{"id":345013,"date":"2023-02-06T09:00:51","date_gmt":"2023-02-06T09:00:51","guid":{"rendered":"http:\/\/savepearlharbor.com\/?p=345013"},"modified":"-0001-11-30T00:00:00","modified_gmt":"-0001-11-29T21:00:00","slug":"","status":"publish","type":"post","link":"https:\/\/savepearlharbor.com\/?p=345013","title":{"rendered":"\u041f\u0440\u0435\u0434\u0441\u043a\u0430\u0437\u0430\u043d\u0438\u0435 \u043e\u0442\u0442\u043e\u043a\u0430 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439<\/span>"},"content":{"rendered":"
<\/div>\n
\n
\n
\n
\n

\u0417\u0434\u0440\u0430\u0432\u0441\u0442\u0432\u0443\u0439\u0442\u0435, \u0432 \u0434\u0430\u043d\u043d\u043e\u0439 \u0441\u0442\u0430\u0442\u044c\u0435 \u044f \u043f\u043e\u0441\u0442\u0430\u0440\u0430\u044e\u0441\u044c \u0440\u0430\u0437\u043e\u0431\u0440\u0430\u0442\u044c \u043e\u0441\u043d\u043e\u0432\u043d\u044b\u0435 \u0448\u0430\u0433\u0438 \u0438 \u043c\u0435\u0442\u043e\u0434\u044b \u0440\u0435\u0448\u0435\u043d\u0438\u044f \u0441\u043e\u0440\u0435\u0432\u043d\u043e\u0432\u0430\u043d\u0438\u0439 \u043d\u0430 Kaggle<\/a> \u043d\u0430 \u043f\u0440\u0438\u043c\u0435\u0440\u0435 \u0440\u0435\u0448\u0435\u043d\u0438\u044f \u043e\u0431\u0443\u0447\u0430\u044e\u0449\u0435\u0433\u043e \u0441\u043e\u0440\u0435\u0432\u043d\u043e\u0432\u0430\u043d\u0438\u044f \u043e\u0442 DeepLearningSchool \u041c\u0424\u0422\u0418 \u043f\u043e \u043f\u0440\u0435\u0434\u0441\u043a\u0430\u0437\u0430\u043d\u0438\u044e \u043e\u0442\u0442\u043e\u043a\u0430 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439. <\/p>\n

\u0420\u0430\u0431\u043e\u0442\u0430 \u0441 \u0434\u0430\u043d\u043d\u044b\u043c\u0438<\/h2>\n

\u041f\u0440\u0435\u0434\u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0430<\/h3>\n

\u0418\u0442\u0430\u043a, \u0434\u043b\u044f \u043d\u0430\u0447\u0430\u043b\u0430 \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u0437\u0430\u0433\u0440\u0443\u0437\u0438\u043c \u043d\u0430\u0448 \u0434\u0430\u0442\u0430\u0441\u0435\u0442 \u0438 \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u043c \u043d\u0430 5 \u0441\u043b\u0443\u0447\u0430\u0439\u043d\u044b\u0445 \u0441\u0442\u0440\u043e\u043a \u0432 \u043d\u0435\u043c.<\/p>\n

\n
\n\n\n\n\n\n\n\n\n
\n

<\/p>\n<\/td>\n

\n

ClientPeriod<\/p>\n<\/th>\n

\n

MonthlySpending<\/p>\n<\/th>\n

\n

TotalSpent<\/p>\n<\/th>\n

\n

Sex<\/p>\n<\/th>\n

\n

IsSeniorCitizen<\/p>\n<\/th>\n

\n

HasPartner<\/p>\n<\/th>\n

\n

HasChild<\/p>\n<\/th>\n

\n

HasPhoneService<\/p>\n<\/th>\n

\n

HasMultiplePhoneNumbers<\/p>\n<\/th>\n

\n

HasInternetService<\/p>\n<\/th>\n

\n

HasOnlineSecurityService<\/p>\n<\/th>\n

\n

HasOnlineBackup<\/p>\n<\/th>\n

\n

HasDeviceProtection<\/p>\n<\/th>\n

\n

HasTechSupportAccess<\/p>\n<\/th>\n

\n

HasOnlineTV<\/p>\n<\/th>\n

\n

HasMovieSubscription<\/p>\n<\/th>\n

\n

HasContractPhone<\/p>\n<\/th>\n

\n

IsBillingPaperless<\/p>\n<\/th>\n

\n

PaymentMethod<\/p>\n<\/th>\n

\n

Churn<\/p>\n<\/th>\n<\/tr>\n

\n

4650<\/p>\n<\/th>\n

\n

66<\/p>\n<\/td>\n

\n

20.35<\/p>\n<\/td>\n

\n

1359.5<\/p>\n<\/td>\n

\n

Male<\/p>\n<\/td>\n

\n

0<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

One year<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Electronic check<\/p>\n<\/td>\n

\n

0<\/p>\n<\/td>\n<\/tr>\n

\n

29<\/p>\n<\/th>\n

\n

25<\/p>\n<\/td>\n

\n

89.70<\/p>\n<\/td>\n

\n

2187.55<\/p>\n<\/td>\n

\n

Female<\/p>\n<\/td>\n

\n

1<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Fiber optic<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Month-to-month<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Electronic check<\/p>\n<\/td>\n

\n

1<\/p>\n<\/td>\n<\/tr>\n

\n

1688<\/p>\n<\/th>\n

\n

36<\/p>\n<\/td>\n

\n

76.35<\/p>\n<\/td>\n

\n

2606.35<\/p>\n<\/td>\n

\n

Female<\/p>\n<\/td>\n

\n

0<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

DSL<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

One year<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Mailed check<\/p>\n<\/td>\n

\n

0<\/p>\n<\/td>\n<\/tr>\n

\n

2946<\/p>\n<\/th>\n

\n

20<\/p>\n<\/td>\n

\n

19.60<\/p>\n<\/td>\n

\n

356.15<\/p>\n<\/td>\n

\n

Male<\/p>\n<\/td>\n

\n

0<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

No internet service<\/p>\n<\/td>\n

\n

Month-to-month<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Credit card (automatic)<\/p>\n<\/td>\n

\n

0<\/p>\n<\/td>\n<\/tr>\n

\n

4865<\/p>\n<\/th>\n

\n

13<\/p>\n<\/td>\n

\n

98.00<\/p>\n<\/td>\n

\n

1237.85<\/p>\n<\/td>\n

\n

Male<\/p>\n<\/td>\n

\n

1<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

Fiber optic<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

No<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Month-to-month<\/p>\n<\/td>\n

\n

Yes<\/p>\n<\/td>\n

\n

Electronic check<\/p>\n<\/td>\n

\n

1<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n

\u041a\u0430\u043a \u0432\u0438\u0434\u0438\u043c, \u0443 \u043d\u0430\u0441 \u0435\u0441\u0442\u044c 20 \u043a\u043e\u043b\u043e\u043d\u043e\u043a, \u0432 \u043a\u043e\u0442\u043e\u0440\u044b\u0445 \u0437\u0430\u043f\u0438\u0441\u0430\u043d\u0430 \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u044f \u043e \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u044f\u0445. \u041d\u0430\u043c \u043d\u0443\u0436\u043d\u043e \u043f\u043e\u043d\u044f\u0442\u044c, \u043a\u0430\u043a\u0438\u0435 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0438 \u0447\u0430\u0449\u0435 \u0432\u0441\u0435\u0433\u043e \u0443\u0445\u043e\u0434\u044f\u0442 \u043a \u0434\u0440\u0443\u0433\u043e\u043c\u0443 \u043e\u043f\u0435\u0440\u0430\u0442\u043e\u0440\u0443, \u0430 \u043a\u0430\u043a\u0438\u0435 \u043e\u0441\u0442\u0430\u044e\u0442\u0441\u044f. \u0414\u043b\u044f \u043d\u0430\u0447\u0430\u043b\u0430 \u043d\u0430 \u0431\u0443\u0434\u0443\u0449\u0435\u0435 \u0440\u0430\u0437\u043c\u0435\u0442\u0438\u043c \u043a\u043e\u043b\u043e\u043d\u043a\u0438, \u0447\u0430\u0441\u0442\u044c \u0438\u0437 \u043d\u0438\u0445 \u043d\u0430\u043c \u043d\u0443\u0436\u043d\u043e \u043e\u0431\u043e\u0437\u043d\u0430\u0447\u0438\u0442\u044c \u043a\u0430\u043a \u043a\u0430\u0442\u0435\u0433\u043e\u0440\u0438\u0430\u043b\u044c\u043d\u044b\u0435(\u0442\u0435\u043a\u0441\u0442\u043e\u0432\u044b\u0435), \u0430 \u0447\u0430\u0441\u0442\u044c — \u043a\u0430\u043a \u0447\u0438\u0441\u043b\u043e\u0432\u044b\u0435. \u041a\u043e\u043b\u043e\u043d\u043a\u0443 Churn \u043e\u0431\u043e\u0437\u043d\u0430\u0447\u0438\u043c \u043a\u0430\u043a \u0446\u0435\u043b\u044c \u043d\u0430\u0448\u0438\u0445 \u043f\u0440\u0435\u0434\u0441\u043a\u0430\u0437\u0430\u043d\u0438\u0439. <\/p>\n

num_cols = [     \"ClientPeriod\",     \"MonthlySpending\",     \"TotalSpent\", ]  cat_cols = [     \"Sex\",     \"IsSeniorCitizen\",     \"HasPartner\",     \"HasChild\",     \"HasPhoneService\",     \"HasMultiplePhoneNumbers\",     \"HasInternetService\",     \"HasOnlineSecurityService\",     \"HasOnlineBackup\",     \"HasDeviceProtection\",     \"HasTechSupportAccess\",     \"HasOnlineTV\",     \"HasMovieSubscription\",     \"HasContractPhone\",     \"IsBillingPaperless\",     \"PaymentMethod\", ]  target = 'Churn'<\/code><\/pre>\n
\u0417\u0430\u0442\u0435\u043c \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u0440\u043e\u0432\u0435\u0440\u0438\u043c, \u0435\u0441\u0442\u044c \u043b\u0438 \u043f\u043e\u0432\u0442\u043e\u0440\u044f\u044e\u0449\u0438\u0435\u0441\u044f \u0437\u0430\u043f\u0438\u0441\u0438<\/p>\n
print(f\"Duplicated rows: {data.duplicated(keep=False).sum()}\") print(f\"Duplicated rows without target: {data.drop(target, axis=1).duplicated(keep=False).sum()}\") <\/code><\/pre>\n
\n
Duplicated rows: 28 <\/p>\n
Duplicated rows without target: 41 <\/p>\n<\/blockquote>\n
\u0412\u0438\u0434\u0438\u043c, \u0447\u0442\u043e \u0443 \u043d\u0430\u0441 28 \u043e\u0434\u0438\u043d\u0430\u043a\u043e\u0432\u044b\u0439 \u0441\u0442\u0440\u043e\u043a, \u0435\u0441\u043b\u0438 \u0443\u0447\u0438\u0442\u044b\u0432\u0430\u0442\u044c \u0446\u0435\u043b\u0435\u0432\u0443\u044e Chern \u0438 41 \u043e\u0434\u0438\u043d\u0430\u043a\u043e\u0432\u0430\u044f \u0441\u0442\u0440\u043e\u043a\u0430, \u0435\u0441\u043b\u0438 \u043d\u0435 \u0443\u0447\u0438\u0442\u044b\u0432\u0430\u0442\u044c. \u042d\u0442\u043e \u0437\u043d\u0430\u0447\u0438\u0442, \u0447\u0442\u043e \u0443 \u043d\u0430\u0441 \u0435\u0441\u0442\u044c \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u043e\u0435 \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u043e\u0434\u0438\u043d\u0430\u043a\u043e\u0432\u044b\u0445 \u0437\u0430\u043f\u0438\u0441\u0435\u0439 \u0441 \u0440\u0430\u0437\u043d\u044b\u043c \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u043e\u043c. \u0422\u0430\u043a\u0438\u0435 \u0441\u0442\u0440\u043e\u0447\u043a\u0438 \u0432\u0440\u0435\u0434\u043d\u044b \u0434\u043b\u044f \u043c\u043e\u0434\u0435\u043b\u0435\u0439, \u043f\u043e\u0441\u043a\u043e\u043b\u044c\u043a\u0443 \u043d\u0435 \u0434\u0430\u044e\u0442 \u0447\u0435\u0442\u043a\u043e\u0433\u043e \u0440\u0430\u0437\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u043a\u043b\u0430\u0441\u0441\u043e\u0432, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u043c\u044b \u0438\u0445 \u0443\u0434\u0430\u043b\u044f\u0435\u043c.<\/p>\n
data[data.drop(target, axis=1).duplicated(keep=False)].sort_values(by=[*data.columns])<\/code><\/pre>\n
\u0414\u0430\u043b\u0435\u0435 \u043d\u0430\u043c \u043d\u0443\u0436\u043d\u043e \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0435\u0442\u044c, \u0435\u0441\u0442\u044c \u043b\u0438 \u043f\u0440\u043e\u043f\u0443\u0449\u0435\u043d\u043d\u044b\u0435 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f \u0432 \u0434\u0430\u0442\u0430\u0441\u0435\u0442\u0435. \u0412 \u043d\u0430\u0448\u0435\u043c \u0441\u043b\u0443\u0447\u0430\u0435 \u043a\u0440\u043e\u043c\u0435 NaN \u043d\u0430 \u043c\u0435\u0441\u0442\u0435 \u043f\u0440\u043e\u043f\u0443\u0441\u043a\u043e\u0432 \u0431\u044b\u043b \u0435\u0449\u0435 \u0438 \u043f\u0440\u043e\u0431\u0435\u043b: » «. \u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043d\u0430\u0439\u0434\u0435\u043c, \u0433\u0434\u0435 \u0438\u043c\u0435\u043d\u043d\u043e \u043e\u043d\u0438 \u0431\u044b\u043b\u0438<\/p>\n
data.replace(\" \", np.nan, inplace=True) X_test.replace(\" \", np.nan, inplace=True) pd.DataFrame(data.isna().sum(), columns=[\"NaN Count\"]) \\     .sort_values(\"NaN Count\") \\     .plot(kind=\"barh\", legend=False, figsize=(12, 8));<\/code><\/pre>\n
<\/figcaption><\/figure>\n
\u041f\u043e\u043b\u0443\u0447\u0430\u0435\u043c 9 NaN \u0432 \u0441\u0442\u043e\u043b\u0431\u0446\u0435 TotalSpent. \u0420\u0430\u0441\u0441\u043c\u043e\u0442\u0440\u0438\u043c \u044d\u0442\u0438\u0445 \u043a\u043b\u0438\u0435\u043d\u0442\u043e\u0432 \u043f\u043e\u0434\u0440\u043e\u0431\u043d\u0435\u0435.<\/p>\n
\n
\n\n\n\n\n\n\n\n\n\n\n\n\n\n
\n
<\/p>\n<\/th>\n
\n
ClientPeriod<\/p>\n<\/th>\n
\n
MonthlySpending<\/p>\n<\/th>\n
\n
TotalSpent<\/p>\n<\/th>\n
\n
Sex<\/p>\n<\/th>\n
\n
IsSeniorCitizen<\/p>\n<\/th>\n
\n
HasPartner<\/p>\n<\/th>\n
\n
HasChild<\/p>\n<\/th>\n
\n
HasPhoneService<\/p>\n<\/th>\n
\n
HasMultiplePhoneNumbers<\/p>\n<\/th>\n
\n
HasInternetService<\/p>\n<\/th>\n
\n
HasOnlineSecurityService<\/p>\n<\/th>\n
\n
HasOnlineBackup<\/p>\n<\/th>\n
\n
HasDeviceProtection<\/p>\n<\/th>\n
\n
HasTechSupportAccess<\/p>\n<\/th>\n
\n
HasOnlineTV<\/p>\n<\/th>\n
\n
HasMovieSubscription<\/p>\n<\/th>\n
\n
HasContractPhone<\/p>\n<\/th>\n
\n
IsBillingPaperless<\/p>\n<\/th>\n
\n
PaymentMethod<\/p>\n<\/th>\n
\n
Churn<\/p>\n<\/th>\n<\/tr>\n
\n
1157<\/p>\n<\/th>\n
\n
11<\/p>\n<\/td>\n
\n
94.20<\/p>\n<\/td>\n
\n
999.9<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Fiber optic<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Month-to-month<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Electronic check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
1048<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
25.75<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Male<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
1707<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
73.35<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
DSL<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
2543<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
19.70<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Male<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
One year<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
3078<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
80.85<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
DSL<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
3697<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
20.00<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
4002<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
61.90<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Male<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
DSL<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Bank transfer (automatic)<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
4326<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
25.35<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Male<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
4551<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
52.55<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No phone service<\/p>\n<\/td>\n
\n
DSL<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Bank transfer (automatic)<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
4598<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
56.05<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No phone service<\/p>\n<\/td>\n
\n
DSL<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Credit card (automatic)<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n
\u041e\u0447\u0435\u0432\u0438\u0434\u043d\u043e, \u044d\u0442\u043e \u043d\u043e\u0432\u044b\u0435 \u043a\u043b\u0438\u0435\u043d\u0442\u044b, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0435\u0449\u0435 \u043d\u0435 \u0432\u043d\u0435\u0441\u043b\u0438 \u043f\u0435\u0440\u0432\u044b\u0439 \u043f\u043b\u0430\u0442\u0435\u0436. \u0417\u0430\u043f\u043e\u043b\u043d\u0438\u043c \u0438\u0445 \u043d\u0443\u043b\u044f\u043c\u0438.  <\/p>\n
data[\"TotalSpent\"] = data.TotalSpent.fillna(0).astype(float) X_test[\"TotalSpent\"] = X_test.TotalSpent.fillna(0).astype(float)<\/code><\/pre>\n
\u0417\u0430\u0442\u0435\u043c \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u043c, \u043a\u0430\u043a \u0443 \u043d\u0430\u0441 \u0440\u0430\u0441\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u044b \u0434\u0430\u043d\u043d\u044b\u0435 <\/p>\n
fig, axes = plt.subplots(5, 4, figsize=(25, 20)) for ax, col in zip(axes.flatten(), data.columns):   ax.set_title(col)   if col in cat_cols or col == target:     ax.pie(data[col].value_counts(), autopct=\"%1.1f%%\", labels=data[col].value_counts().index)     else:       data[col].plot(kind=\"hist\", ec=\"black\", ax=ax)<\/code><\/pre>\n
<\/figcaption><\/figure>\n
\u041d\u0430 \u0433\u0440\u0430\u0444\u0438\u043a\u0435 Churn \u0432 \u043f\u0440\u0430\u0432\u043e\u043c \u043d\u0438\u0436\u043d\u0435\u043c \u0443\u0433\u043b\u0443 \u0432\u0438\u0434\u043d\u043e, \u0447\u0442\u043e \u043a\u043b\u0430\u0441\u0441 1 \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d \u0447\u0435\u0442\u0432\u0435\u0440\u0442\u044c\u044e \u0434\u0430\u043d\u043d\u044b\u0445. \u042d\u0442\u043e \u043e\u0437\u043d\u0430\u0447\u0430\u0435\u0442, \u0447\u0442\u043e \u043b\u044e\u0434\u0438 \u0432 \u0442\u0440\u0438 \u0440\u0430\u0437\u0430 \u0447\u0430\u0449\u0435 \u043e\u0441\u0442\u0430\u044e\u0442\u0441\u044f, \u0447\u0435\u043c \u0443\u0445\u043e\u0434\u044f\u0442. \u041c\u043d\u043e\u0433\u0438\u0435 \u0441\u0442\u043e\u043b\u0431\u0446\u044b \u0438\u043c\u0435\u044e\u0442 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f \u00abNo internet service\u00bb \u0438 \u00abNo Phone service\u00bb. \u041f\u043e\u0441\u043a\u043e\u043b\u044c\u043a\u0443 \u0443 \u043d\u0430\u0441 \u0443\u0436\u0435 \u0435\u0441\u0442\u044c \u0444\u0443\u043d\u043a\u0446\u0438\u0438 \u00abHasPhoneService\u00bb \u0438 \u00abHasInternetService\u00bb \u044d\u0442\u0430 \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u044f \u0438\u0437\u0431\u044b\u0442\u043e\u0447\u043d\u0430. \u041c\u044b \u043c\u043e\u0436\u0435\u043c \u043e\u0431\u044a\u0435\u0434\u0438\u043d\u0438\u0442\u044c \u0438\u0445 \u0441 \u043e\u043f\u0446\u0438\u0435\u0439 \u00abNo\u00bb.<\/p>\n
\u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u043e\u0438\u0449\u0435\u043c \u0437\u0430\u043a\u043e\u043d\u043e\u043c\u0435\u0440\u043d\u043e\u0441\u0442\u0438 \u0432 \u0434\u0430\u043d\u043d\u044b\u0445<\/h3>\n
\u041c\u0435\u0436\u0434\u0443 Churn \u0438 PaymentMethod<\/h4>\n
tmp = data.groupby(\"PaymentMethod\", as_index=False).agg({\"Churn\": [\"sum\", \"count\"]}) tmp[\"Churn (%)\"] = 100 * tmp[\"Churn\", \"sum\"] \/ tmp[\"Churn\", \"count\"] tmp.sort_values(\"Churn (%)\").reset_index(drop=True)<\/code><\/pre>\n
\n
\n\n\n\n\n\n\n\n\n
\n
<\/p>\n<\/th>\n
\n
PaymentMethod<\/p>\n<\/th>\n
\n
Churn<\/p>\n<\/th>\n
\n
Churn (%)<\/p>\n<\/th>\n<\/tr>\n
\n
<\/p>\n<\/th>\n
\n
<\/p>\n<\/th>\n
\n
sum<\/p>\n<\/th>\n
\n
count<\/p>\n<\/th>\n
\n
<\/p>\n<\/th>\n<\/tr>\n
\n
0<\/p>\n<\/th>\n
\n
Credit card (automatic)<\/p>\n<\/td>\n
\n
165<\/p>\n<\/td>\n
\n
1143<\/p>\n<\/td>\n
\n
14.435696<\/p>\n<\/td>\n<\/tr>\n
\n
1<\/p>\n<\/th>\n
\n
Bank transfer (automatic)<\/p>\n<\/td>\n
\n
195<\/p>\n<\/td>\n
\n
1159<\/p>\n<\/td>\n
\n
16.824849<\/p>\n<\/td>\n<\/tr>\n
\n
2<\/p>\n<\/th>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
230<\/p>\n<\/td>\n
\n
1194<\/p>\n<\/td>\n
\n
19.262982<\/p>\n<\/td>\n<\/tr>\n
\n
3<\/p>\n<\/th>\n
\n
Electronic check<\/p>\n<\/td>\n
\n
794<\/p>\n<\/td>\n
\n
1786<\/p>\n<\/td>\n
\n
44.456887<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n
\u0412\u0438\u0434\u0438\u043c, \u0447\u0442\u043e \u0440\u0430\u0437\u043d\u0438\u0446\u0430 \u043c\u0435\u0436\u0434\u0443 \u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u044b\u043c \u0447\u0435\u043a\u043e\u043c \u0438 \u0434\u0440\u0443\u0433\u0438\u043c\u0438 \u0441\u043f\u043e\u0441\u043e\u0431\u0430\u043c\u0438 \u043e\u043f\u043b\u0430\u0442\u044b \u0433\u043e\u0440\u0430\u0437\u0434\u043e \u0431\u043e\u043b\u044c\u0448\u0435, \u0447\u0435\u043c \u043c\u0435\u0436\u0434\u0443 \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u0438 \u043d\u0435\u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u043c.<\/p>\n
\u041c\u0435\u0436\u0434\u0443 Churn \u0438 HasContractPhone<\/h4>\n
tmp = data.groupby(\"HasContractPhone\", as_index=False).agg({\"Churn\": [\"sum\", \"count\"]}) tmp[\"Churn (%)\"] = 100 * tmp[\"Churn\", \"sum\"] \/ tmp[\"Churn\", \"count\"] tmp.sort_values(\"Churn (%)\").reset_index(drop=True)<\/code><\/pre>\n
\n
\n\n\n\n\n\n\n\n
\n
<\/p>\n<\/th>\n
\n
HasContractPhone<\/p>\n<\/th>\n
\n
Churn<\/p>\n<\/th>\n
\n
Churn (%)<\/p>\n<\/th>\n<\/tr>\n
\n
<\/p>\n<\/th>\n
\n
<\/p>\n<\/th>\n
\n
sum<\/p>\n<\/th>\n
\n
count<\/p>\n<\/th>\n
\n
<\/p>\n<\/th>\n<\/tr>\n
\n
0<\/p>\n<\/th>\n
\n
Two year<\/p>\n<\/td>\n
\n
33<\/p>\n<\/td>\n
\n
1280<\/p>\n<\/td>\n
\n
2.578125<\/p>\n<\/td>\n<\/tr>\n
\n
1<\/p>\n<\/th>\n
\n
One year<\/p>\n<\/td>\n
\n
120<\/p>\n<\/td>\n
\n
1082<\/p>\n<\/td>\n
\n
11.090573<\/p>\n<\/td>\n<\/tr>\n
\n
2<\/p>\n<\/th>\n
\n
Month-to-month<\/p>\n<\/td>\n
\n
1231<\/p>\n<\/td>\n
\n
2920<\/p>\n<\/td>\n
\n
42.157534<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n
\u0418\u043d\u0430\u0447\u0435 \u0433\u043e\u0432\u043e\u0440\u044f, \u043b\u044e\u0434\u0438 \u0440\u0435\u0434\u043a\u043e \u0440\u0430\u0437\u0440\u044b\u0432\u0430\u044e\u0442 \u0434\u043e\u043b\u0433\u043e\u0441\u0440\u043e\u0447\u043d\u044b\u0435 \u0442\u0435\u043b\u0435\u0444\u043e\u043d\u043d\u044b\u0435 \u043a\u043e\u043d\u0442\u0440\u0430\u043a\u0442\u044b<\/p>\n
\u041c\u0435\u0436\u0434\u0443 Churn \u0438 HasInternetService <\/h4>\n
tmp = data.groupby(\"HasInternetService\", as_index=False).agg({\"Churn\": [\"sum\", \"count\"]}) tmp[\"Churn (%)\"] = 100 * tmp[\"Churn\", \"sum\"] \/ tmp[\"Churn\", \"count\"] tmp.sort_values(\"Churn (%)\").reset_index(drop=True)<\/code><\/pre>\n
\n
\n\n\n\n\n\n\n\n
\n<\/th>\n\n
HasInternetService<\/p>\n<\/th>\n
\n
Churn<\/p>\n<\/th>\n
\n
Churn (%)<\/p>\n<\/th>\n<\/tr>\n
\n<\/th>\n\n<\/th>\n\n
sum<\/p>\n<\/th>\n
\n
count<\/p>\n<\/th>\n
\n<\/th>\n<\/tr>\n
\n
0<\/p>\n<\/th>\n
\n
No<\/p>\n<\/td>\n
\n
82<\/p>\n<\/td>\n
\n
1141<\/p>\n<\/td>\n
\n
7.186678<\/p>\n<\/td>\n<\/tr>\n
\n
1<\/p>\n<\/th>\n
\n
DSL<\/p>\n<\/td>\n
\n
342<\/p>\n<\/td>\n
\n
1800<\/p>\n<\/td>\n
\n
19.000000<\/p>\n<\/td>\n<\/tr>\n
\n
2<\/p>\n<\/th>\n
\n
Fiber optic<\/p>\n<\/td>\n
\n
960<\/p>\n<\/td>\n
\n
2341<\/p>\n<\/td>\n
\n
41.008116<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n
\u041b\u044e\u0434\u0438 \u0441 Fiber optic \u0447\u0430\u0449\u0435 \u043d\u0435\u0434\u043e\u0432\u043e\u043b\u044c\u043d\u044b \u0443\u0441\u043b\u0443\u0433\u0430\u043c\u0438 \u043f\u0440\u043e\u0432\u0430\u0439\u0434\u0435\u0440\u0430, \u0447\u0435\u043c \u043e\u0441\u0442\u0430\u043b\u044c\u043d\u044b\u0435 <\/p>\n
\u041c\u0435\u0436\u0434\u0443 Churn \u0438 \u0421lientPeriod<\/h4>\n
sns.catplot(data=data, x=\"ClientPeriod\", hue=\"Churn\", kind=\"count\", height=8, aspect=20\/8) plt.xticks(rotation=45);<\/code><\/pre>\n
\"\u0417\u0430\u0432\u0438\u0441\u0438\u043c\u043e\u0441\u0442\u044c
\u0417\u0430\u0432\u0438\u0441\u0438\u043c\u043e\u0441\u0442\u044c \u043c\u0435\u0436\u0434\u0443 \u043b\u043e\u044f\u043b\u044c\u043d\u043e\u0441\u0442\u044c\u044e \u0438 \u0432\u0440\u0435\u043c\u0435\u043d\u0435\u043c \u043a\u043b\u0438\u0435\u043d\u0442\u0441\u043a\u043e\u0433\u043e \u043f\u0435\u0440\u0438\u043e\u0434\u0430<\/figcaption><\/figure>\n
\u0412\u0438\u0434\u043d\u043e, \u0447\u0442\u043e \u043d\u043e\u0432\u044b\u0435 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0438 \u0447\u0430\u0441\u0442\u043e \u0443\u0445\u043e\u0434\u044f\u0442 \u043f\u043e\u0441\u043b\u0435 \u043f\u0435\u0440\u0432\u043e\u0433\u043e \u043c\u0435\u0441\u044f\u0446\u0430 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f, \u0430 \u043f\u043e\u0441\u0442\u043e\u044f\u043d\u043d\u044b\u0435 \u043a\u043b\u0438\u0435\u043d\u0442\u044b \u043e\u0441\u0442\u0430\u044e\u0442\u0441\u044f \u0432\u0435\u0440\u043d\u044b \u043f\u0440\u0438\u0432\u044b\u0447\u043a\u0430\u043c. <\/p>\n
\u041f\u0440\u0435\u043e\u0431\u0440\u0430\u0437\u0443\u0435\u043c \u043a\u0430\u0442\u0435\u0433\u043e\u0440\u0438\u0430\u043b\u044c\u043d\u044b\u0435 \u043f\u0440\u0438\u0437\u043d\u0430\u043a\u0438 \u0432 \u0442\u0438\u043f int \u0441\u043e\u0433\u043b\u0430\u0441\u043d\u043e \u043d\u0430\u0431\u043b\u044e\u0434\u0435\u043d\u0438\u044f\u043c. \u0422.\u0435. \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f \u00abNo internet service\u00bb \u0438 \u00abNo phone service\u00bb \u043f\u043e\u043b\u0443\u0447\u0430\u044e\u0442 0, \u0442\u0430\u043a \u0436\u0435, \u043a\u0430\u043a \u0438 \u00abNo\u00bb. \u0417\u043d\u0430\u0447\u0435\u043d\u0438\u044f \u0432 \u00abPaymentMethod\u00bb \u0438 \u00abHadContractPhone\u00bb \u0431\u0443\u0434\u0443\u0442 \u043f\u0440\u043e\u043d\u0443\u043c\u0435\u0440\u043e\u0432\u0430\u043d\u044b \u0432 \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0438\u0438 \u0441 \u0438\u0445 \u043a\u043e\u0440\u0440\u0435\u043b\u044f\u0446\u0438\u0435\u0439 \u0441 Chern. \u0414\u0432\u043e\u0438\u0447\u043d\u044b\u043c \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f\u043c \u0431\u0443\u0434\u0443\u0442 \u043f\u0440\u0438\u0441\u0432\u043e\u0435\u043d\u044b 0 \u0438 1.<\/p>\n
patterns = {     \"No\": 0,     \"No internet service\": 0,     \"No phone service\": 0,     \"Yes\": 1,     \"Male\": 0,     \"Female\": 1,     \"DSL\": 1,     \"Fiber optic\": 2,     \"Month-to-month\": 0,     \"One year\": 1,     \"Two year\": 2,     \"Credit card (automatic)\": 0,     \"Bank transfer (automatic)\": 1,     \"Mailed check\": 2,     \"Electronic check\": 3, } X_train = data.replace(patterns).drop(target, axis=1) y_train = data[target] X_test = X_test.replace(patterns)<\/code><\/pre>\n
\u0422\u0435\u043f\u0435\u0440\u044c \u043c\u044b \u043c\u043e\u0436\u0435\u043c \u043f\u043e\u0441\u0442\u0440\u043e\u0438\u0442\u044c \u0442\u0435\u043f\u043b\u043e\u0432\u0443\u044e \u043a\u043e\u0440\u0440\u0435\u043b\u044f\u0446\u0438\u043e\u043d\u043d\u0443\u044e \u043c\u0430\u0442\u0440\u0438\u0446\u0443<\/p>\n
sns.heatmap(data=pd.concat([X_train, y_train], axis=1).corr(),             annot=True,             cmap=\"coolwarm\",             center=0,             ax=plt.subplots(figsize=(15,10))[1]);<\/code><\/pre>\n
\"\u0422\u0435\u043f\u043b\u043e\u0432\u0430\u044f
\u0422\u0435\u043f\u043b\u043e\u0432\u0430\u044f \u043a\u043e\u0440\u0440\u0435\u043b\u044f\u0446\u0438\u043e\u043d\u043d\u0430\u044f \u043c\u0430\u0442\u0440\u0438\u0446\u0430<\/figcaption><\/figure>\n
\u041d\u0430\u043a\u043e\u043d\u0435\u0446, \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u0432\u0438\u0437\u0443\u0430\u043b\u0438\u0437\u0438\u0440\u0443\u0435\u043c \u0434\u0430\u043d\u043d\u044b\u0435 \u043f\u043e\u0441\u043b\u0435 \u0443\u043c\u0435\u043d\u044c\u0448\u0435\u043d\u0438\u044f \u0438\u0445 \u0440\u0430\u0437\u043c\u0435\u0440\u043d\u043e\u0441\u0442\u0438 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e PCA.<\/p>\n
pca = PCA(n_components=2) pca.fit(X_train_std) x0, x1 = pca.components_ sns.set(font_scale=1.5) y = data[\"Churn\"].map({0: False, 1: True}) fig = sns.pairplot(data=pd.concat([pd.DataFrame(data=X_train_std @ np.stack([x0, x1]).T, columns=[\"PC1\", \"PC2\"]), y], axis=1),                    x_vars=\"PC1\",                    y_vars=\"PC2\",                    hue=\"Churn\",                    markers=('^', 's'),                    palette=[\"blue\", \"red\"],                    plot_kws={'s': 100, 'alpha': 0.5},                    height=6) fig.set(title=\"Customer churn visialization (PCA)\") fig.axes[0][0].axhline(y=0, color='black', lw=3, alpha=0.1) fig.axes[0][0].axvline(x=0, color='black', lw=3, alpha=0.1);<\/code><\/pre>\n
<\/figcaption><\/figure>\n
\u041c\u044b \u0432\u0438\u0434\u0438\u043c, \u0447\u0442\u043e \u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e \u0433\u0440\u0443\u0431\u043e \u0440\u0430\u0437\u0434\u0435\u043b\u0438\u0442\u044c \u043a\u043b\u0430\u0441\u0441\u044b \u043f\u0440\u044f\u043c\u043e\u0439 \u043b\u0438\u043d\u0438\u0435\u0439. \u0422\u0430\u043a \u0447\u0442\u043e \u0441\u0442\u0430\u0440\u0430\u044f \u0434\u043e\u0431\u0440\u0430\u044f \u043b\u043e\u0433\u0438\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u0430\u044f \u0440\u0435\u0433\u0440\u0435\u0441\u0441\u0438\u044f, \u0432\u0435\u0440\u043e\u044f\u0442\u043d\u043e, \u043f\u043e\u0434\u043e\u0439\u0434\u0435\u0442. \u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u0440\u043e\u0432\u0435\u0440\u0438\u043c \u0435\u0433\u043e \u0438 \u0441\u0440\u0430\u0432\u043d\u0438\u043c \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b \u0441 \u0434\u0440\u0443\u0433\u0438\u043c\u0438 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0430\u043c\u0438.<\/p>\n
\u041e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 \u043c\u043e\u0434\u0435\u043b\u0435\u0439<\/h2>\n
\u041b\u043e\u0433\u0438\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u0430\u044f \u0440\u0435\u0433\u0440\u0435\u0441\u0441\u0438\u044f<\/h3>\n
\u0414\u043b\u044f \u0442\u043e\u0433\u043e \u0447\u0442\u043e\u0431\u044b \u043a\u0430\u043a\u0430\u044f-\u043b\u0438\u0431\u043e \u043c\u043e\u0434\u0435\u043b\u044c \u0434\u0430\u0432\u0430\u043b\u0430 \u043d\u0430\u0438\u043b\u0443\u0447\u0448\u0438\u0439 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442, \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e \u043f\u0440\u0430\u0432\u0438\u043b\u044c\u043d\u043e \u043f\u043e\u0434\u043e\u0431\u0440\u0430\u0442\u044c \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b \u043c\u043e\u0434\u0435\u043b\u0438. \u041e\u0431\u044b\u0447\u043d\u043e \u0434\u043b\u044f \u044d\u0442\u043e\u0433\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0442 GridSearchCV, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438 \u043f\u0435\u0440\u0435\u0431\u0438\u0440\u0430\u0435\u0442 \u0432\u0430\u0440\u0438\u0430\u043d\u0442\u044b \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432 \u0432 \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u043e\u043c \u0434\u0438\u0430\u043f\u0430\u0437\u043e\u043d\u0435.<\/p>\n
PARAMS = {     \"model__C\": np.arange(0.001, 100, 0.001)#\u0441\u0442\u0430\u0432\u0438\u043c \u0434\u0438\u0430\u043f\u0430\u0437\u043e\u043d \u043e\u0442 0.001 \u0434\u043e 100 \u0441 \u0448\u0430\u0433\u043e\u043c 0.001 } clf = Pipeline(steps=[     (\"scaler\", StandardScaler()),     (\"model\", LogisticRegression(penalty=\"l1\", solver=\"saga\", max_iter=1000, random_state=42)), ]) grid_search = GridSearchCV(     estimator=clf,     param_grid=PARAMS,     scoring=\"roc_auc\",     n_jobs=-1,     cv=10,     refit=True, ) logreg = grid_search.fit(X_train, y_train)<\/code><\/pre>\n
\u0417\u0430\u0442\u0435\u043c \u043c\u044b \u043c\u043e\u0436\u0435\u043c \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0435\u0442\u044c \u043b\u0443\u0447\u0448\u0438\u0435 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b \u0434\u043b\u044f \u0434\u0430\u043d\u043d\u043e\u0439 \u043c\u043e\u0434\u0435\u043b\u0438 \u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0438\u0445 \u0432 \u0434\u0430\u043b\u044c\u043d\u0435\u0439\u0448\u0435\u043c<\/p>\n
print(f\"best score: {logreg.best_score_}\") print(f\"best params: {logreg.best_params_}\")<\/code><\/pre>\n
\n
best score: 0.8451031617037706 <\/p>\n
best params: {‘model__C’: 1.734}<\/p>\n<\/blockquote>\n
\u041d\u0435\u043f\u043b\u043e\u0445\u043e\u0439 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0434\u043b\u044f \u043f\u0440\u044f\u043c\u043e\u0439 \u043b\u0438\u043d\u0438\u0438 \ud83d\ude42 , \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u0436\u0435 \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u043c, \u0447\u0442\u043e \u043d\u0430\u043c \u043e\u0442\u0432\u0435\u0442\u0438\u0442 Kaggle!<\/p>\n
\"\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442
\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0434\u043b\u044f \u043b\u043e\u0433\u0438\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0439 \u0440\u0435\u0433\u0440\u0435\u0441\u0441\u0438\u0438<\/figcaption><\/figure>\n
\u041c\u0434\u0430\u0430\u0430\u0430, \u0434\u043b\u044f \u044d\u0442\u043e\u0433\u043e \u0441\u043e\u0440\u0435\u0432\u043d\u043e\u0432\u0430\u043d\u0438\u044f \u044f\u0432\u043d\u043e \u043d\u0435\u0434\u043e\u0441\u0442\u0430\u0442\u043e\u0447\u043d\u043e, \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u043e\u043f\u0440\u043e\u0431\u0443\u0435\u043c \u0434\u0440\u0443\u0433\u0438\u0435 \u043c\u043e\u0434\u0435\u043b\u0438.<\/p>\n
KNN<\/h3>\n
KNN — \u044d\u0442\u043e \u043c\u0435\u0442\u043e\u0434 \u043a\u043b\u0430\u0441\u0441\u0438\u0444\u0438\u043a\u0430\u0446\u0438\u0438, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u043e\u0441\u043d\u043e\u0432\u0430\u043d \u043d\u0430 \u043f\u0440\u0438\u043d\u0446\u0438\u043f\u0435 \u043f\u043e\u0438\u0441\u043a\u0430 \u0431\u043b\u0438\u0436\u0430\u0439\u0448\u0438\u0445 \u0441\u043e\u0441\u0435\u0434\u0435\u0439, \u0435\u0433\u043e \u0447\u0430\u0441\u0442\u043e \u043f\u0440\u0438\u043c\u0435\u043d\u044f\u044e\u0442 \u0432 \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u0445 \u0437\u0430\u0434\u0430\u0447\u0430\u0445 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f. \u041f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u043c, \u043a\u0430\u043a \u043e\u043d \u0441\u043f\u0440\u0430\u0432\u0438\u0442\u0441\u044f \u0441 \u0437\u0430\u0434\u0430\u0447\u0435\u0439.<\/p>\n
numeric_transformer = Pipeline(steps=[     (\"scaler\", StandardScaler()) ]) preprocessor = ColumnTransformer(  transformers=[         (\"num\", numeric_transformer, num_cols),#\u0434\u0435\u043b\u0438\u043c \u043d\u0430 \u0447\u0438\u0441\u043b\u043e\u0432\u044b\u0435         (\"cat\", OneHotEncoder(handle_unknown='ignore'), cat_cols)#\u0438 \u043a\u0430\u0442\u0435\u0433\u043e\u0440\u0438\u0430\u043b\u044c\u043d\u044b\u0435, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043f\u0440\u0435\u043e\u0431\u0440\u0430\u0437\u0443\u0435\u043c \u0432 \u0447\u0438\u0441\u043b\u043e\u0432\u044b\u0435 \u0447\u0435\u0440\u0435\u0437 OneHotEncoder     ] ) PARAMS = {#\u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b \u0434\u043b\u044f grid search   \"model__n_neighbors\": range(1, 100),   \"model__metric\": [\"cityblock\", \"cosine\", \"euclidean\", \"l1\", \"l2\", \"manhattan\", \"nan_euclidean\"], } clf = Pipeline(steps=[     (\"preproc\", preprocessor),#\u043d\u0430\u0448\u0438 \u0440\u0430\u0437\u0434\u0435\u043b\u0435\u043d\u043d\u044b\u0435 \u0434\u0430\u043d\u043d\u044b\u0435     (\"model\", KNeighborsClassifier()), ]) grid_search = GridSearchCV( estimator=clf, param_grid=PARAMS, scoring=\"roc_auc\", n_jobs=-1, cv=10, refit=True, ) knn = grid_search.fit(X_train, y_train)<\/code><\/pre>\n
\u0438 \u0441\u043c\u043e\u0442\u0440\u0438\u043c \u043d\u0430 \u043b\u0443\u0447\u0448\u0438\u0435<\/p>\n
print(f\"best score: {knn.best_score_}\") print(f\"best params: {knn.best_params_}\")<\/code><\/pre>\n
\n
best score: 0.8347721646087625 <\/p>\n
best params: {‘model__metric’: ‘manhattan’, ‘model__n_neighbors’: 44}<\/p>\n<\/blockquote>\n
\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u043f\u043e\u0445\u0443\u0436\u0435, \u0447\u0435\u043c \u0443 \u043b\u043e\u0433\u0438\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0439 \u0440\u0435\u0433\u0440\u0435\u0441\u0441\u0438\u0438, \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u043c, \u0447\u0442\u043e \u0441\u043a\u0430\u0436\u0435\u0442 Kaggle<\/p>\n
\"\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442
\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u043d\u0430 Kaggle \u0434\u043b\u044f KNN<\/figcaption><\/figure>\n
\u0414\u0430, \u0441\u0435\u0431\u044f \u043c\u044b \u043d\u0435 \u043f\u0440\u0435\u0432\u0437\u043e\u0448\u043b\u0438, \u043d\u043e \u043d\u0438\u0447\u0435\u0433\u043e, \u043c\u043e\u0434\u0435\u043b\u044c \u043c\u043e\u0436\u0435\u0442 \u043d\u0430\u043c \u043f\u0440\u0438\u0433\u043e\u0434\u0438\u0442\u044c\u0441\u044f \u043f\u0440\u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0438 Stacking \u0432 \u0431\u0443\u0434\u0443\u0449\u0435\u043c.<\/p>\n
Random Forest<\/h3>\n
\u0421\u043b\u0443\u0447\u0430\u0439\u043d\u044b\u0439 \u043b\u0435\u0441 \u0443\u0436\u0435 \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u044f\u0435\u0442 \u0438\u0437 \u0441\u0435\u0431\u044f \u0441\u0435\u0440\u044c\u0435\u0437\u043d\u044b\u0439 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f, \u043f\u0440\u0438 \u043a\u043e\u0442\u043e\u0440\u043e\u043c \u043c\u043d\u043e\u0436\u0435\u0441\u0442\u0432\u043e \u0434\u0435\u0440\u0435\u0432\u044c\u0435\u0432 \u0440\u0435\u0448\u0435\u043d\u0438\u0439 \u0441\u0442\u0440\u043e\u044f\u0442\u0441\u044f \u043d\u0430 \u0440\u0430\u0437\u043d\u044b\u0445 \u0447\u0430\u0441\u0442\u044f\u0445 \u0434\u0430\u043d\u043d\u044b\u0445 \u0438 \u0438\u0445 \u043f\u0440\u043e\u0433\u043d\u043e\u0437\u044b \u043e\u0431\u044a\u0435\u0434\u0438\u043d\u044f\u044e\u0442\u0441\u044f \u0432 \u043e\u0434\u0438\u043d \u043e\u043a\u043e\u043d\u0447\u0430\u0442\u0435\u043b\u044c\u043d\u044b\u0439 \u043f\u0440\u043e\u0433\u043d\u043e\u0437.<\/p>\n
PARAMS = {     \"min_samples_split\": range(2, 200),     \"min_samples_leaf\": range(1, 200), } clf = RandomForestClassifier(n_estimators=200, random_state=42)  grid_search = GridSearchCV(clf, PARAMS, scoring=\"roc_auc\", cv=5) rf = grid_search.fit(X_train, y_train);<\/code><\/pre>\n
\u041a\u043e\u0434 \u043f\u043e\u043b\u0443\u0447\u0438\u043b\u0441\u044f \u0441\u043e\u0432\u0441\u0435\u043c \u043d\u0435\u0431\u043e\u043b\u044c\u0448\u043e\u0439, \u043f\u043e \u0442\u0440\u0430\u0434\u0438\u0446\u0438\u0438 \u0441\u043c\u043e\u0442\u0440\u0438\u043c \u043d\u0430 \u043b\u0443\u0447\u0448\u0438\u0435 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b <\/p>\n
print(f\"Best score: {rf.best_score_}\") print(f\"Best params: {rf.best_params_}\")<\/code><\/pre>\n
\n
Best score: 0.8433171488881694<\/p>\n
Best params: {‘min_samples_leaf’: 18, ‘min_samples_split’: 9}<\/p>\n<\/blockquote>\n
\u0421\u0442\u0440\u0430\u043d\u043d\u043e, \u043d\u0430 \u0442\u0440\u0435\u0439\u043d\u043e\u0432\u044b\u0445 \u0434\u0430\u043d\u043d\u044b\u0445 \u043c\u044b \u043b\u043e\u0433\u0438\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u0443\u044e \u0440\u0435\u0433\u0440\u0435\u0441\u0441\u0438\u044e \u043d\u0435 \u043f\u0440\u0435\u0432\u0437\u043e\u0448\u043b\u0438<\/p>\n
\"\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442
\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u043d\u0430 Kaggle \u0434\u043b\u044f \u0441\u043b\u0443\u0447\u0430\u0439\u043d\u043e\u0433\u043e \u043b\u0435\u0441\u0430<\/figcaption><\/figure>\n
\u0410 \u0432\u043e\u0442 \u043d\u0430 Kaggle \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0441\u0442\u0430\u043b \u0433\u043e\u0440\u0430\u0437\u0434\u043e \u043b\u0443\u0447\u0448\u0435! \u041c\u044b \u0434\u0430\u0436\u0435 \u043f\u0440\u0435\u043e\u0434\u043e\u043b\u0435\u043b\u0438 \u043f\u043e\u0440\u043e\u0433 0.85!<\/p>\n
CatBoost<\/h3>\n
\u0421\u0430\u043c\u043e\u0439 \u0441\u0438\u043b\u044c\u043d\u043e\u0439 \u043c\u043e\u0434\u0435\u043b\u044c\u044e \u043d\u0430 \u0441\u0435\u0433\u043e\u0434\u043d\u044f \u0431\u0443\u0434\u0435\u0442 \u043c\u043e\u0434\u0435\u043b\u044c \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u043d\u043e\u0433\u043e \u0431\u0443\u0441\u0442\u0438\u043d\u0433\u0430 catboost. \u041c\u043e\u0434\u0435\u043b\u0438 \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u043d\u043e\u0433\u043e \u0431\u0443\u0441\u0442\u0438\u043d\u0433\u0430 \u0432\u0441\u0435\u0433\u0434\u0430 \u043c\u043e\u0436\u043d\u043e \u0432\u0441\u0442\u0440\u0435\u0442\u0438\u0442\u044c \u043d\u0430 \u0441\u043e\u0440\u0435\u0432\u043d\u043e\u0432\u0430\u043d\u0438\u044f\u0445, \u0437\u0430\u0447\u0430\u0441\u0442\u0443\u044e \u0432\u0441\u0435 \u0438\u043c\u0435\u043d\u043d\u043e \u0438\u043c\u0438 \u0438 \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0438\u0432\u0430\u0435\u0442\u0441\u044f. \u041e\u0434\u043d\u0430\u043a\u043e \u0447\u0442\u043e\u0431\u044b catboost \u043f\u043e\u043a\u0430\u0437\u044b\u0432\u0430\u043b \u043e\u0442\u043b\u0438\u0447\u043d\u044b\u0439 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442, \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e \u043f\u043e\u0442\u0440\u0430\u0442\u0438\u0442\u044c \u0442\u0443\u0447\u0443 \u0432\u0440\u0435\u043c\u0435\u043d\u0438 \u043d\u0430 \u043f\u043e\u0434\u0431\u043e\u0440 \u0435\u0433\u043e \u0433\u0438\u043f\u0435\u0440\u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432 (\u043f\u043e\u0441\u043a\u043e\u043b\u044c\u043a\u0443 \u043e\u0431\u0443\u0447\u0430\u0442\u044c\u0441\u044f catboost \u0431\u0443\u0434\u0435\u0442 \u0443\u0436\u0435 \u0433\u043e\u0440\u0430\u0437\u0434\u043e \u0434\u043e\u043b\u044c\u0448\u0435 \u043e\u0441\u0442\u0430\u043b\u044c\u043d\u044b\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439). \u0423 \u043c\u043e\u0434\u0435\u043b\u0438 \u0434\u043b\u044f \u044d\u0442\u043e\u0433\u043e \u0435\u0441\u0442\u044c \u0441\u0432\u043e\u0439 \u043e\u0442\u0434\u0435\u043b\u044c\u043d\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 grid_search.<\/p>\n
catboost = CatBoostClassifier(     cat_features=cat_cols,     logging_level=\"Silent\",     eval_metric=\"AUC:hints=skip_train~false\",     grow_policy=\"Lossguide\",     metric_period=1000,     random_seed=0, ) PARAMS = { \"n_estimators\": [5, 10, 20, 30, 40, 50, 70, 100, 150, 200, 250, 300, 500, 1000], \"learning_rate\": [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.02, 0.04, 0.05, 0.1, 0.2, 0.3, 0.5], \"max_depth\": np.arange(4, 20, 1), \"l2_leaf_reg\": np.arange(0.1, 1, 0.05), \"subsample\": [3, 5, 7, 10], \"random_strength\": [1, 2, 5, 10, 20, 50, 100], \"min_data_in_leaf\": np.arange(10, 1001, 10), } catboost.grid_search(PARAMS, X_train, y_train, cv=5, plot=True, refit=True)<\/code><\/pre>\n
\u0418 \u0442\u0430\u043a\u0436\u0435 \u0441\u043c\u043e\u0442\u0440\u0438\u043c \u043d\u0430 \u043b\u0443\u0447\u0448\u0438\u0435 \u0438\u0437 \u043d\u0438\u0445<\/p>\n
print(\"Best score:\", end=' ') pprint(catboost.best_score_) best_params = catboost.get_params() for f in (\"cat_features\", \"logging_level\", \"eval_metric\"):   best_params.pop(f) print(\"Best params:\", end=' ') pprint(best_params)<\/code><\/pre>\n
\n
Best score: {‘learn’: {‘AUC’: 0.8542032782485164, ‘Logloss’: 0.39144271235447}}<\/p>\n
Best params: {‘depth’: 4, ‘grow_policy’: ‘Lossguide’, ‘iterations’: 250, ‘l2_leaf_reg’: 10, ‘learning_rate’: 0.05, ‘metric_period’: 1000, ‘min_data_in_leaf’: 100, ‘random_seed’: 0, ‘random_strength’: 5, ‘subsample’: 0.6}<\/p>\n<\/blockquote>\n
\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0434\u0430\u0436\u0435 \u043b\u0443\u0447\u0448\u0435, \u0447\u0435\u043c \u0443 Random Forest! \u041f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u043c \u0447\u0442\u043e \u0441\u043a\u0430\u0436\u0435\u0442 Kaggle<\/p>\n
\"\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442
\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0434\u043b\u044f CatBoost \u043d\u0430 Kaggle<\/figcaption><\/figure>\n
Stacking<\/h3>\n
\u041a\u0430\u043a \u0433\u043e\u0432\u043e\u0440\u0438\u043b \u041f\u0430\u0432\u0435\u043b \u041f\u043b\u0435\u0441\u043a\u043e\u0432 (\u0433\u0440\u0430\u043d\u0434 \u043c\u0430\u0441\u0442\u0435\u0440 Kaggle) \u0435\u0441\u043b\u0438 \u0432\u044b \u043d\u0430\u0443\u0447\u0438\u0442\u0435\u0441\u044c \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c\u0441\u044f \u0441\u0442\u0435\u0439\u043a\u0438\u043d\u0433\u043e\u043c, \u0431\u0443\u0434\u0435\u0442\u0435 \u0432\u044b\u0438\u0433\u0440\u044b\u0432\u0430\u0442\u044c \u043b\u044e\u0431\u044b\u0435 \u0441\u043e\u0440\u0435\u0432\u043d\u043e\u0432\u0430\u043d\u0438\u044f. \u0421\u0443\u0442\u044c \u043c\u0435\u0442\u043e\u0434\u0430 \u0437\u0430\u043a\u043b\u044e\u0447\u0430\u0435\u0442\u0441\u044f \u0432 \u0442\u043e\u043c, \u0447\u0442\u043e \u043c\u044b \u043e\u0431\u044a\u0435\u0434\u0438\u043d\u044f\u0435\u043c \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b \u0440\u0430\u0431\u043e\u0442\u044b \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0432\u043c\u0435\u0441\u0442\u0435, \u0443\u043b\u0443\u0447\u0448\u0430\u044f \u043d\u0430\u0448 \u043e\u0431\u0449\u0438\u0439 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442.<\/p>\n
meta = CatBoostClassifier(     logging_level='Silent',     eval_metric=\"AUC:hints=skip_train~false\",     metric_period=1000,     random_seed=0,     grow_policy=\"Depthwise\",     l2_leaf_reg=1,     learning_rate=0.08,     max_depth=10,     min_data_in_leaf=10,     n_estimators=10,     random_strength=11,     subsample=0.1, ) stacking = StackingClassifier(     estimators=[         (\"logreg\", logreg),         (\"knn\", knn),         (\"rf\", rf),         (\"catboost\", catboost),     ],     final_estimator=meta,     n_jobs=-1, ) stacking.fit(X_train, y_train)<\/code><\/pre>\n
\u041d\u0443 \u0438, \u043d\u0430\u043a\u043e\u043d\u0435\u0446, \u0444\u0438\u043d\u0430\u043b\u044c\u043d\u044b\u0439 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442. \u0411\u0430\u0440\u0430\u0431\u0430\u043d\u043d\u0430\u044f \u0434\u0440\u043e\u0431\u044c…<\/p>\n
\"\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442
\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0434\u043b\u044f Stacking \u043d\u0430 Kaggle<\/figcaption><\/figure>\n
\u0421\u0443\u043f\u0435\u0440! \u041e\u0442\u043b\u0438\u0447\u043d\u044b\u0439 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442! \u041b\u0438\u0434\u0435\u0440\u0431\u043e\u0440\u0434 \u0434\u043e\u0441\u0442\u0443\u043f\u0435\u043d \u043f\u043e \u0441\u0441\u044b\u043b\u043a\u0435<\/a>.<\/p>\n
\u041f\u043e\u043b\u043d\u044b\u0439 ipynb \u0438\u0449\u0438\u0442\u0435 \u0442\u0443\u0442<\/a>.<\/p>\n<\/div>\n<\/div>\n<\/div>\n
  <\/div>\n
  
 \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438  https:\/\/habr.com\/ru\/post\/715070\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"
<\/div>\n
\n
\n
\n
\n
\u0417\u0434\u0440\u0430\u0432\u0441\u0442\u0432\u0443\u0439\u0442\u0435, \u0432 \u0434\u0430\u043d\u043d\u043e\u0439 \u0441\u0442\u0430\u0442\u044c\u0435 \u044f \u043f\u043e\u0441\u0442\u0430\u0440\u0430\u044e\u0441\u044c \u0440\u0430\u0437\u043e\u0431\u0440\u0430\u0442\u044c \u043e\u0441\u043d\u043e\u0432\u043d\u044b\u0435 \u0448\u0430\u0433\u0438 \u0438 \u043c\u0435\u0442\u043e\u0434\u044b \u0440\u0435\u0448\u0435\u043d\u0438\u044f \u0441\u043e\u0440\u0435\u0432\u043d\u043e\u0432\u0430\u043d\u0438\u0439 \u043d\u0430 Kaggle<\/a> \u043d\u0430 \u043f\u0440\u0438\u043c\u0435\u0440\u0435 \u0440\u0435\u0448\u0435\u043d\u0438\u044f \u043e\u0431\u0443\u0447\u0430\u044e\u0449\u0435\u0433\u043e \u0441\u043e\u0440\u0435\u0432\u043d\u043e\u0432\u0430\u043d\u0438\u044f \u043e\u0442 DeepLearningSchool \u041c\u0424\u0422\u0418 \u043f\u043e \u043f\u0440\u0435\u0434\u0441\u043a\u0430\u0437\u0430\u043d\u0438\u044e \u043e\u0442\u0442\u043e\u043a\u0430 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439. <\/p>\n
\u0420\u0430\u0431\u043e\u0442\u0430 \u0441 \u0434\u0430\u043d\u043d\u044b\u043c\u0438<\/h2>\n
\u041f\u0440\u0435\u0434\u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0430<\/h3>\n
\u0418\u0442\u0430\u043a, \u0434\u043b\u044f \u043d\u0430\u0447\u0430\u043b\u0430 \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u0437\u0430\u0433\u0440\u0443\u0437\u0438\u043c \u043d\u0430\u0448 \u0434\u0430\u0442\u0430\u0441\u0435\u0442 \u0438 \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u043c \u043d\u0430 5 \u0441\u043b\u0443\u0447\u0430\u0439\u043d\u044b\u0445 \u0441\u0442\u0440\u043e\u043a \u0432 \u043d\u0435\u043c.<\/p>\n
\n
\n\n\n\n\n\n\n\n\n
\n
<\/p>\n<\/td>\n
\n
ClientPeriod<\/p>\n<\/th>\n
\n
MonthlySpending<\/p>\n<\/th>\n
\n
TotalSpent<\/p>\n<\/th>\n
\n
Sex<\/p>\n<\/th>\n
\n
IsSeniorCitizen<\/p>\n<\/th>\n
\n
HasPartner<\/p>\n<\/th>\n
\n
HasChild<\/p>\n<\/th>\n
\n
HasPhoneService<\/p>\n<\/th>\n
\n
HasMultiplePhoneNumbers<\/p>\n<\/th>\n
\n
HasInternetService<\/p>\n<\/th>\n
\n
HasOnlineSecurityService<\/p>\n<\/th>\n
\n
HasOnlineBackup<\/p>\n<\/th>\n
\n
HasDeviceProtection<\/p>\n<\/th>\n
\n
HasTechSupportAccess<\/p>\n<\/th>\n
\n
HasOnlineTV<\/p>\n<\/th>\n
\n
HasMovieSubscription<\/p>\n<\/th>\n
\n
HasContractPhone<\/p>\n<\/th>\n
\n
IsBillingPaperless<\/p>\n<\/th>\n
\n
PaymentMethod<\/p>\n<\/th>\n
\n
Churn<\/p>\n<\/th>\n<\/tr>\n
\n
4650<\/p>\n<\/th>\n
\n
66<\/p>\n<\/td>\n
\n
20.35<\/p>\n<\/td>\n
\n
1359.5<\/p>\n<\/td>\n
\n
Male<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
One year<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Electronic check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
29<\/p>\n<\/th>\n
\n
25<\/p>\n<\/td>\n
\n
89.70<\/p>\n<\/td>\n
\n
2187.55<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
1<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Fiber optic<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Month-to-month<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Electronic check<\/p>\n<\/td>\n
\n
1<\/p>\n<\/td>\n<\/tr>\n
\n
1688<\/p>\n<\/th>\n
\n
36<\/p>\n<\/td>\n
\n
76.35<\/p>\n<\/td>\n
\n
2606.35<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
DSL<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
One year<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
2946<\/p>\n<\/th>\n
\n
20<\/p>\n<\/td>\n
\n
19.60<\/p>\n<\/td>\n
\n
356.15<\/p>\n<\/td>\n
\n
Male<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
Month-to-month<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Credit card (automatic)<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
4865<\/p>\n<\/th>\n
\n
13<\/p>\n<\/td>\n
\n
98.00<\/p>\n<\/td>\n
\n
1237.85<\/p>\n<\/td>\n
\n
Male<\/p>\n<\/td>\n
\n
1<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Fiber optic<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Month-to-month<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Electronic check<\/p>\n<\/td>\n
\n
1<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n
\u041a\u0430\u043a \u0432\u0438\u0434\u0438\u043c, \u0443 \u043d\u0430\u0441 \u0435\u0441\u0442\u044c 20 \u043a\u043e\u043b\u043e\u043d\u043e\u043a, \u0432 \u043a\u043e\u0442\u043e\u0440\u044b\u0445 \u0437\u0430\u043f\u0438\u0441\u0430\u043d\u0430 \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u044f \u043e \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u044f\u0445. \u041d\u0430\u043c \u043d\u0443\u0436\u043d\u043e \u043f\u043e\u043d\u044f\u0442\u044c, \u043a\u0430\u043a\u0438\u0435 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0438 \u0447\u0430\u0449\u0435 \u0432\u0441\u0435\u0433\u043e \u0443\u0445\u043e\u0434\u044f\u0442 \u043a \u0434\u0440\u0443\u0433\u043e\u043c\u0443 \u043e\u043f\u0435\u0440\u0430\u0442\u043e\u0440\u0443, \u0430 \u043a\u0430\u043a\u0438\u0435 \u043e\u0441\u0442\u0430\u044e\u0442\u0441\u044f. \u0414\u043b\u044f \u043d\u0430\u0447\u0430\u043b\u0430 \u043d\u0430 \u0431\u0443\u0434\u0443\u0449\u0435\u0435 \u0440\u0430\u0437\u043c\u0435\u0442\u0438\u043c \u043a\u043e\u043b\u043e\u043d\u043a\u0438, \u0447\u0430\u0441\u0442\u044c \u0438\u0437 \u043d\u0438\u0445 \u043d\u0430\u043c \u043d\u0443\u0436\u043d\u043e \u043e\u0431\u043e\u0437\u043d\u0430\u0447\u0438\u0442\u044c \u043a\u0430\u043a \u043a\u0430\u0442\u0435\u0433\u043e\u0440\u0438\u0430\u043b\u044c\u043d\u044b\u0435(\u0442\u0435\u043a\u0441\u0442\u043e\u0432\u044b\u0435), \u0430 \u0447\u0430\u0441\u0442\u044c — \u043a\u0430\u043a \u0447\u0438\u0441\u043b\u043e\u0432\u044b\u0435. \u041a\u043e\u043b\u043e\u043d\u043a\u0443 Churn \u043e\u0431\u043e\u0437\u043d\u0430\u0447\u0438\u043c \u043a\u0430\u043a \u0446\u0435\u043b\u044c \u043d\u0430\u0448\u0438\u0445 \u043f\u0440\u0435\u0434\u0441\u043a\u0430\u0437\u0430\u043d\u0438\u0439. <\/p>\n
num_cols = [     \"ClientPeriod\",     \"MonthlySpending\",     \"TotalSpent\", ]  cat_cols = [     \"Sex\",     \"IsSeniorCitizen\",     \"HasPartner\",     \"HasChild\",     \"HasPhoneService\",     \"HasMultiplePhoneNumbers\",     \"HasInternetService\",     \"HasOnlineSecurityService\",     \"HasOnlineBackup\",     \"HasDeviceProtection\",     \"HasTechSupportAccess\",     \"HasOnlineTV\",     \"HasMovieSubscription\",     \"HasContractPhone\",     \"IsBillingPaperless\",     \"PaymentMethod\", ]  target = 'Churn'<\/code><\/pre>\n
\u0417\u0430\u0442\u0435\u043c \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u0440\u043e\u0432\u0435\u0440\u0438\u043c, \u0435\u0441\u0442\u044c \u043b\u0438 \u043f\u043e\u0432\u0442\u043e\u0440\u044f\u044e\u0449\u0438\u0435\u0441\u044f \u0437\u0430\u043f\u0438\u0441\u0438<\/p>\n
print(f\"Duplicated rows: {data.duplicated(keep=False).sum()}\") print(f\"Duplicated rows without target: {data.drop(target, axis=1).duplicated(keep=False).sum()}\") <\/code><\/pre>\n
\n
Duplicated rows: 28 <\/p>\n
Duplicated rows without target: 41 <\/p>\n<\/blockquote>\n
\u0412\u0438\u0434\u0438\u043c, \u0447\u0442\u043e \u0443 \u043d\u0430\u0441 28 \u043e\u0434\u0438\u043d\u0430\u043a\u043e\u0432\u044b\u0439 \u0441\u0442\u0440\u043e\u043a, \u0435\u0441\u043b\u0438 \u0443\u0447\u0438\u0442\u044b\u0432\u0430\u0442\u044c \u0446\u0435\u043b\u0435\u0432\u0443\u044e Chern \u0438 41 \u043e\u0434\u0438\u043d\u0430\u043a\u043e\u0432\u0430\u044f \u0441\u0442\u0440\u043e\u043a\u0430, \u0435\u0441\u043b\u0438 \u043d\u0435 \u0443\u0447\u0438\u0442\u044b\u0432\u0430\u0442\u044c. \u042d\u0442\u043e \u0437\u043d\u0430\u0447\u0438\u0442, \u0447\u0442\u043e \u0443 \u043d\u0430\u0441 \u0435\u0441\u0442\u044c \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u043e\u0435 \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u043e\u0434\u0438\u043d\u0430\u043a\u043e\u0432\u044b\u0445 \u0437\u0430\u043f\u0438\u0441\u0435\u0439 \u0441 \u0440\u0430\u0437\u043d\u044b\u043c \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u043e\u043c. \u0422\u0430\u043a\u0438\u0435 \u0441\u0442\u0440\u043e\u0447\u043a\u0438 \u0432\u0440\u0435\u0434\u043d\u044b \u0434\u043b\u044f \u043c\u043e\u0434\u0435\u043b\u0435\u0439, \u043f\u043e\u0441\u043a\u043e\u043b\u044c\u043a\u0443 \u043d\u0435 \u0434\u0430\u044e\u0442 \u0447\u0435\u0442\u043a\u043e\u0433\u043e \u0440\u0430\u0437\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u043a\u043b\u0430\u0441\u0441\u043e\u0432, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u043c\u044b \u0438\u0445 \u0443\u0434\u0430\u043b\u044f\u0435\u043c.<\/p>\n
data[data.drop(target, axis=1).duplicated(keep=False)].sort_values(by=[*data.columns])<\/code><\/pre>\n
\u0414\u0430\u043b\u0435\u0435 \u043d\u0430\u043c \u043d\u0443\u0436\u043d\u043e \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0435\u0442\u044c, \u0435\u0441\u0442\u044c \u043b\u0438 \u043f\u0440\u043e\u043f\u0443\u0449\u0435\u043d\u043d\u044b\u0435 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f \u0432 \u0434\u0430\u0442\u0430\u0441\u0435\u0442\u0435. \u0412 \u043d\u0430\u0448\u0435\u043c \u0441\u043b\u0443\u0447\u0430\u0435 \u043a\u0440\u043e\u043c\u0435 NaN \u043d\u0430 \u043c\u0435\u0441\u0442\u0435 \u043f\u0440\u043e\u043f\u0443\u0441\u043a\u043e\u0432 \u0431\u044b\u043b \u0435\u0449\u0435 \u0438 \u043f\u0440\u043e\u0431\u0435\u043b: » «. \u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043d\u0430\u0439\u0434\u0435\u043c, \u0433\u0434\u0435 \u0438\u043c\u0435\u043d\u043d\u043e \u043e\u043d\u0438 \u0431\u044b\u043b\u0438<\/p>\n
data.replace(\" \", np.nan, inplace=True) X_test.replace(\" \", np.nan, inplace=True) pd.DataFrame(data.isna().sum(), columns=[\"NaN Count\"]) \\     .sort_values(\"NaN Count\") \\     .plot(kind=\"barh\", legend=False, figsize=(12, 8));<\/code><\/pre>\n
<\/figcaption><\/figure>\n
\u041f\u043e\u043b\u0443\u0447\u0430\u0435\u043c 9 NaN \u0432 \u0441\u0442\u043e\u043b\u0431\u0446\u0435 TotalSpent. \u0420\u0430\u0441\u0441\u043c\u043e\u0442\u0440\u0438\u043c \u044d\u0442\u0438\u0445 \u043a\u043b\u0438\u0435\u043d\u0442\u043e\u0432 \u043f\u043e\u0434\u0440\u043e\u0431\u043d\u0435\u0435.<\/p>\n
\n
\n\n\n\n\n\n\n\n\n\n\n\n\n\n
\n
<\/p>\n<\/th>\n
\n
ClientPeriod<\/p>\n<\/th>\n
\n
MonthlySpending<\/p>\n<\/th>\n
\n
TotalSpent<\/p>\n<\/th>\n
\n
Sex<\/p>\n<\/th>\n
\n
IsSeniorCitizen<\/p>\n<\/th>\n
\n
HasPartner<\/p>\n<\/th>\n
\n
HasChild<\/p>\n<\/th>\n
\n
HasPhoneService<\/p>\n<\/th>\n
\n
HasMultiplePhoneNumbers<\/p>\n<\/th>\n
\n
HasInternetService<\/p>\n<\/th>\n
\n
HasOnlineSecurityService<\/p>\n<\/th>\n
\n
HasOnlineBackup<\/p>\n<\/th>\n
\n
HasDeviceProtection<\/p>\n<\/th>\n
\n
HasTechSupportAccess<\/p>\n<\/th>\n
\n
HasOnlineTV<\/p>\n<\/th>\n
\n
HasMovieSubscription<\/p>\n<\/th>\n
\n
HasContractPhone<\/p>\n<\/th>\n
\n
IsBillingPaperless<\/p>\n<\/th>\n
\n
PaymentMethod<\/p>\n<\/th>\n
\n
Churn<\/p>\n<\/th>\n<\/tr>\n
\n
1157<\/p>\n<\/th>\n
\n
11<\/p>\n<\/td>\n
\n
94.20<\/p>\n<\/td>\n
\n
999.9<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Fiber optic<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Month-to-month<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Electronic check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
1048<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
25.75<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Male<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
1707<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
73.35<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
DSL<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
2543<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
19.70<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Male<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
One year<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
3078<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
80.85<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
DSL<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
3697<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
20.00<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
4002<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
61.90<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Male<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
DSL<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Bank transfer (automatic)<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
4326<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
25.35<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Male<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
No internet service<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
4551<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
52.55<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No phone service<\/p>\n<\/td>\n
\n
DSL<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Bank transfer (automatic)<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n
\n
4598<\/p>\n<\/th>\n
\n
0<\/p>\n<\/td>\n
\n
56.05<\/p>\n<\/td>\n
\n
NaN<\/p>\n<\/td>\n
\n
Female<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
No phone service<\/p>\n<\/td>\n
\n
DSL<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
Yes<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Two year<\/p>\n<\/td>\n
\n
No<\/p>\n<\/td>\n
\n
Credit card (automatic)<\/p>\n<\/td>\n
\n
0<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n
\u041e\u0447\u0435\u0432\u0438\u0434\u043d\u043e, \u044d\u0442\u043e \u043d\u043e\u0432\u044b\u0435 \u043a\u043b\u0438\u0435\u043d\u0442\u044b, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0435\u0449\u0435 \u043d\u0435 \u0432\u043d\u0435\u0441\u043b\u0438 \u043f\u0435\u0440\u0432\u044b\u0439 \u043f\u043b\u0430\u0442\u0435\u0436. \u0417\u0430\u043f\u043e\u043b\u043d\u0438\u043c \u0438\u0445 \u043d\u0443\u043b\u044f\u043c\u0438.  <\/p>\n
data[\"TotalSpent\"] = data.TotalSpent.fillna(0).astype(float) X_test[\"TotalSpent\"] = X_test.TotalSpent.fillna(0).astype(float)<\/code><\/pre>\n
\u0417\u0430\u0442\u0435\u043c \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u043c, \u043a\u0430\u043a \u0443 \u043d\u0430\u0441 \u0440\u0430\u0441\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u044b \u0434\u0430\u043d\u043d\u044b\u0435 <\/p>\n
fig, axes = plt.subplots(5, 4, figsize=(25, 20)) for ax, col in zip(axes.flatten(), data.columns):   ax.set_title(col)   if col in cat_cols or col == target:     ax.pie(data[col].value_counts(), autopct=\"%1.1f%%\", labels=data[col].value_counts().index)     else:       data[col].plot(kind=\"hist\", ec=\"black\", ax=ax)<\/code><\/pre>\n
<\/figcaption><\/figure>\n
\u041d\u0430 \u0433\u0440\u0430\u0444\u0438\u043a\u0435 Churn \u0432 \u043f\u0440\u0430\u0432\u043e\u043c \u043d\u0438\u0436\u043d\u0435\u043c \u0443\u0433\u043b\u0443 \u0432\u0438\u0434\u043d\u043e, \u0447\u0442\u043e \u043a\u043b\u0430\u0441\u0441 1 \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d \u0447\u0435\u0442\u0432\u0435\u0440\u0442\u044c\u044e \u0434\u0430\u043d\u043d\u044b\u0445. \u042d\u0442\u043e \u043e\u0437\u043d\u0430\u0447\u0430\u0435\u0442, \u0447\u0442\u043e \u043b\u044e\u0434\u0438 \u0432 \u0442\u0440\u0438 \u0440\u0430\u0437\u0430 \u0447\u0430\u0449\u0435 \u043e\u0441\u0442\u0430\u044e\u0442\u0441\u044f, \u0447\u0435\u043c \u0443\u0445\u043e\u0434\u044f\u0442. \u041c\u043d\u043e\u0433\u0438\u0435 \u0441\u0442\u043e\u043b\u0431\u0446\u044b \u0438\u043c\u0435\u044e\u0442 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f \u00abNo internet service\u00bb \u0438 \u00abNo Phone service\u00bb. \u041f\u043e\u0441\u043a\u043e\u043b\u044c\u043a\u0443 \u0443 \u043d\u0430\u0441 \u0443\u0436\u0435 \u0435\u0441\u0442\u044c \u0444\u0443\u043d\u043a\u0446\u0438\u0438 \u00abHasPhoneService\u00bb \u0438 \u00abHasInternetService\u00bb \u044d\u0442\u0430 \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u044f \u0438\u0437\u0431\u044b\u0442\u043e\u0447\u043d\u0430. \u041c\u044b \u043c\u043e\u0436\u0435\u043c \u043e\u0431\u044a\u0435\u0434\u0438\u043d\u0438\u0442\u044c \u0438\u0445 \u0441 \u043e\u043f\u0446\u0438\u0435\u0439 \u00abNo\u00bb.<\/p>\n
\u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u043e\u0438\u0449\u0435\u043c \u0437\u0430\u043a\u043e\u043d\u043e\u043c\u0435\u0440\u043d\u043e\u0441\u0442\u0438 \u0432 \u0434\u0430\u043d\u043d\u044b\u0445<\/h3>\n
\u041c\u0435\u0436\u0434\u0443 Churn \u0438 PaymentMethod<\/h4>\n
tmp = data.groupby(\"PaymentMethod\", as_index=False).agg({\"Churn\": [\"sum\", \"count\"]}) tmp[\"Churn (%)\"] = 100 * tmp[\"Churn\", \"sum\"] \/ tmp[\"Churn\", \"count\"] tmp.sort_values(\"Churn (%)\").reset_index(drop=True)<\/code><\/pre>\n
\n
\n\n\n\n\n\n\n\n\n
\n
<\/p>\n<\/th>\n
\n
PaymentMethod<\/p>\n<\/th>\n
\n
Churn<\/p>\n<\/th>\n
\n
Churn (%)<\/p>\n<\/th>\n<\/tr>\n
\n
<\/p>\n<\/th>\n
\n
<\/p>\n<\/th>\n
\n
sum<\/p>\n<\/th>\n
\n
count<\/p>\n<\/th>\n
\n
<\/p>\n<\/th>\n<\/tr>\n
\n
0<\/p>\n<\/th>\n
\n
Credit card (automatic)<\/p>\n<\/td>\n
\n
165<\/p>\n<\/td>\n
\n
1143<\/p>\n<\/td>\n
\n
14.435696<\/p>\n<\/td>\n<\/tr>\n
\n
1<\/p>\n<\/th>\n
\n
Bank transfer (automatic)<\/p>\n<\/td>\n
\n
195<\/p>\n<\/td>\n
\n
1159<\/p>\n<\/td>\n
\n
16.824849<\/p>\n<\/td>\n<\/tr>\n
\n
2<\/p>\n<\/th>\n
\n
Mailed check<\/p>\n<\/td>\n
\n
230<\/p>\n<\/td>\n
\n
1194<\/p>\n<\/td>\n
\n
19.262982<\/p>\n<\/td>\n<\/tr>\n
\n
3<\/p>\n<\/th>\n
\n
Electronic check<\/p>\n<\/td>\n
\n
794<\/p>\n<\/td>\n
\n
1786<\/p>\n<\/td>\n
\n
44.456887<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n
\u0412\u0438\u0434\u0438\u043c, \u0447\u0442\u043e \u0440\u0430\u0437\u043d\u0438\u0446\u0430 \u043c\u0435\u0436\u0434\u0443 \u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u044b\u043c \u0447\u0435\u043a\u043e\u043c \u0438 \u0434\u0440\u0443\u0433\u0438\u043c\u0438 \u0441\u043f\u043e\u0441\u043e\u0431\u0430\u043c\u0438 \u043e\u043f\u043b\u0430\u0442\u044b \u0433\u043e\u0440\u0430\u0437\u0434\u043e \u0431\u043e\u043b\u044c\u0448\u0435, \u0447\u0435\u043c \u043c\u0435\u0436\u0434\u0443 \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u0438 \u043d\u0435\u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u043c.<\/p>\n
\u041c\u0435\u0436\u0434\u0443 Churn \u0438 HasContractPhone<\/h4>\n
tmp = data.groupby(\"HasContractPhone\", as_index=False).agg({\"Churn\": [\"sum\", \"count\"]}) tmp[\"Churn (%)\"] = 100 * tmp[\"Churn\", \"sum\"] \/ tmp[\"Churn\", \"count\"] tmp.sort_values(\"Churn (%)\").reset_index(drop=True)<\/code><\/pre>\n
\n
\n\n\n\n\n\n\n\n
\n
<\/p>\n<\/th>\n
\n
HasContractPhone<\/p>\n<\/th>\n
\n
Churn<\/p>\n<\/th>\n
\n
Churn (%)<\/p>\n<\/th>\n<\/tr>\n
\n
<\/p>\n<\/th>\n
\n
<\/p>\n<\/th>\n
\n
sum<\/p>\n<\/th>\n
\n
count<\/p>\n<\/th>\n
\n
<\/p>\n<\/th>\n<\/tr>\n
\n
0<\/p>\n<\/th>\n
\n
Two year<\/p>\n<\/td>\n
\n
33<\/p>\n<\/td>\n
\n
1280<\/p>\n<\/td>\n
\n
2.578125<\/p>\n<\/td>\n<\/tr>\n
\n
1<\/p>\n<\/th>\n
\n
One year<\/p>\n<\/td>\n
\n
120<\/p>\n<\/td>\n
\n
1082<\/p>\n<\/td>\n
\n
11.090573<\/p>\n<\/td>\n<\/tr>\n
\n
2<\/p>\n<\/th>\n
\n
Month-to-month<\/p>\n<\/td>\n
\n
1231<\/p>\n<\/td>\n
\n
2920<\/p>\n<\/td>\n
\n
42.157534<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n
\u0418\u043d\u0430\u0447\u0435 \u0433\u043e\u0432\u043e\u0440\u044f, \u043b\u044e\u0434\u0438 \u0440\u0435\u0434\u043a\u043e \u0440\u0430\u0437\u0440\u044b\u0432\u0430\u044e\u0442 \u0434\u043e\u043b\u0433\u043e\u0441\u0440\u043e\u0447\u043d\u044b\u0435 \u0442\u0435\u043b\u0435\u0444\u043e\u043d\u043d\u044b\u0435 \u043a\u043e\u043d\u0442\u0440\u0430\u043a\u0442\u044b<\/p>\n
\u041c\u0435\u0436\u0434\u0443 Churn \u0438 HasInternetService <\/h4>\n
tmp = data.groupby(\"HasInternetService\", as_index=False).agg({\"Churn\": [\"sum\", \"count\"]}) tmp[\"Churn (%)\"] = 100 * tmp[\"Churn\", \"sum\"] \/ tmp[\"Churn\", \"count\"] tmp.sort_values(\"Churn (%)\").reset_index(drop=True)<\/code><\/pre>\n
\n
\n\n\n\n\n\n\n\n
\n<\/th>\n\n
HasInternetService<\/p>\n<\/th>\n
\n
Churn<\/p>\n<\/th>\n
\n
Churn (%)<\/p>\n<\/th>\n<\/tr>\n
\n<\/th>\n\n<\/th>\n\n
sum<\/p>\n<\/th>\n
\n
count<\/p>\n<\/th>\n
\n<\/th>\n<\/tr>\n
\n
0<\/p>\n<\/th>\n
\n
No<\/p>\n<\/td>\n
\n
82<\/p>\n<\/td>\n
\n
1141<\/p>\n<\/td>\n
\n
7.186678<\/p>\n<\/td>\n<\/tr>\n
\n
1<\/p>\n<\/th>\n
\n
DSL<\/p>\n<\/td>\n
\n
342<\/p>\n<\/td>\n
\n
1800<\/p>\n<\/td>\n
\n
19.000000<\/p>\n<\/td>\n<\/tr>\n
\n
2<\/p>\n<\/th>\n
\n
Fiber optic<\/p>\n<\/td>\n
\n
960<\/p>\n<\/td>\n
\n
2341<\/p>\n<\/td>\n
\n
41.008116<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n
\u041b\u044e\u0434\u0438 \u0441 Fiber optic \u0447\u0430\u0449\u0435 \u043d\u0435\u0434\u043e\u0432\u043e\u043b\u044c\u043d\u044b \u0443\u0441\u043b\u0443\u0433\u0430\u043c\u0438 \u043f\u0440\u043e\u0432\u0430\u0439\u0434\u0435\u0440\u0430, \u0447\u0435\u043c \u043e\u0441\u0442\u0430\u043b\u044c\u043d\u044b\u0435 <\/p>\n
\u041c\u0435\u0436\u0434\u0443 Churn \u0438 \u0421lientPeriod<\/h4>\n
sns.catplot(data=data, x=\"ClientPeriod\", hue=\"Churn\", kind=\"count\", height=8, aspect=20\/8) plt.xticks(rotation=45);<\/code><\/pre>\n
\u0417\u0430\u0432\u0438\u0441\u0438\u043c\u043e\u0441\u0442\u044c \u043c\u0435\u0436\u0434\u0443 \u043b\u043e\u044f\u043b\u044c\u043d\u043e\u0441\u0442\u044c\u044e \u0438 \u0432\u0440\u0435\u043c\u0435\u043d\u0435\u043c \u043a\u043b\u0438\u0435\u043d\u0442\u0441\u043a\u043e\u0433\u043e \u043f\u0435\u0440\u0438\u043e\u0434\u0430<\/figcaption><\/figure>\n
\u0412\u0438\u0434\u043d\u043e, \u0447\u0442\u043e \u043d\u043e\u0432\u044b\u0435 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0438 \u0447\u0430\u0441\u0442\u043e \u0443\u0445\u043e\u0434\u044f\u0442 \u043f\u043e\u0441\u043b\u0435 \u043f\u0435\u0440\u0432\u043e\u0433\u043e \u043c\u0435\u0441\u044f\u0446\u0430 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f, \u0430 \u043f\u043e\u0441\u0442\u043e\u044f\u043d\u043d\u044b\u0435 \u043a\u043b\u0438\u0435\u043d\u0442\u044b \u043e\u0441\u0442\u0430\u044e\u0442\u0441\u044f \u0432\u0435\u0440\u043d\u044b \u043f\u0440\u0438\u0432\u044b\u0447\u043a\u0430\u043c. <\/p>\n
\u041f\u0440\u0435\u043e\u0431\u0440\u0430\u0437\u0443\u0435\u043c \u043a\u0430\u0442\u0435\u0433\u043e\u0440\u0438\u0430\u043b\u044c\u043d\u044b\u0435 \u043f\u0440\u0438\u0437\u043d\u0430\u043a\u0438 \u0432 \u0442\u0438\u043f int \u0441\u043e\u0433\u043b\u0430\u0441\u043d\u043e \u043d\u0430\u0431\u043b\u044e\u0434\u0435\u043d\u0438\u044f\u043c. \u0422.\u0435. \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f \u00abNo internet service\u00bb \u0438 \u00abNo phone service\u00bb \u043f\u043e\u043b\u0443\u0447\u0430\u044e\u0442 0, \u0442\u0430\u043a \u0436\u0435, \u043a\u0430\u043a \u0438 \u00abNo\u00bb. \u0417\u043d\u0430\u0447\u0435\u043d\u0438\u044f \u0432 \u00abPaymentMethod\u00bb \u0438 \u00abHadContractPhone\u00bb \u0431\u0443\u0434\u0443\u0442 \u043f\u0440\u043e\u043d\u0443\u043c\u0435\u0440\u043e\u0432\u0430\u043d\u044b \u0432 \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0438\u0438 \u0441 \u0438\u0445 \u043a\u043e\u0440\u0440\u0435\u043b\u044f\u0446\u0438\u0435\u0439 \u0441 Chern. \u0414\u0432\u043e\u0438\u0447\u043d\u044b\u043c \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f\u043c \u0431\u0443\u0434\u0443\u0442 \u043f\u0440\u0438\u0441\u0432\u043e\u0435\u043d\u044b 0 \u0438 1.<\/p>\n
patterns = {     \"No\": 0,     \"No internet service\": 0,     \"No phone service\": 0,     \"Yes\": 1,     \"Male\": 0,     \"Female\": 1,     \"DSL\": 1,     \"Fiber optic\": 2,     \"Month-to-month\": 0,     \"One year\": 1,     \"Two year\": 2,     \"Credit card (automatic)\": 0,     \"Bank transfer (automatic)\": 1,     \"Mailed check\": 2,     \"Electronic check\": 3, } X_train = data.replace(patterns).drop(target, axis=1) y_train = data[target] X_test = X_test.replace(patterns)<\/code><\/pre>\n
\u0422\u0435\u043f\u0435\u0440\u044c \u043c\u044b \u043c\u043e\u0436\u0435\u043c \u043f\u043e\u0441\u0442\u0440\u043e\u0438\u0442\u044c \u0442\u0435\u043f\u043b\u043e\u0432\u0443\u044e \u043a\u043e\u0440\u0440\u0435\u043b\u044f\u0446\u0438\u043e\u043d\u043d\u0443\u044e \u043c\u0430\u0442\u0440\u0438\u0446\u0443<\/p>\n
sns.heatmap(data=pd.concat([X_train, y_train], axis=1).corr(),             annot=True,             cmap=\"coolwarm\",             center=0,             ax=plt.subplots(figsize=(15,10))[1]);<\/code><\/pre>\n
\u0422\u0435\u043f\u043b\u043e\u0432\u0430\u044f \u043a\u043e\u0440\u0440\u0435\u043b\u044f\u0446\u0438\u043e\u043d\u043d\u0430\u044f \u043c\u0430\u0442\u0440\u0438\u0446\u0430<\/figcaption><\/figure>\n
\u041d\u0430\u043a\u043e\u043d\u0435\u0446, \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u0432\u0438\u0437\u0443\u0430\u043b\u0438\u0437\u0438\u0440\u0443\u0435\u043c \u0434\u0430\u043d\u043d\u044b\u0435 \u043f\u043e\u0441\u043b\u0435 \u0443\u043c\u0435\u043d\u044c\u0448\u0435\u043d\u0438\u044f \u0438\u0445 \u0440\u0430\u0437\u043c\u0435\u0440\u043d\u043e\u0441\u0442\u0438 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e PCA.<\/p>\n
pca = PCA(n_components=2) pca.fit(X_train_std) x0, x1 = pca.components_ sns.set(font_scale=1.5) y = data[\"Churn\"].map({0: False, 1: True}) fig = sns.pairplot(data=pd.concat([pd.DataFrame(data=X_train_std @ np.stack([x0, x1]).T, columns=[\"PC1\", \"PC2\"]), y], axis=1),                    x_vars=\"PC1\",                    y_vars=\"PC2\",                    hue=\"Churn\",                    markers=('^', 's'),                    palette=[\"blue\", \"red\"],                    plot_kws={'s': 100, 'alpha': 0.5},                    height=6) fig.set(title=\"Customer churn visialization (PCA)\") fig.axes[0][0].axhline(y=0, color='black', lw=3, alpha=0.1) fig.axes[0][0].axvline(x=0, color='black', lw=3, alpha=0.1);<\/code><\/pre>\n
<\/figcaption><\/figure>\n
\u041c\u044b \u0432\u0438\u0434\u0438\u043c, \u0447\u0442\u043e \u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e \u0433\u0440\u0443\u0431\u043e \u0440\u0430\u0437\u0434\u0435\u043b\u0438\u0442\u044c \u043a\u043b\u0430\u0441\u0441\u044b \u043f\u0440\u044f\u043c\u043e\u0439 \u043b\u0438\u043d\u0438\u0435\u0439. \u0422\u0430\u043a \u0447\u0442\u043e \u0441\u0442\u0430\u0440\u0430\u044f \u0434\u043e\u0431\u0440\u0430\u044f \u043b\u043e\u0433\u0438\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u0430\u044f \u0440\u0435\u0433\u0440\u0435\u0441\u0441\u0438\u044f, \u0432\u0435\u0440\u043e\u044f\u0442\u043d\u043e, \u043f\u043e\u0434\u043e\u0439\u0434\u0435\u0442. \u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u0440\u043e\u0432\u0435\u0440\u0438\u043c \u0435\u0433\u043e \u0438 \u0441\u0440\u0430\u0432\u043d\u0438\u043c \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b \u0441 \u0434\u0440\u0443\u0433\u0438\u043c\u0438 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0430\u043c\u0438.<\/p>\n
\u041e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 \u043c\u043e\u0434\u0435\u043b\u0435\u0439<\/h2>\n
\u041b\u043e\u0433\u0438\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u0430\u044f \u0440\u0435\u0433\u0440\u0435\u0441\u0441\u0438\u044f<\/h3>\n
\u0414\u043b\u044f \u0442\u043e\u0433\u043e \u0447\u0442\u043e\u0431\u044b \u043a\u0430\u043a\u0430\u044f-\u043b\u0438\u0431\u043e \u043c\u043e\u0434\u0435\u043b\u044c \u0434\u0430\u0432\u0430\u043b\u0430 \u043d\u0430\u0438\u043b\u0443\u0447\u0448\u0438\u0439 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442, \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e \u043f\u0440\u0430\u0432\u0438\u043b\u044c\u043d\u043e \u043f\u043e\u0434\u043e\u0431\u0440\u0430\u0442\u044c \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b \u043c\u043e\u0434\u0435\u043b\u0438. \u041e\u0431\u044b\u0447\u043d\u043e \u0434\u043b\u044f \u044d\u0442\u043e\u0433\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0442 GridSearchCV, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438 \u043f\u0435\u0440\u0435\u0431\u0438\u0440\u0430\u0435\u0442 \u0432\u0430\u0440\u0438\u0430\u043d\u0442\u044b \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432 \u0432 \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u043e\u043c \u0434\u0438\u0430\u043f\u0430\u0437\u043e\u043d\u0435.<\/p>\n
PARAMS = {     \"model__C\": np.arange(0.001, 100, 0.001)#\u0441\u0442\u0430\u0432\u0438\u043c \u0434\u0438\u0430\u043f\u0430\u0437\u043e\u043d \u043e\u0442 0.001 \u0434\u043e 100 \u0441 \u0448\u0430\u0433\u043e\u043c 0.001 } clf = Pipeline(steps=[     (\"scaler\", StandardScaler()),     (\"model\", LogisticRegression(penalty=\"l1\", solver=\"saga\", max_iter=1000, random_state=42)), ]) grid_search = GridSearchCV(<\/code><\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-345013","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/345013","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=345013"}],"version-history":[{"count":0,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/345013\/revisions"}],"wp:attachment":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=345013"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=345013"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=345013"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}