def connect_by_db_(self):
''' '''
from CMGTools.RootTools.utils.connect import connect
connect(self.MC_list,
self.tier,
self.pattern,
self.aliases,
cache=self.cache,
verbose=self.verbose)
def connect_by_pck_(self):
''' '''
from CMGTools.RootTools.utils.getFiles import getFiles
redict_aliases = dict(zip(self.aliases.values(), self.aliases.keys()))
regex = re.compile(r'(?P<sample>[a-zA-Z0-9_]+[a-zA-Z])(?:[0-9]+)$')
for alias_k, alias_v in self.mc_dict.items():
m = regex.match(alias_k)
if m and 'QCD' not in alias_k:
alias_k = m.group('sample')
if alias_k not in self.aliases.values():
continue
sample_pck = '*'.join([
'', redict_aliases[alias_k].replace('/', '').replace('.', '*'),
self.tier.replace('%', ''), self.pattern + '.pck'
])
cached_sample = glob.glob('/'.join(
[self.homedir, '.cmgdataset', sample_pck]))
single_mc_list = [alias_v]
if len(cached_sample) == 0:
print 'sample not cached yet, connecting to the DB'
from CMGTools.RootTools.utils.connect import connect
connect(single_mc_list,
self.tier,
self.pattern,
self.aliases,
cache=self.cache,
verbose=self.verbose)
elif len(cached_sample) > 1:
print 'better specify which sample, many found'
print cached_sample
raise
else:
file = open(cached_sample[0])
mycomp = pickle.load(file)
single_mc_list[0].files = getFiles(
'/'.join([''] + mycomp.lfnDir.split('/')
[mycomp.lfnDir.split('/').index('CMG') + 1:]),
mycomp.user,
self.pattern,
useCache=self.cache)
print 'attached files to %s' % (single_mc_list[0].name)
print 'files %s' % (
'/'.join(single_mc_list[0].files[0].split('/')[:-1] +
[self.pattern]))
def connect_by_pck_(self):
''' '''
from CMGTools.RootTools.utils.getFiles import getFiles
redict_aliases = dict( zip(self.aliases.values(), self.aliases.keys()) )
regex = re.compile(r'(?P<sample>[a-zA-Z0-9_]+[a-zA-Z])(?:[0-9]+)$')
for alias_k, alias_v in self.mc_dict.items():
m = regex.match(alias_k)
if m and 'QCD' not in alias_k:
alias_k = m.group('sample')
if alias_k not in self.aliases.values():
continue
sample_pck = '*'.join(['',redict_aliases[alias_k].replace('/','').replace('.','*'),
self.tier.replace('%',''),self.pattern+'.pck'])
cached_sample = glob.glob('/'.join([self.homedir,'.cmgdataset',sample_pck]))
single_mc_list = [alias_v]
if len(cached_sample) == 0:
print 'sample not cached yet, connecting to the DB'
from CMGTools.RootTools.utils.connect import connect
connect(single_mc_list, self.tier, self.pattern, self.aliases,
cache=self.cache, verbose=self.verbose)
elif len(cached_sample) >1:
print 'better specify which sample, many found'
print cached_sample
raise
else:
file = open(cached_sample[0])
mycomp = pickle.load(file)
single_mc_list[0].files = getFiles('/'.join( ['']+mycomp.lfnDir.split('/')[mycomp.lfnDir.split('/').index('CMG')+1:] ),
mycomp.user, self.pattern, useCache=self.cache)
print 'attached files to %s' %(single_mc_list[0].name)
print 'files %s' %('/'.join(single_mc_list[0].files[0].split('/')[:-1]+[self.pattern]))
aliases = {
'/DYJets.*': 'DYJets',
'/TauPlusX/Run2012A-13Jul2012.*': 'data_Run2012A',
'/TauPlusX/Run2012A-recover-06Aug2012-v1.*': 'data_Run2012A_aug6',
'/TauPlusX/Run2012B-13Jul2012.*': 'data_Run2012B',
'/TauPlusX/Run2012C-24Aug2012-v1.*': 'data_Run2012C_v1',
'/TauPlusX/Run2012C-PromptReco-v2.*': 'data_Run2012C_v2'
}
MC_list = [DYJets, WJets]
allsamples = copy.copy(MC_list)
allsamples.extend(data_list)
connect([WJets],
'/WJets%TAUMU_2012%',
'tauMu.*root',
walias,
cache=True,
verbose=False)
# connect( allsamples, '%TAUMU_2012_MuRm_SVFit_Recoil_ZtoW_C_15Oct%', 'tauMu.*root', aliases, cache=True, verbose=False)
connect(allsamples,
'%TAUMU_MuRm_OSVFit_Colin18Oct',
'tauMu.*root',
aliases,
cache=True,
verbose=False)
allsamples = []
for mc in MC_list:
mc.triggers = mc_triggers
allsamples.append(mc)
'/TauPlusX/Run2012B-22Jan2013-v1.*':'data_Run2012B',
'/TauPlusX/Run2012C-22Jan2013-v1.*':'data_Run2012C',
'/TauPlusX/Run2012D-22Jan2013-v1.*':'data_Run2012D',
}
MC_list = copy.copy( mc_ewk )
MC_list.extend( mc_higgs )
MC_list.extend( mc_diboson )
allsamples = copy.copy( MC_list )
allsamples.extend( data_list )
allsamples.extend( embed_list )
connect( allsamples, '%TAUMU_MuRm_%Colin_%Jun13', 'tauMu.*root', aliases, cache=True, verbose=False)
connect( [WJets], '%TAUMU_NewRecoil_RelTauIso_Colin_1Jul13', 'tauMu.*root',
{'/WJets.*START53.*NewRecoil.*':'WJets'}, cache=True, verbose=False)
dy_nevents = [ DYJets.nGenEvents,
DY1Jets.nGenEvents,
DY2Jets.nGenEvents,
DY3Jets.nGenEvents,
DY4Jets.nGenEvents
]
for dy in mc_dy:
dy.nevents = dy_nevents
'/DoubleMuParked/Run2012D-22Jan2013-v1':'data_Run2012D',
}
MC_list = copy.copy( mc_ewk )
MC_list.extend( mc_diboson_inc )
allsamples = copy.copy(MC_list)
allsamples.extend( data_list )
# the pattern provided to this function is a SQL pattern.
# % represents the wildcard.
# this pattern allows to select a whole group of samples.
connect( allsamples, '%CMGPF_V5_16_0', 'cmgTuple.*root', aliases, cache=True, verbose=False)
# guessing the best split factor for each component,
# to get about the same number of events in each job
for c in allsamples:
c.splitFactor = splitFactor(c, nEventsPerJob=2e5)
# picking up the json file automatically. Here, we use the dcs jsons.
for data in data_list:
if len(data.files):
data.json = jsonPick( data.files[0], jsonMap )
if __name__ == '__main__':
from CMGTools.RootTools.fwlite.Config import printComps
'/DoubleMu/StoreResults-DoubleMu_2012B_PromptReco_v1_Run193752to195135':
'embed_Run2012B_193752_195135',
'/DoubleMu/StoreResults-DoubleMu_2012B_PromptReco_v1_Run195147to196070':
'embed_Run2012B_195147_196070',
'/WW_TuneZ2star.*START52.*': 'WW',
'/WZ_TuneZ2star.*START52.*': 'WZ',
'/ZZ_TuneZ2star.*START52.*': 'ZZ'
}
MC = copy.copy(mc_ewk)
MC.extend(mc_higgs)
MC.extend(mc_diboson)
for sam in MC:
sam.triggers = mc_triggers
for data in data_list_2012:
data.triggers = data_triggers
allsamples = copy.copy(MC)
allsamples.extend(data_list_2012)
allsamples.extend(embed_list_2012)
connect(allsamples,
'%TAUMU_NewSVFit_Colin17Sep',
'tauMu.*root',
aliases,
cache=True,
verbose=False)
# this number is not in the DB (dbs says this sample is still in production)
WJets.nGenEvents = 61444940
'/DoubleMuParked/Run2012D-22Jan2013-v1': 'data_Run2012D',
}
MC_list = copy.copy(mc_ewk)
MC_list.extend(mc_diboson_inc)
allsamples = copy.copy(MC_list)
allsamples.extend(data_list)
# the pattern provided to this function is a SQL pattern.
# % represents the wildcard.
# this pattern allows to select a whole group of samples.
connect(allsamples,
'%CMGPF_V5_16_0',
'cmgTuple.*root',
aliases,
cache=True,
verbose=False)
# guessing the best split factor for each component,
# to get about the same number of events in each job
for c in allsamples:
c.splitFactor = splitFactor(c, nEventsPerJob=2e5)
# picking up the json file automatically. Here, we use the dcs jsons.
for data in data_list:
if len(data.files):
data.json = jsonPick(data.files[0], jsonMap)
if __name__ == '__main__':
from CMGTools.RootTools.fwlite.Config import printComps
'/GluGluToHToTauTau.*Phys14DR.*': 'HiggsGGH',
'/VBF_HToTauTau_M-125_13TeV-powheg-pythia6.*Phys14DR.*': 'HiggsVBF',
}
# dictionarize
mc_dict = {}
for s in mc_higgs:
mc_dict[s.name] = s
MC_list = [v for k, v in mc_dict.items()
] #[mc_dict['HiggsGGH125'], mc_dict['HiggsVBF125']]
for sam in MC_list:
# Set MC triggers
sam.triggers = mc_triggers
connect(MC_list,
'%TAUMU_MINIAOD_SVFIT25ns_steggema',
'.*root',
aliases,
cache=True,
verbose=False)
MC_list = [m for m in MC_list if m.files]
for sample in MC_list:
sample.splitFactor = splitFactor(sample, 10e4)
# JAN - temporarily use local file until we have TAUELE samples
sample.files = [
'/afs/cern.ch/user/s/steggema/work/CMSSW_7_2_3/src/CMGTools/H2TauTau/prod/tauEle_fullsel_tree_CMG.root'
]
# from CMGTools.H2TauTau.proto.samples.run2012.diboson import *
# from CMGTools.H2TauTau.proto.samples.run2012.higgs import *
from CMGTools.H2TauTau.proto.samples.run2012.triggers_tauMu import data_triggers, mc_triggers
aliases = {
'/TauPlusX/Run2012A-13Jul2012.*':'data_Run2012A',
'/TauPlusX/Run2012A-recover-06Aug2012-v1.*':'data_Run2012A_aug6',
'/TauPlusX/Run2012B-13Jul2012.*':'data_Run2012B',
'/TauPlusX/Run2012C-24Aug2012-v1.*':'data_Run2012C_v1',
'/TauPlusX/Run2012C-PromptReco-v2.*':'data_Run2012C_v2'
}
allsamples = copy.copy(data_list)
connect( allsamples, '%Run2012%PAT_CMG_V5_8_0', 'cmgTuple.*root', aliases, cache=True, verbose=False)
allsamples = []
for data in data_list:
data.json = jsonPick( data.files[0])
data.triggers = data_triggers
allsamples.append(data)
for c in allsamples:
c.splitFactor = splitFactor(c)
# for c in data_list:
# computeLumi(c, test=True)
'/W2Jets.*START53.*': 'W2Jets',
'/W3Jets.*START53.*': 'W3Jets',
'/W4Jets.*START53.*': 'W4Jets',
}
MC_list = copy.copy(mc_ewk)
MC_list.extend(mc_higgs)
MC_list.extend(mc_diboson)
allsamples = copy.copy(MC_list)
allsamples.extend(data_list)
allsamples.extend(embed_list)
connect(allsamples,
'/W%Jet%PAT_CMG_V5_14_0',
'cmgTuple.*root',
aliases,
cache=True,
verbose=False)
# this number is not in the DB (dbs says this sample is still in production)
# WJets.nGenEvents = 61444940
## for mc in MC_list:
## mc.triggers = mc_triggers
## # allsamples.append(mc)
## for data in data_list:
## if len(data.files):
## data.json = jsonPick( data.files[0], jsonMap)
## data.triggers = data_triggers
## # allsamples.append(data)
## for embed in embed_list:
from CMGTools.H2TauTau.proto.samples.phys14.higgs import *
from CMGTools.Production.getFiles import getFiles
from CMGTools.RootTools.utils.connect import connect
from CMGTools.RootTools.utils.splitFactor import splitFactor
from CMGTools.RootTools.fwlite.Config import printComps
aliases = {
'/GluGluToHToTauTau.*Phys14DR.*': 'HiggsGGH',
}
MC_list = [HiggsGGH125]
for sam in MC_list:
sam.triggers = None # No triggers yet
allsamples = copy.copy(MC_list)
connect(allsamples,
'%htt_tt_27jan15_manzoni_nom',
'miniAOD*root',
aliases,
cache=True,
verbose=False)
HiggsGGH125.files = [
# '/afs/cern.ch/work/m/manzoni/diTau2015/CMSSW_7_2_3/src/CMGTools/H2TauTau/prod/diTau_fullsel_tree_CMG_tt.root',
# '/afs/cern.ch/work/m/manzoni/diTau2015/CMSSW_7_2_3/src/CMGTools/H2TauTau/prod/muEle_fullsel_tree_CMG.root' ,
# '/afs/cern.ch/work/m/manzoni/diTau2015/CMSSW_7_2_3/src/CMGTools/H2TauTau/prod/diTau_fullsel_tree_CMG.root' ,
'/afs/cern.ch/work/m/manzoni/diTau2015/CMSSW_7_2_3/src/CMGTools/H2TauTau/prod/tauEle_fullsel_tree_CMG.root',
# '/afs/cern.ch/work/m/manzoni/diTau2015/CMSSW_7_2_3/src/CMGTools/H2TauTau/prod/tauMu_fullsel_tree_CMG.root' ,
]
'/WZJetsTo3LNu.*START42.*': 'WZJetsTo3LNu',
'/ZZJetsTo2L2Nu.*START42.*': 'ZZJetsTo2L2Nu',
'/ZZJetsTo2L2Q.*START42.*': 'ZZJetsTo2L2Q',
'/ZZJetsTo4L.*START42.*': 'ZZJetsTo4L',
}
MC_list = copy.copy(mc_ewk)
MC_list.extend(mc_higgs)
MC_list.extend(mc_diboson)
for sam in MC_list:
sam.triggers = mc_triggers
for data in data_list_2011A:
data.triggers = data_triggers_2011A
for data in data_list_2011B:
data.triggers = data_triggers_2011B
allsamples = copy.copy(MC_list)
allsamples.extend(data_list_2011)
allsamples.extend(embed_list_2011)
connect(allsamples,
'%TAUMU_2011_Colin_Oct24',
'tauMu.*root',
aliases,
cache=True,
verbose=False)
Tbar_tW.nGenEvents = 809984.
for c in allsamples:
c.splitFactor = splitFactor(c)
'/DoubleMu/StoreResults-Run2012A_22Jan2013_v1_RHembedded_trans1_tau116_ptmu1_16had1_18_v1.*':'embed_Run2012A_22Jan',
'/DoubleMuParked/StoreResults-Run2012D_22Jan2013_v1_RHembedded_trans1_tau116_ptmu1_16had1_18_v1.*':'embed_Run2012B_22Jan',
'/DoubleMuParked/StoreResults-Run2012C_22Jan2013_v1_RHembedded_trans1_tau116_ptmu1_16had1_18_v1.*':'embed_Run2012C_22Jan',
'/DoubleMuParked/StoreResults-Run2012B_22Jan2013_v1_RHembedded_trans1_tau116_ptmu1_16had1_18_v1.*':'embed_Run2012D_22Jan',
}
MC_list = copy.copy( mc_ewk )
MC_list.extend( mc_higgs )
MC_list.extend( mc_diboson )
allsamples = copy.copy( MC_list )
# allsamples.extend( data_list )
# allsamples.extend( embed_list )
connect( allsamples, '%TAUMU_SVF%_Jun13%', 'tauMu.*root', aliases, cache=True, verbose=False)
connect( data_list, '%TAUMU_SVF%_Jun21%', 'tauMu.*root', aliases, cache=True, verbose=False)
connect( embed_list, '%TAUMU_SVF%_Jul02', 'tauMu.*root', aliases, cache=True, verbose=False)
allsamples.extend( data_list )
allsamples.extend( embed_list )
# Attach number of generated events for stitching
dy_nevents = [ DYJets.nGenEvents,
DY1Jets.nGenEvents,
DY2Jets.nGenEvents,
DY3Jets.nGenEvents,
DY4Jets.nGenEvents
]
for dy in mc_dy:
'/DoubleMu/Run2011B-16Jan2012-v1/AOD/V5/PAT_CMG_V5_6_0_B$':'data_Run2011B',
'/DoubleMu/Run2011A-16Jan2012-v1/AOD/V5/PAT_CMG_V5_6_0_B$':'data_Run2011A',
'/TTJets.*START42.*/VertexWeight':'TTJets',
'/WWJetsTo2L2Nu.*START42.*/VertexWeight':'WWJetsTo2L2Nu',
'/WZJetsTo2L2Q.*START42.*/VertexWeight':'WZJetsTo2L2Q',
'/WZJetsTo3LNu.*START42.*/VertexWeight':'WZJetsTo3LNu',
'/ZZJetsTo2L2Nu.*START42.*/VertexWeight':'ZZJetsTo2L2Nu',
'/ZZJetsTo2L2Q.*START42.*/VertexWeight':'ZZJetsTo2L2Q',
'/ZZJetsTo4L.*START42.*/VertexWeight':'ZZJetsTo4L',
}
data_list = data_list_2011
MC_list = copy.copy( mc_ewk )
MC_list.extend( mc_diboson )
allsamples = copy.copy(MC_list)
allsamples.extend( data_list_2011 )
connect( allsamples, '%PAT_CMG_V5_6_0_B%', 'cmgTuple.*root', aliases, cache=True, verbose=False)
for c in allsamples:
c.splitFactor = splitFactor(c, nEventsPerJob=2e5)
for data in data_list:
if len(data.files):
data.json = jsonPick( data.files[0])
# the following for 52X sync purposes only:
MC.append(HiggsGGH125)
MC.append(HiggsVBF125)
MC.extend(mc_diboson)
MC.extend(mc_diboson_xcl)
allsamples = copy.copy(MC)
allsamples.extend(data_list_2012)
allsamples.extend(embed_list_2012)
# allsamples = copy.copy(data_list_2012)
connect(allsamples,
'%H2TauTau_tauEle_20Sep_PG_newSVFit_MVAMET',
'tauEle.*root',
aliases,
cache=False,
verbose=False)
print
for sam in MC:
print 'setting trigger', mc_triggers, 'for sample', sam.name
sam.triggers = mc_triggers
for data in data_list_2012:
print 'setting trigger', data_triggers, 'for sample', data.name
data.triggers = data_triggers
print
# this number is not in the DB (dbs says this sample is still in production)
WJets.nGenEvents = 61444940
'/WZ_TuneZ2.*START42.*':'WZ',
'/ZZ_TuneZ2.*START42.*':'ZZ',
'/WWJetsTo2L2Nu.*START42.*':'WWJetsTo2L2Nu',
'/WZJetsTo2L2Q.*START42.*':'WZJetsTo2L2Q',
'/WZJetsTo3LNu.*START42.*':'WZJetsTo3LNu',
'/ZZJetsTo2L2Nu.*START42.*':'ZZJetsTo2L2Nu',
'/ZZJetsTo2L2Q.*START42.*':'ZZJetsTo2L2Q',
}
MC = copy.copy( mc_ewk )
MC.extend( mc_higgs )
MC.extend( mc_diboson )
for sam in MC:
sam.triggers = mc_triggers
for data in data_list_2011A:
data.triggers = data_triggers_2011A
for data in data_list_2011B:
data.triggers = data_triggers_2011B
allsamples = copy.copy(MC)
allsamples.extend( data_list_2011 )
allsamples.extend( embed_list_2011 )
connect( allsamples, '%/TAUMU_2011_ColinSep21_NewSVFit', 'tauMu.*root', aliases, cache=True, verbose=False)
for c in allsamples:
c.splitFactor = splitFactor(c)
if '2012A' in sam.name:
sam.triggers = data_triggers_2012A
elif '2012B' in sam.name:
sam.triggers = data_triggers_2012B
elif '2012C' in sam.name:
sam.triggers = data_triggers_2012C
elif '2012D' in sam.name:
sam.triggers = data_triggers_2012D
allsamples1 = copy.copy( mc_higgs )
allsamples1.extend( ztt_mc_ewk )
allsamples1.extend( embed_list )
allsamples1.extend( mc_higgs_susy )
pat1 = '%HTT_Feb6_hinzmann_Nom'
connect( allsamples1, pat1, 'diTau.*root', aliases, cache=True, verbose=False)
allsamples2 = copy.copy( data_2012 )
allsamples2.extend( t_mc_ewk )
allsamples2.extend( mc_diboson_incl )
allsamples2.extend( w_mc_ewk )
pat2 = '%V5_8_0/HTT_Sep12_hinzmann'
connect( allsamples2, pat2, 'diTau.*root', aliases, cache=True, verbose=False)
allsamples = copy.copy(allsamples1)
allsamples.extend(allsamples2)
DYJets.nGenEvents /= 0.8 ## overall trigger efficiency in MC
for h in mc_higgs :
h.nGenEvents /= 0.8 ## overall trigger efficiency in MC
def connect_by_db_(self):
''' '''
from CMGTools.RootTools.utils.connect import connect
connect(self.MC_list, self.tier, self.pattern,
self.aliases, cache=self.cache, verbose=self.verbose)
MC_list.extend(mc_diboson)
MC_list.extend(mc_higgs)
# the following for 52X sync purposes only:
#MC_list.append (HiggsGGH125)
#MC_list.append (HiggsVBF125)
allsamples = copy.copy(MC_list)
allsamples.extend(data_list)
allsamples.extend(embed_list)
print 'start connecting... \n\n'
connect(allsamples,
'%H2TauTau_tauEle_22oct_PG',
'tauEle.*root',
aliases,
cache=True,
verbose=False)
from CMGTools.H2TauTau.proto.samples.density import *
print
print 'density test'
density(allsamples)
print
print
for sam in MC_list:
print 'setting trigger', mc_triggers, 'for sample', sam.name
sam.triggers = mc_triggers
sam.splitFactor = splitFactor(sam)
mc_ewk = []
# mc_ewk += mc_dy
# mc_ewk += t_mc_ewk
MC_list = copy.copy( mc_ewk )
MC_list.extend( mc_higgs )
MC_list.extend( mc_higgs_susy )
# MC_list.extend( mc_diboson )
allsamples = copy.copy( MC_list )
# allsamples.extend( data_list )
allsamples.extend( embed_list )
connect( allsamples, '%TAUELE_SVFitVEGASTESDown_Aug12%', 'tauEle.*root', aliases, cache=True, verbose=False)
connect( data_list, '%TAUELE_SVFitVEGAS_Aug06%', 'tauEle.*root', aliases, cache=True, verbose=False)
connect( mc_dy, '%TAUELE_SVFitVEGASTESDown_Aug26%', 'tauEle.*root', aliases, cache=True, verbose=False)
allsamples.extend( data_list )
allsamples.extend( mc_dy )
MC_list.extend( mc_dy )
# Attach number of generated events for stitching
dy_nevents = [ DYJets.nGenEvents,
DY1Jets.nGenEvents,
DY2Jets.nGenEvents,
DY3Jets.nGenEvents,
DY4Jets.nGenEvents
]
for dy in mc_dy:
data_Run2011B_MuRm = cfg.DataComponent(name='data_Run2011B_MuRm',
files=[],
intLumi=0.,
triggers=[])
aliases = {
'/DYJets.*START42.*': 'DYJetsMuRm',
'/WJetsToLNu.*START42.*': 'WJets',
'/DoubleMu/Run2011A-16Jan2012-v1/AOD.*': 'data_Run2011A_MuRm',
'/DoubleMu/Run2011B-16Jan2012-v1/AOD.*': 'data_Run2011B_MuRm',
}
allsamples = [DYJetsMuRm, WJets, data_Run2011A_MuRm, data_Run2011B_MuRm]
# connect( allsamples, '%TAUMU_%MuRm_ColinSep28', 'tauMu.*root', aliases, cache=True, verbose=False)
connect(allsamples,
'%TAUMU_MuRm_rlxTauIso_ColinOct6',
'tauMu.*root',
aliases,
cache=True,
verbose=False)
MC_list = [DYJetsMuRm, WJets]
data_list_2011 = [data_Run2011A_MuRm, data_Run2011B_MuRm]
embed_list = []
for mc in MC_list:
mc.triggers = mc_triggers
for data in data_list_2011:
data.json = jsonPick(data.files[0])
mc_ewk = []
# mc_ewk += mc_dy
# mc_ewk += t_mc_ewk
MC_list = copy.copy(mc_ewk)
MC_list.extend(mc_higgs)
MC_list.extend(mc_higgs_susy)
# MC_list.extend( mc_diboson )
allsamples = copy.copy(MC_list)
connect(allsamples,
'%TAUMU_SVFitVEGAS_TESDown_Aug02_steggema',
'tauMu.*root',
aliases,
cache=True,
verbose=False)
connect(embed_list,
'%TAUMU_SVFitVEGASTESDown_Aug07_steggema',
'tauMu.*root',
aliases,
cache=True,
verbose=False)
# Import the non-shifted data such that the plotting scripts know the integrated luminosity
connect(data_list,
'%TAUMU_SVFitVEGAS_Jul29_steggema',
'tauMu.*root',
aliases,
cache=True,
verbose=False)
'/WZJetsTo3LNu.*START42.*':'WZJetsTo3LNu',
'/ZZJetsTo2L2Nu.*START42.*':'ZZJetsTo2L2Nu',
'/ZZJetsTo2L2Q.*START42.*':'ZZJetsTo2L2Q',
'/ZZJetsTo4L.*START42.*':'ZZJetsTo4L',
}
MC_list = copy.copy( mc_ewk )
MC_list.extend( mc_higgs )
MC_list.extend( mc_diboson )
for sam in MC_list:
sam.triggers = mc_triggers
for data in data_list_2011A:
data.triggers = data_triggers_2011A
for data in data_list_2011B:
data.triggers = data_triggers_2011B
allsamples = copy.copy(MC_list)
allsamples.extend( data_list_2011 )
allsamples.extend( embed_list_2011 )
# pat = '/VBF%TAUELE_2011_Colin_Oct25'
# pat = '/VBF%/TAUELE_2011_ColinOct31_Test1'
pat = '%/TAUELE_2011_OK_ColinOct31%'
connect( allsamples, pat, 'tauEle.*root', aliases, cache=True, verbose=False)
Tbar_tW.nGenEvents = 809984.
for c in allsamples:
c.splitFactor = splitFactor(c)
'/DoubleMu/Run2012C-24Aug2012-v1':'data_Run2012C_v1',
'/DoubleMu/Run2012C-PromptReco-v2/AOD/PAT_CMG_V5_10_0_runrange_start-203002':'data_Run2012C_v2',
}
MC_list = copy.copy( mc_ewk )
MC_list.extend( mc_diboson_inc )
allsamples = copy.copy(MC_list)
allsamples.extend( data_list )
# the pattern provided to this function is a SQL pattern.
# % represents the wildcard.
# this pattern allows to select a whole group of samples.
connect( allsamples, '%PAT_CMG_V5_10_0%', 'cmgTuple.*root', aliases, cache=True, verbose=False)
# guessing the best split factor for each component,
# to get about the same number of events in each job
for c in allsamples:
c.splitFactor = splitFactor(c, nEventsPerJob=2e5)
# picking up the json file automatically. Here, we use the dcs jsons.
for data in data_list:
if len(data.files):
data.json = jsonPick( data.files[0], jsonMap )
# '/WJetsToLNu_TuneZ2Star_8TeV-madgraph-tarball/Summer12-PU_S7_START52_V9-v1':'WJets',
'/WJetsToLNu_TuneZ2Star_8TeV-madgraph-tarball/Summer12-PU_S7_START52_V9_extension-v1':'WJets',
'/W2Jets':'W2Jets',
'/W3Jets':'W3Jets',
'/TTJets':'TTJets',
'/TauPlusX/Run2012A-PromptReco-v1':'data_Run2012A',
'/TauPlusX/Run2012B-PromptReco-v1':'data_Run2012B_start_196509',
'/DoubleMu/StoreResults-DoubleMu_2012A_PromptReco_v1':'embed_Run2012A',
'/DoubleMu/StoreResults-DoubleMu_2012B_PromptReco_v1_Run193752to195135':'embed_Run2012B_193752_195135',
'/DoubleMu/StoreResults-DoubleMu_2012B_PromptReco_v1_Run195147to196070':'embed_Run2012B_195147_196070'
}
MC = copy.copy( mc_ewk )
MC.extend( mc_higgs )
# MC.extend( mc_diboson )
for sam in MC:
sam.triggers = mc_triggers
for data in data_list_2012:
data.triggers = data_triggers
allsamples = copy.copy(MC)
allsamples.extend( data_list_2012 )
allsamples.extend( embed_list_2012 )
connect( allsamples, '%TAUMU_Colin_Jul4', 'tauMu.*root', aliases, cache=True)
# this number is not in the DB (dbs says this sample is still in production)
WJets.nGenEvents = 61444940
mc_ewk = []
mc_ewk += mc_dy
mc_ewk += t_mc_ewk
MC_list = copy.copy(mc_ewk)
MC_list.extend(mc_higgs)
MC_list.extend(mc_diboson)
allsamples = copy.copy(MC_list)
allsamples.extend(data_list)
allsamples.extend(embed_list)
connect(allsamples,
'%TAUELE_SVFitNoES_Jul09%',
'tauEle.*root',
aliases,
cache=True,
verbose=False)
MC_list.extend(mc_w)
allsamples.extend(mc_w)
connect(mc_w,
'%TAUELE_SVFitNoESFixedRecoil_Jul19_steggema',
'tauEle.*root',
aliases,
cache=True,
verbose=False)
# Attach number of generated events for stitching
dy_nevents = [
DYJets.nGenEvents, DY1Jets.nGenEvents, DY2Jets.nGenEvents,
MC_list = copy.copy(mc_ewk)
# MC_list.extend( mc_higgs )
# MC_list.extend( mc_higgs_susy )
MC_list.extend(mc_diboson)
allsamples = copy.copy(MC_list)
allsamples.extend(data_list)
mc_repro = []
mc_repro += mc_dy
mc_repro += mc_higgs
mc_repro += mc_higgs_susy
connect(allsamples,
'%TAUELE_SVFitVEGAS_Aug06%',
'tauEle.*root',
aliases,
cache=True,
verbose=False)
connect(embed_list,
'%TAUELE_SVFitVEGAS_Aug07%',
'tauEle.*root',
aliases,
cache=True,
verbose=False)
connect(mc_repro,
'%TAUELE_SVFitVEGAS_Aug26%',
'tauEle.*root',
aliases,
cache=True,
verbose=False)
'/WZJetsTo3LNu.*START42.*': 'WZJetsTo3LNu',
'/ZZJetsTo2L2Nu.*START42.*': 'ZZJetsTo2L2Nu',
'/ZZJetsTo2L2Q.*START42.*': 'ZZJetsTo2L2Q',
'/ZZJetsTo4L.*START42.*': 'ZZJetsTo4L',
}
MC_list = copy.copy(mc_ewk)
MC_list.extend(mc_higgs)
MC_list.extend(mc_diboson)
for sam in MC_list:
sam.triggers = mc_triggers
for data in data_list_2011A:
data.triggers = data_triggers_2011A
for data in data_list_2011B:
data.triggers = data_triggers_2011B
allsamples = copy.copy(MC_list)
allsamples.extend(data_list_2011)
allsamples.extend(embed_list_2011)
connect(allsamples,
'%TAUMU_2011_Colin_OSVFit_RecoilTest_Oct23',
'tauMu.*root',
aliases,
cache=True,
verbose=False)
Tbar_tW.nGenEvents = 809984.
for c in allsamples:
c.splitFactor = splitFactor(c)
## '/WWJetsTo2L2Nu.*START42.*':'WWJetsTo2L2Nu',
## '/WZJetsTo2L2Q.*START42.*':'WZJetsTo2L2Q',
## '/WZJetsTo3LNu.*START42.*':'WZJetsTo3LNu',
## '/ZZJetsTo2L2Nu.*START42.*':'ZZJetsTo2L2Nu',
## '/ZZJetsTo2L2Q.*START42.*':'ZZJetsTo2L2Q',
## '/ZZJetsTo4L.*START42.*':'ZZJetsTo4L',
}
MC_list = copy.copy( mc_ewk )
MC_list.extend( mc_higgs )
MC_list.extend( mc_diboson )
for sam in MC_list:
sam.triggers = mc_triggers
for data in data_list_2011A:
data.triggers = data_triggers_2011A
for data in data_list_2011B:
data.triggers = data_triggers_2011B
allsamples = copy.copy(MC_list)
allsamples.extend( data_list_2011 )
allsamples.extend( embed_list_2011 )
connect( allsamples, '%TAUMU_Up_ColinOct30', 'tauMu.*root', aliases, cache=True, verbose=False)
Tbar_tW.nGenEvents = 809984.
for c in allsamples:
c.splitFactor = splitFactor(c)
'embed_Run2012C_24Aug2012_v1',
'/DoubleMu/StoreResults-DoubleMu_2012D_PromptReco_v1_embedded_trans1.*':
'embed_2012D_PromptReco_v1',
}
MC_list = copy.copy(mc_ewk)
MC_list.extend(mc_higgs)
MC_list.extend(mc_diboson)
allsamples = copy.copy(MC_list)
allsamples.extend(data_list)
allsamples.extend(embed_list)
connect(allsamples,
'%TAUMU_OSVFit_May27%',
'tauMu.*root',
aliases,
cache=True,
verbose=False)
# this number is not in the DB (dbs says this sample is still in production)
# WJets.nGenEvents = 61444940
for mc in MC_list:
mc.triggers = mc_triggers
# allsamples.append(mc)
for data in data_list:
if len(data.files):
data.json = jsonPick(data.files[0], jsonMap)
data.triggers = data_triggers
# allsamples.append(data)
for embed in embed_list:
from CMGTools.H2TauTau.proto.samples.csa2014.ewk import *
aliases = {'/VBF_HToTauTau.*POSTLS170.*': 'HiggsVBF'}
MC_list = [HiggsVBF125]
for sam in MC_list:
sam.triggers = None # No triggers yet
allsamples = copy.copy(MC_list)
pat = '/VBF_HToTauTau_M-125_8TeV-powheg-pythia6/Summer12_DR53X-PU_S10_START53_V7A-v1/AODSIM/V5_B/PAT_CMG_V5_14_0/TAUMU_OSVFit_NoRecoil_May1'
connect(allsamples,
'%TAUMU_MINIAODTEST_steggema',
'miniAOD*root',
aliases,
cache=True,
verbose=False)
# take stuff from yuta
MC_list = [HiggsVBF125, HiggsGGH125, DYJets]
HiggsVBF125.files = getFiles(
'/VBF_HToTauTau_M-125_13TeV-powheg-pythia6/Spring14miniaod-PU20bx25_POSTLS170_V5-v2/MINIAODSIM',
'CMS', '*.root')
HiggsGGH125.files = getFiles(
'/GluGluToHToTauTau_M-125_13TeV-powheg-pythia6/Spring14miniaod-PU20bx25_POSTLS170_V5-v1/MINIAODSIM',
'CMS', '*.root')
DYJets.files = getFiles(
'embed_Run2012C_22Jan',
'/DoubleMuParked/StoreResults-Run2012B_22Jan2013_v1_RHembedded_trans1_tau115_ptelec1_20had1_18_v1.*':
'embed_Run2012D_22Jan',
}
MC_list = copy.copy(mc_ewk)
MC_list.extend(mc_higgs)
MC_list.extend(mc_diboson)
allsamples = copy.copy(MC_list)
allsamples.extend(data_list)
# allsamples.extend( embed_list )
connect(allsamples,
'%TAUELE_SVF%_Jun28%',
'tauEle.*root',
aliases,
cache=True,
verbose=False)
# Accidentally named the e-tau embedded jobs TAUMU
connect(embed_list,
'%PAT_CMG_V5_16_0_B%TAUMU_SVFit_Jun28_steggema',
'tauEle.*root',
aliases,
cache=True,
verbose=False)
allsamples.extend(embed_list)
# Attach number of generated events for stitching
dy_nevents = [