在Pipeline中使用ColumnTransformer来指定OneHotEncoder应该转换哪些列，以便转换器可以在后续列中识别新列。

示例代码：

from sklearn.compose import ColumnTransformer from sklearn.pipeline import Pipeline from sklearn.preprocessing import OneHotEncoder from sklearn.preprocessing import StandardScaler

假设前3列是类别变量，后3列是连续变量

col_transformer = ColumnTransformer([ ('onehot', OneHotEncoder(), [0,1,2]), ('scaler', StandardScaler(), [3,4,5]) ], remainder='passthrough')

将ColumnTransformer加入Pipeline中

pipe = Pipeline([ ('col_trans', col_transformer), ('clf', RandomForestClassifier()) ])

使用fit_transform方法对所有列进行转换

X_transformed = pipe.fit_transform(X)