document_filter.py 文件源码

def __create_ngram_model(self, lang):
        if   lang == 'en':
            tfidf_ngrams = EnglishTfidfVectorizer(decode_error='ignore')
        elif lang == 'ja':
            tfidf_ngrams = JapaneseTfidfVectorizer(decode_error='ignore')

        clf              = MultinomialNB()
        pipeline         = Pipeline([('vect', tfidf_ngrams), ('clf', clf)])

        return pipeline