以下是与问题相关的一部分代码。如果需要完整代码，这里有一个可以下载数据的完整可重现代码：https://github.com/ageron/handson-ml2/blob/master/02_end_to_end_machine_learning_project.ipynb

我有一个管道：

prepare_select_and_predict_pipeline = Pipeline([    ('preparation', full_pipeline),    ('feature_selection', TopFeatureSelector(feature_importances, k)),    ('svm_reg', SVR(**rnd_search.best_params_))])

现在，我只想执行上述管道中的这部分：

('preparation', full_pipeline),('feature_selection', TopFeatureSelector(feature_importances, k)),

我尝试了prepare_select_and_predict_pipeline.fit(housing, housing_labels)，但它也执行了SVM部分。

最终，我需要从上述管道中获得与下面代码执行相同的结果：

preparation_and_feature_selection_pipeline = Pipeline([    ('preparation', full_pipeline),    ('feature_selection', TopFeatureSelector(feature_importances, k))])housing_prepared_top_k_features = preparation_and_feature_selection_pipeline.fit_transform(housing)

我该如何做到这一点？

回答：

FeatureUnion可以解决这个问题：

from sklearn.pipeline import FeatureUnion, Pipelineprepare_select_pipeline = Pipeline([    ('preparation', full_pipeline),    ('feature_selection', TopFeatureSelector(feature_importances, k))])feats = FeatureUnion([('prepare_and_select', prepare_select_pipeline)])prepare_select_and_predict_pipeline = Pipeline([('feats', feats),                               ('svm_reg', SVR(**rnd_search.best_params_))])

您可以在深入了解Sklearn管道中找到更多相关信息