centroid_w2v.py 文件源码

def get_topic_idf(self, sentences):
        vectorizer = CountVectorizer()
        sent_word_matrix = vectorizer.fit_transform(sentences)

        transformer = TfidfTransformer(norm=None, sublinear_tf=False, smooth_idf=False)
        tfidf = transformer.fit_transform(sent_word_matrix)
        tfidf = tfidf.toarray()

        centroid_vector = tfidf.sum(0)
        centroid_vector = np.divide(centroid_vector, centroid_vector.max())
        # print(centroid_vector.max())

        feature_names = vectorizer.get_feature_names()
        word_list = []
        for i in range(centroid_vector.shape[0]):
            if centroid_vector[i] > self.topic_threshold:
                # print(feature_names[i], centroid_vector[i])
                word_list.append(feature_names[i])

        return word_list