def gen(self, args):
genFeats = featureManager.loadJson(config.getGenInFeatFilename(args))
genFeat = genFeats[0]
scoreName = genFeat['name']
scoreFeats = genFeat['scoreFeats']
#wrap genFeats in [] to match data structure in train
lines = self.formatLineDirect([genFeat])
#logging.printDebug(lines)
allLines = map(lambda l: "0 " + l, lines)
#logging.printDebug(allLines)
#TODO: collect filenames
SVMGenInputFilename = self.getGenInputFilename(args)
with open(SVMGenInputFilename, 'w') as f:
f.writelines(map(lambda x:x+"\n", allLines))
for featName in config.perfFeatsList:
cmd = [self.genBinPath]
cmd.append(SVMGenInputFilename)
singleModelFilename= self.getSingleModelFilename(args, featName)
cmd.append(singleModelFilename)
perfFeatFilename= self.getGenOutputFilename(args, featName)
cmd.append(perfFeatFilename)
#logging.printDebug(" ".join(cmd))
subprocess.call(" ".join(cmd), shell=True)
#TODO: read all perfFeatFilename, transform to dict and return
perfFeats = {}
for featName in config.perfFeatsList:
#TODO: put all filename definition in one place
#perfFeatFilename= self.getGenOutputFilename(args, featName)
with open(perfFeatFilename, 'r') as f:
lines = f.readlines()
#dequantize
q = quantizer.getQuantizerObj(self.getQuantizeFilename(args, featName))
realVals= q.dequantize(lines)
#feat = map(float, lines)
perfFeats[featName]=realVals
#logging.printDebug(perfFeats)
return featureManager.formatFeatFile(scoreName, {}, perfFeats)
def gen(self, args):
genFeats = featureManager.loadJson(config.getGenInFeatFilename(args))
genFeat = genFeats[0]
scoreName = genFeat['name']
scoreFeats = genFeat['scoreFeats']
#wrap genFeats in [] to match data structure in train
lines = self.formatLineDirect([genFeat])
#logging.printDebug(lines)
allLines = map(lambda l: "0 " + l, lines)
#logging.printDebug(allLines)
#TODO: collect filenames
SVMGenInputFilename = self.getGenInputFilename(args)
with open(SVMGenInputFilename, 'w') as f:
f.writelines(map(lambda x: x + "\n", allLines))
for featName in config.perfFeatsList:
cmd = [self.genBinPath]
cmd.append(SVMGenInputFilename)
singleModelFilename = self.getSingleModelFilename(args, featName)
cmd.append(singleModelFilename)
perfFeatFilename = self.getGenOutputFilename(args, featName)
cmd.append(perfFeatFilename)
#logging.printDebug(" ".join(cmd))
subprocess.call(" ".join(cmd), shell=True)
#TODO: read all perfFeatFilename, transform to dict and return
perfFeats = {}
for featName in config.perfFeatsList:
#TODO: put all filename definition in one place
#perfFeatFilename= self.getGenOutputFilename(args, featName)
with open(perfFeatFilename, 'r') as f:
lines = f.readlines()
#dequantize
q = quantizer.getQuantizerObj(
self.getQuantizeFilename(args, featName))
realVals = q.dequantize(lines)
#feat = map(float, lines)
perfFeats[featName] = realVals
#logging.printDebug(perfFeats)
return featureManager.formatFeatFile(scoreName, {}, perfFeats)
def train(self, args):
#ex filenames:
# trainFeat.json -> [quantizer] -> <perfFeatName>.train.dat
# | |
# +-> <perfFeatName>.quant |
# +-------------------------------------------------------+
# +-> [svm^hmm] -> <perfFeatName>.model.bin
trainFeats = featureManager.loadJson(
config.getTrainInFeatFilename(args))
perfFeats = collectPerfFeats(trainFeats)
#logging.printDebug(perfFeats)
#for each perfFeature, a svmFeatFilename (quantized feat for svm^hmm)
#and singleModelFilename (model file for svm^hmm) will be saved
#scoreFeatLines = self.formatLine(scoreFeats)
scoreFeatLines = self.formatLineDirect(trainFeats)
for pkey, pval in perfFeats.items():
allLines = [("# " + pkey)]
#TODO:quantize pval
q = quantizer.getQuantizerObj(self.getQuantizeFilename(args, pkey))
quantizedVal = q.quantize(pval)
lines = zip(map(str, quantizedVal), scoreFeatLines)
#logging.printDebug(lines)
allLines = map(lambda l: " ".join(l), lines)
#logging.printDebug(allLines)
svmFeatFilename = self.getTrainInputFilename(args, pkey)
with open(svmFeatFilename, 'w') as f:
f.writelines(map(lambda x: x + "\n", allLines))
cmd = [self.trainBinPath]
if (config.svmhmm_c != None):
cmd.append("-c " + str(config.svmhmm_c))
else:
cmd.append("-c 0.01")
cmd.append(svmFeatFilename)
singleModelFilename = self.getSingleModelFilename(args, pkey)
cmd.append(singleModelFilename)
#logging.printDebug(" ".join(cmd))
subprocess.call(" ".join(cmd), shell=True)
def train(self, args):
#ex filenames:
# trainFeat.json -> [quantizer] -> <perfFeatName>.train.dat
# | |
# +-> <perfFeatName>.quant |
# +-------------------------------------------------------+
# +-> [svm^hmm] -> <perfFeatName>.model.bin
trainFeats = featureManager.loadJson(config.getTrainInFeatFilename(args))
perfFeats = collectPerfFeats(trainFeats)
#logging.printDebug(perfFeats)
#for each perfFeature, a svmFeatFilename (quantized feat for svm^hmm)
#and singleModelFilename (model file for svm^hmm) will be saved
#scoreFeatLines = self.formatLine(scoreFeats)
scoreFeatLines = self.formatLineDirect(trainFeats)
for pkey, pval in perfFeats.items():
allLines = [("# " + pkey)]
#TODO:quantize pval
q = quantizer.getQuantizerObj(self.getQuantizeFilename(args, pkey))
quantizedVal = q.quantize(pval)
lines = zip(map(str, quantizedVal), scoreFeatLines)
#logging.printDebug(lines)
allLines = map(lambda l:" ".join(l), lines)
#logging.printDebug(allLines)
svmFeatFilename = self.getTrainInputFilename(args, pkey)
with open(svmFeatFilename, 'w') as f:
f.writelines(map(lambda x:x+"\n", allLines))
cmd = [self.trainBinPath]
if (config.svmhmm_c != None):
cmd.append("-c " + str(config.svmhmm_c))
else:
cmd.append("-c 0.01")
cmd.append(svmFeatFilename)
singleModelFilename = self.getSingleModelFilename(args,pkey)
cmd.append(singleModelFilename)
#logging.printDebug(" ".join(cmd))
subprocess.call(" ".join(cmd), shell=True)
