def saveParams(paramsFile):
"""
This method runs model selection for the SVM and saves the parameters
and errors. Only need to do this once for the data.
"""
graphFileName = InfoExperiment.getGraphFileName()
graph = SparseGraph.load(graphFileName)
logging.info("Find all ego networks")
trees = graph.findTrees()
subgraphSize = 10000
subgraphIndices = []
for i in range(len(trees)):
subgraphIndices.extend(trees[i])
if len(subgraphIndices) > subgraphSize:
logging.info("Chose " + str(i) + " ego networks.")
break
graph = graph.subgraph(subgraphIndices)
logging.info("Taking random subgraph of size " + str(graph.getNumVertices()))
folds = 3
sampleSize = graph.getNumEdges()
lambda1s = 2.0**numpy.arange(-8,-2)
lambda2s = 2.0**numpy.arange(-8,-2)
sigmas = 2.0**numpy.arange(-6,0)
#lambda1s = [0.0625, 2.0, 10.0]
#lambda2s = [0.0625, 5.0, 30.0]
#sigmas = [0.0625, 1.0, 10.0]
logging.info("lambda1s = " + str(lambda1s))
logging.info("lambda2s = " + str(lambda2s))
logging.info("sigmas = " + str(sigmas))
lmbda = 0.1
alpha = 5.0 #Note that this is not the same as that used the errorFunc
kernel = LinearKernel()
alterRegressor = PrimalWeightedRidgeRegression(lmbda, alpha)
egoRegressor = KernelRidgeRegression(kernel, lmbda)
predictor = EgoEdgeLabelPredictor(alterRegressor, egoRegressor)
simulator = EgoNetworkSimulator(graph, predictor)
errorFunc = Evaluator.weightedRootMeanSqError
paramList = []
paramFuncs = [egoRegressor.setLambda, alterRegressor.setLambda]
#First just use the linear kernel
for i in lambda1s:
for j in lambda2s:
paramList.append([i, j])
params, paramFuncs, error = simulator.modelSelection(paramList, paramFuncs, folds, errorFunc, sampleSize)
#Now try the RBF kernel
kernel = GaussianKernel()
egoRegressor.setKernel(kernel)
paramFuncs2 = [egoRegressor.setLambda, alterRegressor.setLambda, kernel.setSigma]
paramList2 = []
for i in lambda1s:
for j in lambda2s:
for k in sigmas:
paramList2.append([i, j, k])
params2, paramFuncs2, error2 = simulator.modelSelection(paramList2, paramFuncs2, folds, errorFunc, sampleSize)
if error2 < error:
params = params2
paramFuncs = paramFuncs2
paramsFile = InfoExperiment.getParamsFileName()
(means, vars) = simulator.evaluateClassifier(params, paramFuncs, folds, errorFunc, sampleSize)
logging.info("Evaluated classifier with mean errors " + str(means))
simulator.getClassifier().saveParams(params, paramFuncs, paramsFile)
class EgoNetworkSimulatorTest(unittest.TestCase):
def setUp(self):
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
dataDir = PathDefaults.getDataDir() + "infoDiffusion/"
numVertices = 100
numFeatures = 5
c = numpy.random.rand(numFeatures)
vList = VertexList(numVertices, numFeatures)
vList.setVertices(numpy.random.rand(numVertices, numFeatures))
graph = SparseGraph(vList)
p = 0.1
generator = ErdosRenyiGenerator(p)
graph = generator.generate(graph)
#Now rewrite some vertices to have different labels which depend only
#on the alter.
edges = graph.getAllEdges()
for i in range(edges.shape[0]):
edgeLabel = numpy.dot(graph.getVertex(edges[i, 1]), c)
graph.addEdge(edges[i, 0], edges[i, 1], edgeLabel)
#Create the predictor
lmbda = 0.01
self.alterRegressor = PrimalRidgeRegression(lmbda)
self.egoRegressor = PrimalRidgeRegression(lmbda)
predictor = EgoEdgeLabelPredictor(self.alterRegressor, self.egoRegressor)
self.egoNetworkSimulator = EgoNetworkSimulator(graph, predictor)
self.graph = graph
def testSampleExamples(self):
numEdges = 100
graph = self.egoNetworkSimulator.sampleEdges(numEdges)
self.assertEquals(graph.getNumEdges(), numEdges)
self.assertEquals(graph.getNumVertices(), self.graph.getNumVertices())
self.assertEquals(graph.isUndirected(), self.graph.isUndirected())
def testModelSelection(self):
paramList = [[0.1, 0.1], [0.2, 0.1], [0.1, 0.2]]
paramFunc = [self.egoRegressor.setLambda, self.alterRegressor.setLambda]
folds = 3
errorFunc = Evaluator.rootMeanSqError
sampleSize = 100
params, paramFuncs, errors = self.egoNetworkSimulator.modelSelection(paramList, paramFunc, folds, errorFunc, sampleSize)
logging.debug(params)
logging.debug(paramFuncs)
logging.debug(errors)
def testEvaluateClassifier(self):
params = [0.1, 0.1]
paramFunc = [self.egoRegressor.setLambda, self.alterRegressor.setLambda]
folds = 3
errorFunc = Evaluator.rootMeanSqError
sampleSize = 100
(means, vars) = self.egoNetworkSimulator.evaluateClassifier(params, paramFunc, folds, errorFunc, sampleSize)
logging.debug(means)
logging.debug(vars)
def testTrainClassifier(self):
params= [0.1, 0.1]
paramFuncs = [self.egoRegressor.setLambda, self.alterRegressor.setLambda]
sampleSize = 100
self.egoNetworkSimulator.trainClassifier(params, paramFuncs, sampleSize)
def testGenerateRandomGraph(self):
egoFileName = PathDefaults.getDataDir() + "infoDiffusion/EgoData.csv"
alterFileName = PathDefaults.getDataDir() + "infoDiffusion/AlterData.csv"
numVertices = 1000
infoProb = 0.1
graphType = "SmallWorld"
p = 0.1
neighbours = 10
self.egoNetworkSimulator.generateRandomGraph(egoFileName, alterFileName, numVertices, infoProb, graphType, p, neighbours)
def testRunSimulation(self):
egoFileName = PathDefaults.getDataDir() + "infoDiffusion/EgoData.csv"
alterFileName = PathDefaults.getDataDir() + "infoDiffusion/AlterData.csv"
numVertices = 1000
infoProb = 0.1
graphType = "SmallWorld"
p = 0.1
neighbours = 10
params= [0.1, 0.1]
paramFuncs = [self.egoRegressor.setLambda, self.alterRegressor.setLambda]
sampleSize = 100
maxIterations = 5
self.egoNetworkSimulator.trainClassifier(params, paramFuncs, sampleSize)
self.egoNetworkSimulator.generateRandomGraph(egoFileName, alterFileName, numVertices, infoProb, graphType, p, neighbours)
self.egoNetworkSimulator.runSimulation(maxIterations)