풀이에서는

 <이건 풀이코드 중 일부 발췌>

Preprocessing

In [10]:

X_train = X_train.select_dtypes(exclude=['object'])

X_test = X_test.select_dtypes(exclude=['object'])

target = y_train['SalePrice']

In [11]:

X_train.head(3)

In [12]:

from sklearn.impute import SimpleImputer

이렇게 범주형 제외시키고 수치형으로 전처리 끝낸 다음에 SimpleImputer로 핏, 예측했는데

<이건 제가 해보려 한 라벨인코딩>

제가 범주형데이터 잡고 라벨인코딩으로 전처리를 하려고 해봤는데

cols = X_train.select_dtypes(include='object').columns

from sklearn.preprocessing import LabelEncoder

le = LabelEncoder()

for col in cols:

    X_train[col] = le.fit_transform(X_train[col])

    X_test[col] = le.transform(X_test[col])

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
/opt/conda/lib/python3.7/site-packages/sklearn/preprocessing/_label.py in _encode(values, uniques, encode, check_unknown)
    112         try:
--> 113             res = _encode_python(values, uniques, encode)
    114         except TypeError:

/opt/conda/lib/python3.7/site-packages/sklearn/preprocessing/_label.py in _encode_python(values, uniques, encode)
     60     if uniques is None:
---> 61         uniques = sorted(set(values))
     62         uniques = np.array(uniques, dtype=values.dtype)

TypeError: '<' not supported between instances of 'str' and 'float'

During handling of the above exception, another exception occurred:

TypeError                                 Traceback (most recent call last)
/tmp/ipykernel_20/2364802253.py in <module>
      3 le = LabelEncoder()
      4 for col in cols:
----> 5     X_train[col] = le.fit_transform(X_train[col])
      6     X_test[col] = le.transform(X_test[col])

/opt/conda/lib/python3.7/site-packages/sklearn/preprocessing/_label.py in fit_transform(self, y)
    254         """
    255         y = column_or_1d(y, warn=True)
--> 256         self.classes_, y = _encode(y, encode=True)
    257         return y
    258 

/opt/conda/lib/python3.7/site-packages/sklearn/preprocessing/_label.py in _encode(values, uniques, encode, check_unknown)
    115             types = sorted(t.__qualname__
    116                            for t in set(type(v) for v in values))
--> 117             raise TypeError("Encoders require their input to be uniformly "
    118                             f"strings or numbers. Got {types}")
    119         return res

TypeError: Encoders require their input to be uniformly strings or numbers. Got ['float', 'str']

이러한 에러가 뜨더라구요,, 범주형 데이터 잡고 라벨인코딩으로 하면 안되는 문제인건가요??