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
# random pairwise constraints and watch to see our
# NMI increase
import pickle
import EM
import cData
import sys
if len(sys.argv) < 2:
print "provide filename and optionally a filename for the pickle of centers"
exit(1)
# use the same code for getting initial points as baturay did
D = cData.cData(sys.argv[1])
D.setType("2", "random")
EmAlg = EM.cEM(D)
EmAlg.EM(len(D.classlist))
EmAlg.bPPC = True
#Creates clusters depending on what EM guessed.
D.createClusters(EmAlg)
#Finds the outerpoints and the midpoints and assigns them in emclusters.
D.repPoints(EmAlg)
#This makes the algorithm start with good initial points.
EmAlg = D.goodInitial(EmAlg)
print "pickling starting position to: ",
picklefname = "pickles/"+sys.argv[1].split('/')[-1]+".pickle"
if len(sys.argv) > 2:
picklefname = sys.argv[2]
f = open(picklefname,"w")
l = EmAlg.lCenters
def run():
D = cData.cData("data/winenorm3_pyre.csv")
E = EM.cEM(D)
E.EM(3)
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)
