def vectorStatistics(self, graph, treeStats=False, eigenStats=True):
"""
Find a series of statistics for the given input graph which can be represented
as vector values.
"""
Parameter.checkClass(graph, AbstractMatrixGraph)
Parameter.checkBoolean(treeStats)
statsDict = {}
statsDict["inDegreeDist"] = graph.inDegreeDistribution()
statsDict["outDegreeDist"] = graph.degreeDistribution()
logging.debug("Computing hop counts")
P = graph.findAllDistances(False)
statsDict["hopCount"] = graph.hopCount(P)
logging.debug("Computing triangle count")
if graph.getNumVertices() != 0:
statsDict["triangleDist"] = numpy.bincount(
graph.triangleSequence())
else:
statsDict["triangleDist"] = numpy.array([])
#Get the distribution of component sizes
logging.debug("Finding distribution of component sizes")
if graph.isUndirected():
components = graph.findConnectedComponents()
if len(components) != 0:
statsDict["componentsDist"] = numpy.bincount(
numpy.array([len(c) for c in components], numpy.int))
#Make sure weight matrix is symmetric
if graph.getNumVertices() != 0 and eigenStats:
logging.debug("Computing eigenvalues/vectors")
W = graph.getWeightMatrix()
W = (W + W.T) / 2
eigenDistribution, V = numpy.linalg.eig(W)
i = numpy.argmax(eigenDistribution)
statsDict["maxEigVector"] = V[:, i]
statsDict["eigenDist"] = numpy.flipud(
numpy.sort(eigenDistribution[eigenDistribution > 0]))
gc.collect()
else:
statsDict["maxEigVector"] = numpy.array([])
statsDict["eigenDist"] = numpy.array([])
if treeStats:
logging.debug("Computing statistics on trees")
trees = graph.findTrees()
statsDict["treeSizesDist"] = numpy.bincount(
[len(x) for x in trees])
treeDepths = [
GraphUtils.treeDepth((graph.subgraph(x))) for x in trees
]
statsDict["treeDepthsDist"] = numpy.bincount(treeDepths)
return statsDict
def testTreeDepth(self):
numVertices = 4
numFeatures = 1
vList = VertexList(numVertices, numFeatures)
graph = SparseGraph(vList, False)
graph.addEdge(0, 1)
graph.addEdge(0, 2)
graph.addEdge(2, 3)
self.assertEquals(GraphUtils.treeDepth(graph), 2)
numVertices = 5
vList = VertexList(numVertices, numFeatures)
graph = SparseGraph(vList, False)
graph.addEdge(0, 1)
graph.addEdge(0, 2)
graph.addEdge(2, 3)
graph.addEdge(3, 4)
self.assertEquals(GraphUtils.treeDepth(graph), 3)
def testTreeDepth(self):
numVertices = 4
numFeatures = 1
vList = VertexList(numVertices, numFeatures)
graph = SparseGraph(vList, False)
graph.addEdge(0, 1)
graph.addEdge(0, 2)
graph.addEdge(2, 3)
self.assertEquals(GraphUtils.treeDepth(graph), 2)
numVertices = 5
vList = VertexList(numVertices, numFeatures)
graph = SparseGraph(vList, False)
graph.addEdge(0, 1)
graph.addEdge(0, 2)
graph.addEdge(2, 3)
graph.addEdge(3, 4)
self.assertEquals(GraphUtils.treeDepth(graph), 3)
def vectorStatistics(self, graph, treeStats=False, eigenStats=True):
"""
Find a series of statistics for the given input graph which can be represented
as vector values.
"""
Parameter.checkClass(graph, AbstractMatrixGraph)
Parameter.checkBoolean(treeStats)
statsDict = {}
statsDict["inDegreeDist"] = graph.inDegreeDistribution()
statsDict["outDegreeDist"] = graph.degreeDistribution()
logging.debug("Computing hop counts")
P = graph.findAllDistances(False)
statsDict["hopCount"] = graph.hopCount(P)
logging.debug("Computing triangle count")
if graph.getNumVertices() != 0:
statsDict["triangleDist"] = numpy.bincount(graph.triangleSequence())
else:
statsDict["triangleDist"] = numpy.array([])
#Get the distribution of component sizes
logging.debug("Finding distribution of component sizes")
if graph.isUndirected():
components = graph.findConnectedComponents()
if len(components) != 0:
statsDict["componentsDist"] = numpy.bincount(numpy.array([len(c) for c in components], numpy.int))
#Make sure weight matrix is symmetric
if graph.getNumVertices()!=0 and eigenStats:
logging.debug("Computing eigenvalues/vectors")
W = graph.getWeightMatrix()
W = (W + W.T)/2
eigenDistribution, V = numpy.linalg.eig(W)
i = numpy.argmax(eigenDistribution)
statsDict["maxEigVector"] = V[:, i]
statsDict["eigenDist"] = numpy.flipud(numpy.sort(eigenDistribution[eigenDistribution>0]))
gc.collect()
else:
statsDict["maxEigVector"] = numpy.array([])
statsDict["eigenDist"] = numpy.array([])
if treeStats:
logging.debug("Computing statistics on trees")
trees = graph.findTrees()
statsDict["treeSizesDist"] = numpy.bincount([len(x) for x in trees])
treeDepths = [GraphUtils.treeDepth((graph.subgraph(x))) for x in trees]
statsDict["treeDepthsDist"] = numpy.bincount(treeDepths)
return statsDict
def scalarStatistics(self, graph, slowStats=True, treeStats=False):
"""
Find a series of statistics for the given input graph which can be represented
as scalar values. Return results as a vector.
"""
#This method is a bit of a mess
Parameter.checkClass(graph, AbstractSingleGraph)
Parameter.checkBoolean(slowStats)
Parameter.checkBoolean(treeStats)
statsArray = numpy.ones(self.numStats)*-1
statsArray[self.numVerticesIndex] = graph.getNumVertices()
statsArray[self.numEdgesIndex] = graph.getNumEdges()
statsArray[self.numDirEdgesIndex] = graph.getNumDirEdges()
statsArray[self.densityIndex] = graph.density()
if graph.isUndirected():
logging.debug("Finding connected components")
subComponents = graph.findConnectedComponents()
logging.debug("Done")
statsArray[self.numComponentsIndex] = len(subComponents)
nonSingletonSubComponents = [c for c in subComponents if len(c) > 1]
statsArray[self.numNonSingletonComponentsIndex] = len(nonSingletonSubComponents)
triOrMoreSubComponents = [c for c in subComponents if len(c) > 2]
statsArray[self.numTriOrMoreComponentsIndex] = len(triOrMoreSubComponents)
logging.debug("Studying max component")
if len(subComponents) != 0:
maxCompGraph = graph.subgraph(list(subComponents[0]))
statsArray[self.maxComponentSizeIndex] = len(subComponents[0])
if len(subComponents) >= 2:
statsArray[self.secondComponentSizeIndex] = len(subComponents[1])
statsArray[self.maxComponentEdgesIndex] = maxCompGraph.getNumEdges()
statsArray[self.meanComponentSizeIndex] = sum([len(x) for x in subComponents])/float(statsArray[self.numComponentsIndex])
statsArray[self.maxCompMeanDegreeIndex] = numpy.mean(maxCompGraph.outDegreeSequence())
else:
statsArray[self.maxComponentSizeIndex] = 0
statsArray[self.maxComponentEdgesIndex] = 0
statsArray[self.meanComponentSizeIndex] = 0
statsArray[self.geodesicDistMaxCompIndex] = 0
if graph.getNumVertices() != 0:
statsArray[self.meanDegreeIndex] = numpy.mean(graph.outDegreeSequence())
else:
statsArray[self.meanDegreeIndex] = 0
if slowStats:
if self.useFloydWarshall:
logging.debug("Running Floyd-Warshall")
P = graph.floydWarshall(False)
else:
logging.debug("Running Dijkstra's algorithm")
P = graph.findAllDistances(False)
statsArray[self.diameterIndex] = graph.diameter(P=P)
statsArray[self.effectiveDiameterIndex] = graph.effectiveDiameter(self.q, P=P)
statsArray[self.powerLawIndex] = graph.fitPowerLaw()[0]
statsArray[self.geodesicDistanceIndex] = graph.geodesicDistance(P=P)
statsArray[self.harmonicGeoDistanceIndex] = graph.harmonicGeodesicDistance(P=P)
if graph.isUndirected() and len(subComponents) != 0:
statsArray[self.geodesicDistMaxCompIndex] = graph.geodesicDistance(P=P, vertexInds=list(subComponents[0]))
if treeStats:
logging.debug("Computing statistics on trees")
trees = graph.findTrees()
statsArray[self.numTreesIndex] = len(trees)
nonSingletonTrees = [c for c in trees if len(c) > 1]
statsArray[self.numNonSingletonTreesIndex] = len(nonSingletonTrees)
statsArray[self.meanTreeSizeIndex] = numpy.mean([len(x) for x in trees])
treeDepths = [GraphUtils.treeDepth((graph.subgraph(list(x)))) for x in trees]
statsArray[self.meanTreeDepthIndex] = numpy.mean(treeDepths)
if len(trees) != 0:
maxTreeGraph = graph.subgraph(trees[0])
statsArray[self.maxTreeSizeIndex] = len(trees[0])
statsArray[self.maxTreeDepthIndex] = GraphUtils.treeDepth(maxTreeGraph)
if len(trees) >= 2:
secondTreeGraph = graph.subgraph(trees[1])
statsArray[self.secondTreeSizeIndex] = len(trees[1])
statsArray[self.secondTreeDepthIndex] = GraphUtils.treeDepth(secondTreeGraph)
return statsArray
def scalarStatistics(self, graph, slowStats=True, treeStats=False):
"""
Find a series of statistics for the given input graph which can be represented
as scalar values. Return results as a vector.
"""
#This method is a bit of a mess
Parameter.checkClass(graph, AbstractSingleGraph)
Parameter.checkBoolean(slowStats)
Parameter.checkBoolean(treeStats)
statsArray = numpy.ones(self.numStats) * -1
statsArray[self.numVerticesIndex] = graph.getNumVertices()
statsArray[self.numEdgesIndex] = graph.getNumEdges()
statsArray[self.numDirEdgesIndex] = graph.getNumDirEdges()
statsArray[self.densityIndex] = graph.density()
if graph.isUndirected():
subComponents = graph.findConnectedComponents()
statsArray[self.numComponentsIndex] = len(subComponents)
nonSingletonSubComponents = [
c for c in subComponents if len(c) > 1
]
statsArray[self.numNonSingletonComponentsIndex] = len(
nonSingletonSubComponents)
triOrMoreSubComponents = [c for c in subComponents if len(c) > 2]
statsArray[self.numTriOrMoreComponentsIndex] = len(
triOrMoreSubComponents)
#logging.debug("Studying max component")
if len(subComponents) != 0:
maxCompGraph = graph.subgraph(list(subComponents[0]))
statsArray[self.maxComponentSizeIndex] = len(subComponents[0])
if len(subComponents) >= 2:
statsArray[self.secondComponentSizeIndex] = len(
subComponents[1])
statsArray[
self.maxComponentEdgesIndex] = maxCompGraph.getNumEdges()
statsArray[self.meanComponentSizeIndex] = sum([
len(x) for x in subComponents
]) / float(statsArray[self.numComponentsIndex])
statsArray[self.maxCompMeanDegreeIndex] = numpy.mean(
maxCompGraph.outDegreeSequence())
else:
statsArray[self.maxComponentSizeIndex] = 0
statsArray[self.maxComponentEdgesIndex] = 0
statsArray[self.meanComponentSizeIndex] = 0
statsArray[self.geodesicDistMaxCompIndex] = 0
if graph.getNumVertices() != 0:
statsArray[self.meanDegreeIndex] = numpy.mean(
graph.outDegreeSequence())
else:
statsArray[self.meanDegreeIndex] = 0
if slowStats:
if self.useFloydWarshall:
logging.debug("Running Floyd-Warshall")
P = graph.floydWarshall(False)
else:
logging.debug("Running Dijkstra's algorithm")
P = graph.findAllDistances(False)
statsArray[self.diameterIndex] = graph.diameter(P=P)
statsArray[self.effectiveDiameterIndex] = graph.effectiveDiameter(
self.q, P=P)
statsArray[self.powerLawIndex] = graph.fitPowerLaw()[0]
statsArray[self.geodesicDistanceIndex] = graph.geodesicDistance(
P=P)
statsArray[
self.
harmonicGeoDistanceIndex] = graph.harmonicGeodesicDistance(P=P)
if graph.isUndirected() and len(subComponents) != 0:
statsArray[
self.geodesicDistMaxCompIndex] = graph.geodesicDistance(
P=P, vertexInds=list(subComponents[0]))
if treeStats:
logging.debug("Computing statistics on trees")
trees = graph.findTrees()
statsArray[self.numTreesIndex] = len(trees)
nonSingletonTrees = [c for c in trees if len(c) > 1]
statsArray[self.numNonSingletonTreesIndex] = len(nonSingletonTrees)
statsArray[self.meanTreeSizeIndex] = numpy.mean(
[len(x) for x in trees])
treeDepths = [
GraphUtils.treeDepth((graph.subgraph(list(x)))) for x in trees
]
statsArray[self.meanTreeDepthIndex] = numpy.mean(treeDepths)
if len(trees) != 0:
maxTreeGraph = graph.subgraph(trees[0])
statsArray[self.maxTreeSizeIndex] = len(trees[0])
statsArray[self.maxTreeDepthIndex] = GraphUtils.treeDepth(
maxTreeGraph)
if len(trees) >= 2:
secondTreeGraph = graph.subgraph(trees[1])
statsArray[self.secondTreeSizeIndex] = len(trees[1])
statsArray[
self.secondTreeDepthIndex] = GraphUtils.treeDepth(
secondTreeGraph)
return statsArray
