def findPairwiseDistance(featureFile, outFile):
featMan = FeatureManager()
featMan.readFeatures(featureFile)
featDict = featMan.featureDict
oFile = open(outFile, 'w')
ids = featDict.keys()
keys = sorted(ids)
print len(keys), keys[-5:]
for i in range(0, len(keys) - 1):
qid1, qf1 = featMan.returnFeature(keys[i])
for j in range(i + 1, len(keys)):
qid2, qf2 = featMan.returnFeature(keys[j])
qcos, ucos, userCos, sessionCos, ngramCos, entCos, \
catCos,typeCos = qf1.findCosineDistance(qf2)
qjac = qf1.findJacardDistance(qf2)
#qedit = qf1.findEditDistance(qf2)
edgeScore = (15*((qcos + qjac )/2.0) +\
12.5*ngramCos + 12.5*ucos + 20*sessionCos +\
20*userCos + 10*((entCos + catCos)/2.0) + 10*typeCos)/100.0
if edgeScore > 0.0:
oFile.write(
#str(qid1) + ' ' + str(qid2) + ' ' + str(round(edgeScore, 3)) + '\n')
featMan.returnQuery(qid1) + '\t' + featMan.returnQuery(qid2) + '\t' + str(round(edgeScore, 3)) + '\n')
#oFile1.write(str(qid1)+'\t'+str(qid2)+'\t'+\
#str(round(qcos,2))+'\t'+str(round(qjac,2))+'\t'+\
#str(round(ngramCos,2))+'\t'+str(round(userCos,2))+'\t' + \
#str(round(entCos,2))+'\t'+ str(round(catCos,2))+\
#'\t'+ str(round(sessionCos,2))+'\t'+ str(round(typeCos,2))+'\n')
oFile.close()
edgeScore = 1.0 - weightMatrix[qid2][qid1]
if edgeScore > threshold:
qcc.addEdge(qid1, qid2, edgeScore)
except:
pass
else:
print 'Query feature error ', session[i]
sessCount += 1
labels = qcc.getTaskComponents()
fname = args.outDir + '_'+args.algo+'_' + str(threshold) + '.txt'
outFile = open(fname, 'w')
for entry in labels:
string = ''
for qid in entry:
string += featMan.returnQuery(qid) + '\t'
outFile.write(string.strip() + '\n')
outFile.close()
predicted_same_pairs, predicted_different_pairs=\
getPairLabelsFromClusters(labels,featMan)
metrics[threshold] = getRecallPrecision(samePairsSet, differentPairsSet, predicted_same_pairs, predicted_different_pairs)
for tcount, met in metrics.items():
print tcount, met
mergeMetrics(total_metrics_dict, metrics)
computeAverageAndVarianceOfMetrics(args.algo, total_metrics_dict)
#qcos, ucos, userCos, sessionCos, ngramCos, entCos, \
#catCos,typeCos = qf1.findCosineDistance(qf2)
#qjac = qf1.findJacardDistance(qf2)
##qedit = qf1.findEditDistance(qf2)
##normalized distance
