작업 2유형 : 3회차

from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_auc_score
from sklearn.metrics import classification_report

x = x_train.drop(columns = ['ID'])

test_drop = test.drop(columns = ['ID'])



sc = StandardScaler()
sc.fit(x)


xs = sc.transform(x)
x_test_scaler = sc.transform(test_drop)

X_train, X_test, y_train, y_test = train_test_split(xs, y_train['pose'], test_size=0.33, random_state=42)

lr = LogisticRegression()
lr.fit(X_train,y_train)

pred = lr.predict_proba(X_test)
print('validation_auc : ',roc_auc_score(y_test,pred[:,1]))



# # 아래 코드 예측변수와 수험번호를 개인별로 변경하여 활용
# # pd.DataFrame({'id': test.id, 'stroke': pred}).to_csv('003000000.csv', index=False)
pd.DataFrame({'id': test.ID, 'pose': lr.predict_proba(x_test_scaler)[:,1]}).to_csv('003000000.csv', index=False)