汉语句子的相似度量化匹配python

import math
def duibixiangliang(list1,list2):
    list=[]
    for i in range(len(list1)):
        list.append(list1[i])
    for j in range(len(list2)):
        if list2[j] not in list:
             list.append(list2[j])
    print("标准向量为：",list)
    return list
def xlh(list,list0):
    listx=[]
    for i in range(len(list)):
        if list[i] in list0:
            listx.extend([1])
        else:
            listx.extend([0])
    return listx
def cos(list1,list2):
    k=0
    k1=0
    k2=0
    for i in range(len(list1)):
        k=k+list1[i]*list2[i]
        k1=k1+math.pow(list1[i],2)
    for i in range(len(list2)):
        k2=k2+math.pow(list2[i],2)
    p=k/(math.sqrt(k1)*math.sqrt(k2))
    return p
list1=['北京','你好','发展','繁荣','富强']
list2=['北京','腾飞','发展','迅速']
list=duibixiangliang(list1,list2)
list1xlh=xlh(list,list1)
list2xlh=xlh(list,list2)
print("向量一：",list1xlh)
print("向量二：",list2xlh)
p=cos(list1xlh,list2xlh)
print("向量的相似度为：",p)