基于MapReduce框架的FP-Tree算法研究与优化  

作　　者：薛俊杰 韩素青[1] 

机构地区：[1]太原师范学院,山西晋中030619

出　　处：《数码设计》2019年第15期46-46,共1页Peak Data Science

摘　　要：FP-Tree算法是关联规则经典算法之一,它避免重复扫描数据库,比Apriori快一个数量级。FP-Tree算法在数据量较小时可以取得很好的效果,但是当数据库规模非常大时,在内存中构建FP-Tree是不切实际的。本文提出一种基于MapReduce的FP-Tree算法,通过并行化算法扩大算法可处理的数据集规模,并提高构建和挖掘FP-Tree的速度,实验表明优化后的算法性能有所提高。fp-tree algorithm is one of the classical association rule algorithms.It avoids repeated scanning of database and is an order of magnitude faster than Apriori.Fp-tree algorithm can achieve good results when the data volume is small,but when the database size is very large,it is impractical to build fp-tree in memory.In this paper,a fp-tree algorithm based on MapReduce is proposed to expand the data set size that can be processed by the algorithm through the parallel algorithm,and improve the speed of constructing and mining fp-tree.Experiments show that the performance of the optimized algorithm is improved.

关 键 词：FP-TREE APRIORI MAPREDUCE 并行化 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]