转自：

def Ngram_distance(str1, str2, n=2):    tmp = ' ' * (n-1)    str1 = tmp + str1 + tmp#表示以首字母开头和本char结尾    str2 = tmp + str2 + tmp    set1 = set([str1[i:i+n] for i in range(len(str1)-(n-1))])    set2 = set([str2[i:i+n] for i in range(len(str2)-(n-1))])    setx = set1 & set2    len1 = len(set1)    len2 = len(set2)    lenx = len(setx)    num_dist = len1 + len2 - 2*lenx    num_sim = 1 - num_dist / (len1 + len2)    return set1,set2,{
   'dist': num_dist, 'sim': num_sim}print(Ngram_distance('girl','girlfriend'))

输出结果：

({
   'gi', 'ir', 'rl', 'l ', ' g'}, {
   'gi', 'en', 'd ', 'ir', 'lf', 'ie', 'rl', 'fr', 'ri', ' g', 'nd'}, {
   'dist': 8, 'sim': 0.5})