桂林电子科技大学学报2017，Vol.37Issue(2)：122-126,5.
一种基于Hadoop的关联规则改进算法
An improved association rules algorithm based on Hadoop
摘要
Abstract
To solve the problem of time and space complexity when the traditional frequent pattern growth algorithm (FP-Growth) is working, an improved FP-Growth algorithm based on Hadoop (IFPH) is presented.IFPH achieves parallel computing through Hadoop, and the pruning strategy is introduced in the process of constructing frequent pattern tree to compress the size of frequent pattern tree for reducing the amount of data processing.This algorithm's performance is evaluated by different data volume and number of computing nodes.Experimental results show that the processing efficiency of the algorithm is enhanced with the increase of the data size and the number of computing nodes.IFPH algorithm has a good feasibility and scalability.关键词
FP-Growth/FP-tree/频繁项集/HadoopKey words
FP-Growth/FP-tree/frequent item sets/Hadoop分类
信息技术与安全科学引用本文复制引用
付浩征,王勇..一种基于Hadoop的关联规则改进算法[J].桂林电子科技大学学报,2017,37(2):122-126,5.基金项目
国家自然科学基金(61163058),广西可信软件重点实验室基金(KX201306) （61163058）
