def calculate_expected_limit(self, selection, idx, m_point, temp_results):
yields = {}
for i in range(len(selection)):
bin = "Bin_%d" % i
yields[bin] = {}
for process in self.signal + self.resonant_bkgs:
signalModelConfig = {
"var":
"mass",
"weightVar":
"weight",
"plotpath":
self.scanConfig["plotpath"],
"modelpath":
self.scanConfig["modelpath"],
"filename":
self.input,
"savename":
"CMS-HGG_sigfit_mva_" + process + "_hgg_" + self.channel +
"_" + str(i) + "_" + str(idx),
"tag":
"hggpdfsmrel_" + process + "_hgg_" + self.channel + "_" +
str(i) + "_" + str(idx),
"selection":
self.base_selection() + "&&" +
self.process_selection(process) + " && " + selection[i],
}
model = makeModel(signalModelConfig)
model.getTree(self.scanner.getTree())
sig_yield = model.makeSignalModel(
"wsig_13TeV",
{
"replaceNorm": False,
"norm_in": -1,
"fixParameters": True
},
)
yields[bin][process] = sig_yield
bkgModelConfig = {
"var":
"mass",
"weightVar":
"weight",
"plotpath":
self.scanConfig["plotpath"],
"modelpath":
self.scanConfig["modelpath"],
"filename":
self.input,
"savename":
"CMS-HGG_bkg_" + self.channel + "_" + str(i) + "_" + str(idx),
"tag":
"CMS_hgg_bkgshape_" + self.channel + "_" + str(i) + "_" +
str(idx),
"selection":
self.base_selection() + "&&" + self.process_selection("bkg") +
" && " + selection[i],
}
model = makeModel(bkgModelConfig)
model.getTree(self.scanner.getTree())
bkg_yield, bkg_yield_raw = model.makeBackgroundModel(
"wbkg_13TeV", self.channel + "_" + str(i) + "_" + str(idx))
yields[bin]["bkg"] = bkg_yield
datacard = makeCards(
self.scanConfig["modelpath"],
"CMS-HGG_mva_13TeV_datacard_" + str(idx) + ".txt",
{"sm_higgs_unc": self.sm_higgs_unc},
)
tagList = [self.channel + "_" + str(x) for x in range(len(selection))]
sigList = [self.signal[0] + "_hgg"]
bkgList = ["bkg_mass"]
for bkg in self.resonant_bkgs:
bkgList.append(bkg + "_hgg")
datacard.WriteCard(sigList, bkgList, tagList, "_" + str(idx))
combineConfig = {
"combineOption": self.combineOption,
"combineOutName": "sig_" + str(idx),
"cardName": "CMS-HGG_mva_13TeV_datacard_" + str(idx) + ".txt",
"outtxtName": "sig_" + str(idx) + ".txt",
}
exp_lim, exp_lim_up1sigma, exp_lim_down1sigma, exp_lim_up2sigma, exp_lim_down2sigma = self.scanner.runCombine(
combineConfig)
result = {
"idx":
idx,
"x": [float(x) for x in m_point],
"exp_lim": [
exp_lim, exp_lim_up1sigma, exp_lim_down1sigma,
exp_lim_up2sigma, exp_lim_down2sigma
],
"selection":
selection,
"yields":
yields
}
temp_results[",".join(selection) + str(idx)] = result
if self.verbose:
print("[GUIDED OPTIMIZER]", result)
return
def calculate_expected_limit(self, selection, idx, m_point, temp_results):
yields = {}
disqualify_srs = False # disqualify certain binning combinations if they don't have enough non-res bkg events in mgg sidebands (require 10 expected)
for i in range(len(selection)):
bin = "Bin_%d" % i
yields[bin] = {}
for process in self.signal + self.resonant_bkgs:
signalModelConfig = {
"var":
"mass",
"weightVar":
"weight_central",
"plotpath":
self.scanConfig["plotpath"],
"modelpath":
self.scanConfig["modelpath"],
"filename":
self.input,
"savename":
"CMS-HGG_sigfit_mva_" + process + "_hgg_" + self.channel +
"_" + str(i) + "_" + str(idx),
"tag":
"hggpdfsmrel_" + process + "_hgg_" + self.channel + "_" +
str(i) + "_" + str(idx),
"selection":
self.base_selection() + "&&" +
self.process_selection(process) + " && " + selection[i],
}
if "nottH" in self.resonant_bkgs[0]:
simple = True # just fit a single gaussian
else:
simple = False
model = makeModel(signalModelConfig)
model.getTree(self.scanner.getTree())
sig_yield = model.makeSignalModel(
"wsig_13TeV",
{
"replaceNorm": False,
"norm_in": -1,
"fixParameters": True,
"simple": simple
},
)
yields[bin][process] = sig_yield
bkgModelConfig = {
"var":
"mass",
"weightVar":
"weight_central",
"plotpath":
self.scanConfig["plotpath"],
"modelpath":
self.scanConfig["modelpath"],
"filename":
self.input,
"savename":
"CMS-HGG_bkg_" + self.channel + "_" + str(i) + "_" + str(idx),
"tag":
"CMS_hgg_bkgshape_" + self.channel + "_" + str(i) + "_" +
str(idx),
"selection":
self.base_selection() + "&&" +
self.process_selection(self.nrb_choice) + " && " +
selection[i],
}
model = makeModel(bkgModelConfig)
model.getTree(self.scanner.getTree())
bkg_yield, bkg_yield_full, bkg_yield_raw = model.makeBackgroundModel(
"wbkg_13TeV", self.channel + "_" + str(i) + "_" + str(idx))
bkgModelConfig["selection"] = self.base_selection(
) + "&&" + self.process_selection("data") + " && " + selection[i]
bkgModelConfig["savename"] = "dummy"
model2 = makeModel(bkgModelConfig)
model2.getTree(self.scanner.getTree())
bkg_yield_data, bkg_yield_data_full, bkg_yield_raw_data = model2.makeBackgroundModel(
"wdata_13TeV",
self.channel + "_" + str(i) + "_" + str(idx) + "dummy")
#print("[GUIDED OPTIMIZER] Bkg events from fit: %
yields[bin]["bkg"] = bkg_yield
# if bkg_yield_raw < 8. or bkg_yield_raw_data < 8.:
# print("[GUIDED OPTIMIZER] Only %.6f expected background events in one bin, disqualifying signal region set." % bkg_yield_raw)
# disqualify_srs = True
datacard = makeCards(
self.scanConfig["modelpath"],
"CMS-HGG_mva_13TeV_datacard_" + str(idx) + ".txt",
{"sm_higgs_unc": self.sm_higgs_unc},
)
tagList = [self.channel + "_" + str(x) for x in range(len(selection))]
sigList = [self.signal[0] + "_hgg"]
bkgList = ["bkg_mass"]
for bkg in self.resonant_bkgs:
bkgList.append(bkg + "_hgg")
datacard.WriteCard(sigList, bkgList, tagList, "_" + str(idx))
for tag in tagList:
datacard = makeCards(
self.scanConfig["modelpath"],
"CMS-HGG_mva_13TeV_datacard_" + str(idx) + "_" + tag + ".txt",
{"sm_higgs_unc": self.sm_higgs_unc},
)
datacard.WriteCard(sigList, bkgList, [tag], "_" + str(idx))
combineConfig = {
"combineOption": self.combineOption,
"combineOutName": "sig_" + str(idx),
"cardName": "CMS-HGG_mva_13TeV_datacard_" + str(idx) + ".txt",
"outtxtName": "sig_" + str(idx) + ".txt",
}
exp_lim, exp_lim_up1sigma, exp_lim_down1sigma, exp_lim_up2sigma, exp_lim_down2sigma = self.scanner.runCombine(
combineConfig)
if "Significance" in self.combineOption:
exp_lim = 1. / exp_lim # make negative so that we can still minimize the POI
# if disqualify_srs:
# exp_lim *= 3 # double the expected limit if the SR combination is disqualified bc too few non-res bkg events
# # the reason we double the exp_lim, is that we still want the expected limit to be a relatively smooth function of the cut values. this way, the optimization bdt can hopefully learn that cut values resulting in very narrow bins have a penalty applied on them
exp_lim_full = {}
exp_lim_full["combined"] = [
exp_lim, exp_lim_up1sigma, exp_lim_down1sigma, exp_lim_up2sigma,
exp_lim_down2sigma
]
for tag in tagList:
combineConfig["combineOutName"] = "sig_" + str(idx) + "_" + tag
combineConfig["cardName"] = "CMS-HGG_mva_13TeV_datacard_" + str(
idx) + "_" + tag + ".txt"
combineConfig["outtxtName"] = "sig_" + str(
idx) + "_" + tag + ".txt"
lim, lim_up1, lim_down1, lim_up2, lim_down2 = self.scanner.runCombine(
combineConfig)
exp_lim_full[tag] = [lim, lim_up1, lim_down1, lim_up2, lim_down2]
result = {
"idx":
idx,
"x": [float(x) for x in m_point],
"exp_lim": [
exp_lim, exp_lim_up1sigma, exp_lim_down1sigma,
exp_lim_up2sigma, exp_lim_down2sigma
],
"exp_lim_full":
exp_lim_full,
"selection":
selection,
"yields":
yields,
"disqualified":
str(disqualify_srs)
}
temp_results[",".join(selection) + str(idx)] = result
if self.verbose:
print("[GUIDED OPTIMIZER]", result)
return
def calculate_bins_significance(idx, scanConfig, scanner, cuts, results):
tree = scanner.getTree()
nBins = len(cuts)
print "[BINNING_SCRIPT_INFO] Testing cut combo %d" % idx
for i in range(nBins):
# MVA score cut
cut = "mva_score > " + str(cuts[i])
if not (i == (nBins - 1)):
cut += " && mva_score < " + str(cuts[i + 1])
#cut_string = ""
#for mva_name, cut in zip(mvas, cuts):
# cut_string += " ( %s > " + str(cut[i])
# if not (i == (nBins - 1)):
# cut_string += " && %s < " + str(cut[i+1])
# cut_string += " ) &&"
# Make signal model
signals = args.signal.split(",") + args.resonant_bkgs.split(",")
for signal in signals:
sigModelConfig = {
"var": "mass",
"weightVar": "weight",
"plotpath": scanConfig["plotpath"],
"modelpath": scanConfig["modelpath"],
"filename": scanConfig["filename"]
}
sigModelConfig[
"savename"] = "CMS-HGG_sigfit_mva_" + signal + "_hgg_" + scanConfig[
"tag"] + "_" + str(i) + "_" + str(idx)
sigModelConfig[
"tag"] = "hggpdfsmrel_" + signal + "_hgg_" + scanConfig[
"tag"] + "_" + str(i) + "_" + str(idx)
processSelection = "("
for j in range(len(process_dict[signal])):
processSelection += "process_id == " + str(
process_dict[signal][j])
if j == (len(process_dict[signal]) - 1):
processSelection += ")"
else:
processSelection += " || "
sigModelConfig["selection"] = scanConfig[
"selection"] + " && " + cut + " && " + processSelection
if "FCNC" not in args.signal.split(
","
)[0]: # this is the ttH analysis, we use M127 for optimization
signal_sample_selection = " && signal_mass_category == 127"
else: # this is FCNC, use M125 since we don't have other mass points for FCNC
signal_sample_selection = " && ((process_id >= 22 && process_id <= 25) || (signal_mass_label == 0 && signal_mass_category == 125))" # accept all FCNC events, only M125 Madgraph (not Powheg) for all other SM Higgs # FIXME
sigModelConfig["selection"] += signal_sample_selection
print "\n[BINNING_SCRIPT_INFO] Making signal model with selection %s" % sigModelConfig[
"selection"]
print "\n[BINNING_SCRIPT_INFO] Saving as %s" % "CMS-HGG_sigfit_mva_" + signal + "_hgg_" + scanConfig[
"tag"] + "_" + str(i) + "_" + str(idx)
print "\n\n"
model = makeModel(sigModelConfig)
model.getTree(tree)
model.makeSignalModel("wsig_13TeV", {
"replaceNorm": False,
"norm_in": -1,
"fixParameters": True
})
# Make background model
bkgModelConfig = {
"var": "mass",
"weightVar": "weight",
"plotpath": scanConfig["plotpath"],
"modelpath": scanConfig["modelpath"],
"filename": scanConfig["filename"]
}
bkgModelConfig["selection"] = scanConfig[
"selection"] + " && " + cut + " && (process_id == 1 || process_id == 2 || process_id == 3 || process_id == 5 || process_id == 6 || process_id == 7 || process_id == 9 || process_id == 13 || process_id == 18 || process_id == 19 || process_id == 20 || process_id == 21 || process_id == 26)"
bkgModelConfig["savename"] = "CMS-HGG_bkg_" + scanConfig[
"tag"] + "_" + str(i) + "_" + str(idx)
bkgModelConfig["tag"] = "CMS_hgg_bkgshape_" + scanConfig[
"tag"] + "_" + str(i) + "_" + str(idx)
print "[BINNING_SCRIPT_INFO] Making background model with selection %s" % bkgModelConfig[
"selection"]
model = makeModel(bkgModelConfig)
model.getTree(tree)
model.makeBackgroundModel(
"wbkg_13TeV", scanConfig["tag"] + "_" + str(i) + "_" + str(idx))
# Make datacard
print "[BINNING_SCRIPT_INFO] Making datacard for cut combo %d" % idx
sigList = [args.signal + "_hgg"]
bkgList = ["bkg_mass"]
for bkg in args.resonant_bkgs.split(","):
bkgList.append(bkg + "_hgg")
card = makeCards(scanConfig["modelpath"],
"CMS-HGG_mva_13TeV_datacard_" + str(idx) + ".txt")
tagList = [(scanConfig["tag"] + "_%d" % x) for x in range(nBins)]
print "tagList is", tagList, "\n\n\n\n"
card.WriteCard(sigList, bkgList, tagList, "_" + str(idx))
if args.limit:
combineOption = "AsymptoticLimits -m 125 "
else:
combineOption = "Significance --significance "
combineConfig = {
"combineOption": combineOption,
"combineOutName": "sig_" + str(idx),
"cardName": "CMS-HGG_mva_13TeV_datacard_" + str(idx) + ".txt",
"outtxtName": "sig_" + str(idx) + ".txt",
"grepContent": "\"Significance\""
}
significance = float(scanner.runCombine(combineConfig))
print "[BINNING_SCRIPT_INFO] %s for cut combo %d is %.6f" % (
"Significance" if not args.limit else "Limit", idx, significance)
for cut in cuts:
cut = float(cut)
result = {
"mva_cuts": [str(cut) for cut in cuts],
("limit" if args.limit else "significance"): significance,
"datacard": scanConfig["modelpath"] + combineConfig["cardName"]
}
results[idx] = result
print results
return