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)
