余弦相似性计算及python代码实现

    from functools import reduce   python3中reduce函数集成在functolls里面了
    def mix(self):
        merge_vdict = set(self.vdict1.keys()) | set(self.vdict2.keys())  #vdict1和vdict2分别为两个句子的TF_IDF值，merge_vdict为并集
        for key in merge_vdict:
            self.vdict1[key] = self.vdict1.get(key,0)  
            self.vdict2[key] = self.vdict2.get(key,0)   #计算向量

    #余弦函数的实现
    def similar(self):
        self.vector()
        self.mix()
        sum = 0
        for key in self.vdict1:
            sum += self.vdict1[key] * self.vdict2[key]   
        A = sqrt(reduce(lambda x,y: x+y, map(lambda x: x*x,self.vdict1.values())))
        B = sqrt(reduce(lambda x,y: x+y, map(lambda x: x*x, self.vdict2.values())))
        return sum/(A*B)