인프런 커뮤니티 질문&답변

# 시험환경 세팅 (코드 변경 X)
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split

def exam_data_load(df, target, id_name="", null_name=""):
    if id_name == "":
        df = df.reset_index().rename(columns={"index": "id"})
        id_name = 'id'
    else:
        id_name = id_name
    
    if null_name != "":
        df[df == null_name] = np.nan
    
    X_train, X_test = train_test_split(df, test_size=0.2, shuffle=True, random_state=2021)
    y_train = X_train[[id_name, target]]
    X_train = X_train.drop(columns=[id_name, target])
    y_test = X_test[[id_name, target]]
    X_test = X_test.drop(columns=[id_name, target])
    return X_train, X_test, y_train, y_test 
    
df = pd.read_csv("../input/house-prices-advanced-regression-techniques/train.csv")
X_train, X_test, y_train, y_test = exam_data_load(df, target='SalePrice', id_name='Id')

X_train.shape, X_test.shape, y_train.shape, y_test.shape

((1168, 79), (292, 79), (1168, 2), (292, 2))

target = y_train.pop('SalePrice')
y_test_id = y_train.pop('Id')

# 레이블 인코딩을 수행합니다.
# 모든 문자열 특성에 대해 레이블 인코딩을 적용합니다.
for col in X_train.columns:
    if X_train[col].dtype == 'object':
        # Train에만 있는 레이블을 'unknown'으로 바꾸고 인코딩
        train_unique_labels = set(X_train[col].unique())
        test_unique_labels = set(X_test[col].unique())
        
        # `X_test`에만 존재하는 레이블을 'unknown'으로 변경
        X_test[col] = X_test[col].apply(
            lambda x: 'unknown' if x not in train_unique_labels else x
        )
        
        # 인코딩
        encoder = LabelEncoder()
        encoder.fit(list(train_unique_labels) + ['unknown'])  # 'unknown' 포함하여 학습
        X_train[col] = encoder.transform(X_train[col].astype(str))
        X_test[col] = encoder.transform(X_test[col].astype(str))

from sklearn.model_selection import train_test_split
X_tr, X_val, y_tr, y_val = train_test_split(X_train, target, test_size=0.2, random_state=2022)
X_tr.shape, X_val.shape, y_tr.shape, y_val.shape
((934, 79), (234, 79), (934,), (234,))

여기까지는 잘 수행이 됐습니다!! unknown 설명 감사합니다

그런데,

from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import r2_score
rf = RandomForestClassifier(random_state=2022)
rf.fit(X_tr, y_tr)
pred = rf.predict(X_val)
print(r2_score(y_val, pred))

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/tmp/ipykernel_20/3726132327.py in <module>
      2 from sklearn.metrics import r2_score
      3 rf = RandomForestClassifier(random_state=2022)
----> 4 rf.fit(X_tr, y_tr)
      5 pred = rf.predict(X_val)
      6 print(r2_score(y_val, pred))

/opt/conda/lib/python3.7/site-packages/sklearn/ensemble/_forest.py in fit(self, X, y, sample_weight)
    302             )
    303         X, y = self._validate_data(X, y, multi_output=True,
--> 304                                    accept_sparse="csc", dtype=DTYPE)
    305         if sample_weight is not None:
    306             sample_weight = _check_sample_weight(sample_weight, X)

/opt/conda/lib/python3.7/site-packages/sklearn/base.py in _validate_data(self, X, y, reset, validate_separately, **check_params)
    430                 y = check_array(y, **check_y_params)
    431             else:
--> 432                 X, y = check_X_y(X, y, **check_params)
    433             out = X, y
    434 

/opt/conda/lib/python3.7/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
     70                           FutureWarning)
     71         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 72         return f(**kwargs)
     73     return inner_f
     74 

/opt/conda/lib/python3.7/site-packages/sklearn/utils/validation.py in check_X_y(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, estimator)
    800                     ensure_min_samples=ensure_min_samples,
    801                     ensure_min_features=ensure_min_features,
--> 802                     estimator=estimator)
    803     if multi_output:
    804         y = check_array(y, accept_sparse='csr', force_all_finite=True,

/opt/conda/lib/python3.7/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
     70                           FutureWarning)
     71         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 72         return f(**kwargs)
     73     return inner_f
     74 

/opt/conda/lib/python3.7/site-packages/sklearn/utils/validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator)
    643         if force_all_finite:
    644             _assert_all_finite(array,
--> 645                                allow_nan=force_all_finite == 'allow-nan')
    646 
    647     if ensure_min_samples > 0:

/opt/conda/lib/python3.7/site-packages/sklearn/utils/validation.py in _assert_all_finite(X, allow_nan, msg_dtype)
     97                     msg_err.format
     98                     (type_err,
---> 99                      msg_dtype if msg_dtype is not None else X.dtype)
    100             )
    101     # for object dtype data, we only check for NaNs (GH-13254)

ValueError: Input contains NaN, infinity or a value too large for dtype('float32').

여기서 이런 에러가 뜹니다,,,