def readGraph(self, vertexFileName, edgeFileNames, undirected=True, delimiter=None):
"""
Read a MultiGraph from at least 2 files: one is the information about
vertices and the other(s) are lists of edges. For the list of vertices
the first column must be the ID of the vertex.
"""
X = numpy.loadtxt(vertexFileName, skiprows=1, converters=self.converters, usecols=self.vertexIndices, delimiter=delimiter)
numVertices = X.shape[0]
numFeatures = X.shape[1]-1
vertexIds = X[:, 0]
vertexIdsDict = {}
for i in range(0, numVertices):
vertexIdsDict[vertexIds[i]] = i
if self.nanProcessor != None:
X[:, 1:numFeatures+1] = self.nanProcessor(X[:, 1:numFeatures+1])
vertexList = VertexList(numVertices, numFeatures)
vertexList.setVertices(X[:, 1:numFeatures+1])
maxEdgeTypes = len(edgeFileNames)
sparseMultiGraph = SparseMultiGraph(vertexList, maxEdgeTypes, undirected)
for i in range(0, maxEdgeTypes):
self.__readEdgeFile(vertexIdsDict, edgeFileNames[i], sparseMultiGraph, i)
logging.info("MultiGraph read with " + str(sparseMultiGraph.getNumVertices()) + " vertices and " + str(sparseMultiGraph.getNumEdges()) + " edges")
return sparseMultiGraph
class VertexListTest(unittest.TestCase, AbstractVertexListTest):
def setUp(self):
self.numVertices = 10
self.numFeatures = 3
self.vList = VertexList(self.numVertices, self.numFeatures)
self.emptyVertex = numpy.zeros(self.numFeatures)
self.initialise()
def testConstructor(self):
self.assertEquals(self.vList.getNumFeatures(), self.numFeatures)
self.assertEquals(self.vList.getNumVertices(), self.numVertices)
def testSaveLoad(self):
try:
vList = VertexList(self.numVertices, self.numFeatures)
vList.setVertex(0, numpy.array([1, 2, 3]))
vList.setVertex(1, numpy.array([4, 5, 6]))
vList.setVertex(2, numpy.array([7, 8, 9]))
tempDir = PathDefaults.getTempDir()
fileName = tempDir + "vList"
vList.save(fileName)
vList2 = VertexList.load(fileName)
self.assertTrue(
(vList.getVertices() == vList2.getVertices()).all())
except IOError as e:
logging.warn(e)
pass
def testGetItem2(self):
V = numpy.random.rand(self.numVertices, self.numFeatures)
self.vList.setVertices(V)
for i in range(self.numVertices):
nptst.assert_array_equal(self.vList[i, :], V[i, :])
def testSetItem2(self):
V = numpy.random.rand(self.numVertices, self.numFeatures)
for i in range(self.numVertices):
self.vList[i, :] = V[i, :]
nptst.assert_array_equal(self.vList[i, :], V[i, :])
def testAddVertices(self):
numFeatures = 5
vList = VertexList(10, numFeatures)
vList.setVertex(1, numpy.ones(numFeatures) * 0.1)
self.assertEquals(vList.getNumVertices(), 10)
nptst.assert_array_equal(vList[1], numpy.ones(numFeatures) * 0.1)
vList.addVertices(5)
self.assertEquals(vList.getNumVertices(), 15)
vList.setVertex(11, numpy.ones(numFeatures) * 2)
nptst.assert_array_equal(vList[1], numpy.ones(numFeatures) * 0.1)
nptst.assert_array_equal(vList[11], numpy.ones(numFeatures) * 2)
class VertexListTest(unittest.TestCase, AbstractVertexListTest):
def setUp(self):
self.numVertices = 10
self.numFeatures = 3
self.vList = VertexList(self.numVertices, self.numFeatures)
self.emptyVertex = numpy.zeros(self.numFeatures)
self.initialise()
def testConstructor(self):
self.assertEquals(self.vList.getNumFeatures(), self.numFeatures)
self.assertEquals(self.vList.getNumVertices(), self.numVertices)
def testSaveLoad(self):
try:
vList = VertexList(self.numVertices, self.numFeatures)
vList.setVertex(0, numpy.array([1, 2, 3]))
vList.setVertex(1, numpy.array([4, 5, 6]))
vList.setVertex(2, numpy.array([7, 8, 9]))
tempDir = PathDefaults.getTempDir()
fileName = tempDir + "vList"
vList.save(fileName)
vList2 = VertexList.load(fileName)
self.assertTrue((vList.getVertices() == vList2.getVertices()).all())
except IOError as e:
logging.warn(e)
pass
def testGetItem2(self):
V = numpy.random.rand(self.numVertices, self.numFeatures)
self.vList.setVertices(V)
for i in range(self.numVertices):
nptst.assert_array_equal(self.vList[i, :], V[i, :])
def testSetItem2(self):
V = numpy.random.rand(self.numVertices, self.numFeatures)
for i in range(self.numVertices):
self.vList[i, :] = V[i, :]
nptst.assert_array_equal(self.vList[i, :], V[i, :])
def testAddVertices(self):
numFeatures = 5
vList = VertexList(10, numFeatures)
vList.setVertex(1, numpy.ones(numFeatures)*0.1)
self.assertEquals(vList.getNumVertices(), 10)
nptst.assert_array_equal(vList[1], numpy.ones(numFeatures)*0.1)
vList.addVertices(5)
self.assertEquals(vList.getNumVertices(), 15)
vList.setVertex(11, numpy.ones(numFeatures)*2)
nptst.assert_array_equal(vList[1], numpy.ones(numFeatures)*0.1)
nptst.assert_array_equal(vList[11], numpy.ones(numFeatures)*2)
def testVertexLabelPairs(self):
numVertices = 6
numFeatures = 1
vList = VertexList(numVertices, numFeatures)
vList.setVertices(numpy.array([numpy.arange(0, 6)]).T)
graph = DenseGraph(vList, True)
graph.addEdge(0, 1, 0.1)
graph.addEdge(1, 3, 0.1)
graph.addEdge(0, 2, 0.2)
graph.addEdge(2, 3, 0.5)
graph.addEdge(0, 4, 0.1)
graph.addEdge(3, 4, 0.1)
tol = 10**-6
edges = graph.getAllEdges()
X = GraphUtils.vertexLabelPairs(graph, edges)
self.assertTrue(numpy.linalg.norm(X - edges) < tol )
X = GraphUtils.vertexLabelPairs(graph, edges[[5, 2, 1], :])
self.assertTrue(numpy.linalg.norm(X - edges[[5,2,1], :]) < tol )
#Try a bigger graph
numVertices = 6
numFeatures = 2
vList = VertexList(numVertices, numFeatures)
vList.setVertices(numpy.random.randn(numVertices, numFeatures))
graph = DenseGraph(vList, True)
graph.addEdge(0, 1, 0.1)
graph.addEdge(1, 3, 0.1)
edges = graph.getAllEdges()
X = GraphUtils.vertexLabelPairs(graph, edges)
self.assertTrue(numpy.linalg.norm(X[0, 0:numFeatures] - vList.getVertex(1)) < tol )
self.assertTrue(numpy.linalg.norm(X[0, numFeatures:numFeatures*2] - vList.getVertex(0)) < tol )
self.assertTrue(numpy.linalg.norm(X[1, 0:numFeatures] - vList.getVertex(3)) < tol )
self.assertTrue(numpy.linalg.norm(X[1, numFeatures:numFeatures*2] - vList.getVertex(1)) < tol )
#Try directed graphs
graph = DenseGraph(vList, False)
graph.addEdge(0, 1, 0.1)
graph.addEdge(1, 3, 0.1)
edges = graph.getAllEdges()
X = GraphUtils.vertexLabelPairs(graph, edges)
self.assertTrue(numpy.linalg.norm(X[0, 0:numFeatures] - vList.getVertex(0)) < tol )
self.assertTrue(numpy.linalg.norm(X[0, numFeatures:numFeatures*2] - vList.getVertex(1)) < tol )
self.assertTrue(numpy.linalg.norm(X[1, 0:numFeatures] - vList.getVertex(1)) < tol )
self.assertTrue(numpy.linalg.norm(X[1, numFeatures:numFeatures*2] - vList.getVertex(3)) < tol )
def readGraph(self,
vertexFileName,
edgeFileNames,
undirected=True,
delimiter=None):
"""
Read a MultiGraph from at least 2 files: one is the information about
vertices and the other(s) are lists of edges. For the list of vertices
the first column must be the ID of the vertex.
"""
X = numpy.loadtxt(vertexFileName,
skiprows=1,
converters=self.converters,
usecols=self.vertexIndices,
delimiter=delimiter)
numVertices = X.shape[0]
numFeatures = X.shape[1] - 1
vertexIds = X[:, 0]
vertexIdsDict = {}
for i in range(0, numVertices):
vertexIdsDict[vertexIds[i]] = i
if self.nanProcessor != None:
X[:, 1:numFeatures + 1] = self.nanProcessor(X[:,
1:numFeatures + 1])
vertexList = VertexList(numVertices, numFeatures)
vertexList.setVertices(X[:, 1:numFeatures + 1])
maxEdgeTypes = len(edgeFileNames)
sparseMultiGraph = SparseMultiGraph(vertexList, maxEdgeTypes,
undirected)
for i in range(0, maxEdgeTypes):
self.__readEdgeFile(vertexIdsDict, edgeFileNames[i],
sparseMultiGraph, i)
logging.info("MultiGraph read with " +
str(sparseMultiGraph.getNumVertices()) +
" vertices and " + str(sparseMultiGraph.getNumEdges()) +
" edges")
return sparseMultiGraph
def setUp(self):
numpy.random.seed(21)
numVertices = 10
numFeatures = 5
vList = VertexList(numVertices, numFeatures)
vList.setVertices(numpy.random.rand(numVertices, numFeatures))
graph = SparseGraph(vList, False)
graph.addEdge(0, 1, 1)
graph.addEdge(0, 2, 1)
graph.addEdge(0, 3, 1)
graph.addEdge(0, 4, -1)
graph.addEdge(0, 5, -1)
graph.addEdge(1, 2, 1)
graph.addEdge(1, 3, -1)
graph.addEdge(1, 8, 1)
graph.addEdge(2, 3, -1)
graph.addEdge(2, 4, -1)
graph.addEdge(2, 5, -1)
graph.addEdge(2, 6, 1)
self.graph = graph
def setUp(self):
numpy.random.seed(21)
numVertices = 10
numFeatures = 5
vList = VertexList(numVertices, numFeatures)
vList.setVertices(numpy.random.rand(numVertices, numFeatures))
graph = SparseGraph(vList, False)
graph.addEdge(0, 1, 1)
graph.addEdge(0, 2, 1)
graph.addEdge(0, 3, 1)
graph.addEdge(0, 4, -1)
graph.addEdge(0, 5, -1)
graph.addEdge(1, 2, 1)
graph.addEdge(1, 3, -1)
graph.addEdge(1, 8, 1)
graph.addEdge(2, 3, -1)
graph.addEdge(2, 4, -1)
graph.addEdge(2, 5, -1)
graph.addEdge(2, 6, 1)
self.graph = graph
def generateIndicatorVertices2(self, numVertices, mu, sigma, p, minVals, maxVals):
"""
Generate a set of vertices from the means and variances of Y using the multivariate
normal distribution. Also add at the end an indicator variables which is 1
with probability p. Make sure the values fall within minVals and maxVals.
"""
if numpy.linalg.norm(sigma.T - sigma) > 10**-8 :
raise ValueError("Must use symmetric sigma matrix: " + str(sigma.T - sigma))
if (minVals > maxVals).any():
raise ValueError("minVals must be less than or equal to maxVals")
logging.info("Generating " + str(numVertices) + " vertices")
n = mu.shape[0]
X = numpy.round(random.multivariate_normal(mu, sigma, numVertices)).astype(numpy.int32)
indVector = (random.rand(numVertices) < p).astype(numpy.int32)
constantValueInds = numpy.nonzero(minVals == maxVals)[0]
constantValues = minVals[constantValueInds]
blockSize = 10000
X = X[numpy.logical_and(X >= minVals, X <= maxVals).all(1), :]
while X.shape[0] < numVertices:
logging.info("Generated " + str(X.shape[0]) + " vertices so far")
XBlock = numpy.round(random.multivariate_normal(mu, sigma, blockSize)).astype(numpy.int32)
XBlock[:, constantValueInds] = constantValues
XBlock = XBlock[numpy.logical_and(XBlock >= minVals, XBlock <= maxVals).all(1), :]
X = numpy.r_[X, XBlock]
X = X[0:numVertices, :]
X = numpy.c_[X, indVector]
vList = VertexList(numVertices, n+1)
vList.setVertices(X)
return vList
def testVertexLabelPairs(self):
numVertices = 6
numFeatures = 1
vList = VertexList(numVertices, numFeatures)
vList.setVertices(numpy.array([numpy.arange(0, 6)]).T)
graph = DenseGraph(vList, True)
graph.addEdge(0, 1, 0.1)
graph.addEdge(1, 3, 0.1)
graph.addEdge(0, 2, 0.2)
graph.addEdge(2, 3, 0.5)
graph.addEdge(0, 4, 0.1)
graph.addEdge(3, 4, 0.1)
tol = 10**-6
edges = graph.getAllEdges()
X = GraphUtils.vertexLabelPairs(graph, edges)
self.assertTrue(numpy.linalg.norm(X - edges) < tol)
X = GraphUtils.vertexLabelPairs(graph, edges[[5, 2, 1], :])
self.assertTrue(numpy.linalg.norm(X - edges[[5, 2, 1], :]) < tol)
#Try a bigger graph
numVertices = 6
numFeatures = 2
vList = VertexList(numVertices, numFeatures)
vList.setVertices(numpy.random.randn(numVertices, numFeatures))
graph = DenseGraph(vList, True)
graph.addEdge(0, 1, 0.1)
graph.addEdge(1, 3, 0.1)
edges = graph.getAllEdges()
X = GraphUtils.vertexLabelPairs(graph, edges)
self.assertTrue(
numpy.linalg.norm(X[0, 0:numFeatures] - vList.getVertex(1)) < tol)
self.assertTrue(
numpy.linalg.norm(X[0, numFeatures:numFeatures * 2] -
vList.getVertex(0)) < tol)
self.assertTrue(
numpy.linalg.norm(X[1, 0:numFeatures] - vList.getVertex(3)) < tol)
self.assertTrue(
numpy.linalg.norm(X[1, numFeatures:numFeatures * 2] -
vList.getVertex(1)) < tol)
#Try directed graphs
graph = DenseGraph(vList, False)
graph.addEdge(0, 1, 0.1)
graph.addEdge(1, 3, 0.1)
edges = graph.getAllEdges()
X = GraphUtils.vertexLabelPairs(graph, edges)
self.assertTrue(
numpy.linalg.norm(X[0, 0:numFeatures] - vList.getVertex(0)) < tol)
self.assertTrue(
numpy.linalg.norm(X[0, numFeatures:numFeatures * 2] -
vList.getVertex(1)) < tol)
self.assertTrue(
numpy.linalg.norm(X[1, 0:numFeatures] - vList.getVertex(1)) < tol)
self.assertTrue(
numpy.linalg.norm(X[1, numFeatures:numFeatures * 2] -
vList.getVertex(3)) < tol)
