余弦相似性计算及python代码实现

A：西米喜欢健身

B：超超不爱健身，喜欢打游戏

step1:分词

A：西米／喜欢／健身

B：超超／不／喜欢／健身，喜欢／打／游戏

step2:列出两个句子的并集

西米／喜欢／健身／超超／不／打／游戏

step3:计算词频向量

A：[1,1,1,0,0,0,0]

B：[0,1,1,1,1,1,1]

step4:计算余弦值

 余弦值越大，证明夹角越小，两个向量越相似。

step5:python代码实现

?

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41

import jieba import jieba.analyse   def words2vec(words1=None, words2=None):     v1 = []     v2 = []     tag1 = jieba.analyse.extract_tags(words1, withWeight=True)     tag2 = jieba.analyse.extract_tags(words2, withWeight=True)     tag_dict1 = {i[0]: i[1] for i in tag1}     tag_dict2 = {i[0]: i[1] for i in tag2}     merged_tag = set(tag_dict1.keys()) | set(tag_dict2.keys())     for i in merged_tag:         if i in tag_dict1:             v1.append(tag_dict1[i])         else:             v1.append(0)         if i in tag_dict2:             v2.append(tag_dict2[i])         else:             v2.append(0)     return v1, v2     def cosine_similarity(vector1, vector2):     dot_product = 0.0     normA = 0.0     normB = 0.0     for a, b in zip(vector1, vector2):         dot_product += a * b         normA += a ** 2         normB += b ** 2     if normA == 0.0 or normB == 0.0:         return 0     else:         return round(dot_product / ((normA**0.5)*(normB**0.5)) * 100, 2)       def cosine(str1, str2):     vec1, vec2 = words2vec(str1, str2)     return cosine_similarity(vec1, vec2)   print(cosine('阿克苏苹果', '阿克苏苹果'))