# -*- coding: utf-8 -*-
# __jiahuiyu__
"""
对英文的处理
"""
import logging
from gensim import models, similarities, corpora
from collections import defaultdict
import os
# 日志输出
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
# 停用词
stoplist = set('for a of the and to in'.split())
# 英文标点符号
punctions = [' ', '\
gensim 英文文本相似度
最新推荐文章于 2021-01-29 19:45:40 发布