printPrecisions = False
printDocuments = True
numpy.set_printoptions(suppress=True, precision=3, linewidth=100)
dataset = ArnetMinerDataset(runLSI=ranLSI)
#dataset.fields = ["Intelligent Agents"]
if printDocuments:
print("Reading article data")
authorList, documentList, citationList = dataset.readAuthorsAndDocuments(useAbstract=False)
print("Done")
ns = numpy.arange(5, 55, 5)
bestaverageTestPrecisions = numpy.zeros(len(dataset.fields))
computeInfluence = True
graphRanker = GraphRanker(k=100, numRuns=100, computeInfluence=computeInfluence, p=0.05, inputRanking=[1, 2])
methodNames = graphRanker.getNames()
methodNames.append("MC2")
numMethods = len(methodNames)
averageTrainPrecisions = numpy.zeros((len(dataset.fields), len(ns), numMethods))
averageTestPrecisions = numpy.zeros((len(dataset.fields), len(ns), numMethods))
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"
testExpertMatchesInds = authorIndexer.translate(testExpertMatches)
relevantAuthorInds1 = authorIndexer.translate(relAuthorsDocSimilarity)
relevantAuthorInds2 = authorIndexer.translate(relAuthorsDocCitations)
relevantAuthorsInds = authorIndexer.translate(relevantAuthors)
expertAuthorsInds = authorIndexer1.translate(expertAuthors)#Get Ids our BM25 List
assert (numpy.array(relevantAuthorInds1) < len(relevantAuthorsInds)).all()
assert (numpy.array(relevantAuthorInds2) < len(relevantAuthorsInds)).all()
if len(testExpertMatches) != 0:
fich.write(field)
fich.write("\n")
#First compute graph properties
computeInfluence = False
#graphRanker = GraphRanker(k=100, numRuns=100, computeInfluence=computeInfluence, p=0.05, inputRanking=[relevantAuthorInds1, relevantAuthorInds2])
graphRanker = GraphRanker(k=100, numRuns=100, computeInfluence=computeInfluence, p=0.05, inputRanking=None)
outputLists = graphRanker.vertexRankings(graph, relevantAuthorsInds)
for line in outputLists:
ListeAuthorsFinale = authorIndexer.reverseTranslate(line)
#fich.write(' '.join(map(str, ListeAuthorsFinale)))
fich.write(str(ListeAuthorsFinale)+"\n")
outputListsE = []
#outputListsE.append(expertAuthorsInds)#Add BM25 Listto the outputList in order to aggregate scores later
for line in outputListsE:
ListeAuthorsFinale = authorIndexer1.reverseTranslate(line)
#fich.write(' '.join(map(str, ListeAuthorsFinale)))
fich.write(str(ListeAuthorsFinale)+"\n")
#Save relevant authors
#numpy.save(dataset.dataDir + "relevantAuthorsReputation" + field + ".txt", outputLists)
fich.write("-----------------------------------------------")
