Data Mining: Practical Machine Learning Tools and ...

1 Data MiningPractical Machine Learning Tools and 5/3/05 2:21 PM Page iThe Morgan Kaufmann Series in Data Management SystemsSeries Editor:Jim Gray, Microsoft ResearchData Mining: Practical Machine LearningTools and Techniques, Second EditionIan H. Witten and Eibe FrankFuzzy Modeling and Genetic Algorithms forData Mining and ExplorationEarl CoxData Modeling Essentials, Third EditionGraeme C. Simsion and Graham C. WittLocation-Based ServicesJochen Schiller and Agn s VoisardDatabase Modeling with Microsoft Visio forEnterprise ArchitectsTerry Halpin, Ken Evans, Patrick Hallock,and Bill MacleanDesigning Data-Intensive Web ApplicationsStefano Ceri, Piero Fraternali, Aldo Bongio,Marco Brambilla, Sara Comai, andMaristella MateraMining the Web: Discovering Knowledgefrom Hypertext DataSoumen ChakrabartiAdvanced SQL: 1999 UnderstandingObject-Relational and Other AdvancedFeaturesJim MeltonDatabase Tuning.

2 Principles, Experiments,and Troubleshooting TechniquesDennis Shasha and Philippe BonnetSQL: 1999 Understanding RelationalLanguage ComponentsJim Melton and Alan R. SimonInformation Visualization in Data Miningand Knowledge DiscoveryEdited by Usama Fayyad, Georges , and Andreas WierseTransactional Information Systems: Theory,Algorithms, and the Practice of ConcurrencyControl and RecoveryGerhard Weikum and Gottfried VossenSpatial Databases: With Application to GISP hilippe Rigaux, Michel Scholl, and Agn sVoisardInformation Modeling and RelationalDatabases: From Conceptual Analysis toLogical DesignTerry HalpinComponent Database SystemsEdited by Klaus R.

3 Dittrich and AndreasGeppertManaging Reference Data in EnterpriseDatabases: Binding Corporate Data to theWider WorldMalcolm ChisholmData Mining: Concepts and TechniquesJiawei Han and Micheline KamberUnderstanding SQL and Java Together: AGuide to SQLJ, JDBC, and RelatedTechnologiesJim Melton and Andrew EisenbergDatabase: Principles, Programming, andPerformance, Second EditionPatrick O Neil and Elizabeth O NeilThe Object Data Standard: ODMG by R. G. G. Cattell, Douglas , Mark Berler, Jeff Eastman, DavidJordan, Craig Russell, Olaf Schadow,Torsten Stanienda, and Fernando VelezData on the Web: From Relations toSemistructured Data and XMLS erge Abiteboul, Peter Buneman, and DanSuciuData Mining: Practical Machine LearningTools and Techniques with JavaImplementationsIan H.

4 Witten and Eibe FrankJoe Celko s SQL for Smarties: advanced SQLP rogramming, Second EditionJoe CelkoJoe Celko s Data and Databases: Concepts inPracticeJoe CelkoDeveloping Time-Oriented DatabaseApplications in SQLR ichard T. SnodgrassWeb Farming for the Data WarehouseRichard D. HackathornDatabase Modeling & Design, Third EditionTo b y J . Te o r e yManagement of Heterogeneous andAutonomous Database SystemsEdited by Ahmed Elmagarmid, MarekRusinkiewicz, and Amit ShethObject-Relational DBMSs: Tracking the NextGreat Wave, Second EditionMichael Stonebraker and Paul Brown, withDorothy MooreA Complete Guide to DB2 UniversalDatabaseDon ChamberlinUniversal Database Management: A Guideto Object/Relational TechnologyCynthia Maro SaraccoReadings in Database Systems, Third EditionEdited by Michael Stonebraker and JosephM.

5 HellersteinUnderstanding SQL s Stored Procedures: AComplete Guide to SQL/PSMJim MeltonPrinciples of Multimedia Database SystemsV. S. SubrahmanianPrinciples of Database Query Processing forAdvanced ApplicationsClement T. Yu and Weiyi MengAdvanced Database SystemsCarlo Zaniolo, Stefano Ceri, ChristosFaloutsos, Richard T. Snodgrass, V. , and Roberto ZicariPrinciples of Transaction Processing for theSystems ProfessionalPhilip A. Bernstein and Eric NewcomerUsing the New DB2: IBM s Object-RelationalDatabase SystemDon ChamberlinDistributed AlgorithmsNancy A.

6 LynchActive Database Systems: Triggers and RulesFor advanced Database ProcessingEdited by Jennifer Widom and Stefano CeriMigrating Legacy Systems: Gateways,Interfaces & the Incremental ApproachMichael L. Brodie and Michael StonebrakerAtomic TransactionsNancy Lynch, Michael Merritt, WilliamWeihl, and Alan FeketeQuery Processing For advanced DatabaseSystemsEdited by Johann Christoph Freytag, DavidMaier, and Gottfried VossenTransaction Processing: Concepts andTechniquesJim Gray and Andreas ReuterBuilding an Object-Oriented DatabaseSystem: The Story of O2 Edited by Fran ois Bancilhon, ClaudeDelobel, and Paris KanellakisDatabase Transaction Models For AdvancedApplicationsEdited by Ahmed K.

7 ElmagarmidA Guide to Developing Client/Server SQLA pplicationsSetrag Khoshafian, Arvola Chan, AnnaWong, and Harry K. T. WongThe Benchmark Handbook For Databaseand Transaction Processing Systems, SecondEditionEdited by Jim GrayCamelot and Avalon: A DistributedTransaction FacilityEdited by Jeffrey L. Eppinger, Lily , and Alfred Z. SpectorReadings in Object-Oriented DatabaseSystemsEdited by Stanley B. Zdonik and 5/3/05 5:42 PM Page iiData MiningPractical Machine Learning Tools and Techniques,Second EditionIan H. WittenDepartment of Computer ScienceUniversity of WaikatoEibe FrankDepartment of Computer ScienceUniversity of WaikatoAMSTERDAM BOSTON HEIDELBERG LONDONNEW YORK OXFORD PARIS SAN DIEGOSAN FRANCISCO SINGAPORE SYDNEY TOKYOMORGAN KAUFMANN PUBLISHERS IS AN IMPRINT OF 4/30/05 10:55 AM Page iiiPublisher:Diane CerraPublishing Services Manager:Simon CrumpProject Manager:Brandy LillyEditorial Assistant:Asma StephanCover Design:Yvo Riezebos DesignCover Image:Getty ImagesComposition.

8 SNP Best-set Typesetter Ltd., Hong KongTechnical Illustration:Dartmouth Publishing, :Graphic World :Graphic World :Graphic World printer:The Maple-Vail Book Manufacturing GroupCover printer:Phoenix Color CorpMorgan Kaufmann Publishers is an imprint of Sansome Street, Suite 400, San Francisco, CA 94111 This book is printed on acid-free paper. 2005 by Elsevier Inc. All rights used by companies to distinguish their products are often claimed as trademarksor registered trademarks. In all instances in which Morgan Kaufmann Publishers is aware of aclaim, the product names appear in initial capital or all capital letters.

9 Readers, however, shouldcontact the appropriate companies for more complete information regarding trademarks part of this publication may be reproduced, stored in a retrieval system, or transmitted inany form or by any means electronic, mechanical, photocopying, scanning, or otherwise without prior written permission of the may be sought directly from Elsevier s Science & Technology Rights Department inOxford, UK: phone: (+44) 1865 843830, fax: (+44) 1865 853333, You may also complete your request on-line via the Elsevierhomepage ( ) by selecting Customer Support and then ObtainingPermissions.

10 Library of Congress Cataloging-in-Publication DataWitten, (Ian H.)Data mining : Practical Machine Learning Tools and techniques / Ian H. Witten, Eibe Frank. 2nd cm. (Morgan Kaufmann series in data management systems)Includes bibliographical references and : 0-12-088407-01. Data Frank, dc222005043385 For information on all Morgan Kaufmann publications,visit our Web site at in the United States of America050607080954321 Working together to grow libraries in developing | | 5/3/05 2:22 PM Page ivForewordJim Gray, Series EditorMicrosoft ResearchTechnology now allows us to capture and store vast quantities of data.