report almost done

clustering/org.apache.xerces.dom.CoreDocumentImpl_silhouette.csv

@@ -1,45 +1,45 @@
 ,k_means,hierarchical
-2,0.7008424223503156,0.3958383820498147
+2,0.3958383820498147,0.7008424223503156
-3,0.5710705368479275,0.4083355324423938
+3,0.4083355324423938,0.5710705368479275
-4,0.5612355754261723,0.4894345431495262
+4,0.4894345431495262,0.5612355754261723
-5,0.45447105698494905,0.49390485171067744
+5,0.49390485171067744,0.45447105698494905
-6,0.4542950961743021,0.49437178337314974
+6,0.49437178337314974,0.4542950961743021
-7,0.5169337345938171,0.4996628258355101
+7,0.4996628258355101,0.5169337345938171
-8,0.5048012323625627,0.504680719000111
+8,0.504680719000111,0.5048012323625627
-9,0.4981437021345769,0.5104029882614454
+9,0.5104029882614454,0.4981437021345769
-10,0.514873610056946,0.39391549620101274
+10,0.39391549620101274,0.514873610056946
-11,0.4397616290614397,0.35593829934237226
+11,0.35593829934237226,0.4397616290614397
-12,0.3966368345309925,0.3965649809723018
+12,0.3965649809723018,0.3966368345309925
-13,0.40515142998089104,0.4035942512051252
+13,0.4035942512051252,0.40515142998089104
-14,0.40783453521401053,0.41018624058063885
+14,0.41018624058063885,0.40783453521401053
-15,0.4239033913796109,0.45557751119565765
+15,0.45557751119565765,0.4239033913796109
-16,0.42065530265413026,0.47640709656766556
+16,0.47640709656766556,0.42065530265413026
-17,0.44344469866152514,0.4974425160835303
+17,0.4974425160835303,0.44344469866152514
-18,0.4400719065542468,0.5290487299051633
+18,0.5290487299051633,0.4400719065542468
-19,0.44608395823875535,0.5485454650471248
+19,0.5485454650471248,0.44608395823875535
-20,0.44877269935654723,0.5586056973417746
+20,0.5586056973417746,0.44877269935654723
-21,0.48118392208651517,0.5385866967307906
+21,0.5385866967307906,0.48118392208651517
-22,0.48389798035280496,0.538222592035968
+22,0.538222592035968,0.48389798035280496
-23,0.48663428414368126,0.550727295003801
+23,0.550727295003801,0.48663428414368126
-24,0.5087496231379599,0.5729072600132372
+24,0.5729072600132372,0.5087496231379599
-25,0.5308958702007723,0.5954078415061489
+25,0.5954078415061489,0.5308958702007723
-26,0.533742178035476,0.6182602907647171
+26,0.6182602907647171,0.533742178035476
-27,0.5366335268898433,0.6415000474402278
+27,0.6415000474402278,0.5366335268898433
-28,0.5688721496510291,0.6464201697751911
+28,0.6464201697751911,0.5688721496510291
-29,0.5718756117789308,0.6701951689242575
+29,0.6701951689242575,0.5718756117789308
-30,0.5749678644659783,0.6738663960033637
+30,0.6738663960033637,0.5749678644659783
-31,0.5975986067541601,0.6776704976739869
+31,0.6776704976739869,0.5975986067541601
-32,0.6010454124801283,0.6759936834928909
+32,0.6759936834928909,0.6010454124801283
-33,0.6047324451505658,0.6780082327270405
+33,0.6780082327270405,0.6047324451505658
-34,0.6087467116081876,0.6819745883778254
+34,0.6819745883778254,0.6087467116081876
-35,0.613131689815019,0.6860900076219251
+35,0.6860900076219251,0.613131689815019
-36,0.6386708325196511,0.6921336553243742
+36,0.6921336553243742,0.6386708325196511
-37,0.6449490032291169,0.6964066920515507
+37,0.6964066920515507,0.6449490032291169
-38,0.6764810977640761,0.6932020971027025
+38,0.6932020971027025,0.6764810977640761
-39,0.6773895830074159,0.6977143227629022
+39,0.6977143227629022,0.6773895830074159
-40,0.6918179479278735,0.7024070374495096
+40,0.7024070374495096,0.6918179479278735
-41,0.6964034645667346,0.7072912915110808
+41,0.7072912915110808,0.6964034645667346
-42,0.7024471122691838,0.712379056158551
+42,0.712379056158551,0.7024471122691838
-43,0.7256701207957181,0.7176833214293175
+43,0.7176833214293175,0.7256701207957181
-44,0.7230610997944976,0.7232182069292477
+44,0.7232182069292477,0.7230610997944976
-45,0.7289990873402858,0.7289990873402857
+45,0.7289990873402857,0.7289990873402858

clustering/org.apache.xerces.dom.CoreDocumentImpl_stats.csv

@@ -0,0 +1,89 @@
+,algorithm,k,min,mean,max
+0,hierarchical,2,1,58.5,116
+1,k_means,2,1,58.5,116
+2,hierarchical,3,1,39.0,113
+3,k_means,3,1,39.0,115
+4,hierarchical,4,1,29.25,113
+5,k_means,4,1,29.25,98
+6,hierarchical,5,1,23.4,111
+7,k_means,5,1,23.4,98
+8,hierarchical,6,1,19.5,111
+9,k_means,6,1,19.5,98
+10,hierarchical,7,1,16.714285714285715,97
+11,k_means,7,1,16.714285714285715,98
+12,hierarchical,8,1,14.625,97
+13,k_means,8,1,14.625,98
+14,hierarchical,9,1,13.0,96
+15,k_means,9,1,13.0,97
+16,hierarchical,10,1,11.7,96
+17,k_means,10,1,11.7,92
+18,hierarchical,11,1,10.636363636363637,93
+19,k_means,11,1,10.636363636363637,89
+20,hierarchical,12,1,9.75,86
+21,k_means,12,1,9.75,84
+22,hierarchical,13,1,9.0,84
+23,k_means,13,1,9.0,83
+24,hierarchical,14,1,8.357142857142858,84
+25,k_means,14,1,8.357142857142858,83
+26,hierarchical,15,1,7.8,84
+27,k_means,15,1,7.8,77
+28,hierarchical,16,1,7.3125,84
+29,k_means,16,1,7.3125,75
+30,hierarchical,17,1,6.882352941176471,79
+31,k_means,17,1,6.882352941176471,73
+32,hierarchical,18,1,6.5,79
+33,k_means,18,1,6.5,70
+34,hierarchical,19,1,6.157894736842105,46
+35,k_means,19,1,6.157894736842105,70
+36,hierarchical,20,1,5.85,46
+37,k_means,20,1,5.85,70
+38,hierarchical,21,1,5.571428571428571,46
+39,k_means,21,1,5.571428571428571,70
+40,hierarchical,22,1,5.318181818181818,46
+41,k_means,22,1,5.318181818181818,70
+42,hierarchical,23,1,5.086956521739131,46
+43,k_means,23,1,5.086956521739131,68
+44,hierarchical,24,1,4.875,46
+45,k_means,24,1,4.875,66
+46,hierarchical,25,1,4.68,46
+47,k_means,25,1,4.68,64
+48,hierarchical,26,1,4.5,46
+49,k_means,26,1,4.5,62
+50,hierarchical,27,1,4.333333333333333,46
+51,k_means,27,1,4.333333333333333,60
+52,hierarchical,28,1,4.178571428571429,46
+53,k_means,28,1,4.178571428571429,60
+54,hierarchical,29,1,4.0344827586206895,46
+55,k_means,29,1,4.0344827586206895,58
+56,hierarchical,30,1,3.9,46
+57,k_means,30,1,3.9,57
+58,hierarchical,31,1,3.774193548387097,46
+59,k_means,31,1,3.774193548387097,56
+60,hierarchical,32,1,3.65625,46
+61,k_means,32,1,3.65625,56
+62,hierarchical,33,1,3.5454545454545454,46
+63,k_means,33,1,3.5454545454545454,56
+64,hierarchical,34,1,3.4411764705882355,46
+65,k_means,34,1,3.4411764705882355,55
+66,hierarchical,35,1,3.342857142857143,46
+67,k_means,35,1,3.342857142857143,54
+68,hierarchical,36,1,3.25,46
+69,k_means,36,1,3.25,54
+70,hierarchical,37,1,3.1621621621621623,46
+71,k_means,37,1,3.1621621621621623,53
+72,hierarchical,38,1,3.0789473684210527,46
+73,k_means,38,1,3.0789473684210527,53
+74,hierarchical,39,1,3.0,46
+75,k_means,39,1,3.0,52
+76,hierarchical,40,1,2.925,46
+77,k_means,40,1,2.925,51
+78,hierarchical,41,1,2.8536585365853657,46
+79,k_means,41,1,2.8536585365853657,50
+80,hierarchical,42,1,2.7857142857142856,46
+81,k_means,42,1,2.7857142857142856,49
+82,hierarchical,43,1,2.7209302325581395,46
+83,k_means,43,1,2.7209302325581395,48
+84,hierarchical,44,1,2.659090909090909,46
+85,k_means,44,1,2.659090909090909,47
+86,hierarchical,45,1,2.6,46
+87,k_means,45,1,2.6,46

clustering/org.apache.xerces.impl.dtd.DTDGrammar_hierarchical.csv

@@ -1,92 +1,92 @@
 ,cluster
-getGrammarDescription,5
+getGrammarDescription,0
 getElementDeclIsExternal,0
 getAttributeDeclIsExternal,0
-getAttributeDeclIndex,42
+getAttributeDeclIndex,0
-startDTD,2
+startDTD,0
-startParameterEntity,6
+startParameterEntity,0
-startExternalSubset,41
+startExternalSubset,0
-endParameterEntity,6
+endParameterEntity,0
-endExternalSubset,41
+endExternalSubset,0
-elementDecl,31
+elementDecl,1
-attributeDecl,39
+attributeDecl,1
-internalEntityDecl,40
+internalEntityDecl,0
-externalEntityDecl,40
+externalEntityDecl,0
-unparsedEntityDecl,40
+unparsedEntityDecl,0
-notationDecl,38
+notationDecl,0
-endDTD,8
+endDTD,0
-setDTDSource,23
+setDTDSource,0
-getDTDSource,23
+getDTDSource,0
-textDecl,5
+textDecl,0
-comment,5
+comment,0
-processingInstruction,5
+processingInstruction,0
-startAttlist,5
+startAttlist,0
-endAttlist,5
+endAttlist,0
-startConditional,5
+startConditional,0
-ignoredCharacters,5
+ignoredCharacters,0
-endConditional,5
+endConditional,0
-setDTDContentModelSource,11
+setDTDContentModelSource,0
-getDTDContentModelSource,11
+getDTDContentModelSource,0
-startContentModel,33
+startContentModel,0
-startGroup,53
+startGroup,0
-pcdata,51
+pcdata,0
-element,34
+element,0
-separator,44
+separator,0
-occurrence,32
+occurrence,0
-endGroup,35
+endGroup,0
-any,5
+any,0
-empty,5
+empty,0
-endContentModel,5
+endContentModel,0
-isNamespaceAware,5
+isNamespaceAware,0
-getSymbolTable,52
+getSymbolTable,0
-getFirstElementDeclIndex,7
+getFirstElementDeclIndex,0
-getNextElementDeclIndex,7
+getNextElementDeclIndex,0
-getElementDeclIndex,55
+getElementDeclIndex,0
-getContentSpecType,37
+getContentSpecType,0
-getElementDecl,54
+getElementDecl,0
-getElementDeclName,8
+getElementDeclName,0
-getFirstAttributeDeclIndex,20
+getFirstAttributeDeclIndex,0
-getNextAttributeDeclIndex,57
+getNextAttributeDeclIndex,0
-getAttributeDecl,28
+getAttributeDecl,0
-isCDATAAttribute,47
+isCDATAAttribute,0
-getEntityDeclIndex,5
+getEntityDeclIndex,0
-getEntityDecl,1
+getEntityDecl,0
-getNotationDeclIndex,5
+getNotationDeclIndex,0
-getNotationDecl,10
+getNotationDecl,0
-getContentSpec,9
+getContentSpec,0
-getContentSpecIndex,19
+getContentSpecIndex,0
-getContentSpecAsString,43
+getContentSpecAsString,0
-printElements,50
+printElements,0
-printAttributes,49
+printAttributes,0
-addContentSpecToElement,29
+addContentSpecToElement,0
-getElementContentModelValidator,25
+getElementContentModelValidator,0
-createElementDecl,36
+createElementDecl,0
-setElementDecl,17
+setElementDecl,0
-putElementNameMapping,5
+putElementNameMapping,0
-setFirstAttributeDeclIndex,20
+setFirstAttributeDeclIndex,0
-setContentSpecIndex,19
+setContentSpecIndex,0
-createAttributeDecl,18
+createAttributeDecl,0
-setAttributeDecl,48
+setAttributeDecl,0
-createContentSpec,21
+createContentSpec,0
-setContentSpec,9
+setContentSpec,0
-createEntityDecl,16
+createEntityDecl,0
-setEntityDecl,1
+setEntityDecl,0
-createNotationDecl,56
+createNotationDecl,0
-setNotationDecl,10
+setNotationDecl,0
-addContentSpecNode,4
+addContentSpecNode,0
-addUniqueLeafNode,4
+addUniqueLeafNode,0
-initializeContentModelStack,2
+initializeContentModelStack,0
-isImmutable,24
+isImmutable,0
-appendContentSpec,45
+appendContentSpec,0
-printAttribute,26
+printAttribute,0
-createChildModel,3
+createChildModel,0
-buildSyntaxTree,3
+buildSyntaxTree,0
-contentSpecTree,46
+contentSpecTree,0
-ensureElementDeclCapacity,27
+ensureElementDeclCapacity,0
-ensureAttributeDeclCapacity,30
+ensureAttributeDeclCapacity,0
-ensureEntityDeclCapacity,14
+ensureEntityDeclCapacity,0
-ensureNotationDeclCapacity,13
+ensureNotationDeclCapacity,0
-ensureContentSpecCapacity,12
+ensureContentSpecCapacity,0
-resize,5
+resize,0
-isEntityDeclared,22
+isEntityDeclared,0
-isEntityUnparsed,15
+isEntityUnparsed,0

clustering/org.apache.xerces.impl.dtd.DTDGrammar_kmeans.csv

@@ -1,92 +1,92 @@
 ,cluster
-getGrammarDescription,1
+getGrammarDescription,6
-getElementDeclIsExternal,0
+getElementDeclIsExternal,50
-getAttributeDeclIsExternal,0
+getAttributeDeclIsExternal,43
-getAttributeDeclIndex,1
+getAttributeDeclIndex,36
-startDTD,1
+startDTD,13
-startParameterEntity,1
+startParameterEntity,23
-startExternalSubset,1
+startExternalSubset,54
-endParameterEntity,1
+endParameterEntity,23
-endExternalSubset,1
+endExternalSubset,54
-elementDecl,0
+elementDecl,5
-attributeDecl,0
+attributeDecl,4
-internalEntityDecl,1
+internalEntityDecl,17
-externalEntityDecl,1
+externalEntityDecl,17
-unparsedEntityDecl,1
+unparsedEntityDecl,17
-notationDecl,1
+notationDecl,40
-endDTD,0
+endDTD,29
-setDTDSource,1
+setDTDSource,53
-getDTDSource,1
+getDTDSource,53
-textDecl,1
+textDecl,6
-comment,1
+comment,6
-processingInstruction,1
+processingInstruction,6
-startAttlist,1
+startAttlist,6
-endAttlist,1
+endAttlist,6
-startConditional,1
+startConditional,6
-ignoredCharacters,1
+ignoredCharacters,6
-endConditional,1
+endConditional,6
-setDTDContentModelSource,1
+setDTDContentModelSource,51
-getDTDContentModelSource,1
+getDTDContentModelSource,51
-startContentModel,1
+startContentModel,28
-startGroup,1
+startGroup,39
-pcdata,1
+pcdata,52
-element,1
+element,2
-separator,1
+separator,49
-occurrence,1
+occurrence,24
-endGroup,1
+endGroup,27
-any,1
+any,6
-empty,1
+empty,6
-endContentModel,1
+endContentModel,6
-isNamespaceAware,1
+isNamespaceAware,6
-getSymbolTable,1
+getSymbolTable,56
-getFirstElementDeclIndex,1
+getFirstElementDeclIndex,47
-getNextElementDeclIndex,1
+getNextElementDeclIndex,47
-getElementDeclIndex,1
+getElementDeclIndex,57
-getContentSpecType,0
+getContentSpecType,38
 getElementDecl,0
-getElementDeclName,0
+getElementDeclName,29
-getFirstAttributeDeclIndex,0
+getFirstAttributeDeclIndex,3
-getNextAttributeDeclIndex,0
+getNextAttributeDeclIndex,46
-getAttributeDecl,0
+getAttributeDecl,25
-isCDATAAttribute,1
+isCDATAAttribute,44
-getEntityDeclIndex,1
+getEntityDeclIndex,6
-getEntityDecl,0
+getEntityDecl,8
-getNotationDeclIndex,1
+getNotationDeclIndex,6
-getNotationDecl,0
+getNotationDecl,10
-getContentSpec,0
+getContentSpec,41
-getContentSpecIndex,0
+getContentSpecIndex,12
-getContentSpecAsString,0
+getContentSpecAsString,37
-printElements,1
+printElements,55
-printAttributes,1
+printAttributes,35
-addContentSpecToElement,1
+addContentSpecToElement,20
-getElementContentModelValidator,0
+getElementContentModelValidator,21
-createElementDecl,0
+createElementDecl,33
-setElementDecl,0
+setElementDecl,16
-putElementNameMapping,1
+putElementNameMapping,6
-setFirstAttributeDeclIndex,0
+setFirstAttributeDeclIndex,3
-setContentSpecIndex,0
+setContentSpecIndex,12
-createAttributeDecl,0
+createAttributeDecl,19
-setAttributeDecl,0
+setAttributeDecl,7
-createContentSpec,0
+createContentSpec,41
-setContentSpec,0
+setContentSpec,9
-createEntityDecl,0
+createEntityDecl,31
-setEntityDecl,0
+setEntityDecl,8
-createNotationDecl,1
+createNotationDecl,32
-setNotationDecl,0
+setNotationDecl,10
-addContentSpecNode,1
+addContentSpecNode,18
-addUniqueLeafNode,1
+addUniqueLeafNode,18
-initializeContentModelStack,1
+initializeContentModelStack,13
-isImmutable,1
+isImmutable,6
-appendContentSpec,1
+appendContentSpec,42
 printAttribute,1
-createChildModel,1
+createChildModel,11
-buildSyntaxTree,1
+buildSyntaxTree,11
-contentSpecTree,1
+contentSpecTree,30
-ensureElementDeclCapacity,1
+ensureElementDeclCapacity,15
-ensureAttributeDeclCapacity,1
+ensureAttributeDeclCapacity,14
-ensureEntityDeclCapacity,1
+ensureEntityDeclCapacity,22
-ensureNotationDeclCapacity,1
+ensureNotationDeclCapacity,26
-ensureContentSpecCapacity,1
+ensureContentSpecCapacity,34
-resize,1
+resize,6
-isEntityDeclared,1
+isEntityDeclared,48
-isEntityUnparsed,0
+isEntityUnparsed,45

clustering/org.apache.xerces.impl.dtd.DTDGrammar_silhouette.csv

@@ -1,64 +1,64 @@
 ,k_means,hierarchical
-2,0.43549549160206547,0.22916634455195753
+2,0.22916634455195753,0.43549549160206547
-3,0.3737398924595095,0.2246280732293034
+3,0.2246280732293034,0.3737398924595095
-4,0.3557451009153901,0.22489420158108267
+4,0.22489420158108267,0.3557451009153901
-5,0.23295505680144496,0.23659327576115802
+5,0.23659327576115802,0.23295505680144496
-6,0.262133112331066,0.1944787865029721
+6,0.1944787865029721,0.262133112331066
-7,0.2578980101543562,0.14449036253228517
+7,0.14449036253228517,0.2578980101543562
-8,0.2549368125378225,0.14148366678653188
+8,0.14148366678653188,0.2549368125378225
-9,0.2774793093993747,0.13842552961645824
+9,0.13842552961645824,0.2774793093993747
-10,0.29633149188806335,0.17251507022640497
+10,0.17251507022640497,0.29633149188806335
-11,0.28457149559807815,0.20347568890084347
+11,0.20347568890084347,0.28457149559807815
-12,0.2774764884391462,0.23906895503283213
+12,0.23906895503283213,0.2774764884391462
-13,0.2807117319594596,0.2433263434151139
+13,0.2433263434151139,0.2807117319594596
-14,0.2756438988231549,0.2378679295617759
+14,0.2378679295617759,0.2756438988231549
-15,0.2725133030686268,0.23691994972126937
+15,0.23691994972126937,0.2725133030686268
-16,0.26609972785171476,0.23116431400607626
+16,0.23116431400607626,0.26609972785171476
-17,0.2622978716191777,0.250626112587838
+17,0.250626112587838,0.2622978716191777
-18,0.2599277555662332,0.25367962227891766
+18,0.25367962227891766,0.2599277555662332
-19,0.2627008352505403,0.27152241207311917
+19,0.27152241207311917,0.2627008352505403
-20,0.27904812684322156,0.2937526253744639
+20,0.2937526253744639,0.27904812684322156
-21,0.2862853638532431,0.29866907908096096
+21,0.29866907908096096,0.2862853638532431
-22,0.28363618305324206,0.2982900685039696
+22,0.2982900685039696,0.28363618305324206
-23,0.27298124922178313,0.29267556171442216
+23,0.29267556171442216,0.27298124922178313
-24,0.2755401967064185,0.30932258932020334
+24,0.30932258932020334,0.2755401967064185
-25,0.2699256899168711,0.30931433471981734
+25,0.30931433471981734,0.2699256899168711
-26,0.27327610109462835,0.309284891816073
+26,0.309284891816073,0.27327610109462835
-27,0.2741779110906256,0.30820922828647973
+27,0.30820922828647973,0.2741779110906256
-28,0.2772726745209296,0.306394576589556
+28,0.306394576589556,0.2772726745209296
-29,0.2763152122041744,0.31629054291989955
+29,0.31629054291989955,0.2763152122041744
-30,0.27822954116587556,0.31889378927031037
+30,0.31889378927031037,0.27822954116587556
-31,0.2765547788352012,0.31793632695355517
+31,0.31793632695355517,0.2765547788352012
-32,0.2873045247363621,0.3198803243841521
+32,0.3198803243841521,0.2873045247363621
-33,0.28417974562649284,0.3322984924566154
+33,0.3322984924566154,0.28417974562649284
-34,0.2685472504040367,0.33205224383012144
+34,0.33205224383012144,0.2685472504040367
-35,0.2640970877653046,0.32946433944653786
+35,0.32946433944653786,0.2640970877653046
-36,0.26594127941463497,0.34064178452545657
+36,0.34064178452545657,0.26594127941463497
-37,0.2671662834055061,0.34279546744648637
+37,0.34279546744648637,0.2671662834055061
-38,0.26972862144514015,0.3520414342812306
+38,0.3520414342812306,0.26972862144514015
-39,0.2745566131731437,0.35684038034252413
+39,0.35684038034252413,0.2745566131731437
-40,0.3085760240111521,0.34927826706954956
+40,0.34927826706954956,0.3085760240111521
-41,0.32756637032777863,0.3490443084779255
+41,0.3490443084779255,0.32756637032777863
-42,0.3310796986888577,0.34372287471805796
+42,0.34372287471805796,0.3310796986888577
-43,0.32889480000768656,0.32421890240508233
+43,0.32421890240508233,0.32889480000768656
-44,0.31610864049926274,0.27315698867962007
+44,0.27315698867962007,0.31610864049926274
-45,0.3140921194105564,0.27051011105427114
+45,0.27051011105427114,0.3140921194105564
-46,0.3088953240503273,0.29627121773250714
+46,0.29627121773250714,0.3088953240503273
-47,0.2693097731576138,0.32261382027270064
+47,0.32261382027270064,0.2693097731576138
-48,0.2809797636777669,0.3299248655060567
+48,0.3299248655060567,0.2809797636777669
-49,0.29384518410058824,0.3171387059976329
+49,0.3171387059976329,0.29384518410058824
-50,0.29793575895571417,0.3442080317722919
+50,0.3442080317722919,0.29793575895571417
-51,0.3025569827442159,0.3408776851426114
+51,0.3408776851426114,0.3025569827442159
-52,0.32032808958922193,0.3408776851426114
+52,0.3408776851426114,0.32032808958922193
-53,0.33852852210954587,0.33765907834246356
+53,0.33765907834246356,0.33852852210954587
-54,0.339541278009214,0.36565310355269914
+54,0.36565310355269914,0.339541278009214
-55,0.35774171052953796,0.3818328805784584
+55,0.3818328805784584,0.35774171052953796
-56,0.37594214304986195,0.3866470678901348
+56,0.3866470678901348,0.37594214304986195
-57,0.4080257854586148,0.3919955336887361
+57,0.3919955336887361,0.4080257854586148
-58,0.4046954388289342,0.3979724365432809
+58,0.3979724365432809,0.4046954388289342
-59,0.4046954388289342,0.38857621891133143
+59,0.38857621891133143,0.4046954388289342
-60,0.3931263574608019,0.3953492191827632
+60,0.3953492191827632,0.3931263574608019
-61,0.38155727609266954,0.38748610984623766
+61,0.38748610984623766,0.38155727609266954
-62,0.37132316722174985,0.39516141319506437
+62,0.39516141319506437,0.37132316722174985
-63,0.36810456042160206,0.3850224051641811
+63,0.3850224051641811,0.36810456042160206
-64,0.3565354790534698,0.3785851915638855
+64,0.3785851915638855,0.3565354790534698

clustering/org.apache.xerces.impl.dtd.DTDGrammar_stats.csv

@@ -0,0 +1,127 @@
+,algorithm,k,min,mean,max
+0,hierarchical,2,2,45.5,89
+1,k_means,2,29,45.5,62
+2,hierarchical,3,2,30.333333333333332,85
+3,k_means,3,3,30.333333333333332,62
+4,hierarchical,4,2,22.75,82
+5,k_means,4,3,22.75,56
+6,hierarchical,5,2,18.2,64
+7,k_means,5,3,18.2,55
+8,hierarchical,6,2,15.166666666666666,57
+9,k_means,6,3,15.166666666666666,51
+10,hierarchical,7,1,13.0,57
+11,k_means,7,2,13.0,50
+12,hierarchical,8,1,11.375,57
+13,k_means,8,1,11.375,57
+14,hierarchical,9,1,10.11111111111111,57
+15,k_means,9,1,10.11111111111111,57
+16,hierarchical,10,1,9.1,50
+17,k_means,10,1,9.1,51
+18,hierarchical,11,1,8.272727272727273,46
+19,k_means,11,1,8.272727272727273,50
+20,hierarchical,12,1,7.583333333333333,46
+21,k_means,12,1,7.583333333333333,47
+22,hierarchical,13,1,7.0,46
+23,k_means,13,1,7.0,46
+24,hierarchical,14,1,6.5,46
+25,k_means,14,1,6.5,46
+26,hierarchical,15,1,6.066666666666666,46
+27,k_means,15,1,6.066666666666666,46
+28,hierarchical,16,1,5.6875,46
+29,k_means,16,1,5.6875,46
+30,hierarchical,17,1,5.352941176470588,39
+31,k_means,17,1,5.352941176470588,44
+32,hierarchical,18,1,5.055555555555555,39
+33,k_means,18,1,5.055555555555555,44
+34,hierarchical,19,1,4.7894736842105265,34
+35,k_means,19,1,4.7894736842105265,43
+36,hierarchical,20,1,4.55,34
+37,k_means,20,1,4.55,41
+38,hierarchical,21,1,4.333333333333333,34
+39,k_means,21,1,4.333333333333333,40
+40,hierarchical,22,1,4.136363636363637,34
+41,k_means,22,1,4.136363636363637,40
+42,hierarchical,23,1,3.9565217391304346,31
+43,k_means,23,1,3.9565217391304346,40
+44,hierarchical,24,1,3.7916666666666665,31
+45,k_means,24,1,3.7916666666666665,38
+46,hierarchical,25,1,3.64,31
+47,k_means,25,1,3.64,38
+48,hierarchical,26,1,3.5,31
+49,k_means,26,1,3.5,38
+50,hierarchical,27,1,3.3703703703703702,31
+51,k_means,27,1,3.3703703703703702,38
+52,hierarchical,28,1,3.25,30
+53,k_means,28,1,3.25,38
+54,hierarchical,29,1,3.1379310344827585,30
+55,k_means,29,1,3.1379310344827585,36
+56,hierarchical,30,1,3.033333333333333,30
+57,k_means,30,1,3.033333333333333,35
+58,hierarchical,31,1,2.935483870967742,30
+59,k_means,31,1,2.935483870967742,35
+60,hierarchical,32,1,2.84375,30
+61,k_means,32,1,2.84375,35
+62,hierarchical,33,1,2.757575757575758,30
+63,k_means,33,1,2.757575757575758,33
+64,hierarchical,34,1,2.676470588235294,30
+65,k_means,34,1,2.676470588235294,33
+66,hierarchical,35,1,2.6,30
+67,k_means,35,1,2.6,33
+68,hierarchical,36,1,2.5277777777777777,30
+69,k_means,36,1,2.5277777777777777,33
+70,hierarchical,37,1,2.4594594594594597,30
+71,k_means,37,1,2.4594594594594597,33
+72,hierarchical,38,1,2.3947368421052633,30
+73,k_means,38,1,2.3947368421052633,33
+74,hierarchical,39,1,2.3333333333333335,29
+75,k_means,39,1,2.3333333333333335,32
+76,hierarchical,40,1,2.275,29
+77,k_means,40,1,2.275,32
+78,hierarchical,41,1,2.2195121951219514,29
+79,k_means,41,1,2.2195121951219514,32
+80,hierarchical,42,1,2.1666666666666665,29
+81,k_means,42,1,2.1666666666666665,32
+82,hierarchical,43,1,2.116279069767442,29
+83,k_means,43,1,2.116279069767442,31
+84,hierarchical,44,1,2.0681818181818183,29
+85,k_means,44,1,2.0681818181818183,31
+86,hierarchical,45,1,2.022222222222222,29
+87,k_means,45,1,2.022222222222222,31
+88,hierarchical,46,1,1.9782608695652173,29
+89,k_means,46,1,1.9782608695652173,29
+90,hierarchical,47,1,1.9361702127659575,28
+91,k_means,47,1,1.9361702127659575,27
+92,hierarchical,48,1,1.8958333333333333,17
+93,k_means,48,1,1.8958333333333333,27
+94,hierarchical,49,1,1.8571428571428572,17
+95,k_means,49,1,1.8571428571428572,27
+96,hierarchical,50,1,1.82,17
+97,k_means,50,1,1.82,25
+98,hierarchical,51,1,1.7843137254901962,17
+99,k_means,51,1,1.7843137254901962,25
+100,hierarchical,52,1,1.75,17
+101,k_means,52,1,1.75,25
+102,hierarchical,53,1,1.7169811320754718,17
+103,k_means,53,1,1.7169811320754718,25
+104,hierarchical,54,1,1.6851851851851851,17
+105,k_means,54,1,1.6851851851851851,23
+106,hierarchical,55,1,1.6545454545454545,17
+107,k_means,55,1,1.6545454545454545,21
+108,hierarchical,56,1,1.625,17
+109,k_means,56,1,1.625,20
+110,hierarchical,57,1,1.5964912280701755,17
+111,k_means,57,1,1.5964912280701755,19
+112,hierarchical,58,1,1.5689655172413792,17
+113,k_means,58,1,1.5689655172413792,18
+114,hierarchical,59,1,1.5423728813559323,17
+115,k_means,59,1,1.5423728813559323,18
+116,hierarchical,60,1,1.5166666666666666,17
+117,k_means,60,1,1.5166666666666666,17
+118,hierarchical,61,1,1.4918032786885247,17
+119,k_means,61,1,1.4918032786885247,17
+120,hierarchical,62,1,1.467741935483871,17
+121,k_means,62,1,1.467741935483871,16
+122,hierarchical,63,1,1.4444444444444444,17
+123,k_means,63,1,1.4444444444444444,16
+124,hierarchical,64,1,1.421875,17
+125,k_means,64,1,1.421875,16

clustering/org.apache.xerces.impl.xs.traversers.XSDHandler_hierarchical.csv

@@ -11,7 +11,7 @@ constructTrees,0
 isExistingGrammar,0
 updateImportListFor,0
 updateImportListWith,0
-buildGlobalNameRegistries,0
+buildGlobalNameRegistries,2
 traverseSchemas,0
 needReportTNSError,0
 addGlobalAttributeDecl,0

clustering/org.apache.xerces.impl.xs.traversers.XSDHandler_kmeans.csv

@@ -36,7 +36,7 @@ getGrpOrAttrGrpRedefinedByRestriction,0
 resolveKeyRefs,0
 getIDRegistry,0
 getIDRegistry_sub,0
-storeKeyRef,2
+storeKeyRef,0
 resolveSchema,0
 resolveSchemaSource,0
 getSchemaDocument,0

clustering/org.apache.xerces.impl.xs.traversers.XSDHandler_silhouette.csv

@@ -1,64 +1,64 @@
 ,k_means,hierarchical
 2,0.598553678618089,0.598553678618089
-3,0.5988635577957939,0.4340479638200015
+3,0.4340479638200015,0.5988635577957939
-4,0.5768968986366794,0.4446910360233003
+4,0.4446910360233003,0.5768968986366794
-5,0.5600582308059449,0.44970649031040394
+5,0.44970649031040394,0.5600582308059449
-6,0.4754961922118064,0.42291318953408236
+6,0.42291318953408236,0.4754961922118064
-7,0.4716129791423394,0.37302776265331616
+7,0.37302776265331616,0.4716129791423394
-8,0.4215235973451702,0.16585341129364783
+8,0.16585341129364783,0.4215235973451702
-9,0.4270412461769427,0.1805562766904707
+9,0.1805562766904707,0.4270412461769427
-10,0.42033460704259445,0.10021703881198853
+10,0.10021703881198853,0.42033460704259445
-11,0.3979172260202459,0.11227880527684016
+11,0.11227880527684016,0.3979172260202459
-12,0.3992377842624971,0.13834960978465374
+12,0.13834960978465374,0.3992377842624971
-13,0.36351812430049024,0.14637482631499601
+13,0.14637482631499601,0.36351812430049024
-14,0.36086605127470145,0.15339700393049752
+14,0.15339700393049752,0.36086605127470145
-15,0.27803229144747893,0.17519153912543511
+15,0.17519153912543511,0.27803229144747893
-16,0.24764306057751692,0.18163489682652323
+16,0.18163489682652323,0.24764306057751692
-17,0.2546247662068935,0.1920283064393974
+17,0.1920283064393974,0.2546247662068935
-18,0.27281600254442556,0.1968887014348958
+18,0.1968887014348958,0.27281600254442556
-19,0.2705186834360297,0.22320550740329767
+19,0.22320550740329767,0.2705186834360297
-20,0.29969231483298964,0.2278559856358303
+20,0.2278559856358303,0.29969231483298964
-21,0.31507175636228785,0.21631113790331308
+21,0.21631113790331308,0.31507175636228785
-22,0.3170839571491974,0.23240216910856668
+22,0.23240216910856668,0.3170839571491974
-23,0.3201062001500274,0.23590483919206368
+23,0.23590483919206368,0.3201062001500274
-24,0.24788100874579763,0.24413294581937137
+24,0.24413294581937137,0.24788100874579763
-25,0.24932439019964475,0.2514892577758059
+25,0.2514892577758059,0.24932439019964475
-26,0.25682838168308425,0.2573251636281981
+26,0.2573251636281981,0.25682838168308425
-27,0.25691108409617125,0.2629575908594159
+27,0.2629575908594159,0.25691108409617125
-28,0.2606141413445487,0.27452933746874875
+28,0.27452933746874875,0.2606141413445487
-29,0.2538973293819504,0.27138907448677696
+29,0.27138907448677696,0.2538973293819504
-30,0.26300677134410877,0.27608901099722993
+30,0.27608901099722993,0.26300677134410877
-31,0.25958787047274295,0.2734068655042204
+31,0.2734068655042204,0.25958787047274295
-32,0.2620577633391267,0.26668692055998694
+32,0.26668692055998694,0.2620577633391267
-33,0.2677665846189286,0.27190541883537933
+33,0.27190541883537933,0.2677665846189286
-34,0.2698493206362974,0.2737953942290021
+34,0.2737953942290021,0.2698493206362974
-35,0.26871523120875485,0.2792490491212266
+35,0.2792490491212266,0.26871523120875485
-36,0.2706224838853019,0.285255446778457
+36,0.285255446778457,0.2706224838853019
-37,0.27443698923839605,0.28791640737048424
+37,0.28791640737048424,0.27443698923839605
-38,0.27814176822064324,0.279340819685821
+38,0.279340819685821,0.27814176822064324
-39,0.27606460269195954,0.27183941054653343
+39,0.27183941054653343,0.27606460269195954
-40,0.27307694582354536,0.2763117563875985
+40,0.2763117563875985,0.27307694582354536
-41,0.27681213230462487,0.28090687018324295
+41,0.28090687018324295,0.27681213230462487
-42,0.2763401507651925,0.2823757748346625
+42,0.2823757748346625,0.2763401507651925
-43,0.2905756087008992,0.284106939165533
+43,0.284106939165533,0.2905756087008992
-44,0.2901305465431984,0.28892051024774673
+44,0.28892051024774673,0.2901305465431984
-45,0.2866682178814574,0.31067801214219776
+45,0.31067801214219776,0.2866682178814574
-46,0.2748147271365624,0.33271255209429573
+46,0.33271255209429573,0.2748147271365624
-47,0.2824570955002154,0.33809240352772785
+47,0.33809240352772785,0.2824570955002154
-48,0.28532199483886955,0.342466005901906
+48,0.342466005901906,0.28532199483886955
-49,0.3194897125271686,0.3472678571815208
+49,0.3472678571815208,0.3194897125271686
-50,0.32227149882332984,0.3494143489069156
+50,0.3494143489069156,0.32227149882332984
-51,0.32507315719109064,0.3553262507378467
+51,0.3553262507378467,0.32507315719109064
-52,0.3483927215781152,0.3577437943048381
+52,0.3577437943048381,0.3483927215781152
-53,0.35116863658039477,0.36265544445738723
+53,0.36265544445738723,0.35116863658039477
-54,0.35397195095412226,0.3652777392559547
+54,0.3652777392559547,0.35397195095412226
-55,0.35681293946359083,0.3635299110583668
+55,0.3635299110583668,0.35681293946359083
-56,0.35970774816697515,0.36657235082485046
+56,0.36657235082485046,0.35970774816697515
-57,0.36268328716123316,0.369801843033111
+57,0.369801843033111,0.36268328716123316
-58,0.365787994620889,0.373236109725014
+58,0.373236109725014,0.365787994620889
-59,0.36911874689499113,0.3768951711426859
+59,0.3768951711426859,0.36911874689499113
-60,0.3899012348681259,0.38080172755114144
+60,0.38080172755114144,0.3899012348681259
-61,0.3925538526988892,0.38498161884368615
+61,0.38498161884368615,0.3925538526988892
-62,0.3952064705296526,0.38946438071227807
+62,0.38946438071227807,0.3952064705296526
-63,0.40051170619117926,0.39428392137375445
+63,0.39428392137375445,0.40051170619117926
-64,0.4003435986724249,0.4003771346837245
+64,0.4003771346837245,0.4003435986724249

clustering/org.apache.xerces.impl.xs.traversers.XSDHandler_stats.csv

@@ -0,0 +1,127 @@
+,algorithm,k,min,mean,max
+0,hierarchical,2,1,53.0,105
+1,k_means,2,1,53.0,105
+2,hierarchical,3,1,35.333333333333336,104
+3,k_means,3,1,35.333333333333336,104
+4,hierarchical,4,1,26.5,102
+5,k_means,4,1,26.5,102
+6,hierarchical,5,1,21.2,102
+7,k_means,5,1,21.2,101
+8,hierarchical,6,1,17.666666666666668,99
+9,k_means,6,1,17.666666666666668,99
+10,hierarchical,7,1,15.142857142857142,98
+11,k_means,7,1,15.142857142857142,98
+12,hierarchical,8,1,13.25,96
+13,k_means,8,1,13.25,91
+14,hierarchical,9,1,11.777777777777779,96
+15,k_means,9,1,11.777777777777779,90
+16,hierarchical,10,1,10.6,95
+17,k_means,10,1,10.6,86
+18,hierarchical,11,1,9.636363636363637,94
+19,k_means,11,1,9.636363636363637,84
+20,hierarchical,12,1,8.833333333333334,93
+21,k_means,12,1,8.833333333333334,82
+22,hierarchical,13,1,8.153846153846153,91
+23,k_means,13,1,8.153846153846153,81
+24,hierarchical,14,1,7.571428571428571,91
+25,k_means,14,1,7.571428571428571,80
+26,hierarchical,15,1,7.066666666666666,83
+27,k_means,15,1,7.066666666666666,76
+28,hierarchical,16,1,6.625,83
+29,k_means,16,1,6.625,75
+30,hierarchical,17,1,6.235294117647059,78
+31,k_means,17,1,6.235294117647059,74
+32,hierarchical,18,1,5.888888888888889,78
+33,k_means,18,1,5.888888888888889,73
+34,hierarchical,19,1,5.578947368421052,78
+35,k_means,19,1,5.578947368421052,71
+36,hierarchical,20,1,5.3,71
+37,k_means,20,1,5.3,70
+38,hierarchical,21,1,5.0476190476190474,68
+39,k_means,21,1,5.0476190476190474,69
+40,hierarchical,22,1,4.818181818181818,68
+41,k_means,22,1,4.818181818181818,65
+42,hierarchical,23,1,4.608695652173913,68
+43,k_means,23,1,4.608695652173913,65
+44,hierarchical,24,1,4.416666666666667,64
+45,k_means,24,1,4.416666666666667,64
+46,hierarchical,25,1,4.24,64
+47,k_means,25,1,4.24,62
+48,hierarchical,26,1,4.076923076923077,64
+49,k_means,26,1,4.076923076923077,61
+50,hierarchical,27,1,3.925925925925926,64
+51,k_means,27,1,3.925925925925926,60
+52,hierarchical,28,1,3.7857142857142856,63
+53,k_means,28,1,3.7857142857142856,55
+54,hierarchical,29,1,3.6551724137931036,63
+55,k_means,29,1,3.6551724137931036,55
+56,hierarchical,30,1,3.533333333333333,63
+57,k_means,30,1,3.533333333333333,54
+58,hierarchical,31,1,3.4193548387096775,63
+59,k_means,31,1,3.4193548387096775,54
+60,hierarchical,32,1,3.3125,52
+61,k_means,32,1,3.3125,54
+62,hierarchical,33,1,3.212121212121212,52
+63,k_means,33,1,3.212121212121212,53
+64,hierarchical,34,1,3.1176470588235294,52
+65,k_means,34,1,3.1176470588235294,52
+66,hierarchical,35,1,3.0285714285714285,52
+67,k_means,35,1,3.0285714285714285,51
+68,hierarchical,36,1,2.9444444444444446,52
+69,k_means,36,1,2.9444444444444446,50
+70,hierarchical,37,1,2.864864864864865,52
+71,k_means,37,1,2.864864864864865,50
+72,hierarchical,38,1,2.789473684210526,51
+73,k_means,38,1,2.789473684210526,50
+74,hierarchical,39,1,2.717948717948718,51
+75,k_means,39,1,2.717948717948718,50
+76,hierarchical,40,1,2.65,51
+77,k_means,40,1,2.65,49
+78,hierarchical,41,1,2.5853658536585367,51
+79,k_means,41,1,2.5853658536585367,48
+80,hierarchical,42,1,2.5238095238095237,51
+81,k_means,42,1,2.5238095238095237,47
+82,hierarchical,43,1,2.4651162790697674,47
+83,k_means,43,1,2.4651162790697674,47
+84,hierarchical,44,1,2.409090909090909,47
+85,k_means,44,1,2.409090909090909,46
+86,hierarchical,45,1,2.3555555555555556,47
+87,k_means,45,1,2.3555555555555556,44
+88,hierarchical,46,1,2.3043478260869565,46
+89,k_means,46,1,2.3043478260869565,42
+90,hierarchical,47,1,2.25531914893617,25
+91,k_means,47,1,2.25531914893617,41
+92,hierarchical,48,1,2.2083333333333335,25
+93,k_means,48,1,2.2083333333333335,41
+94,hierarchical,49,1,2.163265306122449,25
+95,k_means,49,1,2.163265306122449,41
+96,hierarchical,50,1,2.12,25
+97,k_means,50,1,2.12,40
+98,hierarchical,51,1,2.0784313725490198,25
+99,k_means,51,1,2.0784313725490198,39
+100,hierarchical,52,1,2.0384615384615383,25
+101,k_means,52,1,2.0384615384615383,38
+102,hierarchical,53,1,2.0,25
+103,k_means,53,1,2.0,38
+104,hierarchical,54,1,1.962962962962963,25
+105,k_means,54,1,1.962962962962963,37
+106,hierarchical,55,1,1.9272727272727272,25
+107,k_means,55,1,1.9272727272727272,35
+108,hierarchical,56,1,1.8928571428571428,25
+109,k_means,56,1,1.8928571428571428,34
+110,hierarchical,57,1,1.8596491228070176,25
+111,k_means,57,1,1.8596491228070176,33
+112,hierarchical,58,1,1.8275862068965518,25
+113,k_means,58,1,1.8275862068965518,32
+114,hierarchical,59,1,1.7966101694915255,25
+115,k_means,59,1,1.7966101694915255,31
+116,hierarchical,60,1,1.7666666666666666,25
+117,k_means,60,1,1.7666666666666666,30
+118,hierarchical,61,1,1.7377049180327868,25
+119,k_means,61,1,1.7377049180327868,29
+120,hierarchical,62,1,1.7096774193548387,25
+121,k_means,62,1,1.7096774193548387,28
+122,hierarchical,63,1,1.6825396825396826,25
+123,k_means,63,1,1.6825396825396826,27
+124,hierarchical,64,1,1.65625,25
+125,k_means,64,1,1.65625,27

clustering/org.apache.xerces.xinclude.XIncludeHandler_silhouette.csv

@@ -1,64 +1,64 @@
 ,k_means,hierarchical
-2,0.6855584100867681,0.6979818296524081
+2,0.6979818296524081,0.6855584100867681
-3,0.6658312390685782,0.5363440260613704
+3,0.5363440260613704,0.6658312390685782
 4,0.5447405755407478,0.5447405755407478
-5,0.49469855877597974,0.4950944104608897
+5,0.4950944104608897,0.49469855877597974
-6,0.49629928069605667,0.3167619075077442
+6,0.3167619075077442,0.49629928069605667
-7,0.4937183177275972,0.3273304877495634
+7,0.3273304877495634,0.4937183177275972
-8,0.4903327662796836,0.16989336921679118
+8,0.16989336921679118,0.4903327662796836
-9,0.33791118198002373,0.17626101482318196
+9,0.17626101482318196,0.33791118198002373
-10,0.2667320598048964,0.19790344008120894
+10,0.19790344008120894,0.2667320598048964
-11,0.2629948976926796,0.1943827895435377
+11,0.1943827895435377,0.2629948976926796
-12,0.25965211932671445,0.20556562870341602
+12,0.20556562870341602,0.25965211932671445
-13,0.26164323937367595,0.20144552653966163
+13,0.20144552653966163,0.26164323937367595
-14,0.25806076142240403,0.22548403695669203
+14,0.22548403695669203,0.25806076142240403
-15,0.26997893998401756,0.22918194758667895
+15,0.22918194758667895,0.26997893998401756
-16,0.27256451459055664,0.2404290571765335
+16,0.2404290571765335,0.27256451459055664
-17,0.2608837912623233,0.2345015455494567
+17,0.2345015455494567,0.2608837912623233
-18,0.241790230179569,0.2390816398182416
+18,0.2390816398182416,0.241790230179569
-19,0.24484234464495422,0.24094820256010968
+19,0.24094820256010968,0.24484234464495422
-20,0.2361050155539465,0.2435369787081999
+20,0.2435369787081999,0.2361050155539465
-21,0.23692336175194548,0.262463283756636
+21,0.262463283756636,0.23692336175194548
-22,0.23946566771940794,0.2742864390420934
+22,0.2742864390420934,0.23946566771940794
-23,0.24594283942153175,0.2979619533428987
+23,0.2979619533428987,0.24594283942153175
-24,0.24734609860636583,0.29936015461670856
+24,0.29936015461670856,0.24734609860636583
-25,0.2372755932074588,0.30224440986202594
+25,0.30224440986202594,0.2372755932074588
-26,0.24082497341896647,0.30600924875137986
+26,0.30600924875137986,0.24082497341896647
-27,0.24547723657004195,0.3147862783718484
+27,0.3147862783718484,0.24547723657004195
-28,0.2503460498700128,0.31887407003386015
+28,0.31887407003386015,0.2503460498700128
-29,0.26565769288673047,0.3204052924706567
+29,0.3204052924706567,0.26565769288673047
-30,0.2951470761811464,0.3106572702067674
+30,0.3106572702067674,0.2951470761811464
-31,0.30158824153259317,0.31330774028648145
+31,0.31330774028648145,0.30158824153259317
-32,0.3180875184494547,0.33210454757827634
+32,0.33210454757827634,0.3180875184494547
-33,0.32604023717225655,0.340503634089749
+33,0.340503634089749,0.32604023717225655
-34,0.3162922149083673,0.33568440892081625
+34,0.33568440892081625,0.3162922149083673
-35,0.31716183472339093,0.3545992807283562
+35,0.3545992807283562,0.31716183472339093
-36,0.3214298482703343,0.3575403386841057
+36,0.3575403386841057,0.3214298482703343
-37,0.32681546873349715,0.36503026576341707
+37,0.36503026576341707,0.32681546873349715
-38,0.32732304963529885,0.3738835074795801
+38,0.3738835074795801,0.32732304963529885
-39,0.32990135488218114,0.3929681262996284
+39,0.3929681262996284,0.32990135488218114
-40,0.32432743478528314,0.38848432563159185
+40,0.38848432563159185,0.32432743478528314
-41,0.3198436341172465,0.39163178463382314
+41,0.39163178463382314,0.3198436341172465
-42,0.32643375049241685,0.3860578645369252
+42,0.3860578645369252,0.32643375049241685
-43,0.32203761977337186,0.4053389048253979
+43,0.4053389048253979,0.32203761977337186
-44,0.3346466456087704,0.4217820126417848
+44,0.4217820126417848,0.3346466456087704
-45,0.33223356867673165,0.4257244699851672
+45,0.4257244699851672,0.33223356867673165
-46,0.33057959050289126,0.42988772845220063
+46,0.42988772845220063,0.33057959050289126
-47,0.34588619420359423,0.4342738007458362
+47,0.4342738007458362,0.34588619420359423
-48,0.3328354412937589,0.4416623097378058
+48,0.4416623097378058,0.3328354412937589
-49,0.33565227636252953,0.4426712673092602
+49,0.4426712673092602,0.33565227636252953
-50,0.35908519690010676,0.4440749104193141
+50,0.4440749104193141,0.35908519690010676
-51,0.3619904717574287,0.4456199850626709
+51,0.4456199850626709,0.3619904717574287
-52,0.36212543071422687,0.45074758794403463
+52,0.45074758794403463,0.36212543071422687
-53,0.3651696447072414,0.472336181881003
+53,0.472336181881003,0.3651696447072414
-54,0.3982691624564969,0.47730382490643575
+54,0.47730382490643575,0.3982691624564969
-55,0.4013572084387477,0.454200815600248
+55,0.454200815600248,0.4013572084387477
-56,0.4246326548929088,0.4565666319605046
+56,0.4565666319605046,0.4246326548929088
-57,0.44773608146478383,0.4522750157266781
+57,0.4522750157266781,0.44773608146478383
-58,0.45157671443203573,0.4549088773042353
+58,0.4549088773042353,0.45157671443203573
-59,0.4563204517812888,0.46145616231522185
+59,0.46145616231522185,0.4563204517812888
-60,0.46300257860702615,0.4641242358826516
+60,0.4641242358826516,0.46300257860702615
-61,0.4967563269695634,0.47006659021417746
+61,0.47006659021417746,0.4967563269695634
-62,0.4994732063134373,0.47352022985333136
+62,0.47352022985333136,0.4994732063134373
-63,0.49518159007961093,0.4775136217473302
+63,0.4775136217473302,0.49518159007961093
-64,0.4872143751031807,0.4821848224907804
+64,0.4821848224907804,0.4872143751031807

clustering/org.apache.xerces.xinclude.XIncludeHandler_stats.csv

@@ -0,0 +1,127 @@
+,algorithm,k,min,mean,max
+0,hierarchical,2,2,54.0,106
+1,k_means,2,1,54.0,107
+2,hierarchical,3,1,36.0,106
+3,k_means,3,1,36.0,103
+4,hierarchical,4,1,27.0,102
+5,k_means,4,1,27.0,102
+6,hierarchical,5,1,21.6,101
+7,k_means,5,1,21.6,102
+8,hierarchical,6,1,18.0,100
+9,k_means,6,1,18.0,93
+10,hierarchical,7,1,15.428571428571429,99
+11,k_means,7,1,15.428571428571429,91
+12,hierarchical,8,1,13.5,99
+13,k_means,8,1,13.5,71
+14,hierarchical,9,1,12.0,90
+15,k_means,9,1,12.0,68
+16,hierarchical,10,1,10.8,80
+17,k_means,10,1,10.8,62
+18,hierarchical,11,1,9.818181818181818,80
+19,k_means,11,1,9.818181818181818,62
+20,hierarchical,12,1,9.0,80
+21,k_means,12,1,9.0,61
+22,hierarchical,13,1,8.307692307692308,79
+23,k_means,13,1,8.307692307692308,63
+24,hierarchical,14,1,7.714285714285714,77
+25,k_means,14,1,7.714285714285714,57
+26,hierarchical,15,1,7.2,77
+27,k_means,15,1,7.2,56
+28,hierarchical,16,1,6.75,76
+29,k_means,16,1,6.75,55
+30,hierarchical,17,1,6.352941176470588,76
+31,k_means,17,1,6.352941176470588,55
+32,hierarchical,18,1,6.0,65
+33,k_means,18,1,6.0,54
+34,hierarchical,19,1,5.684210526315789,65
+35,k_means,19,1,5.684210526315789,54
+36,hierarchical,20,1,5.4,65
+37,k_means,20,1,5.4,53
+38,hierarchical,21,1,5.142857142857143,65
+39,k_means,21,1,5.142857142857143,53
+40,hierarchical,22,1,4.909090909090909,64
+41,k_means,22,1,4.909090909090909,51
+42,hierarchical,23,1,4.695652173913044,64
+43,k_means,23,1,4.695652173913044,47
+44,hierarchical,24,1,4.5,64
+45,k_means,24,1,4.5,47
+46,hierarchical,25,1,4.32,34
+47,k_means,25,1,4.32,46
+48,hierarchical,26,1,4.153846153846154,34
+49,k_means,26,1,4.153846153846154,45
+50,hierarchical,27,1,4.0,34
+51,k_means,27,1,4.0,42
+52,hierarchical,28,1,3.857142857142857,34
+53,k_means,28,1,3.857142857142857,41
+54,hierarchical,29,1,3.7241379310344827,34
+55,k_means,29,1,3.7241379310344827,41
+56,hierarchical,30,1,3.6,34
+57,k_means,30,1,3.6,41
+58,hierarchical,31,1,3.4838709677419355,34
+59,k_means,31,1,3.4838709677419355,40
+60,hierarchical,32,1,3.375,34
+61,k_means,32,1,3.375,38
+62,hierarchical,33,1,3.272727272727273,34
+63,k_means,33,1,3.272727272727273,36
+64,hierarchical,34,1,3.176470588235294,34
+65,k_means,34,1,3.176470588235294,36
+66,hierarchical,35,1,3.085714285714286,34
+67,k_means,35,1,3.085714285714286,34
+68,hierarchical,36,1,3.0,34
+69,k_means,36,1,3.0,33
+70,hierarchical,37,1,2.918918918918919,34
+71,k_means,37,1,2.918918918918919,31
+72,hierarchical,38,1,2.8421052631578947,34
+73,k_means,38,1,2.8421052631578947,31
+74,hierarchical,39,1,2.769230769230769,33
+75,k_means,39,1,2.769230769230769,29
+76,hierarchical,40,1,2.7,33
+77,k_means,40,1,2.7,29
+78,hierarchical,41,1,2.6341463414634148,33
+79,k_means,41,1,2.6341463414634148,28
+80,hierarchical,42,1,2.5714285714285716,33
+81,k_means,42,1,2.5714285714285716,28
+82,hierarchical,43,1,2.511627906976744,33
+83,k_means,43,1,2.511627906976744,26
+84,hierarchical,44,1,2.4545454545454546,33
+85,k_means,44,1,2.4545454545454546,26
+86,hierarchical,45,1,2.4,33
+87,k_means,45,1,2.4,25
+88,hierarchical,46,1,2.347826086956522,33
+89,k_means,46,1,2.347826086956522,24
+90,hierarchical,47,1,2.297872340425532,33
+91,k_means,47,1,2.297872340425532,23
+92,hierarchical,48,1,2.25,21
+93,k_means,48,1,2.25,23
+94,hierarchical,49,1,2.204081632653061,20
+95,k_means,49,1,2.204081632653061,23
+96,hierarchical,50,1,2.16,18
+97,k_means,50,1,2.16,22
+98,hierarchical,51,1,2.1176470588235294,17
+99,k_means,51,1,2.1176470588235294,21
+100,hierarchical,52,1,2.076923076923077,16
+101,k_means,52,1,2.076923076923077,20
+102,hierarchical,53,1,2.0377358490566038,16
+103,k_means,53,1,2.0377358490566038,18
+104,hierarchical,54,1,2.0,16
+105,k_means,54,1,2.0,18
+106,hierarchical,55,1,1.9636363636363636,16
+107,k_means,55,1,1.9636363636363636,19
+108,hierarchical,56,1,1.9285714285714286,16
+109,k_means,56,1,1.9285714285714286,18
+110,hierarchical,57,1,1.894736842105263,16
+111,k_means,57,1,1.894736842105263,18
+112,hierarchical,58,1,1.8620689655172413,16
+113,k_means,58,1,1.8620689655172413,18
+114,hierarchical,59,1,1.8305084745762712,16
+115,k_means,59,1,1.8305084745762712,18
+116,hierarchical,60,1,1.8,16
+117,k_means,60,1,1.8,17
+118,hierarchical,61,1,1.7704918032786885,16
+119,k_means,61,1,1.7704918032786885,17
+120,hierarchical,62,1,1.7419354838709677,16
+121,k_means,62,1,1.7419354838709677,17
+122,hierarchical,63,1,1.7142857142857142,16
+123,k_means,63,1,1.7142857142857142,17
+124,hierarchical,64,1,1.6875,16
+125,k_means,64,1,1.6875,17

prec_recall.py

@@ -25,10 +25,16 @@ def intrapairs(path: str) -> set[set[str, str]]:
 
 def main():
     filelist = glob.glob(IN_DIR + '/*_groundtruth.csv')
+    df_table = pd.DataFrame(columns=pd.MultiIndex.from_tuples([
+        ('KMeans', 'Precision'),
+        ('KMeans', 'Recall'),
+        ('Agglomerative', 'Precision'),
+        ('Agglomerative', 'Recall')]))
+    df_table.index.name = 'Class Name'
+
     for f in filelist:
         clazz_name = os.path.basename(f)
         clazz_name = clazz_name[:clazz_name.rfind('_groundtruth.csv')]
-        print(clazz_name)
 
         ground_pairs = intrapairs(f)
         for method in ['kmeans', 'hierarchical']:
@@ -39,10 +45,15 @@ def main():
             precision = n_common / len(cluster_pairs)
             recall = n_common / len(ground_pairs)
 
-            print(method + " precision: " + str(precision))
+            algo = 'KMeans' if method == 'kmeans' else 'Agglomerative'
-            print(method + " recall: " + str(recall))
+            
+            df_table.loc[clazz_name, [(algo, 'Precision'), (algo, 'Recall')]] = [
+                str(round(precision * 100, 2)) + '%', 
+                str(round(recall * 100, 2)) + '%'
+            ]
 
-        print()
+    df_table.columns = [x[0] + ' ' + x[1] for x in df_table.columns]
+    print(df_table.to_markdown())
 
 
 if __name__ == '__main__':

report/build.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+set -e
+
+SCRIPT_DIR=$(cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd)
+
+cd "$SCRIPT_DIR"
+pandoc main.md -o main.pdf  

report/main.md

@@ -1,7 +1,7 @@
 ---
 author: Claudio Maggioni
 title: Information Modelling & Analysis -- Project 1
-geometry: margin=2.5cm,bottom=3cm
+geometry: margin=2cm,bottom=3cm
 ---
 
 <!--
@@ -9,59 +9,62 @@ The following shows a minimal submission report for project 1. If you
 choose to use this template, replace all template instructions (the
 yellow bits) with your own values. In addition, for any section, if
 **and only if** anything was unclear or warnings were raised by the
-code, and you had to take assumptions about the correct implementation
+code, and you had to take assumptions about the correct implementation (e.g.,
-(e.g., about details of a metric), describe your assumptions in one or
+about details of a metric), describe your assumptions in one or two sentences.
-two sentences.
 
-You may - at your own risk - also choose not to use this template. As
+You may - at your own risk - also choose not to use this template. As long as
-long as your submission is a latex-generated, English PDF containing all
+your submission is a latex-generated, English PDF containing all expected info,
-expected info, you'll be fine.
+you'll be fine.  -->
--->
 
 # Code Repository
 
 The code and result files part of this submission can be found at:
 
-::: center
+::: center Repository:
-Repository: \url{https://github.com/infoMA2023/project-01-god-classes-maggicl}
+\url{https://github.com/infoMA2023/project-01-god-classes-maggicl}
 
-Commit ID: **TBD**
+Commit ID: **TBD** :::
-:::
 
 # Data Pre-Processing
 
 ## God Classes
 
-The first part of the project requires to label some classes of the _Xerces_ 
+The first part of the project requires to label some classes of the _Xerces_
-project as "God classes" based on the number of methods each class has.
+project as "God classes" based on the number of methods each class has. From
+here onwards the Java package prefix `org.apache.xerces` is omitted when discussing 
+fully qualified domain names of classes for sake of brevity.
+
 Specifically, I label "God classes" the classes that have a number of methods
-six times the standard deviation above the the mean number of methods, i.e. where
+six times the standard deviation above the the mean number of methods, i.e.
-the condition
+where the condition
 
 $$|M(C)| > \mu(M) + 6\sigma(M)$$
 
 holds.
 
-To scan and compute the number of methods of each class I use the Python library `javalang`, which implements the Java AST and parser. The Python script
+To scan and compute the number of methods of each class I use the Python library
-`./find_god_classes.py` uses this library to parse each file in the project and 
+`javalang`, which implements the Java AST and parser. The Python script
-compute the number of methods of each class. Note that only non-constructor methods are counted (specifically the code counts the number of `method` nodes in each `ClassDeclaration` node).
+`./find_god_classes.py` uses this library to parse each file in the project and
+compute the number of methods of each class. Note that only non-constructor
+methods are counted (specifically the code counts the number of `method` nodes
+in each `ClassDeclaration` node).
 
-Then, the script computes mean and standard 
+Then, the script computes mean and standard deviation of the number of methods
-deviation of the number of methods and filters the list of classes according to the 
+and filters the list of classes according to the condition described above. The
-condition described above. The file `god_classes/god_classes.csv` then is outputted
+file `god_classes/god_classes.csv` then is outputted listing all the god classes
-listing all the god classes found.
+found.
 
-The god classes I identified, and their corresponding number of methods
+The god classes I identified, and their corresponding number of methods can be
-can be found in Table [1](#tab:god_classes){reference-type="ref"
+found in Table [1](#tab:god_classes){reference-type="ref"
 reference="tab:god_classes"}. 
 
 ::: {#tab:god_classes}
 | **Class Name**                                 | **# Methods** |
 |:------------------------------------------------|------------:|
-| org.apache.xerces.impl.xs.traversers.XSDHandler |         118 |
+| impl.xs.traversers.XSDHandler |         118 |
-| org.apache.xerces.impl.dtd.DTDGrammar           |         101 |
+| impl.dtd.DTDGrammar           |         101 |
-| org.apache.xerces.xinclude.XIncludeHandler      |         116 |
+| xinclude.XIncludeHandler      |         116 |
-| org.apache.xerces.dom.CoreDocumentImpl          |         125 |
+| dom.CoreDocumentImpl          |         125 |
 
   : Identified God Classes
 :::
@@ -70,84 +73,198 @@ reference="tab:god_classes"}.
 ## Feature Vectors
 
 In this part of the project we produce the feature vectors used to later cluster
-the methods of each God class into separate clusters. We produce one feature method per
+the methods of each God class into separate clusters. We produce one feature
-non-constructor Java method in each god class.
+method per non-constructor Java method in each god class.
 
-The columns of each vector represent 
+The columns of each vector represent fields and methods referenced by each
-fields and methods referenced by each method, i.e. fields and methods actively used by the method in their method's body.
+method, i.e. fields and methods actively used by the method in their method's
+body.
 
-When analyzing references to fields, additional constraints need to be specified to handle edge cases. 
+When analyzing references to fields, additional constraints need to be specified
-Namely, a field's property may be referenced (e.g. an access to array `a` may fetch its `length` property, i.e. `a.length`). In this
+to handle edge cases.  Namely, a field's property may be referenced (e.g. an
-cases I consider the qualifier (i.e. the field itself, `a`) itself and not its property. When the qualifier is a class (i.e. 
+access to array `a` may fetch its `length` property, i.e. `a.length`). In this
-the code references a property of another class, e.g. `Integer.MAX_VALUE`) we consider the class name itself (i.e. `Integer`) and not 
+cases I consider the qualifier (i.e. the field itself, `a`) itself and not its
-the name of the property. Should the qualifier be a subproperty itself (e.g. in `a.b.c`, where `a.b` would be the qualifier according to `javalang`)
+property. When the qualifier is a class (i.e.  the code references a property of
+another class, e.g. `Integer.MAX_VALUE`) we consider the class name itself (i.e.
+`Integer`) and not the name of the property. Should the qualifier be a
+subproperty itself (e.g. in `a.b.c`, where `a.b` would be the qualifier
+according to `javalang`)
 
-For methods, I only consider calls to methods of the class itself where the qualifier is unspecified or `this`. Calls to parent methods
+For methods, I only consider calls to methods of the class itself where the
-(i.e. calls like `super.something()`) are not considered.
+qualifier is unspecified or `this`. Calls to parent methods (i.e. calls like
+`super.something()`) are not considered.
 
-The feature vector extraction phase is performed by the Python script `extract_feature_vectors.py`. The script takes `god_classes/god_classes.csv` as input
+The feature vector extraction phase is performed by the Python script
-and loads the AST of each class listed in it. Then, a list of all the fields and methods in the class is built, and each method is scanned to see which fields
+`extract_feature_vectors.py`. The script takes `god_classes/god_classes.csv` as
-and methods it references in its body according to the previously described rules. Then, a CSV per class is built storing all feature vectors. Each file has a name matching to the FQDN (Fully-qualified domain name) of the class. Each CSV row refers to a method in the class, and each CSV column refers to a field, method or referenced class. A cell has the value of 1 when the method of that row references the field, method or class marked by that column, and it has the value 0 otherwise. Columns with only zeros are omitted.
+input and loads the AST of each class listed in it. Then, a list of all the
+fields and methods in the class is built, and each method is scanned to see
+which fields and methods it references in its body according to the previously
+described rules. Then, a CSV per class is built storing all feature vectors.
+Each file has a name matching to the FQDN (Fully-qualified domain name) of the
+class. Each CSV row refers to a method in the class, and each CSV column refers
+to a field, method or referenced class. A cell has the value of 1 when the
+method of that row references the field, method or class marked by that column,
+and it has the value 0 otherwise. Columns with only zeros are omitted.
 
-Table [2](#tab:feat_vec){reference-type="ref" reference="tab:feat_vec"}
+Table [2](#tab:feat_vec){reference-type="ref" reference="tab:feat_vec"} shows
-shows aggregate numbers regarding the extracted feature vectors for the
+aggregate numbers regarding the extracted feature vectors for the god classes.
-god classes. Note that the number of attributes refers to the number of fields, methods or classes actually references (i.e. the number of columns after omission of 0s).
+Note that the number of attributes refers to the number of fields, methods or
+classes actually references (i.e. the number of columns after omission of 0s).
 
 ::: {#tab:feat_vec}
 | **Class Name**                                  | **# Feature Vectors** | **# Attributes\*** |
 |:------------------------------------------------|----------------------:|-----------------:|
-| org.apache.xerces.impl.xs.traversers.XSDHandler |                 106 |            183 |
+| impl.xs.traversers.XSDHandler |                 106 |            183 |
-| org.apache.xerces.impl.dtd.DTDGrammar           |                  91 |            106 |
+| impl.dtd.DTDGrammar           |                  91 |            106 |
-| org.apache.xerces.xinclude.XIncludeHandler      |                 108 |            143 |
+| xinclude.XIncludeHandler      |                 108 |            143 |
-| org.apache.xerces.dom.CoreDocumentImpl          |                 117 |             63 |
+| dom.CoreDocumentImpl          |                 117 |             63 |
 
   : Feature vector summary (\*= used at least once)
 :::
 
 # Clustering {#sec:clustering}
 
+In this section I covering the techniques to cluster the methods of each god
+class. The project aims to use KMeans clustering and agglomerative hierarchical
+clustering to group these methods toghether in cohesive units which could be
+potentially refactored out of the god class they belong to.
+
 ## Algorithm Configurations
 
-Report/comment the algorithm configurations (distance function, linkage
+To perform KMeans clustering, I use the `cluster.KMeans` Scikit-Learn
-rule, etc.). You may do so in any form you feel suited, but a short
+implementation of the algorithm.  I use the default parameters: feature vectors
-paragraph of text is probably sufficient.
+are compared with euclidian distance, centroids are used instead of medioids,
+and the initial centroids are computed with the greedy algorithm `kmeans++`. The
+random seed is fixed to $0$ to allow for reproducibility between executions of
+the clustering script.
+
+To perform Hierarchical clustering, I use the `cluster.AgglomerativeClustering`
+Scikit-Learn implementation of the algorithm.  Again feature vectors are
+compared with euclidian distance, but as a linkage metric I choose to use
+complete linkage.  As agglomerative clustering is deternministic, no random seed
+is needed for this algorithm.
+
+I run the two algorithms for all $k \in [2,65]$, or if less than 65 feature
+vectors with distinct values are assigned to the god class, the upper bound of
+$k$ is such value.
 
 ## Testing Various K & Silhouette Scores
 
-\(1\) Report data about the clusters produced by the two algorithms at
+To find the optimal value of $k$ for both algorithms, the distribution of
-various k (#clusters, size of clusters, silhouette scores). You may use
+cluster sizes and silhouette across values of $k$, and to apply the optimal
-any suitable format (table, graph, \...).
+clustering for each god class I run the command:
 
-\(2\) Briefly comment your results. What is the best configuration, and
+```shell
-why? Anything else you observed?
+./silhouette.py --validate --autorun
+```
+
+Feature vectors are read from the `feature_vectors` directory and all the
+results are stored in the `clustering` directory.
+
+Figures [1](#fig:xsd){reference-type="ref" reference="fig:xsd"},
+[2](#fig:dtd){reference-type="ref" reference="fig:dtd"},
+[3](#fig:xinc){reference-type="ref" reference="fig:xinc"}, and
+[4](#fig:cimpl){reference-type="ref" reference="fig:cimpl"} show the
+distributions of cluster sizes for each god class obtained by running the KMeans
+and agglomerative clustering algorithm as described in the previous sections.
+
+For all god classes, the mean of number of elements in each cluster
+exponentially decreases as $k$ increases. Aside the first values of $k$ for
+class `DTDGrammar` (where it was 2), the minimum cluster size was 1 for all
+analyzed clusterings.  Conversely, the maximum cluster size varies a lot, almost
+always being monotonically non increasing as $k$ increases, occasionally forming
+wide plateaus. The silhouette metric distribution instead generally follows a
+dogleg-like path, sharply decreasing for the first values of $k$ and slowly
+increasing afterwards $k$. This leads the choice of the optimal $k$ number of
+clusters for each algorithm to be between really low and really high values.
+
+The figures also show the distribution of the silhouette metric per algorithm
+and per value of $k$. The optimal values of $k$ and the respective silhouette
+values for each implementation are reported in Table
+[3](#tab:sumup){reference-type="ref" reference="tab:sumup"}.
+
+From the values we can gather that agglomerative clustering performs overall
+better than KMeans for the god classes in the project.  Almost god classes are
+optimally clustered with few clusters, with the exception of `CoreDocumentImpl`
+being optimally clustered with unit clusters. This could indicate higher
+cohesion between implementation details of the other classes, and lower cohesion
+in `CoreDocumentImpl` (given the name it would not be surprising if this class
+plays the role of an utility class of sort, combining lots of implementation
+details affecting different areas of the code).
+
+Agglomerative clustering with complete linkage could perform better than KMeans
+due to a more urgent need for separation rather than cohesion in the classes
+that were analyzed. Given the high dimensionality of the feature vectures used,
+and the fact that eucledian distance is used to compare feature vectors, the
+hyper-space of method features for each god class is likely sparse, with
+occasional clusters of tightly-knit features.  Given the prevailing sparsity,
+complete linkage could be suitable here since it avoids to agglomerate distant
+clusters above all.
+
+![Clustering metrics for class impl.xs.traversers.XSDHandler](../clustering/org.apache.xerces.impl.xs.traversers.XSDHandler_stats.png){#fig:xsd}
+
+![Clustering metrics for class impl.dtd.DTDGrammar](../clustering/org.apache.xerces.impl.dtd.DTDGrammar_stats.png){#fig:dtd}
+
+![Clustering metrics for class xinclude.XIncludeHandler](../clustering/org.apache.xerces.xinclude.XIncludeHandler_stats.png){#fig:xinc}
+
+![Clustering metrics for class dom.CoreDocumentImpl](../clustering/org.apache.xerces.dom.CoreDocumentImpl_stats.png){#fig:cimpl}
+
+::: {#tab:sumup}
+| **Class Name**            | **KMeans K** |   **KMeans silhouette** |   **Hierarchical K** |   **Hierarchical silhouette** |
+|:------------- --------------|-----------:|--------------------:|-----------------:|--------------------------:|
+| dom.CoreDocumentImpl        |         45 |0.7290 |               45 |                    0.7290 | 
+| impl.xs.traversers.XSDHandler |          2 |0.5986 |                3 |                    0.5989 | 
+| impl.dtd.DTDGrammar           |         58 |0.3980 |                2 |                    0.4355 | 
+| xinclude.XIncludeHandler      |          2 |0.6980 |                2 |                    0.6856 |
+
+  : Optimal hyperparameters and corresponding silhouette metrics for KMeans and
+Hierarchical clustering algorithm. 
+:::
 
 # Evaluation
 
 ## Ground Truth
 
-I computed the ground truth using the command \.... The generated files
+I computed the ground truth using the Python script `./ground_truth.py` The
-are checked into the repository with the names \....
+generated files are checked into the repository with the names
+`clustering/{className}_groundtruth.csv` where `{className}` is the FQDN of each
+god class.
 
-Comment briefly on the strengths & weaknesses of our ground truth.
+The ground truth in this project is not given but generated according to simple
+heuristics. Since no inherent structure or labelling from experts exists to
+group the methods in each god class, the project requires to label methods based
+on keyword matching whitin each method name. The list of keywords used can be
+found in `keyword_list.txt`. This approach allows to have a ground truth at all
+with little computational cost and labelling effort, but it assumes the method
+name and the chosen keywords are indeed of enough significance to form a
+meaningful clustering of methods that form refactorable cohesive units of
+functionality. 
 
 ## Precision and Recall
 
 ::: {#tab:eval}
-  ---------------- ------------------- -------- ------------- --------
+| **Class Name**                                      | **KMeans Precision**   | **KMeans Recall**   | **Agglomerative Precision**   | **Agglomerative Recall**   |
-  **Class Name**    **Agglomerative**            **K-Means**  
+|:------------------------------------------------|-------------------:|----------------:|--------------------------:|-----------------------:|
-                          Prec.         Recall      Prec.      Recall
+| xinclude.XIncludeHandler      | 69.83%             | 97.80%           | 69.58%                    | 95.65%                 |
-  \...                    \...           \...       \...        \...
+| dom.CoreDocumentImpl          | 64.80%              | 28.26%          | 68.11%                    | 29.70%                  |
-  ---------------- ------------------- -------- ------------- --------
+| impl.xs.traversers.XSDHandler | 36.17%             | 97.24%          | 36.45%                    | 96.11%                 |
+| impl.dtd.DTDGrammar           | 87.65%             | 6.87%           | 52.21%                    | 94.28%                 |
 
   : Evaluation Summary
 :::
 
 Precision and Recall, for the optimal configurations found in Section
-[3](#sec:clustering){reference-type="ref" reference="sec:clustering"},
+[3](#sec:clustering){reference-type="ref" reference="sec:clustering"}, are
-are reported in Table [3](#tab:eval){reference-type="ref"
+reported in Table [4](#tab:eval){reference-type="ref" reference="tab:eval"}.
-reference="tab:eval"}.
+
+\begin{center}
+\color{red} comment precision and recall values
+\end{center}
 
 ## Practical Usefulness
 
-Discuss the practical usefulness of the obtained code refactoring
+\begin{center}
-assistant in a realistic setting (1 paragraph).
+\color{red}Discuss the practical usefulness of the obtained code refactoring assistant in a
+realistic setting (1 paragraph).
+\end{center}
+

silhouette.py

@@ -8,6 +8,9 @@ import pandas as pd
 import argparse
 from k_means import cluster_kmeans
 from hierarchical import cluster_hierarchical
+from collections import Counter
+import seaborn as sns
+import matplotlib.pyplot as plt
 
 DIR: str = os.path.dirname(os.path.realpath(__file__))
 OUT_DIR: str = DIR + '/clustering'
@@ -20,47 +23,91 @@ def clean_output():
     filelist = glob.glob(OUT_DIR + '/*_silhouette.csv')
     for f in filelist:
         os.remove(f)
+    filelist = glob.glob(OUT_DIR + '/*.png')
+    for f in filelist:
+        os.remove(f)
 
 
-def validate(path: str, clazz_name: str, autorun: bool):
+def validate(path: str, clazz_name: str, autorun: bool, df_table):
     df = pd.DataFrame(columns=['k_means', 'hierarchical'], dtype=float)
+    df_stats = pd.DataFrame(columns=['algorithm', 'k', 'min', 'mean', 'max'])
+    
+    def add_stat(algo: str, k: int, Y: any, i: int):
+        y_occurs = list(Counter(Y).values()) # count number of elements in each cluster
+        df_stats.loc[i, :] = [algo, k, np.min(y_occurs), np.mean(y_occurs), np.max(y_occurs)]
 
     # We bound the number of clusters by the number of distinct points in our dataset.
     # To count them, we compute the number of "distinct" feature vectors and we
     # bound to the minimum of K_MAX and this number.
     nodup = pd.read_csv(path, index_col=0).drop_duplicates()
     max_distinct = len(nodup)
-    print("Max distinct:", max_distinct)
+    limit = min(K_MAX, max_distinct)
 
-    for n in range(2, min(K_MAX, max_distinct)):
+    i: int = 0
+    for n in range(2, limit):
         X_h, Y_h = cluster_hierarchical(path, n, save_to_disk=False)
-        df.loc[n, 'k_means'] = silhouette_score(X_h, Y_h)
+        add_stat('hierarchical', n, Y_h, i)
+        i += 1
+        df.loc[n, 'hierarchical'] = silhouette_score(X_h, Y_h)
         
         X_k, Y_k = cluster_kmeans(path, n, save_to_disk=False)
-        df.loc[n, 'hierarchical'] = silhouette_score(X_k, Y_k)
+        add_stat('k_means', n, Y_k, i)
+        i += 1
+        df.loc[n, 'k_means'] = silhouette_score(X_k, Y_k)
 
     k_kmeans = df[['k_means']].idxmax()[0]
     k_hierarchical = df[['hierarchical']].idxmax()[0]
 
-    print("K_means optimal value: " + str(k_kmeans))
+    df_table.loc[clazz_name] = [k_kmeans, 0, k_hierarchical, 0]
-    print("Hierarchical optimal value: " + str(k_hierarchical))
 
     df.to_csv(OUT_DIR + '/' + clazz_name + '_silhouette.csv')
+    df_stats.to_csv(OUT_DIR + '/' + clazz_name + '_stats.csv')
 
     if autorun:
         cluster_hierarchical(path, k_hierarchical)
         cluster_kmeans(path, k_kmeans)
 
+    # Plot stats
+    sns.set_theme(palette="hls")
+
+    # Initialize the matplotlib figure
+    f = plt.figure(figsize=(14, 12))
+    gs = f.add_gridspec(2, 2)
+    ax1 = f.add_subplot(gs[0, 0])
+    ax2 = f.add_subplot(gs[0, 1])
+    ax3 = f.add_subplot(gs[1, :])
+
+    df_k = df_stats.loc[df_stats.algorithm == 'k_means', ['k', 'min', 'mean', 'max']].set_index('k', drop=True)
+    df_h = df_stats.loc[df_stats.algorithm == 'hierarchical', ['k', 'min', 'mean', 'max']].set_index('k', drop=True)
+        
+    sns.lineplot(data=df_k, palette="tab10", ax=ax1)
+    sns.lineplot(data=df_h, palette="tab10", ax=ax2)
+    sns.lineplot(data=df, palette="tab10", ax=ax3)
+
+    # Add a legend and informative axis label
+    ax1.set(ylabel="# of elements", ylim=[0, 130], xlabel="# of clusters", xlim=[2, limit])
+    ax1.set_title("K-Means cluster sizes")
+    ax2.set(ylabel="# of elements", ylim=[0, 130], xlabel="# of clusters", xlim=[2, limit])
+    ax2.set_title("Hierarchical cluster sizes")
+    ax3.set(ylabel="Silhouette", ylim=[0, 1], xlabel="# of clusters", xlim=[2, limit])
+    ax3.set_title("Silhouette metrics per # of clusters")
+    
+    sns.despine(left=True, bottom=True)
+    f.savefig(OUT_DIR + '/' + clazz_name + '_stats.png')
+    plt.clf()
 
 
-def compute_silhouette(path: str, clazz_name: str, suffix: str):
+def compute_silhouette(path: str, clazz_name: str, suffix: str) -> float:
     df_y = pd.read_csv(OUT_DIR + '/' + clazz_name + '_' + suffix + '.csv')
     Y = df_y.iloc[:, 1].values
 
     df = pd.read_csv(path)
     X = df.drop(df.columns[0], axis=1).to_numpy()
 
-    print("Silhouette for " + suffix + ": " + str(silhouette_score(X, Y)))
+    s = round(silhouette_score(X, Y), 4)
+
+    print("Silhouette for " + suffix + ": " + str(s))
+    return s
 
 
 def main():
@@ -70,26 +117,30 @@ def main():
     parser.add_argument('--autorun', action='store_true',
                         help='if validating, computes CSV for optimal clustering automatically')
 
-
     args = parser.parse_args()
 
     if args.validate:
         clean_output()
 
+    df_table = pd.DataFrame(columns=['KMeans K', 'KMeans silhouette', 'Hierarchical K', 'Hierarchical silhouette'])
+
     filelist = glob.glob(IN_DIR + '/*.csv')
     for f in filelist:
         clazz_name = os.path.basename(f)
         clazz_name = clazz_name[:clazz_name.rfind('.')]
 
-        print(clazz_name)
+        if args.validate:
+            validate(f, clazz_name, args.autorun, df_table)
+        
+        sk = compute_silhouette(f, clazz_name, 'kmeans')
+        sh = compute_silhouette(f, clazz_name, 'hierarchical')
 
         if args.validate:
-            validate(f, clazz_name, args.autorun)
+            df_table.loc[clazz_name, 'KMeans silhouette'] = sk
+            df_table.loc[clazz_name, 'Hierarchical silhouette'] = sh
         
-        compute_silhouette(f, clazz_name, 'kmeans')
+    df_table.index.name = 'Class Name'
-        compute_silhouette(f, clazz_name, 'hierarchical')
+    print(df_table.to_markdown())
-        
-        print()
 
 
 if __name__ == '__main__':