인프런 커뮤니티 질문&답변

선생님!!!

작업형2 모의문제3에서 마지막에 데이터프레임을 작성하는데서 에러가 발생하는데, 원인과 수정 방법이 무엇인지 궁급합니다.

[코딩내용]

import pandas as pd

train = pd.read_csv('train.csv')

test = pd.read_csv('test.csv')

print(train.shape, test.shape)

train.head(3)

test.head(3)

train.info()

train.describe()

test.describe()

train.isnull().sum()

test.isnull().sum()

train = train.drop('id', axis=1)

test_id = test.pop('id')

test.head(3)

from sklearn.model_selection import train_test_split

X_tr, X_val, y_tr, y_val = train_test_split(train.drop('output', axis=1),train['output'], test_size=0.1, random_state=2022)

X_tr.shape, X_val.shape, y_tr.shape, y_val.shape

from sklearn.metrics import roc_auc_score, accuracy_score, f1_score

from sklearn.ensemble import RandomForestClassifier

rf = RandomForestClassifier(random_state=2022, max_depth=5, n_estimators=100)

rf.fit(X_tr, y_tr)

pred_proba = rf.predict_proba(X_val)

pred_proba[:10]

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

pred_proba = rf.predict_proba(test)

pred_proba[:10]

pd.DataFrame({'id' : test_id, 'output' : pred_proba[ : , 1]}).to_csv('0000.csv', index=False)

[에러메시지]

TypeError Traceback (most recent call last)

<ipython-input-128-a023f69b95e2> in <cell line: 3>()

1 pred_proba = rf.predict_proba(test)

2 pred_proba[:10]

----> 3 pd.DataFrame({'id' : test_id, 'output' : pred_proba[ : , 1]}).to_csv('0000.csv', index=False)

TypeError: 'dict' object is not callable