資源描述:
《OURMINE An Open Source Data Mining Toolkit》由會員上傳分享,免費(fèi)在線閱讀,更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫。
1、OURMINE:AnOpenSourceDataMiningToolkitAdamR.NelsonThesissubmittedtotheCollegeofEngineeringandMineralResourcesatWestVirginiaUniversityinpartialful?llmentoftherequirementsforthedegreeofMasterofScienceinComputerScienceTimMenzies,Ph.D.,ChairFrancesVanScoy,Ph.
2、D.TimMcGraw,Ph.D.LaneDepartmentofComputerScienceandElectricalEngineeringMorgantown,WestVirginia2010Keywords:DataMining,Toolkit,SoftwareDefectPrediction,Bash,Awk,Scriptingc2010AdamR.NelsonAbstractOURMINE:AnOpenSourceDataMiningToolkitAdamR.NelsonWhenresear
3、cherswanttorepeat,improveorrefutepriorconclusions,itisusefultohaveacompleteandoperationaldescriptionofpriorexperiments.Ifthosedescriptionsareoverlylongorcomplex,thensharingtheirdetailsmaynotbeinformative.OURMINEisascriptingenvironmentforthedevelopmentand
4、deploymentofdataminingex-periments.UsingOURMINE,dataminingnovicescanspecifyandexecuteintricateexperiments,whileresearcherscanpublishtheircompleteexperimentalrigalongsidetheirconclusions.ThisisachievablebecauseofOURMINEssuccinctness.Forexample,thisthesisp
5、resentsthreecasestudiesdocumentedintheOURMINEsyntax.Thus,thebrevityandsimplicityofOURMINErecommendsitasabettertoolfordocumenting,executing,andsharingdataminingexperiments.AcknowledgmentsAmongthosetothank,Iwould?rstliketoacknowledgemyparentsandmysisterfor
6、theirutmostsupportinbothgoodtimes,andbad.Theirdedicationtomyhappinesswillneverbeforgotten.Iwouldalsoliketothankmyadvisor,Dr.Menzies,whobelievedinmeandalwayslookedoutformyprofessionalwell-being.Finally,IwouldliketoacknowledgeGregGay,TomiPrifti,AndrewMathe
7、ny,andeveryoneelsewhosecontribution,directorindirect,wasmonumentalinmyresearch.iContents1Introduction11.1StatementofThesis..................................21.2ContributionsofthisThesis..............................31.3PapersfromthisWork.................
8、...............31.4StructureofthisThesis................................32RelatedWork52.1ExistingOpenSourceDataMiningTools......................52.1.1ADaM....................................52.1.2DatabionicESOMTools.......