637 lines
22 KiB
Plaintext
637 lines
22 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Lab2 Pibd-31 Sagirov M M"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Загрузка трёх датасетов"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"df = pd.read_csv(\"..//datasets//Lab_2//world-population-by-country-2020.csv\", sep=\",\")\n",
|
||
"df2 = pd.read_csv(\"..//datasets//Lab_2//Starbucks Dataset.csv\", sep=\",\")\n",
|
||
"df3 = pd.read_csv(\"..//datasets//Lab_2//students_adaptability_level_online_education.csv\", sep=\",\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Пункты 2-8 представленны далее в виде Markdown:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Пункт 2 - Проблемные области:\n",
|
||
"df - Население планеты\n",
|
||
"\n",
|
||
"df2 - Акции Starbucks\n",
|
||
"\n",
|
||
"df3 - Эффективность онлайн обучения"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Пункт 3 - Объекты, их аттрибуты и связи:\n",
|
||
"df - Объектом наблюдения является Страна. Имеет в себе аттрибуты такие как: место в списке, название, население на 2020 год, изменение за год, процентное изменение, плотность населения, а так же процент мигрантов и рождаемость. \n",
|
||
"\n",
|
||
"df2 - Объектом наблюдения является Акция. Имеет в себе аттрибуты такие как: дата торговли, цена на открытие биржи, высшая и низшая цена за день, цена на закрытии и объем торговли.\n",
|
||
"\n",
|
||
"df3 - Объектом наблюдения является Студент. Имеет в себе аттрибуты такие как: Уровень образования, тип обучения (платно/бесплатно), пол, возраст, расположение, финансовое состояние и уровень адаптируемости к онлайн обучению.\n",
|
||
"\n",
|
||
"Связей между объектами нет."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Пункт 4 - Бизнес-цели:\n",
|
||
"df - Для составления списка приоритетных стран для показа рекламы для миграции.\n",
|
||
"\n",
|
||
"df2 - Для выявления тенденций Акций Starbucks.\n",
|
||
"\n",
|
||
"df3 - Для решения о целесообразности введения онлайн обучения в учереждении."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Пункт 5 - Цели проектов:\n",
|
||
"df - Поступает нужны процент мигрантов, а на выходе страны с подходящим числом мигрантов.\n",
|
||
"\n",
|
||
"df2 - Поступает высшая стоимость сегодняшней акции, а на выходе предполагаемый процент завтра.\n",
|
||
"\n",
|
||
"df3 - Поступает список студентов с их состояниями, а на выходе вердикт оправдает ли себя ввод онлайн обучения. "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Пункт 6 - Проблемы наборов:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### Проверка на пропущенные значения:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"no 0\n",
|
||
"Country (or dependency) 0\n",
|
||
"Population 2020 0\n",
|
||
"Yearly Change 0\n",
|
||
"Net Change 0\n",
|
||
"Density (P/Km²) 0\n",
|
||
"Land Area (Km²) 0\n",
|
||
"Migrants (net) 34\n",
|
||
"Fert. Rate 0\n",
|
||
"Med. Age 0\n",
|
||
"Urban Pop % 0\n",
|
||
"World Share 0\n",
|
||
"dtype: int64\n",
|
||
"Date 0\n",
|
||
"Open 0\n",
|
||
"High 0\n",
|
||
"Low 0\n",
|
||
"Close 0\n",
|
||
"Adj Close 0\n",
|
||
"Volume 0\n",
|
||
"dtype: int64\n",
|
||
"Education Level 0\n",
|
||
"Institution Type 0\n",
|
||
"Gender 0\n",
|
||
"Age 0\n",
|
||
"Device 0\n",
|
||
"IT Student 0\n",
|
||
"Location 0\n",
|
||
"Financial Condition 0\n",
|
||
"Internet Type 0\n",
|
||
"Network Type 0\n",
|
||
"Flexibility Level 0\n",
|
||
"dtype: int64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(df.isnull().sum())\n",
|
||
"print(df2.isnull().sum())\n",
|
||
"print(df3.isnull().sum())"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"Как можно заметить, пустых данных почти нет, 34 пустых ячейки есть только в df в столбце с процентами мигрантов"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"df и df2 - неактуальные, так как в первом используется информация 4-х летней давности, а во втором - с 1992. "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Пункт 7 - Примеры решений:\n",
|
||
"Для обоих датасетов решением будет полное обновление данных."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Пункт 8 - Оценка качества:\n",
|
||
"Информативность лучше всего у df и df3, так же как и степень покрытия. Реальным данным соответствует очень хорошо df2. Во всех датасетах метки хорошо согласованны."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Пункт 9 - Устранение пустых данных:\n",
|
||
"Устраним пустые данные в df путем удаления строк, в которых они присутствуют"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df['Migrants (net)'] = df['Migrants (net)'].replace('', pd.NA)\n",
|
||
"df_cleaned = df.dropna(subset=['Migrants (net)'])\n",
|
||
"df_cleaned.to_csv(\"..//datasets//Lab_2//World_population_cleaned.csv\", index=False)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"А теперь просто проведем действия с оставшимися наборами данных:\n",
|
||
"\n",
|
||
"В df2 поставим у всех записей цену при открытии на 12"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" Date Open High Low Close Adj Close Volume\n",
|
||
"0 1992-06-26 12 0.347656 0.320313 0.335938 0.260703 224358400\n",
|
||
"1 1992-06-29 12 0.367188 0.332031 0.359375 0.278891 58732800\n",
|
||
"2 1992-06-30 12 0.371094 0.343750 0.347656 0.269797 34777600\n",
|
||
"3 1992-07-01 12 0.359375 0.339844 0.355469 0.275860 18316800\n",
|
||
"4 1992-07-02 12 0.359375 0.347656 0.355469 0.275860 13996800\n",
|
||
"... ... ... ... ... ... ... ...\n",
|
||
"8031 2024-05-17 12 78.000000 74.919998 77.849998 77.849998 14436500\n",
|
||
"8032 2024-05-20 12 78.320000 76.709999 77.540001 77.540001 11183800\n",
|
||
"8033 2024-05-21 12 78.220001 77.500000 77.720001 77.720001 8916600\n",
|
||
"8034 2024-05-22 12 81.019997 77.440002 80.720001 80.720001 22063400\n",
|
||
"8035 2024-05-23 12 80.699997 79.169998 79.260002 79.260002 4651418\n",
|
||
"\n",
|
||
"[8036 rows x 7 columns]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"df2['Open'] = 12\n",
|
||
"print(df2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"В df3 установим у всех средний по столбцу возраст"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" Age\n",
|
||
"0 17.06556\n",
|
||
"1 17.06556\n",
|
||
"2 17.06556\n",
|
||
"3 17.06556\n",
|
||
"4 17.06556\n",
|
||
"... ...\n",
|
||
"1200 17.06556\n",
|
||
"1201 17.06556\n",
|
||
"1202 17.06556\n",
|
||
"1203 17.06556\n",
|
||
"1204 17.06556\n",
|
||
"\n",
|
||
"[1205 rows x 1 columns]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"Age_mean = df3['Age'].mean()\n",
|
||
"df3['Age'] = Age_mean\n",
|
||
"print(df3[['Age']])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Пункт 10 - Разбиение"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Train df: (140, 12), Validation df: (30, 12), Test df: (31, 12)\n",
|
||
"Train df2: (5625, 7), Validation df2: (1205, 7), Test df2: (1206, 7)\n",
|
||
"Train df3: (843, 11), Validation df3: (181, 11), Test df3: (181, 11)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from sklearn.model_selection import train_test_split\n",
|
||
"\n",
|
||
"train_df, temp_df = train_test_split(df_cleaned, test_size=0.3, random_state=22)\n",
|
||
"val_df, test_df = train_test_split(temp_df, test_size=0.5, random_state=22) \n",
|
||
"\n",
|
||
"train_df2, temp_df2 = train_test_split(df2, test_size=0.3, random_state=22)\n",
|
||
"val_df2, test_df2 = train_test_split(temp_df2, test_size=0.5, random_state=22)\n",
|
||
"\n",
|
||
"train_df3, temp_df3 = train_test_split(df3, test_size=0.3, random_state=22)\n",
|
||
"val_df3, test_df3 = train_test_split(temp_df3, test_size=0.5, random_state=22)\n",
|
||
"print(f\"Train df: {train_df.shape}, Validation df: {val_df.shape}, Test df: {test_df.shape}\")\n",
|
||
"print(f\"Train df2: {train_df2.shape}, Validation df2: {val_df2.shape}, Test df2: {test_df2.shape}\")\n",
|
||
"print(f\"Train df3: {train_df3.shape}, Validation df3: {val_df3.shape}, Test df3: {test_df3.shape}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Пункт 11 - Проверка на сбалансированность"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 13,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Баланс Train df:\n",
|
||
"Распределение по столбцу 'Migrants (net)':\n",
|
||
" Migrants (net)\n",
|
||
"-800 2.857143\n",
|
||
"0 2.857143\n",
|
||
"-4,000 2.142857\n",
|
||
"40,000 2.142857\n",
|
||
"-5,000 2.142857\n",
|
||
" ... \n",
|
||
"52,000 0.714286\n",
|
||
"515 0.714286\n",
|
||
"50,000 0.714286\n",
|
||
"-39,858 0.714286\n",
|
||
"1,485 0.714286\n",
|
||
"Name: proportion, Length: 115, dtype: float64\n",
|
||
"\n",
|
||
"Баланс Validation df:\n",
|
||
"Распределение по столбцу 'Migrants (net)':\n",
|
||
" Migrants (net)\n",
|
||
"900 6.666667\n",
|
||
"-40,000 6.666667\n",
|
||
"36,400 3.333333\n",
|
||
"-67,152 3.333333\n",
|
||
"87,400 3.333333\n",
|
||
"-62,920 3.333333\n",
|
||
"16,000 3.333333\n",
|
||
"-451 3.333333\n",
|
||
"-2,803 3.333333\n",
|
||
"-4,000 3.333333\n",
|
||
"380 3.333333\n",
|
||
"11,370 3.333333\n",
|
||
"-163,313 3.333333\n",
|
||
"-1,500 3.333333\n",
|
||
"-1,000 3.333333\n",
|
||
"10,220 3.333333\n",
|
||
"-852 3.333333\n",
|
||
"168,694 3.333333\n",
|
||
"2,000 3.333333\n",
|
||
"-98,955 3.333333\n",
|
||
"-200 3.333333\n",
|
||
"47,800 3.333333\n",
|
||
"-60,000 3.333333\n",
|
||
"10,000 3.333333\n",
|
||
"3,000 3.333333\n",
|
||
"-14,837 3.333333\n",
|
||
"320 3.333333\n",
|
||
"-20,000 3.333333\n",
|
||
"Name: proportion, dtype: float64\n",
|
||
"\n",
|
||
"Баланс Test df:\n",
|
||
"Распределение по столбцу 'Migrants (net)':\n",
|
||
" Migrants (net)\n",
|
||
"-10,000 6.451613\n",
|
||
"1,000 3.225806\n",
|
||
"204,796 3.225806\n",
|
||
"-14,704 3.225806\n",
|
||
"-6,800 3.225806\n",
|
||
"3,911 3.225806\n",
|
||
"-16,053 3.225806\n",
|
||
"145,405 3.225806\n",
|
||
"4,800 3.225806\n",
|
||
"39,520 3.225806\n",
|
||
"71,560 3.225806\n",
|
||
"-4,806 3.225806\n",
|
||
"0 3.225806\n",
|
||
"-14,400 3.225806\n",
|
||
"4,000 3.225806\n",
|
||
"6,413 3.225806\n",
|
||
"120 3.225806\n",
|
||
"-8,353 3.225806\n",
|
||
"-116,858 3.225806\n",
|
||
"40,000 3.225806\n",
|
||
"260,650 3.225806\n",
|
||
"1,200 3.225806\n",
|
||
"-9,000 3.225806\n",
|
||
"1,351 3.225806\n",
|
||
"2,001 3.225806\n",
|
||
"-1,256 3.225806\n",
|
||
"-8,863 3.225806\n",
|
||
"-38,033 3.225806\n",
|
||
"-1,342 3.225806\n",
|
||
"5,000 3.225806\n",
|
||
"Name: proportion, dtype: float64\n",
|
||
"\n",
|
||
"Баланс Train df2:\n",
|
||
"Распределение по столбцу 'High':\n",
|
||
" High\n",
|
||
"0.804688 0.248889\n",
|
||
"0.742188 0.231111\n",
|
||
"0.765625 0.231111\n",
|
||
"0.789063 0.213333\n",
|
||
"0.757813 0.195556\n",
|
||
" ... \n",
|
||
"29.485001 0.017778\n",
|
||
"38.290001 0.017778\n",
|
||
"97.580002 0.017778\n",
|
||
"74.769997 0.017778\n",
|
||
"64.040001 0.017778\n",
|
||
"Name: proportion, Length: 4071, dtype: float64\n",
|
||
"\n",
|
||
"Баланс Validation df2:\n",
|
||
"Распределение по столбцу 'High':\n",
|
||
" High\n",
|
||
"0.851563 0.414938\n",
|
||
"0.757813 0.414938\n",
|
||
"0.726563 0.331950\n",
|
||
"0.812500 0.331950\n",
|
||
"0.914063 0.331950\n",
|
||
" ... \n",
|
||
"13.000000 0.082988\n",
|
||
"10.452500 0.082988\n",
|
||
"2.492188 0.082988\n",
|
||
"61.720001 0.082988\n",
|
||
"3.800781 0.082988\n",
|
||
"Name: proportion, Length: 1078, dtype: float64\n",
|
||
"\n",
|
||
"Баланс Test df2:\n",
|
||
"Распределение по столбцу 'High':\n",
|
||
" High\n",
|
||
"0.796875 0.414594\n",
|
||
"0.765625 0.414594\n",
|
||
"1.640625 0.331675\n",
|
||
"0.882813 0.331675\n",
|
||
"0.757813 0.331675\n",
|
||
" ... \n",
|
||
"8.085000 0.082919\n",
|
||
"10.595000 0.082919\n",
|
||
"7.540000 0.082919\n",
|
||
"99.470001 0.082919\n",
|
||
"88.540001 0.082919\n",
|
||
"Name: proportion, Length: 1088, dtype: float64\n",
|
||
"\n",
|
||
"Баланс Train df3:\n",
|
||
"Распределение по столбцу 'Flexibility Level':\n",
|
||
" Flexibility Level\n",
|
||
"Moderate 52.669039\n",
|
||
"Low 38.552788\n",
|
||
"High 8.778173\n",
|
||
"Name: proportion, dtype: float64\n",
|
||
"\n",
|
||
"Баланс Validation df3:\n",
|
||
"Распределение по столбцу 'Flexibility Level':\n",
|
||
" Flexibility Level\n",
|
||
"Moderate 50.276243\n",
|
||
"Low 44.198895\n",
|
||
"High 5.524862\n",
|
||
"Name: proportion, dtype: float64\n",
|
||
"\n",
|
||
"Баланс Test df3:\n",
|
||
"Распределение по столбцу 'Flexibility Level':\n",
|
||
" Flexibility Level\n",
|
||
"Moderate 49.723757\n",
|
||
"Low 41.436464\n",
|
||
"High 8.839779\n",
|
||
"Name: proportion, dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"#Проверка на сбалансированность\n",
|
||
"def check_balance(df, target_column):\n",
|
||
" distribution = df[target_column].value_counts(normalize=True) * 100\n",
|
||
" print(f\"Распределение по столбцу '{target_column}':\\n\", distribution)\n",
|
||
"\n",
|
||
"# Для датасета 1\n",
|
||
"print(\"Баланс Train df:\")\n",
|
||
"check_balance(train_df, 'Migrants (net)') \n",
|
||
"print(\"\\nБаланс Validation df:\")\n",
|
||
"check_balance(val_df, 'Migrants (net)')\n",
|
||
"print(\"\\nБаланс Test df:\")\n",
|
||
"check_balance(test_df, 'Migrants (net)')\n",
|
||
"\n",
|
||
"# Для датасета 2\n",
|
||
"print(\"\\nБаланс Train df2:\")\n",
|
||
"check_balance(train_df2, 'High')\n",
|
||
"print(\"\\nБаланс Validation df2:\")\n",
|
||
"check_balance(val_df2, 'High')\n",
|
||
"print(\"\\nБаланс Test df2:\")\n",
|
||
"check_balance(test_df2, 'High')\n",
|
||
"\n",
|
||
"# Для датасета 3\n",
|
||
"print(\"\\nБаланс Train df3:\")\n",
|
||
"check_balance(train_df3, 'Flexibility Level')\n",
|
||
"print(\"\\nБаланс Validation df3:\")\n",
|
||
"check_balance(val_df3, 'Flexibility Level')\n",
|
||
"print(\"\\nБаланс Test df3:\")\n",
|
||
"check_balance(test_df3, 'Flexibility Level')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"Наши выборки сбалансированно распределены. "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Пункт 12 - Приращение данных:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 15,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"df - Oversampling:\n",
|
||
"Размер выборки после oversampling: (460, 11)\n",
|
||
"\n",
|
||
"df - Undersampling:\n",
|
||
"Размер выборки после undersampling: (115, 11)\n",
|
||
"\n",
|
||
"df2 - Oversampling:\n",
|
||
"Размер выборки после oversampling: (21868, 6)\n",
|
||
"\n",
|
||
"df2 - Undersampling:\n",
|
||
"Размер выборки после undersampling: (5467, 6)\n",
|
||
"\n",
|
||
"df3 - Oversampling:\n",
|
||
"Размер выборки после oversampling: (1332, 10)\n",
|
||
"\n",
|
||
"df3 - Undersampling:\n",
|
||
"Размер выборки после undersampling: (222, 10)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from imblearn.over_sampling import RandomOverSampler\n",
|
||
"from imblearn.under_sampling import RandomUnderSampler\n",
|
||
"\n",
|
||
"# Функция для выполнения oversampling\n",
|
||
"def apply_oversampling(X, y):\n",
|
||
" oversampler = RandomOverSampler(random_state=22)\n",
|
||
" X_resampled, y_resampled = oversampler.fit_resample(X, y)\n",
|
||
" print(f\"Размер выборки после oversampling: {X_resampled.shape}\")\n",
|
||
" return X_resampled, y_resampled\n",
|
||
"\n",
|
||
"# Функция для выполнения undersampling\n",
|
||
"def apply_undersampling(X, y):\n",
|
||
" undersampler = RandomUnderSampler(random_state=22)\n",
|
||
" X_resampled, y_resampled = undersampler.fit_resample(X, y)\n",
|
||
" print(f\"Размер выборки после undersampling: {X_resampled.shape}\")\n",
|
||
" return X_resampled, y_resampled\n",
|
||
"\n",
|
||
"# Пример для первого набора данных (df)\n",
|
||
"X_1 = train_df.drop(columns=['Migrants (net)']) \n",
|
||
"y_1 = train_df['Migrants (net)']\n",
|
||
"\n",
|
||
"print(\"df - Oversampling:\")\n",
|
||
"X_resampled1, y_resampled1 = apply_oversampling(X_1, y_1)\n",
|
||
"\n",
|
||
"print(\"\\ndf - Undersampling:\")\n",
|
||
"X_resampled1_under, y_resampled1_under = apply_undersampling(X_1, y_1)\n",
|
||
"\n",
|
||
"# Пример для второго набора данных (df2)\n",
|
||
"X_2 = train_df2.drop(columns=['Volume'])\n",
|
||
"y_2 = train_df2['Volume']\n",
|
||
"\n",
|
||
"print(\"\\ndf2 - Oversampling:\")\n",
|
||
"X_resampled2, y_resampled2 = apply_oversampling(X_2, y_2)\n",
|
||
"\n",
|
||
"print(\"\\ndf2 - Undersampling:\")\n",
|
||
"X_resampled2_under, y_resampled2_under = apply_undersampling(X_2, y_2)\n",
|
||
"\n",
|
||
"# Пример для третьего набора данных (df3)\n",
|
||
"X_3 = train_df3.drop(columns=['Flexibility Level'])\n",
|
||
"y_3 = train_df3['Flexibility Level']\n",
|
||
"\n",
|
||
"print(\"\\ndf3 - Oversampling:\")\n",
|
||
"X_resampled3, y_resampled3 = apply_oversampling(X_3, y_3)\n",
|
||
"\n",
|
||
"print(\"\\ndf3 - Undersampling:\")\n",
|
||
"X_resampled3_under, y_resampled3_under = apply_undersampling(X_3, y_3)"
|
||
]
|
||
}
|
||
],
|
||
"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": "3.12.2"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 2
|
||
}
|