로지스틱 회귀함수

import

from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import f1_score

train_test_split(X, y, test_size, random_state)

seed = 123

#X <-1)
#y <-2)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=seed)

수치형 데이터 제거

col_cate=X_train.select_dtypes(exclude='number').columns
col_cate

Yes : 1 , No : 0 , 그 외 값 : -1 치환

X_train[col_cate].applymap(lambda x: 1 if x=='Yes' else (0 if x=='No' else -1))

*X_train,x_test 모두 적용

MinMax정규화

scaler_mm = MinMaxScaler()
X_train_scaler=scaler_mm.fit_transform(X_train)
X_test_scaler=scaler_mm.transform(X_test)

https://deepinsight.tistory.com/165

[scikit-learn] transform()과 fit_transform()의 차이는 무엇일까?

 

 

LogisticRegression

model_lr = LogisticRegression(random_state = seed)
model_lr.fit(X = X_train_scaler,
             y = y_train)

predict

y_pred=model_lr.predict(X_test_scaler)

f1

f1_score(y_test, y_pred, pos_label='Yes').round(2)

confusion_matrix

confusion_matrix(y_test, y_pred)

classification_report

from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))