计算机工程与设计
計算機工程與設計
계산궤공정여설계
Computer Engineering and Design
2015年
10期
2725-2728,2748
,共5页
数据挖掘%MapReduce编程模型%约束频繁项集%频繁模式树%关联规则
數據挖掘%MapReduce編程模型%約束頻繁項集%頻繁模式樹%關聯規則
수거알굴%MapReduce편정모형%약속빈번항집%빈번모식수%관련규칙
data mining%MapReduce programming model%constrained frequent itemsets%frequent pattern tree%association rules
传统的约束频繁项集挖掘方法无法实现对较大数据量的快速处理，针对该问题，结合分布式框架 Hadoop的分布式计算优势，提出一种基于M apReduce的约束频繁项集挖掘算法。将一个完整的挖掘任务分成若干个相对独立的子任务，根据用户自定义的约束条件对子任务进行并行挖掘，提高算法的执行效率。实验结果表明，该算法具有较好的实用性和良好的扩展性。
傳統的約束頻繁項集挖掘方法無法實現對較大數據量的快速處理，針對該問題，結閤分佈式框架 Hadoop的分佈式計算優勢，提齣一種基于M apReduce的約束頻繁項集挖掘算法。將一箇完整的挖掘任務分成若榦箇相對獨立的子任務，根據用戶自定義的約束條件對子任務進行併行挖掘，提高算法的執行效率。實驗結果錶明，該算法具有較好的實用性和良好的擴展性。
전통적약속빈번항집알굴방법무법실현대교대수거량적쾌속처리，침대해문제，결합분포식광가 Hadoop적분포식계산우세，제출일충기우M apReduce적약속빈번항집알굴산법。장일개완정적알굴임무분성약간개상대독립적자임무，근거용호자정의적약속조건대자임무진행병행알굴，제고산법적집행효솔。실험결과표명，해산법구유교호적실용성화량호적확전성。
Traditional constrained frequent item set mining methods fail to achieve fast processing of large amounts of data .To solve these problems ,a constraint frequent item sets mining algorithm based on MapReduce combining with distributed compu‐ting framework advantage of the distributed Hadoop .A complete mining task was split into several relatively independent sub‐tasks ,and subtasks were parallel mined based on user‐defined constraints ,so that the efficiency of the algorithm was improved . Experimental results show that the algorithm has good practicability and good scalability .
