learn.py 文件源码

def construct_pipeline(classifier):
    """
    This function creates a feature extraction pipeline that accepts data
    from a CorpusLoader and appends the classification model to the end of
    the pipeline, returning a newly constructed Pipeline object that is
    ready to be fit and trained!
    """

    return Pipeline([
        # Create a Feature Union of Text Stats and Bag of Words
        ('union', FeatureUnion(
            transformer_list = [

                # Pipeline for pulling document structure features
                ('stats', Pipeline([
                    ('stats', TextStats()),
                    ('vect', DictVectorizer()),
                ])),

                # Pipeline for creating a bag of words TF-IDF vector
                ('bow', Pipeline([
                    ('tokens', TextNormalizer()),
                    ('tfidf',  TfidfVectorizer(
                        tokenizer=identity, preprocessor=None, lowercase=False
                    )),
                    ('best', TruncatedSVD(n_components=1000)),
                ])),

            ],

            # weight components in feature union
            transformer_weights = {
                'stats': 0.15,
                'bow': 0.85,
            },
        )),

        # Append the estimator to the end of the pipeline
        ('classifier', classifier),
    ])