tfid_lsi_lda.py 文件源码

def run_model(name):
    if name == 'lsi':
        lsi = models.LsiModel(corpus_gensim, id2word=vocab_gensim, num_topics=num_topics)
        print('Saving lsi_model...')
        lsi.save('exports/lsi.model')
        print('lsi_model saved!')
        # lsi_matrix = gensim.matutils.corpus2dense(lsi[corpus_gensim], len(lsi.projection.s)).T / lsi.projection.s
        # print('Saving lsi_matrix...')
        # pickle.dump(lsi_matrix, open('exports/lsi_matrix.p','wb'))
        # print('lsi_matrix saved!')

    elif name == 'lda':
        # lda = models.LdaModel(corpus_gensim, id2word=vocab_gensim, num_topics=num_topics, passes=5)
        lda = models.ldamulticore.LdaMulticore(corpus_gensim, id2word=vocab_gensim, num_topics=num_topics, passes=5)#, alpha='auto') #auto needs non multicore LDA
        print('Saving lda_model...')
        lda.save('exports/lda.model')
        print('lda_model saved!')
        # lda_matrix = gensim.matutils.corpus2dense(lda[corpus_gensim], lda.num_topics)
        # print('Saving lda_matrix...')
        # pickle.dump(lda_matrix, open('exports/lda_matrix.p','wb'))
        # print('lda_matrix saved!')
    gc.collect()