'dR03mva': 'Loose',
##'deepVSj' : 'Loose', # CV: use for datacard production
'deepVSj': 'Medium', # CV: use for datacard production
}
hadTau_selection = tau_id + hadTauWP_map[tau_id]
blacklist = []
if use_blacklist:
blacklist.append('postproc')
if use_preselected:
blacklist.append('skimmed_multilepton')
if mode == "default":
samples = load_samples(era,
suffix="preselected" if use_preselected else "")
samples = load_samples_stitched(samples, era, ['dy_nlo', 'wjets'])
elif mode == "forBDTtraining":
if use_preselected:
raise ValueError(
"Producing Ntuples for BDT training from preselected Ntuples makes no sense!"
)
samples = load_samples(era, suffix="BDT")
samples = load_samples_stitched(samples, era, ['dy_lo'])
hadTauWP_map_relaxed = {
'dR03mva': 'VLoose',
'deepVSj': 'VVVLoose', # CV: use for BDT training
}
if args.tau_id_wp:
tau_id = args.tau_id[:7]
if lep_mva_wp != 'default' and use_preselected:
raise RuntimeError(
"Cannot use skimmed samples with non-default lepton definition")
# Use the arguments
central_or_shifts = []
for systematic_label in systematics_label:
for central_or_shift in getattr(systematics, systematic_label):
if central_or_shift not in central_or_shifts:
central_or_shifts.append(central_or_shift)
lumi = get_lumi(era)
jet_cleaning_by_index = (jet_cleaning == 'by_index')
gen_matching_by_index = (gen_matching == 'by_index')
samples = load_samples(era, suffix="preselected" if use_preselected else "")
samples = load_samples_stitched(samples, era, use_stitched)
for sample_name, sample_info in samples.items():
if sample_name == 'sum_events':
continue
if sample_info["use_it"] == False:
continue
if sample_info["type"] == "mc":
sample_info["triggers"] = ["1mu", "2mu"]
if re.match("/DY(\d)?Jets", sample_name
) or sample_info["process_name_specific"].startswith("DYToLL"):
sample_info["sample_category"] = "DY"
elif sample_info["process_name_specific"].startswith(("TTTo", "TTJets")):
sample_info["sample_category"] = "TTbar"
elif re.match("/W(\d)?Jets", sample_name):
sample_info["sample_category"] = "WJets"
for central_or_shift in getattr(systematics, systematic_label):
if central_or_shift not in central_or_shifts:
central_or_shifts.append(central_or_shift)
lumi = get_lumi(era)
jet_cleaning_by_index = (jet_cleaning == 'by_index')
gen_matching_by_index = (gen_matching == 'by_index')
if mode == 'default':
samples = load_samples(era)
elif mode == 'sync':
samples = load_samples(era, suffix='leptonFR_sync')
else:
raise ValueError('Invalid mode: %s' % mode)
samples = load_samples_stitched(samples,
era,
load_dy='dy' in use_stitched,
load_wjets='wjets' in use_stitched)
for sample_name, sample_info in samples.items():
if sample_name == 'sum_events': continue
if sample_info["type"] == "mc":
sample_info["triggers"] = ["1e", "1mu", "2e", "2mu"]
if sample_info["sample_category"] == "QCD":
sample_info["use_it"] = True
if sample_info["process_name_specific"].endswith("_Mu5"):
sample_info["use_it"] = not qcd_inclusive
elif sample_info["process_name_specific"] == "QCD_Mu15":
sample_info["use_it"] = qcd_inclusive
if sample_name.startswith(('/MuonEG/Run', '/Tau/Run')):
central_or_shifts.append(central_or_shift)
do_sync = mode.startswith('sync')
lumi = get_lumi(era)
if mode == "default":
samples = load_samples(era,
suffix="preselected" if use_preselected else "")
elif mode == "forBDTtraining":
if use_preselected:
raise ValueError(
"Producing Ntuples for BDT training from preselected Ntuples makes no sense!"
)
samples = load_samples(era, suffix="BDT")
samples = load_samples_stitched(samples,
era,
load_dy=True,
load_wjets=True)
elif mode == "sync":
samples = load_samples(era, suffix="sync")
else:
raise ValueError("Internal logic error")
evtCategories = None
if mode == "default" and len(central_or_shifts) <= 1:
evtCategories = [
"hh_bb2l", "hh_bb2l_resolvedHbb", "hh_bb2l_resolvedHbb_vbf",
"hh_bb2l_resolvedHbb_nonvbf", "hh_bb2l_boostedHbb", "hh_bb2l_vbf",
"hh_bb2l_nonvbf", "hh_2bM2l", "hh_2bM2l_resolvedHbb",
"hh_2bM2l_resolvedHbb_nonvbf", "hh_2bM2l_nonvbf", "hh_1bM1bL2l",
"hh_1bM1bL2l_resolvedHbb", "hh_1bM1bL2l_resolvedHbb_nonvbf",
"hh_1bM1bL2l_nonvbf", "hh_1bM2l", "hh_1bM2l_resolvedHbb",
if use_preselected:
sample_suffix = "preselected_{}".format(sample_suffix)
samples = load_samples(era, suffix = sample_suffix)
else:
raise ValueError("Invalid mode: %s" % mode)
if not mode.startswith("sync"):
for sample_name, sample_info in samples.items():
if sample_name == 'sum_events':
continue
if era == "2018" and sample_info["sample_category"] == "tHq" and sample_info["use_it"]:
sample_info["skipEvery"] = 3
if use_stitched:
samples = load_samples_stitched(
samples, era, load_dy = 'dy' in use_stitched, load_wjets = 'wjets' in use_stitched,
disable_dy_inclusive = 'dy_noincl' in use_stitched, disable_wjets_inclusive = 'wjets_noincl' in use_stitched,
)
#--------------------------------------------------------------------------------
# CV: add ttbar MC samples to make a few extra plots for the HIG-19-008 paper
#for sample_name, sample_info in samples.items():
# if sample_name == 'sum_events':
# continue
# if sample_name.startswith(('/TTTo2L2Nu', '/TTToSemiLeptonic')):
# sample_info["use_it"] = True
#--------------------------------------------------------------------------------
if __name__ == '__main__':
logging.info(
"Running the jobs with the following systematic uncertainties enabled: %s" % \
', '.join(central_or_shifts)
from hhAnalysis.multilepton.samples.hhAnalyzeSamples_2018 import samples_2018
from tthAnalysis.HiggsToTauTau.common import load_samples_stitched
samples_2018 = load_samples_stitched(
samples_2018, '2018', ['dy_lo', 'wjets']) # load LO DY and W+jets
for sample_name, sample_info in samples_2018.items():
if sample_name == 'sum_events':
continue
process_name = sample_info["process_name_specific"]
if process_name.startswith('WZTo3LNu'):
sample_info["use_it"] = process_name.startswith(
('WZTo3LNu_powheg', 'WZTo3LNu_mllmin01'))
elif process_name.lower().startswith('ttz'):
sample_info["use_it"] = 'TTZJets_LO' in process_name
elif process_name.lower().startswith('ttw'):
sample_info["use_it"] = 'TTWJets_LO' in process_name
