def testFindAllSimilarityFromNodeOnPathSimExampleThree(self): """ Tests similarity for all other nodes given a single node, using example 3 from PathSim paper """ graph, authorMap, conferenceMap = SampleGraphUtility.constructPathSimExampleThree() metaPath = [Author, Paper, Conference, Paper, Author] strategy = PathSimStrategy(graph, metaPath) mike = authorMap['Mike'] mostSimilarNodes = strategy.findMostSimilarNodes(mike, 5) self.assertEquals([authorMap['Bob'], authorMap['Mary'], authorMap['Jim']], mostSimilarNodes)
def testFindAllSimilarityFromNodeOnPathSimExampleThree(self): """ Tests similarity for all other nodes given a single node, using example 3 from PathSim paper """ graph, authorMap, conferenceMap = SampleGraphUtility.constructPathSimExampleThree( ) metaPath = [Author, Paper, Conference, Paper, Author] strategy = PathSimStrategy(graph, metaPath) mike = authorMap['Mike'] mostSimilarNodes = strategy.findMostSimilarNodes(mike, 5) self.assertEquals( [authorMap['Bob'], authorMap['Mary'], authorMap['Jim']], mostSimilarNodes)
def testFindSingleSimilarityPathSimExampleThree(self): """ Tests pairwise similarity for nodes, using example 3 from PathSim paper (compute similarity scores from Mike) """ graph, authorMap, conferenceMap = SampleGraphUtility.constructPathSimExampleThree() metaPath = [Author, Paper, Conference, Paper, Author] strategy = PathSimStrategy(graph, metaPath) mike = authorMap['Mike'] jimScore, maryScore, bobScore, annScore = strategy.findSimilarityScores( mike, [authorMap['Jim'], authorMap['Mary'], authorMap['Bob'], authorMap['Ann']] ) self.assertEquals(bobScore, max([jimScore, maryScore, bobScore, annScore])) self.assertEquals(annScore, 0)
def testFindSingleSimilarityPathSimExampleThree(self): """ Tests pairwise similarity for nodes, using example 3 from PathSim paper (compute similarity scores from Mike) """ graph, authorMap, conferenceMap = SampleGraphUtility.constructPathSimExampleThree( ) metaPath = [Author, Paper, Conference, Paper, Author] strategy = PathSimStrategy(graph, metaPath) mike = authorMap['Mike'] jimScore, maryScore, bobScore, annScore = strategy.findSimilarityScores( mike, [ authorMap['Jim'], authorMap['Mary'], authorMap['Bob'], authorMap['Ann'] ]) self.assertEquals(bobScore, max([jimScore, maryScore, bobScore, annScore])) self.assertEquals(annScore, 0)
def run(self): strategy = PathSimStrategy( self.graph, [Conference, Paper, Author, Paper, Conference], True) experimentHelper = LabeledExperimentHelper( os.path.join('data', 'dbis', 'query_label', 'PathSim')) conferenceQueryNames = [ 'SIGMOD Conference', 'VLDB', 'ICDE', 'PODS', 'EDBT', 'DASFAA', 'KDD', 'ICDM', 'PKDD', 'SDM', 'PAKDD', 'WWW', 'SIGIR', 'TREC', 'APWeb' ] for conferenceQueryName in conferenceQueryNames: conferences = experimentHelper.getNodesByAttribute( self.graph, 'name', conferenceQueryName) assert (len(conferences) == 1) target = list(conferences)[0] number = 10 # Output the top ten most similar conferences on the CPAPC meta path self.output( '\n\nTop Ten Similar Conferences to %s (CPAPC meta path):' % conferenceQueryName) mostSimilarNodes = strategy.findMostSimilarNodes(target, number) apaPathTable = texttable.Texttable() headerRow = [['Rank', 'Conference', 'Relevance']] dataRows = [[ i + 1, mostSimilarNodes[i].name, experimentHelper.getLabelForNode(target, mostSimilarNodes[i]) ] for i in xrange(0, number)] apaPathTable.add_rows(headerRow + dataRows) self.output(apaPathTable.draw()) # Output the nDCG for these results self.output( '%1.3f' % CumulativeGainMeasures.normalizedDiscountedCumulativeGain( target, mostSimilarNodes, experimentHelper.labelDictionary))
def run(self): strategy = PathSimStrategy(self.graph, [Conference, Paper, Author, Paper, Conference], True) experimentHelper = LabeledExperimentHelper(os.path.join('data', 'dbis', 'query_label', 'PathSim')) conferenceQueryNames = [ 'SIGMOD Conference', 'VLDB', 'ICDE', 'PODS', 'EDBT', 'DASFAA', 'KDD', 'ICDM', 'PKDD', 'SDM', 'PAKDD', 'WWW', 'SIGIR', 'TREC', 'APWeb' ] for conferenceQueryName in conferenceQueryNames: conferences = experimentHelper.getNodesByAttribute(self.graph, 'name', conferenceQueryName) assert(len(conferences) == 1) target = list(conferences)[0] number = 10 # Output the top ten most similar conferences on the CPAPC meta path self.output('\n\nTop Ten Similar Conferences to %s (CPAPC meta path):' % conferenceQueryName) mostSimilarNodes = strategy.findMostSimilarNodes(target, number) apaPathTable = texttable.Texttable() headerRow = [['Rank', 'Conference', 'Relevance']] dataRows = [[i + 1, mostSimilarNodes[i].name, experimentHelper.getLabelForNode(target, mostSimilarNodes[i])] for i in xrange(0, number)] apaPathTable.add_rows(headerRow + dataRows) self.output(apaPathTable.draw()) # Output the nDCG for these results self.output('%1.3f' % CumulativeGainMeasures.normalizedDiscountedCumulativeGain(target, mostSimilarNodes, experimentHelper.labelDictionary))
def run(self): citationMap = { 'Mike': { 'Mike': 0, 'Jim': 0, 'Mary': 0, 'Bob': 0, 'Ann': 0, 'Joe': 0, 'Nancy': 0 }, 'Jim': { 'Mike': 20, 'Jim': 0, 'Mary': 20, 'Bob': 20, 'Ann': 0, 'Joe': 20, 'Nancy': 0 }, 'Mary': { 'Mike': 1, 'Jim': 10, 'Mary': 0, 'Bob': 1, 'Ann': 0, 'Joe': 1, 'Nancy': 0 }, 'Bob': { 'Mike': 1, 'Jim': 10, 'Mary': 1, 'Bob': 0, 'Ann': 0, 'Joe': 1, 'Nancy': 0 }, 'Ann': { 'Mike': 0, 'Jim': 0, 'Mary': 0, 'Bob': 0, 'Ann': 0, 'Joe': 0, 'Nancy': 0 }, 'Joe': { 'Mike': 0, 'Jim': 0, 'Mary': 0, 'Bob': 0, 'Ann': 0, 'Joe': 0, 'Nancy': 0 }, 'Nancy': { 'Mike': 1, 'Jim': 10, 'Mary': 1, 'Bob': 1, 'Ann': 0, 'Joe': 1, 'Nancy': 0 } } self.graph, authorMap, conferenceMap =\ SampleGraphUtility.constructPathSimExampleThree(extraAuthorsAndCitations=True, citationMap = citationMap) # Get the nodes we care about conferences = [ conferenceMap['SIGMOD'], conferenceMap['VLDB'], conferenceMap['ICDE'], conferenceMap['KDD'] ] authors = [ authorMap['Mike'], authorMap['Jim'], authorMap['Mary'], authorMap['Bob'], authorMap['Ann'], authorMap['Joe'], authorMap['Nancy'], ] metaPathUtility = EdgeBasedMetaPathUtility() # Project a 2-typed heterogeneous graph over adapted PathSim example publicationProjectedGraph = metaPathUtility.createHeterogeneousProjection( self.graph, [Author, Paper, Conference], symmetric=True) self.output('\nAdjacency Matrix (Projected):') adjMatrixTable = texttable.Texttable() rows = [['Author'] + [conference.name for conference in conferences]] rows += [[author.name] + [ publicationProjectedGraph.getNumberOfEdges(author, conference) for conference in conferences ] for author in authors] adjMatrixTable.add_rows(rows) self.output(adjMatrixTable.draw()) # Project a homogeneous citation graph over adapted PathSim example citationProjectedGraph = metaPathUtility.createHomogeneousProjection( self.graph, [Author, Paper, Paper, Author]) self.output('\nCitation Matrix:') adjMatrixTable = texttable.Texttable() rows = [['Author'] + [author.name for author in authors]] rows += [[author.name] + [ citationProjectedGraph.getNumberOfEdges(author, otherAuthor) for otherAuthor in authors ] for author in authors] adjMatrixTable.add_rows(rows) self.output(adjMatrixTable.draw()) # Output total out/in citations self.output('\nCitations Total:') totalCitationsTable = texttable.Texttable() rows = [['Author', 'In', 'Out']] for author in authors: inCount = sum( citationProjectedGraph.getNumberOfEdges(otherAuthor, author) for otherAuthor in authors) outCount = sum( citationProjectedGraph.getNumberOfEdges(author, otherAuthor) for otherAuthor in authors) rows += [[author.name, inCount, outCount]] totalCitationsTable.add_rows(rows) self.output(totalCitationsTable.draw()) # Get PathSim similarity scores pathSimStrategy = PathSimStrategy( self.graph, [Author, Paper, Conference, Paper, Author], True) self.outputSimilarityScores(authorMap, authors, pathSimStrategy, 'APCPA PathSim') # Output SimRank-related scores strategy = SimRankStrategy(self.graph, [Author, Paper, Paper, Author], symmetric=True) self.outputSimilarityScores(authorMap, authors, strategy, "SimRank") # Output the projected PageRank/HITS similarity scores for name, algorithm in zip( ['PageRank', 'HITS'], [PageRankDistanceStrategy, HITSDistanceStrategy]): strategy = algorithm(self.graph, [Author, Paper, Paper, Author], symmetric=True) self.outputSimilarityScores(authorMap, authors, strategy, "%s-Distance" % name) # Get NeighborSim similarity scores inNeighborSimStrategy = NeighborSimStrategy( self.graph, [Author, Paper, Paper, Author]) self.outputSimilarityScores(authorMap, authors, inNeighborSimStrategy, 'APPA NeighborSim-In') outNeighborSimStrategy = NeighborSimStrategy( self.graph, [Author, Paper, Paper, Author], reversed=True, smoothed=True) self.outputSimilarityScores(authorMap, authors, outNeighborSimStrategy, 'APPA NeighborSim-Out') # Combined best PR-distance algorithm simRankStrategy = SimRankStrategy(self.graph, [Author, Paper, Paper, Author], symmetric=True) simRank = AggregateSimilarityStrategy( self.graph, [pathSimStrategy, simRankStrategy], [0.5, 0.5]) self.outputSimilarityScores(authorMap, authors, simRank, 'APCPA Pathsim, APPA SimRank') # Combined best neighborsim score combinedNeighborSim = AggregateSimilarityStrategy( self.graph, [pathSimStrategy, inNeighborSimStrategy, outNeighborSimStrategy], [0.6, 0.2, 0.2]) self.outputSimilarityScores( authorMap, authors, combinedNeighborSim, 'APCPA Pathsim, APPA NeighborSim-Combined')
def run(self): self.graph, authorMap, conferenceMap, totalCitationCount = SampleGraphUtility.constructMultiDisciplinaryAuthorExample(indirectAuthor = True) # Get the nodes we care about conferences = [ conferenceMap['VLDB'], conferenceMap['KDD'] ] authors = [ authorMap['A'], authorMap['B'], authorMap['C'], authorMap['D'], authorMap['E'], authorMap['F'], authorMap['G'], authorMap['H'], authorMap['I'], authorMap['J'], ] self.metaPathUtility = EdgeBasedMetaPathUtility() # Build homogeneous projection of network (authors, with edges for times authors cite each other) projectedGraph = self.metaPathUtility.createHomogeneousProjection(self.graph, [Author, Paper, Paper, Author]) authorCitationCounts = {} for author in projectedGraph.getNodes(): authorCitationCounts[author] = {} for otherAuthor in projectedGraph.getNodes(): authorCitationCounts[author][otherAuthor] = projectedGraph.getNumberOfEdges(author, otherAuthor) # Output the adjacency matrix for authors-authors in the graph self.output('\nCitation Matrix:') adjMatrixTable = texttable.Texttable() rows = [['Author'] + [author.name for author in authors]] rows += [[author.name] + [authorCitationCounts[author][otherAuthor] for otherAuthor in authors] for author in authors] adjMatrixTable.add_rows(rows) self.output(adjMatrixTable.draw()) # Output the adjacency matrix for authors & conferences in the graph self.output('\nAdjacency Matrix:') adjMatrixTable = texttable.Texttable() projectedGraph = self.metaPathUtility.createHeterogeneousProjection(self.graph, [Author, Paper, Conference]) rows = [[''] + [conference.name for conference in conferences]] rows += [[author.name] + [projectedGraph.getNumberOfEdges(author, conference) for conference in conferences] for author in authors] adjMatrixTable.add_rows(rows) self.output(adjMatrixTable.draw()) # Output total citation counts self.output('\nTotal Citation Counts:') rows = [[author.name for author in authors],['%d' % totalCitationCount[author.name] for author in authors]] citationCountTable = texttable.Texttable() citationCountTable.add_rows(rows) self.output(citationCountTable.draw()) # Output the PathSim similarity scores pathsimStretegy = PathSimStrategy(self.graph, [Author, Paper, Conference, Paper, Author], True) self.outputSimilarityScores(authorMap, authors, pathsimStretegy, "PathSim") # Output the NeighborSim similarity scores neighborsimStrategy = NeighborSimStrategy(self.graph, [Conference, Paper, Paper, Author]) self.outputSimilarityScores(authorMap, authors, neighborsimStrategy, "NeighborSim (CPPA)") # Output the NeighborSim similarity scores neighborsimStrategy = NeighborSimStrategy(self.graph, [Author, Paper, Paper, Author]) self.outputSimilarityScores(authorMap, authors, neighborsimStrategy, "NeighborSim (APPA)") # Constant weight propagation strategy propagatedNeighborsimStrategy = NeighborSimConstantPropagationStrategy(self.graph, [Author, Paper, Paper, Author], iterations = 2) self.outputSimilarityScores(authorMap, authors, propagatedNeighborsimStrategy, "NeighborSim-ConstantPropagation-2") propagatedNeighborsimStrategy = NeighborSimConstantPropagationStrategy(self.graph, [Author, Paper, Paper, Author], iterations = 3) self.outputSimilarityScores(authorMap, authors, propagatedNeighborsimStrategy, "NeighborSim-ConstantPropagation-3") propagatedNeighborsimStrategy = NeighborSimConstantPropagationStrategy(self.graph, [Author, Paper, Paper, Author], iterations = 4) self.outputSimilarityScores(authorMap, authors, propagatedNeighborsimStrategy, "NeighborSim-ConstantPropagation-4") propagatedNeighborsimStrategy = NeighborSimConstantPropagationStrategy(self.graph, [Author, Paper, Paper, Author], iterations = 50) self.outputSimilarityScores(authorMap, authors, propagatedNeighborsimStrategy, "NeighborSim-ConstantPropagation-50") # Preferential attachment propagation strategy propagatedNeighborsimStrategy = NeighborSimConstantPreferentialAttachmentStrategy(self.graph, [Author, Paper, Paper, Author], iterations = 2) self.outputSimilarityScores(authorMap, authors, propagatedNeighborsimStrategy, "NeighborSim-WeightedPropagation-2") propagatedNeighborsimStrategy = NeighborSimConstantPreferentialAttachmentStrategy(self.graph, [Author, Paper, Paper, Author], iterations = 3) self.outputSimilarityScores(authorMap, authors, propagatedNeighborsimStrategy, "NeighborSim-WeightedPropagation-3") propagatedNeighborsimStrategy = NeighborSimConstantPreferentialAttachmentStrategy(self.graph, [Author, Paper, Paper, Author], iterations = 4) self.outputSimilarityScores(authorMap, authors, propagatedNeighborsimStrategy, "NeighborSim-WeightedPropagation-4") propagatedNeighborsimStrategy = NeighborSimConstantPreferentialAttachmentStrategy(self.graph, [Author, Paper, Paper, Author], iterations = 50) self.outputSimilarityScores(authorMap, authors, propagatedNeighborsimStrategy, "NeighborSim-WeightedPropagation-50") # Neighbor citation count difference strategy citeCountNeighborsimStrategy = NeighborSimStrategy(self.graph, [Paper, Paper, Author], commonNeighbors = False) self.outputSimilarityScores(authorMap, authors, citeCountNeighborsimStrategy, "NeighborSim-CiteCountDiff", citationCounts = totalCitationCount)
def run(self): self.graph, authorMap, conferenceMap, totalCitationCount = SampleGraphUtility.constructMultiDisciplinaryAuthorExample() # Get the nodes we care about conferences = [ conferenceMap['VLDB'], conferenceMap['KDD'] ] authors = [ authorMap['A'], authorMap['B'], authorMap['C'], authorMap['D'], authorMap['E'], authorMap['F'], authorMap['G'], authorMap['H'], authorMap['I'], ] self.metaPathUtility = EdgeBasedMetaPathUtility() # Build homogeneous projection of network (authors, with edges for times authors cite each other) projectedGraph = self.metaPathUtility.createHomogeneousProjection(self.graph, [Author, Paper, Paper, Author]) authorCitationCounts = {} for author in projectedGraph.getNodes(): authorCitationCounts[author] = {} for otherAuthor in projectedGraph.getNodes(): authorCitationCounts[author][otherAuthor] = projectedGraph.getNumberOfEdges(author, otherAuthor) # Output the adjacency matrix for authors-authors in the graph self.output('\nCitation Matrix:') adjMatrixTable = texttable.Texttable() rows = [['Author'] + [author.name for author in authors]] rows += [[author.name] + [authorCitationCounts[author][otherAuthor] for otherAuthor in authors] for author in authors] adjMatrixTable.add_rows(rows) self.output(adjMatrixTable.draw()) # Output the adjacency matrix for authors & conferences in the graph self.output('\nAdjacency Matrix:') adjMatrixTable = texttable.Texttable() projectedGraph = self.metaPathUtility.createHeterogeneousProjection(self.graph, [Author, Paper, Conference]) rows = [[''] + [conference.name for conference in conferences]] rows += [[author.name] + [projectedGraph.getNumberOfEdges(author, conference) for conference in conferences] for author in authors] adjMatrixTable.add_rows(rows) self.output(adjMatrixTable.draw()) # Output total citation counts self.output('\nTotal Citation Counts:') rows = [[author.name for author in authors],['%d' % totalCitationCount[author.name] for author in authors]] citationCountTable = texttable.Texttable() citationCountTable.add_rows(rows) self.output(citationCountTable.draw()) # Output the NeighborSim similarity scores strategy = NeighborSimStrategy(self.graph, [Conference, Paper, Paper, Author]) self.outputSimilarityScores(authorMap, authors, strategy, "NeighborSim") # Output the PathSim similarity scores pathsimStretegy = PathSimStrategy(self.graph, [Author, Paper, Conference, Paper, Author], True) self.outputSimilarityScores(authorMap, authors, pathsimStretegy, "PathSim") # Output SimRank-related scores simrankStrategy = SimRankStrategy(self.graph, [Author, Paper, Paper, Author]) self.outputSimilarityScores(authorMap, authors, simrankStrategy, "SimRank") # Output pathsim - simrank scores combinedNeighborSim = AggregateSimilarityStrategy(self.graph, [simrankStrategy, pathsimStretegy], [0.5, 0.5]) self.outputSimilarityScores(authorMap, authors, combinedNeighborSim, 'APCPA Pathsim, APPA SimRank') # Output the projected PageRank/HITS similarity scores for name, algorithm in zip(['PageRank', 'HITS'], [PageRankDistanceStrategy, HITSDistanceStrategy]): researchAreas = { (authorMap['A'], authorMap['B'], authorMap['C'], authorMap['D'], authorMap['E'], authorMap['I']), (authorMap['F'], authorMap['G'], authorMap['H'], authorMap['D'], authorMap['E'], authorMap['I']), } strategy = algorithm(self.graph, [Author, Paper, Paper, Author], nodeSets=researchAreas, symmetric=True) self.outputSimilarityScores(authorMap, authors, strategy, "%s-Distance" % name)
def run(self): self.graph, authorMap, conferenceMap = SampleGraphUtility.constructPathSimExampleThree( ) # Get the nodes we care about conferences = [ conferenceMap['SIGMOD'], conferenceMap['VLDB'], conferenceMap['ICDE'], conferenceMap['KDD'] ] authors = [ authorMap['Mike'], authorMap['Jim'], authorMap['Mary'], authorMap['Bob'], authorMap['Ann'], ] metaPathUtility = EdgeBasedMetaPathUtility() self.output('\nAPC Adjacency Matrix:') apcadjMatrix, nodesIndex = metaPathUtility.getAdjacencyMatrixFromGraph( self.graph, [Author, Paper, Conference], project=True) adjMatrixTable = texttable.Texttable() rows = [['Author'] + [conference.name for conference in conferences]] rows += [[author.name] + [ apcadjMatrix[nodesIndex[author]][nodesIndex[conference]] for conference in conferences ] for author in authors] adjMatrixTable.add_rows(rows) self.output(adjMatrixTable.draw()) self.output('\nCPA Adjacency Matrix:') cpaadjMatrix, dsad = metaPathUtility.getAdjacencyMatrixFromGraph( self.graph, [Conference, Paper, Author], project=True) adjMatrixTable = texttable.Texttable() rows = [['Conference'] + [author.name for author in authors]] rows += [[conference.name] + [ cpaadjMatrix[nodesIndex[conference]][nodesIndex[author]] for author in authors ] for conference in conferences] adjMatrixTable.add_rows(rows) self.output(adjMatrixTable.draw()) self.output('\nAPCPA Adjacency Matrix (Computed):') adjMatrix = numpy.dot(apcadjMatrix, cpaadjMatrix) adjMatrixTable = texttable.Texttable() rows = [['Author'] + [author.name for author in authors]] rows += [[author.name] + [ adjMatrix[nodesIndex[author]][nodesIndex[otherAuthor]] for otherAuthor in authors ] for author in authors] adjMatrixTable.add_rows(rows) self.output(adjMatrixTable.draw()) # Output homogeneous simrank comparison homogeneousSimRankStrategy = SimRankStrategy(self.graph) self.outputSimilarityScores(authorMap, authors, homogeneousSimRankStrategy, 'Homogeneous SimRank') projectedGraph = metaPathUtility.createHeterogeneousProjection( self.graph, [Author, Paper, Conference], symmetric=True) # Output heterogeneous simrank comparison heterogeneousSimRankStrategy = SimRankStrategy(projectedGraph) self.outputSimilarityScores(authorMap, authors, heterogeneousSimRankStrategy, 'APC Heterogeneous SimRank') # Output heterogeneous simrank w/ squared neighbors comparison def sqNeighborsNorm(graph, a, b, sim): aNeighbors, bNeighbors = graph.getPredecessors( a), graph.getPredecessors(b) return float(len(aNeighbors)**2 * len(bNeighbors)**2) heterogeneousSquaredSimRankStrategy = SimRankStrategy( projectedGraph, normalization=sqNeighborsNorm) self.outputSimilarityScores(authorMap, authors, heterogeneousSquaredSimRankStrategy, 'Squared Heterogeneous SimRank') # Output NeighborSim similarity scores neighborSimStrategy = NeighborSimStrategy(self.graph, [Author, Paper, Conference], symmetric=True) self.outputSimilarityScores(authorMap, authors, neighborSimStrategy, 'APC NeighborSim') # Output the PathSim similarity scores pathsimStrategy = PathSimStrategy( self.graph, [Author, Paper, Conference, Paper, Author], symmetric=True) self.outputSimilarityScores(authorMap, authors, pathsimStrategy, 'APCPA PathSim')