topic_modeling.py 文件源码

def print_topic_summary(self, df, topic_num, num_words=20):
        '''
        Function to print summary of a topic from NMF clustering

        INPUT:
            df: pandas DataFrame that NMF clustering was run on
            topic_num: index of topic from clustering
            num_words: top n words to print in summary
        '''
        num_reviews = self.labels[:, topic_num].sum()
        print 'Summary of Topic {}:'.format(topic_num)
        print 'Number of reviews in topic: {}'.format(num_reviews)
        print 'Top {} words in topic:'.format(num_words)
        print self.top_words_by_topic(num_words, topic_num)
        if not num_reviews:
            return None