def cvModelSelection(self, graph, paramList, paramFunc, folds, errorFunc):
"""
ParamList is a list of lists of parameters and paramFunc
is a list of the corresponding functions to call with the parameters
as arguments. Note that a parameter can also be a tuple which is expanded
out before the function is called.
e.g.
paramList = [[1, 2], [2, 1], [12, 1]]
paramFunc = [predictor.setC, predictor.setD]
"""
inds = Sampling.crossValidation(folds, graph.getNumEdges())
errors = numpy.zeros((len(paramList), folds))
allEdges = graph.getAllEdges()
for i in range(len(paramList)):
paramSet = paramList[i]
logging.debug("Using paramSet=" + str(paramSet))
for j in range(len(paramSet)):
if type(paramSet[j]) == tuple:
paramFunc[j](*paramSet[j])
else:
paramFunc[j](paramSet[j])
predY = numpy.zeros(0)
y = numpy.zeros(0)
j = 0
for (trainInds, testInds) in inds:
trainEdges = allEdges[trainInds, :]
testEdges = allEdges[testInds, :]
trainGraph = SparseGraph(graph.getVertexList(),
graph.isUndirected())
trainGraph.addEdges(trainEdges,
graph.getEdgeValues(trainEdges))
testGraph = SparseGraph(graph.getVertexList(),
graph.isUndirected())
testGraph.addEdges(testEdges, graph.getEdgeValues(testEdges))
self.learnModel(trainGraph)
predY = self.predictEdges(testGraph, testGraph.getAllEdges())
y = testGraph.getEdgeValues(testGraph.getAllEdges())
#Note that the order the edges is different in testGraphs as
#opposed to graph when calling getAllEdges()
errors[i, j] = errorFunc(y, predY)
j = j + 1
logging.info("Error of current fold: " +
str(numpy.mean(errors[i, :])))
meanErrors = numpy.mean(errors, 1)
strErrors = numpy.std(errors, 1)
return meanErrors, strErrors
def cvModelSelection(self, graph, paramList, paramFunc, folds, errorFunc):
"""
ParamList is a list of lists of parameters and paramFunc
is a list of the corresponding functions to call with the parameters
as arguments. Note that a parameter can also be a tuple which is expanded
out before the function is called.
e.g.
paramList = [[1, 2], [2, 1], [12, 1]]
paramFunc = [predictor.setC, predictor.setD]
"""
inds = Sampling.crossValidation(folds, graph.getNumEdges())
errors = numpy.zeros((len(paramList), folds))
allEdges = graph.getAllEdges()
for i in range(len(paramList)):
paramSet = paramList[i]
logging.debug("Using paramSet=" + str(paramSet))
for j in range(len(paramSet)):
if type(paramSet[j]) == tuple:
paramFunc[j](*paramSet[j])
else:
paramFunc[j](paramSet[j])
predY = numpy.zeros(0)
y = numpy.zeros(0)
j = 0
for (trainInds, testInds) in inds:
trainEdges = allEdges[trainInds, :]
testEdges = allEdges[testInds, :]
trainGraph = SparseGraph(graph.getVertexList(), graph.isUndirected())
trainGraph.addEdges(trainEdges, graph.getEdgeValues(trainEdges))
testGraph = SparseGraph(graph.getVertexList(), graph.isUndirected())
testGraph.addEdges(testEdges, graph.getEdgeValues(testEdges))
self.learnModel(trainGraph)
predY = self.predictEdges(testGraph, testGraph.getAllEdges())
y = testGraph.getEdgeValues(testGraph.getAllEdges())
#Note that the order the edges is different in testGraphs as
#opposed to graph when calling getAllEdges()
errors[i, j] = errorFunc(y, predY)
j = j+1
logging.info("Error of current fold: " + str(numpy.mean(errors[i, :])))
meanErrors = numpy.mean(errors, 1)
strErrors = numpy.std(errors, 1)
return meanErrors, strErrors
def findInfoDecayGraph(self, egoTestFileName, alterTestFileName, egoIndicesR, alterIndices, egoIndicesNR, alterIndicesNR, egoFileName, alterFileName, missing=0):
(egoTestArray, egoTitles) = self.readFile(egoTestFileName, self.egoTestIds, missing=0)
(alterTestArray, alterTitles) = self.readFile(alterTestFileName, self.alterTestIds, missing=0)
egoMarks = numpy.zeros(egoTestArray.shape[0])
alterMarks = numpy.zeros(alterTestArray.shape[0])
decays = numpy.zeros(egoIndicesR.shape[0])
correctAnswers = numpy.array([1,2,4,5,8,9,10,12])
wrongAnswers = numpy.array([3, 6, 7, 11])
for i in range(egoTestArray.shape[0]):
egoMarks[i] = numpy.intersect1d(egoTestArray[i], correctAnswers).shape[0]
egoMarks[i] += wrongAnswers.shape[0] - numpy.intersect1d(egoTestArray[i], wrongAnswers).shape[0]
for i in range(alterMarks.shape[0]):
alterMarks[i] = numpy.intersect1d(alterTestArray[i], correctAnswers).shape[0]
alterMarks[i] += wrongAnswers.shape[0] - numpy.intersect1d(alterTestArray[i], wrongAnswers).shape[0]
"""
We just return how much the alter understood, since this represents the
decay in understanding of the ego and transmission.
"""
for i in range(decays.shape[0]):
decays[i] = alterMarks[alterIndices[i]]
#A lot of people could not be bothered to fill the questions and hence
#get 4 correct by default
decays = (decays) / float(self.numTestQuestions)
defaultDecay = 10**-6
#Finally, put the data into a graph
(egoArray, egoTitles) = self.readFile(egoFileName, self.egoQuestionIds, missing)
(alterArray, alterTitles) = self.readFile(alterFileName, self.alterQuestionIds, missing)
V = egoArray
V = numpy.r_[V, alterArray[alterIndices, :]]
V = numpy.r_[V, egoArray[alterIndicesNR, :]]
vList = VertexList(V.shape[0], V.shape[1])
vList.setVertices(V)
graph = SparseGraph(vList, False)
edgesR = numpy.c_[egoIndicesR, egoArray.shape[0]+numpy.arange(alterIndices.shape[0])]
graph.addEdges(edgesR, decays)
edgesNR = numpy.c_[egoIndicesNR, egoArray.shape[0]+alterIndices.shape[0]+numpy.arange(alterIndicesNR.shape[0])]
graph.addEdges(edgesNR, numpy.ones(edgesNR.shape[0]) * defaultDecay)
return graph
def cvModelSelection(self, graph, paramList, paramFunc, folds):
"""
ParamList is a list of lists of parameters and paramFunc
is a list of the corresponding functions to call with the parameters
as arguments.
e.g.
paramList = [[1, 2], [2, 1], [12, 1]]
paramFunc = [predictor.setC, predictor.setD]
"""
inds = Sampling.crossValidation(folds, graph.getNumEdges())
errors = numpy.zeros(len(paramList))
allEdges = graph.getAllEdges()
numTestExamples = 0
for i in range(len(paramList)):
paramSet = paramList[i]
logging.debug("Using paramSet=" + str(paramSet))
for j in range(len(paramSet)):
paramFunc[j](paramSet[j])
for (trainInds, testInds) in inds:
trainEdges = allEdges[trainInds, :]
testEdges = allEdges[testInds, :]
trainGraph = SparseGraph(graph.getVertexList())
trainGraph.addEdges(trainEdges)
self.learnModel(trainGraph)
P, S = self.predictEdges(testEdges[:, 0])
for k in range(testEdges.shape[0]):
if not testEdges[k, 1] in P[k, :]:
errors[i] += 1.0
numTestExamples += testEdges.shape[0]
return errors / numTestExamples
Data: December, 2016 function: """ import numpy from apgl.graph.VertexList import VertexList from apgl.graph.SparseGraph import SparseGraph numVertex = 5 numFeature = 2 # vector labels of size 2 graph = SparseGraph(VertexList(numVertex, numFeature)) # Add some edges to the graph(method 1) # Vertices are indexed starting from 0 # graph[0, 1] = 0.1 # graph[1, 2] = 1 # Add some edges to the graph(method 2 is identity to method 1) edges = numpy.array([[0, 1], [1, 2]], numpy.int) edgeValues = numpy.array([0.1, 1]) graph.addEdges(edges, edgeValues) # Set the label of 0th vertex to [2, 3] graph.setVertex(0, numpy.array([2, 3])) # Displays edge weights print(graph[1, 2]) print(graph[1, 3])
class GraphMatchTest(unittest.TestCase):
def setUp(self):
numpy.set_printoptions(suppress=True, precision=3)
numpy.random.seed(21)
numpy.set_printoptions(threshold=numpy.nan, linewidth=100)
#Use the example in the document
self.numVertices = 10
self.numFeatures = 2
self.graph1 = SparseGraph(VertexList(self.numVertices, self.numFeatures))
self.graph1.setVertices(range(self.numVertices), numpy.random.rand(self.numVertices, self.numFeatures))
edges = numpy.array([[0,1], [0, 2], [0,4], [0,5], [0,8], [0,9]])
self.graph1.addEdges(edges)
edges = numpy.array([[1,3], [1, 5], [1,6], [1,8], [2,9], [3,4], [3,5], [3,6], [3,7], [3,8], [3,9]])
self.graph1.addEdges(edges)
edges = numpy.array([[4,2], [4, 7], [4,9], [5,8], [6, 7]])
self.graph1.addEdges(edges)
self.graph2 = SparseGraph(VertexList(self.numVertices, self.numFeatures))
self.graph2.setVertices(range(self.numVertices), numpy.random.rand(self.numVertices, self.numFeatures))
edges = numpy.array([[0,3], [0, 4], [0,5], [0,8], [0,9], [1,2]])
self.graph2.addEdges(edges)
edges = numpy.array([[1,3], [1,5], [1, 7], [1,8], [1,9], [2,3], [2,5], [3,5], [4,5], [4,6]])
self.graph2.addEdges(edges)
edges = numpy.array([[4,9], [6, 8], [7,8], [7,9], [8, 9]])
self.graph2.addEdges(edges)
def testMatch(self):
matcher = GraphMatch(algorithm="U", alpha=0.3)
permutation, distance, time = matcher.match(self.graph1, self.graph2)
#Checked output file - seems correct
distance2 = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2, permutation)
self.assertAlmostEquals(distance[0], distance2)
#Now test case in which alpha is different
matcher = GraphMatch(algorithm="U", alpha=0.5)
permutation, distance, time = matcher.match(self.graph1, self.graph2)
distance2 = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2, permutation)
self.assertAlmostEquals(distance[0], distance2)
#Test normalised distance
alpha = 0.0
permutation, distance, time = GraphMatch(algorithm="U", alpha=alpha).match(self.graph1, self.graph2)
distance2 = GraphMatch(alpha=alpha).distance(self.graph1, self.graph2, permutation, True)
self.assertAlmostEquals(distance[1], distance2)
alpha = 1.0
permutation, distance, time = GraphMatch(algorithm="U", alpha=alpha).match(self.graph1, self.graph2)
distance2 = GraphMatch(alpha=alpha).distance(self.graph1, self.graph2, permutation, True)
self.assertAlmostEquals(distance[1], distance2, 5)
#Test empty graph
alpha = 0.0
graph1 = SparseGraph(VertexList(0, 0))
graph2 = SparseGraph(VertexList(0, 0))
permutation, distance, time = GraphMatch(algorithm="U", alpha=alpha).match(graph1, graph2)
nptst.assert_array_equal(permutation, numpy.array([], numpy.int))
self.assertEquals(distance, [0, 0, 0])
#Test where 1 graph is empty
permutation, distance, time = GraphMatch(algorithm="U", alpha=alpha).match(graph1, self.graph1)
self.assertEquals(numpy.linalg.norm(self.graph1.getWeightMatrix())**2, distance[0])
self.assertEquals(distance[1], 1)
self.assertEquals(distance[2], 1)
permutation, distance, time = GraphMatch(algorithm="U", alpha=alpha).match(self.graph1, graph1)
self.assertEquals(numpy.linalg.norm(self.graph1.getWeightMatrix())**2, distance[0])
self.assertEquals(distance[1], 1)
self.assertEquals(distance[2], 1)
alpha = 1.0
permutation, distance, time = GraphMatch(algorithm="U", alpha=alpha).match(graph1, self.graph1)
self.assertEquals(numpy.linalg.norm(self.graph1.getWeightMatrix())**2, distance[0])
V2 = self.graph1.vlist.getVertices()
V1 = numpy.zeros(V2.shape)
C = GraphMatch(algorithm="U", alpha=alpha).matrixSimilarity(V1, V2)
dist = numpy.trace(C)/numpy.linalg.norm(C)
self.assertAlmostEquals(distance[1], -dist, 4)
self.assertAlmostEquals(distance[2], -dist, 4)
permutation, distance, time = GraphMatch(algorithm="U", alpha=alpha).match(self.graph1, graph1)
self.assertEquals(numpy.linalg.norm(self.graph1.getWeightMatrix())**2, distance[0])
self.assertAlmostEquals(distance[1], -dist, 4)
self.assertAlmostEquals(distance[2], -dist, 4)
#Test one graph which is a subgraph of another
p = 0.2
k = 10
numVertices = 20
generator = SmallWorldGenerator(p, k)
graph = SparseGraph(VertexList(numVertices, 2))
graph = generator.generate(graph)
subgraphInds = numpy.random.permutation(numVertices)[0:10]
subgraph = graph.subgraph(subgraphInds)
matcher = GraphMatch(algorithm="U", alpha=0.0)
permutation, distance, time = matcher.match(graph, subgraph)
distance = matcher.distance(graph, subgraph, permutation, True, True)
self.assertTrue(distance < 1)
def testDistance(self):
permutation = numpy.arange(self.numVertices)
dist = GraphMatch(alpha=0.0).distance(self.graph1, self.graph1, permutation)
self.assertEquals(dist, 0.0)
dist = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2, permutation)
self.assertAlmostEquals(dist, 50.0)
permutation = numpy.arange(self.numVertices)
permutation[8] = 9
permutation[9] = 8
dist = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2, permutation)
self.assertAlmostEquals(dist, 54.0)
#Try graphs of unequal size
graph3 = self.graph1.subgraph(range(8))
permutation = numpy.arange(self.numVertices)
dist1 = GraphMatch(alpha=0.0).distance(self.graph1, graph3, permutation)
dist1a = GraphMatch(alpha=0.0).distance(graph3, self.graph1, permutation)
self.assertEquals(dist1, dist1a)
graph3 = self.graph1.subgraph(range(5))
dist2 = GraphMatch(alpha=0.0).distance(self.graph1, graph3, permutation)
dist2a = GraphMatch(alpha=0.0).distance(graph3, self.graph1, permutation)
self.assertEquals(dist2, dist2a)
self.assertTrue(dist1 < dist2)
#Test case where alpha!=0
alpha = 1.0
permutation = numpy.arange(self.numVertices)
distance = GraphMatch(alpha=alpha).distance(self.graph1, self.graph2, permutation, False)
C = GraphMatch(alpha=alpha).vertexSimilarities(self.graph1, self.graph2)
distance2 = -numpy.trace(C)
self.assertEquals(distance, distance2)
#Check case where we want non negativve distance even when alpha!=0
distance = GraphMatch(alpha=alpha).distance(self.graph1, self.graph2, permutation, True, True)
self.assertTrue(distance >= 0)
permutation = numpy.arange(self.numVertices)
distance = GraphMatch(alpha=alpha).distance(self.graph1, self.graph1, permutation, True, True)
self.assertEquals(distance, 0)
#Check case where both graphs are empty
graph1 = SparseGraph(VertexList(0, 0))
graph2 = SparseGraph(VertexList(0, 0))
permutation = numpy.array([], numpy.int)
distance = GraphMatch(alpha=alpha).distance(graph1, graph1, permutation, True, True)
self.assertEquals(distance, 0)
#Now, just one graph is empty
#Distance is always 1 due to normalisations
alpha = 0.0
permutation = numpy.arange(10, dtype=numpy.int)
distance = GraphMatch(alpha=alpha).distance(self.graph1, graph1, permutation, True, True)
self.assertEquals(distance, 1.0)
permutation = numpy.arange(10, dtype=numpy.int)
distance = GraphMatch(alpha=alpha).distance(self.graph2, graph1, permutation, True, True)
self.assertEquals(distance, 1.0)
#distance = GraphMatch(alpha=alpha).distance(self.graph1, graph1, permutation, False, False)
#self.assertEquals(distance, numpy.linalg.norm(self.graph1.getWeightMatrix())**2)
alpha = 0.9
matcher = GraphMatch("U", alpha=alpha)
permutation, distanceVector, time = matcher.match(self.graph2, graph1)
distance = matcher.distance(self.graph2, graph1, permutation, True, True)
self.assertEquals(distance, 1.0)
alpha = 1.0
permutation = numpy.arange(10, dtype=numpy.int)
distance = GraphMatch(alpha=alpha).distance(self.graph1, graph1, permutation, True, True)
self.assertEquals(distance, 1.0)
permutation = numpy.arange(10, dtype=numpy.int)
distance = GraphMatch(alpha=alpha).distance(self.graph2, graph1, permutation, True, True)
self.assertEquals(distance, 1.0)
alpha = 0.5
permutation = numpy.arange(10, dtype=numpy.int)
distance = GraphMatch(alpha=alpha).distance(self.graph2, graph1, permutation, True, True)
self.assertEquals(distance, 1.0)
#Test on unequal graphs and compare against distance from graphm
alpha = 0.5
matcher = GraphMatch(alpha=alpha)
permutation, distanceVector, time = matcher.match(self.graph1, self.graph2)
distance = matcher.distance(self.graph1, self.graph2, permutation, True, False)
self.assertAlmostEquals(distanceVector[1], distance, 3)
def testDistance2(self):
permutation = numpy.arange(self.numVertices)
dist = GraphMatch(alpha=0.0).distance2(self.graph1, self.graph1, permutation)
self.assertEquals(dist, 0.0)
dist = GraphMatch(alpha=0.0).distance2(self.graph1, self.graph2, permutation)
dist2 = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2, permutation, True)
self.assertAlmostEquals(dist, dist2)
permutation = numpy.arange(self.numVertices)
permutation[8] = 9
permutation[9] = 8
dist = GraphMatch(alpha=0.0).distance2(self.graph1, self.graph2, permutation)
dist2 = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2, permutation, True)
self.assertAlmostEquals(dist, dist2)
#Try graphs of unequal size
graph3 = self.graph1.subgraph(range(8))
permutation = numpy.arange(self.numVertices)
dist1 = GraphMatch(alpha=0.0).distance2(self.graph1, graph3, permutation)
dist1a = GraphMatch(alpha=0.0).distance2(graph3, self.graph1, permutation)
self.assertEquals(dist1, dist1a)
graph3 = self.graph1.subgraph(range(5))
dist2 = GraphMatch(alpha=0.0).distance2(self.graph1, graph3, permutation)
dist2a = GraphMatch(alpha=0.0).distance2(graph3, self.graph1, permutation)
self.assertEquals(dist2, dist2a)
self.assertTrue(dist1 < dist2)
#Test case where alpha!=0
alpha = 1.0
permutation = numpy.arange(self.numVertices)
distance = GraphMatch(alpha=alpha).distance2(self.graph1, self.graph1, permutation)
self.assertEquals(distance, 0.0)
#Check distances are between 0 and 1
for i in range(100):
alpha = numpy.random.rand()
permutation = numpy.random.permutation(self.numVertices)
distance = GraphMatch(alpha=alpha).distance2(self.graph1, self.graph1, permutation)
self.assertTrue(0<=distance<=1)
def testVertexSimilarities(self):
matcher = GraphMatch(alpha=0.0)
C = matcher.vertexSimilarities(self.graph1, self.graph1)
Cdiag = numpy.diag(C)
nptst.assert_array_almost_equal(Cdiag, numpy.ones(Cdiag.shape[0]))
#Now compute trace(C)/||C||
#print(numpy.trace(C)/numpy.linalg.norm(C))
#Test use of feature inds
matcher = GraphMatch(alpha=0.0, featureInds=numpy.array([0]))
C = matcher.vertexSimilarities(self.graph1, self.graph2)
#Now, let's vary the non-used feature
self.graph1.vlist[:, 1] = 0
C2 = matcher.vertexSimilarities(self.graph1, self.graph2)
nptst.assert_array_equal(C, C2)
self.graph2.vlist[:, 1] = 0
C2 = matcher.vertexSimilarities(self.graph1, self.graph2)
nptst.assert_array_equal(C, C2)
#Vary used feature
self.graph1.vlist[:, 0] = 0
C2 = matcher.vertexSimilarities(self.graph1, self.graph2)
self.assertTrue((C != C2).any())
def testMatrixSimilarity(self):
numExamples = 5
numFeatures = 3
V1 = numpy.random.rand(numExamples, numFeatures)
matcher = GraphMatch(alpha=0.0)
C = matcher.matrixSimilarity(V1, V1)
Cdiag = numpy.diag(C)
nptst.assert_array_almost_equal(Cdiag, numpy.ones(Cdiag.shape[0]))
V1[:, 2] *= 10
C2 = matcher.matrixSimilarity(V1, V1)
Cdiag = numpy.diag(C2)
nptst.assert_array_almost_equal(Cdiag, numpy.ones(Cdiag.shape[0]))
nptst.assert_array_almost_equal(C, C2)
#print("Running match")
J = numpy.ones((numExamples, numFeatures))
Z = numpy.zeros((numExamples, numFeatures))
C2 = matcher.matrixSimilarity(J, Z)
#This should be 1 ideally
nptst.assert_array_almost_equal(C2, numpy.ones(C2.shape))
C2 = matcher.matrixSimilarity(J, J)
nptst.assert_array_almost_equal(C2, numpy.ones(C2.shape))
"""
Name: Generate Graph:
Author: Jia_qiu Wang(王佳秋)
Data: December, 2016
function:
"""
from apgl.graph.DictGraph import DictGraph
from apgl.graph.SparseGraph import SparseGraph
from apgl.graph.GeneralVertexList import GeneralVertexList
graph = DictGraph()
graph.addEdge("a", "b")
graph.addEdge("a", "c")
graph.addEdge("a", "d")
edgeIndices = graph.getAllEdgeIndices()
graph2 = SparseGraph(GeneralVertexList(graph.getNumVertices()))
graph2.addEdges(edgeIndices)
# -*- coding: utf-8 -*-
from apgl.graph.DictGraph import DictGraph
from apgl.graph.SparseGraph import SparseGraph
from apgl.graph.GeneralVertexList import GeneralVertexList
graph = DictGraph()
graph.addEdge("a", "b")
graph.addEdge("a", "c")
graph.addEdge("a", "d")
edgeIndices = graph.getAllEdgeIndices()
graph2 = SparseGraph(GeneralVertexList(graph.getNumVertices()))
graph2.addEdges(edgeIndices)
#!/usr/bin/env python import numpy as np from apgl.graph.VertexList import VertexList from apgl.graph.SparseGraph import SparseGraph numVertices = 5 numFeatures = 2 graph = SparseGraph(VertexList(numVertices, numFeatures)) # Add some edges to the graph. # Vertices are indexed starting from 0. graph[0, 1] = 0.1 graph[1, 2] = 1.0 # Set the label of the 0th vertex to [2, 3]. graph.setVertex(0, np.array([2, 3])) # Display edge weights. print(graph[1, 2]) # 1.0 print(graph[1, 3]) # 0.0 (default) # Add some edges to the graph. edges = np.array([[0, 1], [1, 2]], np.int) edgeValues = np.array([0.1, 1.0]) graph.addEdges(edges, edgeValues) # Display the edge weight between v1 and v2. print(graph[1, 2])
class GraphMatchTest(unittest.TestCase):
def setUp(self):
numpy.set_printoptions(suppress=True, precision=3)
numpy.random.seed(21)
numpy.set_printoptions(threshold=numpy.nan, linewidth=100)
#Use the example in the document
self.numVertices = 10
self.numFeatures = 2
self.graph1 = SparseGraph(
VertexList(self.numVertices, self.numFeatures))
self.graph1.setVertices(
range(self.numVertices),
numpy.random.rand(self.numVertices, self.numFeatures))
edges = numpy.array([[0, 1], [0, 2], [0, 4], [0, 5], [0, 8], [0, 9]])
self.graph1.addEdges(edges)
edges = numpy.array([[1, 3], [1, 5], [1, 6], [1, 8], [2, 9], [3, 4],
[3, 5], [3, 6], [3, 7], [3, 8], [3, 9]])
self.graph1.addEdges(edges)
edges = numpy.array([[4, 2], [4, 7], [4, 9], [5, 8], [6, 7]])
self.graph1.addEdges(edges)
self.graph2 = SparseGraph(
VertexList(self.numVertices, self.numFeatures))
self.graph2.setVertices(
range(self.numVertices),
numpy.random.rand(self.numVertices, self.numFeatures))
edges = numpy.array([[0, 3], [0, 4], [0, 5], [0, 8], [0, 9], [1, 2]])
self.graph2.addEdges(edges)
edges = numpy.array([[1, 3], [1, 5], [1, 7], [1, 8], [1, 9], [2, 3],
[2, 5], [3, 5], [4, 5], [4, 6]])
self.graph2.addEdges(edges)
edges = numpy.array([[4, 9], [6, 8], [7, 8], [7, 9], [8, 9]])
self.graph2.addEdges(edges)
def testMatch(self):
matcher = GraphMatch(algorithm="U", alpha=0.3)
permutation, distance, time = matcher.match(self.graph1, self.graph2)
#Checked output file - seems correct
distance2 = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2,
permutation)
self.assertAlmostEquals(distance[0], distance2)
#Now test case in which alpha is different
matcher = GraphMatch(algorithm="U", alpha=0.5)
permutation, distance, time = matcher.match(self.graph1, self.graph2)
distance2 = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2,
permutation)
self.assertAlmostEquals(distance[0], distance2)
#Test normalised distance
alpha = 0.0
permutation, distance, time = GraphMatch(algorithm="U",
alpha=alpha).match(
self.graph1, self.graph2)
distance2 = GraphMatch(alpha=alpha).distance(self.graph1, self.graph2,
permutation, True)
self.assertAlmostEquals(distance[1], distance2)
alpha = 1.0
permutation, distance, time = GraphMatch(algorithm="U",
alpha=alpha).match(
self.graph1, self.graph2)
distance2 = GraphMatch(alpha=alpha).distance(self.graph1, self.graph2,
permutation, True)
self.assertAlmostEquals(distance[1], distance2, 5)
#Test empty graph
alpha = 0.0
graph1 = SparseGraph(VertexList(0, 0))
graph2 = SparseGraph(VertexList(0, 0))
permutation, distance, time = GraphMatch(algorithm="U",
alpha=alpha).match(
graph1, graph2)
nptst.assert_array_equal(permutation, numpy.array([], numpy.int))
self.assertEquals(distance, [0, 0, 0])
#Test where 1 graph is empty
permutation, distance, time = GraphMatch(algorithm="U",
alpha=alpha).match(
graph1, self.graph1)
self.assertEquals(
numpy.linalg.norm(self.graph1.getWeightMatrix())**2, distance[0])
self.assertEquals(distance[1], 1)
self.assertEquals(distance[2], 1)
permutation, distance, time = GraphMatch(algorithm="U",
alpha=alpha).match(
self.graph1, graph1)
self.assertEquals(
numpy.linalg.norm(self.graph1.getWeightMatrix())**2, distance[0])
self.assertEquals(distance[1], 1)
self.assertEquals(distance[2], 1)
alpha = 1.0
permutation, distance, time = GraphMatch(algorithm="U",
alpha=alpha).match(
graph1, self.graph1)
self.assertEquals(
numpy.linalg.norm(self.graph1.getWeightMatrix())**2, distance[0])
V2 = self.graph1.vlist.getVertices()
V1 = numpy.zeros(V2.shape)
C = GraphMatch(algorithm="U", alpha=alpha).matrixSimilarity(V1, V2)
dist = numpy.trace(C) / numpy.linalg.norm(C)
self.assertAlmostEquals(distance[1], -dist, 4)
self.assertAlmostEquals(distance[2], -dist, 4)
permutation, distance, time = GraphMatch(algorithm="U",
alpha=alpha).match(
self.graph1, graph1)
self.assertEquals(
numpy.linalg.norm(self.graph1.getWeightMatrix())**2, distance[0])
self.assertAlmostEquals(distance[1], -dist, 4)
self.assertAlmostEquals(distance[2], -dist, 4)
#Test one graph which is a subgraph of another
p = 0.2
k = 10
numVertices = 20
generator = SmallWorldGenerator(p, k)
graph = SparseGraph(VertexList(numVertices, 2))
graph = generator.generate(graph)
subgraphInds = numpy.random.permutation(numVertices)[0:10]
subgraph = graph.subgraph(subgraphInds)
matcher = GraphMatch(algorithm="U", alpha=0.0)
permutation, distance, time = matcher.match(graph, subgraph)
distance = matcher.distance(graph, subgraph, permutation, True, True)
self.assertTrue(distance < 1)
def testDistance(self):
permutation = numpy.arange(self.numVertices)
dist = GraphMatch(alpha=0.0).distance(self.graph1, self.graph1,
permutation)
self.assertEquals(dist, 0.0)
dist = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2,
permutation)
self.assertAlmostEquals(dist, 50.0)
permutation = numpy.arange(self.numVertices)
permutation[8] = 9
permutation[9] = 8
dist = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2,
permutation)
self.assertAlmostEquals(dist, 54.0)
#Try graphs of unequal size
graph3 = self.graph1.subgraph(range(8))
permutation = numpy.arange(self.numVertices)
dist1 = GraphMatch(alpha=0.0).distance(self.graph1, graph3,
permutation)
dist1a = GraphMatch(alpha=0.0).distance(graph3, self.graph1,
permutation)
self.assertEquals(dist1, dist1a)
graph3 = self.graph1.subgraph(range(5))
dist2 = GraphMatch(alpha=0.0).distance(self.graph1, graph3,
permutation)
dist2a = GraphMatch(alpha=0.0).distance(graph3, self.graph1,
permutation)
self.assertEquals(dist2, dist2a)
self.assertTrue(dist1 < dist2)
#Test case where alpha!=0
alpha = 1.0
permutation = numpy.arange(self.numVertices)
distance = GraphMatch(alpha=alpha).distance(self.graph1, self.graph2,
permutation, False)
C = GraphMatch(alpha=alpha).vertexSimilarities(self.graph1,
self.graph2)
distance2 = -numpy.trace(C)
self.assertEquals(distance, distance2)
#Check case where we want non negativve distance even when alpha!=0
distance = GraphMatch(alpha=alpha).distance(self.graph1, self.graph2,
permutation, True, True)
self.assertTrue(distance >= 0)
permutation = numpy.arange(self.numVertices)
distance = GraphMatch(alpha=alpha).distance(self.graph1, self.graph1,
permutation, True, True)
self.assertEquals(distance, 0)
#Check case where both graphs are empty
graph1 = SparseGraph(VertexList(0, 0))
graph2 = SparseGraph(VertexList(0, 0))
permutation = numpy.array([], numpy.int)
distance = GraphMatch(alpha=alpha).distance(graph1, graph1,
permutation, True, True)
self.assertEquals(distance, 0)
#Now, just one graph is empty
#Distance is always 1 due to normalisations
alpha = 0.0
permutation = numpy.arange(10, dtype=numpy.int)
distance = GraphMatch(alpha=alpha).distance(self.graph1, graph1,
permutation, True, True)
self.assertEquals(distance, 1.0)
permutation = numpy.arange(10, dtype=numpy.int)
distance = GraphMatch(alpha=alpha).distance(self.graph2, graph1,
permutation, True, True)
self.assertEquals(distance, 1.0)
#distance = GraphMatch(alpha=alpha).distance(self.graph1, graph1, permutation, False, False)
#self.assertEquals(distance, numpy.linalg.norm(self.graph1.getWeightMatrix())**2)
alpha = 0.9
matcher = GraphMatch("U", alpha=alpha)
permutation, distanceVector, time = matcher.match(self.graph2, graph1)
distance = matcher.distance(self.graph2, graph1, permutation, True,
True)
self.assertEquals(distance, 1.0)
alpha = 1.0
permutation = numpy.arange(10, dtype=numpy.int)
distance = GraphMatch(alpha=alpha).distance(self.graph1, graph1,
permutation, True, True)
self.assertEquals(distance, 1.0)
permutation = numpy.arange(10, dtype=numpy.int)
distance = GraphMatch(alpha=alpha).distance(self.graph2, graph1,
permutation, True, True)
self.assertEquals(distance, 1.0)
alpha = 0.5
permutation = numpy.arange(10, dtype=numpy.int)
distance = GraphMatch(alpha=alpha).distance(self.graph2, graph1,
permutation, True, True)
self.assertEquals(distance, 1.0)
#Test on unequal graphs and compare against distance from graphm
alpha = 0.5
matcher = GraphMatch(alpha=alpha)
permutation, distanceVector, time = matcher.match(
self.graph1, self.graph2)
distance = matcher.distance(self.graph1, self.graph2, permutation,
True, False)
self.assertAlmostEquals(distanceVector[1], distance, 3)
def testDistance2(self):
permutation = numpy.arange(self.numVertices)
dist = GraphMatch(alpha=0.0).distance2(self.graph1, self.graph1,
permutation)
self.assertEquals(dist, 0.0)
dist = GraphMatch(alpha=0.0).distance2(self.graph1, self.graph2,
permutation)
dist2 = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2,
permutation, True)
self.assertAlmostEquals(dist, dist2)
permutation = numpy.arange(self.numVertices)
permutation[8] = 9
permutation[9] = 8
dist = GraphMatch(alpha=0.0).distance2(self.graph1, self.graph2,
permutation)
dist2 = GraphMatch(alpha=0.0).distance(self.graph1, self.graph2,
permutation, True)
self.assertAlmostEquals(dist, dist2)
#Try graphs of unequal size
graph3 = self.graph1.subgraph(range(8))
permutation = numpy.arange(self.numVertices)
dist1 = GraphMatch(alpha=0.0).distance2(self.graph1, graph3,
permutation)
dist1a = GraphMatch(alpha=0.0).distance2(graph3, self.graph1,
permutation)
self.assertEquals(dist1, dist1a)
graph3 = self.graph1.subgraph(range(5))
dist2 = GraphMatch(alpha=0.0).distance2(self.graph1, graph3,
permutation)
dist2a = GraphMatch(alpha=0.0).distance2(graph3, self.graph1,
permutation)
self.assertEquals(dist2, dist2a)
self.assertTrue(dist1 < dist2)
#Test case where alpha!=0
alpha = 1.0
permutation = numpy.arange(self.numVertices)
distance = GraphMatch(alpha=alpha).distance2(self.graph1, self.graph1,
permutation)
self.assertEquals(distance, 0.0)
#Check distances are between 0 and 1
for i in range(100):
alpha = numpy.random.rand()
permutation = numpy.random.permutation(self.numVertices)
distance = GraphMatch(alpha=alpha).distance2(
self.graph1, self.graph1, permutation)
self.assertTrue(0 <= distance <= 1)
def testVertexSimilarities(self):
matcher = GraphMatch(alpha=0.0)
C = matcher.vertexSimilarities(self.graph1, self.graph1)
Cdiag = numpy.diag(C)
nptst.assert_array_almost_equal(Cdiag, numpy.ones(Cdiag.shape[0]))
#Now compute trace(C)/||C||
#print(numpy.trace(C)/numpy.linalg.norm(C))
#Test use of feature inds
matcher = GraphMatch(alpha=0.0, featureInds=numpy.array([0]))
C = matcher.vertexSimilarities(self.graph1, self.graph2)
#Now, let's vary the non-used feature
self.graph1.vlist[:, 1] = 0
C2 = matcher.vertexSimilarities(self.graph1, self.graph2)
nptst.assert_array_equal(C, C2)
self.graph2.vlist[:, 1] = 0
C2 = matcher.vertexSimilarities(self.graph1, self.graph2)
nptst.assert_array_equal(C, C2)
#Vary used feature
self.graph1.vlist[:, 0] = 0
C2 = matcher.vertexSimilarities(self.graph1, self.graph2)
self.assertTrue((C != C2).any())
def testMatrixSimilarity(self):
numExamples = 5
numFeatures = 3
V1 = numpy.random.rand(numExamples, numFeatures)
matcher = GraphMatch(alpha=0.0)
C = matcher.matrixSimilarity(V1, V1)
Cdiag = numpy.diag(C)
nptst.assert_array_almost_equal(Cdiag, numpy.ones(Cdiag.shape[0]))
V1[:, 2] *= 10
C2 = matcher.matrixSimilarity(V1, V1)
Cdiag = numpy.diag(C2)
nptst.assert_array_almost_equal(Cdiag, numpy.ones(Cdiag.shape[0]))
nptst.assert_array_almost_equal(C, C2)
#print("Running match")
J = numpy.ones((numExamples, numFeatures))
Z = numpy.zeros((numExamples, numFeatures))
C2 = matcher.matrixSimilarity(J, Z)
#This should be 1 ideally
nptst.assert_array_almost_equal(C2, numpy.ones(C2.shape))
C2 = matcher.matrixSimilarity(J, J)
nptst.assert_array_almost_equal(C2, numpy.ones(C2.shape))
import numpy import matplotlib.pyplot as plt from apgl.data.Standardiser import Standardiser from apgl.data.FeatureGenerator import FeatureGenerator from apgl.graph.SparseGraph import SparseGraph from apgl.graph.GeneralVertexList import GeneralVertexList from sklearn.cluster import KMeans """ Test the error bound for the clustering process. """ k = 3 numVertices = 15 graph1 = SparseGraph(GeneralVertexList(numVertices)) cluster1 = numpy.array([[0,1], [0,2], [1,3], [2,3], [3,4], [4,5]]) graph1.addEdges(cluster1) cluster2 = numpy.array([[5,7], [5,8], [7,9], [8,9], [6,7]]) graph1.addEdges(cluster2) cluster3 = numpy.array([[6,10], [10,11], [10,12], [11,12], [11,13], [12,14]]) graph1.addEdges(cluster3) graph2 = SparseGraph(GeneralVertexList(numVertices)) cluster1 = numpy.array([[0,1], [0,2], [1,3], [2,3], [3,4], [0,3],[4,5]]) graph2.addEdges(cluster1) cluster2 = numpy.array([[5,7], [5,8], [7,9], [8,9], [6,7]]) graph2.addEdges(cluster2) cluster3 = numpy.array([[6,10], [10,11], [10,12], [11,12], [11,13], [12,14]]) graph2.addEdges(cluster3) L1 = graph1.normalisedLaplacianSym() L2 = graph2.normalisedLaplacianSym()
