高效FP-TREE创建算法

High Efficiency FP-tree Creating Algorithm

如何从大型数据库中挖掘关联规则是数据挖掘的一个重要的问题。FP-growth是一个著名的不产生候选集的高效频繁模式挖掘算法,它使用专门的数据结构FP-tree。为了进一步提高FP-grown算法效率,提出一个新的并行算法PFPTC,可以并发地创建子FP-tree,以及一个FP-tree合并算法称作FP-merge,可以将两个FP-tree合并为一个。

Mining association rules from large databases is an important problem in data mining. FP-growth is a famous algorithm to mine frequent patterns and it is non-candidate generation algorithm using a special structure FPtree. In order to enhance the efficiency of FP-grown algorithm,propose a novel parallel algorithm PFPTC to create sub FP-trees concurrently and a FP-tree merging algorithm called FP-merge which can merge two FP-trees into one FP-tree.