eCsvReader = EgoCsvReader()
egoQuestionIds = eCsvReader.getEgoQuestionIds()
pajekWriter = PajekWriter()
simpleGraphWriter = SimpleGraphWriter()
vertexWriter = CsvVertexWriter()
for i in range(len(graphTypes)):
graphType = graphTypes[i]
p = ps[i]
k = ks[i]
outputDirectory = PathDefaults.getOutputDir()
baseFileName = outputDirectory + "InfoGraph" + graphType
graph = simulator.generateRandomGraph(egoFileName, alterFileName, numVertices, infoProb, graphType, p, k)
#Notice that the data is preprocessed in the same way as the survey data
egoSimulator = EgoSimulator(graph, classifier, preprocessor)
totalInfo = numpy.zeros(maxIterations+1)
totalInfo[0] = EgoUtils.getTotalInformation(graph)
logging.info("Total number of people with information: " + str(totalInfo[0]))
logging.info("--- Simulation Started ---")
for i in range(0, maxIterations):
logging.info("--- Iteration " + str(i) + " ---")
graph = egoSimulator.advanceGraph()
totalInfo[i+1] = EgoUtils.getTotalInformation(graph)
logging.info("Total number of people with information: " + str(totalInfo[i+1]))
class SvmEgoSimulatorTest(unittest.TestCase):
def setUp(self):
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
dataDir = PathDefaults.getDataDir() + "infoDiffusion/"
#dataDir = "/home/charanpal/Private/Postdoc/Code/APGL/data/"
matFileName = dataDir + "EgoAlterTransmissions.mat"
self.svmEgoSimulator = SvmEgoSimulator(matFileName)
def testSampleExamples(self):
self.svmEgoSimulator.sampleExamples(100)
self.assertEquals(self.svmEgoSimulator.examplesList.getNumSampledExamples(), 100)
def testModelSelection(self):
Cs = [1.0, 2.0]
kernel = "linear"
kernelParams = [0.0]
errorCosts = [0.1, 0.2]
folds = 5
sampleSize = 1000
CVal, kernelParamVal, errorCost, error = self.svmEgoSimulator.modelSelection(Cs, kernel, kernelParams, errorCosts, folds, sampleSize)
self.assertTrue(CVal in Cs)
self.assertTrue(kernelParamVal in kernelParams)
self.assertTrue(errorCost in errorCosts)
self.assertTrue(error >= 0.0 and error < 1.0)
def testEvaluateClassifier(self):
CVal = 1.0
kernel = "linear"
kernelParamVal = 0.0
errorCost = 0.5
folds = 6
sampleSize = 1000
invert = False
(means, vars) = self.svmEgoSimulator.evaluateClassifier(CVal, kernel, kernelParamVal, errorCost, folds, sampleSize, invert)
def testTrainClassifier(self):
CVal = 1.0
kernel = "linear"
kernelParamVal = 0.0
errorCost = 0.5
folds = 6
sampleSize = 1000
self.svmEgoSimulator.trainClassifier(CVal, kernel, kernelParamVal, errorCost, sampleSize)
def testGenerateRandomGraph(self):
egoFileName = PathDefaults.getDataDir() + "infoDiffusion/EgoData.csv"
alterFileName = PathDefaults.getDataDir() + "infoDiffusion/AlterData.csv"
numVertices = 1000
infoProb = 0.1
p = 0.1
neighbours = 10
generator = SmallWorldGenerator(p, neighbours)
graph = SparseGraph(VertexList(numVertices, 0))
graph = generator.generate(graph)
self.svmEgoSimulator.generateRandomGraph(egoFileName, alterFileName, infoProb, graph)
def testRunSimulation(self):
egoFileName = PathDefaults.getDataDir() + "infoDiffusion/EgoData.csv"
alterFileName = PathDefaults.getDataDir() + "infoDiffusion/AlterData.csv"
numVertices = 1000
infoProb = 0.1
p = 0.1
neighbours = 10
generator = SmallWorldGenerator(p, neighbours)
graph = SparseGraph(VertexList(numVertices, 0))
graph = generator.generate(graph)
CVal = 1.0
kernel = "linear"
kernelParamVal = 0.0
errorCost = 0.5
folds = 6
sampleSize = 1000
maxIterations = 5
self.svmEgoSimulator.trainClassifier(CVal, kernel, kernelParamVal, errorCost, sampleSize)
self.svmEgoSimulator.generateRandomGraph(egoFileName, alterFileName, infoProb, graph)
self.svmEgoSimulator.runSimulation(maxIterations)
#List of the numbers we want to store at each simulation
quantitiesArray = numpy.zeros((simulationRepetitions, maxIterations+1))
genderDistributions = numpy.zeros((simulationRepetitions, maxIterations+3, numGenders))
ageDistributions = numpy.zeros((simulationRepetitions, maxIterations+3, numAges))
educationDistributions = numpy.zeros((simulationRepetitions, maxIterations+3, numEducations))
professionDistributions = numpy.zeros((simulationRepetitions, maxIterations+3, numProfessions))
foodRiskDistributions = numpy.zeros((simulationRepetitions, maxIterations+3, numFoodRisks))
experienceDistributions = numpy.zeros((simulationRepetitions, maxIterations+3, numExperiences))
internetFreqDistributions = numpy.zeros((simulationRepetitions, maxIterations+3, numInternets))
for i in range(0, simulationRepetitions):
vList = VertexList(numVertices, 0)
graph = SparseGraph(vList)
graph = generator.generate(graph)
simulator.generateRandomGraph(egoFileName, alterFileName, infoProb, graph)
(totalInfo, transmissions) = simulator.runSimulation(maxIterations)
alters = []
egos = numpy.unique(transmissions[0][:, 0])
quantitiesArray[i, 0] = egos.shape[0]
for j in range(len(transmissions)):
alters.append(numpy.unique(transmissions[j][:, 1]))
quantitiesArray[i, 1+j] = alters[j].shape[0]
"""
The commented features have very large ranges - we need to bin them appropriately.
Either that, or ignore them.
"""