#encoding=utf-8

 import jieba

 import jieba.posseg as pseg

 import re

 import sys

 reload(sys)

 sys.setdefaultencoding( "utf-8" )

 filename='D:/hellowxc/python/1.txt'

 fileneedCut='D:/hellowxc/python/test.txt'

 fn=open(fileneedCut,"r")

 f=open(filename,"w+")

 lines =fn.readlines()  # 读取全部内容

 for line in lines:

     line.replace('\t', '').replace('\n', '').replace(' ','')

     seg_list = jieba.cut(line, cut_all=False)

     f.write(" ".join(seg_list))

 f.close()

 fn.close()

 # -*- coding: utf-8 -*-

 """

 功能：测试gensim使用，处理中文语料

 时间：2017年5月16日17:10:23

 """

 from gensim.models import word2vec

 import logging

 # 主程序

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

 sentences = word2vec.Text8Corpus(u"D:\\hellowxc\\python\\1.txt")  # 加载语料

 model = word2vec.Word2Vec(sentences, size=200)

 #

 print model

 # 计算两个词的相似度/相关程度

 try:

     y1 = model.similarity(u"屋顶", u"建成")

 except KeyError:

     y1 = 0

 print u"【屋顶】和【建成】的相似度为：", y1

 print"-----\n"

 y2 = model.most_similar(u"屋顶", topn=20)  # 20个最相关的

 print u"和【屋顶】最相关的词有：\n"

 for item in y2:

     print item[0], item[1]

 print"-----\n"

 # 寻找对应关系

 print u"屋顶-建成，形状-"

 y3 =model.most_similar([u'建成', u'形状'], [u'屋顶'], topn=3)

 for item in y3:

     print item[0], item[1]

 print"----\n"

 # 寻找不合群的词

 y4 =model.doesnt_match(u"屋顶 建成 形状 酒店".split())

 print u"不合群的词：", y4

 print"-----\n"