besttau = tau
bestwfa = copy.deepcopy(wfa)
elif score < bestscore and abs(score-1000)<0.1:
bestscore = score
besttau = tau
bestwfa = copy.deepcopy(wfa)
print "Tau: ",tau, " Score: ", score
avruntime += wfa.buildtime
nummodelsmade += 1
if metric == "WER":
bestscore = bestwfa.get_WER(testdata)
iohelpers.write_results(RESULTS_DIR+"co-"+wfatype+"-"+str(maxbasissize)+"-pautomac="+problem+"-"+metric+".txt", problem, wfatype+", "+"tau= "+str(besttau)+", basis size="+str(len(basisdict)), metric, bestscore, avruntime/float(nummodelsmade))
if probabilistic:
iohelpers.write_pnfa_model(MODEL_DIR+"co-"+wfatype+"-"+str(maxbasissize)+"-pautomac="+problem+"-"+metric+".fsm", bestwfa)
else:
RESULTS_DIR = "/home/williamleif/Dropbox/icml2014-experiments/results/real/"
if problem == "tree":
traindata = iohelpers.parse_file("/home/williamleif/Dropbox/icml2014-experiments/datasets/treebankdata.obs")
validdata = traindata[0:5000]
testdata = traindata[5000:10000]
traindata = traindata[10000:len(traindata)]
wfa = MomentInitEmWFA(dimension, n_symbols, MODELPATH+modelfile)
wfa.fit(PAUTOMACPATH+problem+".pautomac.em")
wer = wfa.wer
kl = wfa.kl
else:
traindata = iohelpers.parse_file("/home/williamleif/Dropbox/icml2014-experiments/datasets/treebankdata.obs")
validdata = traindata[0:5000]
testdata = traindata[5000:10000]
traindata = traindata[10000:len(traindata)]
fp = open("treetemp.obs", "w")
fp.write("\n".join([" ".join([str(j) for j in i]) for i in traindata]))
fp.close()
wfa = MomentInitEmWFA(dimension, n_symbols, MODELPATH+modelfile)
wfa.realfit("treetemp.obs",validdata)
kl = wfa.kl
wer = wfa.bestwfa.get_WER(testdata)
print "KL: ", kl, " WER: ", wer
iohelpers.write_results(RESULTS_DIR+"em"+modelfile, problem, "size= "+str(dimension), "KL,WER", str(kl)+", "+str(wer), wfa.buildtime)
if bestsize == 0:
bestwfa = copy.deepcopy(wfa)
bestsize = i
elif score < bestscore or math.isnan(bestscore):
bestscore = score
bestsize = i
avruntime += wfa.buildtime
nummodelsmade += 1
print "Model size: ", i, " Score: ", score
if metric == "WER":
wfa.resize(traindata,i,substring)
bestscore = wfa.get_WER(testdata)
iohelpers.write_results(RESULTS_DIR+"spectral-"+esttype+"-pautomac="+problem+"-"+metric+".txt", problem, esttype+", "+"size= "+str(bestsize)+", basis size="+str(basislength), metric, bestscore, avruntime/float(nummodelsmade))
else:
RESULTS_DIR = "/home/williamleif/Dropbox/icml2014-experiments/results/real/"
if problem == "tree":
traindata = iohelpers.parse_file("/home/williamleif/Dropbox/icml2014-experiments/datasets/treebankdata.obs")
validdata = traindata[0:5000]
testdata = traindata[5000:10000]
traindata = traindata[10000:len(traindata)]
if substring:
basisdict = hankelmatrixcreator.top_k_basis(traindata,maxbasissize,n_symbols, 4)
basislength = len(basisdict)
else:
if not success:
break
if metric == "WER":
score = wfa.get_WER(validdata)
else:
score = wfa.get_perplexity(validdata)
if bestsize == 0:
bestscore = score
bestsize = i
bestwfa = copy.deepcopy(wfa)
elif score < bestscore and abs(score-1000) > 0.1:
bestscore = score
bestsize = i
bestwfa = copy.deepcopy(wfa)
print "Model size: ", i, " Score: ", score
avruntime += wfa.buildtime
nummodelsmade += 1
if metric == "WER":
bestscore = bestwfa.get_WER(testdata)
else:
bestscore = bestwfa.get_perplexity(testdata)
iohelpers.write_results(RESULTS_DIR+"tensor-"+metric+".txt", problem,"size= "+str(bestsize)+", basis size="+str(basislength), metric, bestscore, 0)
iohelpers.write_pnfa_model(MODEL_DIR+"tensor-"+str(bestsize)+"-pautomac="+problem+"-"+metric+".fsm", bestwfa)
klsize = i
wersize = i
else:
if kl < bestkl:
bestkl = kl
klsize = i
if wer < bestwer:
bestwer = wer
wersize = i
avruntime += wfa.buildtime
nummodelsmade += 1
print "Model size: ", i, " KL: ", kl, " WER: ", wer
iohelpers.write_results(RESULTS_DIR+"em-pautomac="+problem+".txt", problem, "KL size:"+str(klsize)+" WER size: "+str(wersize)+" 30 KL: "+str(thirtykl)+" 30 WER: "+str(thirtywer), "KL, WER", str(bestkl)+","+str(bestwer), avruntime/float(nummodelsmade))
else:
if problem == "tree":
traindata = iohelpers.parse_file("/home/williamleif/Dropbox/icml2014-experiments/datasets/treebankdata.obs")
validdata = traindata[0:5000]
testdata = traindata[5000:10000]
traindata = traindata[10000:len(traindata)]
fp = open("treetemp.obs", "w")
fp.write("\n".join([" ".join([str(j) for j in i]) for i in traindata]))
fp.close()
avruntime = 0
nummodelsmade = 0
