cos和Jaccard
cos公式就是计算两个向量的距离
Jaccard是两向量的交 / 两向量的并,因此也可以更快的计算相似度
"""
Step 1:Cosine
Step 2:Jaccard
"""
# Step 1: Cosine
input1_str = "我们 带来 阿里巴巴 希望 差 差 差"
input2_str = "我们 带来 阿里巴巴 希望 好 好 好"
def cosine(input1_str, input2_str):
t1_dict = {}
sum = 0
for k, v in get_tfidf(input1_str):
sum += pow(v,2)
sum = math.sqrt(sum)
for k, v in get_tfidf(input1_str):
t1_dict[k] = float(v / sum)
for k, v in get_tfidf(input1_str):
sum += pow(v,2)
sum = math.sqrt(sum)
final_score = 0
for k, v in get_tfidf(input2_str):
if k not in t1_dict:
continue
s1 = t1_dict[k]
s2 = float(v / sum)
final_score += s1 * s2
return final_score
print(cosine(input1_str, input2_str))
# Step 1: Jaccard
input1_str = "我们 带来 阿里巴巴 希望 差 差 差"
input2_str = "我们 带来 "
def jaccard(input1_str, input2_str):
s1_set = set(input1_str.strip().split(' '))
s2_set = set(input2_str.strip().split(' '))
score = 0
s1_s2_join = s1_set & s2_set
len1 = len(s1_s2_join)
s1_s2_union = s1_set | s2_set
len2 = len(s1_s2_union)
return float(len1) / float(len2)
print(jaccard(input1_str, input2_str))