内容简介
DataSciencegetsthrownaroundinthepresslikeit'smagic.MajorretailersarepredictingeverythingfromwhentheircustomersarepregnanttowhentheywantanewpairofChuckTaylors.It'sabravenewworldwhereseeminglymeaninglessdatacanbetransformedintovaluableinsighttodrivesmartbusinessdecisions.Buthowdoesoneexactlydodatascience?Doyouhavetohireoneofthesepriestsofthedarkarts,the"datascientist,"toextractthisgoldfromyourdata?Nope.Datascienceislittlemorethanusingstraight-forwardstepstoprocessrawdataintoactionableinsight.AndinDataSmart,authoranddatascientistJohnForemanwillshowyouhowthat'sdonewithinthefamiliarenvironmentofaspreadsheet.Whyaspreadsheet?It'scomfortable!Yougettolookatthedataeverystepoftheway,buildingconfidenceasyoulearnthetricksofthetrade.Plus,spreadsheetsareavendor-neutralplacetolearndatasciencewithoutthehype.Butdon'tlettheExcelsheetsfoolyou.Thisisabookforthoseseriousaboutlearningtheanalytictechniques,themathandthemagic,behindbigdata.Eachchapterwillcoveradifferenttechniqueinaspreadsheetsoyoucanfollowalong:Mathematicaloptimization,includingnon-linearprogrammingandgeneticalgorithmsClusteringviak-means,sphericalk-means,andgraphmodularityDataminingingraphs,suchasoutlierdetectionSupervisedAIthroughlogisticregression,ensemblemodels,andbag-of-wordsmodelsForecasting,seasonaladjustments,andpredictionintervalsthroughmontecarlosimulationMovingfromspreadsheetsintotheRprogramminglanguageYougetyourhandsdirtyasyouworkalongsideJohnthrougheachtechnique.Butneverfear,thetopicsarereadilyapplicableandtheauthorlaceshumorthroughout.You'llevenlearnwhatadeadsquirrelhastodowithoptimizationmodeling,whichyounodoubtaredyingtoknow.
作者简介
JohnW.ForemanisChiefDataScientistforMailChimp.com,whereheleadsadatascienceproductdevelopmenteffortcalledtheEmailGenomeProject.Asananalyticsconsultant,JohnhascreateddatasciencesolutionsforTheCoca-ColaCompany,RoyalCaribbeanInternational,IntercontinentalHotelsGroup,Dell,theDepartmentofDefense,theIRS,andtheFBI.