时间:2023-02-01 10:28:38 | 栏目:Python代码 | 点击:次
1.计算SimHash值,及Hamming距离。
2.SimHash适用于较长文本(大于三五百字)的相似性比较,文本越短误判率越高。
代码如下
# -*- encoding:utf-8 -*- import math import jieba import jieba.analyse class SimHash(object): def getBinStr(self, source): if source == "": return 0 else: x = ord(source[0]) << 7 m = 1000003 mask = 2 ** 128 - 1 for c in source: x = ((x * m) ^ ord(c)) & mask x ^= len(source) if x == -1: x = -2 x = bin(x).replace('0b', '').zfill(64)[-64:] return str(x) def getWeight(self, source): return ord(source) def unwrap_weight(self, arr): ret = "" for item in arr: tmp = 0 if int(item) > 0: tmp = 1 ret += str(tmp) return ret def sim_hash(self, rawstr): seg = jieba.cut(rawstr) keywords = jieba.analyse.extract_tags("|".join(seg), topK=100, withWeight=True) ret = [] for keyword, weight in keywords: binstr = self.getBinStr(keyword) keylist = [] for c in binstr: weight = math.ceil(weight) if c == "1": keylist.append(int(weight)) else: keylist.append(-int(weight)) ret.append(keylist) # 降维 rows = len(ret) cols = len(ret[0]) result = [] for i in range(cols): tmp = 0 for j in range(rows): tmp += int(ret[j][i]) if tmp > 0: tmp = "1" elif tmp <= 0: tmp = "0" result.append(tmp) return "".join(result) def distince(self, hashstr1, hashstr2): length = 0 for index, char in enumerate(hashstr1): if char == hashstr2[index]: continue else: length += 1 return length if __name__ == "__main__": simhash = SimHash() str1 = '咱哥俩谁跟谁啊' str2 = '咱们俩谁跟谁啊' hash1 = simhash.sim_hash(str1) print(hash1) hash2 = simhash.sim_hash(str2) distince = simhash.distince(hash1, hash2) value = 5 print("simhash", distince, "距离:", value, "是否相似:", distince<=value)