def __init__(self,
graph,
metaPath=None,
symmetric=False,
conserveMemory=False):
"""
Constructs a meta path similarity strategy, storing the meta path data for this strategy.
@param metaPath Meta path object where the list of classes contains classes of nodes in the graph,
and weights in [0,1] containing the importance of the meta path
@param symmetric Whether or not to enforce that meta paths must be symmetric
For example, if 'symmetric' and 'evenLength' are both 'true', for meta path 'ABC', we will only count meta
path 'ABCCBA', depending on, and if 'symmetric' is 'true' while 'evenLength' is 'false', we will only count
meta paths 'ABCBA'
"""
super(MetaPathSimilarityStrategy, self).__init__(graph)
self.metaPath = metaPath
self.symmetric = symmetric
self.conserveMemory = conserveMemory
self.metaPathUtility = EdgeBasedMetaPathUtility()
class MetaPathSimilarityStrategy(SimilarityStrategy):
"""
Generic class for similarity strategies that use meta paths
"""
def __init__(self, graph, metaPath = None, symmetric = False, conserveMemory = False):
"""
Constructs a meta path similarity strategy, storing the meta path data for this strategy.
@param metaPath Meta path object where the list of classes contains classes of nodes in the graph,
and weights in [0,1] containing the importance of the meta path
@param symmetric Whether or not to enforce that meta paths must be symmetric
For example, if 'symmetric' and 'evenLength' are both 'true', for meta path 'ABC', we will only count meta
path 'ABCCBA', depending on, and if 'symmetric' is 'true' while 'evenLength' is 'false', we will only count
meta paths 'ABCBA'
"""
super(MetaPathSimilarityStrategy, self).__init__(graph)
self.metaPath = metaPath
self.symmetric = symmetric
self.conserveMemory = conserveMemory
self.metaPathUtility = EdgeBasedMetaPathUtility()
def findMostSimilarNodes(self, source, number=None, conserveMemory=False):
"""
Simple find the similarity scores between this node and all reachable nodes on this meta path. Note that if
there are fewer reachable nodes than "number", the number of reachable nodes will be returned.
"""
# If no number is provided, default to the number of nodes in the graph
if number is None:
number = self.n
# Get similarity scores for all entries
reachableNodes = self.metaPathUtility.findMetaPathNeighbors(self.graph, source, self.metaPath)
for reachableNode in reachableNodes:
self.similarityScores[source][reachableNode] = self.findSimilarityScore(source, reachableNode)
# Sort by increasing score
mostSimilarNodes = sorted(self.similarityScores[source].iteritems(), key=operator.itemgetter(1))
# Remove source, nodes of different types, and reverse
newMostSimilarNodes = []
for node, score in mostSimilarNodes:
if node != source and node.__class__ == source.__class__:
newMostSimilarNodes.append(node)
newMostSimilarNodes.reverse()
number = min([number, len(newMostSimilarNodes)])
mostSimilarNodes = newMostSimilarNodes[:number]
return mostSimilarNodes
def __init__(self, graph, metaPath = None, symmetric = False, conserveMemory = False):
"""
Constructs a meta path similarity strategy, storing the meta path data for this strategy.
@param metaPath Meta path object where the list of classes contains classes of nodes in the graph,
and weights in [0,1] containing the importance of the meta path
@param symmetric Whether or not to enforce that meta paths must be symmetric
For example, if 'symmetric' and 'evenLength' are both 'true', for meta path 'ABC', we will only count meta
path 'ABCCBA', depending on, and if 'symmetric' is 'true' while 'evenLength' is 'false', we will only count
meta paths 'ABCBA'
"""
super(MetaPathSimilarityStrategy, self).__init__(graph)
self.metaPath = metaPath
self.symmetric = symmetric
self.conserveMemory = conserveMemory
self.metaPathUtility = EdgeBasedMetaPathUtility()
def run(self):
self.graph, authorMap, conference, citationsPublications = SampleGraphUtility.constructSkewedCitationPublicationExample(
introduceRandomness=False
)
# Get the nodes we care about
authors = [
authorMap["Alice"],
authorMap["Bob"],
authorMap["Carol"],
authorMap["Dave"],
authorMap["Ed"],
authorMap["Frank"],
]
metaPathUtility = EdgeBasedMetaPathUtility()
# Output adjacency matrices
self.output("\nCPA Adjacency Matrix:")
cpaadjMatrix, nodesIndex = 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]]
adjMatrixTable.add_rows(rows)
self.output(adjMatrixTable.draw())
self.output("\nCPPA Adjacency Matrix:")
cpaadjMatrix, nodesIndex = metaPathUtility.getAdjacencyMatrixFromGraph(
self.graph, [Conference, Paper, 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]]
adjMatrixTable.add_rows(rows)
self.output(adjMatrixTable.draw())
# Total citation & publication counts
self.output("\nCitation & Publication Counts")
adjMatrixTable = texttable.Texttable()
rows = [["Measure"] + [author.name for author in authors]]
rows += [["Citations"] + [citationsPublications[author][0] for author in authors]]
rows += [["Publications"] + [citationsPublications[author][1] for author in authors]]
adjMatrixTable.add_rows(rows)
self.output(adjMatrixTable.draw())
# Output NeighborSim & PathSim similarity scores
neighborSimStrategy = NeighborSimStrategy(self.graph, [Conference, Paper, Author], symmetric=True)
self.outputSimilarityScores(authorMap, authors, neighborSimStrategy, "APCPA PathSim")
neighborSimStrategy = NeighborSimStrategy(self.graph, [Conference, Paper, Paper, Author])
self.outputSimilarityScores(authorMap, authors, neighborSimStrategy, "APPCPPA PathSim")
# Omit extra duplicate entry in path, and weight at different levels of 'relative'
for strategy, generalStrategyTitle in [
(FlattenedMatrixStrategy, "FlatMat"),
(VectorProductStrategy, "VectorProduct"),
]:
for w in [1.0, 0.5, 0]:
neighborPathShapeStrategy = strategy(
self.graph, weight=w, omit=[], metaPath=[Conference, Paper, Paper, Author], symmetric=True
)
strategyTitle = "APPCPPA %s ShapeSim (%1.2f weight)" % (generalStrategyTitle, w)
self.outputSimilarityScores(authorMap, authors, neighborPathShapeStrategy, strategyTitle)
w = 1.0
neighborPathShapeStrategy = VectorProductStrategy(
self.graph, weight=w, omit=[0], metaPath=[Conference, Paper, Paper, Author], symmetric=True
)
strategyTitle = "APPCPPA VectorProduct ShapeSim omitting CPC (%1.2f weight)" % w
self.outputSimilarityScores(authorMap, authors, neighborPathShapeStrategy, strategyTitle)
# Output recursive pathsim strategy score(s)
recursivePathSimStrategy = RecursivePathSimStrategy(self.graph, [Conference, Paper, Paper, Author])
self.outputSimilarityScores(authorMap, authors, recursivePathSimStrategy, "APPCPPA Recursive PathSim")
class MetaPathSimilarityStrategy(SimilarityStrategy):
"""
Generic class for similarity strategies that use meta paths
"""
def __init__(self,
graph,
metaPath=None,
symmetric=False,
conserveMemory=False):
"""
Constructs a meta path similarity strategy, storing the meta path data for this strategy.
@param metaPath Meta path object where the list of classes contains classes of nodes in the graph,
and weights in [0,1] containing the importance of the meta path
@param symmetric Whether or not to enforce that meta paths must be symmetric
For example, if 'symmetric' and 'evenLength' are both 'true', for meta path 'ABC', we will only count meta
path 'ABCCBA', depending on, and if 'symmetric' is 'true' while 'evenLength' is 'false', we will only count
meta paths 'ABCBA'
"""
super(MetaPathSimilarityStrategy, self).__init__(graph)
self.metaPath = metaPath
self.symmetric = symmetric
self.conserveMemory = conserveMemory
self.metaPathUtility = EdgeBasedMetaPathUtility()
def findMostSimilarNodes(self, source, number=None, conserveMemory=False):
"""
Simple find the similarity scores between this node and all reachable nodes on this meta path. Note that if
there are fewer reachable nodes than "number", the number of reachable nodes will be returned.
"""
# If no number is provided, default to the number of nodes in the graph
if number is None:
number = self.n
# Get similarity scores for all entries
reachableNodes = self.metaPathUtility.findMetaPathNeighbors(
self.graph, source, self.metaPath)
for reachableNode in reachableNodes:
self.similarityScores[source][
reachableNode] = self.findSimilarityScore(
source, reachableNode)
# Sort by increasing score
mostSimilarNodes = sorted(self.similarityScores[source].iteritems(),
key=operator.itemgetter(1))
# Remove source, nodes of different types, and reverse
newMostSimilarNodes = []
for node, score in mostSimilarNodes:
if node != source and node.__class__ == source.__class__:
newMostSimilarNodes.append(node)
newMostSimilarNodes.reverse()
number = min([number, len(newMostSimilarNodes)])
mostSimilarNodes = newMostSimilarNodes[:number]
return mostSimilarNodes
def _getImplementation(self):
return EdgeBasedMetaPathUtility()
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):
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 = 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')
def testConstructPathSimExampleThree(self):
"""
Tests the construction of "Example 3" from PathSim paper. Specifically, checks adjacency matrix shown in
this example for Author-Paper-Conference meta paths.
"""
graph, authorMap, conferenceMap = SampleGraphUtility.constructPathSimExampleThree()
metaPath = [Author, Paper, Conference]
metaPathUtility = EdgeBasedMetaPathUtility()
# Mike's adjacency to conferences
self.assertEquals(2, len(metaPathUtility.findMetaPaths(graph, authorMap['Mike'], conferenceMap['SIGMOD'], metaPath)))
self.assertEquals(1, len(metaPathUtility.findMetaPaths(graph, authorMap['Mike'], conferenceMap['VLDB'], metaPath)))
self.assertEquals(0, len(metaPathUtility.findMetaPaths(graph, authorMap['Mike'], conferenceMap['ICDE'], metaPath)))
self.assertEquals(0, len(metaPathUtility.findMetaPaths(graph, authorMap['Mike'], conferenceMap['KDD'], metaPath)))
# Jim's adjacency to conferences
self.assertEquals(50, len(metaPathUtility.findMetaPaths(graph, authorMap['Jim'], conferenceMap['SIGMOD'], metaPath)))
self.assertEquals(20, len(metaPathUtility.findMetaPaths(graph, authorMap['Jim'], conferenceMap['VLDB'], metaPath)))
self.assertEquals(0, len(metaPathUtility.findMetaPaths(graph, authorMap['Jim'], conferenceMap['ICDE'], metaPath)))
self.assertEquals(0, len(metaPathUtility.findMetaPaths(graph, authorMap['Jim'], conferenceMap['KDD'], metaPath)))
# Mary's adjacency to conferences
self.assertEquals(2, len(metaPathUtility.findMetaPaths(graph, authorMap['Mary'], conferenceMap['SIGMOD'], metaPath)))
self.assertEquals(0, len(metaPathUtility.findMetaPaths(graph, authorMap['Mary'], conferenceMap['VLDB'], metaPath)))
self.assertEquals(1, len(metaPathUtility.findMetaPaths(graph, authorMap['Mary'], conferenceMap['ICDE'], metaPath)))
self.assertEquals(0, len(metaPathUtility.findMetaPaths(graph, authorMap['Mary'], conferenceMap['KDD'], metaPath)))
# Bob's adjacency to conferences
self.assertEquals(2, len(metaPathUtility.findMetaPaths(graph, authorMap['Bob'], conferenceMap['SIGMOD'], metaPath)))
self.assertEquals(1, len(metaPathUtility.findMetaPaths(graph, authorMap['Bob'], conferenceMap['VLDB'], metaPath)))
self.assertEquals(0, len(metaPathUtility.findMetaPaths(graph, authorMap['Bob'], conferenceMap['ICDE'], metaPath)))
self.assertEquals(0, len(metaPathUtility.findMetaPaths(graph, authorMap['Bob'], conferenceMap['KDD'], metaPath)))
# Ann's adjacency to conferences
self.assertEquals(0, len(metaPathUtility.findMetaPaths(graph, authorMap['Ann'], conferenceMap['SIGMOD'], metaPath)))
self.assertEquals(0, len(metaPathUtility.findMetaPaths(graph, authorMap['Ann'], conferenceMap['VLDB'], metaPath)))
self.assertEquals(1, len(metaPathUtility.findMetaPaths(graph, authorMap['Ann'], conferenceMap['ICDE'], metaPath)))
self.assertEquals(1, len(metaPathUtility.findMetaPaths(graph, authorMap['Ann'], conferenceMap['KDD'], metaPath)))
def run(self):
self.graph, authorMap, conference, citationsPublications = \
SampleGraphUtility.constructSkewedCitationPublicationExample(introduceRandomness=False)
# Get the nodes we care about
authors = [
authorMap['Alice'],
authorMap['Bob'],
authorMap['Carol'],
authorMap['Dave'],
authorMap['Ed'],
authorMap['Frank']
]
metaPathUtility = EdgeBasedMetaPathUtility()
# Output adjacency matrices
self.output('\nCPA Adjacency Matrix:')
cpaadjMatrix, nodesIndex = 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]]
adjMatrixTable.add_rows(rows)
self.output(adjMatrixTable.draw())
self.output('\nCPPA Adjacency Matrix:')
cpaadjMatrix, nodesIndex = metaPathUtility.getAdjacencyMatrixFromGraph(
self.graph, [Conference, Paper, 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]]
adjMatrixTable.add_rows(rows)
self.output(adjMatrixTable.draw())
# Total citation & publication counts
self.output('\nCitation & Publication Counts')
adjMatrixTable = texttable.Texttable()
rows = [['Measure'] + [author.name for author in authors]]
rows += [['Citations'] + [citationsPublications[author][0] for author in authors]]
rows += [['Publications'] + [citationsPublications[author][1] for author in authors]]
adjMatrixTable.add_rows(rows)
self.output(adjMatrixTable.draw())
# Output NeighborSim & PathSim similarity scores
neighborSimStrategy = NeighborSimStrategy(self.graph, [Conference, Paper, Author], symmetric=True)
self.outputSimilarityScores(authorMap, authors, neighborSimStrategy, 'APCPA PathSim')
neighborSimStrategy = NeighborSimStrategy(self.graph, [Conference, Paper, Paper, Author])
self.outputSimilarityScores(authorMap, authors, neighborSimStrategy, 'APPCPPA PathSim')
# Omit extra duplicate entry in path, and weight at different levels of 'relative'
for strategy, generalStrategyTitle in [(FlattenedMatrixStrategy, 'FlatMat'), (VectorProductStrategy, 'VectorProduct')]:
for w in [1.0, 0.5, 0]:
neighborPathShapeStrategy = strategy(
self.graph, weight=w, omit=[], metaPath=[Conference, Paper, Paper, Author], symmetric=True
)
strategyTitle = 'APPCPPA %s ShapeSim (%1.2f weight)' % (generalStrategyTitle, w)
self.outputSimilarityScores(authorMap, authors, neighborPathShapeStrategy, strategyTitle)
w = 1.0
neighborPathShapeStrategy = VectorProductStrategy(
self.graph, weight=w, omit=[0], metaPath=[Conference, Paper, Paper, Author], symmetric=True
)
strategyTitle = 'APPCPPA VectorProduct ShapeSim omitting CPC (%1.2f weight)' % w
self.outputSimilarityScores(authorMap, authors, neighborPathShapeStrategy, strategyTitle)
# Output recursive pathsim strategy score(s)
recursivePathSimStrategy = RecursivePathSimStrategy(self.graph, [Conference, Paper, Paper, Author])
self.outputSimilarityScores(authorMap, authors, recursivePathSimStrategy, 'APPCPPA Recursive PathSim')
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')
