topicModel.py 文件源码

def fit(self, documents):
        '''
        parameters:
          documents: list of strings, each represents a document
        '''

        # tokens, dictionary, corpus for LDA
        self.tokens = self.preProcessCorpus(documents)
        self.dictionary = corpora.Dictionary(self.tokens)
        self.corpus = [self.dictionary.doc2bow(text) for text in self.tokens]

        self.lda = self.getLDA(dictionary=self.dictionary, 
                               corpus=self.corpus, 
                               num_topics=self.num_topics, 
                               random_state=self.random_state)

        self.num_dominant_topics=min(10, self.num_topics)
        self.dominant_topic_ids = self.getDominantTopics(self.corpus, 
                                                         self.lda, 
                                                         self.num_dominant_topics)