def getsampleset(channel, era, **kwargs):
verbosity = LOG.getverbosity(kwargs)
year = getyear(era) # get integer year
tag = kwargs.get('tag', "")
table = kwargs.get('table', True) # print sample set table
setera(era) # set era for plot style and lumi normalization
negative_fractions = {
"DYJetsToLL_M-50": 0.0004,
"WJetsToLNu": 0.0004,
"WW_TuneCP5_13TeV-pythia8":
0.0, # <-- no adaption of effective events needed
"WZ_TuneCP5_13TeV-pythia8":
0.0, # <-- no adaption of effective events needed
"ZZ_TuneCP5_13TeV-pythia8":
0.0, # <-- no adaption of effective events needed
"ST_t-channel_top": 0.033,
"ST_t-channel_antitop": 0.031,
"ST_tW_top": 0.002,
"ST_tW_antitop": 0.002,
"TTTo2L2Nu": 0.004,
"TTToHadronic": 0.004,
"TTToSemiLeptonic": 0.004,
}
# SM BACKGROUND MC SAMPLES
expsamples = [ # table of MC samples to be converted to Sample objects
# GROUP NAME TITLE XSEC [pb] effective NEVENTS = simulated NEVENTS * ( 1 - 2 * negative fraction)
# Cross-secitons: https://twiki.cern.ch/twiki/bin/viewauth/CMS/StandardModelCrossSectionsat13TeV, Z/a* (50)
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 6077.22, {
"nevts":
100194597 * (1.0 - 2 * negative_fractions["DYJetsToLL_M-50"])
}),
# Cross-sections: https://twiki.cern.ch/twiki/bin/viewauth/CMS/StandardModelCrossSectionsat13TeV, Total W
('WJ', "WJetsToLNu", "W + jets", 3 * 20508.9, {
"nevts": 71072199 * (1.0 - 2 * negative_fractions["WJetsToLNu"])
}),
# Cross-sections: https://twiki.cern.ch/twiki/bin/viewauth/CMS/StandardModelCrossSectionsat13TeV, W+ W-
('VV', "WW", "WW", 118.7, {
"nevts": 7850000
}),
# Cross-sections: from generator (https://cms-gen-dev.cern.ch/xsdb with 'process_name=WZ_TuneCP5_13TeV-pythia8')
('VV', "WZ", "WZ", 27.6, {
"nevts": 3885000
}),
# Cross-sections: from generator (https://cms-gen-dev.cern.ch/xsdb with 'process_name=ZZ_TuneCP5_13TeV-pythia8')
('VV', "ZZ", "ZZ", 12.14, {
"nevts": 1979000
}),
# Cross-sections: # https://twiki.cern.ch/twiki/bin/viewauth/CMS/SingleTopSigma
('ST', "ST_t-channel_top", "ST t-channel t", 136.02, {
"nevts":
154307600 * (1.0 - 2 * negative_fractions["ST_t-channel_top"])
}),
('ST', "ST_t-channel_antitop", "ST t-channel at", 80.95, {
"nevts":
79090800 * (1.0 - 2 * negative_fractions["ST_t-channel_antitop"])
}),
('ST', "ST_tW_top", "ST tW", 35.85, {
"nevts": 9598000 * (1.0 - 2 * negative_fractions["ST_tW_top"])
}),
('ST', "ST_tW_antitop", "ST atW", 35.85, {
"nevts": 7623000 * (1.0 - 2 * negative_fractions["ST_tW_antitop"])
}),
# Cross-sections: https://twiki.cern.ch/twiki/bin/view/LHCPhysics/TtbarNNLO#Top_quark_pair_cross_sections_at, m_top = 172.5 GeV + PDG for W boson decays
('TT', "TTTo2L2Nu", "ttbar 2l2#nu", 831.76 * (3 * 0.1086)**2, {
"nevts": 64310000 * (1.0 - 2 * negative_fractions["TTTo2L2Nu"])
}),
('TT', "TTToHadronic", "ttbar hadronic",
831.76 * 2 * (3 * 0.1086) * (0.6741), {
"nevts":
199524000 * (1.0 - 2 * negative_fractions["TTToHadronic"])
}),
('TT', "TTToSemiLeptonic", "ttbar semileptonic", 831.76 * (0.6741)**2,
{
"nevts":
199925998 * (1.0 - 2 * negative_fractions["TTToSemiLeptonic"])
}),
]
# OBSERVED DATA SAMPLES
if 'mutau' in channel: dataset = "SingleMuon_Run%d?" % year
elif 'etau' in channel: dataset = "SingleElectron_Run%d?" % year
else:
LOG.throw(IOError, "Did not recognize channel %r!" % (channel))
datasample = ('Data', dataset) # Data for chosen channel
# SAMPLE SET
# TODO section 5: This weight needs to be extended with correction weights common to all simulated samples (MC)
weight = "genweight/abs(genweight)" # normalize weight, since sometimes the generator cross-section is contained in it.
kwargs.setdefault('weight', weight) # common weight for MC
sampleset = _getsampleset(datasample,
expsamples,
channel=channel,
era=era,
**kwargs)
# JOIN
# Note: titles are set via STYLE.sample_titles
sampleset.join('WW', 'WZ', 'ZZ', name='VV') # Diboson
sampleset.join('VV', 'WJ', name='EWK') # Electroweak
sampleset.join('TT', name='TT') # ttbar
sampleset.join('ST', name='ST') # single top
sampleset.join('ST', 'TT', name='Top') #ttbar & single top
# SPLIT
# TODO section 5: Check the generator matching for various samples in the flat n-tuples.
# Is it justified to require only the tauh candidate to match to generator level hadronic tau to declare the full process with Z->tautau in mutau final state?
# What is the major contribution from Drell-Yan to genmatch_2!=5? How does this look like for other processes?
GMR = "genmatch_2==5"
GMO = "genmatch_2!=5"
sampleset.split('DY', [('ZTT', GMR), ('ZL', GMO)])
sampleset.split('Top', [('TopT', GMR), ('TopJ', GMO)])
sampleset.split('EWK', [('EWKT', GMR), ('EWKJ', GMO)])
if table:
sampleset.printtable(merged=True, split=True)
return sampleset
def getsampleset(channel, era, **kwargs):
verbosity = LOG.getverbosity(kwargs)
year = getyear(era) # get integer year
dysample = kwargs.get('dy', "jet")
dyweight = kwargs.get('dyweight', "")
split = kwargs.get('split',
[]) # split samples (e.g. DY) into genmatch components
join = kwargs.get('join', ['VV', 'Top']) # join samples (e.g. VV, top)
tag = kwargs.get('tag', "")
table = kwargs.get('table', True) # print sample set table
setera(era) # set global era for plot style and lumi-xsec normalization
if 'UL2016' in era and 'VFP' not in era: # join pre-/post-VFP into full UL2016
kwargs['table'] = False
kwargs1 = kwargs.copy() # prevent overwriting
kwargs2 = kwargs.copy() # prevent overwriting
sampleset1 = getsampleset(channel, era + "_preVFP", **kwargs1)
sampleset2 = getsampleset(channel, era + "_postVFP", **kwargs2)
setera(era) # reset era for plot style and lumi-xsec normalization
sampleset = sampleset1 + sampleset2 # merge samples
if table:
sampleset.printtable(merged=True, split=True)
return sampleset
# SM BACKGROUND MC SAMPLES
xsec_dy_lo = 4963.0 # MadGraph (LO)
xsec_dy_nlo = 6529.0 # aMC@NLO
xsec_dy_nnlo = 3 * 2025.74 # FEWZ (NNLO)
k_lo = xsec_dy_nnlo / xsec_dy_lo
k_nlo = 1. #xsec_dy_nnlo/xsec_dy_nlo
if 'UL' in era:
expsamples = [ # table of MC samples to be converted to Sample objects
# GROUP NAME TITLE XSEC EXTRA OPTIONS
#( 'DY', "DYJetsToLL_M-10to50", "Drell-Yan 10-50", 18610.0 ),
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 5343.0, {
'extraweight': dyweight
}),
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 877.8, {
'extraweight': dyweight
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 304.4, {
'extraweight': dyweight
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 111.5, {
'extraweight': dyweight
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 44.05, {
'extraweight': dyweight
}),
###( 'DY', "DYJetsToMuTauh_M-50", "DYJetsToMuTauh_M-50", 5343.0, {'extraweight': dyweight} ),
('WJ', "WJetsToLNu", "W + jets", 52940.0),
('WJ', "W1JetsToLNu", "W + 1J", 8104.0),
('WJ', "W2JetsToLNu", "W + 2J", 2793.0),
('WJ', "W3JetsToLNu", "W + 3J", 992.5),
('WJ', "W4JetsToLNu", "W + 4J", 544.3),
('VV', "WW", "WW", 75.88),
('VV', "WZ", "WZ", 27.6),
('VV', "ZZ", "ZZ", 12.14),
('ST', "ST_t-channel_top", "ST t-channel t", 136.02),
('ST', "ST_t-channel_antitop", "ST t-channel at", 80.95),
('ST', "ST_tW_top", "ST tW", 35.85),
('ST', "ST_tW_antitop", "ST atW", 35.85),
('TT', "TTTo2L2Nu", "ttbar 2l2#nu", 88.29, {
'extraweight': 'ttptweight'
}),
('TT', "TTToHadronic", "ttbar hadronic", 377.96, {
'extraweight': 'ttptweight'
}),
('TT', "TTToSemiLeptonic", "ttbar semileptonic", 365.35, {
'extraweight': 'ttptweight'
}),
]
else:
if era == '2016':
expsamples = [
] # table of MC samples to be converted to Sample objects
if 'mass' in dysample:
expsamples += [
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('DY', "DYJetsToLL_M-100to200", "Drell-Yan 100to200",
k_nlo * 226.6, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-200to400", "Drell-Yan 200to400",
k_nlo * 7.77, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-400to500", "Drell-Yan 400to500",
k_nlo * 0.4065, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-500to700", "Drell-Yan 500to700",
k_nlo * 0.2334, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-700to800", "Drell-Yan 700to800",
k_nlo * 0.03614, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-800to1000", "Drell-Yan 800to1000",
k_nlo * 0.03047, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-1000to1500", "Drell-Yan 1000to1500",
k_nlo * 0.01636, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-1500to2000", "Drell-Yan 1500to2000",
k_nlo * 0.00218, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-2000to3000", "Drell-Yan 2000to3000",
k_nlo * 0.0005156, {
'extraweight': dyweight
}),
]
else:
expsamples += [
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('DY', "DYJetsToLL_M-10to50", "Drell-Yan 10-50", 18610.0, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 4963.0, {
'extraweight': dyweight
}),
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 1012.0, {
'extraweight': dyweight
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 334.7, {
'extraweight': dyweight
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 102.3, {
'extraweight': dyweight
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 54.52, {
'extraweight': dyweight
}),
]
expsamples += [
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('WJ', "WJetsToLNu", "W + jets", 50260.0),
('WJ', "W1JetsToLNu", "W + 1J", 9625.0),
('WJ', "W2JetsToLNu", "W + 2J", 3161.0),
('WJ', "W3JetsToLNu", "W + 3J", 954.8),
('WJ', "W4JetsToLNu", "W + 4J", 494.6),
('VV', "WW", "WW", 75.88),
('VV', "WZ", "WZ", 27.6),
('VV', "ZZ", "ZZ", 12.14),
('ST', "ST_t-channel_top", "ST t-channel t", 136.02),
('ST', "ST_t-channel_antitop", "ST t-channel at", 80.95),
('ST', "ST_tW_top", "ST tW", 35.85),
('ST', "ST_tW_antitop", "ST atW", 35.85),
('TT', "TT", "ttbar", 831.76, {
'extraweight': 'ttptweight'
}),
]
elif era == '2017':
expsamples = [
] # table of MC samples to be converted to Sample objects
if 'mass' in dysample:
expsamples += [
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('DY', "DYJetsToLL_M-100to200", "Drell-Yan 100to200",
k_nlo * 247.8, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-200to400", "Drell-Yan 200to400",
k_nlo * 8.502, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-400to500", "Drell-Yan 400to500",
k_nlo * 0.4514, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-500to700", "Drell-Yan 500to700",
k_nlo * 0.2558, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-700to800", "Drell-Yan 700to800",
k_nlo * 0.04023, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-800to1000", "Drell-Yan 800to1000",
k_nlo * 0.03406, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-1000to1500", "Drell-Yan 1000to1500",
k_nlo * 0.01828, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-1500to2000", "Drell-Yan 1500to2000",
k_nlo * 0.002367, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-2000to3000", "Drell-Yan 2000to3000",
k_nlo * 0.0005409, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-3000toInf", "Drell-Yan 3000toInf",
k_nlo * 3.048e-05, {
'extraweight': dyweight
}),
]
else:
expsamples += [
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('DY', "DYJetsToLL_M-10to50", "Drell-Yan 10-50", 18610.0, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 5343.0, {
'extraweight': dyweight
}),
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 877.8, {
'extraweight': dyweight
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 304.4, {
'extraweight': dyweight
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 111.5, {
'extraweight': dyweight
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 44.05, {
'extraweight': dyweight
}),
]
expsamples += [
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('WJ', "WJetsToLNu", "W + jets", 52940.0),
('WJ', "W1JetsToLNu", "W + 1J", 8104.0),
('WJ', "W2JetsToLNu", "W + 2J", 2793.0),
#( 'WJ', "W3JetsToLNu", "W + 3J", 992.5 ),
('WJ', "W4JetsToLNu", "W + 4J", 544.3),
('VV', "WW", "WW", 75.88),
('VV', "WZ", "WZ", 27.6),
('VV', "ZZ", "ZZ", 12.14),
('ST', "ST_t-channel_top", "ST t-channel t", 136.02),
('ST', "ST_t-channel_antitop", "ST t-channel at", 80.95),
('ST', "ST_tW_top", "ST tW", 35.85),
('ST', "ST_tW_antitop", "ST atW", 35.85),
('TT', "TTTo2L2Nu", "ttbar 2l2#nu", 88.29, {
'extraweight': 'ttptweight'
}),
('TT', "TTToHadronic", "ttbar hadronic", 377.96, {
'extraweight': 'ttptweight'
}),
('TT', "TTToSemiLeptonic", "ttbar semileptonic", 365.35, {
'extraweight': 'ttptweight'
}),
]
elif era == '2018':
expsamples = [
] # table of MC samples to be converted to Sample objects
if 'mass' in dysample:
expsamples += [
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('DY', "DYJetsToLL_M-100to200", "Drell-Yan 100to200",
k_nlo * 247.8, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-200to400", "Drell-Yan 200to400",
k_nlo * 8.502, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-400to500", "Drell-Yan 400to500",
k_nlo * 0.4514, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-500to700", "Drell-Yan 500to700",
k_nlo * 0.2558, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-700to800", "Drell-Yan 700to800",
k_nlo * 0.04023, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-800to1000", "Drell-Yan 800to1000",
k_nlo * 0.03406, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-1000to1500", "Drell-Yan 1000to1500",
k_nlo * 0.01828, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-1500to2000", "Drell-Yan 1500to2000",
k_nlo * 0.002367, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-2000to3000", "Drell-Yan 2000to3000",
k_nlo * 0.0005409, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-3000toInf", "Drell-Yan 3000toInf",
k_nlo * 3.048e-05, {
'extraweight': dyweight
}),
]
else:
expsamples += [
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('DY', "DYJetsToLL_M-10to50", "Drell-Yan 10-50", 18610.0, {
'extraweight': dyweight
}),
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 5343.0, {
'extraweight': dyweight
}),
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 877.8, {
'extraweight': dyweight
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 304.4, {
'extraweight': dyweight
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 111.5, {
'extraweight': dyweight
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 44.05, {
'extraweight': dyweight
}),
]
expsamples += [
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('WJ', "WJetsToLNu", "W + jets", 52940.0),
('WJ', "W1JetsToLNu", "W + 1J", 8104.0),
('WJ', "W2JetsToLNu", "W + 2J", 2793.0),
('WJ', "W3JetsToLNu", "W + 3J", 992.5),
('WJ', "W4JetsToLNu", "W + 4J", 544.3),
('VV', "WW", "WW", 75.88),
('VV', "WZ", "WZ", 27.6),
('VV', "ZZ", "ZZ", 12.14),
('ST', "ST_t-channel_top", "ST t-channel t", 136.02),
('ST', "ST_t-channel_antitop", "ST t-channel at", 80.95),
('ST', "ST_tW_top", "ST tW", 35.85),
('ST', "ST_tW_antitop", "ST atW", 35.85),
('TT', "TTTo2L2Nu", "ttbar 2l2#nu", 88.29, {
'extraweight': 'ttptweight'
}),
('TT', "TTToHadronic", "ttbar hadronic", 377.96, {
'extraweight': 'ttptweight'
}),
('TT', "TTToSemiLeptonic", "ttbar semileptonic", 365.35, {
'extraweight': 'ttptweight'
}),
]
else:
LOG.throw(IOError, "Did not recognize era %r!" % (era))
# OBSERVED DATA SAMPLES
dataset = "SingleMuon_Run%d?" % year
datasample = ('Data', dataset) # GROUP, NAME
# SAMPLE SET
weight = "genweight*trigweight*puweight*idisoweight_1*idisoweight_2"
fname = "$PICODIR/$SAMPLE_$CHANNEL$TAG.root"
kwargs.setdefault('weight', weight) # common weight for MC
kwargs.setdefault('fname', fname) # default filename pattern
sampleset = _getsampleset(datasample,
expsamples,
channel=channel,
era=era,
**kwargs)
# JOIN
ZMM = STYLE.sample_titles.get('ZMM', "Z -> mumu") # title
# Note: titles are set via STYLE.sample_titles
sampleset.stitch("W*Jets", incl='WJ', name='WJ') # W + jets
if 'mass' not in dysample:
sampleset.stitch("DY*J*M-10to50", incl='DYJ', name="DY_M10to50")
sampleset.stitch("DY*J*M-50", incl='DYJ',
name='DY') # Drell-Yan, M > 50 GeV
sampleset.join('DY', name='DY') # Drell-Yan, M < 50 GeV + M > 50 GeV
if 'VV' in join:
sampleset.join('VV', 'WZ', 'WW', 'ZZ', name='VV') # Diboson
if 'TT' in join and era != 'year':
sampleset.join('TT', name='TT') # ttbar
if 'ST' in join:
sampleset.join('ST', name='ST') # single top
if 'Top' in join:
sampleset.join('TT', 'ST', name='Top') # ttbar + single top
# SPLIT
GMR = "genmatch_1>0 && genmatch_2>0"
GMF = "(genmatch_1<=0 || genmatch_2<=0)"
if 'DY' in split:
sampleset.split('DY', [
('ZMM', ZMM, GMR),
('ZJ', GMF),
])
if 'TT' in split:
sampleset.split('TT', [
('TMM', GMR),
('TTJ', GMF),
])
if table:
sampleset.printtable(merged=True, split=True)
return sampleset
def getsampleset_simple(channel, era, **kwargs):
"""Simplified version of Plotter/config/samples.py:getsampleset"""
fname = "$PICODIR/$SAMPLE_$CHANNEL$TAG.root"
if 'mutau' in channel:
weight = "genweight*trigweight*puweight*idisoweight_1*idweight_2*ltfweight_2"
else:
weight = "genweight*trigweight*puweight*idweight_1*idweight_2*ltfweight_1*ltfweight_2"
fname = kwargs.get('fname',
fname) or fname # file name pattern of pico files
weight = kwargs.get('weight', weight)
tag = kwargs.get('tag', "")
table = kwargs.get('table', True) # print sample set table
setera(era) # set era for plot style and lumi-xsec normalization
year = getyear(era) # get integer year
if 'UL' in era: # UltraLegacy
expsamples = [ # table of MC samples to be converted to Sample objects
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 5343.0, {
'extraweight': 'zptweight'
}), # apply k-factor in stitching
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 877.8, {
'extraweight': 'zptweight'
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 304.4, {
'extraweight': 'zptweight'
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 111.5, {
'extraweight': 'zptweight'
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 44.05, {
'extraweight': 'zptweight'
}),
('WJ', "WJetsToLNu", "W + jets", 52940.0),
('WJ', "W1JetsToLNu", "W + 1J", 8104.0),
('WJ', "W2JetsToLNu", "W + 2J", 2793.0),
('WJ', "W3JetsToLNu", "W + 3J", 992.5),
('WJ', "W4JetsToLNu", "W + 4J", 544.3),
('VV', "WW", "WW", 75.88),
('VV', "WZ", "WZ", 27.6),
('VV', "ZZ", "ZZ", 12.14),
('ST', "ST_t-channel_top", "ST t-channel t", 136.02),
('ST', "ST_t-channel_antitop", "ST t-channel at", 80.95),
('ST', "ST_tW_top", "ST tW", 35.85),
('ST', "ST_tW_antitop", "ST atW", 35.85),
('TT', "TTTo2L2Nu", "ttbar 2l2#nu", 88.29, {
'extraweight': 'ttptweight'
}),
('TT', "TTToHadronic", "ttbar hadronic", 377.96, {
'extraweight': 'ttptweight'
}),
('TT', "TTToSemiLeptonic", "ttbar semileptonic", 365.35, {
'extraweight': 'ttptweight'
}),
]
#if 'mutau' in channel:
# expsamples.append(('DY',"DYJetsToMuTauh_M-50","DYJetsToMuTauh_M-50",5343.0,{'extraweight': dyweight})) # apply correct normalization in stitching
elif era == '2016': # pre-UL
expsamples = [ # table of MC samples to be converted to Sample objects
('DY', "DYJetsToLL_M-10to50", "Drell-Yan 10-50", 18610.0, {
'extraweight': 'zptweight'
}),
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 4963.0, {
'extraweight': 'zptweight'
}),
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 1012.0, {
'extraweight': 'zptweight'
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 334.7, {
'extraweight': 'zptweight'
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 102.3, {
'extraweight': 'zptweight'
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 54.52, {
'extraweight': 'zptweight'
}),
(
'WJ',
"WJetsToLNu",
"W + jets",
50260.0,
),
('WJ', "W1JetsToLNu", "W + 1 jet", 9625.0),
('WJ', "W2JetsToLNu", "W + 2 jets", 3161.0),
('WJ', "W3JetsToLNu", "W + 3 jets", 954.8),
('WJ', "W4JetsToLNu", "W + 4 jets", 494.6),
('TT', "TT", "ttbar", 831.76, {
'extraweight': 'ttptweight'
}),
]
elif era == '2017': # pre-UL
expsamples = [ # table of MC samples to be converted to Sample objects
('DY', "DYJetsToLL_M-10to50", "Drell-Yan 10-50", 18610.0, {
'extraweight': 'zptweight'
}),
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 4963.0, {
'extraweight': 'zptweight'
}),
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 1012.0, {
'extraweight': 'zptweight'
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 334.7, {
'extraweight': 'zptweight'
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 102.3, {
'extraweight': 'zptweight'
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 54.52, {
'extraweight': 'zptweight'
}),
(
'WJ',
"WJetsToLNu",
"W + jets",
50260.0,
),
('WJ', "W1JetsToLNu", "W + 1 jet", 9625.0),
('WJ', "W2JetsToLNu", "W + 2 jets", 3161.0),
('WJ', "W3JetsToLNu", "W + 3 jets", 954.8),
('WJ', "W4JetsToLNu", "W + 4 jets", 494.6),
('TT', "TTTo2L2Nu", "ttbar 2l2#nu", 88.29, {
'extraweight': 'ttptweight'
}),
('TT', "TTToHadronic", "ttbar hadronic", 377.96, {
'extraweight': 'ttptweight'
}),
('TT', "TTToSemiLeptonic", "ttbar semileptonic", 365.35, {
'extraweight': 'ttptweight'
}),
]
elif era == '2018': # pre-UL
expsamples = [ # table of MC samples to be converted to Sample objects
('DY', "DYJetsToLL_M-10to50", "Drell-Yan 10-50", 18610.0, {
'extraweight': 'zptweight'
}),
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 4963.0, {
'extraweight': 'zptweight'
}),
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 1012.0, {
'extraweight': 'zptweight'
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 334.7, {
'extraweight': 'zptweight'
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 102.3, {
'extraweight': 'zptweight'
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 54.52, {
'extraweight': 'zptweight'
}),
(
'WJ',
"WJetsToLNu",
"W + jets",
50260.0,
),
('WJ', "W1JetsToLNu", "W + 1 jet", 9625.0),
('WJ', "W2JetsToLNu", "W + 2 jets", 3161.0),
('WJ', "W3JetsToLNu", "W + 3 jets", 954.8),
('WJ', "W4JetsToLNu", "W + 4 jets", 494.6),
('TT', "TTTo2L2Nu", "ttbar 2l2#nu", 88.29, {
'extraweight': 'ttptweight'
}),
('TT', "TTToHadronic", "ttbar hadronic", 377.96, {
'extraweight': 'ttptweight'
}),
('TT', "TTToSemiLeptonic", "ttbar semileptonic", 365.35, {
'extraweight': 'ttptweight'
}),
]
else:
LOG.throw(IOError, "Did not recognize era %r!" % (era))
datasamples = { # table of data samples (per channel) to be converted to Sample objects
'mutau': ('Data', "SingleMuon_Run%s?"%year),
'etau': ('Data', "SingleElectron_Run%s?"%year),
'tautau': ('Data', "Tau_Run%s?"%year),
}
# SAMPLE SET
sampleset = _getsampleset(datasamples,
expsamples,
channel=channel,
era=era,
weight=weight,
file=fname)
sampleset.stitch("DY*J*M-50", incl='DYJ', name="DY_M50", npart='NUP')
sampleset.stitch("W*Jets", incl='WJ', name='WJ', npart='NUP')
if era != '2016':
sampleset.join('TT')
sampleset.join('DY', name='DY')
sampleset.printtable()
return sampleset
def getsampleset(channel, era, **kwargs):
verbosity = LOG.getverbosity(kwargs)
year = getyear(era) # get integer year
split = kwargs.get(
'split', ['DY']) # split samples (e.g. DY) into genmatch components
join = kwargs.get('join', ['VV', 'Top']) # join samples (e.g. VV, top)
tag = kwargs.get('tag', "")
table = kwargs.get('table', True) # print sample set table
setera(era) # set era for plot style and lumi-xsec normalization
# SM BACKGROUND MC SAMPLES
if era == '2016':
expsamples = [ # table of MC samples to be converted to Sample objects
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('DY', "DYJetsToLL_M-10to50", "Drell-Yan 10-50", 18610.0, {
'extraweight': 'zptweight'
}),
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 4963.0, {
'extraweight': 'zptweight'
}),
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 1012.0, {
'extraweight': 'zptweight'
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 334.7, {
'extraweight': 'zptweight'
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 102.3, {
'extraweight': 'zptweight'
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 54.52, {
'extraweight': 'zptweight'
}),
('WJ', "WJetsToLNu", "W + jets", 50260.0),
('WJ', "W1JetsToLNu", "W + 1J", 9625.0),
('WJ', "W2JetsToLNu", "W + 2J", 3161.0),
('WJ', "W3JetsToLNu", "W + 3J", 954.8),
('WJ', "W4JetsToLNu", "W + 4J", 494.6),
('VV', "WW", "WW", 75.88),
('VV', "WZ", "WZ", 27.6),
('VV', "ZZ", "ZZ", 12.14),
('ST', "ST_t-channel_top", "ST t-channel t", 136.02),
('ST', "ST_t-channel_antitop", "ST t-channel at", 80.95),
('ST', "ST_tW_top", "ST tW", 35.85),
('ST', "ST_tW_antitop", "ST atW", 35.85),
('TT', "TT", "ttbar", 831.76, {
'extraweight': 'ttptweight'
}),
]
elif era == '2017':
expsamples = [ # table of MC samples to be converted to Sample objects
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('DY', "DYJetsToLL_M-10to50", "Drell-Yan 10-50", 18610.0, {
'extraweight': 'zptweight'
}),
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 5343.0, {
'extraweight': 'zptweight'
}),
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 877.8, {
'extraweight': 'zptweight'
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 304.4, {
'extraweight': 'zptweight'
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 111.5, {
'extraweight': 'zptweight'
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 44.05, {
'extraweight': 'zptweight'
}),
('WJ', "WJetsToLNu", "W + jets", 52940.0),
('WJ', "W1JetsToLNu", "W + 1J", 8104.0),
('WJ', "W2JetsToLNu", "W + 2J", 2793.0),
('WJ', "W3JetsToLNu", "W + 3J", 992.5),
('WJ', "W4JetsToLNu", "W + 4J", 544.3),
('VV', "WW", "WW", 75.88),
('VV', "WZ", "WZ", 27.6),
('VV', "ZZ", "ZZ", 12.14),
('ST', "ST_t-channel_top", "ST t-channel t", 136.02),
('ST', "ST_t-channel_antitop", "ST t-channel at", 80.95),
('ST', "ST_tW_top", "ST tW", 35.85),
('ST', "ST_tW_antitop", "ST atW", 35.85),
('TT', "TTTo2L2Nu", "ttbar 2l2#nu", 88.29, {
'extraweight': 'ttptweight'
}),
('TT', "TTToHadronic", "ttbar hadronic", 377.96, {
'extraweight': 'ttptweight'
}),
('TT', "TTToSemiLeptonic", "ttbar semileptonic", 365.35, {
'extraweight': 'ttptweight'
}),
]
elif era == 'UL2017':
expsamples = [ # table of MC samples to be converted to Sample objects
# GROUP NAME TITLE XSEC EXTRA OPTIONS
#( 'DY', "DYJetsToLL_M-10to50", "Drell-Yan 10-50", 18610.0, {'extraweight': 'zptweight'} ),
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 5343.0, {
'extraweight': 'zptweight'
}),
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 877.8, {
'extraweight': 'zptweight'
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 304.4, {
'extraweight': 'zptweight'
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 111.5, {
'extraweight': 'zptweight'
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 44.05, {
'extraweight': 'zptweight'
}),
('WJ', "WJetsToLNu", "W + jets", 52940.0),
('WJ', "W1JetsToLNu", "W + 1J", 8104.0),
('WJ', "W2JetsToLNu", "W + 2J", 2793.0),
('WJ', "W3JetsToLNu", "W + 3J", 992.5),
('WJ', "W4JetsToLNu", "W + 4J", 544.3),
('VV', "WW", "WW", 75.88),
('VV', "WZ", "WZ", 27.6),
('VV', "ZZ", "ZZ", 12.14),
('ST', "ST_t-channel_top", "ST t-channel t", 136.02),
('ST', "ST_t-channel_antitop", "ST t-channel at", 80.95),
('ST', "ST_tW_top", "ST tW", 35.85),
('ST', "ST_tW_antitop", "ST atW", 35.85),
('TT', "TTTo2L2Nu", "ttbar 2l2#nu", 88.29, {
'extraweight': 'ttptweight'
}),
('TT', "TTToHadronic", "ttbar hadronic", 377.96, {
'extraweight': 'ttptweight'
}),
('TT', "TTToSemiLeptonic", "ttbar semileptonic", 365.35, {
'extraweight': 'ttptweight'
}),
]
elif era == '2018':
expsamples = [ # table of MC samples to be converted to Sample objects
# GROUP NAME TITLE XSEC EXTRA OPTIONS
('DY', "DYJetsToLL_M-10to50", "Drell-Yan 10-50", 18610.0, {
'extraweight': 'zptweight'
}),
('DY', "DYJetsToLL_M-50", "Drell-Yan 50", 4963.0, {
'extraweight': 'zptweight'
}),
('DY', "DY1JetsToLL_M-50", "Drell-Yan 1J 50", 1012.0, {
'extraweight': 'zptweight'
}),
('DY', "DY2JetsToLL_M-50", "Drell-Yan 2J 50", 334.7, {
'extraweight': 'zptweight'
}),
('DY', "DY3JetsToLL_M-50", "Drell-Yan 3J 50", 102.3, {
'extraweight': 'zptweight'
}),
('DY', "DY4JetsToLL_M-50", "Drell-Yan 4J 50", 54.52, {
'extraweight': 'zptweight'
}),
('WJ', "WJetsToLNu", "W + jets", 52940.0),
('WJ', "W1JetsToLNu", "W + 1J", 8104.0),
('WJ', "W2JetsToLNu", "W + 2J", 2793.0),
('WJ', "W3JetsToLNu", "W + 3J", 992.5),
('WJ', "W4JetsToLNu", "W + 4J", 544.3),
('VV', "WW", "WW", 75.88),
('VV', "WZ", "WZ", 27.6),
('VV', "ZZ", "ZZ", 12.14),
('ST', "ST_t-channel_top", "ST t-channel t", 136.02),
('ST', "ST_t-channel_antitop", "ST t-channel at", 80.95),
('ST', "ST_tW_top", "ST tW", 35.85),
('ST', "ST_tW_antitop", "ST atW", 35.85),
('TT', "TTTo2L2Nu", "ttbar 2l2#nu", 88.29, {
'extraweight': 'ttptweight'
}),
('TT', "TTToHadronic", "ttbar hadronic", 377.96, {
'extraweight': 'ttptweight'
}),
('TT', "TTToSemiLeptonic", "ttbar semileptonic", 365.35, {
'extraweight': 'ttptweight'
}),
]
else:
LOG.throw(IOError, "Did not recognize era %r!" % (era))
# OBSERVED DATA SAMPLES
if 'tautau' in channel: dataset = "Tau_Run%d?" % year
elif 'mutau' in channel: dataset = "SingleMuon_Run%d?" % year
elif 'etau' in channel:
dataset = "EGamma_Run%d?" % year if year == 2018 else "SingleElectron_Run%d?" % year
elif 'mumu' in channel:
dataset = "SingleMuon_Run%d?" % year
elif 'emu' in channel:
dataset = "SingleMuon_Run%d?" % year
elif 'ee' in channel:
dataset = "EGamma_Run%d?" % year if year == 2018 else "SingleElectron_Run%d?" % year
else:
LOG.throw(IOError, "Did not recognize channel %r!" % (channel))
datasample = ('Data', dataset) # GROUP, NAME
# SAMPLE SET
weight = "genweight*trigweight*puweight*idisoweight_1*idweight_2"
if era == 'UL2017':
weight = weight.replace("*idweight_2", "")
fname = "$PICODIR/$SAMPLE_$CHANNEL$TAG.root"
kwargs.setdefault('weight', weight) # common weight for MC
kwargs.setdefault('fname', fname) # default filename pattern
sampleset = _getsampleset(datasample,
expsamples,
channel=channel,
era=era,
**kwargs)
# JOIN
# Note: titles are set via STYLE.sample_titles
sampleset.stitch("W*Jets", incl='WJ', name='WJ') # W + jets
sampleset.stitch("DY*J*M-50", incl='DYJ',
name="DY_M50") # Drell-Yan, M > 50 GeV
#sampleset.stitch("DY*J*M-10to50", incl='DYJ', name="DY_M10to50" )
sampleset.join('DY', name='DY') # Drell-Yan, M < 50 GeV + M > 50 GeV
if 'VV' in join:
sampleset.join('VV', 'WZ', 'WW', 'ZZ', name='VV') # Diboson
if 'TT' in join and era != 'year':
sampleset.join('TT', name='TT') # ttbar
if 'ST' in join:
sampleset.join('ST', name='ST') # single top
if 'Top' in join:
sampleset.join('TT', 'ST', name='Top') # ttbar + single top
# SPLIT
# Note: titles are set via STYLE.sample_titles
if split and channel.count('tau') == 1:
ZTT = STYLE.sample_titles.get('ZTT', "Z -> %s" % channel) # title
if channel.count('tau') == 1:
ZTT = ZTT.replace("{l}", "{mu}" if "mu" in channel else "{e}")
GMR = "genmatch_2==5"
GML = "genmatch_2>0 && genmatch_2<5"
GMJ = "genmatch_2==0"
GMF = "genmatch_2<5"
elif channel.count('tau') == 2:
ZTT = ZTT.replace("{l}", "{h}")
GMR = "genmatch_1==5 && genmatch_2==5"
GML = "(genmatch_1<5 || genmatch_2<5) && genmatch_1>0 && genmatch_2>0"
GMJ = "(genmatch_1==0 || genmatch_2==0)"
GMF = "(genmatch_1<5 || genmatch_2<5)"
else:
LOG.throw(IOError, "Did not recognize channel %r!" % (channel))
if 'DY' in split:
sampleset.split('DY', [
('ZTT', ZTT, GMR),
('ZL', GML),
('ZJ', GMJ),
])
if 'DM' in split: # split DY by decay modes
samples.split('DY', [
('ZTT_DM0', ZTT + ", h^{#pm}", GMR + " && decayMode_2==0"),
('ZTT_DM1', ZTT + ", h^{#pm}h^{0}",
GMR + " && decayMode_2==1"),
('ZTT_DM10', ZTT + ", h^{#pm}h^{#mp}h^{#pm}",
GMR + " && decayMode_2==10"),
('ZTT_DM11', ZTT + ", h^{#pm}h^{#mp}h^{#pm}h^{0}",
GMR + " && decayMode_2==11"),
('ZL', GML),
('ZJ', GMJ),
])
if 'TT' in split:
sampleset.split('TT', [
('TTT', GMR),
('TTJ', GMF),
])
if table:
sampleset.printtable(merged=True, split=True)
return sampleset
