def trainCGandEM(distInit, accumulate, ps = d.getDefaultParamSpec(), createAccEM = d.getDefaultCreateAcc(), estimateTotAux = d.getDefaultEstimateTotAux(), iterations = 5, length = -50, afterEst = None, verbosity = 0):
"""Re-estimates a distribution using conjugate gradients and EM.
See the note in the docstring for this module for information on how the
log likelihood is scaled. This scaling is presumed to have only a small
impact on the dist returned by this function (via its impact on trainCG).
"""
assert iterations >= 1
dist = distInit
for it in range(1, iterations + 1):
if verbosity >= 1:
print 'trainCGandEM: starting it =', it, 'of CG and EM'
dist = (timed(trainCG) if verbosity >= 2 else trainCG)(dist, accumulate, ps = ps, length = length, verbosity = verbosity)
dist, _, _, _ = expectationMaximization(dist, accumulate, createAcc = createAccEM, estimateTotAux = estimateTotAux, verbosity = verbosity)
if afterEst is not None:
afterEst(dist = dist, it = it)
if verbosity >= 1:
print 'trainCGandEM: finished it =', it, 'of CG and EM'
print 'trainCGandEM:'
return dist
def addLayers(self, stateInit, questionGroups):
"""Computes all remaining layers of the decision tree."""
splitInfoDict = dict()
state = stateInit
while True:
addLayer = self.addLayer
if self.verbosity >= 3:
addLayer = timed(addLayer)
state, splitInfoDictMore = addLayer(state, questionGroups)
splitInfoDict.update(splitInfoDictMore)
if self.verbosity >= 2:
print 'cluster: added %s nodes' % len(splitInfoDictMore)
if not splitInfoDictMore:
break
return splitInfoDict
def addLayers(self, stateInit, questionGroups):
"""Computes all remaining layers of the decision tree."""
splitInfoDict = dict()
state = stateInit
while True:
addLayer = self.addLayer
if self.verbosity >= 3:
addLayer = timed(addLayer)
state, splitInfoDictMore = addLayer(state, questionGroups)
splitInfoDict.update(splitInfoDictMore)
if self.verbosity >= 2:
print 'cluster: added %s nodes' % len(splitInfoDictMore)
if not splitInfoDictMore:
break
return splitInfoDict
def decisionTreeClusterDepthBased(clusteringSpec, labels, labelledAccChunks,
createAcc):
verbosity = clusteringSpec.verbosity
accSummer1 = DepthBasedFirstLevelAccSummer(labelledAccChunks, createAcc)
accSummer2 = SecondLevelAccSummer(createAcc)
minCount = clusteringSpec.minCount
leafEstimator = LeafEstimator(
clusteringSpec.estimateTotAux,
catchEstimationErrors=clusteringSpec.catchEstimationErrors)
def getProtoRoot():
return leafEstimator.est(accSummer1.all())
if verbosity >= 3:
getProtoRoot = timed(getProtoRoot)
protoRoot = getProtoRoot()
splitValuer = clusteringSpec.utilitySpec(protoRoot.dist,
protoRoot.count,
verbosity=verbosity)
clusterer = DepthBasedClusterer(accSummer1,
accSummer2,
minCount,
leafEstimator,
splitValuer,
clusteringSpec.goodThresh,
verbosity=verbosity)
if verbosity >= 1:
print(
'cluster: decision tree clustering with perLeafPenalty = %s and'
' minCount = %s' % (splitValuer.perLeafPenalty, minCount))
questionGroups = removeTrivialQuestions(labels,
clusteringSpec.questionGroups)
stateInit = clusterer.getInitialState(labels, protoRoot)
splitInfoDict = clusterer.addLayers(stateInit, questionGroups)
dist, (aux, auxRat) = constructTree(splitInfoDict)
if verbosity >= 1:
countRoot = protoRoot.count
# (FIXME : leaf computation relies on specific form of dist)
print 'cluster: %s leaves' % len(dist.dist.distDict)
print('cluster: aux root = %s (%s) -> aux tree = %s (%s) (%s count)' %
(protoRoot.aux / countRoot, d.Rat.toString(protoRoot.auxRat),
aux / countRoot, d.Rat.toString(auxRat), countRoot))
return dist
def subTreeSplitInfoIter(self, stateInit):
agenda = [stateInit]
while agenda:
state = agenda.pop()
labels, questionGroups, answerSeq, protoNoSplit = state
if self.verbosity >= 2:
self.printNodeInfo(state)
if self.verbosity >= 3:
indent = ' ' + ''.join([('| ' if answer != 0 else ' ')
for answer in answerSeq])
computeBestSplit = timed(
self.computeBestSplitAndStateAdj,
msg='cluster:%schoose and perform split took' % indent)
else:
computeBestSplit = self.computeBestSplitAndStateAdj
splitInfo, stateAdj = computeBestSplit(state)
nextStates = self.getNextStates(stateAdj, splitInfo)
agenda.extend(reversed(nextStates))
yield answerSeq, splitInfo
def subTreeSplitInfoIter(self, stateInit):
agenda = [stateInit]
while agenda:
state = agenda.pop()
labels, questionGroups, answerSeq, protoNoSplit = state
if self.verbosity >= 2:
self.printNodeInfo(state)
if self.verbosity >= 3:
indent = ' '+''.join([ ('| ' if answer != 0 else ' ')
for answer in answerSeq ])
computeBestSplit = timed(
self.computeBestSplitAndStateAdj,
msg = 'cluster:%schoose and perform split took' % indent
)
else:
computeBestSplit = self.computeBestSplitAndStateAdj
splitInfo, stateAdj = computeBestSplit(state)
nextStates = self.getNextStates(stateAdj, splitInfo)
agenda.extend(reversed(nextStates))
yield answerSeq, splitInfo
def decisionTreeClusterDepthBased(clusteringSpec, labels, labelledAccChunks,
createAcc):
verbosity = clusteringSpec.verbosity
accSummer1 = DepthBasedFirstLevelAccSummer(labelledAccChunks, createAcc)
accSummer2 = SecondLevelAccSummer(createAcc)
minCount = clusteringSpec.minCount
leafEstimator = LeafEstimator(
clusteringSpec.estimateTotAux,
catchEstimationErrors = clusteringSpec.catchEstimationErrors
)
def getProtoRoot():
return leafEstimator.est(accSummer1.all())
if verbosity >= 3:
getProtoRoot = timed(getProtoRoot)
protoRoot = getProtoRoot()
splitValuer = clusteringSpec.utilitySpec(protoRoot.dist, protoRoot.count,
verbosity = verbosity)
clusterer = DepthBasedClusterer(accSummer1, accSummer2, minCount,
leafEstimator, splitValuer,
clusteringSpec.goodThresh,
verbosity = verbosity)
if verbosity >= 1:
print ('cluster: decision tree clustering with perLeafPenalty = %s and'
' minCount = %s' %
(splitValuer.perLeafPenalty, minCount))
questionGroups = removeTrivialQuestions(labels,
clusteringSpec.questionGroups)
stateInit = clusterer.getInitialState(labels, protoRoot)
splitInfoDict = clusterer.addLayers(stateInit, questionGroups)
dist, (aux, auxRat) = constructTree(splitInfoDict)
if verbosity >= 1:
countRoot = protoRoot.count
# (FIXME : leaf computation relies on specific form of dist)
print 'cluster: %s leaves' % len(dist.dist.distDict)
print ('cluster: aux root = %s (%s) -> aux tree = %s (%s) (%s count)' %
(protoRoot.aux / countRoot, d.Rat.toString(protoRoot.auxRat),
aux / countRoot, d.Rat.toString(auxRat),
countRoot))
return dist
def trainCGandEM(distInit,
accumulate,
ps=d.getDefaultParamSpec(),
createAccEM=d.getDefaultCreateAcc(),
estimateTotAux=d.getDefaultEstimateTotAux(),
iterations=5,
length=-50,
afterEst=None,
verbosity=0):
"""Re-estimates a distribution using conjugate gradients and EM.
See the note in the docstring for this module for information on how the
log likelihood is scaled. This scaling is presumed to have only a small
impact on the dist returned by this function (via its impact on trainCG).
"""
assert iterations >= 1
dist = distInit
for it in range(1, iterations + 1):
if verbosity >= 1:
print 'trainCGandEM: starting it =', it, 'of CG and EM'
dist = (timed(trainCG) if verbosity >= 2 else trainCG)(
dist, accumulate, ps=ps, length=length, verbosity=verbosity)
dist, _, _, _ = expectationMaximization(dist,
accumulate,
createAcc=createAccEM,
estimateTotAux=estimateTotAux,
verbosity=verbosity)
if afterEst is not None:
afterEst(dist=dist, it=it)
if verbosity >= 1:
print 'trainCGandEM: finished it =', it, 'of CG and EM'
print 'trainCGandEM:'
return dist
def synthComplete(self, dist, uttIds, method, synthOutDir, exptTag, afterSynth=None, verbosity=1):
synthAcousticSeqIo = feat.AcousticSeqIo(
synthOutDir,
[vsio.VecSeqIo(stream.order) for stream in self.streams],
["%s.%s" % (exptTag, stream.name) for stream in self.streams],
[stream.encoder for stream in self.streams],
)
if verbosity >= 1:
print "synth: synthesizing to", synthOutDir, "with tag", exptTag
for uttId in uttIds:
synthOutput = self.synth(dist, uttId, method)
if afterSynth is not None:
afterSynth(synthOutput=synthOutput, uttId=uttId, exptTag=exptTag)
synthAcousticSeqIo.writeFiles(uttId, synthOutput)
(timed(feat.doHtsDemoWaveformGeneration) if verbosity >= 1 else feat.doHtsDemoWaveformGeneration)(
self.scriptsDir,
synthOutDir,
basenames=[uttId + "." + exptTag for uttId in uttIds],
logFile=os.path.join(synthOutDir, exptTag + ".log"),
)