model.py 文件源码

def init_model():
        # “????”??
        f_trunk = QuestionTrunkVectorizer(tokenizer=tokenize)

        # Word2Vec ????
        f_word2vec = Question2VecVectorizer(tokenizer=tokenize)

        # ???? (400 ?)
        union_features = FeatureUnion([
            ('f_trunk_lsa', Pipeline([
                ('trunk', f_trunk),
                # ??_????: ?????? (LSA)
                ('lsa', TruncatedSVD(n_components=200, n_iter=10))
            ])),
            ('f_word2vec', f_word2vec),
        ])

        model = Pipeline([('union', union_features), ('clf', LinearSVC(C=0.02))])
        return model