313 lines
8.3 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Загрузка данных в DataFrame"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"df = pd.read_csv(\"../data/kc_house_data.csv\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Получение сведений о пропущенных данных"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(df.isnull().sum())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(df.isnull().any())"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"for i in df.columns:\n",
" null_rate = df[i].isnull().sum() / len(df) * 100\n",
" if null_rate > 0:\n",
" print(f\"{i} процент пустых значений: {null_rate:.2f}%\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Создание выборок данных"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split\n",
"\n",
"\n",
"def split_stratified_into_train_val_test(\n",
" df_input,\n",
" stratify_colname=\"y\",\n",
" frac_train=0.6,\n",
" frac_val=0.15,\n",
" frac_test=0.25,\n",
" random_state=None,\n",
"):\n",
" \"\"\"\n",
" Splits a Pandas dataframe into three subsets (train, val, and test)\n",
" following fractional ratios provided by the user, where each subset is\n",
" stratified by the values in a specific column (that is, each subset has\n",
" the same relative frequency of the values in the column). It performs this\n",
" splitting by running train_test_split() twice.\n",
"\n",
" Parameters\n",
" ----------\n",
" df_input : Pandas dataframe\n",
" Input dataframe to be split.\n",
" stratify_colname : str\n",
" The name of the column that will be used for stratification. Usually\n",
" this column would be for the label.\n",
" frac_train : float\n",
" frac_val : float\n",
" frac_test : float\n",
" The ratios with which the dataframe will be split into train, val, and\n",
" test data. The values should be expressed as float fractions and should\n",
" sum to 1.0.\n",
" random_state : int, None, or RandomStateInstance\n",
" Value to be passed to train_test_split().\n",
"\n",
" Returns\n",
" -------\n",
" df_train, df_val, df_test :\n",
" Dataframes containing the three splits.\n",
" \"\"\"\n",
"\n",
" if frac_train + frac_val + frac_test != 1.0:\n",
" raise ValueError(\n",
" \"fractions %f, %f, %f do not add up to 1.0\"\n",
" % (frac_train, frac_val, frac_test)\n",
" )\n",
"\n",
" if stratify_colname not in df_input.columns:\n",
" raise ValueError(\"%s is not a column in the dataframe\" % (stratify_colname))\n",
"\n",
" X = df_input # Contains all columns.\n",
" y = df_input[\n",
" [stratify_colname]\n",
" ] # Dataframe of just the column on which to stratify.\n",
"\n",
" # Split original dataframe into train and temp dataframes.\n",
" df_train, df_temp, y_train, y_temp = train_test_split(\n",
" X, y, stratify=y, test_size=(1.0 - frac_train), random_state=random_state\n",
" )\n",
"\n",
" # Split the temp dataframe into val and test dataframes.\n",
" relative_frac_test = frac_test / (frac_val + frac_test)\n",
" df_val, df_test, y_val, y_test = train_test_split(\n",
" df_temp,\n",
" y_temp,\n",
" stratify=y_temp,\n",
" test_size=relative_frac_test,\n",
" random_state=random_state,\n",
" )\n",
"\n",
" assert len(df_input) == len(df_train) + len(df_val) + len(df_test)\n",
"\n",
" return df_train, df_val, df_test"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[3 5 4 1 2]\n"
]
}
],
"source": [
"print(df.condition.unique())\n",
"\n",
"data = df[\n",
" [\n",
" \"price\",\n",
" \"bedrooms\",\n",
" \"bathrooms\",\n",
" \"sqft_living\",\n",
" \"sqft_lot\",\n",
" \"floors\",\n",
" \"view\",\n",
" \"condition\",\n",
" \"grade\",\n",
" \"sqft_above\",\n",
" \"sqft_basement\",\n",
" \"yr_built\",\n",
" \"yr_renovated\",\n",
" \"zipcode\",\n",
" \"lat\",\n",
" \"long\",\n",
" ]\n",
"].copy()"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Обучающая выборка: (12967, 16)\n",
"condition\n",
"3 8418\n",
"4 3407\n",
"5 1021\n",
"2 103\n",
"1 18\n",
"Name: count, dtype: int64\n",
"Контрольная выборка: (4323, 16)\n",
"condition\n",
"3 2806\n",
"4 1136\n",
"5 340\n",
"2 35\n",
"1 6\n",
"Name: count, dtype: int64\n",
"Тестовая выборка: (4323, 16)\n",
"condition\n",
"3 2807\n",
"4 1136\n",
"5 340\n",
"2 34\n",
"1 6\n",
"Name: count, dtype: int64\n"
]
}
],
"source": [
"df_train, df_val, df_test = split_stratified_into_train_val_test(\n",
" data,\n",
" stratify_colname=\"condition\",\n",
" frac_train=0.60,\n",
" frac_val=0.20,\n",
" frac_test=0.20,\n",
")\n",
"\n",
"print(\"Обучающая выборка: \", df_train.shape)\n",
"print(df_train.condition.value_counts())\n",
"\n",
"print(\"Контрольная выборка: \", df_val.shape)\n",
"print(df_val.condition.value_counts())\n",
"\n",
"print(\"Тестовая выборка: \", df_test.shape)\n",
"print(df_test.condition.value_counts())"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Обучающая выборка: (12967, 16)\n",
"condition\n",
"3 8418\n",
"4 3407\n",
"5 1021\n",
"2 103\n",
"1 18\n",
"Name: count, dtype: int64\n",
"Обучающая выборка после oversampling: (42073, 16)\n",
"condition\n",
"5 8464\n",
"2 8421\n",
"1 8420\n",
"3 8418\n",
"4 8350\n",
"Name: count, dtype: int64\n"
]
}
],
"source": [
"from imblearn.over_sampling import ADASYN\n",
"\n",
"ada = ADASYN()\n",
"\n",
"print(\"Обучающая выборка: \", df_train.shape)\n",
"print(df_train.condition.value_counts())\n",
"\n",
"X_resampled, y_resampled = ada.fit_resample(df_train, df_train[\"condition\"])\n",
"df_train_adasyn = pd.DataFrame(X_resampled)\n",
"\n",
"print(\"Обучающая выборка после oversampling: \", df_train_adasyn.shape)\n",
"print(df_train_adasyn.condition.value_counts())"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}