"# Вывод распределения количества наблюдений по меткам (классам)\n",
|
|||
|
|
"print(df.HeartDisease.value_counts())\n",
|
|||
|
|
"print()\n",
|
|||
|
|
"\n",
|
|||
|
|
"data = df.copy()\n",
|
|||
|
|
"\n",
|
|||
|
|
"df_train, df_val, df_test = split_stratified_into_train_val_test(\n",
|
|||
|
|
" data, stratify_colname=\"HeartDisease\", frac_train=0.60, frac_val=0.20, frac_test=0.20\n",
|
|||
|
|
")\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(\"Обучающая выборка: \", df_train.shape)\n",
|
|||
|
|
"print(df_train.HeartDisease.value_counts())\n",
|
|||
|
|
"counts = df_train['HeartDisease'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))# Установка размера графика\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)# Построение круговой диаграммы\n",
|
|||
|
|
"plt.title('Распределение классов HeartDisease в обучающей выборке')# Добавление заголовка\n",
|
|||
|
|
"plt.show()# Отображение графика\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(\"Контрольная выборка: \", df_val.shape)\n",
|
|||
|
|
"print(df_val.HeartDisease.value_counts())\n",
|
|||
|
|
"counts = df_val['HeartDisease'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов HeartDisease в контрольной выборке')\n",
|
|||
|
|
"plt.show()\n",
|
|||
|
|
"\n",
|
|||
|
|
"print(\"Тестовая выборка: \", df_test.shape)\n",
|
|||
|
|
"print(df_test.HeartDisease.value_counts())\n",
|
|||
|
|
"counts = df_test['HeartDisease'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов HeartDisease в тестовой выборке')\n",
|
|||
|
|
"plt.show()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"#### Сбалансируем распределение:"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"1. Балансировка данных оверсемплингом. Это метод, увеличивающий число наблюдений в меньшинственном классе для достижения более равномерного распределения классов."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 55,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Обучающая выборка после oversampling: (351482, 51)\n",
|
|||
|
|
"HeartDisease\n",
|
|||
|
|
"Yes 176029\n",
|
|||
|
|
"No 175453\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 600x600 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"from imblearn.over_sampling import ADASYN\n",
|
|||
|
|
"from sklearn.compose import ColumnTransformer\n",
|
|||
|
|
"from sklearn.preprocessing import OneHotEncoder\n",
|
|||
|
|
"\n",
|
|||
|
|
"categorical_features = ['Smoking', 'AlcoholDrinking', 'Stroke', 'DiffWalking', 'Sex', 'AgeCategory', 'Race', 'Diabetic', 'PhysicalActivity', 'GenHealth', 'Asthma', 'KidneyDisease', 'SkinCancer'] # Ваши категориальные признаки\n",
|
|||
|
|
"numeric_features = ['BMI', 'PhysicalHealth', 'MentalHealth', 'SleepTime'] # Ваши числовые признаки\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Создание пайплайна для обработки категориальных данных\n",
|
|||
|
|
"preprocessor = ColumnTransformer(\n",
|
|||
|
|
" transformers=[\n",
|
|||
|
|
" ('cat', OneHotEncoder(), categorical_features), # OneHotEncoder для категориальных данных\n",
|
|||
|
|
" ('num', 'passthrough', numeric_features) # Оставляем числовые колонки без изменений\n",
|
|||
|
|
" ]\n",
|
|||
|
|
")\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Создание экземпляра ADASYN\n",
|
|||
|
|
"ada = ADASYN()\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Преобразование данных с помощью пайплайна\n",
|
|||
|
|
"X = preprocessor.fit_transform(df_train.drop(columns=['HeartDisease']))\n",
|
|||
|
|
"y = df_train['HeartDisease']\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Применение ADASYN\n",
|
|||
|
|
"X_resampled, y_resampled = ada.fit_resample(X, y)\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Создание нового DataFrame\n",
|
|||
|
|
"df_train_adasyn = pd.DataFrame(X_resampled)\n",
|
|||
|
|
"# Восстанавливаем названия столбцов для DataFrame\n",
|
|||
|
|
"ohe_columns = preprocessor.named_transformers_['cat'].get_feature_names_out(categorical_features)\n",
|
|||
|
|
"new_column_names = list(ohe_columns) + numeric_features\n",
|
|||
|
|
"df_train_adasyn.columns = new_column_names\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Добавление целевой переменной\n",
|
|||
|
|
"df_train_adasyn['HeartDisease'] = y_resampled\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Вывод информации о новой выборке\n",
|
|||
|
|
"print(\"Обучающая выборка после oversampling: \", df_train_adasyn.shape)\n",
|
|||
|
|
"print(df_train_adasyn['HeartDisease'].value_counts())\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Визуализация\n",
|
|||
|
|
"counts = df_train_adasyn['HeartDisease'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(6, 6))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов HeartDisease в тренировочной выборке после ADASYN')\n",
|
|||
|
|
"plt.show()"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"2. Балансировка данных андерсемплингом. Этот метод помогает сбалансировать выборку, уменьшая количество экземпляров класса большинства, чтобы привести его в соответствие с классом меньшинства."
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 56,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Обучающая выборка после undersampling: (32848, 18)\n",
|
|||
|
|
"HeartDisease\n",
|
|||
|
|
"No 16424\n",
|
|||
|
|
"Yes 16424\n",
|
|||
|
|
"Name: count, dtype: int64\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"image/png": "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
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 200x200 with 1 Axes>"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "display_data"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"from imblearn.under_sampling import RandomUnderSampler\n",
|
|||
|
|
"\n",
|
|||
|
|
"rus = RandomUnderSampler()# Создание экземпляра RandomUnderSampler\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Применение RandomUnderSampler\n",
|
|||
|
|
"X_resampled, y_resampled = rus.fit_resample(df_train.drop(columns=['HeartDisease']), df_train['HeartDisease'])\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Создание нового DataFrame\n",
|
|||
|
|
"df_train_undersampled = pd.DataFrame(X_resampled)\n",
|
|||
|
|
"df_train_undersampled['HeartDisease'] = y_resampled # Добавление целевой переменной\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Вывод информации о новой выборке\n",
|
|||
|
|
"print(\"Обучающая выборка после undersampling: \", df_train_undersampled.shape)\n",
|
|||
|
|
"print(df_train_undersampled['HeartDisease'].value_counts())\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Визуализация распределения классов\n",
|
|||
|
|
"counts = df_train_undersampled['HeartDisease'].value_counts()\n",
|
|||
|
|
"plt.figure(figsize=(2, 2))\n",
|
|||
|
|
"plt.pie(counts, labels=counts.index, autopct='%1.1f%%', startangle=90)\n",
|
|||
|
|
"plt.title('Распределение классов HeartDisease в тренировочной выборке после Undersampling')\n",
|
|||
|
|
"plt.show()"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"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
|
|||
|
|
}
|