ColumnTransformer在管道中使用CountVectorizer/HashingVectorizer失败(多个文本特性)

Question

类似于这个问题(ColumnTransformer fails with CountVectorizer in a pipeline)，我希望在具有文本特性的列上应用CountVectorizer/HashingVectorizer，使用管道中的ColumnTransformer。但是我没有一个文本功能，而是多个。如果我传递一个特性(不像解决另一个问题的方法中所建议的列表那样)，它可以正常工作，如何对多个特性进行传递？

numeric_features = ['x0', 'x1', 'y0', 'y1']
categorical_features = []
text_features = ['text_feature', 'another_text_feature']

numeric_transformer = Pipeline(steps=[('scaler', StandardScaler())])
categorical_transformer = Pipeline(steps=[('encoder', OneHotEncoder())])
text_transformer = Pipeline(steps=[('hashing', HashingVectorizer())])

preprocessor = ColumnTransformer(transformers=[
    ('numeric', numeric_transformer, numeric_features), 
    ('categorical', categorical_transformer, categorical_features),
    ('text', text_transformer, text_features)
])
    
steps = [('preprocessor', preprocessor),
         ('clf', SGDClassifier())]
    
pipeline = Pipeline(steps=steps)
    
pipeline.fit(X_train, y_train)

Answer 1

只需为每个文本特性使用单独的转换器即可。

preprocessor = ColumnTransformer(transformers=[
    ('numeric', numeric_transformer, numeric_features), 
    ('categorical', categorical_transformer, categorical_features),
    ('text', text_transformer, 'text_feature'),
    ('more_text', text_transformer, 'another_text_feature'),
])

(变压器在安装过程中被克隆，所以您将有两个独立的text_transformer副本，一切都很好。如果需要像这样两次指定相同的转换器，则可以在指定ColumnTransformer之前手动复制/克隆它。)