1、INCITS/ISO/IEC 13249-6:20062007 (ISO/IEC 13249-6:2006, IDT) Information technology Database languages SQL multimediaand application packages Part 6: Data miningINCITS/ISO/IEC 13249-6:20062007 (ISO/IEC 13249-6:2006, IDT)INCITS/ISO/IEC 13249-6:20062007 ii ITIC 2007 All rights reserved PDF disclaimer T
2、his PDF file may contain embedded typefaces. In accordance with Adobes licensing policy, this file may be printed or viewed but shall not be edited unless the typefaces which are embedded are licensed to and installed on the computer performing the editing. In downloading this file, parties accept t
3、herein the responsibility of not infringing Adobes licensing policy. The ISO Central Secretariat accepts no liability in this area. Adobe is a trademark of Adobe Systems Incorporated. Details of the software products used to create this PDF file can be found in the General Info relative to the file;
4、 the PDF-creation parameters were optimized for printing. Every care has been taken to ensure that the file is suitable for use by ISO member bodies. In the unlikely event that a problem relating to it is found, please inform the Central Secretariat at the address given below. Adopted by INCITS (Int
5、erNational Committee for Information Technology Standards) as an American National Standard. Date of ANSI Approval: 3/30/2007 Published by American National Standards Institute, 25 West 43rd Street, New York, New York 10036 Copyright 2007 by Information Technology Industry Council (ITI). All rights
6、reserved. These materials are subject to copyright claims of International Standardization Organization (ISO), International Electrotechnical Commission (IEC), American National Standards Institute (ANSI), and Information Technology Industry Council (ITI). Not for resale. No part of this publication
7、 may be reproduced in any form, including an electronic retrieval system, without the prior written permission of ITI. All requests pertaining to this standard should be submitted to ITI, 1250 Eye Street NW, Washington, DC 20005. Printed in the United States of America iii Contents Page Foreword. ix
8、 Introduction . x 1 Scope. 1 2 Normative references 2 2.1 International standards . 2 2.2 Publicly-available specifications 2 3 Terms, definitions, notations and conventions 3 3.1 Terms and definitions 3 3.2 Notations. 10 3.2.1 Notations provided in ISO/IEC 13249-1 10 3.2.2 Notations provided in thi
9、s part of ISO/IEC 13249 10 3.3 Conventions . 11 4 Concepts. 12 4.1 Data mining techniques. 12 4.2 Computational phases. 12 4.2.1 Training phase 12 4.2.2 Model introspection phase 13 4.2.3 Application phase 15 4.2.4 Testing phase . 16 4.3 Mapping on user-defined types 17 4.3.1 Target application 17 4
10、.3.2 The relationships of the user-defined types . 17 4.3.3 User-defined types that are not related to mining techniques 19 4.3.4 User-defined types that are related to mining techniques 19 5 Data Mining Data Types. 22 5.1 DM_LogicalDataSpec Type and Routines . 22 5.1.1 DM_LogicalDataSpec Type . 22
11、5.1.2 DM_addDataSpecFld Method . 24 5.1.3 DM_remDataSpecFld Method . 25 5.1.4 DM_getNumFields Method 26 5.1.5 DM_getFldName Method . 27 5.1.6 DM_setFldType Method. 28 5.1.7 DM_getFldType Method. 30 5.1.8 DM_isCompatible Method . 31 5.2 DM_MiningData Type and Routines. 32 5.2.1 DM_MiningData Type. 32
12、 5.2.2 DM_defMiningData Method. 34 5.2.3 DM_setFldAlias Method. 35 5.2.4 DM_genDataSpec Method. 36 5.3 DM_ApplicationData Type and Routines. 37 5.3.1 DM_ApplicationData Type. 37 5.3.2 DM_genDataSpec Method. 38 5.3.3 DM_impApplData Method 39 6 Association Rules 40 INCITS/ISO/IEC 13249-6:20062007 ITIC
13、 2007 All rights reservediv 6.1 DM_RuleSettings Type and Routines 40 6.1.1 DM_RuleSettings Type 40 6.1.2 DM_impRuleSettings Method . 43 6.1.3 DM_expRuleSettings Method . 44 6.1.4 DM_setRuleFilter Method 45 6.1.5 DM_getRuleFilter Method 46 6.1.6 DM_setMinSupport Method 47 6.1.7 DM_getMinSupport Metho
14、d 48 6.1.8 DM_setMinConf Method 49 6.1.9 DM_getMinConf Method 50 6.1.10 DM_setMaxLength Method . 51 6.1.11 DM_getMaxLength Method . 52 6.1.12 DM_useRuleDataSpec Method . 53 6.1.13 DM_getRuleDataSpec Method 54 6.1.14 DM_setGroup Method 55 6.1.15 DM_getGroup Method 56 6.1.16 DM_setSequence Method . 57
15、 6.1.17 DM_getSequence Method . 58 6.2 DM_RuleBldTask type and Routines . 59 6.2.1 DM_RuleBldTask Type 59 6.2.2 DM_defRuleBldTask Method 60 6.2.3 DM_getRuleTrnData Method. 61 6.2.4 DM_getRuleSettings Method 62 6.2.5 DM_buildRuleModel Method. 63 6.3 DM_RuleModel Type and Routines 64 6.3.1 DM_RuleMode
16、l Type 64 6.3.2 DM_impRuleModel Method . 67 6.3.3 DM_getRuleMdlType Method 68 6.3.4 DM_expRuleModel Method . 69 6.3.5 DM_applyRuleModel Method 70 6.3.6 DM_getNumItemSets Method . 71 6.3.7 DM_getNumSequences Method . 72 6.3.8 DM_getNumRules Method 73 6.3.9 DM_filterRules Method 74 6.3.10 DM_getNumTra
17、nsacts Method . 75 6.3.11 DM_getItemSets Method . 76 6.3.12 DM_getRules Method. 77 6.3.13 DM_getRuleBodies Method 78 6.3.14 DM_getSequences Method . 79 6.3.15 DM_getSeqDetails Method 80 6.3.16 DM_getSeqRules Method 81 6.3.17 DM_getRuleBldTask method 83 6.4 DM_RuleFilter Type and Routines 84 6.4.1 DM
18、_RuleFilter Type 84 6.4.2 DM_addRangeConstr Method. 86 6.4.3 DM_remRangeConstr Method 88 6.4.4 DM_getRangeConstrs Method 89 6.4.5 DM_setMaxNumRules Method 90 6.4.6 DM_getMaxNumRules Method . 91 6.4.7 DM_addCountConstr Method . 92 6.4.8 DM_remCountConstr Method. 93 6.4.9 DM_getCountConstrs Method 94
19、6.4.10 DM_setItemConstr Method . 95 6.4.11 DM_getItemConstrs Method . 97 6.5 DM_RuleApplTask Type and Routines 98 6.5.1 DM_RuleApplTask Type 98 6.5.2 DM_defRuleApplTask Method 100 6.5.3 DM_getRuleMdl Method 102 INCITS/ISO/IEC 13249-6:20062007 ITIC 2007 All rights reservedv6.5.4 DM_getRuleApplData Me
20、thod. 103 6.5.5 DM_getRuleOutpData Method 104 6.5.6 DM_getRuleGroupFld method 105 6.5.7 DM_applyRuleMdl method 106 7 Clustering . 107 7.1 DM_ClusSettings Type and Routines 107 7.1.1 DM_ClusSettings Type 107 7.1.2 DM_impClusSettings Method . 109 7.1.3 DM_expClusSettings Method . 110 7.1.4 DM_setMaxNu
21、mClus Method 111 7.1.5 DM_getMaxNumClus Method . 112 7.1.6 DM_setFldWeight Method . 113 7.1.7 DM_getFldWeight Method. 114 7.1.8 DM_setFldSimScale Method . 115 7.1.9 DM_getFldSimScale Method. 116 7.1.10 DM_useClusDataSpec Method . 117 7.1.11 DM_getClusDataSpec Method 118 7.2 DM_ClusBldTask type and R
22、outines . 119 7.2.1 DM_ClusBldTask Type 119 7.2.2 DM_defClusBldTask Method 120 7.2.3 DM_getClusTrnData Method. 121 7.2.4 DM_getClusSettings Method 122 7.2.5 DM_buildClusModel Method. 123 7.3 DM_ClusteringModel Type and Routines 124 7.3.1 DM_ClusteringModel Type 124 7.3.2 DM_impClusModel Method . 126
23、 7.3.3 DM_expClusModel Method . 127 7.3.4 DM_getNumClusters Method 128 7.3.5 DM_getClusters Method 129 7.3.6 DM_getMdlQuality Method 130 7.3.7 DM_applyClusModel Method 131 7.3.8 DM_getClusTask method 132 7.3.9 DM_getClusMdlSpec method . 133 7.3.10 DM_getFields 134 7.4 DM_ClusApplTask Type and Routin
24、es 135 7.4.1 DM_ClusApplTask Type 135 7.4.2 DM_defClusApplTask Method 137 7.4.3 DM_getClusMdl Method 138 7.4.4 DM_getClusApplData Method. 139 7.4.5 DM_getClusOutpData Method 140 7.4.6 DM_getClusResFld method 141 7.4.7 DM_applyClusMdl method 142 7.5 DM_ClusResult Type and Routines . 143 7.5.1 DM_Clus
25、Result Type . 143 7.5.2 DM_getClusterID Method 144 7.5.3 DM_getQuality Method 145 8 Classification 146 8.1 DM_ClasSettings Type and Routines 146 8.1.1 DM_ClasSettings Type 146 8.1.2 DM_impClasSettings Method . 149 8.1.3 DM_expClasSettings Method 150 8.1.4 DM_setClasCostRate Method . 151 8.1.5 DM_get
26、ClasCostRate Method. 152 8.1.6 DM_setClasCost Method. 153 8.1.7 DM_getClasCost Method. 154 8.1.8 DM_useClasDataSpec Method . 155 INCITS/ISO/IEC 13249-6:20062007 ITIC 2007 All rights reservedvi 8.1.9 DM_getClasDataSpec Method 156 8.1.10 DM_setClasTarget Method 157 8.1.11 DM_getClasTarget Method 158 8
27、.2 DM_ClasBldTask Type and Routines. 159 8.2.1 DM_ClasBldTask Type 159 8.2.2 DM_defClasBldTask Method. 161 8.2.3 DM_getClasTrnData Method . 162 8.2.4 DM_getClasValData Method . 163 8.2.5 DM_getClasSettings Method 164 8.2.6 DM_buildClasModel Method . 165 8.3 DM_ClasModel Type and Routines 166 8.3.1 D
28、M_ClasModel Type 166 8.3.2 DM_impClasModel Method . 169 8.3.3 DM_expClasModel Method . 170 8.3.4 DM_applyClasModel Method 171 8.3.5 DM_testClasModel Method . 172 8.3.6 DM_getClasCostRate Method. 173 8.3.7 DM_isValidated Method. 174 8.3.8 DM_getRankQuality method. 175 8.3.9 DM_getPredAccuracy Method
29、176 8.3.10 DM_getReliability Method . 177 8.3.11 DM_getMdlQuality Method 178 8.3.12 DM_getGainsChart method. 179 8.3.13 DM_getClasTask method 180 8.3.14 DM_getClasMdlSpec method 181 8.3.15 DM_getFields 182 8.3.16 DM_getClasTarget method . 183 8.4 DM_ClasTestTask Type and Routines. 184 8.4.1 DM_ClasT
30、estTask Type. 184 8.4.2 DM_defClasTestTask Method. 185 8.4.3 DM_getClasTestData Method . 186 8.4.4 DM_getClasTestMdl Method . 187 8.4.5 DM_testClasMdl Method . 188 8.5 DM_ClasTestResult Type and Routines 189 8.5.1 DM_ClasTestResult Type 189 8.5.2 DM_getClasError Method 191 8.5.3 DM_getRankQuality Me
31、thod . 192 8.5.4 DM_getPredAccuracy Method 193 8.5.5 DM_getReliability Method . 194 8.5.6 DM_getMdlQuality Method 195 8.5.7 DM_getGainsChart Method. 196 8.5.8 DM_getNumClasses Method. 197 8.5.9 DM_getClass Method. 198 8.5.10 DM_getClasPreds Method. 199 8.6 DM_ClasApplTask Type and Routines 200 8.6.1
32、 DM_ClasApplTask Type 200 8.6.2 DM_defClasApplTask Method 202 8.6.3 DM_getClasMdl Method 203 8.6.4 DM_getClasApplData Method. 204 8.6.5 DM_getClasOutpData Method 205 8.6.6 DM_getClasResFld method 206 8.6.7 DM_applyClasMdl method 207 8.7 DM_ClasResult Type and Routines 208 8.7.1 DM_ClasResult Type 20
33、8 8.7.2 DM_getPredClass Method. 209 8.7.3 DM_getConfidence Method. 210 INCITS/ISO/IEC 13249-6:20062007 ITIC 2007 All rights reservedvii 9 Regression 211 9.1 DM_RegSettings Type and Routines . 211 9.1.1 DM_RegSettings Type . 211 9.1.2 DM_impRegSettings Method 213 9.1.3 DM_expRegSettings Method 214 9.
34、1.4 DM_setRegRSquared Method. 215 9.1.5 DM_getRegRSquared Method 216 9.1.6 DM_useRegDataSpec Method 217 9.1.7 DM_getRegDataSpec Method . 218 9.1.8 DM_setRegTarget Method. 219 9.1.9 DM_getRegTarget Method 220 9.2 DM_RegBldTask type and Routines 221 9.2.1 DM_RegBldTask Type . 221 9.2.2 DM_defRegBldTas
35、k Method . 223 9.2.3 DM_getRegTrnData Method 224 9.2.4 DM_getRegValData Method 225 9.2.5 DM_getRegSettings Method . 226 9.2.6 DM_buildRegModel Method 227 9.3 DM_RegressionModel Type and Routines 228 9.3.1 DM_RegressionModel Type 228 9.3.2 DM_impRegModel Method 231 9.3.3 DM_expRegModel Method 232 9.3
36、.4 DM_applyRegModel Method . 233 9.3.5 DM_testRegModel Method 234 9.3.6 DM_getRegRSquared method 235 9.3.7 DM_isValidated Method. 236 9.3.8 DM_getRankQuality Method . 237 9.3.9 DM_getPredAccuracy Method 238 9.3.10 DM_getReliability Method . 239 9.3.11 DM_getMdlQuality Method 240 9.3.12 DM_getRMSE Me
37、thod 241 9.3.13 DM_getGainsChart method. 242 9.3.14 DM_getRegTask method . 243 9.3.15 DM_getRegMdlSpec method 244 9.3.16 DM_getFields method 245 9.3.17 DM_getRegTarget method 246 9.4 DM_RegTestTask Type and Routines 247 9.4.1 DM_RegTestTask Type 247 9.4.2 DM_defRegTestTask Method 248 9.4.3 DM_getReg
38、TestData Method 249 9.4.4 DM_getRegTestMdl Method 250 9.4.5 DM_testRegMdl Method 251 9.5 DM_RegTestResult Type and Routines. 252 9.5.1 DM_RegTestResult Type. 252 9.5.2 DM_getPredError Method 254 9.5.3 DM_getRankQuality Method . 255 9.5.4 DM_getPredAccuracy Method 256 9.5.5 DM_getReliability Method .
39、 257 9.5.6 DM_getMdlQuality 258 9.5.7 DM_getRMSE Method 259 9.5.8 DM_getGainsChart Method. 260 9.6 DM_RegApplTask Type and Routines . 261 9.6.1 DM_RegApplTask Type . 261 9.6.2 DM_defRegApplTask Method . 263 9.6.3 DM_getRegMdl Method . 264 9.6.4 DM_getRegApplData Method 265 9.6.5 DM_getRegOutpData Me
40、thod . 266 INCITS/ISO/IEC 13249-6:20062007 ITIC 2007 All rights reservedviii 9.6.6 DM_getRegResFld method . 267 9.6.7 DM_applyRegMdl method . 268 9.7 DM_RegResult Type and Routines 269 9.7.1 DM_RegResult Type 269 9.7.2 DM_getPredValue Method. 270 10 Status Codes 271 11 Conformance 273 11.1 Requireme
41、nts for conformance 273 11.1.1 Support for user-defined types and functions 273 11.1.2 Support for data mining phases. 273 11.1.3 Support for basic user-defined types 273 11.1.4 Support for data mining techniques 273 11.2 Claims of conformance . 274 Annex A (informative) Implementation-defined Eleme
42、nts 276 Annex B (informative) Implementation-dependent elements . 278Annex C (informative) A Scenario Using the Classification Technique. 279Index . 281 Figures Page Figure 1 The training phase 13 Figure 2 Gains chart. 15 Figure 3 The application phase. 15 Figure 4 The testing phase 17 Figure 5 Over
43、view of user-defined types for the training phase. 17 Figure 6 Overview of user-defined types for training, testing and application . 18 Figure 7 Overview of user-defined types for bulk application 19 Tables Page Table 1 Model interpretation . 13 Table 2 Gains chart information . 14 Table 3 Items in
44、ferred from an association rule model 16 Table 4 Groups of items inferred from an association rule model . 16 Table 5 Values for field types 28 Table 6 Values for operators . 86 Table 7 Values for restriction criteria. 87 Table 8 Values for constraint types 95 Table 9 SQLSTATE class and subclass val
45、ues. 272 INCITS/ISO/IEC 13249-6:20062007 ITIC 2007 All rights reservedix Foreword ISO (the International Organization for Standardization) and IEC (the International Electrotechnical Commission) form the specialized system for worldwide standardization. National bodies that are members of ISO or IEC
46、 participate in the development of International Standards through technical committees established by the respective organization to deal with particular fields of technical activity. ISO and IEC technical committees collaborate in fields of mutual interest. Other international organizations, gover
47、nmental and non-governmental, in liaison with ISO and IEC, also take part in the work. In the field of information technology, ISO and IEC have established a joint technical committee, ISO/IEC JTC 1. International Standards are drafted in accordance with the rules given in the ISO/IEC Directives, Pa
48、rt 2. The main task of the joint technical committee is to prepare International Standards. Draft International Standards adopted by the joint technical committee are circulated to national bodies for voting. Publication as an International Standard requires approval by at least 75 % of the national
49、 bodies casting a vote. Attention is drawn to the possibility that some of the elements of this document may be the subject of patent rights. ISO and IEC shall not be held responsible for identifying any or all such patent rights. ISO/IEC 13249-6 was prepared by Joint Technical Committee ISO/IEC JTC 1, Information technology, Subcommittee SC 32, Data management and interchange. This second edition cancels and replaces the first edition (ISO/IEC 13249-6:2002), which has been technically revised. ISO/IEC 13249 consist
