【摘要】 挖掘最大频繁项目集是多种数据挖掘应用中的关键问题。FP-growth算法是目前最有效的频繁模式挖掘算法之一,其在挖掘最大项目集时要递归生成大量的条件FP-树,存在时空效率不高的问题。于是结合改进的FP-树,提出了一种快速挖掘最大项目集的算法。该算法利用改进的FP-树是单向的且每个节点只保留指向父节点的指针,可以节约大量的存储空间;同时引入项目序列集和它的基本操作,使挖掘最大频繁项目集时不生成含大量候选项目的集合或条件FP-树,可以快速地挖掘出所有的最大频繁项目集。实例分析证明所提出的算法是可行的。更多还原

【Abstract】 Mining maximum frequent itemsets is a key problem in many data mining application.FP-growth algorithm is one of the most efficient frequent pattern mining methods.However,FP-growth algorithm must generate a huge number of conditional FP-trees recursively in processes of mining maximum frequent,so the efficiency of it unsatisfactory.This paper proposed an efficient mining maximum frequent algorithm,it unified the improvement FP-tree.The FP-tree was a one-way tree and there is no pointers to point its children in each node,so it saved the massive memories space.By introducing set of item sequences and its operators,the algorithm didn’t generate conditional FP-tree or a large number of candidate sets in mining process,which could conveniently get all maximum frequent itemsets.The example analysis shows the algorithm is feasibility and effectiveness.更多还原