1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
import jieba
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer
import numpy as np
from scipy.linalg import norm
def jaccard_similarity(s1, s2):
s1 = " ".join(jieba.cut(s1))
s2 = " ".join(jieba.cut(s2))
cv = CountVectorizer(tokenizer=lambda s: s.split()) # 转化为TF矩阵
corpus = [s1, s2]
vectors = cv.fit_transform(corpus).toarray()
numerator = np.sum(np.min(vectors, axis=0)) # 计算交集
denominator = np.sum(np.max(vectors, axis=0)) # 计算并集
return 1.0 * numerator / denominator # 计算杰卡德系数
def tf_similarity(s1, s2):
s1 = " ".join(jieba.cut(s1))
s2 = " ".join(jieba.cut(s2))
cv = CountVectorizer(tokenizer=lambda s: s.split()) # 转化为TF矩阵
corpus = [s1, s2]
vectors = cv.fit_transform(corpus).toarray()
return np.dot(vectors[0], vectors[1]) / (norm(vectors[0]) * norm(vectors[1])) # 计算TF系数
def tfidf_similarity(s1, s2):
s1 = " ".join(jieba.cut(s1))
s2 = " ".join(jieba.cut(s2))
cv = TfidfVectorizer(tokenizer=lambda s: s.split()) # 转化为TF矩阵
corpus = [s1, s2]
vectors = cv.fit_transform(corpus).toarray()
return np.dot(vectors[0], vectors[1]) / (norm(vectors[0]) * norm(vectors[1])) # 计算TFIDF系数结果