topic_modeling.py 文件源码

def train_lsi_model_gensim(corpus, total_topics=2):

    norm_tokenized_corpus = normalize_corpus(corpus, tokenize=True)
    dictionary = corpora.Dictionary(norm_tokenized_corpus)
    mapped_corpus = [dictionary.doc2bow(text) 
                     for text in norm_tokenized_corpus]
    tfidf = models.TfidfModel(mapped_corpus)
    corpus_tfidf = tfidf[mapped_corpus]
    lsi = models.LsiModel(corpus_tfidf, 
                          id2word=dictionary,
                          num_topics=total_topics)
    return lsi