| 1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374 |
- # -*- coding:utf-8 -*-
- import config
- import re
- import math
- def merge_word_root(word_root_a, word_root_b):
- """
- 合并词根
- """
- return list(set(word_root_a).union(set(word_root_b)))
- def gen_word_vector(word_a, word_b, word_root_union):
- """
- 生成词向量
- """
- a_word_vector, b_word_vector = [], []
- for word in word_root_union:
- if word in config.RE_SPECIAL_SIMBOL :
- word = "\\" + word
- a_word_vector.append(len(re.findall(word, word_a)))
- b_word_vector.append(len(re.findall(word, word_b)))
- return a_word_vector, b_word_vector
- def vector_multi(a_vector, b_vector):
- """
- 向量相乘求和
- """
- return sum(map(lambda a_b: a_b[0]*a_b[1], zip(a_vector, b_vector)))
- def vector_square_sum(word_vector):
- """
- 向量平方求和
- """
- sum = 0
- for i in word_vector:
- sum = sum + i * i
- return sum
- def vector_cos(v_multi, a_v_ss, b_v_ss):
- """
- 计算余弦值
- """
- return v_multi / (math.sqrt(a_v_ss) * math.sqrt(b_v_ss))
- def cal_cos(a_word, b_word, a_word_root, b_word_root):
- """
- 计算两个长尾关键词的余弦值
- """
- # 合并词根,用于生成词向量
- union_word_root = merge_word_root(a_word_root, b_word_root)
- # 生成词向量
- a_vector, b_vector = gen_word_vector(a_word, b_word, union_word_root)
- # 词向量相乘求和
- ab_vector_multi = vector_multi(a_vector, b_vector)
- # 向量平方求和
- a_vector_squar_sum = vector_square_sum(a_vector)
- b_vector_squar_sum = vector_square_sum(b_vector)
- cos_val = vector_cos(ab_vector_multi, a_vector_squar_sum, b_vector_squar_sum)
- return cos_val
- if __name__ == "__main__":
- a_word = "腋下长了一个小疙瘩是什么东西"
- b_word = "白凉粉是什么东西"
- a_word_root = ['腋下', '长', '了', '一个', '小', '疙瘩', '是', '什么', '东西']
- b_word_root = ['白', '凉粉', '是', '什么', '东西']
- print(cal_cos(a_word, b_word, a_word_root, b_word_root))
|