lda.py 文件源码

def build_model(self, fname=None, save_to=None):
        id2word = self.id2word or self.build_id2word()
        corpus = self.corpus or self.build_corpus()
        # read model.lda file
        if not fname:
            fname = click.prompt('model file name', type=str, default='model.lda')
        fname = self.__dest(fname)
        # if there is no model file or the user wants to rebuild, build .model
        if not os.path.isfile(fname) or click.confirm('There already is %s. Do you want to re run lda?' % fname):
            num_procs = click.prompt('Number of processes to launch',
                                     type=int,
                                     default=multiprocessing.cpu_count())
            num_epochs = click.prompt('Number of epochs to run', type=int, default=20)
            num_topics = click.prompt('Number of topics', type=int, default=100)
            print 'start building model'
            start = time()
            model = LdaMulticore(corpus, id2word=id2word, num_topics=num_topics, workers=num_procs, passes=num_epochs)
            model.save(fname) #save
            print 'building model takes: %s' % LdaUtils.human_readable_time(time() - start)
        self.model = LdaMulticore.load(fname)
        return self.model