def main():
# Takes in the file and parses into datum's.
D = cData(sys.argv[1])
# Starting points from the pickle or not.
EmAlg = parseCommandLine(D, sys.argv)
prevCons = 0
totalcons = 0
nmiResult = evaluateEM_NMI(D, EmAlg)
print "Initial nmi: ",nmiResult
consobj = Cons.cCons(D)
for numCons in range(1,len(D.data)/4,1):
consobj.constype = Cons.cCons.eConsType.TripCenterChunk
consobj.centerChunkSize = 0.2
cons = consobj.tripCons(EmAlg.mGammas,numCons-prevCons)
prevCons = numCons
totalcons += len(cons)
for i in cons:
EmAlg.mCij[i[0]][i[1]] = i[2]
EmAlg.mCij[i[1]][i[0]] = i[2]
EmAlg.EM(len(D.classlist))
nmiresult = evaluateEM_NMI(D, EmAlg)
print numCons, ",", nmiresult, ",", totalcons
if(nmiresult > 0.999 or len(D.data)==numCons):
break
def scenario1(D, sFileStub):
f = open(sFileStub + ".scen1.results", "w")
EMResults = []
for iOutertrial in range(numOuterTrials):
f.write("outertrial: %d\n" % iOutertrial)
f.write("likelihood,NMI\n")
bestEM = []
bestLikelihood = 0
for iRestart in range(numInnerTrials):
EMAlg = EM.cEM(D)
EMAlg.bPPC = False
EMAlg.EM(len(D.classlist))
if iRestart == 0 or EMAlg.dEMLikelihood > bestLikelihood:
bestLikelihood = EMAlg.dEMLikelihood
bestEM = EMAlg
EMResults.append(bestEM)
f.write("%f,%f\n" % (bestLikelihood,
utils.evaluateEM_NMI(D, EMAlg) ) )
f.flush()
f.close()
return EMResults
def TripConsTest(D, sNum, EMStarts, fp):
fp.write("trips,queries,cons,likelihood,NMI\n")
for option in TripConsOptions.lOptions:
optname = TripConsOptions.lOptionNames[option]
fp.write(optname + "\n")
for iOutertrial in range(numOuterTrials):
print "scenario ", sNum, " options ", optname, " outertrial ", iOutertrial
fp.write("outertrial: %d\n" % iOutertrial)
em = copy.deepcopy(EMStarts[iOutertrial])
em.bPPC = True
prevTrips = 0
totalCons = 0
nmiResult = utils.evaluateEM_NMI(D, em)
fp.write("Initial nmi: %f\n" % nmiResult)
consobj = Cons.cCons(D)
for numTrips in range(1,len(D.data)/4,1):
if option == TripConsOptions.CenterChunkCons:
consobj.constype = Cons.cCons.eConsType.TripCenterChunk
elif option == TripConsOptions.MidCons:
consobj.constype = Cons.cCons.eConsType.TripMids
print em.mLikelihood_il
cons = consobj.tripCons(em.mGammas,numTrips-prevTrips)
prevTrips = numTrips
totalCons += len(cons)
for i in cons:
em.mCij[i[0]][i[1]] = i[2]
em.mCij[i[1]][i[0]] = i[2]
em.EM(len(D.classlist))
nmiresult = utils.evaluateEM_NMI(D, em)
fp.write("%d,%d,%d,%f,%f\n" % (numTrips,
numTrips*14,
totalCons,
em.dEMLikelihood,
nmiresult) )
fp.flush()
if (nmiresult > 0.999 or len(D.data)==numTrips):
break
def goodInitial (self,D,em,emclusters,RepPts,fp):
# Consistent means all the midpoints are same with the center.
constraints = []
iters = 0
indEMClusters = range(len(emclusters))
lResetExclusions = []
numUserQueries = 0
for cl in emclusters:
print ([D.data[i.index].cl for i in cl.midpoints],D.data[cl.center.index].cl)," ",cl.center.index
while len(indEMClusters) != 0 and iters < 5:
resetCenters = []
for ind in indEMClusters[:]:
cl = emclusters[ind]
if(len(cl.midpoints) <= 1):
resetCenters.append(ind)
continue
# simulate feedback from real classes
realpoints = [D.data[i.index] for i in cl.midpoints]
realcenter = D.data[cl.center.index]
numUserQueries += len(realpoints) + 1
# points in realpoints s.t. their real class is same as center
rightclass = filter(lambda x: x.cl==realcenter.cl,realpoints)
rightclass.append(realcenter)
wrongclass = filter(lambda x: x.cl!=realcenter.cl,realpoints)
# All the leftovers...
if len(wrongclass) == 0:
indEMClusters.remove(ind)
lResetExclusions.extend( [x.index for x in rightclass] )
else:
resetCenters.append(ind)
# Cross constraints between right and wrong classes.
for i in rightclass:
for j in realpoints:
if j in wrongclass:
constraints.append([i.index,j.index,-2])
elif j!= i:
constraints.append([i.index,j.index,2])
for i in constraints:
em.mCij[i[0]][i[1]] = i[2]
em.mCij[i[1]][i[0]] = i[2]
# If all classes are not right, restart.
em.resetSomeCenters(em.lInitialCenters,resetCenters,lResetExclusions)
em.EM(len(emclusters))
emclusters = RepPts.createClusters(em)
RepPts.repPoints(em, emclusters)
print "goodInitial iter nmi: ", evaluateEM_NMI(D,em)," ",iters
iters += 1
# queries,cons,likelihood,NMI
maybeWrite(fp,
"%d,%d,%f,%f\n" % (numUserQueries,
len(constraints),
em.dEMLikelihood,
evaluateEM_NMI(D,em) ) )
print indEMClusters
for cl in emclusters:
print ([D.data[i.index].cl for i in cl.midpoints],D.data[cl.center.index].cl)," ",cl.center.index
return em
import numpy
import EM
import cData
import utils
# run EM several times and get the likelihood
for iRestart in range(20):
D = cData.cData("data/winenorm3_pyre.csv")
# D = cData.cData("data/normvert.csv")
M = EM.cEM(D)
M.bPPC = False
M.EM(3)
print M.dEMLikelihood,
print " nmi: ",
print utils.evaluateEM_NMI(D, M)
