pipelines.py 文件源码

def word_bigrams():
    preprocessor = TextCleaner(lowercase=True,
                               filter_urls=True,
                               filter_mentions=True,
                               filter_hashtags=True,
                               alphabetic=True,
                               strip_accents=True,
                               filter_rt=True)
    pipeline = Pipeline([('vect', CountVectorizer(preprocessor=preprocessor,
                                                  ngram_range=(2, 2))),
                         ('tfidf', TfidfTransformer(sublinear_tf=True)),
                         ('scale', Normalizer())])
    return ('word_bigrams', pipeline)