Hadoop, Pig, and Twitter

Hadoop, Pig, and Twitter

ID:40080658

大小:2.84 MB

页数:58页

时间:2019-07-20

Hadoop, Pig, and Twitter_第1页
Hadoop, Pig, and Twitter_第2页
Hadoop, Pig, and Twitter_第3页
Hadoop, Pig, and Twitter_第4页
Hadoop, Pig, and Twitter_第5页
资源描述:

《Hadoop, Pig, and Twitter》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、Hadoop,Pig,andTwitterKevinWeil--@kevinweilAnalyticsLead,TwitterTMWednesday,March24,2010Introduction‣HadoopOverview‣WhyPig?‣EvolutionofDataProcessingatTwitter‣PigforCounting‣PigforCorrelating‣PigforResearchandDataMining‣ConclusionsandNextStepsWednesday,March24,2010MyBackground

2、‣StudiedMathematicsandPhysicsatHarvard,PhysicsatStanford‣TroposNetworks(city-widewireless):meshroutingalgorithms,GBsofdata‣Cooliris(webmedia):HadoopandPigforanalytics,TBsofdata‣Twitter:Hadoop,Pig,machinelearning,visualization,socialgraphanalysis,???ofdataWednesday,March24,201

3、0Introduction‣HadoopOverview‣WhyPig?‣EvolutionofDataProcessingatTwitter‣PigforCounting‣PigforCorrelating‣PigforResearchandDataMining‣ConclusionsandNextStepsWednesday,March24,2010DataisGettingBig‣NYSE:1TB/day‣Facebook:20+TBcompressed/day‣CERN/LHC:40TB/day(15PB/year!)‣Andgrowth

4、isaccelerating‣Needmultiplemachines,horizontalscalabilityWednesday,March24,2010Hadoop‣Distributedfilesystem(hardtostoreaPB)‣Fault-tolerant,handlesreplication,nodefailure,etc‣MapReduce-basedparallelcomputation(evenhardertoprocessaPB)‣Generickey-valuebasedcomputationinterfaceal

5、lowsforwideapplicability‣Opensource,top-levelApacheproject‣Scalable:Y!hasa4000-nodecluster‣Powerful:sortedaTBofrandomintegersin62secondsWednesday,March24,2010MapReduce?‣Challenge:howmanytweetsperuser,giventweetstable?‣Input:key=row,value=tweetinfo‣Map:outputkey=user_id,value=

6、1‣Shuffle:sortbyuser_id‣Reduce:foreachuser_id,sum‣Output:user_id,tweetcount‣With2xmachines,runscloseto2xfaster.Wednesday,March24,2010MapReduce?‣Challenge:howmanytweetsperuser,giventweetstable?‣Input:key=row,value=tweetinfo‣Map:outputkey=user_id,value=1‣Shuffle:sortbyuser_id‣R

7、educe:foreachuser_id,sum‣Output:user_id,tweetcount‣With2xmachines,runscloseto2xfaster.Wednesday,March24,2010MapReduce?‣Challenge:howmanytweetsperuser,giventweetstable?‣Input:key=row,value=tweetinfo‣Map:outputkey=user_id,value=1‣Shuffle:sortbyuser_id‣Reduce:foreachuser_id,sum‣

8、Output:user_id,tweetcount‣With2xmachines,runscloseto2xfaster.Wednesd

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。