def greedyMC2(lists, itemList, trainList, n):
"""
A method to greedily select a subset of the outputLists such that
the average precision is maximised
"""
currentListsInds = range(len(lists))
newListsInds = []
currentAvPrecision = 0
lastAvPrecision = -0.1
while currentAvPrecision - lastAvPrecision > 0:
lastAvPrecision = currentAvPrecision
averagePrecisions = numpy.zeros(len(currentListsInds))
for i, j in enumerate(currentListsInds):
newListsInds.append(j)
newLists = []
for k in newListsInds:
newLists.append(lists[k])
rankAggregate, scores = RankAggregator.MC2(newLists, itemList)
averagePrecisions[i] = Evaluator.averagePrecisionFromLists(trainList, rankAggregate[0:n], n)
newListsInds.remove(j)
j = numpy.argmax(averagePrecisions)
currentAvPrecision = averagePrecisions[j]
if currentAvPrecision > lastAvPrecision:
newListsInds.append(currentListsInds.pop(j))
return newListsInds
for item in outputList:
if item not in testExpertMatchesInds:
newTrainOutputList.append(item)
if item not in trainExpertMatchesInds:
newTestOutputList.append(item)
trainOutputLists.append(newTrainOutputList)
testOutputLists.append(newTestOutputList)
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])
"""
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)):
precisions[i, j] = Evaluator.precisionFromIndLists(testExpertMatchesInds, outputLists[j][0:n])
for j in range(len(outputLists)):
averagePrecisions[j] = Evaluator.averagePrecisionFromLists(testExpertMatchesInds, outputLists[j][0:averagePrecisionN], averagePrecisionN)
precisions2 = numpy.c_[numpy.array(ns), precisions]
logging.debug(Latex.listToRow(methodNames))
logging.debug("Computing Precision")
logging.debug(Latex.array2DToRows(precisions2))
logging.debug("Computing Average Precision")
logging.debug(Latex.array1DToRow(averagePrecisions))
#fermer le fichier
fich.close()
logging.debug("All done!")
