AIM-PIbd-31-Potapov-N-S/lab_3/lab3.ipynb

Вариант 2. Показатели сердечных заболеваний¶

In [228]:

from typing import Any
from math import ceil

import pandas as pd
from pandas import DataFrame, Series
from sklearn.model_selection import train_test_split
from imblearn.over_sampling import ADASYN, SMOTE
from imblearn.under_sampling import RandomUnderSampler
import matplotlib.pyplot as plt

Загрузим данные из датасета¶

In [229]:

df = pd.read_csv('csv\\heart_2022_no_nans.csv')

Посмотрим общие сведения о датасете¶

In [230]:

df.info()
df.describe().transpose()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 246022 entries, 0 to 246021
Data columns (total 40 columns):
 #   Column                     Non-Null Count   Dtype  
---  ------                     --------------   -----  
 0   State                      246022 non-null  object 
 1   Sex                        246022 non-null  object 
 2   GeneralHealth              246022 non-null  object 
 3   PhysicalHealthDays         246022 non-null  float64
 4   MentalHealthDays           246022 non-null  float64
 5   LastCheckupTime            246022 non-null  object 
 6   PhysicalActivities         246022 non-null  object 
 7   SleepHours                 246022 non-null  float64
 8   RemovedTeeth               246022 non-null  object 
 9   HadHeartAttack             246022 non-null  object 
 10  HadAngina                  246022 non-null  object 
 11  HadStroke                  246022 non-null  object 
 12  HadAsthma                  246022 non-null  object 
 13  HadSkinCancer              246022 non-null  object 
 14  HadCOPD                    246022 non-null  object 
 15  HadDepressiveDisorder      246022 non-null  object 
 16  HadKidneyDisease           246022 non-null  object 
 17  HadArthritis               246022 non-null  object 
 18  HadDiabetes                246022 non-null  object 
 19  DeafOrHardOfHearing        246022 non-null  object 
 20  BlindOrVisionDifficulty    246022 non-null  object 
 21  DifficultyConcentrating    246022 non-null  object 
 22  DifficultyWalking          246022 non-null  object 
 23  DifficultyDressingBathing  246022 non-null  object 
 24  DifficultyErrands          246022 non-null  object 
 25  SmokerStatus               246022 non-null  object 
 26  ECigaretteUsage            246022 non-null  object 
 27  ChestScan                  246022 non-null  object 
 28  RaceEthnicityCategory      246022 non-null  object 
 29  AgeCategory                246022 non-null  object 
 30  HeightInMeters             246022 non-null  float64
 31  WeightInKilograms          246022 non-null  float64
 32  BMI                        246022 non-null  float64
 33  AlcoholDrinkers            246022 non-null  object 
 34  HIVTesting                 246022 non-null  object 
 35  FluVaxLast12               246022 non-null  object 
 36  PneumoVaxEver              246022 non-null  object 
 37  TetanusLast10Tdap          246022 non-null  object 
 38  HighRiskLastYear           246022 non-null  object 
 39  CovidPos                   246022 non-null  object 
dtypes: float64(6), object(34)
memory usage: 75.1+ MB

Out[230]:

	count	mean	std	min	25%	50%	75%	max
PhysicalHealthDays	246022.0	4.119026	8.405844	0.00	0.00	0.00	3.00	30.00
MentalHealthDays	246022.0	4.167140	8.102687	0.00	0.00	0.00	4.00	30.00
SleepHours	246022.0	7.021331	1.440681	1.00	6.00	7.00	8.00	24.00
HeightInMeters	246022.0	1.705150	0.106654	0.91	1.63	1.70	1.78	2.41
WeightInKilograms	246022.0	83.615179	21.323156	28.12	68.04	81.65	95.25	292.57
BMI	246022.0	28.668136	6.513973	12.02	24.27	27.46	31.89	97.65

Получим информацию о пустых значениях в колонках датасета¶

In [231]:

def get_null_columns_info(df: DataFrame) -> DataFrame:
    """
    Возвращает информацию о пропущенных значениях в колонках датасета
    """
    w = []
    df_len = len(df)

    for column in df.columns:
        column_nulls = df[column].isnull()
        w.append([column, column_nulls.any(), column_nulls.sum() / df_len])

    null_df = DataFrame(w).rename(columns={0: "Column", 1: "Has Null", 2: "Null Percent"})

    return null_df

In [232]:

get_null_columns_info(df)

Out[232]:

	Column	Has Null	Null Percent
0	State	False	0.0
1	Sex	False	0.0
2	GeneralHealth	False	0.0
3	PhysicalHealthDays	False	0.0
4	MentalHealthDays	False	0.0
5	LastCheckupTime	False	0.0
6	PhysicalActivities	False	0.0
7	SleepHours	False	0.0
8	RemovedTeeth	False	0.0
9	HadHeartAttack	False	0.0
10	HadAngina	False	0.0
11	HadStroke	False	0.0
12	HadAsthma	False	0.0
13	HadSkinCancer	False	0.0
14	HadCOPD	False	0.0
15	HadDepressiveDisorder	False	0.0
16	HadKidneyDisease	False	0.0
17	HadArthritis	False	0.0
18	HadDiabetes	False	0.0
19	DeafOrHardOfHearing	False	0.0
20	BlindOrVisionDifficulty	False	0.0
21	DifficultyConcentrating	False	0.0
22	DifficultyWalking	False	0.0
23	DifficultyDressingBathing	False	0.0
24	DifficultyErrands	False	0.0
25	SmokerStatus	False	0.0
26	ECigaretteUsage	False	0.0
27	ChestScan	False	0.0
28	RaceEthnicityCategory	False	0.0
29	AgeCategory	False	0.0
30	HeightInMeters	False	0.0
31	WeightInKilograms	False	0.0
32	BMI	False	0.0
33	AlcoholDrinkers	False	0.0
34	HIVTesting	False	0.0
35	FluVaxLast12	False	0.0
36	PneumoVaxEver	False	0.0
37	TetanusLast10Tdap	False	0.0
38	HighRiskLastYear	False	0.0
39	CovidPos	False	0.0

Получим информацию о выбросах¶

In [233]:

def get_numeric_columns(df: DataFrame) -> list[str]:
    """
    Возвращает список числовых колонок
    """
    return list(filter(lambda column: pd.api.types.is_numeric_dtype(df[column]), df.columns))

In [234]:

def get_outliers_info(df: DataFrame) -> DataFrame:
    """
    Возаращает информацию о выбросах в числовых колонках датасета
    """
    data = {
        "Column": [],
        "Has Outliers": [],
        "Outliers Count": [],
        "Min Value": [],
        "Max Value": [],
        "Q1": [],
        "Q3": []
    }

    info = DataFrame(data)

    for column in get_numeric_columns(df):
        Q1: float = df[column].quantile(0.25)
        Q3: float = df[column].quantile(0.75)
        IQR: float = Q3 - Q1

        lower_bound: float = Q1 - 1.5 * IQR
        upper_bound: float = Q3 + 1.5 * IQR

        outliers: DataFrame = df[(df[column] < lower_bound) | (df[column] > upper_bound)]
        outlier_count: int = outliers.shape[0]

        info.loc[len(info)] = [column, outlier_count > 0, outlier_count, df[column].min(), df[column].max(), Q1, Q3]

    return info

Посмотрим данные по выбросам

In [235]:

outliers_info = get_outliers_info(df)
outliers_info

Out[235]:

	Column	Has Outliers	Outliers Count	Min Value	Max Value	Q1	Q3
0	PhysicalHealthDays	True	38810	0.00	30.00	0.00	3.00
1	MentalHealthDays	True	32714	0.00	30.00	0.00	4.00
2	SleepHours	True	3488	1.00	24.00	6.00	8.00
3	HeightInMeters	True	830	0.91	2.41	1.63	1.78
4	WeightInKilograms	True	5940	28.12	292.57	68.04	95.25
5	BMI	True	7563	12.02	97.65	24.27	31.89

In [236]:

def visualize_outliers(df: DataFrame) -> None:
    """
    Генерирует диаграммы BoxPlot для числовых колонок датасета
    """
    columns = get_numeric_columns(df)
    plt.figure(figsize=(15, 10))
    rows: int = ceil(len(columns) / 3)
    for index, column in enumerate(columns, 1):
        plt.subplot(rows, 3, index)
        plt.boxplot(df[column], vert=True, patch_artist=True)
        plt.title(f"Диаграмма размахов\n\"{column}\"")
        plt.xlabel(column)
            
    plt.tight_layout()
    plt.show()

Визуализируем выбросы с помощью диаграмм

In [237]:

visualize_outliers(df)

In [238]:

def remove_outliers(df: DataFrame, columns: list[str]) -> DataFrame:
    """
    Устраняет выбросы в заданных колонках:
    задает значениям выше максимального значение максимума, ниже минимального - значение минимума
    """
    for column in columns:
        Q1: float = df[column].quantile(0.25)
        Q3: float = df[column].quantile(0.75)
        IQR: float = Q3 - Q1

        lower_bound: float = Q1 - 1.5 * IQR
        upper_bound: float = Q3 + 1.5 * IQR

        df[column] = df[column].apply(lambda x: lower_bound if x < lower_bound else upper_bound if x > upper_bound else x)
    
    return df

Удаляем выбросы

In [239]:

outliers_columns = list(outliers_info[outliers_info["Has Outliers"] == True]["Column"])
df = remove_outliers(df, outliers_columns)

Снова получим данные о выбросах

In [240]:

get_outliers_info(df)

Out[240]:

	Column	Has Outliers	Outliers Count	Min Value	Max Value	Q1	Q3
0	PhysicalHealthDays	False	0	0.000	7.500	0.00	3.00
1	MentalHealthDays	False	0	0.000	10.000	0.00	4.00
2	SleepHours	False	0	3.000	11.000	6.00	8.00
3	HeightInMeters	False	0	1.405	2.005	1.63	1.78
4	WeightInKilograms	False	0	28.120	136.065	68.04	95.25
5	BMI	False	0	12.840	43.320	24.27	31.89

Видим, что выбросов не осталось - проверим через диаграммы

In [241]:

visualize_outliers(df)

Нормализация числовых признаков¶

In [242]:

from sklearn import preprocessing

In [247]:

min_max_scaler = preprocessing.MinMaxScaler()

df_norm = df.copy()

numeric_columns = get_numeric_columns(df)

for column in numeric_columns:
    norm_column = column + "Norm"
    df_norm[norm_column] = min_max_scaler.fit_transform(
        df_norm[column].to_numpy().reshape(-1, 1)
    ).reshape(df_norm[column].shape)

df_norm = df_norm.drop(columns=numeric_columns)


df_norm.describe().transpose()

Out[247]:

	count	mean	std	min	25%	50%	75%	max
PhysicalHealthDaysNorm	246022.0	0.253306	0.385378	0.0	0.000000	0.000000	0.400000	1.0
MentalHealthDaysNorm	246022.0	0.244973	0.378598	0.0	0.000000	0.000000	0.400000	1.0
SleepHoursNorm	246022.0	0.501124	0.165569	0.0	0.375000	0.500000	0.625000	1.0
HeightInMetersNorm	246022.0	0.500401	0.176240	0.0	0.375000	0.491667	0.625000	1.0
WeightInKilogramsNorm	246022.0	0.510963	0.186742	0.0	0.369818	0.495901	0.621891	1.0
BMINorm	246022.0	0.513599	0.194556	0.0	0.375000	0.479659	0.625000	1.0

Конструирование признаков¶

Автоматическое конструирование признаков с помощью фреймворка FeatureTools¶

In [221]:

import featuretools as ft

In [222]:

# Преобразуем датасет с помощью фремйворка
# https://featuretools.alteryx.com/en/stable/getting_started/afe.html

entity_set = ft.EntitySet().add_dataframe(df, "df", make_index=True, index="id")

feature_matrix, feature_defs = ft.dfs(
    entityset=entity_set,
    target_dataframe_name="df",
    max_depth=2
)

feature_matrix: DataFrame
feature_defs: list[ft.Feature]

d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\woodwork\type_sys\utils.py:33: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  pd.to_datetime(
d:\code\AIM-PIbd-31-Potapov-N-S\lab_3\.venv\Lib\site-packages\featuretools\synthesis\deep_feature_synthesis.py:169: UserWarning: Only one dataframe in entityset, changing max_depth to 1 since deeper features cannot be created
  warnings.warn(

Выполняем категориальное и унитарное кодирование признаков с помощью FeatureTools

In [224]:

# Сгенерируем новые признаки
# https://featuretools.alteryx.com/en/stable/guides/tuning_dfs.html

feature_matrix_enc, features_enc = ft.encode_features(feature_matrix, feature_defs)
feature_matrix_enc.to_csv("./csv/generated_features.csv", index=False)

print("Было признаков:", len(feature_defs))
print("Стало признаков:", len(features_enc))
print(*features_enc, sep='\n')

Было признаков: 40
Стало признаков: 99
<Feature: State = Washington>
<Feature: State = Maryland>
<Feature: State = Minnesota>
<Feature: State = Ohio>
<Feature: State = New York>
<Feature: State = Texas>
<Feature: State = Florida>
<Feature: State = Kansas>
<Feature: State = Wisconsin>
<Feature: State = Maine>
<Feature: State is unknown>
<Feature: Sex = Female>
<Feature: Sex = Male>
<Feature: Sex is unknown>
<Feature: GeneralHealth = Very good>
<Feature: GeneralHealth = Good>
<Feature: GeneralHealth = Excellent>
<Feature: GeneralHealth = Fair>
<Feature: GeneralHealth = Poor>
<Feature: GeneralHealth is unknown>
<Feature: PhysicalHealthDays>
<Feature: MentalHealthDays>
<Feature: LastCheckupTime = Within past year (anytime less than 12 months ago)>
<Feature: LastCheckupTime = Within past 2 years (1 year but less than 2 years ago)>
<Feature: LastCheckupTime = Within past 5 years (2 years but less than 5 years ago)>
<Feature: LastCheckupTime = 5 or more years ago>
<Feature: LastCheckupTime is unknown>
<Feature: PhysicalActivities>
<Feature: SleepHours>
<Feature: RemovedTeeth = None of them>
<Feature: RemovedTeeth = 1 to 5>
<Feature: RemovedTeeth = 6 or more, but not all>
<Feature: RemovedTeeth = All>
<Feature: RemovedTeeth is unknown>
<Feature: HadHeartAttack>
<Feature: HadAngina>
<Feature: HadStroke>
<Feature: HadAsthma>
<Feature: HadSkinCancer>
<Feature: HadCOPD>
<Feature: HadDepressiveDisorder>
<Feature: HadKidneyDisease>
<Feature: HadArthritis>
<Feature: HadDiabetes = No>
<Feature: HadDiabetes = Yes>
<Feature: HadDiabetes = No, pre-diabetes or borderline diabetes>
<Feature: HadDiabetes = Yes, but only during pregnancy (female)>
<Feature: HadDiabetes is unknown>
<Feature: DeafOrHardOfHearing>
<Feature: BlindOrVisionDifficulty>
<Feature: DifficultyConcentrating>
<Feature: DifficultyWalking>
<Feature: DifficultyDressingBathing>
<Feature: DifficultyErrands>
<Feature: SmokerStatus = Never smoked>
<Feature: SmokerStatus = Former smoker>
<Feature: SmokerStatus = Current smoker - now smokes every day>
<Feature: SmokerStatus = Current smoker - now smokes some days>
<Feature: SmokerStatus is unknown>
<Feature: ECigaretteUsage = Never used e-cigarettes in my entire life>
<Feature: ECigaretteUsage = Not at all (right now)>
<Feature: ECigaretteUsage = Use them some days>
<Feature: ECigaretteUsage = Use them every day>
<Feature: ECigaretteUsage is unknown>
<Feature: ChestScan>
<Feature: RaceEthnicityCategory = White only, Non-Hispanic>
<Feature: RaceEthnicityCategory = Hispanic>
<Feature: RaceEthnicityCategory = Black only, Non-Hispanic>
<Feature: RaceEthnicityCategory = Other race only, Non-Hispanic>
<Feature: RaceEthnicityCategory = Multiracial, Non-Hispanic>
<Feature: RaceEthnicityCategory is unknown>
<Feature: AgeCategory = Age 65 to 69>
<Feature: AgeCategory = Age 60 to 64>
<Feature: AgeCategory = Age 70 to 74>
<Feature: AgeCategory = Age 55 to 59>
<Feature: AgeCategory = Age 50 to 54>
<Feature: AgeCategory = Age 75 to 79>
<Feature: AgeCategory = Age 80 or older>
<Feature: AgeCategory = Age 40 to 44>
<Feature: AgeCategory = Age 45 to 49>
<Feature: AgeCategory = Age 35 to 39>
<Feature: AgeCategory is unknown>
<Feature: HeightInMeters>
<Feature: WeightInKilograms>
<Feature: BMI>
<Feature: AlcoholDrinkers>
<Feature: HIVTesting>
<Feature: FluVaxLast12>
<Feature: PneumoVaxEver>
<Feature: TetanusLast10Tdap = No, did not receive any tetanus shot in the past 10 years>
<Feature: TetanusLast10Tdap = Yes, received tetanus shot but not sure what type>
<Feature: TetanusLast10Tdap = Yes, received Tdap>
<Feature: TetanusLast10Tdap = Yes, received tetanus shot, but not Tdap>
<Feature: TetanusLast10Tdap is unknown>
<Feature: HighRiskLastYear>
<Feature: CovidPos = No>
<Feature: CovidPos = Yes>
<Feature: CovidPos = Tested positive using home test without a health professional>
<Feature: CovidPos is unknown>