def readFromRootFile(self,filename,TupleMeanStd, weighter):
#the first part is standard, no changes needed
from preprocessing import MeanNormApply, MeanNormZeroPad, MeanNormZeroPadParticles, ZeroPadParticles
import numpy
import ROOT
fileTimeOut(filename,120) #give eos 2 minutes to recover
rfile = ROOT.TFile(filename)
tree = rfile.Get("deepntuplizer/tree")
self.nsamples=tree.GetEntries()
#the definition of what to do with the branches
# those are the global branches (jet pt etc)
# they should be just glued to each other in one vector
# and zero padded (and mean subtracted and normalised)
#x_global = MeanNormZeroPad(filename,TupleMeanStd,
# [self.branches[0]],
# [self.branchcutoffs[0]],self.nsamples)
# the second part (the pf candidates) should be treated particle wise
# an array with (njets, nparticles, nproperties) is created
x_glb = ZeroPadParticles(filename,TupleMeanStd,
self.branches[0],
self.branchcutoffs[0],self.nsamples)
x_db = ZeroPadParticles(filename,TupleMeanStd,
self.branches[1],
self.branchcutoffs[1],self.nsamples)
x_cpf = ZeroPadParticles(filename,TupleMeanStd,
self.branches[2],
self.branchcutoffs[2],self.nsamples)
x_sv = ZeroPadParticles(filename,TupleMeanStd,
self.branches[3],
self.branchcutoffs[3],self.nsamples)
# now, some jets are removed to avoid pt and eta biases
Tuple = self.readTreeFromRootToTuple(filename)
#if self.remove:
# jets are removed until the shapes in eta and pt are the same as
# the truth class 'fj_isNonBB'
notremoves=weighter.createNotRemoveIndices(Tuple)
#undef=Tuple[self.undefTruth]
#notremoves-=undef
if self.weight:
weights=weighter.getJetWeights(Tuple)
elif self.remove:
weights=notremoves
else:
print('neither remove nor weight')
weights=numpy.empty(self.nsamples)
weights.fill(1.)
# create all collections:
#truthtuple = Tuple[self.truthclasses]
alltruth=self.reduceTruth(Tuple)
undef=numpy.sum(alltruth,axis=1)
weights=weights[undef > 0]
x_glb=x_glb[undef > 0]
x_db=x_db[undef > 0]
x_sv=x_sv[undef > 0]
x_cpf=x_cpf[undef > 0]
alltruth=alltruth[undef > 0]
if self.remove: notremoves=notremoves[undef > 0]
# remove the entries to get same jet shapes
if self.remove:
print('remove')
weights=weights[notremoves > 0]
x_glb=x_glb[notremoves > 0]
x_db=x_db[notremoves > 0]
x_sv=x_sv[notremoves > 0]
x_cpf=x_cpf[notremoves > 0]
alltruth=alltruth[notremoves > 0]
#newnsamp=x_global.shape[0]
newnsamp=x_glb.shape[0]
print('reduced content to ', int(float(newnsamp)/float(self.nsamples)*100),'%')
self.nsamples = newnsamp
# fill everything
self.w=[weights]
self.x=[x_db,x_cpf,x_sv]
self.z=[x_glb]
self.y=[alltruth]
def readFromRootFile(self,filename,TupleMeanStd, weighter):
#the first part is standard, no changes needed
from preprocessing import MeanNormApply, MeanNormZeroPad, MeanNormZeroPadParticles, ZeroPadParticles
import numpy
import ROOT
fileTimeOut(filename,120) #give eos 2 minutes to recover
rfile = ROOT.TFile(filename)
tree = rfile.Get("deepntuplizer/tree")
self.nsamples=tree.GetEntries()
x_glb = ZeroPadParticles(filename,TupleMeanStd,
self.branches[0],
self.branchcutoffs[0],self.nsamples)
x_db = MeanNormZeroPadParticles(filename,TupleMeanStd,
self.branches[1],
self.branchcutoffs[1],self.nsamples)
# now, some jets are removed to avoid pt and eta biases
Tuple = self.readTreeFromRootToTuple(filename)
#if self.remove:
# jets are removed until the shapes in eta and pt are the same as
# the truth class 'fj_isNonBB'
notremoves=weighter.createNotRemoveIndices(Tuple)
if self.weight:
weights=weighter.getJetWeights(Tuple)
elif self.remove:
weights=notremoves
else:
print('neither remove nor weight')
weights=numpy.empty(self.nsamples)
weights.fill(1.)
# create all collections:
#truthtuple = Tuple[self.truthclasses]
alltruth=self.reduceTruth(Tuple)
undef=numpy.sum(alltruth,axis=1)
weights=weights[undef > 0]
x_glb=x_glb[undef > 0]
x_db=x_db[undef > 0]
alltruth=alltruth[undef > 0]
notremoves=notremoves[undef > 0]
undef=Tuple['fj_isNonCC'] * Tuple['sample_isQCD'] * Tuple['fj_isQCD'] + Tuple['fj_isCC'] * Tuple['fj_isH']
# remove the entries to get same jet shapes
if self.remove:
print('remove')
weights=weights[notremoves > 0]
x_glb=x_glb[notremoves > 0]
x_db=x_db[notremoves > 0]
alltruth=alltruth[notremoves > 0]
newnsamp=x_glb.shape[0]
print('reduced content to ', int(float(newnsamp)/float(self.nsamples)*100),'%')
self.nsamples = newnsamp
# fill everything
self.w=[weights]
self.x=[x_db]
self.z=[x_glb]
self.y=[alltruth]