인프런 커뮤니티 질문&답변

아래처럼 똑같이 풀었는데

답이 0.22, 0.34 와 같이 소수점으로나옵니다.

0 / 1 로 구분하기 위해서는 어떻게 정리하면되나요?

import pandas as pd

train = pd.read_csv("data/customer_train.csv")

test = pd.read_csv("data/customer_test.csv")

# train.info()

# test.info()

target = train.pop('성별')

train = pd.get_dummies(train)

test = pd.get_dummies(test)

train, test = train.align(test, join='left', axis=1)

# 검증용 데이터

from sklearn.model_selection import train_test_split

X_tr, X_val, y_tr, y_val = train_test_split(train, target, test_size=0.2, random_state = 0)

print(X_tr.shape, X_val.shape, y_tr.shape, y_val.shape)

# 모델 학습 및 평가

from sklearn.ensemble import RandomForestClassifier

model = RandomForestClassifier()

model.fit(X_tr, y_tr)

# pred = model.predict_proba(X_val[cols])

pred = model.predict_proba(X_val)

from sklearn.metrics import roc_auc_score

print(roc_auc_score(y_val, pred[:,1]))

# 제출

pred = model.predict_proba(test)

submit = pd.DataFrame({

'pred': pred2[:,1]

})

submit.to_csv('result.csv', index=False)

print(pd.read_csv('result.csv'))