def testGetAllEdgeIndices(self):
graph = DictGraph()
graph.addEdge("a", "b")
graph.addEdge("a", "c")
graph.addEdge("a", "d")
graph.addEdge("d", "e")
edgeIndices = graph.getAllEdgeIndices()
keys = graph.getAllVertexIds()
self.assertEquals(edgeIndices.shape[0], graph.getNumEdges())
for i in range(edgeIndices.shape[0]):
self.assertTrue(graph.getEdge(keys[int(edgeIndices[i, 0])], keys[edgeIndices[i, 1]]) == 1)
graph = DictGraph(False)
graph.addEdge("a", "b")
graph.addEdge("b", "a")
graph.addEdge("a", "c")
graph.addEdge("a", "d")
graph.addEdge("d", "e")
edgeIndices = graph.getAllEdgeIndices()
keys = graph.getAllVertexIds()
self.assertEquals(edgeIndices.shape[0], graph.getNumEdges())
for i in range(edgeIndices.shape[0]):
self.assertTrue(graph.getEdge(keys[int(edgeIndices[i, 0])], keys[edgeIndices[i, 1]]) == 1)
def testRemoveVertex(self):
graph = DictGraph()
graph.addEdge(0, 1)
graph.addEdge(0, 2)
graph.addEdge(0, 3)
graph.addEdge(1, 2)
graph.addEdge(2, 3)
graph.addEdge(3, 4)
graph.removeVertex(4)
self.assertFalse(graph.vertexExists(4))
self.assertFalse(graph.edgeExists(3, 4))
graph.removeVertex(3)
self.assertFalse(graph.vertexExists(3))
self.assertFalse(graph.edgeExists(2, 3))
self.assertFalse(graph.edgeExists(0, 3))
graph.removeVertex(2)
self.assertFalse(graph.vertexExists(2))
self.assertFalse(graph.edgeExists(1, 2))
self.assertFalse(graph.edgeExists(0, 2))
self.assertTrue(graph.getAllVertexIds() == [0, 1])
self.assertTrue(graph.getAllEdges() == [(0, 1)])
#Try directed graph
graph = DictGraph(False)
graph.addEdge(0, 1)
graph.addEdge(1, 0)
graph.addEdge(0, 3)
graph.addEdge(1, 2)
graph.addEdge(2, 3)
graph.addEdge(3, 4)
graph.removeVertex(0)
self.assertFalse(graph.vertexExists(0))
self.assertFalse(graph.edgeExists(0, 1))
self.assertFalse(graph.edgeExists(0, 3))
self.assertFalse(graph.edgeExists(1, 0))
graph.removeVertex(2)
self.assertFalse(graph.vertexExists(2))
self.assertFalse(graph.edgeExists(1, 2))
self.assertFalse(graph.edgeExists(2, 3))
self.assertTrue(graph.getAllVertexIds() == [1, 3, 4])
self.assertTrue(graph.getAllEdges() == [(3, 4)])
def testGetWeightMatrix(self):
graph = DictGraph()
graph.addEdge("a", "b")
graph.addEdge("a", "c")
graph.addEdge("a", "d")
graph.addEdge("d", "e")
W = graph.getWeightMatrix()
keys = graph.getAllVertexIds()
for i in range(len(keys)):
for j in range(len(keys)):
if W[i, j] == 1:
self.assertEquals(graph.getEdge(keys[i], keys[j]), 1)
else:
self.assertEquals(graph.getEdge(keys[i], keys[j]), None)
#Try a directed graph
graph = DictGraph(False)
graph.addEdge("a", "b")
graph.addEdge("a", "c")
graph.addEdge("a", "d")
graph.addEdge("d", "e")
W = graph.getWeightMatrix()
for i in range(len(keys)):
for j in range(len(keys)):
if W[i, j] == 1:
self.assertEquals(graph.getEdge(keys[i], keys[j]), 1)
else:
self.assertEquals(graph.getEdge(keys[i], keys[j]), None)
def testGetAllVertexIds(self):
dictGraph = DictGraph(True)
dictGraph.addEdge(1, 2, 12)
dictGraph.addEdge(1, 3, 18)
dictGraph.setVertex(5, 12)
self.assertEquals(dictGraph.getAllVertexIds(), [1, 2, 3, 5])
def testSetVertices(self):
graph = DictGraph()
vertexIndices = [1, 2, 3]
vertices = ["a", "b", "c"]
graph.setVertices(vertexIndices, vertices)
vertexIndices2 = graph.getAllVertexIds()
vertices2 = graph.getVertices(vertexIndices2)
self.assertEquals(vertexIndices, vertexIndices2)
self.assertEquals(vertices, vertices2)
def testDijkstrasAlgorithm(self):
graph = DictGraph()
graph.addEdge(0, 1, 1)
graph.addEdge(1, 2, 1)
graph.addEdge(1, 3, 1)
graph.addEdge(2, 4, 1)
graph.setVertex(4, 1)
self.assertTrue((graph.dijkstrasAlgorithm(0) == numpy.array([0, 1, 2, 2, 3])).all())
self.assertTrue((graph.dijkstrasAlgorithm(1) == numpy.array([1, 0, 1, 1, 2])).all())
self.assertTrue((graph.dijkstrasAlgorithm(2) == numpy.array([2, 1, 0, 2, 1])).all())
self.assertTrue((graph.dijkstrasAlgorithm(3) == numpy.array([2, 1, 2, 0, 3])).all())
self.assertTrue((graph.dijkstrasAlgorithm(4) == numpy.array([3, 2, 1, 3, 0])).all())
#Test a graph which has an isolated node
graph = DictGraph()
graph.setVertex(5, 1)
graph.addEdge(0, 1, 1)
graph.addEdge(1, 2, 1)
graph.addEdge(1, 3, 1)
self.assertTrue((graph.dijkstrasAlgorithm(0) == numpy.array([0, 1, 2, 2, numpy.inf])).all())
#Test a graph in a ring
graph = DictGraph()
graph.addEdge(0, 1, 1)
graph.addEdge(1, 2, 1)
graph.addEdge(2, 3, 1)
graph.addEdge(3, 4, 1)
graph.addEdge(4, 0, 1)
self.assertTrue((graph.dijkstrasAlgorithm(0) == numpy.array([0, 1, 2, 2, 1])).all())
#Try case in which vertex ids are not numbers
graph = DictGraph()
graph.addEdge("a", "b", 1)
graph.addEdge("b", "c", 1)
graph.addEdge("b", "d", 1)
graph.addEdge("c", "e", 1)
inds = Util.argsort(graph.getAllVertexIds())
self.assertTrue((graph.dijkstrasAlgorithm("a")[inds] == numpy.array([0, 1, 2, 2, 3])).all())
self.assertTrue((graph.dijkstrasAlgorithm("b")[inds] == numpy.array([1, 0, 1, 1, 2])).all())
self.assertTrue((graph.dijkstrasAlgorithm("c")[inds] == numpy.array([2, 1, 0, 2, 1])).all())
self.assertTrue((graph.dijkstrasAlgorithm("d")[inds] == numpy.array([2, 1, 2, 0, 3])).all())
self.assertTrue((graph.dijkstrasAlgorithm("e")[inds] == numpy.array([3, 2, 1, 3, 0])).all())
def testDegreeSequence(self):
graph = DictGraph()
graph.setVertex("a", 10)
graph["b", "c"] = 1
graph["b", "d"] = 1
graph["d", "e"] = 1
graph["e", "e"] = 1
degreeDict = {}
degreeDict2 = {"a": 0, "b": 2, "c": 1, "d": 2, "e": 3}
for i, id in enumerate(graph.getAllVertexIds()):
degreeDict[id] = graph.degreeSequence()[i]
self.assertEquals(degreeDict, degreeDict2)
def testAdjacencyList(self):
graph = DictGraph()
graph.addEdge("a", "b", 1)
graph.addEdge("b", "c", 1)
graph.addEdge("b", "d", 1)
graph.addEdge("c", "e", 1)
graph.setVertex("f", 1)
neighbourIndices, neighbourWeights = graph.adjacencyList()
vertexIds = graph.getAllVertexIds()
for i in range(len(neighbourIndices)):
for k, j in enumerate(neighbourIndices[i]):
self.assertTrue(graph.edgeExists(vertexIds[i], vertexIds[j]))
self.assertEquals(graph[vertexIds[i], vertexIds[j]], neighbourWeights[i][k])
def testGetSparseWeightMatrix(self):
graph = DictGraph()
graph.addEdge("a", "b")
graph.addEdge("a", "c")
graph.addEdge("a", "d", "blah")
graph.addEdge("d", "e", -1.1)
graph.addEdge("c", "b", 2)
W = graph.getSparseWeightMatrix()
keys = graph.getAllVertexIds()
for i in range(len(keys)):
for j in range(len(keys)):
if graph.edgeExists(keys[i], keys[j]) and not isinstance(graph.getEdge(keys[i], keys[j]), numbers.Number):
self.assertEquals(1, W[i, j])
elif W[i, j] != 0:
self.assertEquals(graph.getEdge(keys[i], keys[j]), W[i, j])
else:
self.assertEquals(graph.getEdge(keys[i], keys[j]), None)
#Try a directed graph
graph = DictGraph(False)
graph.addEdge("a", "b")
graph.addEdge("a", "c", "test")
graph.addEdge("a", "d")
graph.addEdge("d", "e")
graph.addEdge("c", "a", 0.1)
W = graph.getSparseWeightMatrix()
for i in range(len(keys)):
for j in range(len(keys)):
if graph.edgeExists(keys[i], keys[j]) and not isinstance(graph.getEdge(keys[i], keys[j]), numbers.Number):
self.assertEquals(1, W[i, j])
elif W[i, j] != 0:
self.assertEquals(graph.getEdge(keys[i], keys[j]), W[i, j])
else:
self.assertEquals(graph.getEdge(keys[i], keys[j]), None)
def __init__(self, minGraphSize=500, maxGraphSize=None, dayStep=30):
dataDir = PathDefaults.getDataDir() + "cluster/"
edgesFilename = dataDir + "Cit-HepTh.txt"
dateFilename = dataDir + "Cit-HepTh-dates.txt"
#Note the IDs are integers but can start with zero so we prefix "1" to each ID
edges = []
file = open(edgesFilename, 'r')
file.readline()
file.readline()
file.readline()
file.readline()
for line in file:
(vertex1, sep, vertex2) = line.partition("\t")
vertex1 = vertex1.strip()
vertex2 = vertex2.strip()
edges.append([vertex1, vertex2])
#if vertex1 == vertex2:
# print(vertex1)
file.close()
logging.info("Loaded edge file " + str(edgesFilename) + " with " + str(len(edges)) + " edges")
#Keep an edge graph
graph = DictGraph(False)
graph.addEdges(edges)
logging.info("Created directed citation graph with " + str(graph.getNumEdges()) + " edges and " + str(graph.getNumVertices()) + " vertices")
#Read in the dates articles appear in a dict which used the year and month
#as the key and the value is a list of vertex ids. For each month we include
#all papers uploaded that month and those directed cited by those uploads.
startDate = datetime.date(1990, 1, 1)
file = open(dateFilename, 'r')
file.readline()
numLines = 0
subgraphIds = []
for line in file:
(id, sep, date) = line.partition("\t")
id = id.strip()
date = date.strip()
inputDate = datetime.datetime.strptime(date.strip(), "%Y-%m-%d")
inputDate = inputDate.date()
if graph.vertexExists(id):
tDelta = inputDate - startDate
graph.vertices[id] = tDelta.days
subgraphIds.append(id)
#If a paper cites another, it must have been written before
#the citing paper - enforce this rule.
for neighbour in graph.neighbours(id):
if graph.getVertex(neighbour) == None:
graph.setVertex(neighbour, tDelta.days)
subgraphIds.append(neighbour)
elif tDelta.days < graph.getVertex(neighbour):
graph.setVertex(neighbour, tDelta.days)
numLines += 1
file.close()
subgraphIds = set(subgraphIds)
graph = graph.subgraph(list(subgraphIds))
logging.debug(graph)
logging.info("Loaded date file " + str(dateFilename) + " with " + str(len(subgraphIds)) + " dates and " + str(numLines) + " lines")
W = graph.getSparseWeightMatrix()
W = W + W.T
vList = VertexList(W.shape[0], 1)
vList.setVertices(numpy.array([graph.getVertices(graph.getAllVertexIds())]).T)
#Note: we have 16 self edges and some two-way citations so this graph has fewer edges than the directed one
self.graph = SparseGraph(vList, W=W)
logging.debug(self.graph)
#Now pick the max component
components = self.graph.findConnectedComponents()
self.graph = self.graph.subgraph(components[0])
logging.debug("Largest component graph: " + str(self.graph))
self.minGraphSize = minGraphSize
self.maxGraphSize = maxGraphSize
self.dayStep = dayStep
def testGetIterator(self):
generator = CitationIterGenerator()
iterator = generator.getIterator()
lastW = iterator.next()
for W in iterator:
self.assertTrue((W-W.T).getnnz() == 0)
self.assertTrue((lastW - W[0:lastW.shape[0], 0:lastW.shape[0]]).getnnz() ==0 )
lastW = W
numVertices = W.shape[0]
#Now compute the vertexIds manually:
dataDir = PathDefaults.getDataDir() + "cluster/"
edgesFilename = dataDir + "Cit-HepTh.txt"
dateFilename = dataDir + "Cit-HepTh-dates.txt"
#We can't load in numbers using numpy since some may start with zero
edges = []
file = open(edgesFilename, 'r')
file.readline()
file.readline()
file.readline()
file.readline()
for line in file:
(vertex1, sep, vertex2) = line.partition("\t")
vertex1 = vertex1.strip()
vertex2 = vertex2.strip()
edges.append([int("1" + vertex1), int("1" + vertex2)])
edges = numpy.array(edges, numpy.int)
#Check file read correctly
self.assertTrue((edges[0, :] == numpy.array([11001, 19304045])).all())
self.assertTrue((edges[1, :] == numpy.array([11001, 19308122])).all())
self.assertTrue((edges[9, :] == numpy.array([11001, 19503124])).all())
vertexIds1 = numpy.unique(edges)
logging.info("Number of graph vertices: " + str(vertexIds1.shape[0]))
file = open(dateFilename, 'r')
file.readline()
vertexIds2 = []
for line in file:
(id, sep, date) = line.partition("\t")
id = id.strip()
date = date.strip()
vertexIds2.append(int("1" + id))
#Check file read correctly
vertexIds2 = numpy.array(vertexIds2, numpy.int)
self.assertTrue((vertexIds2[0:10] == numpy.array([19203201, 19203202, 19203203, 19203204, 19203205, 19203206, 19203207, 19203208, 19203209, 19203210], numpy.int)).all())
vertexIds2 = numpy.unique(numpy.array(vertexIds2, numpy.int))
graph = DictGraph(False)
graph.addEdges(edges)
#Find the set of vertices with known citation
vertices = []
vertexId2Set = set(vertexIds2.tolist())
for i in graph.getAllVertexIds():
Util.printIteration(i, 50000, edges.shape[0])
if i in vertexId2Set:
vertices.append(i)
vertices.extend(graph.neighbours(i))
logging.debug("Number of final vertices: " + str(numVertices))
numVertices2 = numpy.unique(numpy.array(vertices)).shape[0]
self.assertEquals(numVertices, numVertices2)
#Now compare the weight matrices using the undirected graph
#Note the order of vertices is different from the iterator
graph = DictGraph()
graph.addEdges(edges)
subgraph = graph.subgraph(numpy.unique(numpy.array(vertices)))
W2 = subgraph.getSparseWeightMatrix()
self.assertEquals(W.getnnz(), W2.getnnz())