print("inputList line is not properly formatted:", line)
exit(-3)
conf = GetInitializedCrabConfig() # create fresh crab config
dataset = split[0]
nUnits = int(split[1]) # also used for total lumis for data
nUnitsPerJob = int(
split[2]) # used for files/dataset for MC and LS per data
(
datasetTag,
datasetName,
primaryDatasetName,
secondaryDatasetName,
isData,
) = utils.GetOutputDatasetTagAndModifiedDatasetName(dataset)
outputFile = utils.GetOutputFilename(dataset, not isData)
conf.Data.outputDatasetTag = datasetTag
conf.Data.inputDataset = dataset
print
print("Consider dataset {0}".format(dataset))
if not isData:
conf.Data.splitting = "FileBased"
else:
conf.Data.splitting = "LumiBased"
# get era
# see, for example: https://twiki.cern.ch/twiki/bin/viewauth/CMS/PdmVAnalysisSummaryTable
# secondaryDatasetName looks like 'Run2015D-PromptReco-v3'
if "Summer16" in secondaryDatasetName or "Run2016" in secondaryDatasetName:
year = 2016
keepAndDrop = "keepAndDrop.txt"
## LQ2
elif analysis == "LQ2" :
preselection = "Muon_pt[0] > 40"
keepAndDrop = "keepAndDrop.txt"
## HH
elif analysis == "HH" :
preselection="(Muon_pt[0]>16 && Muon_pt[1]>7 && nJet>2 && Jet_pt[0]>17 && Jet_pt[1]>17) || (Electron_pt[0]>22 && Electron_pt[1]>11 && nJet>2 && Jet_pt[0]>17 && Jet_pt[1]>17)"
keepAndDrop = "keepAndDrop_hh.txt"
else :
print "ERROR: Did not understand the analysis to run! Should be one of LQ1, LQ2, HH. Quitting."
exit(-1)
# for crab
haddFileName = utils.GetOutputFilename(dataset, isMC)
p = PostProcessor(
".",
inputFiles(),
cut=preselection,
outputbranchsel=keepAndDrop,
modules=modulesToRun,
provenance=True,
fwkJobReport=True,
jsonInput=runsAndLumis(),
haddFileName=haddFileName,
)
# interactive testing
# p=PostProcessor(".",utils.GetFileList(''),cut=preselection,outputbranchsel=keepAndDrop,modules=modulesToRun,provenance=True,fwkJobReport=True,jsonInput=runsAndLumis(),haddFileName=haddFileName)
p.run()
#config.Data.outLFNDirBase = '/store/group/phys_exotica/leptonsPlusJets/RootNtuple/RunII/%s/' % (getUsernameFromSiteDB())
config.Data.outLFNDirBase = '/store/group/phys_exotica/leptonsPlusJets/LQ/scooper/2016nanoPostProc/'
config.Data.publication = False
config.Data.outputDatasetTag = 'NanoPostDYJIncAMCNLO'
config.section_("JobType")
config.JobType.pluginName = 'Analysis'
config.JobType.psetName = 'PSet.py'
#config.JobType.pyCfgParams = ['dataset='+config.Data.inputDataset]
config.JobType.scriptExe = 'crab_script.sh'
config.JobType.scriptArgs = ['dataset=' + config.Data.inputDataset]
config.JobType.inputFiles = [
'keepAndDrop.txt', 'utils.py', 'doSkim_stockNanoV5.py',
cmsswBaseDir + '/src/PhysicsTools/NanoAODTools/scripts/haddnano.py'
] #hadd nano will not be needed once nano tools are in cmssw
config.JobType.outputFiles = [
utils.GetOutputFilename(config.Data.inputDataset, True)
]
config.JobType.sendPythonFolder = True
config.section_("Site")
config.Site.storageSite = "T2_CH_CERN"
# this will make sure jobs only run on sites which host the data.
# See: https://twiki.cern.ch/twiki/bin/view/CMSPublic/CRAB3FAQ#What_is_glideinWms_Overflow_and
config.section_("Debug")
config.Debug.extraJDL = ['+CMS_ALLOW_OVERFLOW=False']
#config.section_("User")
#config.User.voGroup = 'dcms'