인프런 커뮤니티 질문&답변

train = pd.read_csv('/kaggle/input/working8-2/churn_train.csv')

test = pd.read_csv('/kaggle/input/working8-2/churn_test.csv')

target = train.pop('TotalCharges')

train = pd.get_dummies(train)

test = pd.get_dummies(test)

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=2022)

from sklearn.metrics import mean_absolute_error

from sklearn.ensemble import RandomForestRegressor

rf = RandomForestRegressor(random_state=2022, max_depth=7, n_estimators=600)

rf.fit(X_tr,y_tr)

pred = rf.predict(X_val)

answer = rf.predict(test)

rf.predict(X_val)까지는 잘 예측이 되어,

866.4986350062683의 값을 얻었습니다.

그리하여 마지막으로 본 test파일을 예측하여 제출하려고 하는데, 계속해서 오류가 발생하네요 ㅠㅠㅠ

아래는 에러 코드입니다.

ValueError Traceback (most recent call last)
Cell In[97], line 14
     12 rf.fit(X_tr,y_tr)
     13 pred = rf.predict(X_val)
---> 14 answer = rf.predict(test)

File /opt/conda/lib/python3.10/site-packages/sklearn/ensemble/_forest.py:981, in ForestRegressor.predict(self, X)
    979 check_is_fitted(self)
    980 # Check data
--> 981 X = self._validate_X_predict(X)
    983 # Assign chunk of trees to jobs
    984 n_jobs, _, _ = _partition_estimators(self.n_estimators, self.n_jobs)

File /opt/conda/lib/python3.10/site-packages/sklearn/ensemble/_forest.py:602, in BaseForest._validate_X_predict(self, X)
    599 """
    600 Validate X whenever one tries to predict, apply, predict_proba."""
    601 check_is_fitted(self)
--> 602 X = self._validate_data(X, dtype=DTYPE, accept_sparse="csr", reset=False)
    603 if issparse(X) and (X.indices.dtype != np.intc or X.indptr.dtype != np.intc):
    604     raise ValueError("No support for np.int64 index based sparse matrices")

File /opt/conda/lib/python3.10/site-packages/sklearn/base.py:548, in BaseEstimator._validate_data(self, X, y, reset, validate_separately, **check_params)
    483 def _validate_data(
    484     self,
    485     X="no_validation",
   (...)
    489     **check_params,
    490 ):
    491     """Validate input data and set or check the `n_features_in_` attribute.
    492 
    493     Parameters
   (...)
    546         validated.
    547     """
--> 548     self._check_feature_names(X, reset=reset)
    550     if y is None and self._get_tags()["requires_y"]:
    551         raise ValueError(
    552             f"This {self.__class__.__name__} estimator "
    553             "requires y to be passed, but the target y is None."
    554         )

File /opt/conda/lib/python3.10/site-packages/sklearn/base.py:481, in BaseEstimator._check_feature_names(self, X, reset)
    476 if not missing_names and not unexpected_names:
    477     message += (
    478         "Feature names must be in the same order as they were in fit.\n"
    479     )
--> 481 raise ValueError(message)

ValueError: The feature names should match those that were passed during fit.
Feature names unseen at fit time:
- customerID_CUST0001
- customerID_CUST0002
- customerID_CUST0006
- customerID_CUST0007
- customerID_CUST0008
- ...
Feature names seen at fit time, yet now missing:
- customerID_CUST0000
- customerID_CUST0003
- customerID_CUST0004
- customerID_CUST0005
- customerID_CUST0009
- ...