인프런 커뮤니티 질문&답변

작업형 2 모음집 하는 도중 마지막 데이터 제출 데이터 파일 생성시 다음과 같은 오류가 나는데 왜 그럴까용..?

[코드]

#전처리 스케일링

target = train.pop('total')

#원핫

print(train.shape, test.shape)

train = pd.get_dummies(train)

teset = pd.get_dummies(test)

print(train.shape, test.shape)

#분리

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)

#모델평가

from sklearn.ensemble import RandomForestRegressor

rf = RandomForestRegressor()

rf.fit(X_tr,y_tr)

pred = rf.predict(X_val)

from sklearn.metrics import mean_squared_error

def rmse(y_true, y_pred):

  mse = mean_squared_error(y_true,y_pred)

  return  mse **0.5

result = rmse(y_val, pred)

#테스트 제

pred = rf.predict(test)

submit = pd.DataFrame({'pred':pred})

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

[오류내역]

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

<ipython-input-23-e536b293909d> in <cell line: 68>()
     66 
     67 # 7. 예측 및 결과 파일 생성
---> 68 pred = rf.predict(test)
     69 submit = pd.DataFrame({'pred':pred})
     70 submit.to_csv("result.csv", index=False)

3 frames

/usr/local/lib/python3.10/dist-packages/sklearn/base.py in _check_feature_names(self, X, reset)
    479                 )
    480 
--> 481             raise ValueError(message)
    482 
    483     def _validate_data(

ValueError: The feature names should match those that were passed during fit.
Feature names unseen at fit time:
- branch
- city
- customer_type
- day_name
- gender
- ...
Feature names seen at fit time, yet now missing:
- branch_A
- branch_B
- branch_C
- city_Mandalay
- city_Naypyitaw
- ...