def testAveragePrecisionFromLists(self):
predList = [4, 2, 10]
testList = [4, 2, 15, 16]
self.assertEquals(Evaluator.averagePrecisionFromLists(testList, predList), 0.5)
predList = [0,1,2,3,4,5]
testList = [0, 3, 4, 5]
self.assertAlmostEquals(Evaluator.averagePrecisionFromLists(testList, predList), 0.691666666666)
def testAveragePrecisionFromLists(self):
predList = [4, 2, 10]
testList = [4, 2, 15, 16]
self.assertEquals(
Evaluator.averagePrecisionFromLists(testList, predList), 0.5)
predList = [0, 1, 2, 3, 4, 5]
testList = [0, 3, 4, 5]
self.assertAlmostEquals(
Evaluator.averagePrecisionFromLists(testList, predList),
0.691666666666)
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
outputLists = graphRanker.vertexRankings(graph, relevantAuthorsInds)
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)):
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(Latex.array2DToRows(precisions2))
logging.debug(Latex.array1DToRow(averagePrecisions))
logging.debug("All done!")
