def mainOptions(options, convertFunction=lambda x: x):
try:
#options.saveFile = getSaveFilename(options)
filename = combineConfigs(options.saveFile, options, convertFunction)
targetData = getFilename(options.targetBase, options.student, TRAIN)
if (options.numSource == 0) or not (options.useSource):
sourceData = []
else:
sourceData = [
getFilename(options.sourceBase, s, TRAIN)
for s in options.otherStudents
]
# run the cmd
print 'save config will be at', options.saveConfigFilename
cmd = [
'bin/%s/trainClassifier' % getArch(), filename, options.saveFile,
targetData
] + sourceData
if options.fracSourceData is not None:
cmd += ['--fracSourceData', str(options.fracSourceData)]
if options.debug:
print ' '.join(cmd)
if options.catchOutput:
p = subprocess.Popen(cmd, stdout=subprocess.PIPE)
output, error = p.communicate()
else:
subprocess.check_call(cmd)
finally:
if not (options.debug):
try:
os.remove(filename)
except:
pass
if options.catchOutput:
return output, error
def main(targetDir,sourceDir,inPrefix,outPrefix,studentInd,origNumSource):
#sourceDir = 'data/dt/perturbed-noop0.1-50000'
#targetDir = 'data/dt/perturbed-noop0.1-1000'
inFilename = inPrefix + '-%s.desc'
outDesc = outPrefix + '-%s.desc'
outTree = outPrefix + '-%s.weka'
studentFile = 'data/newStudents29.txt'
factor = origNumSource / (4 * 50000.0)
students = getUniqueStudents(studentFile)
#maxLength = 0
for i,student in enumerate(students):
if (studentInd is not None) and (i != studentInd):
continue
filename = os.path.join(targetDir,'desc',inFilename % student)
#print student
res = parseDesc(filename)
#print res
if res is None:
print >>sys.stderr,'SKIPPING',student
continue
#maxLength = max(maxLength,len(res))
cmd = ['bin/%s/boostWeights' % getArch(),student,targetDir,sourceDir]
for k,v in res.iteritems():
cmd += [k,str(v * factor)]
#print ' '.join(cmd)
outDescPath = os.path.join(targetDir,'desc',outDesc % student)
outTreePath = os.path.join(targetDir,'weighted',outTree % student)
subprocess.check_call(cmd,stdout=open(outDescPath,'w'))
extractTree(outDescPath,outTreePath)
def mainOptions(options, convertFunction=lambda x: x):
try:
# options.saveFile = getSaveFilename(options)
filename = combineConfigs(options.saveFile, options, convertFunction)
targetData = getFilename(options.targetBase, options.student, TRAIN)
if (options.numSource == 0) or not (options.useSource):
sourceData = []
else:
sourceData = [getFilename(options.sourceBase, s, TRAIN) for s in options.otherStudents]
# run the cmd
print "save config will be at", options.saveConfigFilename
cmd = ["bin/%s/trainClassifier" % getArch(), filename, options.saveFile, targetData] + sourceData
if options.fracSourceData is not None:
cmd += ["--fracSourceData", str(options.fracSourceData)]
if options.debug:
print " ".join(cmd)
if options.catchOutput:
p = subprocess.Popen(cmd, stdout=subprocess.PIPE)
output, error = p.communicate()
else:
subprocess.check_call(cmd)
finally:
if not (options.debug):
try:
os.remove(filename)
except:
pass
if options.catchOutput:
return output, error
def main(targetDir, sourceDir, inPrefix, outPrefix, studentInd, origNumSource):
#sourceDir = 'data/dt/perturbed-noop0.1-50000'
#targetDir = 'data/dt/perturbed-noop0.1-1000'
inFilename = inPrefix + '-%s.desc'
outDesc = outPrefix + '-%s.desc'
outTree = outPrefix + '-%s.weka'
studentFile = 'data/newStudents29.txt'
factor = origNumSource / (4 * 50000.0)
students = getUniqueStudents(studentFile)
#maxLength = 0
for i, student in enumerate(students):
if (studentInd is not None) and (i != studentInd):
continue
filename = os.path.join(targetDir, 'desc', inFilename % student)
#print student
res = parseDesc(filename)
#print res
if res is None:
print >> sys.stderr, 'SKIPPING', student
continue
#maxLength = max(maxLength,len(res))
cmd = [
'bin/%s/boostWeights' % getArch(), student, targetDir, sourceDir
]
for k, v in res.iteritems():
cmd += [k, str(v * factor)]
#print ' '.join(cmd)
outDescPath = os.path.join(targetDir, 'desc', outDesc % student)
outTreePath = os.path.join(targetDir, 'weighted', outTree % student)
subprocess.check_call(cmd, stdout=open(outDescPath, 'w'))
extractTree(outDescPath, outTreePath)
def main(args=sys.argv[1:]):
options = parseArgs(args)
testFile = getFilename(options.testBase, options.student, TRAIN)
cmd = [
'bin/%s/runClassifier' % getArch(), options.saveConfigFilename,
testFile,
str(options.numTest), '--notrain'
]
subprocess.check_call(cmd)
def main(targetDir,sourceDir,destDir,prefix,studentInd):
students = getUniqueStudents(studentFile)
prefix = prefix + '-using%sSource' % (sourceData if sourceData > 0 else 'All')
for i,student in enumerate(students):
if (studentInd is not None) and (i != studentInd):
continue
print '-------------------'
print student
print '-------------------'
cmd = ['bin/%s/boostTest' % getArch(),student,studentFile,targetDir,sourceDir,str(sourceData)]
descFile = os.path.join(destDir,'desc',prefix + '-' + student + '.desc')
resultFile = os.path.join(destDir,'weighted',prefix + '-' + student + '.weka')
subprocess.check_call(cmd,stdout=open(descFile,'w'))
extractTree(descFile,resultFile)
def main(targetDir,sourceDir,destDir,prefix,maxNumBoosts,numTargetInstances,studentInd):
students = getUniqueStudents(studentFile)
for i,student in enumerate(students):
if (studentInd is not None) and (i != studentInd):
continue
print '-------------------'
print student
print '-------------------'
orderFile = os.path.join(destDir,'desc','combined-%s.desc' % student)
cmd = ['bin/%s/boostGivenOrder' % getArch(),student,orderFile,targetDir,sourceDir,str(maxNumBoosts),str(numTargetInstances)]
descFile = os.path.join(destDir,'desc',prefix + '-' + student + '.desc')
resultFile = os.path.join(destDir,'weighted',prefix + '-' + student + '.weka')
subprocess.check_call(cmd,stdout=open(descFile,'w'))
extractTree(descFile,resultFile)
def main(targetDir,sourceDir,destDir,numTargetInstances,jobInd):
students = getUniqueStudents(studentFile)
i = -1
for targetStudent in students:
for sourceStudent in students:
if (targetStudent == sourceStudent):
continue
i += 1
if (jobInd is not None) and (i != jobInd):
continue
print targetStudent, sourceStudent
cmd = ['bin/%s/boostIndependent' % getArch(),targetStudent,sourceStudent,targetDir,sourceDir,str(numTargetInstances)]
descFile = os.path.join(destDir,'boostIndependent',targetStudent + '-' + sourceStudent + '.desc')
subprocess.check_call(cmd,stdout=open(descFile,'w'))
def main(targetDir, sourceDir, destDir, prefix, studentInd):
students = getUniqueStudents(studentFile)
prefix = prefix + '-using%sSource' % (sourceData
if sourceData > 0 else 'All')
for i, student in enumerate(students):
if (studentInd is not None) and (i != studentInd):
continue
print '-------------------'
print student
print '-------------------'
cmd = [
'bin/%s/boostTest' % getArch(), student, studentFile, targetDir,
sourceDir,
str(sourceData)
]
descFile = os.path.join(destDir, 'desc',
prefix + '-' + student + '.desc')
resultFile = os.path.join(destDir, 'weighted',
prefix + '-' + student + '.weka')
subprocess.check_call(cmd, stdout=open(descFile, 'w'))
extractTree(descFile, resultFile)
def main(targetDir, sourceDir, destDir, prefix, maxNumBoosts,
numTargetInstances, studentInd):
students = getUniqueStudents(studentFile)
for i, student in enumerate(students):
if (studentInd is not None) and (i != studentInd):
continue
print '-------------------'
print student
print '-------------------'
orderFile = os.path.join(destDir, 'desc', 'combined-%s.desc' % student)
cmd = [
'bin/%s/boostGivenOrder' % getArch(), student, orderFile,
targetDir, sourceDir,
str(maxNumBoosts),
str(numTargetInstances)
]
descFile = os.path.join(destDir, 'desc',
prefix + '-' + student + '.desc')
resultFile = os.path.join(destDir, 'weighted',
prefix + '-' + student + '.weka')
subprocess.check_call(cmd, stdout=open(descFile, 'w'))
extractTree(descFile, resultFile)
def buildDT(dataFile,outFile,options,randomTree):
if randomTree:
raise ValueError('cannot handle randomTrees here')
cmd = [os.path.join('bin',str(getArch()),'buildDT'),dataFile] + options
subprocess.check_call(cmd,stdout=open(outFile,'w'))
def weightTree(inFile,dataFile,outFile):
cmd = [os.path.join('bin',str(getArch()),'addWeights'),inFile,dataFile]
subprocess.check_call(cmd,stdout=open(outFile,'w'))
def buildDT(dataFile, outFile, options, randomTree):
if randomTree:
raise ValueError('cannot handle randomTrees here')
cmd = [os.path.join('bin', str(getArch()), 'buildDT'), dataFile] + options
subprocess.check_call(cmd, stdout=open(outFile, 'w'))
def weightTree(inFile, dataFile, outFile):
cmd = [os.path.join('bin', str(getArch()), 'addWeights'), inFile, dataFile]
subprocess.check_call(cmd, stdout=open(outFile, 'w'))
def main(args = sys.argv[1:]): options = parseArgs(args) testFile = getFilename(options.testBase,options.student,TRAIN) cmd = ['bin/%s/runClassifier' % getArch(),options.saveConfigFilename,testFile,str(options.numTest),'--notrain'] subprocess.check_call(cmd)
