인프런 커뮤니티 질문&답변

섹션12 작업형 2회 기출유형

아래처럼 풀이했을 때, TypeError: float() argument must be a string or a real number, not 'LabelEncoder' 오류메시지 뜹니다. 어디서 오류가 난건지 이러한 풀이방법은 잘못된건지 알 수 있을까요?

# EDA

X_train = X_train.drop(columns = ['ID'])

X_test_id = X_test.pop('ID')

y_train = y_train.drop(columns = ['ID'])

# 수치형 데이터 스케일링

num = ['Customer_care_calls', 'Customer_rating', 'Cost_of_the_Product', 'Prior_purchases', 'Discount_offered', 'Weight_in_gms']

from sklearn.preprocessing import RobustScaler

scaler = RobustScaler()

X_train[num] = scaler.fit_transform(X_train[num])

X_test[num] = scaler.fit_transform(X_test[num])

# 범주형 데이터 원핫인코딩

cols = ['Mode_of_Shipment', 'Product_importance', 'Gender']

X_train = pd.get_dummies(data = X_train, columns = cols)

X_test = pd.get_dummies(data = X_test, columns = cols)

# 범주형 데이터 라벨인코딩

from sklearn.preprocessing import LabelEncoder

encoder = LabelEncoder()

X_train['Warehouse_block'] = encoder.fit(X_train['Warehouse_block'])

X_test['Warehouse_block'] = encoder.fit(X_test['Warehouse_block'])

# 분리

from sklearn.model_selection import train_test_split

X_tr, X_val, y_tr, y_val = train_test_split(X_train, y_train, test_size = 0.2, random_state = 2023)

# 모델 및 평가

from sklearn.ensemble import RandomForestClassifier

model = RandomForestClassifier()

model.fit(X_tr, y_tr)

pred = model.predict_proba(X_val)

# 평가

from sklearn.metrics import roc_auc_score

roc_auc_score(y_val, pred[:, 1])