topic_models.py 文件源码

def save_topics(model,filename):
    with open(filename,"wt") as outf:
        # ---------- write each topic and words' contribution
        topics = model.show_topics(num_topics=-1, log=False, formatted=True)
        for topic in topics:
            # topic[0]: topic number
            # topic[1]: topic description
            outf.write("\n############# TOPIC {} #############\n".format(topic[0]))
            outf.write(topic[1]+"\n")

        # ---------- words statistics in all topics
        outf.write("\n\n\n****************** KEY WORDS ******************\n")
        topics = model.show_topics(num_topics=-1, log=False, formatted=False)
        keywords = (word for (_,words) in topics for (word,score) in words)

        fdist = nltk.FreqDist(keywords)
        for index,(w,c) in enumerate( fdist.most_common(100) ):
            outf.write("{}-th keyword: <{},{}>\n".format(index+1,w,c))