def customInit(self, initVars):
self.sample = initVars['sample']
self.sampleTree = initVars['sampleTree']
self.config = initVars['config']
self.addBranch(self.branchName)
self.addBranch("weightF")
self.addBranch("weightXS")
if not self.sample.isData():
self.weightString = self.config.get('Weights', 'weightF')
# per sample special weight
if self.config.has_option('Weights', 'useSpecialWeight') and eval(
self.config.get('Weights', 'useSpecialWeight')):
specialweight = self.sample.specialweight
self.weightString = "(({weight})*({specialweight}))".format(
weight=self.weightString, specialweight=specialweight)
print("INFO: use specialweight: {specialweight}".format(
specialweight=specialweight))
self.evalCut = self.config.get('Cuts', 'EvalCut')
self.sampleTree.addFormula(self.weightString)
self.sampleTree.addFormula(self.evalCut)
self.excludeTrainingSet = False
# to compute the correct scale to cross-section, all trees of the sample have to be used!
sampleTreeForCount = SampleTree(
{
'sample': self.sample,
'folder': initVars['pathIN']
},
config=self.config)
self.weightScaleToXS = sampleTreeForCount.getScale(
self.sample) * (2.0 if self.excludeTrainingSet else 1.0)
print "scale:", self.weightScaleToXS, self.sample
def getTree(self):
# if it has already been checked if tree is cached, then use this result dierctly
isCached = self.isCachedChecked
if not isCached:
isCached = self.isCached()
if isCached:
self.sampleTree = SampleTree(self.cachedFileNames,
config=self.config)
self.sampleTree.sampleIdentifier = self.sampleIdentifier
return self.sampleTree
def __init__(self, sample, cutList='1', branches=None, inputFolder=None, tmpFolder=None, outputFolder=None, chunkNumber=-1, splitFilesChunks=-1, splitFilesChunkSize=-1, debug=False, fileList=None, cutSequenceMode='AND', name='', config=None, fileLocator=None):
self.config = config
self.fileLocator = fileLocator if fileLocator is not None else FileLocator(config=self.config)
self.debug = debug or ('XBBDEBUG' in os.environ)
# SAMPLE
if isinstance(sample, Sample):
# sample passed as Sample object
# count number of chunks the cached data is split into
defaultChunkSize = int(config.get('General', 'mergeCachingSize')) if config.has_option('General', 'mergeCachingSize') else 100
splitFilesChunkSize = sample.mergeCachingSize if sample.mergeCachingSize > 0 else defaultChunkSize
splitFilesChunks = SampleTree({'name': sample.identifier, 'folder': inputFolder}, countOnly=True, splitFilesChunkSize=splitFilesChunkSize, config=config, verbose=self.debug, fileLocator=self.fileLocator).getNumberOfParts()
# if sample passed as object, it can be a 'subsample' and habe different name and identifier
self.sample = sample.name
self.sampleIdentifier = sample.identifier
if self.debug:
print ("INFO: use sample=", sample.name, " #parts = ", splitFilesChunks)
else:
# sample identifier passed as string
self.sample = sample
self.sampleIdentifier = sample
self.name = name
# CUTS
self.cutList = cutList
self.cutSequenceMode = cutSequenceMode
self.minCut = SampleTree.findMinimumCut(self.cutList, cutSequenceMode=self.cutSequenceMode)
# PATHS
self.inputFolder = inputFolder
self.outputFolder = (config.get('Directories', 'tmpSamples') if config else 'cache/') if outputFolder is None else outputFolder
self.tmpFolder = (config.get('Directories', 'scratch') if config else 'tmp/') if tmpFolder is None else tmpFolder
self.cachedFileNames = []
self.tmpFiles = []
self.outputFileNameFormat = '{outputFolder}/tmp_{hash}_{part}of{parts}.root'
# BRANCHES and chunk information
self.branches = branches
self.branchesForHash = None # for now make hash independent of selecte branches
self.hash = Hash(sample=sample, minCut=self.minCut, branches=self.branchesForHash, splitFilesChunkSize=splitFilesChunkSize, debug=False, inputPath=self.inputFolder).get()
self.chunkNumber = chunkNumber
self.splitFilesChunks = splitFilesChunks if splitFilesChunks > 1 else 1
self.splitFilesChunkSize = splitFilesChunkSize
# identifier is just used as an arbitrary name for print-out
cutUsedForIdentifier = (self.minCut if len(self.minCut) < 60 else self.minCut[0:50] + '...').replace(' ', '')
self.identifier = '{sample}[{cut}]of{parts}'.format(sample=self.sample, cut=cutUsedForIdentifier, parts=self.splitFilesChunks)
self.sampleTree = None
self.isCachedChecked = False
self.createFolders()
def getTree(self, chunkSize=-1, chunkNumber=-1):
# if it has already been checked if tree is cached, then use this result dierctly
isCached = self.isCachedChecked
if not isCached:
isCached = self.isCached()
if isCached:
if chunkSize > 0 and chunkNumber > 0:
fileNames = self.cachedFileNames[(chunkNumber-1)*chunkSize:chunkNumber*chunkSize]
elif chunkSize < 0 and chunkNumber < 0:
fileNames = self.cachedFileNames
else:
raise Exception("InvalidParameters")
self.sampleTree = SampleTree(self.cachedFileNames, config=self.config, fileNamesToProcess=fileNames)
self.sampleTree.sampleIdentifier = self.sampleIdentifier
# check if even though all files exist, they couldn't be accessed for some reason
# and therefore the tree would be incomplete
if not self.sampleTree.isCompleteTree():
raise Exception("IncompleteTree")
return self.sampleTree
#print(config.get('Weights','weightF'))
#config = XbbConfigReader.read('Zvv2017')
inputFile = 'root://t3dcachedb03.psi.ch:1094//pnfs/psi.ch/cms/trivcat/store/user/berger_p2/VHbb/VHbbPostNano2017/V5/Zvv/rerun/v4j/eval/ggZH_HToBB_ZToNuNu_M125_13TeV_powheg_pythia8/tree_aa5e971734ef4e885512748d534e6937ff03dc61feed21b6772ba943_000000_000000_0000_9_a6c5a52b56e5e0c7ad5aec31429c8926bf32cf39adbe087f05cfb323.root'
path = 'root://t3dcachedb03.psi.ch:1094//pnfs/psi.ch/cms/trivcat/store/user/berger_p2/VHbb/VHbbPostNano2017/V5/Zvv/rerun/v4j/eval/'
samplefiles = '../samples/VHbbPostNano2017_V5/merged_Zvv2017/'
samplesinfo = 'Zvv2017config/samples_nosplit.ini'
info = ParseInfo(samples_path=path, config=config)
sample = [
x for x in info
if x.identifier == 'ggZH_HToBB_ZToNuNu_M125_13TeV_powheg_pythia8'
][0]
# read sample
sampleTree = SampleTree([inputFile], config=config)
# initialize module
w = WeightAsBranch()
w.customInit({
'sampleTree': sampleTree,
'config': config,
'sample': sample,
'pathIN': path
})
#addAsBranch = True
addAsBranch = False
print 'w.getBranches()', w.getBranches()
if __name__ == '__main__':
config = XbbConfigReader.read('Wlv2017')
info = ParseInfo(config=config)
sample = [
x for x in info
if x.identifier == 'WplusH_HToBB_WToLNu_M125_13TeV_powheg_pythia8'
][0]
# read sample
sampleTree = SampleTree([
'/store/group/phys_higgs/hbb/ntuples/VHbbPostNano/2017/V11/WplusH_HToBB_WToLNu_M125_13TeV_powheg_pythia8/adewit-crab_nano2017_WplusH_HT81/190606_065851/0000/tree_1.root'
],
treeName='Events',
xrootdRedirector="root://eoscms.cern.ch/")
# initialize module
w = JetSmearer("2017")
w.customInit({
'sampleTree': sampleTree,
'sample': sample,
'config': config
})
n = 0
#for event in sampleTree:
# w.processEvent(event)
# n=n+1
# if n==3: break
# print("Processed {0} events in {1:.2f} seconds, {2:.2f} ev/s".format(self.nEvent, tot_time, self.nEvent/tot_time))
if __name__ == '__main__':
config = XbbConfigReader.read('Zvv2018')
info = ParseInfo(config=config)
sample = [
x for x in info
if x.identifier == 'ZH_HToBB_ZToNuNu_M125_13TeV_powheg_pythia8'
][0]
#sampleTree = SampleTree(['/store/group/phys_higgs/hbb/ntuples/VHbbPostNano/2018/V12/ZH_HToBB_ZToNuNu_M125_13TeV_powheg_pythia8/RunIIAutumn18NanoAODv6-Nano25O133/200221_205457/0000/tree_1.root'], treeName='Events', xrootdRedirector="root://eoscms.cern.ch/")
sampleTree = SampleTree([
'/store/group/phys_higgs/hbb/ntuples/VHbbPostNano/2018/V13/ZH_HToBB_ZToNuNu_M125_13TeV_powheg_pythia8/RunIIAutumn18NanoAODv7-Nano02A85/200519_095652/0000/tree_1.root'
],
treeName='Events',
xrootdRedirector="root://eoscms.cern.ch/")
w = JECcorrelator("2018")
w.customInit({
'sampleTree': sampleTree,
'sample': sample,
'config': config
})
sampleTree.addOutputBranches(w.getBranches())
histograms = {}
for jec in w.JEC_reduced:
histograms[jec] = {}
for var in [
"Jet_pt", "Jet_mass", "MET_pt", "MET_phi", "FatJet_pt",
