gensim 中文文本相似度计算

# -*- coding: utf-8 -*-
# __jiahuiyu__
import jieba
import logging
from gensim import corpora, models, similarities
from collections import defaultdict


logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)


def a_sub_b(a, b):
    ret = []
    for el in a:
        if el not in b