from math import* from decimal import Decimal class Similarity(): """ Five similarity measures function """ def euclidean_distance(self,x,y): # 欧式距离 """ return euclidean distance between two lists """ return sqrt(sum(pow(a-b,2) for a, b in zip(x, y))) def manhattan_distance(self,x,y): # 曼哈顿距离 """ return manhattan distance between two lists """ return sum(abs(a-b) for a,b in zip(x,y)) def minkowski_distance(self,x,y,p_value): # 闵可夫斯基距离 """ return minkowski distance between two lists """ return self.nth_root(sum(pow(abs(a-b),p_value) for a,b in zip(x, y)), p_value) def nth_root(self,value, n_root): # 开n次方 """ returns the n_root of an value """ root_value = 1/float(n_root) return round (Decimal(value) ** Decimal(root_value),3) def cosine_similarity(self,x,y): # 余弦相似度 """ return cosine similarity between two lists """ numerator = sum(a*b for a,b in zip(x,y)) denominator = self.square_rooted(x)*self.square_rooted(y) return round(numerator/float(denominator),3) def square_rooted(self,x): # 平方根距离 """ return 3 rounded square rooted value """ return round(sqrt(sum([a*a for a in x])),3) def jaccard_similarity(self,x,y): # 杰卡德距离 """ returns the jaccard similarity between two lists """ intersection_cardinality = len(set.intersection(*[set(x), set(y)])) union_cardinality = len(set.union(*[set(x), set(y)])) return intersection_cardinality/float(union_cardinality)
