比较字符串相似度 Levenshtein

Levenshtein是编辑距离，在自然语言处理中很常见。

# coding=utf-8
def Levenshtein(s, t):
    len_s = len(s)
    len_t = len(t)

    temp = [[0 for i in range(0, len_t+1)] for j in range(len_s+1)]
    # print(temp)
    # 将第一行和第一列初始化 0，1，2，3，。。。
    for i in range(len_s+1):
        temp[i][0] = i
    for i in range(len_t+1):
        temp[0][i] = i
    # 更新矩阵
    for i in range(1, len_s+1):
        for j in range(1, len_t+1):
            if s[i - 1] == t[j - 1]:
                flag = 0
            else:
                flag = 1
            temp[i][j] = min(temp[i - 1][j - 1] + flag,
                             temp[i][j - 1] + 1, temp[i - 1][j] + 1)
    print(temp[len_s][len_t] / (max(len_s, len_t)))
    for i in temp:
        print (i)
    print(temp[len_s][len_t])

if __name__=="__main__":
    # //要比较的两个字符串 
    Levenshtein("ddddsssss",'dddsssss')
   d  d  d  s  s  s  s  s
d [0, 1, 2, 3, 4, 5, 6, 7]
d [1, 0, 1, 2, 3, 4, 5, 6]
d [2, 1, 0, 1, 2, 3, 4, 5]
d [3, 2, 1, 0, 1, 2, 3, 4]
s [4, 3, 2, 1, 1, 2, 3, 4]
s [5, 4, 3, 2, 1, 1, 2, 3]
s [6, 5, 4, 3, 2, 1, 1, 2]
s [7, 6, 5, 4, 3, 2, 1, 1]
s [8, 7, 6, 5, 4, 3, 2, 1]

以上是python实现