你好,游客 登录 注册 发布搜索
背景:
阅读新闻

[PDF]A MapReduce Implementation of C4.5 Decision Tree

[日期:2014-03-19] 来源:google学术  作者:Wei Dai and Wei Ji [字体: ]

A MapReduce Implementation of C4.5 Decision Tree Algorithm  

Wei Dai and Wei Ji

First, as the  size  of  dataset becomes extremely big, the process of building a decision tree can be quite time consuming. Second, because the data cannot fit in memory any more, some computation must be moved to the  external  storage  and  therefore  increases  the  I/O  cost.  To  this  end,  we  propose  to implement  a  typical  decision  tree  algorithm,  C4.5,  using  MapReduce  programming  model. Specifically,  we  transform  the  traditional  algorithm  into  a  series  of  Map  and  Reduce procedures. Besides, we design some data structures to minimize the communication cost. We also  conduct  extensive  experiments  on  a  massive  dataset.  The  results  indicate  that  our algorithm exhibits both time efficiency and scalability.


A MapReduce Implementation of C4.5 Decision Tree

收藏 推荐 打印 | 录入:574107552 | 阅读:
相关新闻       MapReduce 
本文评论   查看全部评论 (0)
表情: 表情 姓名: 字数
点评:
       
评论声明
  • 尊重网上道德,遵守中华人民共和国的各项有关法律法规
  • 承担一切因您的行为而直接或间接导致的民事或刑事法律责任
  • 本站管理人员有权保留或删除其管辖留言中的任意内容
  • 本站有权在网站内转载或引用您的评论
  • 参与本评论即表明您已经阅读并接受上述条款