def plotOtherStats():
#Let's look at geodesic distances in subgraphs and communities
logging.info("Computing other stats")
resultsFileName = resultsDir + "ContactGrowthOtherStats.pkl"
hivGraphStats = HIVGraphStatistics(fInds)
if saveResults:
statsArray = hivGraphStats.sequenceScalarStats(sGraph, subgraphIndicesList)
#statsArray["dayList"] = absDayList
Util.savePickle(statsArray, resultsFileName, True)
else:
statsArray = Util.loadPickle(resultsFileName)
#Just load the harmonic geodesic distances of the full graph
resultsFileName = resultsDir + "ContactGrowthScalarStats.pkl"
statsArray2 = Util.loadPickle(resultsFileName)
global plotInd
msmGeodesic = statsArray[:, hivGraphStats.msmGeodesicIndex]
msmGeodesic[msmGeodesic < 0] = 0
msmGeodesic[msmGeodesic == float('inf')] = 0
#Output all the results into plots
plt.figure(plotInd)
plt.plot(absDayList, msmGeodesic, 'k-', absDayList, statsArray[:, hivGraphStats.mostConnectedGeodesicIndex], 'k--')
plt.xticks(locs, labels)
#plt.ylim([0, 0.1])
plt.xlabel("Year")
plt.ylabel("Mean harmonic geodesic distance")
plt.legend(("MSM individuals", "Top 10% degree"), loc="upper right")
plt.savefig(figureDir + "MSM10Geodesic" + ".eps")
plotInd += 1
plt.figure(plotInd)
plt.plot(absDayList, statsArray2[:, graphStats.harmonicGeoDistanceIndex], 'k-', absDayList, statsArray[:, hivGraphStats.menSubgraphGeodesicIndex], 'k--')
plt.xticks(locs, labels)
plt.ylim([0, 200.0])
plt.xlabel("Year")
plt.ylabel("Mean harmonic geodesic distance")
plt.legend(("All individuals", "Men subgraph"), loc="upper right")
plt.savefig(figureDir + "MenSubgraphGeodesic" + ".eps")
plotInd += 1
def findSimilarDocumentsLSI(self, field):
"""
We use LSI from gensim in this case
"""
self.computeLSI()
self.loadVectoriser()
lsi, index = Util.loadPickle(self.modelFilename)
newX = self.vectoriser.transform([field])
newX = [(i, newX[0, i])for i in newX.nonzero()[1]]
result = lsi[newX]
similarities = index[result]
expertsByDocSimilarity, expertsByCitations = self.expertsFromDocSimilarities(similarities, len(self.trainExpertDict[field]), field)
return expertsByDocSimilarity, expertsByCitations
def coauthorsGraph(self, field, relevantExperts):
"""
Using the relevant authors we find all coauthors.
"""
if not os.path.exists(self.getCoauthorsFilename(field)) or self.overwriteGraph:
logging.debug("Finding coauthors of relevant experts")
if self.knownAuthors:
graph, authorIndexer = self.coauthorsGraphFromAuthors2(set(relevantExperts), field)
else:
graph, authorIndexer = self.coauthorsGraphFromAuthors(set(relevantExperts))
logging.debug(graph.summary())
Util.savePickle([graph, authorIndexer], self.getCoauthorsFilename(field), debug=True)
else:
logging.debug("Files already generated: " + self.getCoauthorsFilename(field))
graph, authorIndexer = Util.loadPickle(self.getCoauthorsFilename(field))
return graph, authorIndexer
def findSimilarDocumentsLDA(self, field):
"""
We use LDA in this case
"""
self.computeLDA()
self.loadVectoriser()
lda, index = Util.loadPickle(self.modelFilename)
newX = self.vectoriser.transform([field])
newX = [(i, newX[0, i])for i in newX.nonzero()[1]]
result = lda[newX]
#Cosine similarity
similarities = index[result]
expertsByDocSimilarity, expertsByCitations = self.expertsFromDocSimilarities(similarities, len(self.trainExpertDict[field]), field)
logging.debug("Number of relevant authors : " + str(len(expertsByDocSimilarity)))
return expertsByDocSimilarity, expertsByCitations
#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]
idealMeasures[ind, contactDetectInd, :] = vertexArrayIdeal[:, contactDetectInd]
idealMeasures[ind, numCompsInd, :] = idealRemovedGraphStats[:, graphStats.numComponentsIndex]
idealMeasures[ind, maxCompSizeInd, :] = idealRemovedGraphStats[:, graphStats.maxComponentSizeIndex]
idealMeasures[ind, numEdgesInd, :] = idealRemovedGraphStats[:, graphStats.numEdgesIndex]
maxDegrees = min(idealFinalRemovedDegrees.shape[0], numDegrees)
coverages = numpy.load(dataset.coverageFilename)
print("==== Coverages ====")
print(coverages)
for s, field in enumerate(dataset.fields):
if ranLSI:
outputFilename = dataset.getOutputFieldDir(field) + "outputListsLSI.npz"
documentFilename = dataset.getOutputFieldDir(field) + "relevantDocsLSI.npy"
else:
outputFilename = dataset.getOutputFieldDir(field) + "outputListsLDA.npz"
documentFilename = dataset.getOutputFieldDir(field) + "relevantDocsLDA.npy"
try:
print(field)
print("-----------")
outputLists, trainExpertMatchesInds, testExpertMatchesInds = Util.loadPickle(outputFilename)
graph, authorIndexer = Util.loadPickle(dataset.getCoauthorsFilename(field))
trainPrecisions = numpy.zeros((len(ns), numMethods))
testPrecisions = numpy.zeros((len(ns), numMethods))
#Remove training experts from the output lists
trainOutputLists = []
testOutputLists = []
for outputList in outputLists:
newTrainOutputList = []
newTestOutputList = []
for item in outputList:
if item not in testExpertMatchesInds:
newTrainOutputList.append(item)
def plotVectorStats():
#Finally, compute some vector stats at various points in the graph
logging.info("Computing vector stats")
global plotInd
resultsFileName = resultsDir + "InfectGrowthVectorStats.pkl"
if saveResults:
statsDictList = graphStats.sequenceVectorStats(sGraph, subgraphIndicesList2, True)
Util.savePickle(statsDictList, resultsFileName, True)
else:
statsDictList = Util.loadPickle(resultsFileName)
treeSizesDistArray = numpy.zeros((len(dayList2), 3000))
treeDepthsDistArray = numpy.zeros((len(dayList2), 100))
numVerticesEdgesArray = numpy.zeros((len(dayList2), 2), numpy.int)
numVerticesEdgesArray[:, 0] = [len(sgl) for sgl in subgraphIndicesList2]
numVerticesEdgesArray[:, 1] = [sGraph.subgraph(sgl).getNumEdges() for sgl in subgraphIndicesList2]
for j in range(len(dayList2)):
dateStr = (str(DateUtils.getDateStrFromDay(dayList2[j], startYear)))
logging.info(dateStr)
statsDict = statsDictList[j]
degreeDist = statsDict["outDegreeDist"]
degreeDist = degreeDist/float(numpy.sum(degreeDist))
maxEigVector = statsDict["maxEigVector"]
maxEigVector = numpy.flipud(numpy.sort(numpy.abs(maxEigVector)))
maxEigVector = numpy.log(maxEigVector[maxEigVector>0])
treeSizesDist = statsDict["treeSizesDist"]
treeSizesDist = numpy.array(treeSizesDist, numpy.float64)/numpy.sum(treeSizesDist)
treeSizesDistArray[j, 0:treeSizesDist.shape[0]] = treeSizesDist
treeDepthsDist = statsDict["treeDepthsDist"]
#treeDepthsDist = numpy.array(treeDepthsDist, numpy.float64)/numpy.sum(treeDepthsDist)
treeDepthsDist = numpy.array(treeDepthsDist, numpy.float64)
treeDepthsDistArray[j, 0:treeDepthsDist.shape[0]] = treeDepthsDist
plotInd2 = plotInd
plt.figure(plotInd2)
plt.plot(numpy.arange(degreeDist.shape[0]), degreeDist, label=dateStr)
plt.xlabel("Degree")
plt.ylabel("Probability")
plt.ylim((0, 0.8))
plt.legend()
plt.savefig(figureDir + "DegreeDist" + ".eps")
plotInd2 += 1
plt.figure(plotInd2)
plt.scatter(numpy.arange(treeSizesDist.shape[0])[treeSizesDist!=0], numpy.log(treeSizesDist[treeSizesDist!=0]), s=30, c=plotStyles2[j][0], label=dateStr)
plt.xlabel("Size")
plt.ylabel("log(probability)")
plt.xlim((0, 125))
plt.legend()
plt.savefig(figureDir + "TreeSizeDist" + ".eps")
plotInd2 += 1
plt.figure(plotInd2)
plt.scatter(numpy.arange(treeDepthsDist.shape[0])[treeDepthsDist!=0], numpy.log(treeDepthsDist[treeDepthsDist!=0]), s=30, c=plotStyles2[j][0], label=dateStr)
plt.xlabel("Depth")
plt.ylabel("log(probability)")
plt.xlim((0, 15))
plt.legend()
plt.savefig(figureDir + "TreeDepthDist" + ".eps")
plotInd2 += 1
dateStrList = [DateUtils.getDateStrFromDay(day, startYear) for day in dayList2]
precision = 4
treeSizesDistArray = treeSizesDistArray[:, 0:treeSizesDist.shape[0]]
nonZeroCols = numpy.sum(treeSizesDistArray, 0)!=0
print((Latex.array1DToRow(numpy.arange(treeSizesDistArray.shape[1])[nonZeroCols])))
print((Latex.array2DToRows(treeSizesDistArray[:, nonZeroCols])))
print("Tree depths")
treeDepthsDistArray = treeDepthsDistArray[:, 0:treeDepthsDist.shape[0]]
nonZeroCols = numpy.sum(treeDepthsDistArray, 0)!=0
print((Latex.array1DToRow(numpy.arange(treeDepthsDistArray.shape[1])[nonZeroCols])))
print((Latex.array2DToRows(treeDepthsDistArray[:, nonZeroCols])))
print(numpy.sum(treeDepthsDistArray[:, 0:3], 1))
print("Edges and verticies")
print(Latex.listToRow(dateStrList))
print(Latex.array2DToRows(numVerticesEdgesArray.T, precision))
def plotScalarStats():
logging.info("Computing scalar stats")
resultsFileName = resultsDir + "InfectGrowthScalarStats.pkl"
if saveResults:
statsArray = graphStats.sequenceScalarStats(sGraph, subgraphIndicesList, treeStats=True)
Util.savePickle(statsArray, resultsFileName, True)
else:
statsArray = Util.loadPickle(resultsFileName)
global plotInd
#Output all the results into plots
#Take the mean of the results over the configuration model graphs
resultsFileNameBase = resultsDir + "ConfigInfectGraphScalarStats"
numGraphs = len(subgraphIndicesList)
configStatsArrays = numpy.zeros((numGraphs, graphStats.getNumStats(), numConfigGraphs))
for j in range(numConfigGraphs):
resultsFileName = resultsFileNameBase + str(j)
configStatsArrays[:, :, j] = Util.loadPickle(resultsFileName)
configStatsArray = numpy.mean(configStatsArrays, 2)
configStatsStd = numpy.std(configStatsArrays, 2)
#Make sure we don't include 0 in the array
vertexIndex = numpy.argmax(statsArray[:, graphStats.numVerticesIndex] > 0)
edgeIndex = numpy.argmax(statsArray[:, graphStats.numEdgesIndex] > 0)
minIndex = numpy.maximum(vertexIndex, edgeIndex)
def plotRealConfigError(index, styleReal, styleConfig, realLabel, configLabel):
plt.hold(True)
plt.plot(absDayList, statsArray[:, index], styleReal, label=realLabel)
#errors = numpy.c_[configStatsArray[:, index]-configStatsMinArray[:, index] , configStatsMaxArray[:, index]-configStatsArray[:, index]].T
errors = numpy.c_[configStatsStd[:, index], configStatsStd[:, index]].T
plt.plot(absDayList, configStatsArray[:, index], styleConfig, label=configLabel)
plt.errorbar(absDayList, configStatsArray[:, index], errors, linewidth=0, elinewidth=0, label="_nolegend_", ecolor=styleConfig[0])
xmin, xmax = plt.xlim()
plt.xlim((0, xmax))
ymin, ymax = plt.ylim()
plt.ylim((0, ymax))
plt.figure(plotInd)
plt.plot(numpy.log(statsArray[minIndex:, graphStats.numVerticesIndex]), numpy.log(statsArray[minIndex:, graphStats.numEdgesIndex]))
plt.xlabel("log(|V|)")
plt.ylabel("log(|E|)")
plt.savefig(figureDir + "LogVerticesEdgesGrowth.eps")
plotInd += 1
plt.figure(plotInd)
#plt.plot(absDayList, statsArray[:, graphStats.numTreesIndex], plotStyles3[0], label="Trees Size >= 1")
#plt.plot(absDayList, statsArray[:, graphStats.numNonSingletonTreesIndex], plotStyles3[1], label="Trees Size >= 2")
plotRealConfigError(graphStats.numTreesIndex, plotStyles3[0], plotStyles5[0], "Trees size >= 1", "CM trees size >= 1")
plotRealConfigError(graphStats.numNonSingletonTreesIndex, plotStyles3[0], plotStyles5[0], "Trees size >= 2", "CM trees size >= 2")
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("No. trees")
plt.legend(loc="upper left")
plt.savefig(figureDir + "NumTreesGrowth.eps")
plotInd += 1
for k in range(len(dayList)):
day = dayList[k]
print(str(DateUtils.getDateStrFromDay(day, startYear)) + ": " + str(statsArray[k, graphStats.numTreesIndex]))
print(str(DateUtils.getDateStrFromDay(day, startYear)) + ": " + str(configStatsArray[k, graphStats.numTreesIndex]))
#Load stats from a file to get the max tree from its root
resultsFilename = resultsDir + "treeSizesDepths.npz"
file = open(resultsFilename, 'r')
arrayDict = numpy.load(file)
statsArray[:, graphStats.maxTreeDepthIndex] = arrayDict["arr_0"]
statsArray[:, graphStats.maxTreeSizeIndex] = arrayDict["arr_1"]
statsArray[:, graphStats.secondTreeDepthIndex] = arrayDict["arr_2"]
statsArray[:, graphStats.secondTreeSizeIndex] = arrayDict["arr_3"]
plt.figure(plotInd)
plotRealConfigError(graphStats.maxTreeSizeIndex, plotStyles3[0], plotStyles5[0], "Max tree", "CM max tree")
plotRealConfigError(graphStats.secondTreeSizeIndex, plotStyles3[1], plotStyles5[1], "2nd tree", "CM 2nd tree")
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("Size")
plt.legend(loc="upper left")
plt.savefig(figureDir + "MaxTreeGrowth.eps")
plotInd += 1
plt.figure(plotInd)
plotRealConfigError(graphStats.maxTreeDepthIndex, plotStyles3[0], plotStyles5[0], "Max tree", "CM max tree")
plotRealConfigError(graphStats.secondTreeDepthIndex, plotStyles3[1], plotStyles5[1], "2nd tree", "CM 2nd tree")
#plt.plot(absDayList, statsArray[:, graphStats.maxTreeDepthIndex], plotStyles3[0], absDayList, statsArray[:, graphStats.secondTreeDepthIndex], plotStyles3[1] )
#plt.plot(absDayList, configStatsArray[:, graphStats.maxTreeDepthIndex], plotStyles4[0], absDayList, configStatsArray[:, graphStats.secondTreeDepthIndex], plotStyles4[1])
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("Depth")
plt.legend(loc="lower right")
plt.savefig(figureDir + "MaxTreeDepthGrowth.eps")
plotInd += 1
def plotTreeStats():
logging.info("Computing tree stats")
resultsFileName = resultsDir + "InfectGrowthTreeStats.pkl"
if saveResults:
statsDictList = []
for j in range(len(subgraphIndicesList2)):
Util.printIteration(j, 1, len(subgraphIndicesList2))
subgraphIndices = subgraphIndicesList2[j]
subgraph = sGraph.subgraph(subgraphIndices)
logging.info("Finding trees")
trees = subgraph.findTrees()
logging.info("Computing tree statistics")
statsDict = {}
locationEntropy = []
orientEntropy = []
detectionRanges = []
for i in range(len(trees)):
if len(trees[i]) > 1:
treeGraph = subgraph.subgraph(trees[i])
vertexArray = treeGraph.getVertexList().getVertices(list(range(treeGraph.getNumVertices())))
locationEntropy.append(Util.entropy(vertexArray[:, locationIndex]))
orientEntropy.append(Util.entropy(vertexArray[:, orientationIndex]))
detections = vertexArray[:, detectionIndex]
detectionRanges.append(numpy.max(detections) - numpy.min(detections))
statsDict["locationEnt"] = numpy.array(locationEntropy)
statsDict["orientEnt"] = numpy.array(orientEntropy)
statsDict["detectRanges"] = numpy.array(detectionRanges)
statsDictList.append(statsDict)
Util.savePickle(statsDictList, resultsFileName, True)
else:
statsDictList = Util.loadPickle(resultsFileName)
locBins = numpy.arange(0, 2.4, 0.2)
detectBins = numpy.arange(0, 6500, 500)
locationEntDists = []
orientEntDists = []
detectionDists = []
for j in range(0, len(dayList2)):
dateStr = (str(DateUtils.getDateStrFromDay(dayList2[j], startYear)))
logging.info(dateStr)
statsDict = statsDictList[j]
plotInd2 = plotInd
locationEntDists.append(statsDict["locationEnt"])
orientEntDists.append(statsDict["orientEnt"])
detectionDists.append(statsDict["detectRanges"])
#for j in range(len(orientEntDists)):
# print(numpy.sum(numpy.histogram(orientEntDists[j])[0]))
# print(numpy.histogram(orientEntDists[j])[0]/float(orientEntDists[j].shape[0]))
dateStrs = [DateUtils.getDateStrFromDay(dayList2[i], startYear) for i in range(1, len(dayList2))]
plt.figure(plotInd2)
histOut = plt.hist(locationEntDists, locBins, normed=True)
plt.xlabel("Location Entropy")
plt.ylabel("Probability Density")
plt.savefig(figureDir + "LocationEnt" + ".eps")
#plt.legend()
plotInd2 += 1
plt.figure(plotInd2)
histOut = plt.hist(orientEntDists, normed=True)
plt.xlabel("Orientation Entropy")
plt.ylabel("Probability Density")
plt.savefig(figureDir + "OrientEnt" + ".eps")
#plt.legend()
plotInd2 += 1
plt.figure(plotInd2)
histOut = plt.hist(detectionDists, detectBins, normed=True)
plt.xlabel("Detection Range (days)")
plt.ylabel("Probability Density")
plt.savefig(figureDir + "DetectionRanges" + ".eps")
#plt.legend()
plotInd2 += 1
def loadVectoriser(self):
self.vectoriser = Util.loadPickle(self.vectoriserFilename)
self.vectoriser.tokenizer = PorterTokeniser()
self.authorList = Util.loadPickle(self.authorListFilename)
self.citationList = Util.loadPickle(self.citationListFilename)
logging.debug("Loaded vectoriser, citation and author list")
def plotVectorStats():
#Finally, compute some vector stats at various points in the graph
logging.info("Computing vector stats")
global plotInd
resultsFileName = resultsDir + "ContactGrowthVectorStats.pkl"
if saveResults:
statsDictList = graphStats.sequenceVectorStats(sGraph, subgraphIndicesList2)
Util.savePickle(statsDictList, resultsFileName, False)
else:
statsDictList = Util.loadPickle(resultsFileName)
#Load up configuration model results
configStatsDictList = []
resultsFileNameBase = resultsDir + "ConfigGraphVectorStats"
for j in range(numConfigGraphs):
resultsFileName = resultsFileNameBase + str(j)
configStatsDictList.append(Util.loadPickle(resultsFileName))
#Now need to take mean of 1st element of list
meanConfigStatsDictList = configStatsDictList[0]
for i in range(len(configStatsDictList[0])):
for k in range(1, numConfigGraphs):
for key in configStatsDictList[k][i].keys():
if configStatsDictList[k][i][key].shape[0] > meanConfigStatsDictList[i][key].shape[0]:
meanConfigStatsDictList[i][key] = numpy.r_[meanConfigStatsDictList[i][key], numpy.zeros(configStatsDictList[k][i][key].shape[0] - meanConfigStatsDictList[i][key].shape[0])]
elif configStatsDictList[k][i][key].shape[0] < meanConfigStatsDictList[i][key].shape[0]:
configStatsDictList[k][i][key] = numpy.r_[configStatsDictList[k][i][key], numpy.zeros(meanConfigStatsDictList[i][key].shape[0] - configStatsDictList[k][i][key].shape[0])]
meanConfigStatsDictList[i][key] += configStatsDictList[k][i][key]
for key in configStatsDictList[0][i].keys():
meanConfigStatsDictList[i][key] = meanConfigStatsDictList[i][key]/numConfigGraphs
triangleDistArray = numpy.zeros((len(dayList2), 100))
configTriangleDistArray = numpy.zeros((len(dayList2), 100))
hopPlotArray = numpy.zeros((len(dayList2), 27))
configHopPlotArray = numpy.zeros((len(dayList2), 30))
componentsDistArray = numpy.zeros((len(dayList2), 3000))
configComponentsDistArray = numpy.zeros((len(dayList2), 3000))
numVerticesEdgesArray = numpy.zeros((len(dayList2), 2), numpy.int)
numVerticesEdgesArray[:, 0] = [len(sgl) for sgl in subgraphIndicesList2]
numVerticesEdgesArray[:, 1] = [sGraph.subgraph(sgl).getNumEdges() for sgl in subgraphIndicesList2]
binWidths = numpy.arange(0, 0.50, 0.05)
eigVectorDists = numpy.zeros((len(dayList2), binWidths.shape[0]-1), numpy.int)
femaleSums = numpy.zeros(len(dayList2))
maleSums = numpy.zeros(len(dayList2))
heteroSums = numpy.zeros(len(dayList2))
biSums = numpy.zeros(len(dayList2))
contactSums = numpy.zeros(len(dayList2))
nonContactSums = numpy.zeros(len(dayList2))
donorSums = numpy.zeros(len(dayList2))
randomTestSums = numpy.zeros(len(dayList2))
stdSums = numpy.zeros(len(dayList2))
prisonerSums = numpy.zeros(len(dayList2))
recommendSums = numpy.zeros(len(dayList2))
meanAges = numpy.zeros(len(dayList2))
degrees = numpy.zeros((len(dayList2), 20))
provinces = numpy.zeros((len(dayList2), 15))
havanaSums = numpy.zeros(len(dayList2))
villaClaraSums = numpy.zeros(len(dayList2))
pinarSums = numpy.zeros(len(dayList2))
holguinSums = numpy.zeros(len(dayList2))
habanaSums = numpy.zeros(len(dayList2))
sanctiSums = numpy.zeros(len(dayList2))
meanDegrees = numpy.zeros(len(dayList2))
stdDegrees = numpy.zeros(len(dayList2))
#Note that death has a lot of missing values
for j in range(len(dayList2)):
dateStr = (str(DateUtils.getDateStrFromDay(dayList2[j], startYear)))
logging.info(dateStr)
statsDict = statsDictList[j]
configStatsDict = meanConfigStatsDictList[j]
degreeDist = statsDict["outDegreeDist"]
degreeDist = degreeDist/float(numpy.sum(degreeDist))
#Note that degree distribution for configuration graph will be identical
eigenDist = statsDict["eigenDist"]
eigenDist = numpy.log(eigenDist[eigenDist>=10**-1])
#configEigenDist = configStatsDict["eigenDist"]
#configEigenDist = numpy.log(configEigenDist[configEigenDist>=10**-1])
hopCount = statsDict["hopCount"]
hopCount = numpy.log10(hopCount)
hopPlotArray[j, 0:hopCount.shape[0]] = hopCount
configHopCount = configStatsDict["hopCount"]
configHopCount = numpy.log10(configHopCount)
#configHopPlotArray[j, 0:configHopCount.shape[0]] = configHopCount
triangleDist = statsDict["triangleDist"]
#triangleDist = numpy.array(triangleDist, numpy.float64)/numpy.sum(triangleDist)
triangleDist = numpy.array(triangleDist, numpy.float64)
triangleDistArray[j, 0:triangleDist.shape[0]] = triangleDist
configTriangleDist = configStatsDict["triangleDist"]
configTriangleDist = numpy.array(configTriangleDist, numpy.float64)/numpy.sum(configTriangleDist)
configTriangleDistArray[j, 0:configTriangleDist.shape[0]] = configTriangleDist
maxEigVector = statsDict["maxEigVector"]
eigenvectorInds = numpy.flipud(numpy.argsort(numpy.abs(maxEigVector)))
top10eigenvectorInds = eigenvectorInds[0:numpy.round(eigenvectorInds.shape[0]/10.0)]
maxEigVector = numpy.abs(maxEigVector[eigenvectorInds])
#print(maxEigVector)
eigVectorDists[j, :] = numpy.histogram(maxEigVector, binWidths)[0]
componentsDist = statsDict["componentsDist"]
componentsDist = numpy.array(componentsDist, numpy.float64)/numpy.sum(componentsDist)
componentsDistArray[j, 0:componentsDist.shape[0]] = componentsDist
configComponentsDist = configStatsDict["componentsDist"]
configComponentsDist = numpy.array(configComponentsDist, numpy.float64)/numpy.sum(configComponentsDist)
configComponentsDistArray[j, 0:configComponentsDist.shape[0]] = configComponentsDist
plotInd2 = plotInd
plt.figure(plotInd2)
plt.plot(numpy.arange(degreeDist.shape[0]), degreeDist, plotStyles2[j], label=dateStr)
plt.xlabel("Degree")
plt.ylabel("Probability")
plt.ylim((0, 0.5))
plt.savefig(figureDir + "DegreeDist" + ".eps")
plt.legend()
plotInd2 += 1
"""
plt.figure(plotInd2)
plt.plot(numpy.arange(eigenDist.shape[0]), eigenDist, label=dateStr)
plt.xlabel("Eigenvalue rank")
plt.ylabel("log(Eigenvalue)")
plt.savefig(figureDir + "EigenDist" + ".eps")
plt.legend()
plotInd2 += 1
"""
#How does kleinberg do the hop plots
plt.figure(plotInd2)
plt.plot(numpy.arange(hopCount.shape[0]), hopCount, plotStyles[j], label=dateStr)
plt.xlabel("k")
plt.ylabel("log10(pairs)")
plt.ylim( (2.5, 7) )
plt.legend(loc="lower right")
plt.savefig(figureDir + "HopCount" + ".eps")
plotInd2 += 1
plt.figure(plotInd2)
plt.plot(numpy.arange(maxEigVector.shape[0]), maxEigVector, plotStyles2[j], label=dateStr)
plt.xlabel("Rank")
plt.ylabel("log(eigenvector coefficient)")
plt.savefig(figureDir + "MaxEigVector" + ".eps")
plt.legend()
plotInd2 += 1
#Compute some information the 10% most central vertices
subgraphIndices = numpy.nonzero(detections <= dayList2[j])[0]
subgraph = sGraph.subgraph(subgraphIndices)
subgraphVertexArray = subgraph.getVertexList().getVertices()
femaleSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, genderIndex]==1)
maleSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, genderIndex]==0)
heteroSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, orientationIndex]==0)
biSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, orientationIndex]==1)
contactSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, contactIndex])
donorSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, donorIndex])
randomTestSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, randomTestIndex])
stdSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, stdIndex])
prisonerSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, prisonerIndex])
recommendSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, doctorIndex])
meanAges[j] = numpy.mean(subgraphVertexArray[top10eigenvectorInds, detectionIndex] - subgraphVertexArray[top10eigenvectorInds, dobIndex])/daysInYear
havanaSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, havanaIndex])
villaClaraSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, villaClaraIndex])
pinarSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, pinarIndex])
holguinSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, holguinIndex])
habanaSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, habanaIndex])
sanctiSums[j] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, sanctiIndex])
provinces[j, :] = numpy.sum(subgraphVertexArray[top10eigenvectorInds, 22:37], 0)
ddist = numpy.bincount(subgraph.outDegreeSequence()[top10eigenvectorInds])
degrees[j, 0:ddist.shape[0]] = numpy.array(ddist, numpy.float)/numpy.sum(ddist)
meanDegrees[j] = numpy.mean(subgraph.outDegreeSequence()[top10eigenvectorInds])
stdDegrees[j] = numpy.std(subgraph.outDegreeSequence()[top10eigenvectorInds])
plt.figure(plotInd2)
plt.plot(numpy.arange(degrees[j, :].shape[0]), degrees[j, :], plotStyles2[j], label=dateStr)
plt.xlabel("Degree")
plt.ylabel("Probability")
#plt.ylim((0, 0.5))
plt.savefig(figureDir + "DegreeDistCentral" + ".eps")
plt.legend()
plotInd2 += 1
precision = 4
dateStrList = [DateUtils.getDateStrFromDay(day, startYear) for day in dayList2]
print("Hop counts")
print(Latex.listToRow(dateStrList))
print(Latex.array2DToRows(hopPlotArray.T))
print("\nHop counts for configuration graphs")
print(Latex.listToRow(dateStrList))
print(Latex.array2DToRows(configHopPlotArray.T))
print("\n\nEdges and vertices")
print((Latex.listToRow(dateStrList)))
print((Latex.array2DToRows(numVerticesEdgesArray.T, precision)))
print("\n\nEigenvector distribution")
print((Latex.array1DToRow(binWidths[1:]) + "\\\\"))
print((Latex.array2DToRows(eigVectorDists)))
print("\n\nDistribution of component sizes")
componentsDistArray = componentsDistArray[:, 0:componentsDist.shape[0]]
nonZeroCols = numpy.sum(componentsDistArray, 0)!=0
componentsDistArray = numpy.r_[numpy.array([numpy.arange(componentsDistArray.shape[1])[nonZeroCols]]), componentsDistArray[:, nonZeroCols]]
print((Latex.listToRow(dateStrList)))
print((Latex.array2DToRows(componentsDistArray.T, precision)))
print("\n\nDistribution of component sizes in configuration graphs")
configComponentsDistArray = configComponentsDistArray[:, 0:configComponentsDist.shape[0]]
nonZeroCols = numpy.sum(configComponentsDistArray, 0)!=0
configComponentsDistArray = numpy.r_[numpy.array([numpy.arange(configComponentsDistArray.shape[1])[nonZeroCols]]), configComponentsDistArray[:, nonZeroCols]]
print((Latex.listToRow(dateStrList)))
print((Latex.array2DToRows(configComponentsDistArray.T, precision)))
print("\n\nDistribution of triangle participations")
triangleDistArray = triangleDistArray[:, 0:triangleDist.shape[0]]
nonZeroCols = numpy.sum(triangleDistArray, 0)!=0
triangleDistArray = numpy.r_[numpy.array([numpy.arange(triangleDistArray.shape[1])[nonZeroCols]])/2, triangleDistArray[:, nonZeroCols]]
print((Latex.listToRow(dateStrList)))
print((Latex.array2DToRows(triangleDistArray.T, precision)))
configTriangleDistArray = configTriangleDistArray[:, 0:configTriangleDist.shape[0]]
nonZeroCols = numpy.sum(configTriangleDistArray, 0)!=0
configTriangleDistArray = numpy.r_[numpy.array([numpy.arange(configTriangleDistArray.shape[1])[nonZeroCols]])/2, configTriangleDistArray[:, nonZeroCols]]
configTriangleDistArray = numpy.c_[configTriangleDistArray, numpy.zeros((configTriangleDistArray.shape[0], triangleDistArray.shape[1]-configTriangleDistArray.shape[1]))]
print("\n\nDistribution of central vertices")
print((Latex.listToRow(dateStrList)))
subgraphSizes = numpy.array(maleSums + femaleSums, numpy.float)
print("Female & " + Latex.array1DToRow(femaleSums*100/subgraphSizes, 1) + "\\\\")
print("Male & " + Latex.array1DToRow(maleSums*100/subgraphSizes, 1) + "\\\\")
print("\hline")
print("Heterosexual & " + Latex.array1DToRow(heteroSums*100/subgraphSizes, 1) + "\\\\")
print("Bisexual & " + Latex.array1DToRow(biSums*100/subgraphSizes, 1) + "\\\\")
print("\hline")
print("Contact traced & " + Latex.array1DToRow(contactSums*100/subgraphSizes, 1) + "\\\\")
print("Blood donor & " + Latex.array1DToRow(donorSums*100/subgraphSizes, 1) + "\\\\")
print("RandomTest & " + Latex.array1DToRow(randomTestSums*100/subgraphSizes, 1) + "\\\\")
print("STD & " + Latex.array1DToRow(stdSums*100/subgraphSizes, 1) + "\\\\")
print("Prisoner & " + Latex.array1DToRow(prisonerSums*100/subgraphSizes, 1) + "\\\\")
print("Doctor recommendation & " + Latex.array1DToRow(recommendSums*100/subgraphSizes, 1) + "\\\\")
print("\hline")
print("Mean ages (years) & " + Latex.array1DToRow(meanAges, 2) + "\\\\")
print("\hline")
print("Holguin & " + Latex.array1DToRow(holguinSums*100/subgraphSizes, 1) + "\\\\")
print("La Habana & " + Latex.array1DToRow(habanaSums*100/subgraphSizes, 1) + "\\\\")
print("Havana City & " + Latex.array1DToRow(havanaSums*100/subgraphSizes, 1) + "\\\\")
print("Pinar del Rio & " + Latex.array1DToRow(pinarSums*100/subgraphSizes, 1) + "\\\\")
print("Sancti Spiritus & " + Latex.array1DToRow(sanctiSums*100/subgraphSizes, 1) + "\\\\")
print("Villa Clara & " + Latex.array1DToRow(villaClaraSums*100/subgraphSizes, 1) + "\\\\")
print("\hline")
print("Mean degrees & " + Latex.array1DToRow(meanDegrees, 2) + "\\\\")
print("Std degrees & " + Latex.array1DToRow(stdDegrees, 2) + "\\\\")
print("\n\nProvinces")
print(Latex.array2DToRows(provinces))
print("\n\nDegree distribution")
print(Latex.array2DToRows(degrees))
def plotScalarStats():
logging.info("Computing scalar stats")
resultsFileName = resultsDir + "ContactGrowthScalarStats.pkl"
if saveResults:
statsArray = graphStats.sequenceScalarStats(sGraph, subgraphIndicesList, slowStats)
Util.savePickle(statsArray, resultsFileName, True)
#Now compute statistics on the configuration graphs
else:
statsArray = Util.loadPickle(resultsFileName)
#Take the mean of the results over the configuration model graphs
resultsFileNameBase = resultsDir + "ConfigGraphScalarStats"
numGraphs = len(subgraphIndicesList)
#configStatsArrays = numpy.zeros((numGraphs, graphStats.getNumStats(), numConfigGraphs))
configStatsArrays = numpy.zeros((numGraphs, graphStats.getNumStats()-2, numConfigGraphs))
for j in range(numConfigGraphs):
resultsFileName = resultsFileNameBase + str(j)
configStatsArrays[:, :, j] = Util.loadPickle(resultsFileName)
configStatsArray = numpy.mean(configStatsArrays, 2)
configStatsStd = numpy.std(configStatsArrays, 2)
global plotInd
def plotRealConfigError(index, styleReal, styleConfig, realLabel, configLabel):
plt.hold(True)
plt.plot(absDayList, statsArray[:, index], styleReal, label=realLabel)
#errors = numpy.c_[configStatsArray[:, index]-configStatsMinArray[:, index] , configStatsMaxArray[:, index]-configStatsArray[:, index]].T
errors = numpy.c_[configStatsStd[:, index], configStatsStd[:, index]].T
plt.plot(absDayList, configStatsArray[:, index], styleConfig, label=configLabel)
plt.errorbar(absDayList, configStatsArray[:, index], errors, linewidth=0, elinewidth=1, label="_nolegend_", ecolor="red")
xmin, xmax = plt.xlim()
plt.xlim((0, xmax))
ymin, ymax = plt.ylim()
plt.ylim((0, ymax))
#Output all the results into plots
plt.figure(plotInd)
plt.hold(True)
plotRealConfigError(graphStats.maxComponentSizeIndex, plotStyleBW[0], plotStyles4[0], "Max comp. vertices", "CM max comp. vertices")
plotRealConfigError(graphStats.maxComponentEdgesIndex, plotStyleBW[1], plotStyles4[1], "Max comp. edges", "CM max comp. edges")
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("No. vertices/edges")
plt.legend(loc="upper left")
plt.savefig(figureDir + "MaxComponentSizeGrowth.eps")
plotInd += 1
for k in range(len(dayList)):
day = dayList[k]
print(str(DateUtils.getDateStrFromDay(day, startYear)) + ": " + str(statsArray[k, graphStats.maxComponentEdgesIndex]))
#print(str(DateUtils.getDateStrFromDay(day, startYear)) + ": " + str(configStatsArray[k, graphStats.numComponentsIndex]))
plt.figure(plotInd)
plotRealConfigError(graphStats.numComponentsIndex, plotStyleBW[0], plotStyles4[0], "Size >= 1", "CM size >= 1")
plotRealConfigError(graphStats.numNonSingletonComponentsIndex, plotStyleBW[1], plotStyles4[1], "Size >= 2", "CM size >= 2")
plotRealConfigError(graphStats.numTriOrMoreComponentsIndex, plotStyleBW[2], plotStyles4[2], "Size >= 3", "CM size >= 3")
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("No. components")
plt.legend(loc="upper left")
plt.savefig(figureDir + "NumComponentsGrowth.eps")
plotInd += 1
plt.figure(plotInd)
plotRealConfigError(graphStats.meanComponentSizeIndex, plotStyleBW[0], plotStyles4[0], "Real graph", "CM")
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("Mean component size")
plt.legend(loc="lower right")
plt.savefig(figureDir + "MeanComponentSizeGrowth.eps")
plotInd += 1
plt.figure(plotInd)
plotRealConfigError(graphStats.diameterIndex, plotStyleBW[0], plotStyles4[0], "Real graph", "CM")
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("Max component diameter")
plt.legend(loc="lower right")
plt.savefig(figureDir + "MaxComponentDiameterGrowth.eps")
plotInd += 1
plt.figure(plotInd)
plotRealConfigError(graphStats.effectiveDiameterIndex, plotStyleBW[0], plotStyles4[0], "Real graph", "CM")
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("Effective diameter")
plt.legend(loc="lower right")
plt.savefig(figureDir + "MaxComponentEffDiameterGrowth.eps")
plotInd += 1
plt.figure(plotInd)
plotRealConfigError(graphStats.meanDegreeIndex, plotStyleBW[0], plotStyles4[0], "All vertices", "CM all vertices")
plotRealConfigError(graphStats.maxCompMeanDegreeIndex, plotStyleBW[1], plotStyles4[1], "Max component", "CM max component")
#plt.plot(absDayList, statsArray[:, graphStats.meanDegreeIndex], plotStyleBW[0], absDayList, statsArray[:, graphStats.maxCompMeanDegreeIndex], plotStyleBW[1], absDayList, configStatsArray[:, graphStats.meanDegreeIndex], plotStyles4[0], absDayList, configStatsArray[:, graphStats.maxCompMeanDegreeIndex], plotStyles4[1])
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("Mean degree")
plt.legend(loc="lower right")
plt.savefig(figureDir + "MeanDegrees.eps")
plotInd += 1
plt.figure(plotInd)
plotRealConfigError(graphStats.densityIndex, plotStyleBW[0], plotStyles4[0], "Real Graph", "Config Model")
#plt.plot(absDayList, statsArray[:, graphStats.densityIndex], plotStyleBW[0], absDayList, configStatsArray[:, graphStats.densityIndex], plotStyles4[0])
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("Density")
plt.legend()
plt.savefig(figureDir + "DensityGrowth.eps")
plotInd += 1
plt.figure(plotInd)
plt.plot(absDayList, statsArray[:, graphStats.powerLawIndex], plotStyleBW[0])
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("Alpha")
plt.savefig(figureDir + "PowerLawGrowth.eps")
plotInd += 1
plt.figure(plotInd)
plotRealConfigError(graphStats.geodesicDistanceIndex, plotStyleBW[0], plotStyles4[0], "Real Graph", "Config Model")
#plt.plot(absDayList, statsArray[:, graphStats.geodesicDistanceIndex], plotStyleBW[0], absDayList, configStatsArray[:, graphStats.geodesicDistanceIndex], plotStyles4[0])
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("Geodesic distance")
plt.legend(loc="lower right")
plt.savefig(figureDir + "GeodesicGrowth.eps")
plotInd += 1
plt.figure(plotInd)
plotRealConfigError(graphStats.harmonicGeoDistanceIndex, plotStyleBW[0], plotStyles4[0], "Real Graph", "Config Model")
#plt.plot(absDayList, statsArray[:, graphStats.harmonicGeoDistanceIndex], plotStyleBW[0], absDayList, configStatsArray[:, graphStats.harmonicGeoDistanceIndex], plotStyles4[0])
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("Mean harmonic geodesic distance")
plt.legend(loc="upper right")
plt.savefig(figureDir + "HarmonicGeodesicGrowth.eps")
plotInd += 1
#print(statsArray[:, graphStats.harmonicGeoDistanceIndex])
plt.figure(plotInd)
plotRealConfigError(graphStats.geodesicDistMaxCompIndex, plotStyleBW[0], plotStyles4[0], "Real graph", "Config model")
#plt.plot(absDayList, statsArray[:, graphStats.geodesicDistMaxCompIndex], plotStyleBW[0], absDayList, configStatsArray[:, graphStats.geodesicDistMaxCompIndex], plotStyles4[0])
plt.xticks(locs, labels)
plt.xlabel("Year")
plt.ylabel("Max component mean geodesic distance")
plt.legend(loc="lower right")
plt.savefig(figureDir + "MaxCompGeodesicGrowth.eps")
plotInd += 1
#Find the number of edges in the infection graph
resultsFileName = resultsDir + "InfectGrowthScalarStats.pkl"
infectStatsArray = Util.loadPickle(resultsFileName)
#Make sure we don't include 0 in the array
vertexIndex = numpy.argmax(statsArray[:, graphStats.numVerticesIndex] > 0)
edgeIndex = numpy.argmax(infectStatsArray[:, graphStats.numEdgesIndex] > 0)
minIndex = numpy.maximum(vertexIndex, edgeIndex)
plt.figure(plotInd)
plt.plot(numpy.log(statsArray[minIndex:, graphStats.numVerticesIndex]), numpy.log(statsArray[minIndex:, graphStats.numEdgesIndex]), plotStyleBW[0])
plt.plot(numpy.log(infectStatsArray[minIndex:, graphStats.numVerticesIndex]), numpy.log(infectStatsArray[minIndex:, graphStats.numEdgesIndex]), plotStyleBW[1])
plt.plot(numpy.log(statsArray[minIndex:, graphStats.maxComponentSizeIndex]), numpy.log(statsArray[minIndex:, graphStats.maxComponentEdgesIndex]), plotStyleBW[2])
plt.xlabel("log(|V|)")
plt.ylabel("log(|E|)/log(|D|)")
plt.legend(("Contact graph", "Infection graph", "Max component"), loc="upper left")
plt.savefig(figureDir + "LogVerticesEdgesGrowth.eps")
plotInd += 1
results = statsArray[:, graphStats.effectiveDiameterIndex]
results = numpy.c_[results, configStatsArray[:, graphStats.effectiveDiameterIndex]]
results = numpy.c_[results, statsArray[:, graphStats.geodesicDistMaxCompIndex]]
results = numpy.c_[results, configStatsArray[:, graphStats.geodesicDistMaxCompIndex]]
configStatsArray
print("\n\n")
print(Latex.listToRow(["Diameter", "CM Diameter", "Mean Geodesic", "CM Mean Geodesic"]))
print("\\hline")
for i in range(0, len(dayList), 4):
day = dayList[i]
print(str(DateUtils.getDateStrFromDay(day, startYear)) + " & " + Latex.array1DToRow(results[i, :]) + "\\\\")
