def evaluateEra(self):
"""
"Era selection"
"""
self._logger.info(self.__class__.__name__ + '::' + sys._getframe().f_code.co_name)
if "2018" in self._era_name:
from shape_producer.era import Run2018 as Run2018
self.era = Run2018(self._datasets)
elif "2017" in self._era_name:
from shape_producer.era import Run2017ReReco31Mar as Run2017
self.era = Run2017(self._datasets)
else:
self.logger.critical("Era {} is not implemented.".format(self.era))
raise Exception
def main(args):
# Container for all distributions to be drawn
logger.info("Set up shape variations.")
systematics = Systematics(
"fake-factor-application/{}_ff_yields.root".format(args.tag),
num_threads=args.num_threads)
# Era selection
if "2018" in args.era:
from shape_producer.estimation_methods_2018 import DataEstimation, ZTTEstimation, ZTTEmbeddedEstimation, ZLEstimation, ZJEstimation, TTLEstimation, TTJEstimation, TTTEstimation, VVLEstimation, VVTEstimation, VVJEstimation, WEstimation
from shape_producer.era import Run2018
era = Run2018(args.datasets)
else:
logger.critical("Era {} is not implemented.".format(args.era))
raise Exception
# Channels and processes
# yapf: disable
directory = args.directory
et_friend_directory = args.et_friend_directory
mt_friend_directory = args.mt_friend_directory
tt_friend_directory = args.tt_friend_directory
mt = MTSM2018()
mt.cuts.remove("tau_iso")
mt.cuts.add(Cut("(byTightIsolationMVArun2017v2DBoldDMwLT2017_2<0.5&&byVLooseIsolationMVArun2017v2DBoldDMwLT2017_2>0.5)", "tau_anti_iso"))
mt_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"EMB" : Process("EMB", ZTTEmbeddedEstimation(era, directory, mt, friend_directory=mt_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"ZL" : Process("ZL", ZLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"TTT" : Process("TTT", TTTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"TTL" : Process("TTL", TTLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"VVT" : Process("VVT", VVTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"VVJ" : Process("VVJ", VVJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"VVL" : Process("VVL", VVLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"W" : Process("W", WEstimation (era, directory, mt, friend_directory=mt_friend_directory))
}
et = ETSM2018()
et.cuts.remove("tau_iso")
et.cuts.add(Cut("(byTightIsolationMVArun2017v2DBoldDMwLT2017_2<0.5&&byVLooseIsolationMVArun2017v2DBoldDMwLT2017_2>0.5)", "tau_anti_iso"))
et_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, et, friend_directory=et_friend_directory)),
"EMB" : Process("EMB", ZTTEmbeddedEstimation(era, directory, et, friend_directory=et_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, et, friend_directory=et_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimation (era, directory, et, friend_directory=et_friend_directory)),
"ZL" : Process("ZL", ZLEstimation (era, directory, et, friend_directory=et_friend_directory)),
"TTT" : Process("TTT", TTTEstimation (era, directory, et, friend_directory=et_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimation (era, directory, et, friend_directory=et_friend_directory)),
"TTL" : Process("TTL", TTLEstimation (era, directory, et, friend_directory=et_friend_directory)),
"VVT" : Process("VVT", VVTEstimation (era, directory, et, friend_directory=et_friend_directory)),
"VVJ" : Process("VVJ", VVJEstimation (era, directory, et, friend_directory=et_friend_directory)),
"VVL" : Process("VVL", VVLEstimation (era, directory, et, friend_directory=et_friend_directory)),
"W" : Process("W", WEstimation (era, directory, et, friend_directory=et_friend_directory))
}
#in tt two 'channels' are needed: antiisolated region for each tau respectively
tt1 = TTSM2018()
tt1.cuts.remove("tau_1_iso")
tt1.cuts.add(Cut("(byTightIsolationMVArun2017v2DBoldDMwLT2017_1<0.5&&byVLooseIsolationMVArun2017v2DBoldDMwLT2017_1>0.5)", "tau_1_anti_iso"))
tt1_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, tt1, friend_directory=tt_friend_directory)),
"EMB" : Process("EMB", ZTTEmbeddedEstimation(era, directory, tt1, friend_directory=tt_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, tt1, friend_directory=tt_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimation (era, directory, tt1, friend_directory=tt_friend_directory)),
"ZL" : Process("ZL", ZLEstimation (era, directory, tt1, friend_directory=tt_friend_directory)),
"TTT" : Process("TTT", TTTEstimation (era, directory, tt1, friend_directory=tt_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimation (era, directory, tt1, friend_directory=tt_friend_directory)),
"TTL" : Process("TTL", TTLEstimation (era, directory, tt1, friend_directory=tt_friend_directory)),
"VVT" : Process("VVT", VVTEstimation (era, directory, tt1, friend_directory=tt_friend_directory)),
"VVJ" : Process("VVJ", VVJEstimation (era, directory, tt1, friend_directory=tt_friend_directory)),
"VVL" : Process("VVL", VVLEstimation (era, directory, tt1, friend_directory=tt_friend_directory)),
"W" : Process("W", WEstimation (era, directory, tt1, friend_directory=tt_friend_directory))
}
tt2 = TTSM2018()
tt2.cuts.remove("tau_2_iso")
tt2.cuts.add(Cut("(byTightIsolationMVArun2017v2DBoldDMwLT2017_2<0.5&&byVLooseIsolationMVArun2017v2DBoldDMwLT2017_2>0.5)", "tau_2_anti_iso"))
tt2_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, tt2, friend_directory=tt_friend_directory)),
"EMB" : Process("EMB", ZTTEmbeddedEstimation(era, directory, tt2, friend_directory=tt_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, tt2, friend_directory=tt_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimation (era, directory, tt2, friend_directory=tt_friend_directory)),
"ZL" : Process("ZL", ZLEstimation (era, directory, tt2, friend_directory=tt_friend_directory)),
"TTT" : Process("TTT", TTTEstimation (era, directory, tt2, friend_directory=tt_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimation (era, directory, tt2, friend_directory=tt_friend_directory)),
"TTL" : Process("TTL", TTLEstimation (era, directory, tt2, friend_directory=tt_friend_directory)),
"VVT" : Process("VVT", VVTEstimation (era, directory, tt2, friend_directory=tt_friend_directory)),
"VVJ" : Process("VVJ", VVJEstimation (era, directory, tt2, friend_directory=tt_friend_directory)),
"VVL" : Process("VVL", VVLEstimation (era, directory, tt2, friend_directory=tt_friend_directory)),
"W" : Process("W", WEstimation (era, directory, tt2, friend_directory=tt_friend_directory))
}
# Variables and categories
config = yaml.load(open("fake-factor-application/config.yaml"))
if not args.config in config.keys():
logger.critical("Requested config key %s not available in fake-factor-application/config.yaml!" % args.config)
raise Exception
config = config[args.config]
et_categories = []
# et
et_categories.append(
Category(
"inclusive",
et,
Cuts(),
variable=Variable(args.config, VariableBinning(config["et"]["binning"]), config["et"]["expression"])))
if not args.only_inclusive:
for i, label in enumerate(["ggh", "qqh", "ztt", "zll", "w", "tt", "ss", "misc"]):
et_categories.append(
Category(
label,
et,
Cuts(
Cut("et_max_index=={index}".format(index=i), "exclusive_score")),
variable=Variable(args.config, VariableBinning(config["et"]["binning"]), config["et"]["expression"])))
mt_categories = []
# mt
mt_categories.append(
Category(
"inclusive",
mt,
Cuts(),
variable=Variable(args.config, VariableBinning(config["mt"]["binning"]), config["mt"]["expression"])))
if not args.only_inclusive:
for i, label in enumerate(["ggh", "qqh", "ztt", "zll", "w", "tt", "ss", "misc"]):
mt_categories.append(
Category(
label,
mt,
Cuts(
Cut("mt_max_index=={index}".format(index=i), "exclusive_score")),
variable=Variable(args.config, VariableBinning(config["mt"]["binning"]), config["mt"]["expression"])))
tt1_categories = []
tt2_categories = []
# tt
tt1_categories.append(
Category(
"tt1_inclusive",
tt1,
Cuts(),
variable=Variable(args.config, VariableBinning(config["tt"]["binning"]), config["tt"]["expression"])))
tt2_categories.append(
Category(
"tt2_inclusive",
tt2,
Cuts(),
variable=Variable(args.config, VariableBinning(config["tt"]["binning"]), config["tt"]["expression"])))
if not args.only_inclusive:
for i, label in enumerate(["ggh", "qqh", "ztt", "noniso", "misc"]):
tt1_categories.append(
Category(
"tt1_"+label,
tt1,
Cuts(
Cut("tt_max_index=={index}".format(index=i), "exclusive_score")),
variable=Variable(args.config, VariableBinning(config["tt"]["binning"]), config["tt"]["expression"])))
tt2_categories.append(
Category(
"tt2_"+label,
tt2,
Cuts(
Cut("tt_max_index=={index}".format(index=i), "exclusive_score")),
variable=Variable(args.config, VariableBinning(config["tt"]["binning"]), config["tt"]["expression"])))
# Nominal histograms
# yapf: enable
for process, category in product(et_processes.values(), et_categories):
systematics.add(
Systematic(category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
for process, category in product(mt_processes.values(), mt_categories):
systematics.add(
Systematic(category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
for process, category in product(tt1_processes.values(), tt1_categories):
systematics.add(
Systematic(category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
for process, category in product(tt2_processes.values(), tt2_categories):
systematics.add(
Systematic(category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
# Produce histograms
logger.info("Start producing shapes.")
systematics.produce()
logger.info("Done producing shapes.")
def main(args):
# Container for all distributions to be drawn
systematics_mm = Systematics("shapes_mm_recoilunc_2018.root",
num_threads=args.num_threads,
find_unique_objects=True)
# Era
era = Run2018(args.datasets)
# Channels and processes
# yapf: disable
directory = args.directory
mm = MM()
mm_processes = {
"ZL" : Process("ZL", ZLEstimation (era, directory, mm, friend_directory=[])),
}
# Variables and categories
binning = yaml.load(open(args.binning))
mm_categories = []
variable_bins = {
"njets" : [0, 1, 2],
"genbosonpt" : [0, 10, 20, 30, 50],
}
variable_names = [
"recoilParToZ",
"puppirecoilParToZ",
]
for njets_bin in range(len(variable_bins["njets"])):
for pt_bin in range(len(variable_bins["genbosonpt"])):
name = "njets_bin_%s_vs_ptvis_bin_%s"%(str(njets_bin),str(pt_bin))
category_njets = ""
category_pt = ""
if njets_bin == (len(variable_bins["njets"]) - 1):
category_njets = "njets >= %s"%str(variable_bins["njets"][njets_bin])
else:
category_njets = "njets == %s"%str(variable_bins["njets"][njets_bin])
if pt_bin == (len(variable_bins["genbosonpt"]) - 1):
category_pt = "genbosonpt > %s"%str(variable_bins["genbosonpt"][pt_bin])
else:
category_pt= "genbosonpt > %s && genbosonpt <= %s"%(str(variable_bins["genbosonpt"][pt_bin]),str(variable_bins["genbosonpt"][pt_bin+1]))
print category_njets, category_pt
cuts = Cuts(
Cut(category_njets,"njets_category"),
Cut(category_pt,"ptvis_category"),
Cut("m_vis > 70 && m_vis < 110","z_peak")
)
for v in variable_names:
mm_categories.append(
Category(
name,
mm,
cuts,
variable=Variable("relative_%s"%v,ConstantBinning(400,-20.0,20.0), expression="-%s/genbosonpt"%v)))
# Nominal histograms
for process, category in product(mm_processes.values(), mm_categories):
systematics_mm.add(
Systematic(
category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
# Produce histograms
systematics_mm.produce()
def main(args):
# Container for all distributions to be drawn
systematics_mm = Systematics("counts_zptm_2018.root",
num_threads=args.num_threads,
find_unique_objects=True)
# Era
era = Run2018(args.datasets)
# Channels and processes
# yapf: disable
directory = args.directory
mm = MM()
mm_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, mm, friend_directory=[])),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, mm, friend_directory=[])),
"ZL" : Process("ZL", ZLEstimation (era, directory, mm, friend_directory=[])),
"TTT" : Process("TTT", TTTEstimation (era, directory, mm, friend_directory=[])),
"TTL" : Process("TTL", TTLEstimation (era, directory, mm, friend_directory=[])),
"VVT" : Process("VVT", VVTEstimation (era, directory, mm, friend_directory=[])),
"VVL" : Process("VVL", VVLEstimation (era, directory, mm, friend_directory=[])),
"W" : Process("W", WEstimation (era, directory, mm, friend_directory=[])),
}
mm_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, mm,
[mm_processes[process] for process in ["ZTT", "ZL", "W", "TTT", "TTL", "VVT", "VVL"]],
mm_processes["data"], friend_directory=[], extrapolation_factor=2.0))
# Variables and categories
mm_categories = []
variable_bins = {
"m_vis" : [50, 100, 200, 500, 1000],
"ptvis" : [0, 10, 20, 30, 40, 50, 100, 150, 200, 300, 400, 1000],
}
for mass_bin in range(len(variable_bins["m_vis"]) - 1):
for pt_bin in range(len(variable_bins["ptvis"]) - 1):
name = "%s_bin_%s_vs_%s_bin_%s"%("m_vis",str(mass_bin),"ptvis",str(pt_bin))
cuts = Cuts(Cut("(m_vis > %s && m_vis < %s) && (ptvis > %s && ptvis < %s)"%(str(variable_bins["m_vis"][mass_bin]),str(variable_bins["m_vis"][mass_bin+1]),str(variable_bins["ptvis"][pt_bin]),str(variable_bins["ptvis"][pt_bin+1])),"zptm_category"))
mm_categories.append(
Category(
name,
mm,
cuts,
variable=None))
# Nominal histograms
for process, category in product(mm_processes.values(), mm_categories):
#if process.name in ["ZTT","ZLL"]:
# process.estimation_method.get_weights().remove("zPtReweightWeight")
systematics_mm.add(
Systematic(
category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
# Produce histograms
systematics_mm.produce()
def main(args):
# Write arparse arguments to YAML config
logger.debug("Write argparse arguments to YAML config.")
output_config = {}
output_config["base_path"] = args.base_path
output_config["friend_paths"] = args.friend_paths
output_config["output_path"] = args.output_path
output_config["output_filename"] = args.output_filename
output_config["tree_path"] = args.tree_path
output_config["event_branch"] = args.event_branch
output_config["training_weight_branch"] = args.training_weight_branch
logger.debug("Channel" + args.channel + " Era " + args.era)
# Define era
if "2016" in args.era:
from shape_producer.estimation_methods_2016 import DataEstimation, ggHEstimation, qqHEstimation, \
ZTTEstimation, ZLEstimation, ZJEstimation, TTTEstimation, TTJEstimation, \
ZTTEmbeddedEstimation, TTLEstimation, \
EWKZEstimation, VVLEstimation, VVTEstimation, VVJEstimation, WEstimation
from shape_producer.era import Run2016
era = Run2016(args.database)
elif "2017" in args.era:
from shape_producer.estimation_methods_2017 import DataEstimation, ZTTEstimation, ZJEstimation, ZLEstimation, \
TTLEstimation, TTJEstimation, TTTEstimation, VVTEstimation, VVJEstimation, VVLEstimation, WEstimation, \
ggHEstimation, qqHEstimation, EWKZEstimation, ZTTEmbeddedEstimation
from shape_producer.era import Run2017
era = Run2017(args.database)
elif "2018" in args.era:
from shape_producer.estimation_methods_2018 import DataEstimation, ZTTEstimation, ZJEstimation, ZLEstimation, \
TTLEstimation, TTJEstimation, TTTEstimation, VVTEstimation, VVJEstimation, VVLEstimation, WEstimation, \
ggHEstimation, qqHEstimation, EWKZEstimation, ZTTEmbeddedEstimation
from shape_producer.era import Run2018
era = Run2018(args.database)
else:
logger.fatal("Era {} is not implemented.".format(args.era))
raise Exception
def estimationMethodAndClassMapGenerator():
###### common processes
if args.training_stxs1p1:
classes_map = {
# class1
"ggH_GG2H_PTH_GT200125": "ggh_PTHGT200",
# class2
"ggH_GG2H_0J_PTH_0_10125": "ggh_0J",
"ggH_GG2H_0J_PTH_GT10125": "ggh_0J",
# class3
"ggH_GG2H_1J_PTH_0_60125": "ggh_1J_PTH0to120",
"ggH_GG2H_1J_PTH_60_120125": "ggh_1J_PTH0to120",
# class4
"ggH_GG2H_1J_PTH_120_200125": "ggh_1J_PTH120to200",
# class5
"ggH_GG2H_GE2J_MJJ_0_350_PTH_0_60125": "ggh_2J",
"ggH_GG2H_GE2J_MJJ_0_350_PTH_60_120125": "ggh_2J",
"ggH_GG2H_GE2J_MJJ_0_350_PTH_120_200125": "ggh_2J",
# class6
"ggH_GG2H_GE2J_MJJ_350_700_PTH_0_200_PTHJJ_0_25125": "vbftopo_lowmjj",
"ggH_GG2H_GE2J_MJJ_350_700_PTH_0_200_PTHJJ_GT25125": "vbftopo_lowmjj",
"qqH_QQ2HQQ_GE2J_MJJ_350_700_PTH_0_200_PTHJJ_0_25125": "vbftopo_lowmjj",
"qqH_QQ2HQQ_GE2J_MJJ_350_700_PTH_0_200_PTHJJ_GT25125": "vbftopo_lowmjj",
# class7
"ggH_GG2H_GE2J_MJJ_GT700_PTH_0_200_PTHJJ_0_25125": "vbftopo_highmjj",
"ggH_GG2H_GE2J_MJJ_GT700_PTH_0_200_PTHJJ_GT25125": "vbftopo_highmjj",
"qqH_QQ2HQQ_GE2J_MJJ_GT700_PTH_0_200_PTHJJ_0_25125": "vbftopo_highmjj",
"qqH_QQ2HQQ_GE2J_MJJ_GT700_PTH_0_200_PTHJJ_GT25125": "vbftopo_highmjj",
# class8
"qqH_QQ2HQQ_GE2J_MJJ_0_60125": "qqh_2J",
"qqH_QQ2HQQ_GE2J_MJJ_60_120125": "qqh_2J",
"qqH_QQ2HQQ_GE2J_MJJ_120_350125": "qqh_2J",
# class9
"qqH_QQ2HQQ_GE2J_MJJ_GT350_PTH_GT200125": "qqh_PTHGT200",
}
estimationMethodList = [
ggHEstimation("ggH_GG2H_PTH_GT200125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_0J_PTH_0_10125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_0J_PTH_GT10125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_1J_PTH_0_60125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_1J_PTH_60_120125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_1J_PTH_120_200125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_GE2J_MJJ_0_350_PTH_0_60125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_GE2J_MJJ_0_350_PTH_60_120125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_GE2J_MJJ_0_350_PTH_120_200125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_GE2J_MJJ_350_700_PTH_0_200_PTHJJ_0_25125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_GE2J_MJJ_350_700_PTH_0_200_PTHJJ_GT25125", era, args.base_path, channel),
qqHEstimation("qqH_QQ2HQQ_GE2J_MJJ_350_700_PTH_0_200_PTHJJ_0_25125", era, args.base_path, channel),
qqHEstimation("qqH_QQ2HQQ_GE2J_MJJ_350_700_PTH_0_200_PTHJJ_GT25125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_GE2J_MJJ_GT700_PTH_0_200_PTHJJ_0_25125", era, args.base_path, channel),
ggHEstimation("ggH_GG2H_GE2J_MJJ_GT700_PTH_0_200_PTHJJ_GT25125", era, args.base_path, channel),
qqHEstimation("qqH_QQ2HQQ_GE2J_MJJ_GT700_PTH_0_200_PTHJJ_0_25125", era, args.base_path, channel),
qqHEstimation("qqH_QQ2HQQ_GE2J_MJJ_GT700_PTH_0_200_PTHJJ_GT25125", era, args.base_path, channel),
qqHEstimation("qqH_QQ2HQQ_GE2J_MJJ_0_60125", era, args.base_path, channel),
qqHEstimation("qqH_QQ2HQQ_GE2J_MJJ_60_120125", era, args.base_path, channel),
qqHEstimation("qqH_QQ2HQQ_GE2J_MJJ_120_350125", era, args.base_path, channel),
qqHEstimation("qqH_QQ2HQQ_GE2J_MJJ_GT350_PTH_GT200125", era, args.base_path, channel),
]
elif args.training_inclusive:
classes_map = {
"ggH125": "xxh",
"qqH125": "xxh",
}
estimationMethodList = [
ggHEstimation("ggH125", era, args.base_path, channel),
qqHEstimation("qqH125", era, args.base_path, channel),
]
else:
classes_map = {
"ggH125": "ggh",
"qqH125": "qqh",
}
estimationMethodList = [
ggHEstimation("ggH125", era, args.base_path, channel),
qqHEstimation("qqH125", era, args.base_path, channel),
]
estimationMethodList.extend([
EWKZEstimation(era, args.base_path, channel),
VVLEstimation(era, args.base_path, channel)
])
classes_map["EWKZ"]="misc"
##### TT* zl,zj processes
estimationMethodList.extend([
TTLEstimation(era, args.base_path, channel),
ZLEstimation(era, args.base_path, channel)
])
if args.channel == "tt":
classes_map.update({
"TTL": "misc",
"ZL": "misc",
"VVL": "misc"
})
## not TTJ,ZJ for em
elif args.channel == "em":
classes_map.update({
"TTL": "tt",
"ZL": "misc",
"VVL": "db"
})
else:
classes_map.update({
"TTL": "tt",
"ZL": "zll",
"VVL": "misc"
})
######## Check for emb vs MC
if args.training_z_estimation_method == "emb":
classes_map["EMB"] = "emb"
estimationMethodList.extend([
ZTTEmbeddedEstimation(era, args.base_path, channel)])
elif args.training_z_estimation_method == "mc":
classes_map["ZTT"] = "ztt"
estimationMethodList.extend([
ZTTEstimation(era, args.base_path, channel),
TTTEstimation(era, args.base_path, channel),
VVTEstimation(era, args.base_path, channel)
])
if args.channel == "tt":
classes_map.update({
"TTT": "misc",
"VVT": "misc"
})
## not TTJ,ZJ for em
elif args.channel == "em":
classes_map.update({
"TTT": "tt",
"VVT": "db"
})
else:
classes_map.update({
"TTT": "tt",
"VVT": "misc"
})
else:
logger.fatal("No valid training-z-estimation-method! Options are emb, mc. Argument was {}".format(
args.training_z_estimation_method))
raise Exception
if args.training_jetfakes_estimation_method == "ff" and args.channel != "em":
classes_map.update({
"ff": "ff"
})
elif args.training_jetfakes_estimation_method == "mc" or args.channel == "em":
# less data-> less categories for tt
if args.channel == "tt":
classes_map.update({
"TTJ": "misc",
"ZJ": "misc"
})
## not TTJ,ZJ for em
elif args.channel != "em":
classes_map.update({
"TTJ": "tt",
"ZJ": "zll"
})
if args.channel != "em":
classes_map.update({
"VVJ": "misc"
})
estimationMethodList.extend([
VVJEstimation(era, args.base_path, channel),
ZJEstimation(era, args.base_path, channel),
TTJEstimation(era, args.base_path, channel)
])
###w:
estimationMethodList.extend([WEstimation(era, args.base_path, channel)])
if args.channel in ["et", "mt"]:
classes_map["W"] = "w"
else:
classes_map["W"] = "misc"
### QCD class
if args.channel == "tt":
classes_map["QCD"] = "noniso"
else:
classes_map["QCD"] = "ss"
else:
logger.fatal("No valid training-jetfakes-estimation-method! Options are ff, mc. Argument was {}".format(
args.training_jetfakes_estimation_method))
raise Exception
return ([classes_map, estimationMethodList])
channelDict = {}
channelDict["2016"] = {"mt": MTSM2016(), "et": ETSM2016(), "tt": TTSM2016(), "em": EMSM2016()}
channelDict["2017"] = {"mt": MTSM2017(), "et": ETSM2017(), "tt": TTSM2017(), "em": EMSM2017()}
channelDict["2018"] = {"mt": MTSM2018(), "et": ETSM2018(), "tt": TTSM2018(), "em": EMSM2018()}
channel = channelDict[args.era][args.channel]
# Set up `processes` part of config
output_config["processes"] = {}
# Additional cuts
additional_cuts = Cuts()
logger.warning("Use additional cuts for mt: %s", additional_cuts.expand())
classes_map, estimationMethodList = estimationMethodAndClassMapGenerator()
### disables all other estimation methods
# classes_map={"ff":"ff"}
# estimationMethodList=[]
for estimation in estimationMethodList:
output_config["processes"][estimation.name] = {
"files": [
str(f).replace(args.base_path.rstrip("/") + "/", "")
for f in estimation.get_files()
],
"cut_string": (estimation.get_cuts() + channel.cuts +
additional_cuts).expand(),
"weight_string":
estimation.get_weights().extract(),
"class":
classes_map[estimation.name]
}
if args.training_jetfakes_estimation_method == "mc" or args.channel == "em":
if args.training_jetfakes_estimation_method == "ff":
logger.warn("ff+em: using mc for em channel")
# Same sign selection for data-driven QCD
estimation = DataEstimation(era, args.base_path, channel)
estimation.name = "QCD"
channel_qcd = copy.deepcopy(channel)
if args.channel != "tt":
## os= opposite sign
channel_qcd.cuts.get("os").invert()
# Same sign selection for data-driven QCD
else:
channel_qcd.cuts.remove("tau_2_iso")
channel_qcd.cuts.add(
Cut("byTightDeepTau2017v2p1VSjet_2<0.5", "tau_2_iso"))
channel_qcd.cuts.add(
Cut("byMediumDeepTau2017v2p1VSjet_2>0.5", "tau_2_iso_loose"))
output_config["processes"][estimation.name] = {
"files": [
str(f).replace(args.base_path.rstrip("/") + "/", "")
for f in estimation.get_files()
],
"cut_string": (estimation.get_cuts() + channel_qcd.cuts + additional_cuts).expand(),
"weight_string": estimation.get_weights().extract(),
"class": classes_map[estimation.name]
}
else: ## ff and not em
estimation = DataEstimation(era, args.base_path, channel)
estimation.name = "ff"
aiso = copy.deepcopy(channel)
if args.channel in ["et", "mt"]:
aisoCut = Cut(
"byTightDeepTau2017v2p1VSjet_2<0.5&&byVLooseDeepTau2017v2p1VSjet_2>0.5",
"tau_aiso")
fakeWeightstring = "ff2_nom"
aiso.cuts.remove("tau_iso")
elif args.channel == "tt":
aisoCut = Cut(
"(byTightDeepTau2017v2p1VSjet_2>0.5&&byTightDeepTau2017v2p1VSjet_1<0.5&&byVLooseDeepTau2017v2p1VSjet_1>0.5)||(byTightDeepTau2017v2p1VSjet_1>0.5&&byTightDeepTau2017v2p1VSjet_2<0.5&&byVLooseDeepTau2017v2p1VSjet_2>0.5)",
"tau_aiso")
fakeWeightstring = "(0.5*ff1_nom*(byTightDeepTau2017v2p1VSjet_1<0.5)+0.5*ff2_nom*(byTightDeepTau2017v2p1VSjet_2<0.5))"
aiso.cuts.remove("tau_1_iso")
aiso.cuts.remove("tau_2_iso")
# self._nofake_processes = [copy.deepcopy(p) for p in nofake_processes]
aiso.cuts.add(aisoCut)
additionalWeights = Weights(Weight(fakeWeightstring, "fake_factor"))
output_config["processes"][estimation.name] = {
"files": [
str(f).replace(args.base_path.rstrip("/") + "/", "")
for f in estimation.get_files()
],
"cut_string": (estimation.get_cuts() + aiso.cuts).expand(),
"weight_string": (estimation.get_weights() + additionalWeights).extract(),
"class": classes_map[estimation.name]
}
output_config["datasets"] = [args.output_path + "/fold" + fold + "_training_dataset.root" for fold in ["0", "1"]]
#####################################
# Write output config
logger.info("Write config to file: {}".format(args.output_config))
yaml.dump(output_config, open(args.output_config, 'w'), default_flow_style=False)
def main(args):
# Write arparse arguments to YAML config
filelist = {}
# Define era
if "2016" in args.era:
from shape_producer.estimation_methods_2016 import DataEstimation, ggHEstimation, qqHEstimation, ZTTEstimation, ZLEstimation, ZJEstimation, WEstimation, TTTEstimation, TTJEstimation, ZTTEmbeddedEstimation, TTLEstimation, EWKZEstimation, VVLEstimation, VVJEstimation, VVEstimation, VVTEstimation, VHEstimation, EWKWpEstimation, EWKWmEstimation, ttHEstimation, ggHWWEstimation, qqHWWEstimation
#QCDEstimation_SStoOS_MTETEM, QCDEstimationTT, HTTEstimation,
from shape_producer.era import Run2016
era = Run2016(args.database)
elif "2017" in args.era:
from shape_producer.estimation_methods_2017 import DataEstimation, ZTTEstimation, ZLEstimation, ZJEstimation, TTLEstimation, TTJEstimation, TTTEstimation, VVTEstimation, VVJEstimation, VVLEstimation, WEstimation, ggHEstimation, qqHEstimation, VHEstimation, EWKZEstimation, ZTTEmbeddedEstimation, ttHEstimation
from shape_producer.era import Run2017
era = Run2017(args.database)
elif "2018" in args.era:
from shape_producer.estimation_methods_2018 import DataEstimation, ZTTEstimation, ZLEstimation, ZJEstimation, TTLEstimation, TTJEstimation, TTTEstimation, VVTEstimation, VVJEstimation, VVLEstimation, WEstimation, ggHEstimation, qqHEstimation, VHEstimation, EWKZEstimation, ZTTEmbeddedEstimation, ttHEstimation
from shape_producer.era import Run2018
era = Run2018(args.database)
else:
logger.fatal("Era {} is not implemented.".format(args.era))
raise Exception
logger.debug("Write filelist for channel %s in era %s.", args.channel,
args.era)
############################################################################
# Era: 2016, Channel: mt
if "2016" in args.era and args.channel == "mt":
channel = MTSM2016()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
#ZTTEmbeddedEstimation(era, args.directory, channel), #TODO include EMB again once samples are there
ZLEstimation(era, args.directory, channel),
ZJEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
TTJEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
EWKWpEstimation(era, args.directory, channel),
EWKWmEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel),
ggHWWEstimation(era, args.directory, channel),
qqHWWEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Era: 2017, Channel: mt
if "2017" in args.era and args.channel == "mt":
channel = MTSM2017()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
ZTTEmbeddedEstimation(era, args.directory, channel),
ZLEstimation(era, args.directory, channel),
ZJEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTJEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVJEstimation(era, args.directory, channel),
VVTEstimation(era, args.directory, channel),
VVLEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Era: 2018, Channel: mt
if "2018" in args.era and args.channel == "mt":
channel = MTSM2018()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
ZTTEmbeddedEstimation(era, args.directory, channel),
ZLEstimation(era, args.directory, channel),
ZJEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTJEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVJEstimation(era, args.directory, channel),
VVTEstimation(era, args.directory, channel),
VVLEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Era: 2016, Channel: et
if "2016" in args.era and args.channel == "et":
channel = ETSM2016()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
#ZTTEmbeddedEstimation(era, args.directory, channel), #TODO include EMB again once samples are there
ZLEstimation(era, args.directory, channel),
ZJEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
TTJEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
EWKWpEstimation(era, args.directory, channel),
EWKWmEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel),
ggHWWEstimation(era, args.directory, channel),
qqHWWEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Era: 2017, Channel: et
if "2017" in args.era and args.channel == "et":
channel = ETSM2017()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
ZTTEmbeddedEstimation(era, args.directory, channel),
ZLEstimation(era, args.directory, channel),
ZJEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTJEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVJEstimation(era, args.directory, channel),
VVTEstimation(era, args.directory, channel),
VVLEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Era: 2018, Channel: et
if "2018" in args.era and args.channel == "et":
channel = ETSM2018()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
ZTTEmbeddedEstimation(era, args.directory, channel),
ZLEstimation(era, args.directory, channel),
ZJEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTJEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVJEstimation(era, args.directory, channel),
VVTEstimation(era, args.directory, channel),
VVLEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Era: 2016, Channel: tt
if "2016" in args.era and args.channel == "tt":
channel = TTSM2016()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
#ZTTEmbeddedEstimation(era, args.directory, channel), #TODO include EMB again once samples are there
ZLEstimation(era, args.directory, channel),
ZJEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
TTJEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
EWKWpEstimation(era, args.directory, channel),
EWKWmEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel),
ggHWWEstimation(era, args.directory, channel),
qqHWWEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Era 2017, Channel: tt
if "2017" in args.era and args.channel == "tt":
channel = TTSM2017()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
ZTTEmbeddedEstimation(era, args.directory, channel),
ZLEstimation(era, args.directory, channel),
ZJEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTJEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVJEstimation(era, args.directory, channel),
VVTEstimation(era, args.directory, channel),
VVLEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Era 2018, Channel: tt
if "2018" in args.era and args.channel == "tt":
channel = TTSM2018()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
ZTTEmbeddedEstimation(era, args.directory, channel),
ZLEstimation(era, args.directory, channel),
ZJEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTJEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVJEstimation(era, args.directory, channel),
VVTEstimation(era, args.directory, channel),
VVLEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Era: 2016, Channel: em
if "2016" in args.era and args.channel == "em":
channel = EMSM2016()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
#ZTTEmbeddedEstimation(era, args.directory, channel), #TODO include EMB again once samples are there
ZLEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
EWKWpEstimation(era, args.directory, channel),
EWKWmEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel),
ggHWWEstimation(era, args.directory, channel),
qqHWWEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Era: 2017, Channel: em
if "2017" in args.era and args.channel == "em":
channel = EMSM2017()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
ZTTEmbeddedEstimation(era, args.directory, channel),
ZLEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVTEstimation(era, args.directory, channel),
VVLEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Era: 2018, Channel: em
if "2018" in args.era and args.channel == "em":
channel = EMSM2018()
for estimation in [
ggHEstimation("ggH", era, args.directory, channel),
qqHEstimation("qqH", era, args.directory, channel),
ttHEstimation(era, args.directory, channel),
VHEstimation(era, args.directory, channel),
ZTTEstimation(era, args.directory, channel),
ZTTEmbeddedEstimation(era, args.directory, channel),
ZLEstimation(era, args.directory, channel),
TTTEstimation(era, args.directory, channel),
TTLEstimation(era, args.directory, channel),
WEstimation(era, args.directory, channel),
VVTEstimation(era, args.directory, channel),
VVLEstimation(era, args.directory, channel),
EWKZEstimation(era, args.directory, channel),
DataEstimation(era, args.directory, channel)
]:
# Get files for estimation method
logger.debug("Get files for estimation method %s.",
estimation.name)
files = [str(f) for f in estimation.get_files()]
# Go through files and get folders for channel
for f in files:
if not os.path.exists(f):
logger.fatal("File does not exist: %s", f)
raise Exception
folders = []
f_ = ROOT.TFile(f)
for k in f_.GetListOfKeys():
if "{}_".format(args.channel) in k.GetName():
folders.append(k.GetName())
f_.Close()
filelist[f] = folders
############################################################################
# Write output filelist
logger.info("Write filelist to file: {}".format(args.output))
yaml.dump(filelist, open(args.output, 'w'), default_flow_style=False)
def main(args):
# Container for all distributions to be drawn
systematics_mt = Systematics("shapes_mt_2018.root", num_threads=args.num_threads, find_unique_objects=True)
systematics_et = Systematics("shapes_et_2018.root", num_threads=args.num_threads, find_unique_objects=True)
systematics_tt = Systematics("shapes_tt_2018.root", num_threads=args.num_threads, find_unique_objects=True)
systematics_em = Systematics("shapes_em_2018.root", num_threads=args.num_threads, find_unique_objects=True)
systematics_mm = Systematics("shapes_mm_2018.root", num_threads=args.num_threads, find_unique_objects=True)
# Era
era = Run2018(args.datasets)
# Channels and processes
# yapf: disable
directory = args.directory
et_friend_directory = args.et_friend_directory
mt_friend_directory = args.mt_friend_directory
tt_friend_directory = args.tt_friend_directory
em_friend_directory = args.em_friend_directory
mm_friend_directory = args.mm_friend_directory
ff_friend_directory = args.fake_factor_friend_directory
#mt = MT()
#mt_processes = {
# "data" : Process("data_obs", DataEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "ZTT" : Process("ZTT", ZTTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "EMB" : Process("EMB", ZTTEmbeddedEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "ZJ" : Process("ZJ", ZJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "ZL" : Process("ZL", ZLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "TTT" : Process("TTT", TTTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "TTJ" : Process("TTJ", TTJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "TTL" : Process("TTL", TTLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "VVT" : Process("VVT", VVTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "VVJ" : Process("VVJ", VVJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "VVL" : Process("VVL", VVLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "W" : Process("W", WEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH" : Process("ggH125", ggHEstimation ("ggH125", era, directory, mt, friend_directory=mt_friend_directory)),
# "qqH" : Process("qqH125", qqHEstimation ("qqH125", era, directory, mt, friend_directory=mt_friend_directory)),
# "VH" : Process("VH125", VHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "WH" : Process("WH125", WHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "ZH" : Process("ZH125", ZHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "ttH" : Process("ttH125", ttHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# }
#mt_processes["FAKES"] = Process("jetFakes", NewFakeEstimationLT(era, directory, mt, [mt_processes[process] for process in ["ZTT", "ZL", "TTT", "TTL", "VVT", "VVL"]], mt_processes["data"], friend_directory=mt_friend_directory+[ff_friend_directory]))
#mt_processes["FAKESEMB"] = Process("jetFakesEMB", NewFakeEstimationLT(era, directory, mt, [mt_processes[process] for process in ["EMB", "ZL", "TTL", "VVL"]], mt_processes["data"], friend_directory=mt_friend_directory+[ff_friend_directory]))
#mt_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, mt,
# [mt_processes[process] for process in ["ZTT", "ZL", "ZJ", "W", "TTT", "TTJ", "TTL", "VVT", "VVJ", "VVL"]],
# mt_processes["data"], friend_directory=mt_friend_directory, extrapolation_factor=1.00))
#mt_processes["QCDEMB"] = Process("QCDEMB", QCDEstimation_SStoOS_MTETEM(era, directory, mt,
# [mt_processes[process] for process in ["EMB", "ZL", "ZJ", "W", "TTJ", "TTL", "VVJ", "VVL"]],
# mt_processes["data"], friend_directory=mt_friend_directory, extrapolation_factor=1.00))
#et = ET()
#et_processes = {
# "data" : Process("data_obs", DataEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "ZTT" : Process("ZTT", ZTTEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "EMB" : Process("EMB", ZTTEmbeddedEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "ZJ" : Process("ZJ", ZJEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "ZL" : Process("ZL", ZLEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "TTT" : Process("TTT", TTTEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "TTJ" : Process("TTJ", TTJEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "TTL" : Process("TTL", TTLEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "VVT" : Process("VVT", VVTEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "VVJ" : Process("VVJ", VVJEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "VVL" : Process("VVL", VVLEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "W" : Process("W", WEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "ggH" : Process("ggH125", ggHEstimation ("ggH125", era, directory, et, friend_directory=et_friend_directory)),
# "qqH" : Process("qqH125", qqHEstimation ("qqH125", era, directory, et, friend_directory=et_friend_directory)),
# "VH" : Process("VH125", VHEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "WH" : Process("WH125", WHEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "ZH" : Process("ZH125", ZHEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "ttH" : Process("ttH125", ttHEstimation (era, directory, et, friend_directory=et_friend_directory)),
# }
#et_processes["FAKES"] = Process("jetFakes", NewFakeEstimationLT(era, directory, et, [et_processes[process] for process in ["ZTT", "ZL", "TTT", "TTL", "VVT", "VVL"]], et_processes["data"], friend_directory=et_friend_directory+[ff_friend_directory]))
#et_processes["FAKESEMB"] = Process("jetFakesEMB", NewFakeEstimationLT(era, directory, et, [et_processes[process] for process in ["EMB", "ZL", "TTL", "VVL"]], et_processes["data"], friend_directory=et_friend_directory+[ff_friend_directory]))
#et_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, et,
# [et_processes[process] for process in ["ZTT", "ZL", "ZJ", "W", "TTT", "TTJ", "TTL", "VVT", "VVJ", "VVL"]],
# et_processes["data"], friend_directory=et_friend_directory, extrapolation_factor=1.00))
#et_processes["QCDEMB"] = Process("QCDEMB", QCDEstimation_SStoOS_MTETEM(era, directory, et,
# [et_processes[process] for process in ["EMB", "ZL", "ZJ", "W", "TTJ", "TTL", "VVJ", "VVL"]],
# et_processes["data"], friend_directory=et_friend_directory, extrapolation_factor=1.00))
#tt = TT()
#tt_processes = {
# "data" : Process("data_obs", DataEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "ZTT" : Process("ZTT", ZTTEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "EMB" : Process("EMB", ZTTEmbeddedEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "ZJ" : Process("ZJ", ZJEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "ZL" : Process("ZL", ZLEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "TTT" : Process("TTT", TTTEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "TTJ" : Process("TTJ", TTJEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "TTL" : Process("TTL", TTLEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "VVT" : Process("VVT", VVTEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "VVJ" : Process("VVJ", VVJEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "VVL" : Process("VVL", VVLEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "W" : Process("W", WEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH" : Process("ggH125", ggHEstimation ("ggH125", era, directory, tt, friend_directory=tt_friend_directory)),
# "qqH" : Process("qqH125", qqHEstimation ("qqH125", era, directory, tt, friend_directory=tt_friend_directory)),
# "VH" : Process("VH125", VHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "WH" : Process("WH125", WHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "ZH" : Process("ZH125", ZHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "ttH" : Process("ttH125", ttHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# }
#tt_processes["FAKESEMB"] = Process("jetFakesEMB", NewFakeEstimationTT(era, directory, tt, [tt_processes[process] for process in ["EMB", "ZL", "TTL", "VVL"]], tt_processes["data"], friend_directory=tt_friend_directory+[ff_friend_directory]))
#tt_processes["FAKES"] = Process("jetFakes", NewFakeEstimationTT(era, directory, tt, [tt_processes[process] for process in ["ZTT", "ZL", "TTT", "TTL", "VVT", "VVL"]], tt_processes["data"], friend_directory=tt_friend_directory+[ff_friend_directory]))
#tt_processes["QCD"] = Process("QCD", QCDEstimation_ABCD_TT_ISO2(era, directory, tt,
# [tt_processes[process] for process in ["ZTT", "ZL", "ZJ", "W", "TTT", "TTJ", "TTL", "VVT", "VVJ", "VVL"]],
# tt_processes["data"], friend_directory=tt_friend_directory))
#tt_processes["QCDEMB"] = Process("QCDEMB", QCDEstimation_ABCD_TT_ISO2(era, directory, tt,
# [tt_processes[process] for process in ["EMB", "ZL", "ZJ", "W", "TTJ", "TTL", "VVJ", "VVL"]],
# tt_processes["data"], friend_directory=tt_friend_directory))
#em = EM()
#em_processes = {
# "data" : Process("data_obs", DataEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "ZTT" : Process("ZTT", ZTTEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "EMB" : Process("EMB", ZTTEmbeddedEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "ZL" : Process("ZL", ZLEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "TTT" : Process("TTT", TTTEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "TTL" : Process("TTL", TTLEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "VVT" : Process("VVT", VVTEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "VVL" : Process("VVL", VVLEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "W" : Process("W", WEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "ggH" : Process("ggH125", ggHEstimation ("ggH125", era, directory, em, friend_directory=em_friend_directory)),
# "qqH" : Process("qqH125", qqHEstimation ("qqH125", era, directory, em, friend_directory=em_friend_directory)),
# "VH" : Process("VH125", VHEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "WH" : Process("WH125", WHEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "ZH" : Process("ZH125", ZHEstimation (era, directory, em, friend_directory=em_friend_directory)),
# "ttH" : Process("ttH125", ttHEstimation (era, directory, em, friend_directory=em_friend_directory)),
# }
#em_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, em, [em_processes[process] for process in ["ZTT", "ZL", "W", "TTT", "VVT", "VVL"]], em_processes["data"], extrapolation_factor=1.0, qcd_weight = Weight("em_qcd_extrap_up_Weight","qcd_weight")))
#em_processes["QCDEMB"] = Process("QCDEMB", QCDEstimation_SStoOS_MTETEM(era, directory, em, [em_processes[process] for process in ["EMB", "ZL", "W", "VVL"]], em_processes["data"], extrapolation_factor=1.0, qcd_weight = Weight("em_qcd_extrap_up_Weight","qcd_weight")))
mm = MM()
mm_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"ZL" : Process("ZL", ZLEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"TTT" : Process("TTT", TTTEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"TTL" : Process("TTL", TTLEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"VVT" : Process("VVT", VVTEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"VVL" : Process("VVL", VVLEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"W" : Process("W", WEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
}
mm_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, mm,
[mm_processes[process] for process in ["ZTT", "ZL", "W", "TTT", "TTL", "VVT", "VVL"]],
mm_processes["data"], friend_directory=mm_friend_directory, extrapolation_factor=2.0))
# Variables and categories
binning = yaml.load(open(args.binning))
mt_categories = []
et_categories = []
tt_categories = []
em_categories = []
mm_categories = []
variable_names = [
"m_vis", "ptvis",
# "DiTauDeltaR",
# "m_sv", "pt_sv", "eta_sv",
# "m_sv_puppi", "pt_sv_puppi", "eta_sv_puppi",
# "m_fastmtt", "pt_fastmtt", "eta_fastmtt",
# "m_fastmtt_puppi", "pt_fastmtt_puppi", "eta_fastmtt_puppi",
# "ME_D", "ME_vbf", "ME_z2j_1", "ME_z2j_2", "ME_q2v1", "ME_q2v2", "ME_costheta1", "ME_costheta2", "ME_costhetastar", "ME_phi", "ME_phi1",
"pt_1", "pt_2", "eta_1", "eta_2",
# "mjj", "jdeta", "dijetpt",
"njets", "jpt_1", "jpt_2", "jeta_1", "jeta_2",
# "nbtag", "bpt_1", "bpt_2", "beta_1", "beta_2",
"met", #"mt_1", "mt_2", "pt_tt", "pZetaMissVis", "pt_ttjj", "mt_tot", "mTdileptonMET",
"puppimet", #"mt_1_puppi", "mt_2_puppi", "pt_tt_puppi", "pZetaPuppiMissVis", "pt_ttjj_puppi", "mt_tot_puppi", "mTdileptonMET_puppi",
# "NNrecoil_pt", "nnmet", "mt_1_nn", "mt_2_nn", "pt_tt_nn", "pZetaNNMissVis", "pt_ttjj_nn", "mt_tot_nn", "mTdileptonMET_nn",
"metParToZ", "metPerpToZ",
"puppimetParToZ", "puppimetPerpToZ",
]
#if "mt" in args.channels:
# variables = [Variable(v,VariableBinning(binning["control"]["mt"][v]["bins"]), expression=binning["control"]["mt"][v]["expression"]) for v in variable_names]
# cuts = Cuts()
# for name, var in zip(variable_names, variables):
# mt_categories.append(
# Category(
# name,
# mt,
# cuts,
# variable=var))
#if "et" in args.channels:
# variables = [Variable(v,VariableBinning(binning["control"]["et"][v]["bins"]), expression=binning["control"]["et"][v]["expression"]) for v in variable_names]
# cuts = Cuts()
# for name, var in zip(variable_names, variables):
# et_categories.append(
# Category(
# name,
# et,
# cuts,
# variable=var))
#if "tt" in args.channels:
# variables = [Variable(v,VariableBinning(binning["control"]["tt"][v]["bins"]), expression=binning["control"]["tt"][v]["expression"]) for v in variable_names]
# cuts = Cuts()
# for name, var in zip(variable_names, variables):
# tt_categories.append(
# Category(
# name,
# tt,
# cuts,
# variable=var))
#if "em" in args.channels:
# variables = [Variable(v,VariableBinning(binning["control"]["em"][v]["bins"]), expression=binning["control"]["em"][v]["expression"]) for v in variable_names]
# cuts = Cuts()
# for name, var in zip(variable_names, variables):
# em_categories.append(
# Category(
# name,
# em,
# cuts,
# variable=var))
if "mm" in args.channels:
variables = [Variable(v,VariableBinning(binning["control"]["mm"][v]["bins"]), expression=binning["control"]["mm"][v]["expression"]) for v in variable_names]
variables.append(Variable("m_vis_high",ConstantBinning(19,50.0,1000.0),expression="m_vis"))
variable_names.append("m_vis_high")
cuts = Cuts()
for name, var in zip(variable_names, variables):
mm_categories.append(
Category(
name,
mm,
cuts,
variable=var))
mm_categories.append(
Category(
name+"_peak",
mm,
Cuts(Cut("m_vis > 70 && m_vis < 110","m_vis_peak")),
variable=var))
# Nominal histograms
#if "mt" in args.channels:
# for process, category in product(mt_processes.values(), mt_categories):
# systematics_mt.add(
# Systematic(
# category=category,
# process=process,
# analysis="smhtt",
# era=era,
# variation=Nominal(),
# mass="125"))
#if "et" in args.channels:
# for process, category in product(et_processes.values(), et_categories):
# systematics_et.add(
# Systematic(
# category=category,
# process=process,
# analysis="smhtt",
# era=era,
# variation=Nominal(),
# mass="125"))
#if "tt" in args.channels:
# for process, category in product(tt_processes.values(), tt_categories):
# systematics_tt.add(
# Systematic(
# category=category,
# process=process,
# analysis="smhtt",
# era=era,
# variation=Nominal(),
# mass="125"))
#if "em" in args.channels:
# for process, category in product(em_processes.values(), em_categories):
# systematics_em.add(
# Systematic(
# category=category,
# process=process,
# analysis="smhtt",
# era=era,
# variation=Nominal(),
# mass="125"))
if "mm" in args.channels:
for process, category in product(mm_processes.values(), mm_categories):
systematics_mm.add(
Systematic(
category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
# Produce histograms
#if "mt" in args.channels: systematics_mt.produce()
#if "et" in args.channels: systematics_et.produce()
#if "tt" in args.channels: systematics_tt.produce()
#if "em" in args.channels: systematics_em.produce()
if "mm" in args.channels: systematics_mm.produce()
def main(args):
# Container for all distributions to be drawn
systematics_mm = Systematics("shapes_mm_recoil_2018.root",
num_threads=args.num_threads,
find_unique_objects=True)
# Era
era = Run2018(args.datasets)
# Channels and processes
# yapf: disable
directory = args.directory
zptm_path = "/portal/ekpbms1/home/akhmet/workdir/FriendTreeProductionMain/CMSSW_10_2_14/src/ZPtMReweighting_workdir/ZPtMReweighting_collected/"
mm = MM()
mm_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, mm, friend_directory=[])),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, mm, friend_directory=[zptm_path])),
"ZL" : Process("ZL", ZLEstimation (era, directory, mm, friend_directory=[zptm_path])),
"TTT" : Process("TTT", TTTEstimation (era, directory, mm, friend_directory=[])),
"TTL" : Process("TTL", TTLEstimation (era, directory, mm, friend_directory=[])),
"VVT" : Process("VVT", VVTEstimation (era, directory, mm, friend_directory=[])),
"VVL" : Process("VVL", VVLEstimation (era, directory, mm, friend_directory=[])),
"W" : Process("W", WEstimation (era, directory, mm, friend_directory=[])),
}
mm_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, mm,
[mm_processes[process] for process in ["ZTT", "ZL", "W", "TTT", "TTL", "VVT", "VVL"]],
mm_processes["data"], friend_directory=[], extrapolation_factor=2.0))
# Variables and categories
binning = yaml.load(open(args.binning))
mm_categories = []
variable_bins = {
"njets" : [0, 1, 2],
"ptvis" : [0, 10, 20, 30, 50],
}
variable_names = [
"metParToZ", "metPerpToZ",
"puppimetParToZ", "puppimetPerpToZ",
# "recoilParToZ", "recoilPerpToZ",
# "puppirecoilParToZ", "puppirecoilPerpToZ",
]
for njets_bin in range(len(variable_bins["njets"])):
for pt_bin in range(len(variable_bins["ptvis"])):
name = "njets_bin_%s_vs_ptvis_bin_%s"%(str(njets_bin),str(pt_bin))
category_njets = ""
category_pt = ""
if njets_bin == (len(variable_bins["njets"]) - 1):
category_njets = "njets >= %s"%str(variable_bins["njets"][njets_bin])
else:
category_njets = "njets == %s"%str(variable_bins["njets"][njets_bin])
if pt_bin == (len(variable_bins["ptvis"]) - 1):
category_pt = "ptvis > %s"%str(variable_bins["ptvis"][pt_bin])
else:
category_pt= "ptvis > %s && ptvis <= %s"%(str(variable_bins["ptvis"][pt_bin]),str(variable_bins["ptvis"][pt_bin+1]))
print category_njets, category_pt
cuts = Cuts(
Cut(category_njets,"njets_category"),
Cut(category_pt,"ptvis_category"),
Cut("m_vis > 70 && m_vis < 110","z_peak")
)
for v in variable_names:
mm_categories.append(
Category(
name,
mm,
cuts,
variable=Variable(v,VariableBinning(binning["control"]["mm"][v]["bins"]), expression=binning["control"]["mm"][v]["expression"])))
# Nominal histograms
for process, category in product(mm_processes.values(), mm_categories):
systematics_mm.add(
Systematic(
category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
# Produce histograms
systematics_mm.produce()
def main(args):
# Container for all distributions to be drawn
logger.info("Set up shape variations.")
systematics = Systematics(
"{}_cutbased_shapes_{}.root".format(args.tag,
args.discriminator_variable),
num_threads=args.num_threads,
skip_systematic_variations=args.skip_systematic_variations)
# Era selection
if "2018" in args.era:
from shape_producer.estimation_methods_2018 import DataEstimation, ZTTEstimation, ZTTEmbeddedEstimation, ZLEstimation, ZJEstimation, TTLEstimation, TTJEstimation, TTTEstimation, VVLEstimation, VVTEstimation, VVJEstimation, WEstimation, ggHEstimation, qqHEstimation, VHEstimation, WHEstimation, ZHEstimation, ttHEstimation, HWWEstimation, ggHWWEstimation, qqHWWEstimation, SUSYggHEstimation, SUSYbbHEstimation, QCDEstimation_ABCD_TT_ISO2, QCDEstimation_SStoOS_MTETEM, NewFakeEstimationLT, NewFakeEstimationTT
from shape_producer.era import Run2018
era = Run2018(args.datasets)
else:
logger.critical("Era {} is not implemented.".format(args.era))
raise Exception
# Channels and processes
# yapf: disable
directory = args.directory
friend_directories = {
"et" : args.et_friend_directory,
"mt" : args.mt_friend_directory,
"tt" : args.tt_friend_directory,
"em" : args.em_friend_directory,
}
ff_friend_directory = args.fake_factor_friend_directory
channel_dict = {
"mt" : MTMSSM2018(),
"et" : ETMSSM2018(),
"tt" : TTMSSM2018(),
"em" : EMMSSM2018(),
}
susyggH_masses = [80, 90, 100, 110, 120, 130, 140, 160, 180, 200, 250, 300, 350, 400, 450, 600, 700, 800, 900, 1200, 1400, 1500, 1600, 1800, 2000, 2300, 2600, 2900, 3200]
susybbH_lo_masses = [80, 90, 100, 110, 120, 130, 140, 160, 180, 200, 250, 300, 350, 400, 450, 600, 700, 800, 900, 1200, 1400, 1500, 1600, 1800, 2000, 2300, 2600, 2900, 3200]
susybbH_masses = [80, 90, 100, 110, 120, 125, 130, 140, 160, 180, 200, 250, 300, 350, 400, 450, 500, 600, 700, 800, 900, 1000, 1200, 1400, 1600, 1800, 2000, 2300, 2600, 2900, 3200, 3500]
processes = {
"mt" : {},
"et" : {},
"tt" : {},
"em" : {},
}
for ch in args.channels:
# common processes
if args.shape_group == "backgrounds":
processes[ch]["data"] = Process("data_obs", DataEstimation (era, directory, channel_dict[args.era][ch], friend_directory=friend_directories[ch]))
processes[ch]["EMB"] = Process("EMB", ZTTEmbeddedEstimation (era, directory, channel_dict[args.era][ch], friend_directory=friend_directories[ch]))
processes[ch]["ZL"] = Process("ZL", ZLEstimation (era, directory, channel_dict[args.era][ch], friend_directory=friend_directories[ch]))
processes[ch]["TTL"] = Process("TTL", TTLEstimation (era, directory, channel_dict[args.era][ch], friend_directory=friend_directories[ch]))
processes[ch]["VVL"] = Process("VVL", VVLEstimation (era, directory, channel_dict[args.era][ch], friend_directory=friend_directories[ch]))
processes[ch]["VH125"] = Process("VH125", VHEstimation (era, directory, channel_dict[args.era][ch], friend_directory=friend_directories[ch]))
processes[ch]["WH125"] = Process("WH125", WHEstimation (era, directory, channel_dict[args.era][ch], friend_directory=friend_directories[ch]))
processes[ch]["ZH125"] = Process("ZH125", ZHEstimation (era, directory, channel_dict[args.era][ch], friend_directory=friend_directories[ch]))
processes[ch]["ttH125"] = Process("ttH125", ttHEstimation (era, directory, channel_dict[args.era][ch], friend_directory=friend_directories[ch]))
processes[ch]["ggHWW125"] = Process("ggHWW125", ggHWWEstimation (era, directory, channel_dict[ch], friend_directory=friend_directories[ch]))
processes[ch]["qqHWW125"] = Process("qqHWW125", qqHWWEstimation (era, directory, channel_dict[ch], friend_directory=friend_directories[ch]))
# mssm ggH and bbH signals
if "gg" in args.shape_group:
for m in susyggH_masses:
name = args.shape_group + "_" + str(m)
processes[ch][name] = Process(name, SUSYggHEstimation(era, directory, channel_dict[ch], str(m), args.shape_group.replace("gg",""), friend_directory=friend_directories[ch]))
if args.shape_group == "bbH":
for m in susybbH_masses:
name = "bbH_" + str(m)
processes[ch][name] = Process(name, SUSYbbHEstimation(era, directory, channel_dict[ch], str(m), friend_directory=friend_directories[ch]))
if args.shape_group == "sm_signals":
# stage 0 and stage 1.1 ggh and qqh
for ggH_htxs in ggHEstimation.htxs_dict:
processes[ch][ggH_htxs] = Process(ggH_htxs, ggHEstimation(ggH_htxs, era, directory, channel_dict[ch], friend_directory=[])) # friend_directories[ch]))
for qqH_htxs in qqHEstimation.htxs_dict:
processes[ch][qqH_htxs] = Process(qqH_htxs, qqHEstimation(qqH_htxs, era, directory, channel_dict[ch], friend_directory=[])) # friend_directories[ch]))
# channel-specific processes
if args.shape_group == "backgrounds":
if ch in ["mt", "et"]:
processes[ch]["FAKES"] = Process("jetFakes", NewFakeEstimationLT(era, directory, channel_dict[ch], [processes[ch][process] for process in ["EMB", "ZL", "TTL", "VVL"]], processes[ch]["data"], friend_directory=friend_directories[ch]+[ff_friend_directory]))
elif ch == "tt":
processes[ch]["FAKES"] = Process("jetFakes", NewFakeEstimationTT(era, directory, channel_dict[ch], [processes[ch][process] for process in ["EMB", "ZL", "TTL", "VVL"]], processes[ch]["data"], friend_directory=friend_directories[ch]+[ff_friend_directory]))
elif ch == "em":
processes[ch]["W"] = Process("W", WEstimation(era, directory, channel_dict[ch], friend_directory=friend_directories[ch]))
processes[ch]["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, channel_dict[ch], [processes[ch][process] for process in ["EMB", "ZL", "W", "VVL", "TTL"]], processes[ch]["data"], extrapolation_factor=1.0, qcd_weight = Weight("em_qcd_extrap_up_Weight","qcd_weight")))
# Variables and categories
if sys.version_info.major <= 2 and sys.version_info.minor <= 7 and sys.version_info.micro <= 15:
binning = yaml.load(open(args.binning))
else:
binning = yaml.load(open(args.binning), Loader=yaml.FullLoader)
# Cut-based analysis shapes
categories = {
"mt" : [],
"et" : [],
"tt" : [],
"em" : [],
}
for ch in args.channels:
discriminator = construct_variable(binning, args.discriminator_variable)
# Get dictionary mapping category name to cut objects.
cut_dict = create_cut_map(binning, ch)
# Create full set of cuts from dict and create category using these cuts.
cuts = Cuts(*cut_dict[args.category])
categories[ch].append(Category(args.category, channel_dict[ch], cuts, variable=discriminator))
# Choice of activated signal processes
signal_nicks = []
sm_htt_backgrounds_nicks = ["WH125", "ZH125", "VH125", "ttH125"]
sm_hww_nicks = ["ggHWW125", "qqHWW125"]
sm_htt_signals_nicks = [ggH_htxs for ggH_htxs in ggHEstimation.htxs_dict] + [qqH_htxs for qqH_htxs in qqHEstimation.htxs_dict]
susy_nicks = []
if "gg" in args.shape_group:
for m in susyggH_masses:
susy_nicks.append(args.shape_group + "_" + str(m))
if args.shape_group == "bbH":
for m in susybbH_masses:
susy_nicks.append("bbH_" + str(m))
if args.shape_group == "backgrounds":
signal_nicks = sm_htt_backgrounds_nicks + sm_hww_nicks
elif args.shape_group == "sm_signals":
signal_nicks = sm_htt_signals_nicks
else:
signal_nicks = susy_nicks
# Nominal histograms
for ch in args.channels:
for process, category in product(processes[ch].values(), categories[ch]):
systematics.add(Systematic(category=category, process=process, analysis="mssmvssm", era=era, variation=Nominal(), mass="125"))
# Setup shapes variations
# EMB: 10% removed events in ttbar simulation (ttbar -> real tau tau events) will be added/subtracted to ZTT shape to use as systematic
if args.shape_group == "backgrounds":
tttautau_process = {}
for ch in args.channels:
tttautau_process[ch] = Process("TTT", TTTEstimation(era, directory, channel_dict[ch], friend_directory=friend_directories[ch]))
processes[ch]['ZTTpTTTauTauDown'] = Process("ZTTpTTTauTauDown", AddHistogramEstimationMethod("AddHistogram", "nominal", era, directory, channel_dict[ch], [processes[ch]["EMB"], tttautau_process[ch]], [1.0, -0.1]))
processes[ch]['ZTTpTTTauTauUp'] = Process("ZTTpTTTauTauUp", AddHistogramEstimationMethod("AddHistogram", "nominal", era, directory, channel_dict[ch], [processes[ch]["EMB"], tttautau_process[ch]], [1.0, 0.1]))
for category in categories[ch]:
for updownvar in ["Down", "Up"]:
systematics.add(Systematic(category=category, process=processes[ch]['ZTTpTTTauTau%s'%updownvar], analysis="smhtt", era=era, variation=Relabel("CMS_htt_emb_ttbar_Run2018", updownvar), mass="125"))
# Split JES shapes
jet_es_variations = create_systematic_variations("CMS_scale_j_Absolute", "jecUncAbsolute", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_Absolute_Run2018", "jecUncAbsoluteYear", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_BBEC1", "jecUncBBEC1", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_BBEC1_Run2018", "jecUncBBEC1Year", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_EC2", "jecUncEC2", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_EC2_Run2018", "jecUncEC2Year", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_FlavorQCD", "jecUncFlavorQCD", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_HF", "jecUncHF", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_HF_Run2018", "jecUncHFYear", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_RelativeBal", "jecUncRelativeBal", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_RelativeSample_Run2018", "jecUncRelativeSampleYear", DifferentPipeline)
# B-tagging
btag_eff_variations = create_systematic_variations("CMS_htt_eff_b_Run2018", "btagEff", DifferentPipeline)
mistag_eff_variations = create_systematic_variations("CMS_htt_mistag_b_Run2018", "btagMistag", DifferentPipeline)
## Variations common for all groups (most of the mc-related systematics)
common_mc_variations = btag_eff_variations + mistag_eff_variations + jet_es_variations
# MET energy scale. Note: only those variations for non-resonant processes are used in the stat. inference
met_unclustered_variations = create_systematic_variations("CMS_scale_met_unclustered", "metUnclusteredEn", DifferentPipeline)
# Recoil correction unc, for resonant processes
recoil_variations = create_systematic_variations( "CMS_htt_boson_reso_met_Run2018", "metRecoilResolution", DifferentPipeline)
recoil_variations += create_systematic_variations( "CMS_htt_boson_scale_met_Run2018", "metRecoilResponse", DifferentPipeline)
# Tau energy scale (general, MC-specific & EMB-specific), it is mt, et & tt specific
tau_es_variations = {}
for unctype in ["", "_mc", "_emb"]:
tau_es_variations[unctype] = create_systematic_variations("CMS_scale%s_t_3prong_Run%s"% (unctype, args.era), "tauEsThreeProng", DifferentPipeline)
tau_es_variations[unctype] += create_systematic_variations("CMS_scale%s_t_3prong1pizero_Run%s"% (unctype, args.era), "tauEsThreeProngOnePiZero", DifferentPipeline)
tau_es_variations[unctype] += create_systematic_variations("CMS_scale%s_t_1prong_Run%s"% (unctype, args.era), "tauEsOneProng", DifferentPipeline)
tau_es_variations[unctype] += create_systematic_variations("CMS_scale%s_t_1prong1pizero_Run%s"% (unctype, args.era), "tauEsOneProngOnePiZero", DifferentPipeline)
# Tau ID variations (general, MC-specific & EMB specific), it is mt, et & tt specific
# in et and mt one nuisance per pT bin, in tt per dm
tau_id_variations = {}
for ch in ["et" , "mt", "tt"]:
tau_id_variations[ch] = {}
for unctype in ["", "_emb"]:
tau_id_variations[ch][unctype] = []
if ch in ["et", "mt"]:
pt = [30, 35, 40, 500, 1000, "inf"]
for i, ptbin in enumerate(pt[:-1]):
bindown = ptbin
binup = pt[i+1]
if binup == "inf":
tau_id_variations[ch][unctype].append(
ReplaceWeight("CMS_eff{unctype}_t_{bindown}-{binup}_Run{era}".format(unctype=unctype,bindown=bindown, binup=binup, era=args.era), "taubyIsoIdWeight",
Weight("(((pt_2 >= {bindown})*tauIDScaleFactorWeightUp_tight_DeepTau2017v2p1VSjet_2)+((pt_2 < {bindown})*tauIDScaleFactorWeight_tight_DeepTau2017v2p1VSjet_2))".format(bindown=bindown), "taubyIsoIdWeight"), "Up"))
tau_id_variations[ch][unctype].append(
ReplaceWeight("CMS_eff{unctype}_t_{bindown}-{binup}_Run{era}".format(unctype=unctype, bindown=bindown, binup=binup, era=args.era), "taubyIsoIdWeight",
Weight("(((pt_2 >= {bindown})*tauIDScaleFactorWeightDown_tight_DeepTau2017v2p1VSjet_2)+((pt_2 < {bindown})*tauIDScaleFactorWeight_tight_DeepTau2017v2p1VSjet_2))".format(bindown=bindown),"taubyIsoIdWeight"), "Down"))
else:
tau_id_variations[ch][unctype].append(
ReplaceWeight("CMS_eff{unctype}_t_{bindown}-{binup}_Run{era}".format(unctype=unctype, bindown=bindown, binup=binup, era=args.era), "taubyIsoIdWeight",
Weight("(((pt_2 >= {bindown} && pt_2 <= {binup})*tauIDScaleFactorWeightUp_tight_DeepTau2017v2p1VSjet_2)+((pt_2 < {bindown} || pt_2 > {binup})*tauIDScaleFactorWeight_tight_DeepTau2017v2p1VSjet_2))".format(bindown=bindown, binup=binup),"taubyIsoIdWeight"), "Up"))
tau_id_variations[ch][unctype].append(
ReplaceWeight("CMS_eff{unctype}_t_{bindown}-{binup}_Run{era}".format(unctype=unctype, bindown=bindown, binup=binup, era=args.era), "taubyIsoIdWeight",
Weight("(((pt_2 >= {bindown} && pt_2 <= {binup})*tauIDScaleFactorWeightDown_tight_DeepTau2017v2p1VSjet_2)+((pt_2 < {bindown} || pt_2 > {binup})*tauIDScaleFactorWeight_tight_DeepTau2017v2p1VSjet_2))".format(bindown=bindown, binup=binup),"taubyIsoIdWeight"), "Down"))
if ch in ["tt"]:
for decaymode in [0, 1, 10, 11]:
tau_id_variations[ch][unctype].append(
ReplaceWeight("CMS_eff{unctype}_t_dm{dm}_Run{era}".format(unctype=unctype, dm=decaymode, era=args.era), "taubyIsoIdWeight",
Weight("(((decayMode_1=={dm})*tauIDScaleFactorWeightUp_tight_DeepTau2017v2p1VSjet_1)+((decayMode_1!={dm})*tauIDScaleFactorWeight_tight_DeepTau2017v2p1VSjet_1)*((decayMode_2=={dm})*tauIDScaleFactorWeightUp_tight_DeepTau2017v2p1VSjet_2)+((decayMode_2!={dm})*tauIDScaleFactorWeight_tight_DeepTau2017v2p1VSjet_2))".format(dm=decaymode), "taubyIsoIdWeight"), "Up"))
tau_id_variations[ch][unctype].append(
ReplaceWeight("CMS_eff{unctype}_t_dm{dm}_Run{era}".format(unctype=unctype, dm=decaymode, era=args.era), "taubyIsoIdWeight",
Weight("(((decayMode_1=={dm})*tauIDScaleFactorWeightDown_tight_DeepTau2017v2p1VSjet_1)+((decayMode_1!={dm})*tauIDScaleFactorWeight_tight_DeepTau2017v2p1VSjet_1)*((decayMode_2=={dm})*tauIDScaleFactorWeightDown_tight_DeepTau2017v2p1VSjet_2)+((decayMode_2!={dm})*tauIDScaleFactorWeight_tight_DeepTau2017v2p1VSjet_2))".format(dm=decaymode), "taubyIsoIdWeight"), "Down"))
# Ele energy scale & smear uncertainties (MC-specific), it is et & em specific
ele_es_variations = create_systematic_variations("CMS_scale_mc_e", "eleScale", DifferentPipeline)
ele_es_variations += create_systematic_variations("CMS_reso_mc_e", "eleSmear", DifferentPipeline)
# Ele energy scale (EMB-specific), it is et & em specific
ele_es_emb_variations = create_systematic_variations("CMS_scale_emb_e", "eleEs", DifferentPipeline)
# Z pt reweighting
zpt_variations = create_systematic_variations("CMS_htt_dyShape_Run2018", "zPtReweightWeight", SquareAndRemoveWeight)
# top pt reweighting
top_pt_variations = create_systematic_variations("CMS_htt_ttbarShape", "topPtReweightWeight", SquareAndRemoveWeight)
# jet to tau fake efficiency
# Needs to be introduced if one wants to create shapes for QCD
# Applied to lt,tt channels for processes ZJ, TTJ, VVJ, W
# value of weight: Up max(1-pt_2*0.002, 0.6)
# Down min(1+pt_2*0.002, 1.4)
# EMB charged track correction uncertainty (DM-dependent)
decayMode_variations = []
decayMode_variations.append(ReplaceWeight("CMS_3ProngEff_Run2018".format(args.era), "decayMode_SF", Weight("embeddedDecayModeWeight_effUp_pi0Nom", "decayMode_SF"), "Up"))
decayMode_variations.append(ReplaceWeight("CMS_3ProngEff_Run2018".format(args.era), "decayMode_SF", Weight("embeddedDecayModeWeight_effDown_pi0Nom", "decayMode_SF"), "Down"))
decayMode_variations.append(ReplaceWeight("CMS_1ProngPi0Eff_Run2018".format(args.era), "decayMode_SF", Weight("embeddedDecayModeWeight_effNom_pi0Up", "decayMode_SF"), "Up"))
decayMode_variations.append(ReplaceWeight("CMS_1ProngPi0Eff_Run2018".format(args.era), "decayMode_SF", Weight("embeddedDecayModeWeight_effNom_pi0Down", "decayMode_SF"), "Down"))
# QCD for em
qcd_variations = []
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_0jet_rate_Run2018", "qcd_weight", Weight("em_qcd_osss_0jet_rateup_Weight", "qcd_weight"), "Up"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_0jet_rate_Run2018", "qcd_weight", Weight("em_qcd_osss_0jet_ratedown_Weight", "qcd_weight"), "Down"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_0jet_shape_Run2018", "qcd_weight", Weight("em_qcd_osss_0jet_shapeup_Weight", "qcd_weight"), "Up"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_0jet_shape_Run2018", "qcd_weight", Weight("em_qcd_osss_0jet_shapedown_Weight", "qcd_weight"), "Down"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_1jet_rate_Run2018", "qcd_weight", Weight("em_qcd_osss_1jet_rateup_Weight", "qcd_weight"), "Up"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_1jet_rate_Run2018", "qcd_weight", Weight("em_qcd_osss_1jet_ratedown_Weight", "qcd_weight"), "Down"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_1jet_shape_Run2018", "qcd_weight", Weight("em_qcd_osss_1jet_shapeup_Weight", "qcd_weight"), "Up"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_1jet_shape_Run2018", "qcd_weight", Weight("em_qcd_osss_1jet_shapedown_Weight", "qcd_weight"), "Down"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_iso_Run2018", "qcd_weight", Weight("em_qcd_extrap_up_Weight", "qcd_weight"), "Up"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_iso_Run2018", "qcd_weight", Weight("em_qcd_extrap_down_Weight", "qcd_weight"), "Down"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_iso", "qcd_weight", Weight("em_qcd_extrap_up_Weight", "qcd_weight"), "Up"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_iso", "qcd_weight", Weight("em_qcd_extrap_down_Weight", "qcd_weight"), "Down"))
# Gluon-fusion WG1 uncertainty scheme
ggh_variations = []
for unc in [
"THU_ggH_Mig01", "THU_ggH_Mig12", "THU_ggH_Mu", "THU_ggH_PT120",
"THU_ggH_PT60", "THU_ggH_Res", "THU_ggH_VBF2j", "THU_ggH_VBF3j",
"THU_ggH_qmtop"
]:
ggh_variations.append(AddWeight(unc, "{}_weight".format(unc), Weight("({})".format(unc), "{}_weight".format(unc)), "Up"))
ggh_variations.append(AddWeight(unc, "{}_weight".format(unc), Weight("(2.0-{})".format(unc), "{}_weight".format(unc)), "Down"))
# ZL fakes energy scale
fakelep_dict = {"et" : "Ele", "mt" : "Mu"}
lep_fake_es_variations = {}
for ch in ["mt", "et"]:
lep_fake_es_variations[ch] = create_systematic_variations("CMS_ZLShape_%s_1prong_Run2018"%ch, "tau%sFakeEsOneProng"%fakelep_dict[ch], DifferentPipeline)
lep_fake_es_variations[ch] += create_systematic_variations("CMS_ZLShape_%s_1prong1pizero_Run2018"%ch, "tau%sFakeEsOneProngPiZeros"%fakelep_dict[ch], DifferentPipeline)
# Lepton trigger efficiency; the same values for (MC & EMB) and (mt & et)
lep_trigger_eff_variations = {}
for ch in ["mt", "et"]:
lep_trigger_eff_variations[ch] = {}
thresh_dict = {"mt": 25., "et": 28.}
for unctype in ["", "_emb"]:
lep_trigger_eff_variations[ch][unctype] = []
lep_trigger_eff_variations[ch][unctype].append(AddWeight("CMS_eff_trigger%s_%s_Run2018"%(unctype, ch), "trg_%s_eff_weight"%ch, Weight("(1.0*(pt_1<={0})+1.02*(pt_1>{0}))".format(thresh_dict[ch]), "trg_%s_eff_weight"%ch), "Up"))
lep_trigger_eff_variations[ch][unctype].append(AddWeight("CMS_eff_trigger%s_%s_Run2018"%(unctype, ch), "trg_%s_eff_weight"%ch, Weight("(1.0*(pt_1<={0})+0.98*(pt_1>{0}))".format(thresh_dict[ch]), "trg_%s_eff_weight"%ch), "Down"))
lep_trigger_eff_variations[ch][unctype].append(AddWeight("CMS_eff_xtrigger%s_%s_Run2018"%(unctype, ch), "xtrg_%s_eff_weight"%ch, Weight("(1.054*(pt_1<={0})+1.0*(pt_1>{0}))".format(thresh_dict[ch]), "xtrg_%s_eff_weight"%ch), "Up"))
lep_trigger_eff_variations[ch][unctype].append(AddWeight("CMS_eff_xtrigger%s_%s_Run2018"%(unctype, ch), "xtrg_%s_eff_weight"%ch, Weight("(0.946*(pt_1<={0})+1.0*(pt_1>{0}))".format(thresh_dict[ch]), "xtrg_%s_eff_weight"%ch), "Down"))
# Fake factor uncertainties
fake_factor_variations = {}
for ch in ["mt", "et", "tt"]:
fake_factor_variations[ch] = []
if ch in ["mt", "et"]:
for systematic_shift in [
"ff_qcd{ch}_syst_Run2018{shift}",
"ff_qcd_dm0_njet0{ch}_stat_Run2018{shift}",
"ff_qcd_dm0_njet1{ch}_stat_Run2018{shift}",
"ff_w_syst_Run2018{shift}",
"ff_w_dm0_njet0{ch}_stat_Run2018{shift}",
"ff_w_dm0_njet1{ch}_stat_Run2018{shift}",
"ff_tt_syst_Run2018{shift}",
"ff_tt_dm0_njet0_stat_Run2018{shift}",
"ff_tt_dm0_njet1_stat_Run2018{shift}",
]:
for shift_direction in ["Up", "Down"]:
fake_factor_variations[ch].append(ReplaceWeight("CMS_%s"%(systematic_shift.format(ch="_"+ch, shift="").replace("_dm0", "")), "fake_factor", Weight("ff2_{syst}".format(syst=systematic_shift.format(ch="", shift="_%s" %shift_direction.lower()).replace("_Run2018", "")), "fake_factor"), shift_direction))
elif ch == "tt":
for systematic_shift in [
"ff_qcd{ch}_syst_Run2018{shift}",
"ff_qcd_dm0_njet0{ch}_stat_Run2018{shift}",
"ff_qcd_dm0_njet1{ch}_stat_Run2018{shift}",
"ff_w{ch}_syst_Run2018{shift}", "ff_tt{ch}_syst_Run2018{shift}",
"ff_w_frac{ch}_syst_Run2018{shift}",
"ff_tt_frac{ch}_syst_Run2018{shift}"
]:
for shift_direction in ["Up", "Down"]:
fake_factor_variations[ch].append(ReplaceWeight("CMS_%s" % (systematic_shift.format(ch="_"+ch, shift="").replace("_dm0", "")), "fake_factor", Weight("(0.5*ff1_{syst}*(byTightDeepTau2017v2p1VSjet_1<0.5)+0.5*ff2_{syst}*(byTightDeepTau2017v2p1VSjet_2<0.5))".format(syst=systematic_shift.format(ch="", shift="_%s" % shift_direction.lower()).replace("_Run2018", "")), "fake_factor"), shift_direction))
## Group nicks
mc_nicks = ["ZL", "TTL", "VVL"] + signal_nicks # to be extended with 'W' in em
boson_mc_nicks = ["ZL"] + signal_nicks # to be extended with 'W' in em
## Add variations to systematics
for ch in args.channels:
channel_mc_nicks = mc_nicks + ["W"] if ch == "em" else mc_nicks
channel_boson_mc_nicks = boson_mc_nicks + ["W"] if ch == "em" else boson_mc_nicks
if args.shape_group != "backgrounds":
channel_mc_nicks = signal_nicks
channel_boson_mc_nicks = signal_nicks
channel_mc_common_variations = common_mc_variations
if ch in ["et", "em"]:
channel_mc_common_variations += ele_es_variations
if ch in ["et", "mt", "tt"]:
channel_mc_common_variations += tau_es_variations[""] + tau_es_variations["_mc"] + tau_id_variations[ch][""]
if ch in ["et", "mt"]:
channel_mc_common_variations += lep_trigger_eff_variations[ch][""]
# variations common accross all shape groups
for variation in channel_mc_common_variations:
for process_nick in channel_mc_nicks:
systematics.add_systematic_variation(variation=variation, process=processes[ch][process_nick], channel=channel_dict[ch], era=era)
for variation in recoil_variations:
for process_nick in channel_boson_mc_nicks:
systematics.add_systematic_variation(variation=variation, process=processes[ch][process_nick], channel=channel_dict[ch], era=era)
# variations relevant for ggH signals in 'sm_signals' shape group
if args.shape_group == "sm_signals":
for variation in ggh_variations:
for process_nick in [nick for nick in signal_nicks if "ggH" in nick and "HWW" not in nick and "ggH_" not in nick]:
systematics.add_systematic_variation(variation=variation, process=processes[ch][process_nick], channel=channel_dict[ch], era=era)
# variations only relevant for the 'background' shape group
if args.shape_group == "backgrounds":
for variation in top_pt_variations:
# TODO: Needs to be adapted if one wants to use DY MC or QCD estimation(lt,tt: TTT, TTL, TTJ, em: TTT, TTL)
systematics.add_systematic_variation(variation=variation, process=processes[ch]["TTL"], channel=channel_dict[ch], era=era)
for variation in met_unclustered_variations:
for process_nick in ["TTL", "VVL"]:
systematics.add_systematic_variation(variation=variation, process=processes[ch][process_nick], channel=channel_dict[ch], era=era)
zl_variations = zpt_variations
if ch in ["et", "mt"]:
zl_variations += lep_fake_es_variations[ch]
# TODO: maybe prepare variations for shape production with DY MC and QCD estimation, then applied to ZTT, ZL and ZJ for lt channels and ZTT and ZL for em channel
for variation in zl_variations:
systematics.add_systematic_variation(variation=variation, process=processes[ch]["ZL"], channel=channel_dict[ch], era=era)
if ch == "em":
for variation in qcd_variations:
systematics.add_systematic_variation(variation=variation ,process=processes[ch]["QCD"], channel=channel_dict[ch], era=era)
if ch in ["mt","et", "tt"]:
ff_variations = fake_factor_variations[ch] + tau_es_variations[""] + tau_es_variations["_mc"] + tau_es_variations["_emb"]
for variation in ff_variations:
systematics.add_systematic_variation(variation=variation, process=processes[ch]["FAKES"], channel=channel_dict[ch], era=era)
emb_variations = []
if ch in ["mt","et", "tt"]:
emb_variations += tau_es_variations[""] + tau_es_variations["_emb"] + tau_id_variations[ch]["_emb"] + decayMode_variations
if ch in ["mt", "et"]:
emb_variations += lep_trigger_eff_variations[ch]["_emb"]
if ch in ["et", "em"]:
emb_variations += ele_es_emb_variations
for variation in emb_variations:
systematics.add_systematic_variation(variation=variation, process=processes[ch]["EMB"], channel=channel_dict[ch], era=era)
# Produce histograms
logger.info("Start producing shapes.")
systematics.produce()
logger.info("Done producing shapes.")
def main(args):
# Write arparse arguments to YAML config
logger.debug("Write argparse arguments to YAML config.")
output_config = {}
output_config["base_path"] = args.base_path
output_config["friend_paths"] = args.friend_paths
output_config["output_path"] = args.output_path
output_config["output_filename"] = args.output_filename
output_config["tree_path"] = args.tree_path
output_config["event_branch"] = args.event_branch
output_config["training_weight_branch"] = args.training_weight_branch
# Define era
if "2016" in args.era:
from shape_producer.estimation_methods_2016 import DataEstimation, ggHEstimation, qqHEstimation, ZTTEstimation, ZLEstimation, ZJEstimation, WEstimation, TTTEstimation, TTJEstimation, ZTTEmbeddedEstimation, TTLEstimation, EWKZEstimation, VVLEstimation, VVJEstimation, VVEstimation, VVTEstimation
#QCDEstimation_SStoOS_MTETEM, QCDEstimationTT, EWKWpEstimation, EWKWmEstimation, , VHEstimation, HTTEstimation,
from shape_producer.era import Run2016
era = Run2016(args.database)
elif "2017" in args.era:
from shape_producer.estimation_methods_2017 import DataEstimation, ZTTEstimation, ZJEstimation, ZLEstimation, TTLEstimation, TTJEstimation, TTTEstimation, VVTEstimation, VVJEstimation, VVLEstimation, WEstimation, ggHEstimation, qqHEstimation, EWKZEstimation, ZTTEmbeddedEstimation
from shape_producer.era import Run2017
era = Run2017(args.database)
elif "2018" in args.era:
from shape_producer.estimation_methods_2018 import DataEstimation, ZTTEstimation, ZJEstimation, ZLEstimation, TTLEstimation, TTJEstimation, TTTEstimation, VVTEstimation, VVJEstimation, VVLEstimation, WEstimation, ggHEstimation, qqHEstimation, EWKZEstimation, ZTTEmbeddedEstimation
from shape_producer.era import Run2018
era = Run2018(args.database)
else:
logger.fatal("Era {} is not implemented.".format(args.era))
raise Exception
def estimationMethodAndClassMapGenerator():
###### common processes
classes_map = {"ggH": "ggh", "qqH": "qqh", "EWKZ": "misc"}
estimationMethodList = [
ggHEstimation("ggH", era, args.base_path, channel),
qqHEstimation("qqH", era, args.base_path, channel),
EWKZEstimation(era, args.base_path, channel),
VVLEstimation(era, args.base_path, channel),
WEstimation(era, args.base_path, channel)
]
######## Check for emb vs MC
if args.training_z_estimation_method == "emb":
classes_map["EMB"] = "ztt"
estimationMethodList.extend(
[ZTTEmbeddedEstimation(era, args.base_path, channel)])
elif args.training_z_estimation_method == "mc":
classes_map["ZTT"] = "ztt"
estimationMethodList.extend([
ZTTEstimation(era, args.base_path, channel),
TTTEstimation(era, args.base_path, channel),
VVTEstimation(era, args.base_path, channel)
])
else:
logger.fatal(
"No valid training-z-estimation-method! Options are emb, mc. Argument was {}"
.format(args.training_z_estimation_method))
raise Exception
##### TT* zl,zj processes
estimationMethodList.extend([
TTLEstimation(era, args.base_path, channel),
ZLEstimation(era, args.base_path, channel)
])
# less data-> less categories for tt
if args.channel == "tt":
classes_map.update({
"TTT": "misc",
"TTL": "misc",
"TTJ": "misc",
"ZL": "misc",
"ZJ": "misc"
})
estimationMethodList.extend([
ZJEstimation(era, args.base_path, channel),
TTJEstimation(era, args.base_path, channel)
])
## not TTJ,ZJ for em
elif args.channel == "em":
classes_map.update({"TTT": "tt", "TTL": "tt", "ZL": "misc"})
else:
classes_map.update({
"TTT": "tt",
"TTL": "tt",
"TTJ": "tt",
"ZL": "zll",
"ZJ": "zll"
})
estimationMethodList.extend([
ZJEstimation(era, args.base_path, channel),
TTJEstimation(era, args.base_path, channel)
])
###w:
# estimation metho already included, just different mapping fror et and mt
if args.channel in ["et", "mt"]:
classes_map["W"] = "w"
else:
classes_map["W"] = "misc"
##### VV/[VVT,VVL,VVJ] split
# VVL in common, VVT in "EMBvsMC"
if args.channel == "em":
classes_map.update({"VVT": "db", "VVL": "db"})
else:
classes_map.update({"VVT": "misc", "VVL": "misc", "VVJ": "misc"})
estimationMethodList.extend([
VVJEstimation(era, args.base_path, channel),
])
### QCD class
if args.channel == "tt":
classes_map["QCD"] = "noniso"
else:
classes_map["QCD"] = "ss"
return ([classes_map, estimationMethodList])
channelDict = {}
channelDict["2016"] = {
"mt": MTSM2016(),
"et": ETSM2016(),
"tt": TTSM2016(),
"em": EMSM2016()
}
channelDict["2017"] = {
"mt": MTSM2017(),
"et": ETSM2017(),
"tt": TTSM2017(),
"em": EMSM2017()
}
channelDict["2018"] = {
"mt": MTSM2018(),
"et": ETSM2018(),
"tt": TTSM2018(),
"em": EMSM2018()
}
channel = channelDict[args.era][args.channel]
# Set up `processes` part of config
output_config["processes"] = {}
# Additional cuts
additional_cuts = Cuts()
logger.warning("Use additional cuts for mt: %s", additional_cuts.expand())
classes_map, estimationMethodList = estimationMethodAndClassMapGenerator()
##MC+/Embedding Processes
for estimation in estimationMethodList:
output_config["processes"][estimation.name] = {
"files": [
str(f).replace(args.base_path.rstrip("/") + "/", "")
for f in estimation.get_files()
],
"cut_string":
(estimation.get_cuts() + channel.cuts + additional_cuts).expand(),
"weight_string":
estimation.get_weights().extract(),
"class":
classes_map[estimation.name]
}
###
# Same sign selection for data-driven QCD
estimation = DataEstimation(era, args.base_path, channel)
estimation.name = "QCD"
channel_qcd = copy.deepcopy(channel)
if args.channel != "tt":
## os= opposite sign
channel_qcd.cuts.get("os").invert()
# Same sign selection for data-driven QCD
else:
channel_qcd.cuts.remove("tau_2_iso")
channel_qcd.cuts.add(
Cut("byTightIsolationMVArun2017v2DBoldDMwLT2017_2<0.5",
"tau_2_iso"))
channel_qcd.cuts.add(
Cut("byLooseIsolationMVArun2017v2DBoldDMwLT2017_2>0.5",
"tau_2_iso_loose"))
output_config["processes"][estimation.name] = {
"files": [
str(f).replace(args.base_path.rstrip("/") + "/", "")
for f in estimation.get_files()
],
"cut_string":
(estimation.get_cuts() + channel_qcd.cuts + additional_cuts).expand(),
"weight_string":
estimation.get_weights().extract(),
"class":
classes_map[estimation.name]
}
#####################################
# Write output config
logger.info("Write config to file: {}".format(args.output_config))
yaml.dump(output_config,
open(args.output_config, 'w'),
default_flow_style=False)
def main(args):
# Container for all distributions to be drawn
logger.info("Set up shape variations.")
systematics = Systematics(
"{}_shapes.root".format(args.tag),
num_threads=args.num_threads,
skip_systematic_variations=args.skip_systematic_variations)
# Era selection
if "2018" in args.era:
from shape_producer.estimation_methods_2018 import DataEstimation, ZTTEstimation, ZTTEmbeddedEstimation, ZLEstimation, ZJEstimation, TTLEstimation, TTJEstimation, TTTEstimation, VVLEstimation, VVTEstimation, VVJEstimation, WEstimation, ggHEstimation, ggHEstimation_0J, ggHEstimation_1J_PTH_0_60, ggHEstimation_1J_PTH_60_120, ggHEstimation_1J_PTH_120_200, ggHEstimation_1J_PTH_GT200, ggHEstimation_GE2J_PTH_0_60, ggHEstimation_GE2J_PTH_60_120, ggHEstimation_GE2J_PTH_120_200, ggHEstimation_GE2J_PTH_GT200, ggHEstimation_VBFTOPO_JET3, ggHEstimation_VBFTOPO_JET3VETO, qqHEstimation, qqHEstimation_VBFTOPO_JET3VETO, qqHEstimation_VBFTOPO_JET3, qqHEstimation_REST, qqHEstimation_VH2JET, qqHEstimation_PTJET1_GT200, VHEstimation, WHEstimation, ZHEstimation, ttHEstimation, QCDEstimation_ABCD_TT_ISO2, QCDEstimation_SStoOS_MTETEM, FakeEstimationLT, NewFakeEstimationLT, FakeEstimationTT, NewFakeEstimationTT
from shape_producer.era import Run2018
era = Run2018(args.datasets)
else:
logger.critical("Era {} is not implemented.".format(args.era))
raise Exception
# Channels and processes
# yapf: disable
directory = args.directory
et_friend_directory = []#args.et_friend_directory
em_friend_directory = []#args.em_friend_directory
mt_friend_directory = []#args.mt_friend_directory
tt_friend_directory = []#args.tt_friend_directory
ff_friend_directory = []#args.fake_factor_friend_directory
mt = MTSM2018()
mt_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"EMB" : Process("EMB", ZTTEmbeddedEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"ZL" : Process("ZL", ZLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"TTT" : Process("TTT", TTTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"TTL" : Process("TTL", TTLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"VVT" : Process("VVT", VVTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"VVJ" : Process("VVJ", VVJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"VVL" : Process("VVL", VVLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"W" : Process("W", WEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"ggH" : Process("ggH125", ggHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"qqH" : Process("qqH125", qqHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH_0J" : Process("ggH_0J125", ggHEstimation_0J (era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH_1J_PTH_0_60" : Process("ggH_1J_PTH_0_60125", ggHEstimation_1J_PTH_0_60 (era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH_1J_PTH_60_120" : Process("ggH_1J_PTH_60_120125", ggHEstimation_1J_PTH_60_120 (era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH_1J_PTH_120_200" : Process("ggH_1J_PTH_120_200125", ggHEstimation_1J_PTH_120_200 (era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH_1J_PTH_GT200" : Process("ggH_1J_PTH_GT200125", ggHEstimation_1J_PTH_GT200 (era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH_GE2J_PTH_0_60" : Process("ggH_GE2J_PTH_0_60125", ggHEstimation_GE2J_PTH_0_60 (era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH_GE2J_PTH_60_120" : Process("ggH_GE2J_PTH_60_120125", ggHEstimation_GE2J_PTH_60_120 (era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH_GE2J_PTH_120_200" : Process("ggH_GE2J_PTH_120_200125", ggHEstimation_GE2J_PTH_120_200(era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH_GE2J_PTH_GT200" : Process("ggH_GE2J_PTH_GT200125", ggHEstimation_GE2J_PTH_GT200 (era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH_VBFTOPO_JET3VETO" : Process("ggH_VBFTOPO_JET3VETO125", ggHEstimation_VBFTOPO_JET3VETO(era, directory, mt, friend_directory=mt_friend_directory)),
# "ggH_VBFTOPO_JET3" : Process("ggH_VBFTOPO_JET3125", ggHEstimation_VBFTOPO_JET3 (era, directory, mt, friend_directory=mt_friend_directory)),
# "qqH_VBFTOPO_JET3VETO" : Process("qqH_VBFTOPO_JET3VETO125", qqHEstimation_VBFTOPO_JET3VETO(era, directory, mt, friend_directory=mt_friend_directory)),
# "qqH_VBFTOPO_JET3" : Process("qqH_VBFTOPO_JET3125", qqHEstimation_VBFTOPO_JET3 (era, directory, mt, friend_directory=mt_friend_directory)),
# "qqH_REST" : Process("qqH_REST125", qqHEstimation_REST (era, directory, mt, friend_directory=mt_friend_directory)),
# "qqH_VH2JET" : Process("qqH_VH2JET125", qqHEstimation_VH2JET (era, directory, mt, friend_directory=mt_friend_directory)),
# "qqH_PTJET1_GT200" : Process("qqH_PTJET1_GT200125", qqHEstimation_PTJET1_GT200 (era, directory, mt, friend_directory=mt_friend_directory)),
# "VH" : Process("VH125", VHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "WH" : Process("WH125", WHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "ZH" : Process("ZH125", ZHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
# "ttH" : Process("ttH125", ttHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
}
# mt_processes["FAKES"] = Process("jetFakes", NewFakeEstimationLT(era, directory, mt, [mt_processes[process] for process in ["EMB", "ZL", "TTL", "VVL"]], mt_processes["data"], friend_directory=[mt_friend_directory, ff_friend_directory]))
#mt_fakes_for_uncs=Process("jetFakes", FakeEstimationLT(era, directory, mt, friend_directory=[mt_friend_directory, ff_friend_directory]))
mt_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, mt,
[mt_processes[process] for process in ["ZTT", "ZL", "ZJ", "TTL","TTT","TTJ", "VVT", "VVJ", "VVL","W"]],
mt_processes["data"], friend_directory=mt_friend_directory, extrapolation_factor=1.1))
mt_processes["QCDEMB"] = Process("QCDEMB", QCDEstimation_SStoOS_MTETEM(era, directory, mt,
[mt_processes[process] for process in ["EMB", "ZL", "ZJ", "TTL", "TTJ", "VVJ", "VVL","W"]],
mt_processes["data"], friend_directory=mt_friend_directory, extrapolation_factor=1.1))
et = ETSM2018()
et_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, et, friend_directory=et_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, et, friend_directory=et_friend_directory)),
"EMB" : Process("EMB", ZTTEmbeddedEstimation (era, directory, et, friend_directory=et_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimation (era, directory, et, friend_directory=et_friend_directory)),
"ZL" : Process("ZL", ZLEstimation (era, directory, et, friend_directory=et_friend_directory)),
"TTT" : Process("TTT", TTTEstimation (era, directory, et, friend_directory=et_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimation (era, directory, et, friend_directory=et_friend_directory)),
"TTL" : Process("TTL", TTLEstimation (era, directory, et, friend_directory=et_friend_directory)),
"VVT" : Process("VVT", VVTEstimation (era, directory, et, friend_directory=et_friend_directory)),
"VVJ" : Process("VVJ", VVJEstimation (era, directory, et, friend_directory=et_friend_directory)),
"VVL" : Process("VVL", VVLEstimation (era, directory, et, friend_directory=et_friend_directory)),
"W" : Process("W", WEstimation (era, directory, et, friend_directory=et_friend_directory)),
"ggH" : Process("ggH125", ggHEstimation (era, directory, et, friend_directory=et_friend_directory)),
"qqH" : Process("qqH125", qqHEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "ggH_0J" : Process("ggH_0J125", ggHEstimation_0J (era, directory, et, friend_directory=et_friend_directory)),
# "ggH_1J_PTH_0_60" : Process("ggH_1J_PTH_0_60125", ggHEstimation_1J_PTH_0_60 (era, directory, et, friend_directory=et_friend_directory)),
# "ggH_1J_PTH_60_120" : Process("ggH_1J_PTH_60_120125", ggHEstimation_1J_PTH_60_120 (era, directory, et, friend_directory=et_friend_directory)),
# "ggH_1J_PTH_120_200" : Process("ggH_1J_PTH_120_200125", ggHEstimation_1J_PTH_120_200 (era, directory, et, friend_directory=et_friend_directory)),
# "ggH_1J_PTH_GT200" : Process("ggH_1J_PTH_GT200125", ggHEstimation_1J_PTH_GT200 (era, directory, et, friend_directory=et_friend_directory)),
# "ggH_GE2J_PTH_0_60" : Process("ggH_GE2J_PTH_0_60125", ggHEstimation_GE2J_PTH_0_60 (era, directory, et, friend_directory=et_friend_directory)),
# "ggH_GE2J_PTH_60_120" : Process("ggH_GE2J_PTH_60_120125", ggHEstimation_GE2J_PTH_60_120 (era, directory, et, friend_directory=et_friend_directory)),
# "ggH_GE2J_PTH_120_200" : Process("ggH_GE2J_PTH_120_200125", ggHEstimation_GE2J_PTH_120_200(era, directory, et, friend_directory=et_friend_directory)),
# "ggH_GE2J_PTH_GT200" : Process("ggH_GE2J_PTH_GT200125", ggHEstimation_GE2J_PTH_GT200 (era, directory, et, friend_directory=et_friend_directory)),
# "ggH_VBFTOPO_JET3VETO" : Process("ggH_VBFTOPO_JET3VETO125", ggHEstimation_VBFTOPO_JET3VETO(era, directory, et, friend_directory=et_friend_directory)),
# "ggH_VBFTOPO_JET3" : Process("ggH_VBFTOPO_JET3125", ggHEstimation_VBFTOPO_JET3 (era, directory, et, friend_directory=et_friend_directory)),
# "qqH_VBFTOPO_JET3VETO" : Process("qqH_VBFTOPO_JET3VETO125", qqHEstimation_VBFTOPO_JET3VETO(era, directory, et, friend_directory=et_friend_directory)),
# "qqH_VBFTOPO_JET3" : Process("qqH_VBFTOPO_JET3125", qqHEstimation_VBFTOPO_JET3 (era, directory, et, friend_directory=et_friend_directory)),
# "qqH_REST" : Process("qqH_REST125", qqHEstimation_REST (era, directory, et, friend_directory=et_friend_directory)),
# "qqH_VH2JET" : Process("qqH_VH2JET125", qqHEstimation_VH2JET (era, directory, et, friend_directory=et_friend_directory)),
# "qqH_PTJET1_GT200" : Process("qqH_PTJET1_GT200125", qqHEstimation_PTJET1_GT200 (era, directory, et, friend_directory=et_friend_directory)),
# "VH" : Process("VH125", VHEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "WH" : Process("WH125", WHEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "ZH" : Process("ZH125", ZHEstimation (era, directory, et, friend_directory=et_friend_directory)),
# "ttH" : Process("ttH125", ttHEstimation (era, directory, et, friend_directory=et_friend_directory)),
}
# et_processes["FAKES"] = Process("jetFakes", NewFakeEstimationLT(era, directory, et, [et_processes[process] for process in ["EMB", "ZL", "TTL", "VVL"]], et_processes["data"], friend_directory=[et_friend_directory, ff_friend_directory]))
et_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, et,
[et_processes[process] for process in ["ZTT", "ZL", "ZJ", "W", "TTT", "TTJ", "TTL", "VVT", "VVJ", "VVL"]],
et_processes["data"], friend_directory=et_friend_directory, extrapolation_factor=1.1))
et_processes["QCDEMB"] = Process("QCDEMB", QCDEstimation_SStoOS_MTETEM(era, directory, et,
[et_processes[process] for process in ["EMB", "ZL", "ZJ", "W", "TTJ", "TTL", "VVJ", "VVL"]],
et_processes["data"], friend_directory=et_friend_directory, extrapolation_factor=1.1))
tt = TTSM2018()
tt_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"EMB" : Process("EMB", ZTTEmbeddedEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"ZL" : Process("ZL", ZLEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"TTT" : Process("TTT", TTTEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"TTL" : Process("TTL", TTLEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"VVT" : Process("VVT", VVTEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"VVJ" : Process("VVJ", VVJEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"VVL" : Process("VVL", VVLEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"W" : Process("W", WEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"ggH" : Process("ggH125", ggHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"qqH" : Process("qqH125", qqHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH_0J" : Process("ggH_0J125", ggHEstimation_0J (era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH_1J_PTH_0_60" : Process("ggH_1J_PTH_0_60125", ggHEstimation_1J_PTH_0_60 (era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH_1J_PTH_60_120" : Process("ggH_1J_PTH_60_120125", ggHEstimation_1J_PTH_60_120 (era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH_1J_PTH_120_200" : Process("ggH_1J_PTH_120_200125", ggHEstimation_1J_PTH_120_200 (era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH_1J_PTH_GT200" : Process("ggH_1J_PTH_GT200125", ggHEstimation_1J_PTH_GT200 (era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH_GE2J_PTH_0_60" : Process("ggH_GE2J_PTH_0_60125", ggHEstimation_GE2J_PTH_0_60 (era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH_GE2J_PTH_60_120" : Process("ggH_GE2J_PTH_60_120125", ggHEstimation_GE2J_PTH_60_120 (era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH_GE2J_PTH_120_200" : Process("ggH_GE2J_PTH_120_200125", ggHEstimation_GE2J_PTH_120_200(era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH_GE2J_PTH_GT200" : Process("ggH_GE2J_PTH_GT200125", ggHEstimation_GE2J_PTH_GT200 (era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH_VBFTOPO_JET3VETO" : Process("ggH_VBFTOPO_JET3VETO125", ggHEstimation_VBFTOPO_JET3VETO(era, directory, tt, friend_directory=tt_friend_directory)),
# "ggH_VBFTOPO_JET3" : Process("ggH_VBFTOPO_JET3125", ggHEstimation_VBFTOPO_JET3 (era, directory, tt, friend_directory=tt_friend_directory)),
# "qqH_VBFTOPO_JET3VETO" : Process("qqH_VBFTOPO_JET3VETO125", qqHEstimation_VBFTOPO_JET3VETO(era, directory, tt, friend_directory=tt_friend_directory)),
# "qqH_VBFTOPO_JET3" : Process("qqH_VBFTOPO_JET3125", qqHEstimation_VBFTOPO_JET3 (era, directory, tt, friend_directory=tt_friend_directory)),
# "qqH_REST" : Process("qqH_REST125", qqHEstimation_REST (era, directory, tt, friend_directory=tt_friend_directory)),
# "qqH_VH2JET" : Process("qqH_VH2JET125", qqHEstimation_VH2JET (era, directory, tt, friend_directory=tt_friend_directory)),
# "qqH_PTJET1_GT200" : Process("qqH_PTJET1_GT200125", qqHEstimation_PTJET1_GT200 (era, directory, tt, friend_directory=tt_friend_directory)),
# "VH" : Process("VH125", VHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "WH" : Process("WH125", WHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "ZH" : Process("ZH125", ZHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
# "ttH" : Process("ttH125", ttHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
}
# tt_processes["FAKES"] = Process("jetFakes", NewFakeEstimationTT(era, directory, tt, [tt_processes[process] for process in ["EMB", "ZL", "TTL", "VVL"]], tt_processes["data"], friend_directory=[tt_friend_directory, ff_friend_directory]))
tt_processes["QCD"] = Process("QCD", QCDEstimation_ABCD_TT_ISO2(era, directory, tt,
[tt_processes[process] for process in ["ZTT", "ZL", "ZJ", "W", "TTT", "TTJ", "TTL", "VVT", "VVJ", "VVL"]],
tt_processes["data"], friend_directory=tt_friend_directory))
tt_processes["QCDEMB"] = Process("QCDEMB", QCDEstimation_ABCD_TT_ISO2(era, directory, tt,
[tt_processes[process] for process in ["EMB", "ZL", "ZJ", "W", "TTJ", "TTL", "VVJ", "VVL"]],
tt_processes["data"], friend_directory=tt_friend_directory))
em = EMSM2018()
em_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, em, friend_directory=em_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, em, friend_directory=em_friend_directory)),
"EMB" : Process("EMB", ZTTEmbeddedEstimation (era, directory, em, friend_directory=em_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimation (era, directory, em, friend_directory=em_friend_directory)),
"ZL" : Process("ZL", ZLEstimation (era, directory, em, friend_directory=em_friend_directory)),
"TTT" : Process("TTT", TTTEstimation (era, directory, em, friend_directory=em_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimation (era, directory, em, friend_directory=em_friend_directory)),
"TTL" : Process("TTL", TTLEstimation (era, directory, em, friend_directory=em_friend_directory)),
"VVT" : Process("VVT", VVTEstimation (era, directory, em, friend_directory=em_friend_directory)),
"VVJ" : Process("VVJ", VVJEstimation (era, directory, em, friend_directory=em_friend_directory)),
"VVL" : Process("VVL", VVLEstimation (era, directory, em, friend_directory=em_friend_directory)),
"W" : Process("W", WEstimation (era, directory, em, friend_directory=em_friend_directory)),
"ggH" : Process("ggH125", ggHEstimation (era, directory, em, friend_directory=em_friend_directory)),
"qqH" : Process("qqH125", qqHEstimation (era, directory, em, friend_directory=em_friend_directory))
}
em_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, em,
[em_processes[process] for process in ["ZTT", "ZL", "ZJ", "W", "TTT", "TTJ", "TTL", "VVT", "VVJ", "VVL"]],
em_processes["data"], friend_directory=em_friend_directory, extrapolation_factor=1.0, qcd_weight = Weight("em_qcd_extrap_up_Weight","qcd_weight")))
em_processes["QCDEMB"] = Process("QCDEMB", QCDEstimation_SStoOS_MTETEM(era, directory, em,
[em_processes[process] for process in ["EMB", "ZL", "ZJ", "W", "TTJ", "TTL", "VVJ", "VVL"]],
em_processes["data"], friend_directory=em_friend_directory, extrapolation_factor=1.0, qcd_weight = Weight("em_qcd_extrap_up_Weight","qcd_weight")))
# Variables and categories
binning = yaml.load(open(args.binning))
et_categories = []
# Analysis shapes
if "et" in args.channels:
classes_et = ["ggh", "qqh", "ztt", "zll", "w", "tt", "ss", "misc"]
for i, label in enumerate(classes_et):
score = Variable(
"et_max_score",
VariableBinning(binning["analysis"]["et"][label]))
et_categories.append(
Category(
label,
et,
Cuts(
Cut("et_max_index=={index}".format(index=i), "exclusive_score")),
variable=score))
if label in ["ggh", "qqh"]:
expression = ""
for i_e, e in enumerate(binning["stxs_stage1"]["lt"][label]):
offset = (binning["analysis"]["et"][label][-1]-binning["analysis"]["et"][label][0])*i_e
expression += "{STXSBIN}*(et_max_score+{OFFSET})".format(STXSBIN=e, OFFSET=offset)
if not e is binning["stxs_stage1"]["lt"][label][-1]:
expression += " + "
score_unrolled = Variable(
"et_max_score_unrolled",
VariableBinning(binning["analysis"]["et"][label+"_unrolled"]),
expression=expression)
et_categories.append(
Category(
"{}_unrolled".format(label),
et,
Cuts(Cut("et_max_index=={index}".format(index=i), "exclusive_score"),
Cut("et_max_score>{}".format(1.0/len(classes_et)), "protect_unrolling")),
variable=score_unrolled))
# Goodness of fit shapes
elif args.gof_channel == "et":
score = Variable(
args.gof_variable,
VariableBinning(binning["gof"]["et"][args.gof_variable]["bins"]),
expression=binning["gof"]["et"][args.gof_variable]["expression"])
if "cut" in binning["gof"]["et"][args.gof_variable].keys():
cuts=Cuts(Cut(binning["gof"]["et"][args.gof_variable]["cut"], "binning"))
else:
cuts=Cuts()
et_categories.append(
Category(
args.gof_variable,
et,
cuts,
variable=score))
mt_categories = []
# Analysis shapes
if "mt" in args.channels:
classes_mt = ["ggh", "qqh", "ztt", "zll", "w", "tt", "ss", "misc"]
for i, label in enumerate(classes_mt):
score = Variable(
"mt_max_score",
VariableBinning(binning["analysis"]["mt"][label]))
mt_categories.append(
Category(
label,
mt,
Cuts(
Cut("mt_max_index=={index}".format(index=i), "exclusive_score")),
variable=score))
if label in ["ggh", "qqh"]:
expression = ""
for i_e, e in enumerate(binning["stxs_stage1"]["lt"][label]):
offset = (binning["analysis"]["mt"][label][-1]-binning["analysis"]["mt"][label][0])*i_e
expression += "{STXSBIN}*(mt_max_score+{OFFSET})".format(STXSBIN=e, OFFSET=offset)
if not e is binning["stxs_stage1"]["lt"][label][-1]:
expression += " + "
score_unrolled = Variable(
"mt_max_score_unrolled",
VariableBinning(binning["analysis"]["mt"][label+"_unrolled"]),
expression=expression)
mt_categories.append(
Category(
"{}_unrolled".format(label),
mt,
Cuts(Cut("mt_max_index=={index}".format(index=i), "exclusive_score"),
Cut("mt_max_score>{}".format(1.0/len(classes_mt)), "protect_unrolling")),
variable=score_unrolled))
# Goodness of fit shapes
elif args.gof_channel == "mt":
score = Variable(
args.gof_variable,
VariableBinning(binning["gof"]["mt"][args.gof_variable]["bins"]),
expression=binning["gof"]["mt"][args.gof_variable]["expression"])
if "cut" in binning["gof"]["mt"][args.gof_variable].keys():
cuts=Cuts(Cut(binning["gof"]["mt"][args.gof_variable]["cut"], "binning"))
else:
cuts=Cuts()
mt_categories.append(
Category(
args.gof_variable,
mt,
cuts,
variable=score))
tt_categories = []
# Analysis shapes
if "tt" in args.channels:
classes_tt = ["ggh", "qqh", "ztt", "noniso", "misc"]
for i, label in enumerate(classes_tt):
score = Variable(
"tt_max_score",
VariableBinning(binning["analysis"]["tt"][label]))
tt_categories.append(
Category(
label,
tt,
Cuts(
Cut("tt_max_index=={index}".format(index=i), "exclusive_score")),
variable=score))
if label in ["ggh", "qqh"]:
expression = ""
for i_e, e in enumerate(binning["stxs_stage1"]["tt"][label]):
offset = (binning["analysis"]["tt"][label][-1]-binning["analysis"]["tt"][label][0])*i_e
expression += "{STXSBIN}*(tt_max_score+{OFFSET})".format(STXSBIN=e, OFFSET=offset)
if not e is binning["stxs_stage1"]["tt"][label][-1]:
expression += " + "
score_unrolled = Variable(
"tt_max_score_unrolled",
VariableBinning(binning["analysis"]["tt"][label+"_unrolled"]),
expression=expression)
tt_categories.append(
Category(
"{}_unrolled".format(label),
tt,
Cuts(Cut("tt_max_index=={index}".format(index=i), "exclusive_score"),
Cut("tt_max_score>{}".format(1.0/len(classes_tt)), "protect_unrolling")),
variable=score_unrolled))
# Goodness of fit shapes
elif args.gof_channel == "tt":
score = Variable(
args.gof_variable,
VariableBinning(binning["gof"]["tt"][args.gof_variable]["bins"]),
expression=binning["gof"]["tt"][args.gof_variable]["expression"])
if "cut" in binning["gof"]["tt"][args.gof_variable].keys():
cuts=Cuts(Cut(binning["gof"]["tt"][args.gof_variable]["cut"], "binning"))
else:
cuts=Cuts()
tt_categories.append(
Category(
args.gof_variable,
tt,
cuts,
variable=score))
em_categories = []
# Analysis shapes
if "em" in args.channels:
classes_em = ["ggh", "qqh", "ztt", "zll", "w", "tt", "ss", "misc"]
for i, label in enumerate(classes_em):
score = Variable(
"em_max_score",
VariableBinning(binning["analysis"]["em"][label]))
em_categories.append(
Category(
label,
em,
Cuts(
Cut("em_max_index=={index}".format(index=i), "exclusive_score")),
variable=score))
if label in ["ggh", "qqh"]:
expression = ""
for i_e, e in enumerate(binning["stxs_stage1"]["lt"][label]):
offsem = (binning["analysis"]["em"][label][-1]-binning["analysis"]["em"][label][0])*i_e
expression += "{STXSBIN}*(em_max_score+{OFFSem})".format(STXSBIN=e, OFFSem=offsem)
if not e is binning["stxs_stage1"]["lt"][label][-1]:
expression += " + "
score_unrolled = Variable(
"em_max_score_unrolled",
VariableBinning(binning["analysis"]["em"][label+"_unrolled"]),
expression=expression)
em_categories.append(
Category(
"{}_unrolled".format(label),
em,
Cuts(Cut("em_max_index=={index}".format(index=i), "exclusive_score"),
Cut("em_max_score>{}".format(1.0/len(classes_em)), "protect_unrolling")),
variable=score_unrolled))
# Goodness of fit shapes
elif args.gof_channel == "em":
score = Variable(
args.gof_variable,
VariableBinning(binning["gof"]["em"][args.gof_variable]["bins"]),
expression=binning["gof"]["em"][args.gof_variable]["expression"])
if "cut" in binning["gof"]["em"][args.gof_variable].keys():
cuts=Cuts(Cut(binning["gof"]["em"][args.gof_variable]["cut"], "binning"))
else:
cuts=Cuts()
em_categories.append(
Category(
args.gof_variable,
em,
cuts,
variable=score))
# Nominal histograms
if args.gof_channel == None:
signal_nicks = [
"ggH", "qqH", "qqH_VBFTOPO_JET3VETO", "qqH_VBFTOPO_JET3",
"qqH_REST", "qqH_PTJET1_GT200", "qqH_VH2JET", "ggH_0J",
"ggH_1J_PTH_0_60", "ggH_1J_PTH_60_120", "ggH_1J_PTH_120_200",
"ggH_1J_PTH_GT200", "ggH_GE2J_PTH_0_60", "ggH_GE2J_PTH_60_120",
"ggH_GE2J_PTH_120_200", "ggH_GE2J_PTH_GT200", "ggH_VBFTOPO_JET3VETO",
"ggH_VBFTOPO_JET3", "VH", "WH", "ZH", "ttH"
]
else:
signal_nicks = ["ggH", "qqH", "WH", "ZH", "ttH"]
# yapf: enable
if "et" in [args.gof_channel] + args.channels:
for process, category in product(et_processes.values(), et_categories):
systematics.add(
Systematic(category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
if "mt" in [args.gof_channel] + args.channels:
for process, category in product(mt_processes.values(), mt_categories):
systematics.add(
Systematic(category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
if "tt" in [args.gof_channel] + args.channels:
for process, category in product(tt_processes.values(), tt_categories):
systematics.add(
Systematic(category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
if "em" in [args.gof_channel] + args.channels:
for process, category in product(em_processes.values(), em_categories):
systematics.add(
Systematic(category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
# Produce histograms
logger.info("Start producing shapes.")
systematics.produce()
logger.info("Done producing shapes.")
def main(args):
# Container for all distributions to be drawn
logger.info("Set up shape variations.")
systematics = Systematics(
"{}_shapes.root".format(args.tag),
num_threads=args.num_threads,
skip_systematic_variations=args.skip_systematic_variations)
# Era selection
if "2018" in args.era:
from shape_producer.estimation_methods_2018 import DataEstimation, ZTTEstimation, ZTTEmbeddedEstimation, ZLEstimation, ZJEstimation, TTLEstimation, TTJEstimation, TTTEstimation, VVLEstimation, VVTEstimation, VVJEstimation, WEstimation, ggHEstimation, ggHEstimation_0J, ggHEstimation_1J_PTH_0_60, ggHEstimation_1J_PTH_60_120, ggHEstimation_1J_PTH_120_200, ggHEstimation_1J_PTH_GT200, ggHEstimation_GE2J_PTH_0_60, ggHEstimation_GE2J_PTH_60_120, ggHEstimation_GE2J_PTH_120_200, ggHEstimation_GE2J_PTH_GT200, ggHEstimation_VBFTOPO_JET3, ggHEstimation_VBFTOPO_JET3VETO, qqHEstimation, qqHEstimation_VBFTOPO_JET3VETO, qqHEstimation_VBFTOPO_JET3, qqHEstimation_REST, qqHEstimation_VH2JET, qqHEstimation_PTJET1_GT200, VHEstimation, WHEstimation, ZHEstimation, ttHEstimation, QCDEstimation_ABCD_TT_ISO2, QCDEstimation_SStoOS_MTETEM, FakeEstimationLT, NewFakeEstimationLT, FakeEstimationTT, NewFakeEstimationTT, DYJetsToLLEstimation, TTEstimation, VVEstimation
from shape_producer.era import Run2018
era = Run2018(args.datasets)
else:
logger.critical("Era {} is not implemented.".format(args.era))
raise Exception
wp_dict_mva = {
"vvloose": "byVVLooseIsolationMVArun2017v2DBoldDMwLT2017_2",
"vloose": "byVLooseIsolationMVArun2017v2DBoldDMwLT2017_2",
"loose": "byLooseIsolationMVArun2017v2DBoldDMwLT2017_2",
"medium": "byMediumIsolationMVArun2017v2DBoldDMwLT2017_2",
"tight": "byTightIsolationMVArun2017v2DBoldDMwLT2017_2",
"vtight": "byVTightIsolationMVArun2017v2DBoldDMwLT2017_2",
"vvtight": "byVVTightIsolationMVArun2017v2DBoldDMwLT2017_2",
"mm": "0<1",
}
wp_dict_deeptau = {
"vvvloose": "byVVVLooseDeepTau2017v2p1VSjet_2",
"vvloose": "byVVLooseDeepTau2017v2p1VSjet_2",
"vloose": "byVLooseDeepTau2017v2p1VSjet_2",
"loose": "byLooseDeepTau2017v2p1VSjet_2",
"medium": "byMediumDeepTau2017v2p1VSjet_2",
"tight": "byTightDeepTau2017v2p1VSjet_2",
"vtight": "byVTightDeepTau2017v2p1VSjet_2",
"vvtight": "byVVTightDeepTau2017v2p1VSjet_2",
"mm": "0<1",
}
wp_dict = wp_dict_deeptau
logger.info("Produce shapes for the %s working point of the MVA Tau ID",
args.working_point)
# Channels and processes
# yapf: disable
directory = args.directory
et_friend_directory = []#args.et_friend_directory
em_friend_directory = []#args.em_friend_directory
mt_friend_directory = []#args.mt_friend_directory
tt_friend_directory = []#args.tt_friend_directory
ff_friend_directory = []#args.fake_factor_friend_directory
mt = MTTauID2018()
mt.cuts.add(Cut(wp_dict[args.working_point]+">0.5", "tau_iso"))
# if args.gof_channel == "mt":
# mt.cuts.remove("m_t")
# mt.cuts.remove("dZeta")
# mt.cuts.remove("absEta")
mt_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"EMB" : Process("EMB", ZTTEmbeddedEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"ZL" : Process("ZL", ZLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"TTT" : Process("TTT", TTTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"TTL" : Process("TTL", TTLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"VVT" : Process("VVT", VVTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"VVJ" : Process("VVJ", VVJEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"VVL" : Process("VVL", VVLEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"W" : Process("W", WEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
}
# mt_processes["FAKES"] = Process("jetFakes", NewFakeEstimationLT(era, directory, mt, [mt_processes[process] for process in ["EMB", "ZL", "TTL", "VVL"]], mt_processes["data"], friend_directory=[mt_friend_directory, ff_friend_directory]))
#mt_fakes_for_uncs=Process("jetFakes", FakeEstimationLT(era, directory, mt, friend_directory=[mt_friend_directory, ff_friend_directory]))
mt_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, mt,
[mt_processes[process] for process in ["ZTT", "ZL", "ZJ", "TTL","TTT","TTJ", "VVT", "VVJ", "VVL","W"]],
mt_processes["data"], friend_directory=mt_friend_directory, extrapolation_factor=1.1))
mt_processes["QCDEMB"] = Process("QCDEMB", QCDEstimation_SStoOS_MTETEM(era, directory, mt,
[mt_processes[process] for process in ["EMB", "ZL", "ZJ", "TTL", "TTJ", "VVJ", "VVL","W"]],
mt_processes["data"], friend_directory=mt_friend_directory, extrapolation_factor=1.1))
# TODO: Include Z-> mumu control region.
mm = MMTauID2018()
mm_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, mm, friend_directory=[])),
"ZLL" : Process("ZLL", DYJetsToLLEstimation (era, directory, mm, friend_directory=[])),
"MMEMB" : Process("MMEMB", ZTTEmbeddedEstimation(era, directory, mm, friend_directory=[])),
"TT" : Process("TT", TTEstimation (era, directory, mm, friend_directory=[])),
"VV" : Process("VV", VVEstimation (era, directory, mm, friend_directory=[])),
"W" : Process("W", WEstimation (era, directory, mm, friend_directory=[])),
}
# mm_processes["FAKES"] = None TODO: Add fake factors or alternative fake rate estimation here
mm_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, mm,
[mm_processes[process] for process in ["ZLL", "W", "TT", "VV"]],
mm_processes["data"], friend_directory=[], extrapolation_factor=1.17))
mm_processes["QCDEMB"] = Process("QCDEMB", QCDEstimation_SStoOS_MTETEM(era, directory, mm,
[mm_processes[process] for process in ["MMEMB", "W"]],
mm_processes["data"], friend_directory=[], extrapolation_factor=1.17))
# Variables and categories
binning = yaml.load(open(args.binning))
mt_categories = []
# Goodness of fit shapes
if args.gof_channel == "mt":
score = Variable(
args.gof_variable,
VariableBinning(binning["control"]["mt"][args.gof_variable]["bins"]),
expression=binning["control"]["mt"][args.gof_variable]["expression"])
if "cut" in binning["control"]["mt"][args.gof_variable].keys():
cuts=Cuts(Cut(binning["control"]["mt"][args.gof_variable]["cut"], "binning"))
else:
cuts=Cuts()
mt_categories.append(
Category(
args.gof_variable,
mt,
cuts,
variable=score))
elif "mt" in args.channels:
for cat in binning["categories"]["mt"]:
category = Category(
cat,
mt,
Cuts(Cut(binning["categories"]["mt"][cat]["cut"], "category")),
variable=Variable(binning["categories"]["mt"][cat]["var"],
VariableBinning(binning["categories"]["mt"][cat]["bins"]),
expression=binning["categories"]["mt"][cat]["expression"]))
mt_categories.append(category)
# yapf: enable
if "mt" in [args.gof_channel] + args.channels:
for process, category in product(mt_processes.values(), mt_categories):
systematics.add(
Systematic(category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
mm_categories = []
if "mm" in args.channels:
category = Category("control",
mm,
Cuts(),
variable=Variable("m_vis",
ConstantBinning(1, 50, 150),
"m_vis"))
mm_categories.append(category)
if "mm" in args.channels:
for process, category in product(mm_processes.values(), mm_categories):
systematics.add(
Systematic(category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
# Shapes variations
# MC tau energy scale
tau_es_3prong_variations = create_systematic_variations(
"CMS_scale_mc_t_3prong_Run2018", "tauEsThreeProng", DifferentPipeline)
tau_es_1prong_variations = create_systematic_variations(
"CMS_scale_mc_t_1prong_Run2018", "tauEsOneProng", DifferentPipeline)
tau_es_1prong1pizero_variations = create_systematic_variations(
"CMS_scale_mc_t_1prong1pizero_Run2018", "tauEsOneProngOnePiZero",
DifferentPipeline)
for variation in tau_es_3prong_variations + tau_es_1prong_variations + tau_es_1prong1pizero_variations:
for process_nick in [
"ZTT",
"TTT",
"TTL",
"VVL",
"VVT", # "FAKES"
]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
# Tau energy scale
tau_es_3prong_variations = create_systematic_variations(
"CMS_scale_t_3prong_Run2018", "tauEsThreeProng", DifferentPipeline)
tau_es_1prong_variations = create_systematic_variations(
"CMS_scale_t_1prong_Run2018", "tauEsOneProng", DifferentPipeline)
tau_es_1prong1pizero_variations = create_systematic_variations(
"CMS_scale_t_1prong1pizero_Run2018", "tauEsOneProngOnePiZero",
DifferentPipeline)
for variation in tau_es_3prong_variations + tau_es_1prong_variations + tau_es_1prong1pizero_variations:
for process_nick in [
"ZTT",
"TTT",
"TTL",
"VVT",
"VVL",
"EMB", # "FAKES"
]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
# Jet energy scale
# Inclusive JES shapes TODO: Check this
jet_es_variations = []
'''jet_es_variations += create_systematic_variations(
"CMS_scale_j_Run2017", "jecUnc", DifferentPipeline)'''
# Splitted JES shapes
jet_es_variations += create_systematic_variations(
"CMS_scale_j_eta0to3_Run2018", "jecUncEta0to3", DifferentPipeline)
jet_es_variations += create_systematic_variations(
"CMS_scale_j_eta0to5_Run2018", "jecUncEta0to5", DifferentPipeline)
jet_es_variations += create_systematic_variations(
"CMS_scale_j_eta3to5_Run2018", "jecUncEta3to5", DifferentPipeline)
jet_es_variations += create_systematic_variations(
"CMS_scale_j_RelativeBal_Run2018", "jecUncRelativeBal",
DifferentPipeline)
jet_es_variations += create_systematic_variations(
"CMS_scale_j_RelativeSample_Run2018", "jecUncRelativeSample",
DifferentPipeline)
for variation in jet_es_variations:
for process_nick in [
"ZTT",
"ZL",
"ZJ",
"W",
"TTT",
"TTL",
"TTJ",
"VVT",
"VVJ",
"VVL",
]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
# MET energy scale. Note: only those variations for non-resonant processes are used in the stat. inference
met_unclustered_variations = create_systematic_variations(
"CMS_scale_met_unclustered", "metUnclusteredEn", DifferentPipeline)
for variation in met_unclustered_variations: # + met_clustered_variations:
for process_nick in [
"ZTT",
"ZL",
"ZJ",
"W",
"TTT",
"TTL",
"TTJ",
"VVT",
"VVJ",
"VVL",
]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
# Recoil correction unc
recoil_resolution_variations = create_systematic_variations(
"CMS_htt_boson_reso_met_Run2018", "metRecoilResolution",
DifferentPipeline)
recoil_response_variations = create_systematic_variations(
"CMS_htt_boson_scale_met_Run2018", "metRecoilResponse",
DifferentPipeline)
for variation in recoil_resolution_variations + recoil_response_variations:
for process_nick in ["ZTT", "ZL", "ZJ", "W"]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
# Z pt reweighting
zpt_variations = create_systematic_variations("CMS_htt_dyShape_Run2018",
"zPtReweightWeight",
SquareAndRemoveWeight)
for variation in zpt_variations:
for process_nick in ["ZTT", "ZL", "ZJ"]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
# top pt reweighting
top_pt_variations = create_systematic_variations("CMS_htt_ttbarShape",
"topPtReweightWeight",
SquareAndRemoveWeight)
for variation in top_pt_variations:
for process_nick in ["TTT", "TTL", "TTJ"]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
# TODO: likely not necessary, to be checked
# jet to tau fake efficiency
jet_to_tau_fake_variations = []
jet_to_tau_fake_variations.append(
AddWeight("CMS_htt_jetToTauFake_Run2018", "jetToTauFake_weight",
Weight("max(1.0-pt_2*0.002, 0.6)", "jetToTauFake_weight"),
"Up"))
jet_to_tau_fake_variations.append(
AddWeight("CMS_htt_jetToTauFake_Run2018", "jetToTauFake_weight",
Weight("min(1.0+pt_2*0.002, 1.4)", "jetToTauFake_weight"),
"Down"))
for variation in jet_to_tau_fake_variations:
for process_nick in ["ZJ", "TTJ", "W", "VVJ"]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
# ZL fakes energy scale
mu_fake_es_1prong_variations = create_systematic_variations(
"CMS_ZLShape_mt_1prong_Run2018", "tauMuFakeEsOneProng",
DifferentPipeline)
mu_fake_es_1prong1pizero_variations = create_systematic_variations(
"CMS_ZLShape_mt_1prong1pizero_Run2018", "tauMuFakeEsOneProngPiZeros",
DifferentPipeline)
if "mt" in [args.gof_channel] + args.channels:
for process_nick in ["ZL"]:
for variation in mu_fake_es_1prong_variations + mu_fake_es_1prong1pizero_variations:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
# lepton trigger efficiency
lep_trigger_eff_variations = []
lep_trigger_eff_variations.append(
AddWeight(
"CMS_eff_trigger_mt_Run2018", "trg_mt_eff_weight",
Weight("(1.0*(pt_1<=25)+1.02*(pt_1>25))", "trg_mt_eff_weight"),
"Up"))
lep_trigger_eff_variations.append(
AddWeight(
"CMS_eff_trigger_mt_Run2018", "trg_mt_eff_weight",
Weight("(1.0*(pt_1<=25)+0.98*(pt_1>25))", "trg_mt_eff_weight"),
"Down"))
for variation in lep_trigger_eff_variations:
for process_nick in [
"ZTT",
"ZL",
"ZJ",
"W",
"TTT",
"TTL",
"TTJ",
"VVL",
"VVT",
"VVJ",
]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
for process_nick in ["ZLL", "TT", "VV", "W"]:
if "mm" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mm_processes[process_nick],
channel=mm,
era=era)
lep_trigger_eff_variations = []
lep_trigger_eff_variations.append(
AddWeight(
"CMS_eff_trigger_emb_mt_Run2018", "trg_mt_eff_weight",
Weight("(1.0*(pt_1<=25)+1.02*(pt_1>25))", "trg_mt_eff_weight"),
"Up"))
lep_trigger_eff_variations.append(
AddWeight(
"CMS_eff_trigger_emb_mt_Run2018", "trg_mt_eff_weight",
Weight("(1.0*(pt_1<=25)+0.98*(pt_1>25))", "trg_mt_eff_weight"),
"Down"))
for variation in lep_trigger_eff_variations:
for process_nick in ["EMB"]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
for process_nick in ["MMEMB"]:
if "mm" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mm_processes[process_nick],
channel=mm,
era=era)
# b tagging
# btag_eff_variations = create_systematic_variations(
# "CMS_htt_eff_b_Run2017", "btagEff", DifferentPipeline)
# mistag_eff_variations = create_systematic_variations(
# "CMS_htt_mistag_b_Run2017", "btagMistag", DifferentPipeline)
# for variation in btag_eff_variations + mistag_eff_variations:
# for process_nick in [
# "ZTT", "ZL", "ZJ", "W", "TTT", "TTL", "TTJ", "VVT", "VVJ",
# "VVL"
# ]:
# if "et" in [args.gof_channel] + args.channels:
# systematics.add_systematic_variation(
# variation=variation,
# process=et_processes[process_nick],
# channel=et,
# era=era)
# if "mt" in [args.gof_channel] + args.channels:
# systematics.add_systematic_variation(
# variation=variation,
# process=mt_processes[process_nick],
# channel=mt,
# era=era)
# if "tt" in [args.gof_channel] + args.channels:
# systematics.add_systematic_variation(
# variation=variation,
# process=tt_processes[process_nick],
# channel=tt,
# era=era)
# for process_nick in ["ZTT", "ZL", "W", "TTT", "TTL", "VVL", "VVT"
# ]:
# if "em" in [args.gof_channel] + args.channels:
# systematics.add_systematic_variation(
# variation=variation,
# process=em_processes[process_nick],
# channel=em,
# era=era)
# Embedded event specifics
# Tau energy scale
tau_es_3prong_variations = create_systematic_variations(
"CMS_scale_emb_t_3prong_Run2018", "tauEsThreeProng", DifferentPipeline)
tau_es_1prong_variations = create_systematic_variations(
"CMS_scale_emb_t_1prong_Run2018", "tauEsOneProng", DifferentPipeline)
tau_es_1prong1pizero_variations = create_systematic_variations(
"CMS_scale_emb_t_1prong1pizero_Run2018", "tauEsOneProngOnePiZero",
DifferentPipeline)
for variation in tau_es_3prong_variations + tau_es_1prong_variations + tau_es_1prong1pizero_variations:
for process_nick in ["EMB"]: #, "FAKES"]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
mt_decayMode_variations = []
mt_decayMode_variations.append(
ReplaceWeight(
"CMS_3ProngEff_Run2018", "decayMode_SF",
Weight("embeddedDecayModeWeight_effUp_pi0Nom", "decayMode_SF"),
"Up"))
mt_decayMode_variations.append(
ReplaceWeight(
"CMS_3ProngEff_Run2018", "decayMode_SF",
Weight("embeddedDecayModeWeight_effDown_pi0Nom", "decayMode_SF"),
"Down"))
mt_decayMode_variations.append(
ReplaceWeight(
"CMS_1ProngPi0Eff_Run2018", "decayMode_SF",
Weight("embeddedDecayModeWeight_effNom_pi0Up", "decayMode_SF"),
"Up"))
mt_decayMode_variations.append(
ReplaceWeight(
"CMS_1ProngPi0Eff_Run2018", "decayMode_SF",
Weight("embeddedDecayModeWeight_effNom_pi0Down", "decayMode_SF"),
"Down"))
for variation in mt_decayMode_variations:
for process_nick in ["EMB"]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
# 10% removed events in ttbar simulation (ttbar -> real tau tau events) will be added/subtracted to ZTT shape to use as systematic
tttautau_process_mt = Process(
"TTT", TTTEstimation(era, directory, mt, friend_directory=[]))
if "mt" in [args.gof_channel] + args.channels:
for category in mt_categories:
mt_processes['ZTTpTTTauTauDown'] = Process(
"ZTTpTTTauTauDown",
AddHistogramEstimationMethod(
"AddHistogram", "nominal", era, directory, mt,
[mt_processes["EMB"], tttautau_process_mt], [1.0, -0.1]))
systematics.add(
Systematic(category=category,
process=mt_processes['ZTTpTTTauTauDown'],
analysis="smhtt",
era=era,
variation=Relabel("CMS_htt_emb_ttbar_Run2018",
"Down"),
mass="125"))
mt_processes['ZTTpTTTauTauUp'] = Process(
"ZTTpTTTauTauUp",
AddHistogramEstimationMethod(
"AddHistogram", "nominal", era, directory, mt,
[mt_processes["EMB"], tttautau_process_mt], [1.0, 0.1]))
systematics.add(
Systematic(category=category,
process=mt_processes['ZTTpTTTauTauUp'],
analysis="smhtt",
era=era,
variation=Relabel("CMS_htt_emb_ttbar_Run2018",
"Up"),
mass="125"))
# jetfakes
# fake_factor_variations_mt = []
# for systematic_shift in [
# "ff_qcd{ch}_syst_Run2017{shift}",
# "ff_qcd_dm0_njet0{ch}_stat_Run2017{shift}",
# "ff_qcd_dm0_njet1{ch}_stat_Run2017{shift}",
# #"ff_qcd_dm1_njet0{ch}_stat_Run2017{shift}",
# #"ff_qcd_dm1_njet1{ch}_stat_Run2017{shift}",
# "ff_w_syst_Run2017{shift}",
# "ff_w_dm0_njet0{ch}_stat_Run2017{shift}",
# "ff_w_dm0_njet1{ch}_stat_Run2017{shift}",
# #"ff_w_dm1_njet0{ch}_stat_Run2017{shift}",
# #"ff_w_dm1_njet1{ch}_stat_Run2017{shift}",
# "ff_tt_syst_Run2017{shift}",
# "ff_tt_dm0_njet0_stat_Run2017{shift}",
# "ff_tt_dm0_njet1_stat_Run2017{shift}",
# #"ff_tt_dm1_njet0_stat_Run2017{shift}",
# #"ff_tt_dm1_njet1_stat_Run2017{shift}"
# ]:
# for shift_direction in ["Up", "Down"]:
# fake_factor_variations_mt.append(
# ReplaceWeight(
# "CMS_%s" % (systematic_shift.format(ch='_mt', shift="").replace("_dm0", "")),
# "fake_factor",
# Weight(
# "ff2_{syst}".format(
# syst=systematic_shift.format(
# ch="", shift="_%s" % shift_direction.lower())
# .replace("_Run2017", "")),
# "fake_factor"), shift_direction))
# if "mt" in [args.gof_channel] + args.channels:
# for variation in fake_factor_variations_mt:
# systematics.add_systematic_variation(
# variation=variation,
# process=mt_processes["FAKES"],
# channel=mt,
# era=era)
# Produce histograms
logger.info("Start producing shapes.")
systematics.produce()
logger.info("Done producing shapes.")
def main(args):
# Container for all distributions to be drawn
systematics_mm = Systematics("fitrecoil_mm_2018.root", num_threads=args.num_threads, find_unique_objects=True)
# Era
era = Run2018(args.datasets)
# Channels and processes
# yapf: disable
directory = args.directory
mm_friend_directory = args.mm_friend_directory
mm = MM()
mm_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"ZL" : Process("ZL", ZLEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"TTT" : Process("TTT", TTTEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"TTL" : Process("TTL", TTLEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"VVT" : Process("VVT", VVTEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"VVL" : Process("VVL", VVLEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
"W" : Process("W", WEstimation (era, directory, mm, friend_directory=mm_friend_directory)),
}
mm_processes["QCD"] = Process("QCD", QCDEstimation_SStoOS_MTETEM(era, directory, mm,
[mm_processes[process] for process in ["ZTT", "ZL", "W", "TTT", "TTL", "VVT", "VVL"]],
mm_processes["data"], friend_directory=mm_friend_directory, extrapolation_factor=2.0))
# Variables and categories
mm_categories = []
variable_names = [
# "met", "metphi",
# "puppimet", "puppimetphi",
"metParToZ", "metPerpToZ",
"puppimetParToZ", "puppimetPerpToZ",
# "recoilParToZ", "recoilPerpToZ",
# "puppirecoilParToZ", "puppirecoilPerpToZ",
]
variables = [Variable(v,ConstantBinning(25,-100.0,100.0)) for v in variable_names]
cuts = [
Cut("njets == 0", "0jet"),
Cut("njets == 1", "1jet"),
Cut("njets >= 2", "ge2jet"),
]
for cut in cuts:
for var in variables:
mm_categories.append(
Category(
cut.name,
mm,
Cuts(Cut("m_vis > 70 && m_vis < 110","m_vis_peak"), cut),
variable=var))
for process, category in product(mm_processes.values(), mm_categories):
systematics_mm.add(
Systematic(
category=category,
process=process,
analysis="smhtt",
era=era,
variation=Nominal(),
mass="125"))
# Recoil correction unc
recoil_resolution_variations = create_systematic_variations(
"CMS_htt_boson_reso_met_Run2018", "metRecoilResolution",
DifferentPipeline)
recoil_response_variations = create_systematic_variations(
"CMS_htt_boson_scale_met_Run2018", "metRecoilResponse",
DifferentPipeline)
for variation in recoil_resolution_variations + recoil_response_variations:
systematics_mm.add_systematic_variation(
variation=variation,
process=mm_processes["ZL"],
channel=mm,
era=era)
# Produce histograms
systematics_mm.produce()
def main(args):
# Define era
if "2016" in args.era:
from shape_producer.era import Run2016
era = Run2016(args.datasets)
elif "2017" in args.era:
from shape_producer.era import Run2017
era = Run2017(args.datasets)
elif "2018" in args.era:
from shape_producer.era import Run2018
era = Run2018(args.datasets)
else:
logger.fatal("Era {} is not implemented.".format(args.era))
raise Exception
# Load variables
variables = yaml.load(open(args.variables))["selected_variables"]
# Define bins and range of binning for variables in enabled channels
channel_dict = {
"et": {
"2016": ETSM2016(),
"2017": ETSM2017(),
"2018": ETSM2018()
},
"mt": {
"2016": MTSM2016(),
"2017": MTSM2017(),
"2018": MTSM2018()
},
"tt": {
"2016": TTSM2016(),
"2017": TTSM2017(),
"2018": TTSM2018()
},
"em": {
"2016": EMSM2016(),
"2017": EMSM2017(),
"2018": EMSM2018()
},
}
friend_directories_dict = {
"em": args.em_friend_directories,
"et": args.et_friend_directories,
"mt": args.mt_friend_directories,
"tt": args.tt_friend_directories,
}
percentiles = [
0.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 70.0, 80.0, 90.0, 100.0
]
config = {"gof": {}}
for ch in channel_dict.keys():
if ch != args.channel:
continue
# Get properties
if "2016" in args.era:
eraname = "2016"
elif "2017" in args.era:
eraname = "2017"
elif "2018" in args.era:
eraname = "2018"
channel = channel_dict[ch][eraname]
logger.info("Channel: %s" % ch)
dict_ = {}
additional_cuts = Cuts()
logger.warning("Use additional cuts for %s: %s" %
(ch, additional_cuts.expand()))
dict_ = get_properties(dict_, era, channel, args.directory,
additional_cuts)
# Build chain
dict_["tree_path"] = "%s_nominal/ntuple" % ch
chain = build_chain(dict_, friend_directories_dict[ch])
# Get percentiles and calculate 1d binning
binning = get_1d_binning(ch, chain, variables[int(eraname)][ch],
percentiles)
# Add binning for unrolled 2d distributions
binning = add_2d_unrolled_binning(variables[int(eraname)][ch], binning)
# Append binning to config
config["gof"][ch] = binning
# Write config
logger.info("Write binning config to %s.", args.output)
yaml.dump(config, open(args.output, 'w'))
"mt": MTSM2017(),
"et": ETSM2017(),
"tt": TTSM2017(),
"em": EMSM2017()
},
"2018": {
"mt": MTSM2018(),
"et": ETSM2018(),
"tt": TTSM2018(),
"em": EMSM2018()
}
}
eraD = {
"2016": Run2016(database),
"2017": Run2017(database),
"2018":Run2018(database)
}
from shape_producer.estimation_methods_2017 import DataEstimation, ZTTEstimation, ZJEstimation, ZLEstimation, TTLEstimation, TTJEstimation, TTTEstimation, VVTEstimation, VVJEstimation, VVLEstimation, WEstimation, ggHEstimation, qqHEstimation, EWKZEstimation, ZTTEmbeddedEstimation, NewFakeEstimationTT, NewFakeEstimationLT
from fake_factor_derivation.cuts import cutDB
class ParSpaceRegion(object):
def __init__(self, eraName, channelName, bkgName):
self.meta = {"era": eraName, "channel": channelName, "bkg": bkgName}
self.era = eraD[eraName]
self.channel = copy.deepcopy(channelDict[eraName][channelName])
if self.meta["era"] not in ["2016", "2017"]: raise Exception
### remove old isolation cuts and add the very Loose isolation, that is needed to to exclude other backgrounds from all regions
# for cut_ in self.channel.cuts.names: