def profileSimulateGraphMatch(self):
N, matchAlpha, breakDist, purtScale = HIVModelUtils.toyABCParams()
startDate, endDate, recordStep, M, targetGraph = HIVModelUtils.toySimulationParams()
theta, stdTheta = HIVModelUtils.toyTheta()
featureInds= numpy.ones(targetGraph.vlist.getNumFeatures(), numpy.bool)
featureInds[HIVVertices.dobIndex] = False
featureInds[HIVVertices.infectionTimeIndex] = False
featureInds[HIVVertices.hiddenDegreeIndex] = False
featureInds[HIVVertices.stateIndex] = False
featureInds = numpy.arange(featureInds.shape[0])[featureInds]
#QCV is fastest and most accurate
#PATH is slowests but quite accurate
#RANK is very fast by less accurate than PATH
#U is fastest but least accurate
matcher = GraphMatch("QCV", alpha=matchAlpha, featureInds=featureInds, useWeightM=False)
matcher.lambdaM = 50
matcher.init = "rand"
graphMetrics = HIVGraphMetrics2(targetGraph, breakDist, matcher, float(endDate))
def run():
times, infectedIndices, removedIndices, graph = HIVModelUtils.simulate(theta, startDate, endDate, recordStep, M, graphMetrics)
print("Mean distance " + str(graphMetrics.meanDistance()))
ProfileUtils.profile('run()', globals(), locals())
def testSimulate(self):
#We want to see if we can get the same simulation twice
N, matchAlpha, breakScale, numEpsilons, epsilon, minEpsilon, matchAlg, abcMaxRuns, batchSize, pertScale = HIVModelUtils.toyABCParams()
startDate, endDate, recordStep, M, targetGraph = HIVModelUtils.toySimulationParams(test=True)
breakSize = (targetGraph.subgraph(targetGraph.removedIndsAt(endDate)).size - targetGraph.subgraph(targetGraph.removedIndsAt(startDate)).size) * breakScale
theta, sigmaTheta, pertTheta = HIVModelUtils.toyTheta()
model = HIVModelUtils.createModel(theta, targetGraph, startDate, endDate, recordStep, M, matchAlpha, breakSize, matchAlg)
model.setParams(theta)
times, infectedIndices, removedIndices, graph, compTimes, graphMetrics = HIVModelUtils.simulate(model)
numEdges = graph.getNumEdges()
lastRemovedIndices = removedIndices[-1]
#Simulate again
model = HIVModelUtils.createModel(theta, targetGraph, startDate, endDate, recordStep, M, matchAlpha, breakSize, matchAlg)
model.setParams(theta)
times, infectedIndices, removedIndices, graph, compTimes, graphMetrics = HIVModelUtils.simulate(model)
numEdges2 = graph.getNumEdges()
lastRemovedIndices2 = removedIndices[-1]
self.assertEquals(numEdges, numEdges2)
self.assertEquals(lastRemovedIndices, lastRemovedIndices2)
def testSimulate2(self):
alpha = 2
zeroVal = 0.9
startDate = 0.0
endDate = 200.0
M = 1000
undirected = True
theta, sigmaTheta, pertTheta = HIVModelUtils.toyTheta()
numpy.random.seed(21)
graph = HIVGraph(M, undirected)
p = Util.powerLawProbs(alpha, zeroVal)
hiddenDegSeq = Util.randomChoice(p, graph.getNumVertices())
rates = HIVRates(graph, hiddenDegSeq)
model = HIVEpidemicModel(graph, rates, endDate, startDate, metrics=None)
#model.setRecordStep(recordStep)
model.setParams(theta)
times, infectedIndices, removedIndices, graph = model.simulate(True)
numVertices = graph.size
numEdges = graph.getNumEdges()
#Try again
numpy.random.seed(21)
graph = HIVGraph(M, undirected)
p = Util.powerLawProbs(alpha, zeroVal)
hiddenDegSeq = Util.randomChoice(p, graph.getNumVertices())
rates = HIVRates(graph, hiddenDegSeq)
model = HIVEpidemicModel(graph, rates, endDate, startDate, metrics=None)
model.setParams(theta)
times, infectedIndices, removedIndices, graph = model.simulate(True)
numVertices2 = graph.size
numEdges2 = graph.getNumEdges()
self.assertEquals(numVertices2, numVertices)
self.assertEquals(numEdges2, numEdges)
def loadParams(ind):
if processReal:
resultsDir = PathDefaults.getOutputDir() + "viroscopy/real/theta" + str(ind) + "/"
outputDir = resultsDir + "stats/"
N, matchAlpha, breakScale, numEpsilons, epsilon, minEpsilon, matchAlg, abcMaxRuns, batchSize, pertScale = HIVModelUtils.realABCParams(True)
startDate, endDate, recordStep, M, targetGraph, numInds = HIVModelUtils.realSimulationParams(test=True, ind=ind)
realTheta, sigmaTheta, pertTheta = HIVModelUtils.estimatedRealTheta(ind)
numInds=2
prefix = "Real"
else:
resultsDir = PathDefaults.getOutputDir() + "viroscopy/toy/theta/"
outputDir = resultsDir + "stats/"
N, matchAlpha, breakScale, numEpsilons, epsilon, minEpsilon, matchAlg, abcMaxRuns, batchSize, pertScale = HIVModelUtils.toyABCParams()
startDate, endDate, recordStep, M, targetGraph = HIVModelUtils.toySimulationParams(test=True)
realTheta, sigmaTheta, pertTheta = HIVModelUtils.toyTheta()
prefix = "Toy"
numInds = 1
breakSize = (targetGraph.subgraph(targetGraph.removedIndsAt(endDate)).size - targetGraph.subgraph(targetGraph.removedIndsAt(startDate)).size) * breakScale
return N, resultsDir, outputDir, recordStep, startDate, endDate, prefix, targetGraph, breakSize, numEpsilons, M, matchAlpha, matchAlg, numInds
for ind in inds:
logging.debug("ind=" + str(ind))
N, resultsDir, outputDir, recordStep, startDate, endDate, prefix, targetGraph, breakSize, numEpsilons, M, matchAlpha, matchAlg, numInds = loadParams(ind)
#Find the max number t for which we have a complete set of particles
t = 0
for i in range(numEpsilons):
thetaArray, objArray = loadThetaArray(N, resultsDir, i)
if thetaArray.shape[0] == N:
t = i
logging.debug("Using particle number " + str(t))
times = numpy.arange(startDate, endDate+1, recordStep)
realTheta, sigmaTheta, purtTheta = HIVModelUtils.toyTheta()
thetaArray, objArray = loadThetaArray(N, resultsDir, t)
thetas.append(thetaArray)
print(thetaArray)
resultsFileName = outputDir + "IdealStats.pkl"
stats = Util.loadPickle(resultsFileName)
vertexArrayIdeal, idealInfectedIndices, idealRemovedIndices, idealContactGraphStats, idealRemovedGraphStats, idealFinalRemovedDegrees = stats
graphStats = GraphStatistics()
idealMeasures[ind, numDetectsInd, :] = vertexArrayIdeal[:, numDetectsInd]
idealMeasures[ind, maleInd, :] = vertexArrayIdeal[:, maleInd]
idealMeasures[ind, femaleInd, :] = vertexArrayIdeal[:, femaleInd]
idealMeasures[ind, heteroInd, :] = vertexArrayIdeal[:, heteroInd]
idealMeasures[ind, biInd, :] = vertexArrayIdeal[:, biInd]
idealMeasures[ind, randDetectInd, :] = vertexArrayIdeal[:, randDetectInd]
import matplotlib.pyplot as plt
"""
This is the epidemic model for the HIV spread in cuba. We want to see how different
graphs can get under the same params but different seeds.
"""
assert False, "Must run with -O flag"
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
numpy.seterr(all='raise')
numpy.random.seed(24)
numpy.set_printoptions(suppress=True, precision=4, linewidth=100)
startDate, endDate, recordStep, M, targetGraph = HIVModelUtils.toySimulationParams()
meanTheta, sigmaTheta = HIVModelUtils.toyTheta()
#In this case, we'll extend the end date
endDate *= 2
epsilon = 5.0
reps = 10
graphDists = []
removedArray = []
biArray = []
maleArray = []
femaleArray = []
for i in range(reps):
print("i=" + str(i))
N, matchAlpha, breakScale, numEpsilons, epsilon, minEpsilon, matchAlg, abcMaxRuns, batchSize, pertScale = HIVModelUtils.toyABCParams()
logging.debug("Total time of simulation is " + str(endDate-startDate))
logging.debug("Posterior sample size " + str(N))
epsilonArray = numpy.ones(numEpsilons)*epsilon
breakSize = (targetGraph.subgraph(targetGraph.removedIndsAt(endDate)).size - targetGraph.subgraph(targetGraph.removedIndsAt(startDate)).size) * breakScale
logging.debug("Largest acceptable graph is " + str(breakSize))
def createModel(t):
"""
The parameter t is the particle index.
"""
return HIVModelUtils.createModel(targetGraph, startDate, endDate, recordStep, M, matchAlpha, breakSize, matchAlg)
meanTheta, sigmaTheta, pertTheta = HIVModelUtils.toyTheta()
abcParams = HIVABCParameters(meanTheta, sigmaTheta, pertTheta)
thetaDir = resultsDir + "theta/"
if not os.path.exists(thetaDir):
os.mkdir(thetaDir)
logging.debug((meanTheta, sigmaTheta))
abcSMC = ABCSMC(epsilonArray, createModel, abcParams, thetaDir, True, minEpsilon=minEpsilon)
abcSMC.setPosteriorSampleSize(N)
abcSMC.batchSize = batchSize
abcSMC.maxRuns = abcMaxRuns
abcSMC.setNumProcesses(numProcesses)
abcSMC.pertScale = pertScale
thetasArray = abcSMC.run()
