def estimationMethodAndClassMapGenerator():
estimationMethodList = [
DataEstimation(era, args.base_path, channel),
ggHEstimation("ggH125", era, args.base_path, channel),
qqHEstimation("qqH125", era, args.base_path, channel),
HWWEstimation(era, args.base_path, channel),
]
return (estimationMethodList)
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["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, HTTEstimation, ggHEstimation, qqHEstimation, VHEstimation, ZTTEstimation, ZTTEstimationTT, ZLEstimationMTSM, ZLEstimationETSM, ZLEstimationTT, ZJEstimationMT, ZJEstimationET, ZJEstimationTT, WEstimationRaw, TTTEstimationMT, TTTEstimationET, TTTEstimationTT, TTJEstimationMT, TTJEstimationET, TTJEstimationTT, VVEstimation, QCDEstimationMT, QCDEstimationET, QCDEstimationTT, ZTTEmbeddedEstimation, TTLEstimationMT, TTLEstimationET, TTLEstimationTT, TTTTEstimationMT, TTTTEstimationET, EWKWpEstimation, EWKWmEstimation, EWKZllEstimation, EWKZnnEstimation
from shape_producer.era import Run2016
era = Run2016(args.database)
else:
logger.fatal("Era {} is not implemented.".format(args.era))
raise Exception
############################################################################
# Channel: mt
if args.channel == "mt":
channel = MTSM()
# 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())
# MC-driven processes
# NOTE: Define here the mappig of the process estimations to the training classes
classes_map = {
"ggH": "ggh",
"qqH": "qqh",
"ZTT": "ztt",
"EMB": "ztt",
"ZL": "zll",
"ZJ": "zll",
"TTT": "tt",
"TTL": "tt",
"TTJ": "tt",
"W": "w",
"EWKWp": "w",
"EWKWm": "w",
"VV": "misc",
"EWKZll": "misc",
"EWKZnn": "misc"
}
for estimation in [
ggHEstimation(era, args.base_path, channel),
qqHEstimation(era, args.base_path, channel),
ZTTEstimation(era, args.base_path, channel),
#ZTTEmbeddedEstimation(era, args.base_path, channel),
ZLEstimationMTSM(era, args.base_path, channel),
ZJEstimationMT(era, args.base_path, channel),
TTTEstimationMT(era, args.base_path, channel),
#TTLEstimationMT(era, args.base_path, channel),
TTJEstimationMT(era, args.base_path, channel),
WEstimationRaw(era, args.base_path, channel),
EWKWpEstimation(era, args.base_path, channel),
EWKWmEstimation(era, args.base_path, channel),
VVEstimation(era, args.base_path, channel),
EWKZllEstimation(era, args.base_path, channel),
#EWKZnnEstimation(era, args.base_path, channel)
]:
output_config["processes"][estimation.name] = {
"files": [
str(f).replace(args.base_path + "/", "")
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_ss = copy.deepcopy(channel)
channel_ss.cuts.get("os").invert()
output_config["processes"][estimation.name] = {
"files": [
str(f).replace(args.base_path + "/", "")
for f in estimation.get_files()
],
"cut_string": (estimation.get_cuts() + channel_ss.cuts +
additional_cuts).expand(),
"weight_string":
estimation.get_weights().extract(),
"class":
"ss"
}
############################################################################
# Channel: et
if args.channel == "et":
channel = ETSM()
# Set up `processes` part of config
output_config["processes"] = {}
# Additional cuts
additional_cuts = Cuts()
logger.warning("Use additional cuts for et: %s",
additional_cuts.expand())
# MC-driven processes
# NOTE: Define here the mappig of the process estimations to the training classes
classes_map = {
"ggH": "ggh",
"qqH": "qqh",
"ZTT": "ztt",
"EMB": "ztt",
"ZL": "zll",
"ZJ": "zll",
"TTT": "tt",
"TTL": "tt",
"TTJ": "tt",
"W": "w",
"EWKWp": "w",
"EWKWm": "w",
"VV": "misc",
"EWKZll": "misc",
"EWKZnn": "misc"
}
for estimation in [
ggHEstimation(era, args.base_path, channel),
qqHEstimation(era, args.base_path, channel),
ZTTEstimation(era, args.base_path, channel),
#ZTTEmbeddedEstimation(era, args.base_path, channel),
ZLEstimationETSM(era, args.base_path, channel),
ZJEstimationET(era, args.base_path, channel),
TTTEstimationET(era, args.base_path, channel),
#TTLEstimationET(era, args.base_path, channel),
TTJEstimationET(era, args.base_path, channel),
WEstimationRaw(era, args.base_path, channel),
EWKWpEstimation(era, args.base_path, channel),
EWKWmEstimation(era, args.base_path, channel),
VVEstimation(era, args.base_path, channel),
EWKZllEstimation(era, args.base_path, channel),
#EWKZnnEstimation(era, args.base_path, channel)
]:
output_config["processes"][estimation.name] = {
"files": [
str(f).replace(args.base_path + "/", "")
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_ss = copy.deepcopy(channel)
channel_ss.cuts.get("os").invert()
output_config["processes"][estimation.name] = {
"files": [
str(f).replace(args.base_path + "/", "")
for f in estimation.get_files()
],
"cut_string": (estimation.get_cuts() + channel_ss.cuts +
additional_cuts).expand(),
"weight_string":
estimation.get_weights().extract(),
"class":
"ss"
}
############################################################################
# Channel: tt
if args.channel == "tt":
channel = TTSM()
# Set up `processes` part of config
output_config["processes"] = {}
# Additional cuts
additional_cuts = Cuts()
logger.warning("Use additional cuts for tt: %s",
additional_cuts.expand())
# MC-driven processes
# NOTE: Define here the mappig of the process estimations to the training classes
classes_map = {
"ggH": "ggh",
"qqH": "qqh",
"ZTT": "ztt",
"EMB": "ztt",
"ZL": "misc",
"ZJ": "misc",
"TTT": "misc",
"TTL": "misc",
"TTJ": "misc",
"W": "misc",
"EWKWp": "misc",
"EWKWm": "misc",
"VV": "misc",
"EWKZll": "misc",
"EWKZnn": "misc"
}
for estimation in [
ggHEstimation(era, args.base_path, channel),
qqHEstimation(era, args.base_path, channel),
ZTTEstimationTT(era, args.base_path, channel),
#ZTTEmbeddedEstimation(era, args.base_path, channel),
ZLEstimationTT(era, args.base_path, channel),
ZJEstimationTT(era, args.base_path, channel),
TTTEstimationTT(era, args.base_path, channel),
#TTLEstimationTT(era, args.base_path, channel),
TTJEstimationTT(era, args.base_path, channel),
WEstimationRaw(era, args.base_path, channel),
EWKWpEstimation(era, args.base_path, channel),
EWKWmEstimation(era, args.base_path, channel),
VVEstimation(era, args.base_path, channel),
EWKZllEstimation(era, args.base_path, channel),
#EWKZnnEstimation(era, args.base_path, channel)
]:
output_config["processes"][estimation.name] = {
"files": [
str(f).replace(args.base_path + "/", "")
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_iso = copy.deepcopy(channel)
channel_iso.cuts.remove("tau_2_iso")
channel_iso.cuts.add(
Cut("byTightIsolationMVArun2v1DBoldDMwLT_2<0.5", "tau_2_iso"))
channel_iso.cuts.add(
Cut("byLooseIsolationMVArun2v1DBoldDMwLT_2>0.5",
"tau_2_iso_loose"))
output_config["processes"][estimation.name] = {
"files": [
str(f).replace(args.base_path + "/", "")
for f in estimation.get_files()
],
"cut_string": (estimation.get_cuts() + channel_iso.cuts +
additional_cuts).expand(),
"weight_string":
estimation.get_weights().extract(),
"class":
"noniso"
}
############################################################################
# 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
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 "2016" in args.era:
from shape_producer.estimation_methods_2016 import DataEstimation, ZTTEstimation, ZTTEmbeddedEstimation, ZLEstimation, ZJEstimation, TTTEstimation, TTLEstimation, TTJEstimation, VVTEstimation, VVLEstimation, VVJEstimation, WEstimation, HTTEstimation, ggHEstimation, qqHEstimation, VHEstimation, WHEstimation, ZHEstimation, ttHEstimation, HWWEstimation, ggHWWEstimation, qqHWWEstimation, SUSYggHEstimation, SUSYbbHEstimation, QCDEstimation_SStoOS_MTETEM, QCDEstimationTT, NewFakeEstimationLT, NewFakeEstimationTT
from shape_producer.era import Run2016
era = Run2016(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 = {
"et": ETMSSM2016(),
"mt": MTMSSM2016(),
"tt": TTMSSM2016(),
"em": EMMSSM2016(),
}
susyggH_masses = [80, 90, 100, 110, 120, 130, 140, 160, 180, 200, 250, 300, 350, 400, 450, 500, 600, 700, 800, 900, 1000, 1200, 1400, 1500, 1600, 1800, 2000, 2300, 2600, 2900, 3200]
susybbH_masses = [80, 90, 100, 110, 120, 130, 140, 160, 180, 200, 250, 300, 350, 400, 450, 500, 600, 700, 800, 900, 1000, 1200, 1400, 1500, 1600, 1800, 2000, 2300, 2600, 2900, 3200]
susybbH_nlo_masses = []
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_Run2016", updownvar), mass="125"))
# Prefiring weights
prefiring_variations = [
ReplaceWeight("CMS_prefiring_Run2016", "prefireWeight", Weight("prefiringweightup", "prefireWeight"),"Up"),
ReplaceWeight("CMS_prefiring_Run2016", "prefireWeight", Weight("prefiringweightdown", "prefireWeight"),"Down"),
]
# 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_Run2016", "jecUncAbsoluteYear", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_BBEC1", "jecUncBBEC1", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_BBEC1_Run2016", "jecUncBBEC1Year", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_EC2", "jecUncEC2", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_EC2_Run2016", "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_Run2016", "jecUncHFYear", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_RelativeBal", "jecUncRelativeBal", DifferentPipeline)
jet_es_variations += create_systematic_variations("CMS_scale_j_RelativeSample_Run2016", "jecUncRelativeSampleYear", DifferentPipeline)
# B-tagging
btag_eff_variations = create_systematic_variations("CMS_htt_eff_b_Run2016", "btagEff", DifferentPipeline)
mistag_eff_variations = create_systematic_variations("CMS_htt_mistag_b_Run2016", "btagMistag", DifferentPipeline)
## Variations common for all groups (most of the mc-related systematics)
common_mc_variations = prefiring_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_Run2016", "metRecoilResolution", DifferentPipeline)
recoil_variations += create_systematic_variations("CMS_htt_boson_scale_met_Run2016", "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_Run2016"% (unctype), "tauEsThreeProng", DifferentPipeline)
tau_es_variations[unctype] += create_systematic_variations("CMS_scale%s_t_3prong1pizero_Run2016"% (unctype), "tauEsThreeProngOnePiZero", DifferentPipeline)
tau_es_variations[unctype] += create_systematic_variations("CMS_scale%s_t_1prong_Run2016"% (unctype), "tauEsOneProng", DifferentPipeline)
tau_es_variations[unctype] += create_systematic_variations("CMS_scale%s_t_1prong1pizero_Run2016"% (unctype), "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}_Run2016".format(unctype=unctype,bindown=bindown, binup=binup), "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}_Run2016".format(unctype=unctype, bindown=bindown, binup=binup), "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}_Run2016".format(unctype=unctype, bindown=bindown, binup=binup), "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}_Run2016".format(unctype=unctype, bindown=bindown, binup=binup), "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}_Run2016".format(unctype=unctype, dm=decaymode), "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}_Run2016".format(unctype=unctype, dm=decaymode), "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_Run2016", "zPtReweightWeight", SquareAndRemoveWeight)
# top pt reweighting
top_pt_variations = create_systematic_variations( "CMS_htt_ttbarShape", "topPtReweightWeight", SquareAndRemoveWeight)
# EMB charged track correction uncertainty (DM-dependent)
decayMode_variations = []
decayMode_variations.append(ReplaceWeight("CMS_3ProngEff_Run2016", "decayMode_SF", Weight("embeddedDecayModeWeight_effUp_pi0Nom", "decayMode_SF"), "Up"))
decayMode_variations.append(ReplaceWeight("CMS_3ProngEff_Run2016", "decayMode_SF", Weight("embeddedDecayModeWeight_effDown_pi0Nom", "decayMode_SF"), "Down"))
decayMode_variations.append(ReplaceWeight("CMS_1ProngPi0Eff_Run2016", "decayMode_SF", Weight("embeddedDecayModeWeight_effNom_pi0Up", "decayMode_SF"), "Up"))
decayMode_variations.append(ReplaceWeight("CMS_1ProngPi0Eff_Run2016", "decayMode_SF", Weight("embeddedDecayModeWeight_effNom_pi0Down", "decayMode_SF"), "Down"))
# QCD for em
qcd_variations = []
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_0jet_rate_Run2016", "qcd_weight", Weight("em_qcd_osss_0jet_rateup_Weight", "qcd_weight"), "Up"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_0jet_rate_Run2016", "qcd_weight", Weight("em_qcd_osss_0jet_ratedown_Weight", "qcd_weight"), "Down"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_0jet_shape_Run2016", "qcd_weight", Weight("em_qcd_osss_0jet_shapeup_Weight", "qcd_weight"), "Up"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_0jet_shape_Run2016", "qcd_weight", Weight("em_qcd_osss_0jet_shapedown_Weight", "qcd_weight"), "Down"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_1jet_rate_Run2016", "qcd_weight", Weight("em_qcd_osss_1jet_rateup_Weight", "qcd_weight"), "Up"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_1jet_rate_Run2016", "qcd_weight", Weight("em_qcd_osss_1jet_ratedown_Weight", "qcd_weight"), "Down"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_1jet_shape_Run2016", "qcd_weight", Weight("em_qcd_osss_1jet_shapeup_Weight", "qcd_weight"), "Up"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_1jet_shape_Run2016", "qcd_weight", Weight("em_qcd_osss_1jet_shapedown_Weight", "qcd_weight"), "Down"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_iso_Run2016", "qcd_weight", Weight("em_qcd_extrap_up_Weight", "qcd_weight"), "Up"))
qcd_variations.append(ReplaceWeight("CMS_htt_qcd_iso_Run2016", "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_Run2016"% (ch), "tau%sFakeEsOneProng"%fakelep_dict[ch], DifferentPipeline)
lep_fake_es_variations[ch] += create_systematic_variations("CMS_ZLShape_%s_1prong1pizero_Run2016"% (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 = {"2016": {"mt": 23., "et": 23.},
"2017": {"mt": 25., "et": 28.},
"2018": {"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_Run2016"%(unctype, ch), "trg_%s_eff_weight"%ch, Weight("(1.0*(pt_1<={0})+1.02*(pt_1>{0}))".format(thresh_dict[args.era][ch]), "trg_%s_eff_weight"%ch), "Up"))
lep_trigger_eff_variations[ch][unctype].append(AddWeight("CMS_eff_trigger%s_%s_Run2016"%(unctype, ch), "trg_%s_eff_weight"%ch, Weight("(1.0*(pt_1<={0})+0.98*(pt_1>{0}))".format(thresh_dict[args.era][ch]), "trg_%s_eff_weight"%ch), "Down"))
lep_trigger_eff_variations[ch][unctype].append(AddWeight("CMS_eff_xtrigger%s_%s_Run2016"%(unctype, ch), "xtrg_%s_eff_weight"%ch, Weight("(1.054*(pt_1<={0})+1.0*(pt_1>{0}))".format(thresh_dict[args.era][ch]), "xtrg_%s_eff_weight"%ch), "Up"))
lep_trigger_eff_variations[ch][unctype].append(AddWeight("CMS_eff_xtrigger%s_%s_Run2016"%(unctype, ch), "xtrg_%s_eff_weight"%ch, Weight("(0.946*(pt_1<={0})+1.0*(pt_1>{0}))".format(thresh_dict[args.era][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_Run2016{shift}",
"ff_qcd_dm0_njet0{ch}_stat_Run2016{shift}",
"ff_qcd_dm0_njet1{ch}_stat_Run2016{shift}",
"ff_w_syst_Run2016{shift}",
"ff_w_dm0_njet0{ch}_stat_Run2016{shift}",
"ff_w_dm0_njet1{ch}_stat_Run2016{shift}",
"ff_tt_syst_Run2016{shift}",
"ff_tt_dm0_njet0_stat_Run2016{shift}",
"ff_tt_dm0_njet1_stat_Run2016{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("_Run2016", "")), "fake_factor"), shift_direction))
elif ch == "tt":
for systematic_shift in [
"ff_qcd{ch}_syst_Run2016{shift}",
"ff_qcd_dm0_njet0{ch}_stat_Run2016{shift}",
"ff_qcd_dm0_njet1{ch}_stat_Run2016{shift}",
"ff_w{ch}_syst_Run2016{shift}", "ff_tt{ch}_syst_Run2016{shift}",
"ff_w_frac{ch}_syst_Run2016{shift}",
"ff_tt_frac{ch}_syst_Run2016{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("_Run2016", "")), "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):
# 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)
# Era selection
if "2016" in args.era:
from shape_producer.estimation_methods_2016 import DataEstimation, HTTEstimation, ggHEstimation, ggHEstimation_0J, ggHEstimation_1J, ggHEstimation_GE2J, ggHEstimation_VBFTOPO, qqHEstimation, qqHEstimation_VBFTOPO_JET3VETO, qqHEstimation_VBFTOPO_JET3, qqHEstimation_REST, qqHEstimation_PTJET1_GT200, VHEstimation, ZTTEstimation, ZTTEstimationTT, ZLEstimationMTSM, ZLEstimationETSM, ZLEstimationTT, ZJEstimationMT, ZJEstimationET, ZJEstimationTT, WEstimation, TTTEstimationMT, TTTEstimationET, TTTEstimationTT, TTJEstimationMT, TTJEstimationET, TTJEstimationTT, VVEstimation, EWKZEstimation, QCDEstimationMT, QCDEstimationET, QCDEstimationTT, ZTTEmbeddedEstimation, TTLEstimationMT, TTLEstimationET, TTLEstimationTT, TTTTEstimationMT, TTTTEstimationET
from shape_producer.era import Run2016
era = Run2016(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 = MTSM()
if args.QCD_extrap_fit:
mt.cuts.remove("muon_iso")
mt.cuts.add(Cut("(iso_1<0.5)*(iso_1>=0.15)", "muon_iso_loose"))
if args.embedding:
mt.cuts.remove("trg_singlemuoncross")
mt.cuts.add(Cut("(trg_singlemuon==1 && pt_1>23 && pt_2>30)", "trg_singlemuon"))
mt_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"HTT" : Process("HTT", HTTEstimation (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("ggH125_0J", ggHEstimation_0J (era, directory, mt, friend_directory=mt_friend_directory)),
"ggH_1J" : Process("ggH125_1J", ggHEstimation_1J (era, directory, mt, friend_directory=mt_friend_directory)),
"ggH_GE2J" : Process("ggH125_GE2J", ggHEstimation_GE2J (era, directory, mt, friend_directory=mt_friend_directory)),
"ggH_VBFTOPO" : Process("ggH125_VBFTOPO", ggHEstimation_VBFTOPO (era, directory, mt, friend_directory=mt_friend_directory)),
"qqH" : Process("qqH125", qqHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"qqH_VBFTOPO_JET3VETO" : Process("qqH125_VBFTOPO_JET3VETO", qqHEstimation_VBFTOPO_JET3VETO(era, directory, mt, friend_directory=mt_friend_directory)),
"qqH_VBFTOPO_JET3" : Process("qqH125_VBFTOPO_JET3", qqHEstimation_VBFTOPO_JET3 (era, directory, mt, friend_directory=mt_friend_directory)),
"qqH_REST" : Process("qqH125_REST", qqHEstimation_REST (era, directory, mt, friend_directory=mt_friend_directory)),
"qqH_PTJET1_GT200" : Process("qqH125_PTJET1_GT200", qqHEstimation_PTJET1_GT200 (era, directory, mt, friend_directory=mt_friend_directory)),
"VH" : Process("VH125", VHEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"ZL" : Process("ZL", ZLEstimationMTSM(era, directory, mt, friend_directory=mt_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimationMT (era, directory, mt, friend_directory=mt_friend_directory)),
"W" : Process("W", WEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"TTT" : Process("TTT", TTTEstimationMT (era, directory, mt, friend_directory=mt_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimationMT (era, directory, mt, friend_directory=mt_friend_directory)),
"VV" : Process("VV", VVEstimation (era, directory, mt, friend_directory=mt_friend_directory)),
"EWKZ" : Process("EWKZ", EWKZEstimation (era, directory, mt, friend_directory=mt_friend_directory))
}
if args.embedding:
mt_processes["ZTT"] = Process("ZTT", ZTTEmbeddedEstimation(era, directory, mt, friend_directory=mt_friend_directory))
mt_processes["TTT"] = Process("TTT", TTLEstimationMT (era, directory, mt, friend_directory=mt_friend_directory))
mt_processes["QCD"] = Process("QCD", QCDEstimationMT(era, directory, mt, [mt_processes[process] for process in ["ZTT", "ZJ", "ZL", "W", "TTT", "TTJ", "VV", "EWKZ"]], mt_processes["data"], extrapolation_factor=1.17))
et = ETSM()
if args.QCD_extrap_fit:
et.cuts.remove("ele_iso")
et.cuts.add(Cut("(iso_1<0.5)*(iso_1>=0.1)", "ele_iso_loose"))
et_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, et, friend_directory=et_friend_directory)),
"HTT" : Process("HTT", HTTEstimation (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("ggH125_0J", ggHEstimation_0J (era, directory, et, friend_directory=et_friend_directory)),
"ggH_1J" : Process("ggH125_1J", ggHEstimation_1J (era, directory, et, friend_directory=et_friend_directory)),
"ggH_GE2J" : Process("ggH125_GE2J", ggHEstimation_GE2J (era, directory, et, friend_directory=et_friend_directory)),
"ggH_VBFTOPO" : Process("ggH125_VBFTOPO", ggHEstimation_VBFTOPO (era, directory, et, friend_directory=et_friend_directory)),
"qqH" : Process("qqH125", qqHEstimation (era, directory, et, friend_directory=et_friend_directory)),
"qqH_VBFTOPO_JET3VETO" : Process("qqH125_VBFTOPO_JET3VETO", qqHEstimation_VBFTOPO_JET3VETO(era, directory, et, friend_directory=et_friend_directory)),
"qqH_VBFTOPO_JET3" : Process("qqH125_VBFTOPO_JET3", qqHEstimation_VBFTOPO_JET3 (era, directory, et, friend_directory=et_friend_directory)),
"qqH_REST" : Process("qqH125_REST", qqHEstimation_REST (era, directory, et, friend_directory=et_friend_directory)),
"qqH_PTJET1_GT200" : Process("qqH125_PTJET1_GT200", qqHEstimation_PTJET1_GT200 (era, directory, et, friend_directory=et_friend_directory)),
"VH" : Process("VH125", VHEstimation (era, directory, et, friend_directory=et_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimation (era, directory, et, friend_directory=et_friend_directory)),
"ZL" : Process("ZL", ZLEstimationETSM(era, directory, et, friend_directory=et_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimationET (era, directory, et, friend_directory=et_friend_directory)),
"W" : Process("W", WEstimation (era, directory, et, friend_directory=et_friend_directory)),
"TTT" : Process("TTT", TTTEstimationET (era, directory, et, friend_directory=et_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimationET (era, directory, et, friend_directory=et_friend_directory)),
"VV" : Process("VV", VVEstimation (era, directory, et, friend_directory=et_friend_directory)),
"EWKZ" : Process("EWKZ", EWKZEstimation (era, directory, et, friend_directory=et_friend_directory))
}
if args.embedding:
et_processes["ZTT"] = Process("ZTT", ZTTEmbeddedEstimation(era, directory, et, friend_directory=et_friend_directory))
et_processes["TTT"] = Process("TTT", TTLEstimationET (era, directory, et, friend_directory=et_friend_directory))
et_processes["QCD"] = Process("QCD", QCDEstimationET(era, directory, et, [et_processes[process] for process in ["ZTT", "ZJ", "ZL", "W", "TTT", "TTJ", "VV", "EWKZ"]], et_processes["data"], extrapolation_factor=1.16))
tt = TTSM()
if args.QCD_extrap_fit:
tt.cuts.get("os").invert()
if args.HIG16043:
tt.cuts.remove("pt_h")
tt_processes = {
"data" : Process("data_obs", DataEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"HTT" : Process("HTT", HTTEstimation (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("ggH125_0J", ggHEstimation_0J (era, directory, tt, friend_directory=tt_friend_directory)),
"ggH_1J" : Process("ggH125_1J", ggHEstimation_1J (era, directory, tt, friend_directory=tt_friend_directory)),
"ggH_GE2J" : Process("ggH125_GE2J", ggHEstimation_GE2J (era, directory, tt, friend_directory=tt_friend_directory)),
"ggH_VBFTOPO" : Process("ggH125_VBFTOPO", ggHEstimation_VBFTOPO (era, directory, tt, friend_directory=tt_friend_directory)),
"qqH" : Process("qqH125", qqHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"qqH_VBFTOPO_JET3VETO" : Process("qqH125_VBFTOPO_JET3VETO", qqHEstimation_VBFTOPO_JET3VETO(era, directory, tt, friend_directory=tt_friend_directory)),
"qqH_VBFTOPO_JET3" : Process("qqH125_VBFTOPO_JET3", qqHEstimation_VBFTOPO_JET3 (era, directory, tt, friend_directory=tt_friend_directory)),
"qqH_REST" : Process("qqH125_REST", qqHEstimation_REST (era, directory, tt, friend_directory=tt_friend_directory)),
"qqH_PTJET1_GT200" : Process("qqH125_PTJET1_GT200", qqHEstimation_PTJET1_GT200 (era, directory, tt, friend_directory=tt_friend_directory)),
"VH" : Process("VH125", VHEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"ZTT" : Process("ZTT", ZTTEstimationTT(era, directory, tt, friend_directory=tt_friend_directory)),
"ZL" : Process("ZL", ZLEstimationTT (era, directory, tt, friend_directory=tt_friend_directory)),
"ZJ" : Process("ZJ", ZJEstimationTT (era, directory, tt, friend_directory=tt_friend_directory)),
"W" : Process("W", WEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"TTT" : Process("TTT", TTTEstimationTT(era, directory, tt, friend_directory=tt_friend_directory)),
"TTJ" : Process("TTJ", TTJEstimationTT(era, directory, tt, friend_directory=tt_friend_directory)),
"VV" : Process("VV", VVEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
"EWKZ" : Process("EWKZ", EWKZEstimation (era, directory, tt, friend_directory=tt_friend_directory)),
}
if args.embedding:
tt_processes["ZTT"] = Process("ZTT", ZTTEmbeddedEstimation(era, directory, tt, friend_directory=tt_friend_directory))
tt_processes["TTT"] = Process("TTT", TTLEstimationTT (era, directory, tt, friend_directory=tt_friend_directory))
tt_processes["QCD"] = Process("QCD", QCDEstimationTT(era, directory, tt, [tt_processes[process] for process in ["ZTT", "ZJ", "ZL", "W", "TTT", "TTJ", "VV", "EWKZ"]], tt_processes["data"]))
# Variables and categories
binning = yaml.load(open(args.binning))
et_categories = []
# HIG16043 shapes
if "et" in args.channels and args.HIG16043:
for category in ["0jet", "vbf", "boosted"]:
variable = Variable(
binning["HIG16043"]["et"][category]["variable"],
VariableBinning(binning["HIG16043"]["et"][category]["binning"]),
expression=binning["HIG16043"]["et"][category]["expression"])
et_categories.append(
Category(
category,
et,
Cuts(
Cut(binning["HIG16043"]["et"][category]["cut_unrolling"],
"et_cut_unrolling_{}".format(category)),
Cut(binning["HIG16043"]["et"][category]["cut_category"],
"et_cut_category_{}".format(category))
),
variable=variable))
# Analysis shapes
elif "et" in args.channels:
for i, label in enumerate(["ggh", "qqh", "ztt", "zll", "w", "tt", "ss", "misc"]):
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))
# Goodness of fit shapes
elif "et" == args.gof_channel:
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 = []
# HIG16043 shapes
if "mt" in args.channels and args.HIG16043:
for category in ["0jet", "vbf", "boosted"]:
variable = Variable(
binning["HIG16043"]["mt"][category]["variable"],
VariableBinning(binning["HIG16043"]["mt"][category]["binning"]),
expression=binning["HIG16043"]["mt"][category]["expression"])
mt_categories.append(
Category(
category,
mt,
Cuts(
Cut(binning["HIG16043"]["mt"][category]["cut_unrolling"],
"mt_cut_unrolling_{}".format(category)),
Cut(binning["HIG16043"]["mt"][category]["cut_category"],
"mt_cut_category_{}".format(category))
),
variable=variable))
# Analysis shapes
elif "mt" in args.channels:
for i, label in enumerate(["ggh", "qqh", "ztt", "zll", "w", "tt", "ss", "misc"]):
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))
# 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 = []
# HIG16043 shapes
if "tt" in args.channels and args.HIG16043:
for category in ["0jet", "vbf", "boosted"]:
variable = Variable(
binning["HIG16043"]["tt"][category]["variable"],
VariableBinning(binning["HIG16043"]["tt"][category]["binning"]),
expression=binning["HIG16043"]["tt"][category]["expression"])
tt_categories.append(
Category(
category,
tt,
Cuts(
Cut(binning["HIG16043"]["tt"][category]["cut_unrolling"],
"tt_cut_unrolling_{}".format(category)),
Cut(binning["HIG16043"]["tt"][category]["cut_category"],
"tt_cut_category_{}".format(category))
),
variable=variable))
# Analysis shapes
elif "tt" in args.channels:
for i, label in enumerate(["ggh", "qqh", "ztt", "noniso", "misc"]):
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))
# 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))
# Nominal histograms
# 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"))
# Shapes variations
# Tau energy scale
tau_es_3prong_variations = create_systematic_variations(
"CMS_scale_t_3prong_13TeV", "tauEsThreeProng", DifferentPipeline)
tau_es_1prong_variations = create_systematic_variations(
"CMS_scale_t_1prong_13TeV", "tauEsOneProng", DifferentPipeline)
tau_es_1prong1pizero_variations = create_systematic_variations(
"CMS_scale_t_1prong1pizero_13TeV", "tauEsOneProngPiZeros",
DifferentPipeline)
for variation in tau_es_3prong_variations + tau_es_1prong_variations + tau_es_1prong1pizero_variations:
for process_nick in [
"HTT", "VH", "ggH", "ggH_0J", "ggH_1J", "ggH_GE2J",
"ggH_VBFTOPO", "qqH", "qqH_VBFTOPO_JET3VETO",
"qqH_VBFTOPO_JET3", "qqH_REST", "qqH_PTJET1_GT200", "ZTT",
"TTT", "VV", "EWKZ"
]:
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)
# Jet energy scale
jet_es_variations = create_systematic_variations("CMS_scale_j_13TeV",
"jecUnc",
DifferentPipeline)
for variation in jet_es_variations:
for process_nick in [
"HTT", "VH", "ggH", "ggH_0J", "ggH_1J", "ggH_GE2J",
"ggH_VBFTOPO", "qqH", "qqH_VBFTOPO_JET3VETO",
"qqH_VBFTOPO_JET3", "qqH_REST", "qqH_PTJET1_GT200", "ZTT",
"ZL", "ZJ", "W", "TTT", "TTJ", "VV", "EWKZ"
]:
if args.embedding and process_nick == 'ZTT':
continue
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)
# MET energy scale
met_unclustered_variations = create_systematic_variations(
"CMS_scale_met_unclustered_13TeV", "metUnclusteredEn",
DifferentPipeline)
met_clustered_variations = create_systematic_variations(
"CMS_scale_met_clustered_13TeV", "metJetEn", DifferentPipeline)
for variation in met_unclustered_variations + met_clustered_variations:
for process_nick in [
"HTT", "VH", "ggH", "ggH_0J", "ggH_1J", "ggH_GE2J",
"ggH_VBFTOPO", "qqH", "qqH_VBFTOPO_JET3VETO",
"qqH_VBFTOPO_JET3", "qqH_REST", "qqH_PTJET1_GT200", "ZTT",
"ZL", "ZJ", "W", "TTT", "TTJ", "VV", "EWKZ"
]:
if args.embedding and process_nick == 'ZTT':
continue
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)
# Z pt reweighting
zpt_variations = create_systematic_variations("CMS_htt_dyShape_13TeV",
"zPtReweightWeight",
SquareAndRemoveWeight)
for variation in zpt_variations:
for process_nick in ["ZTT", "ZL", "ZJ"]:
if args.embedding and process_nick == 'ZTT':
continue
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)
# top pt reweighting
top_pt_variations = create_systematic_variations(
"CMS_htt_ttbarShape_13TeV", "topPtReweightWeight",
SquareAndRemoveWeight)
for variation in top_pt_variations:
for process_nick in ["TTT", "TTJ"]:
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)
# jet to tau fake efficiency
jet_to_tau_fake_variations = []
jet_to_tau_fake_variations.append(
AddWeight("CMS_htt_jetToTauFake_13TeV", "jetToTauFake_weight",
Weight("(1.0+pt_2*0.002)", "jetToTauFake_weight"), "Up"))
jet_to_tau_fake_variations.append(
AddWeight("CMS_htt_jetToTauFake_13TeV", "jetToTauFake_weight",
Weight("(1.0-pt_2*0.002)", "jetToTauFake_weight"), "Down"))
for variation in jet_to_tau_fake_variations:
for process_nick in ["ZJ", "TTJ", "W"]:
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)
# Zll reweighting
zll_et_weight_variations = []
zll_et_weight_variations.append(
ReplaceWeight(
"CMS_htt_eFakeTau_1prong_13TeV", "decay_mode_reweight",
Weight(
"(((decayMode_2 == 0)*0.98*1.12) + ((decayMode_2 == 1 || decayMode_2 == 2)*1.2) + ((decayMode_2 == 10)*1.0))",
"decay_mode_reweight"), "Up"))
zll_et_weight_variations.append(
ReplaceWeight(
"CMS_htt_eFakeTau_1prong_13TeV", "decay_mode_reweight",
Weight(
"(((decayMode_2 == 0)*0.98*0.88) + ((decayMode_2 == 1 || decayMode_2 == 2)*1.2) + ((decayMode_2 == 10)*1.0))",
"decay_mode_reweight"), "Down"))
zll_et_weight_variations.append(
ReplaceWeight(
"CMS_htt_eFakeTau_1prong1pizero_13TeV", "decay_mode_reweight",
Weight(
"(((decayMode_2 == 0)*0.98) + ((decayMode_2 == 1 || decayMode_2 == 2)*1.2*1.12) + ((decayMode_2 == 10)*1.0))",
"decay_mode_reweight"), "Up"))
zll_et_weight_variations.append(
ReplaceWeight(
"CMS_htt_eFakeTau_1prong1pizero_13TeV", "decay_mode_reweight",
Weight(
"(((decayMode_2 == 0)*0.98) + ((decayMode_2 == 1 || decayMode_2 == 2)*1.2*0.88) + ((decayMode_2 == 10)*1.0))",
"decay_mode_reweight"), "Down"))
for variation in zll_et_weight_variations:
for process_nick in ["ZL"]:
if "et" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=et_processes[process_nick],
channel=et,
era=era)
zll_mt_weight_variations = []
zll_mt_weight_variations.append(
ReplaceWeight(
"CMS_htt_mFakeTau_1prong_13TeV", "decay_mode_reweight",
Weight(
"(((decayMode_2 == 0)*0.75*1.25) + ((decayMode_2 == 1 || decayMode_2 == 2)*1.0) + ((decayMode_2 == 10)*1.0))",
"decay_mode_reweight"), "Up"))
zll_mt_weight_variations.append(
ReplaceWeight(
"CMS_htt_mFakeTau_1prong_13TeV", "decay_mode_reweight",
Weight(
"(((decayMode_2 == 0)*0.75*0.75) + ((decayMode_2 == 1 || decayMode_2 == 2)*1.0) + ((decayMode_2 == 10)*1.0))",
"decay_mode_reweight"), "Down"))
zll_mt_weight_variations.append(
ReplaceWeight(
"CMS_htt_mFakeTau_1prong1pizero_13TeV", "decay_mode_reweight",
Weight(
"(((decayMode_2 == 0)*0.75) + ((decayMode_2 == 1 || decayMode_2 == 2)*1.25) + ((decayMode_2 == 10)*1.0))",
"decay_mode_reweight"), "Up"))
zll_mt_weight_variations.append(
ReplaceWeight(
"CMS_htt_mFakeTau_1prong1pizero_13TeV", "decay_mode_reweight",
Weight(
"(((decayMode_2 == 0)*0.75) + ((decayMode_2 == 1 || decayMode_2 == 2)*0.75) + ((decayMode_2 == 10)*1.0))",
"decay_mode_reweight"), "Down"))
for variation in zll_mt_weight_variations:
for process_nick in ["ZL"]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
# b tagging
btag_eff_variations = create_systematic_variations("CMS_htt_eff_b_13TeV",
"btagEff",
DifferentPipeline)
mistag_eff_variations = create_systematic_variations(
"CMS_htt_mistag_b_13TeV", "btagMistag", DifferentPipeline)
for variation in btag_eff_variations + mistag_eff_variations:
for process_nick in [
"HTT", "VH", "ggH", "ggH_0J", "ggH_1J", "ggH_GE2J",
"ggH_VBFTOPO", "qqH", "qqH_VBFTOPO_JET3VETO",
"qqH_VBFTOPO_JET3", "qqH_REST", "qqH_PTJET1_GT200", "ZTT",
"ZL", "ZJ", "W", "TTT", "TTJ", "VV", "EWKZ"
]:
if args.embedding and process_nick == 'ZTT':
continue
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)
if args.embedding:
# Embedded event specifics
# 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(
"TTTT",
TTTTEstimationMT(era,
directory,
mt,
friend_directory=mt_friend_directory))
tttautau_process_et = Process(
"TTTT",
TTTTEstimationET(era,
directory,
et,
friend_directory=et_friend_directory))
tttautau_process_tt = Process(
"TTTT",
TTTEstimationTT(era,
directory,
tt,
friend_directory=tt_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["ZTT"], 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", "Down"),
mass="125"))
mt_processes['ZTTpTTTauTauUp'] = Process(
"ZTTpTTTauTauUp",
AddHistogramEstimationMethod(
"AddHistogram", "nominal", era, directory, mt,
[mt_processes["ZTT"], 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", "Up"),
mass="125"))
#Muon ES uncertainty (needed for smearing due to initial reconstruction)
muon_es_variations = create_systematic_variations(
"CMS_scale_muonES", "muonES", DifferentPipeline)
for variation in muon_es_variations:
for process_nick in ["ZTT"]:
if "mt" in [args.gof_channel] + args.channels:
systematics.add_systematic_variation(
variation=variation,
process=mt_processes[process_nick],
channel=mt,
era=era)
if 'et' in [args.gof_channel] + args.channels:
for category in et_categories:
et_processes['ZTTpTTTauTauDown'] = Process(
"ZTTpTTTauTauDown",
AddHistogramEstimationMethod(
"AddHistogram", "nominal", era, directory, et,
[et_processes["ZTT"], tttautau_process_et],
[1.0, -0.1]))
systematics.add(
Systematic(category=category,
process=et_processes['ZTTpTTTauTauDown'],
analysis="smhtt",
era=era,
variation=Relabel("CMS_htt_emb_ttbar", "Down"),
mass="125"))
et_processes['ZTTpTTTauTauUp'] = Process(
"ZTTpTTTauTauUp",
AddHistogramEstimationMethod(
"AddHistogram", "nominal", era, directory, et,
[et_processes["ZTT"], tttautau_process_et],
[1.0, 0.1]))
systematics.add(
Systematic(category=category,
process=et_processes['ZTTpTTTauTauUp'],
analysis="smhtt",
era=era,
variation=Relabel("CMS_htt_emb_ttbar", "Up"),
mass="125"))
if 'tt' in [args.gof_channel] + args.channels:
for category in tt_categories:
tt_processes['ZTTpTTTauTauDown'] = Process(
"ZTTpTTTauTauDown",
AddHistogramEstimationMethod(
"AddHistogram", "nominal", era, directory, tt,
[tt_processes["ZTT"], tttautau_process_tt],
[1.0, -0.1]))
systematics.add(
Systematic(category=category,
process=tt_processes['ZTTpTTTauTauDown'],
analysis="smhtt",
era=era,
variation=Relabel("CMS_htt_emb_ttbar", "Down"),
mass="125"))
tt_processes['ZTTpTTTauTauUp'] = Process(
"ZTTpTTTauTauUp",
AddHistogramEstimationMethod(
"AddHistogram", "nominal", era, directory, tt,
[tt_processes["ZTT"], tttautau_process_tt],
[1.0, 0.1]))
systematics.add(
Systematic(category=category,
process=tt_processes['ZTTpTTTauTauUp'],
analysis="smhtt",
era=era,
variation=Relabel("CMS_htt_emb_ttbar", "Up"),
mass="125"))
# Produce histograms
logger.info("Start producing shapes.")
systematics.produce()
logger.info("Done producing shapes.")
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])
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])