lda_train.py 文件源码

def query_tag(id2word, model, split_word):
  # id2word = corpora.Dictionary.load(path+'.id2word')
  # model = LdaMulticore.load(path+'.lda')
  bow = id2word.doc2bow(split_word)
  if len(bow) == 0:
    return None
  gamma, _ = model.inference([bow])
  topic_dist = gamma[0] / sum(gamma[0])  # normalize distribution
  # [(topicid, topicvalue) for topicid, topicvalue in enumerate(topic_dist)]
  return topic_dist