# -*- coding: utf-8 -*-
import jieba
import numpy as np
import redef get_word_vector(s1,s2):""":param s1: 句子1:param s2: 句子2:return: 返回句子的余弦相似度"""# 分词cut1 = jieba.cut(s1)cut2 = jieba.cut(s2)list_word1 = (','.join(cut1)).split(',')list_word2 = (','.join(cut2)).split(',')# 列出所有的词,取并集key_word = list(set(list_word1 + list_word2))# 给定形状和类型的用0填充的矩阵存储向量word_vector1 = np.zeros(len(key_word))word_vector2 = np.zeros(len(key_word))# 计算词频# 依次确定向量的每个位置的值for i in range(len(key_word)):# 遍历key_word中每个词在句子中的出现次数for j in range(len(list_word1)):if key_word[i] == list_word1[j]:word_vector1[i] += 1for k in range(len(list_word2)):if key_word[i] == list_word2[k]:word_vector2[i] += 1# 输出向量print(word_vector1)print(word_vector2)return word_vector1, word_vector2def cos_dist(vec1,vec2):""":param vec1: 向量1:param vec2: 向量2:return: 返回两个向量的余弦相似度"""dist1=float(np.dot(vec1,vec2)/(np.linalg.norm(vec1)*np.linalg.norm(vec2)))return dist1def filter_html(html):""":param html: html:return: 返回去掉html的纯净文本"""dr = re.compile(r'<[^>]+>',re.S)dd = dr.sub('',html).strip()return ddif __name__ == '__main__':s1="很高兴见到你"s2="我也很高兴见到你"vec1,vec2=get_word_vector(s1,s2)dist1=cos_dist(vec1,vec2)print(dist1)

Building prefix dict from the default dictionary ...
Loading model from cache C:UsersxiaohuAppDataLocalTempjieba.cache
Loading model cost 0.903 seconds.
Prefix dict has been built succesfully.
[1. 1. 1. 1. 0. 0.]
[1. 1. 1. 1. 1. 1.]
0.8164965809277261