基于FP-tree和支持度数组的最大频繁项集挖掘算法

Efficient mining maximal frequent itemsets by using FP-tree and support array

提出了一个基于频繁模式树即FP-tree和支持度数组相结合的最大频繁项集挖掘算法,首先建立FP-tree,同时建立支持度数组,然后在此基础上建立最大频繁项集树MAXFP-tree,MAXFP-tree中包含了所有最大频繁项集,缩小了搜索空间,提高了算法的效率。算法分析和实验表明,该算法对稠密型数据集和稀疏型数据集均适用,并且特别适于挖掘具有长频繁项集的数据集。

An efficient algorithm based on FP-tree and support array for mining maximal frequent iternsets is proposed. At first the FP-tree and the support array are created at the same time. Then a maximal frequent itemsets tree- MAXFP-tree is built up to store all the maximal frequent itemsets. Therefore, it can reduce the search space and improve the efficiency of the algorithm. The results of experiment show the algorithm can be applied to both dense datasets and sparse datasets and it is especially effective for mining the datasets with long frequent itemsets.