数据挖掘之Apriori算法详解和Python实现代码分享

2019-10-05 14:37:29丽君

            # 生成下一级候选集
            location = self.select(s)
            support = self.sut(location)
            support, location = self.del_location(support, location)
            num = list(sorted(set([j for i in location for j in i])))
            s += 1
            if  location and support and num:
                self.pre_num = self.num
                self.pre_location = self.location
                self.pre_support = self.support

                self.num = num
                self.location = location
                self.support = support
            else:
                break

    def confidence_sup(self):
        "计算confidence"
        if sum(self.pre_support) == 0:
            print 'min_support error' # 第一次迭代即失败
        else:
            for index_location,each_location in enumerate(self.location):
                del_num = [each_location[:index] + each_location[index+1:] for index in range(len(each_location))] # 生成上一级频繁项级
                del_num = [i for i in del_num if i in self.pre_location] # 删除不存在上一级频繁项级子集
                del_support = [self.pre_support[self.pre_location.index(i)] for i in del_num if i in self.pre_location] # 从上一级支持度查找
                # print del_num
                # print self.support[index_location]