segmentation.py 文件源码

def LSI_fit(self, data):
        '''
        Fits an LSI model and returns it with associated dictionary
        '''
        texts = [[tag for tag in sent] for sent in self.get_pos(data)]
        dictionary = corpora.Dictionary(texts)
        texts = map(dictionary.doc2bow, texts)
        lsi = models.LsiModel(texts, id2word=dictionary, 
                                                    num_topics=self.num_topics)

        return dictionary, lsi