基于开源工具的数据分析

图书标准信息

• 作者 [美]雅奈特（Philipp K.Janert） 著
• 出版社 东南大学出版社
• 出版时间 2011-05
• 版次 1
• ISBN 9787564126742
• 定价 82.00元
• 装帧 平装
• 开本 16开
• 纸张 胶版纸
• 页数 509页
• 字数 824千字
• 正文语种 英语

【内容简介】

数据收集相对比较简单，而要把原始信息转化为有用的数据则需要知道如何精确地抽取你想要的内容。通过《基于开源工具的数据分析（影印版·英文版）》的深入讲解，那些对数据分析感兴趣的中等或者富有经验的程序员将可以学习到在商业环境中与数据打交道的技术。你将了解到如何观察数据来找出它所包含的信息，如何在概念模型里捕捉到这些想法，然后把你的理解通过商业计划、度量标准的精确报告和其他方式反馈给你所在的机构。你将会通过《基于开源工具的数据分析（影印版·英文版）》每章结束部分的动手实践来慢慢体验各种概念。最重要的是，你将了解到如何思考你所希望获取的数据--而不是依赖于工具来替你思考。

【作者简介】

     PhilippK．Janert目前提供数据分析和数学模型的咨询服务，他曾经是物理学家和软件工程师。他是《Gnuplot inAction：Understanding Data with Graphs》(Manning出版)的作者，他为O’ReillvNetwork．IBMdeVeloperWorks和IEEEsoftware写过文章。他拥有Washington大学理论物理学的博士学位。

【目录】

PREFACE
1INTRODUCTION
DataAnalysis
What'sinThisBook
What'swiththeWorkshops?
What'swiththeMath?
WhatYou'llNeed
What'sMissing

PARTIGraphics:LookingatData
2ASINGLEVARIABLE:SHAPEANDDISTRIBUTION
DotandJitterPlots
HistogramsandKernelDensityEstimates
TheCumu/atiueDistributionFunction
Rank-OrderPlotsandLiltCharts
OnlyWhenAppropriate:SummaryStatisticsandBoxPlots
Workshop:NumPy
FurtherReading
3TWOVARIABLES:ESTABLISHINGRELATIONSHIPS
ScatterPlots
ConqueringNoise:5moothing
LogarithmicPlots
Banking
LinearReRressionandAllThat
ShouwingWhat'sImportant
GraphicalAnalysisandPresentationGraphics
Workshop:matplotlib
FurtherReading
TIMEASAVARIABLE:TIME-SERIESANALYSIS
Examples
TheTask
Smoothing
Don'tOuerlooktheObuious!
TheCorrelationFunction
Optional:FiltersandConuolutions
Workshop:scipy.signal
FurtherReadinR
5MORETHANTWOVARIABLES:GRAPHICALMULTIVARIATEANALYSIS
False-ColorPlots
ALotataGlance:Multiplots
CompositionProblems
NouelPlotTypes
InteractiueExplorations
Workshop:ToolsforMultiuariateGraphics
FurtherReadinR
6INTERMEZZO:ADATAANALYSISSESSION
ADataAnalysisSession
Workshop:gnuplot
FurtherReadinR

PARTIIAnalyticg:ModelingData
7GUESSTIMATIONANDTHEBACKOFTHEENVELOPE
PrinciplesofGuesstimation
HowGoodAreThoseNumbers?
Optional:ACloserLookatPerturbationTheoryand
ErrorPropaRation
Workshop:TheGnuScientificLibrary(GSL)
FurtherReading
8MODELSFROMSCALINGARGUMENTS
Models
ArRumentsfromScale
Mean-FieldApproximations
CommonTime-EuolutionScenarios
CaseStudy:HowManySeruersAreBest?
WhyModeling?
Workshop:Sage
FurtherReading
9ARGUMENTSFROMPROBABILITYMODELS
The.BinomialDistributionandBernoulliTrials
TheGaussianDistributionandtheCentralLimitTheorem
Power-LawDistributionsandNon-NormalStatistics
OtherDistributions
Optional:CaseStudy--UniqueVisitorsouerTime
Workshop:Power-LawDistributions
FurtherReading
10WHATYOUREALLYNEEDTOKNOWABOUTCLASSICALSTATISTICS
Genesis
StatisticsDefined
StatisticsExplained
ControlledExperimentsVersusObseruationa}Studies
Optional:BayesianStatistics--TheOtherPointofView
Workshop:R
FurtherReading
11INTERMEZZO:MYTHBUSTING--BIGFOOT,LEASTSQUARES,ANDALLTHAT
HowtoAuerageAuerages
TheStandardDeuiation
LeastSquares
FurtherReading

PARTIIIComputation:MininhgData
12SIMULATIONS
AWarm-UpQuestion
MonteCarloSimulations
ResamplingMethods
Workshop:DiscreteEuentSimulationswithSimpy
FurtherReading
13FINDINGCLUSTERS
WhatConstitutesaCluster?
DistanceandSimilarityMeasures
ClusteringMethods
Pre-andPostprocessing
OtherThouRhts
ASpecialCase:MarketBasketAnalysis
AWordofWarninR
Workshop:P/clusterandtheCClusteringLibrary
FurtherReading
14SEEINGTHEFORESTFORTHETREES:FINDING
IMPORTANTATTRIBUTES
PrincipalComponentAnalysis
VisualTechniques
KohonenMaps
Workshop:PCAwithR
FurtherReadin2
15INTERMEZZO:WHENMOREISDIFFERENT
AHorrorStory
SomeSuggestions
WhatAboutMap/Reduce?
Workshop:GeneratingPermutations
FurtherReading

PARTIVApplications:UsingData
16REPORTING,BUSINESSINTELLIGENCE,ANDDASHBOARDS
BusinessIntelligence
CorporateMetricsandDashboards
DataQualityIssues
Workshop:BerkeleyDBandSQLite
FurtherReading
17FINANCIALCALCULATIONSANDMODELING
TheTimeValueo[Money
UncertaintyinPlanningandOpportunityCosts
CostConceptsandDepreciation
ShouldYouCare?
IsThisAllThatMatters?
Workshop:TheNewsuendorProblem
FurtherReading
18PREDICTIVEANALYTICS
Introduction
SomeClassificationTerminology
AlgorithmsforClassification
TheProcess
TheSecretSauce
TheNatureo[StatisticalLearning
Workshop:TwoDo-lt-YourselClassifiers
FurtherReading
19EPILOGUE:FACTSARENOTREALITY
APROGRAMMINGENVIRONMENTSFORSCIENTIFICCOMPUTATION
ANDDATAANALYSIS
SoftwareTools
ACatalogofScientificSoftware
WritingYourOwn
FurtherReading
BRESULTSFROMCALCULUS
CommonFunctions
Calculus
UsefulTricks
NotationandBasicMath
WheretoGofromHere
FurtherReadin9
WORKINGWITHDATA
SourcesforData
Cleanin9andConditioninR
Sarnplin9
DataFileFormats
TheCareandFeedingofYourDataZoo
Skills
Terminology
FurtherFleadin9
INDEX