def toDictGraph(self):
"""
Convert to a DictGraph object. Currently ignores vertex labels.
:return graph: A DictGraph object.
"""
edges = self.getAllEdges()
values = self.getEdgeValues(edges)
graph = DictGraph(self.undirected)
graph.addEdges(edges, values)
return graph
def testAddEdges(self):
graph = DictGraph()
edgeList = [(1, 2), (2, 1), (5, 2), (8, 8)]
graph.addEdges(edgeList)
self.assertEquals(graph.getNumEdges(), 3)
self.assertEquals(graph.getEdge(1, 2), 1)
self.assertEquals(graph.getEdge(5, 2), 1)
self.assertEquals(graph.getEdge(2, 1), 1)
self.assertEquals(graph.getEdge(8, 8), 1)
edgeValues = [1, 2, 3, 4]
graph.addEdges(edgeList, edgeValues)
self.assertEquals(graph.getEdge(1, 2), 2)
self.assertEquals(graph.getEdge(5, 2), 3)
self.assertEquals(graph.getEdge(2, 1), 2)
self.assertEquals(graph.getEdge(8, 8), 4)
#Now test directed graphs
graph = DictGraph(False)
graph.addEdges(edgeList)
self.assertEquals(graph.getNumEdges(), 4)
self.assertEquals(graph.getEdge(1, 2), 1)
self.assertEquals(graph.getEdge(5, 2), 1)
self.assertEquals(graph.getEdge(2, 1), 1)
self.assertEquals(graph.getEdge(8, 8), 1)
edgeValues = [1, 2, 3, 4]
graph.addEdges(edgeList, edgeValues)
self.assertEquals(graph.getEdge(1, 2), 1)
self.assertEquals(graph.getEdge(5, 2), 3)
self.assertEquals(graph.getEdge(2, 1), 2)
self.assertEquals(graph.getEdge(8, 8), 4)
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())
