def testGreedyMC2(self):
list1 = [2, 1, 3, 4, 5, 0]
list2 = [3, 2, 5, 0, 4, 1]
list3 = [3, 4, 2, 5, 1, 0]
list4 = [3, 4, 5, 0, 1, 2]
lists = [list1, list2, list3, list4]
itemList = [0, 1, 2, 3, 4, 5]
topQList = [3, 4, 5]
n = 3
print("Running test")
outputInds = RankAggregator.greedyMC2(lists, itemList, topQList, n)
print("Done")
self.assertEquals(outputInds, [3])
list1 = [2, 1, 3, 4, 5, 0]
list2 = [3, 2, 5, 4, 0, 1]
list3 = [4, 3, 2, 5, 1, 0]
list4 = [3, 4, 0, 5, 1, 2]
lists = [list1, list2, list3, list4]
outputInds = RankAggregator.greedyMC2(lists, itemList, topQList, n)
newLists = []
for ind in outputInds:
newLists.append(lists[ind])
outputList, scores = RankAggregator.MC2(newLists, itemList)
self.assertEquals(outputList[0:3], [3, 4, 5])
def testBorda(self):
list1 = [5, 4, 3, 2, 1, 0]
list2 = [5, 4, 3, 2, 1, 0]
outList = RankAggregator.borda(list1, list2)
nptst.assert_array_equal(outList, numpy.array([5,4,3,2,1,0]))
list2 = [4, 3, 2, 5, 1, 0]
outList = RankAggregator.borda(list1, list2)
nptst.assert_array_equal(outList, numpy.array([4,5,3,2,1,0]))
def testSpearmanFootrule(self):
list1 = [5, 4, 3, 2, 1, 0]
list2 = [5, 4, 3, 2, 1, 0]
dist = RankAggregator.spearmanFootrule(list1, list2)
self.assertEquals(dist, 0)
list2 = [5, 4, 3, 2, 0, 1]
dist = RankAggregator.spearmanFootrule(list1, list2)
self.assertEquals(dist, 1.0/9)
list2 = [0, 1, 2, 3, 4, 5]
dist = RankAggregator.spearmanFootrule(list1, list2)
self.assertEquals(dist, 1.0)
def testSupervisedMC22(self):
list1 = [2, 1, 3, 4, 5, 0]
list2 = [3, 2, 5, 0, 4, 1]
list3 = [3, 4, 2, 5, 1, 0]
list4 = [5, 0, 3, 4, 1, 2]
lists = [list1, list2, list3, list4]
itemList = [0, 1, 2, 3, 4, 5]
topQList = [5, 4, 3, 2, 1, 0]
outputList, scores = RankAggregator.supervisedMC22(lists, itemList, topQList)
for i, n in enumerate(ns):
for j, trainOutputList in enumerate(trainOutputLists):
testOutputList = testOutputLists[j]
trainPrecisions[i, j] = Evaluator.precisionFromIndLists(trainExpertMatchesInds, trainOutputList[0:n])
testPrecisions[i, j] = Evaluator.precisionFromIndLists(testExpertMatchesInds, testOutputList[0:n])
averageTrainPrecisions[s, i, j] = Evaluator.averagePrecisionFromLists(trainExpertMatchesInds, trainOutputList[0:n], n)
averageTestPrecisions[s, i, j] = Evaluator.averagePrecisionFromLists(testExpertMatchesInds, testOutputList[0:n], n)
#Now look at rank aggregations
relevantItems = set([])
for trainOutputList in trainOutputLists:
relevantItems = relevantItems.union(trainOutputList)
relevantItems = list(relevantItems)
listInds = RankAggregator.greedyMC2(trainOutputLists, relevantItems, trainExpertMatchesInds, 20)
newOutputList = []
for listInd in listInds:
newOutputList.append(testOutputLists[listInd])
"""
newOutputList = []
newOutputList.append(testOutputLists[0])
newOutputList.append(testOutputLists[1])
newOutputList.append(testOutputLists[2])
newOutputList.append(testOutputLists[3])
#newOutputList.append(testOutputLists[4])
newOutputList.append(testOutputLists[5])
#newOutputList.append(testOutputLists[6])
"""
#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("-----------------------------------------------")
#for line in outputLists:
#fich.write(line[i])
#Ajout du score de l'expertise
#outputLists.append(expertAuthorsInds)
itemList = RankAggregator.generateItemList(outputLists)
methodNames = graphRanker.getNames()
if runLSI:
outputFilename = dataset.getOutputFieldDir(field) + "outputListsLSI.npz"
else:
outputFilename = dataset.getOutputFieldDir(field) + "outputListsLDA.npz"
Util.savePickle([outputLists, trainExpertMatchesInds, testExpertMatchesInds], outputFilename, debug=True)
numMethods = len(outputLists)
precisions = numpy.zeros((len(ns), numMethods))
averagePrecisions = numpy.zeros(numMethods)
for i, n in enumerate(ns):
for j in range(len(outputLists)):