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')
class MultiDisciplinaryAuthorsExampleExperiment(Experiment): def outputSimilarityScores(self, authorMap, authors, strategy, strategyName, citationCounts = None): self.output('\n%s Scores (compared to D):' % strategyName) if citationCounts is not None: authorRow = ['%s (%d)' % (author.name, citationCounts[author.name]) for author in authors] else: authorRow = [author.name for author in authors] rows = [ authorRow, ['%1.2f' % strategy.findSimilarityScore(authorMap['D'], author) for author in authors] ] pathSimTable = texttable.Texttable() pathSimTable.add_rows(rows) self.output(pathSimTable.draw()) 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): 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')
class MultiDisciplinaryAuthorsExampleExperiment(Experiment): def outputSimilarityScores(self, authorMap, authors, strategy, strategyName): self.output('\n%s Scores (compared to D):' % strategyName) rows = [ [author.name for author in authors], ['%1.2f' % strategy.findSimilarityScore(authorMap['D'], author) for author in authors] ] pathSimTable = texttable.Texttable() pathSimTable.add_rows(rows) self.output(pathSimTable.draw()) 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)