小编Duk*_*ong的帖子

我正在对数据集中的某些功能使用目标编码。我的完整管道是这样的：

from sklearn.compose import ColumnTransformer

from sklearn.pipeline import Pipeline

from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import StandardScaler

from category_encoders.target_encoder import TargetEncoder

from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split

numeric_features = ['feature_1']
numeric_pipeline = Pipeline(steps=[('scaler', StandardScaler())])

ohe_features = ['feature_2', 'feature_3', 'feature_4']
ohe_pipeline = Pipeline(steps=[('ohe', OneHotEncoder())])

te_features = ['feature_5', 'feature_6']
te_pipeline = TargetEncoder()

preprocessor = ColumnTransformer(transformers=[
                                ('numeric', numeric_pipeline, numeric_features), 
                                ('ohe_features', ohe_pipeline, ohe_features), 
                                ('te_features', te_pipeline, te_features)
                                ]
               )

clf_lr = Pipeline(steps=[
                 ('preprocessor', preprocessor), 
                 ('classifier', LogisticRegression())
                 ]
         )

X_train, X_test, y_train, y_test = …