def limits(analysis, model, mass, fit_function, noSyst=False, freezeNuisances=None):
print "\nCalculating limits for {}, {}, {}, {}".format(analysis, model, mass, fit_function)
prefix = 'limits'
postfix = ""
if noSyst:
postfix += "_noSyst"
if freezeNuisances:
postfix += "_" + args.freezeNuisances.replace(",", "_")
datacard = limit_config.get_datacard_filename(analysis, model, mass, fit_function, fitSignal=True)
log_base = limit_config.get_combine_log_path_grid(analysis, model, mass, fit_function, "HybridNewGrid", systematics=(not noSyst), frozen_nps=freezeNuisances)
command_base = "combine {} -M HybridNew -v5 --frequentist --grid={}".format(datacard, limit_config.get_hn_grid(analysis, model, mass, fit_function))
# Observed
#log_observed = log_base.replace(".log", "_obs.log")
print "Observed:"
log_observed = limit_config.get_combine_log_path_grid(analysis, model, mass, fit_function, "obs", method="HybridNewGrid", systematics=(not noSyst), frozen_nps=freezeNuisances)
command_observed = command_base + " 2>&1 | tee {}".format(log_observed)
print command_observed
os.system(command_observed)
# Expected
expected_r = {-2:0.025, -1:0.16, 0:0.5, 1:0.84, 2:0.975}
for exp in [-2, -1, 0, 1, 2]:
print "Expected, " + str(exp)
#log_expected = log_base.replace(".log", "_exp{}.log".format(exp))
log_expected = limit_config.get_combine_log_path_grid(analysis, model, mass, fit_function, "exp" + str(exp), method="HybridNewGrid", systematics=(not noSyst), frozen_nps=freezeNuisances)
print "[debug] Writing log file to " + log_expected
command_expected = command_base + " --expectedFromGrid {} 2>&1 | tee {}".format(expected_r[exp], log_expected)
print command_expected
os.system(command_expected)
combine_options = "-M GoodnessOfFit -v3 --algo {} -s {} --name {} --mass {} ".format(
args.algo,
args.seed,
job_name,
mass
)
if args.cplots:
combine_options += " --plots "
if args.no_signal:
combine_options += " --fixedSignalStrength 0"
elif args.signal != None:
combine_options += " --fixedSignalStrength {} ".format(args.signal)
cmd = "combine {} {} 2>&1 | tee {}".format(
combine_options,
os.path.basename(limit_config.get_datacard_filename(analysis, model, mass, args.fit_function, correctTrigger=args.correctTrigger, qcd=args.qcd, fitTrigger=args.fitTrigger)),
log_name)
if args.toys:
combine_toy_options = "-M GoodnessOfFit -v3 --algo {} -s {} --name {} --mass {} ".format(
args.algo,
args.seed,
job_name + "_toys",
mass
)
if args.no_signal:
combine_toy_options += " --fixedSignalStrength 0"
elif args.signal != None:
combine_toy_options += " --fixedSignalStrength {} ".format(args.signal)
toy_cmd = "combine {} {} -t {} 2>&1 | tee {}".format(
masses[analysis] = [int(x) for x in args.masses.split(",")]
else:
for analysis in analyses:
if "bbl" in analysis:
masses[analysis] = xrange(350, 650, 50)
elif "bbh" in analysis:
masses[analysis] = xrange(600, 1250, 50)
if args.fit:
cwd = os.getcwd()
os.chdir("/uscms/home/dryu/Dijets/data/EightTeeEeVeeBee/Fits/AsimovFits")
for analysis in analyses:
#for model in models:
# for mass in masses[analysis]:
# for fit_function in fit_functions:
# for expected_signal in expected_signals:
# datacard = limit_config.get_datacard_filename(analysis, model, mass, fit_function, #fitSignal=True, correctTrigger=True)
# name = os.path.basename(datacard).replace("datacard", "").replace(".txt", "") + "_" + #str(expected_signal)
# command = "combine {} -M MaxLikelihoodFit -t -1 --expectSignal {} --name {}".format(#datacard, expected_signal, name)
# log = "/uscms/home/dryu/Dijets/data/EightTeeEeVeeBee/Fits/Logs/asimovcheck" + name + "#.log"
# os.system(command + " >& " + log)
Parallel(n_jobs=4)(delayed(RunAsimovCheck)(limit_config.get_datacard_filename(analysis, model, mass, fit_function, correctTrigger=True), expected_signal, condor=args.condor, workspace=limit_config.get_workspace_filename(analysis, model, mass, correctTrigger=True)) for mass in masses[analysis] for model in models for fit_function in fit_functions for expected_signal in expected_signals)
os.chdir(cwd)
if args.table:
for analysis in analyses:
Parallel(n_jobs=4)(delayed(AsimovFitTables)(model, analysis, fit_functions, expected_signal, masses[analysis]) for model in models for expected_signal in expected_signals)
if args.plot:
for analysis in analyses:
Parallel(n_jobs=4)(delayed(AsimovFitPlots)(model, analysis, fit_functions, expected_signal, masses[analysis]) for model in models for expected_signal in expected_signals)
def limits(analysis,
model,
mass,
fit_function,
noSyst=False,
freezeNuisances=None):
print "\nCalculating limits for {}, {}, {}, {}".format(
analysis, model, mass, fit_function)
prefix = 'limits'
postfix = ""
if noSyst:
postfix += "_noSyst"
if freezeNuisances:
postfix += "_" + args.freezeNuisances.replace(",", "_")
datacard = limit_config.get_datacard_filename(analysis,
model,
mass,
fit_function,
fitSignal=True)
log_base = limit_config.get_combine_log_path_grid(
analysis,
model,
mass,
fit_function,
"HybridNewGrid",
systematics=(not noSyst),
frozen_nps=freezeNuisances)
command_base = "combine {} -M HybridNew -v5 --frequentist --grid={}".format(
datacard, limit_config.get_hn_grid(analysis, model, mass,
fit_function))
# Observed
#log_observed = log_base.replace(".log", "_obs.log")
print "Observed:"
log_observed = limit_config.get_combine_log_path_grid(
analysis,
model,
mass,
fit_function,
"obs",
method="HybridNewGrid",
systematics=(not noSyst),
frozen_nps=freezeNuisances)
command_observed = command_base + " 2>&1 | tee {}".format(log_observed)
print command_observed
os.system(command_observed)
# Expected
expected_r = {-2: 0.025, -1: 0.16, 0: 0.5, 1: 0.84, 2: 0.975}
for exp in [-2, -1, 0, 1, 2]:
print "Expected, " + str(exp)
#log_expected = log_base.replace(".log", "_exp{}.log".format(exp))
log_expected = limit_config.get_combine_log_path_grid(
analysis,
model,
mass,
fit_function,
"exp" + str(exp),
method="HybridNewGrid",
systematics=(not noSyst),
frozen_nps=freezeNuisances)
print "[debug] Writing log file to " + log_expected
command_expected = command_base + " --expectedFromGrid {} 2>&1 | tee {}".format(
expected_r[exp], log_expected)
print command_expected
os.system(command_expected)
for analysis in analyses:
job_mu_values[model][analysis] = {}
for gen_mass in gen_masses:
if args.mu == 0:
job_mu_values[model][analysis][gen_mass] = 0.
else:
workspace_file = TFile(limit_config.get_workspace_filename(analysis, model, gen_mass, correctTrigger=False, useMCTrigger=True, qcd=False, fitTrigger=True, fitBonly=False), "READ")
#workspace_file = TFile(datacard_folders[model][analysis] + "/workspace_qq_m" + str(gen_mass) + ".root", "READ")
workspace = workspace_file.Get("w")
signal_norm = workspace.var("signal_norm").getVal()
job_mu_values[model][analysis][gen_mass] = 19700. * limit_config.limit_p2sigma_estimates[analysis][model][gen_mass] / signal_norm
if args.run:
for model in models:
for analysis in analyses:
for gen_mass in gen_masses:
names = []
fit_datacards = {}
fit_workspaces = {}
gen_name = model + "_" + analysis + "/m" + str(gen_mass) + "_mu" + str(args.mu)
gen_datacard = limit_config.get_datacard_filename(analysis, model, gen_mass, "dijet4", correctTrigger=False, useMCTrigger=True, qcd=False, fitTrigger=True, fitBonly=False)
gen_workspace = limit_config.get_workspace_filename(analysis, model, gen_mass, correctTrigger=False, useMCTrigger=True, qcd=False, fitTrigger=True, fitBonly=False)
top_name = model + "_" + analysis + "/genmass_" + str(gen_mass) + "_mu" + str(args.mu)
job_names = []
for fit_mass in fit_masses:
fit_name = model + "_" + analysis + "/m" + str(fit_mass) + "_mu" + str(args.mu)
name = model + "_" + analysis + "_genmass" + str(gen_mass) + "_fitmass_" + str(fit_mass) + "_mu" + str(args.mu)
job_names.append(name)
fit_datacards[name] = limit_config.get_datacard_filename(analysis, model, fit_mass, "dijet4", correctTrigger=False, useMCTrigger=True, qcd=False, fitTrigger=True, fitBonly=False)
fit_workspaces[name] = limit_config.get_workspace_filename(analysis, model, fit_mass, correctTrigger=False, useMCTrigger=True, qcd=False, fitTrigger=True, fitBonly=False)
run_many_granularity_studies(top_name, job_names, gen_datacard=gen_datacard, fit_datacards=fit_datacards, gen_workspace=gen_workspace, fit_workspaces=fit_workspaces, n_toys=args.n_toys, mu=job_mu_values[model][analysis][gen_mass])
def main():
# usage description
usage = "Example: ./scripts/createDatacards.py --inputData inputs/rawhistV7_Run2015D_scoutingPFHT_UNBLINDED_649_838_JEC_HLTplusV7_Mjj_cor_smooth.root --dataHistname mjj_mjjcor_gev --inputSig inputs/ResonanceShapes_gg_13TeV_Scouting_Spring15.root -f gg -o datacards -l 1866 --lumiUnc 0.027 --massrange 1000 1500 50 --runFit --p1 5 --p2 7 --p3 0.4 --massMin 838 --massMax 2037 --fitStrategy 2"
# input parameters
parser = ArgumentParser(description='Script that creates combine datacards and corresponding RooFit workspaces',epilog=usage)
parser.add_argument("analysis", type=str, help="Analysis name")
parser.add_argument("model", type=str, help="Model (Hbb, RSG)")
#parser.add_argument("--inputData", dest="inputData", required=True,
# help="Input data spectrum",
# metavar="INPUT_DATA")
parser.add_argument("--dataHistname", dest="dataHistname", type=str, default="h_data",
help="Data histogram name",
metavar="DATA_HISTNAME")
#parser.add_argument("--inputSig", dest="inputSig", required=True,
# help="Input signal shapes",
# metavar="INPUT_SIGNAL")
parser.add_argument("-f", "--final_state", dest="final_state", default="qq",
help="Final state (e.g. qq, qg, gg)",
metavar="FINAL_STATE")
parser.add_argument("--fit_functions", dest="fit_functions", default="f1,f2,f3,f4,f5", help="List of fit functions")
#parser.add_argument("-f2", "--type", dest="atype", required=True, help="Type (e.g. hG, lG, hR, lR)")
parser.add_argument("-o", "--output_path", dest="output_path",
help="Output path where datacards and workspaces will be stored. If not specified, this is derived from limit_configuration.",
metavar="OUTPUT_PATH")
parser.add_argument("--correctTrigger", dest="correctTrigger",
action='store_true',
help="Include trigger correction in PDF")
parser.add_argument("-l", "--lumi", dest="lumi",
default=19700., type=float,
help="Integrated luminosity in pb-1 (default: %(default).1f)",
metavar="LUMI")
parser.add_argument("--massMin", dest="massMin",
default=500, type=int,
help="Lower bound of the mass range used for fitting (default: %(default)s)",
metavar="MASS_MIN")
parser.add_argument("--massMax", dest="massMax",
default=1200, type=int,
help="Upper bound of the mass range used for fitting (default: %(default)s)",
metavar="MASS_MAX")
parser.add_argument("--fitSignal", action="store_true", help="Use signal fitted shapes (CB+Voigtian) instead of histogram templates")
#parser.add_argument("--lumiUnc", dest="lumiUnc",
# required=True, type=float,
# help="Relative uncertainty in the integrated luminosity",
# metavar="LUMI_UNC")
#parser.add_argument("--jesUnc", dest="jesUnc",
# type=float,
# help="Relative uncertainty in the jet energy scale",
# metavar="JES_UNC")
#parser.add_argument("--jerUnc", dest="jerUnc",
# type=float,
# help="Relative uncertainty in the jet energy resolution",
# metavar="JER_UNC")
parser.add_argument("--sqrtS", dest="sqrtS",
default=8000., type=float,
help="Collision center-of-mass energy (default: %(default).1f)",
metavar="SQRTS")
parser.add_argument("--fixP3", dest="fixP3", default=False, action="store_true", help="Fix the fit function p3 parameter")
parser.add_argument("--runFit", dest="runFit", default=False, action="store_true", help="Run the fit")
parser.add_argument("--fitBonly", dest="fitBonly", default=False, action="store_true", help="Run B-only fit")
parser.add_argument("--fixBkg", dest="fixBkg", default=False, action="store_true", help="Fix all background parameters")
parser.add_argument("--decoBkg", dest="decoBkg", default=False, action="store_true", help="Decorrelate background parameters")
parser.add_argument("--fitStrategy", dest="fitStrategy", type=int, default=1, help="Fit strategy (default: %(default).1f)")
parser.add_argument("--debug", dest="debug", default=False, action="store_true", help="Debug printout")
parser.add_argument("--postfix", dest="postfix", default='', help="Postfix for the output file names (default: %(default)s)")
parser.add_argument("--pyes", dest="pyes", default=False, action="store_true", help="Make files for plots")
parser.add_argument("--jyes", dest="jyes", default=False, action="store_true", help="Make files for JES/JER plots")
parser.add_argument("--pdir", dest="pdir", default='testarea', help="Name a directory for the plots (default: %(default)s)")
parser.add_argument("--chi2", dest="chi2", default=False, action="store_true", help="Compute chi squared")
parser.add_argument("--widefit", dest="widefit", default=False, action="store_true", help="Fit with wide bin hist")
mass_group = parser.add_mutually_exclusive_group(required=True)
mass_group.add_argument("--mass",
type=int,
nargs = '*',
default = 1000,
help="Mass can be specified as a single value or a whitespace separated list (default: %(default)i)"
)
mass_group.add_argument("--massrange",
type=int,
nargs = 3,
help="Define a range of masses to be produced. Format: min max step",
metavar = ('MIN', 'MAX', 'STEP')
)
mass_group.add_argument("--masslist",
help = "List containing mass information"
)
args = parser.parse_args()
fit_functions = args.fit_functions.split(",")
# mass points for which resonance shapes will be produced
masses = []
if args.fitBonly:
masses.append(750)
else:
if args.massrange != None:
MIN, MAX, STEP = args.massrange
masses = range(MIN, MAX+STEP, STEP)
elif args.masslist != None:
# A mass list was provided
print "Will create mass list according to", args.masslist
masslist = __import__(args.masslist.replace(".py",""))
masses = masslist.masses
else:
masses = args.mass
# sort masses
masses.sort()
# import ROOT stuff
from ROOT import gStyle, TFile, TH1F, TH1D, TGraph, kTRUE, kFALSE, TCanvas, TLegend, TPad, TLine
from ROOT import RooHist, RooRealVar, RooDataHist, RooArgList, RooArgSet, RooAddPdf, RooProdPdf, RooEffProd, RooFit, RooGenericPdf, RooWorkspace, RooMsgService, RooHistPdf, RooExtendPdf
if not args.debug:
RooMsgService.instance().setSilentMode(kTRUE)
RooMsgService.instance().setStreamStatus(0,kFALSE)
RooMsgService.instance().setStreamStatus(1,kFALSE)
# input data file
#inputData = TFile(limit_config.get_data_input(args.analysis))
# input data histogram
#hData = inputData.Get(args.dataHistname)
#hData.SetDirectory(0)
data_file = TFile(analysis_config.get_b_histogram_filename(args.analysis, "BJetPlusX_2012"))
hData = data_file.Get("BHistograms/h_pfjet_mjj")
hData.SetDirectory(0)
# input sig file
if not args.fitSignal:
print "[create_datacards] INFO : Opening resonance shapes file at " + limit_config.get_resonance_shapes(args.analysis, args.model)
inputSig = TFile(limit_config.get_resonance_shapes(args.analysis, args.model), "READ")
sqrtS = args.sqrtS
# mass variable
mjj = RooRealVar('mjj','mjj',float(args.massMin),float(args.massMax))
# integrated luminosity and signal cross section
lumi = args.lumi
signalCrossSection = 1. # set to 1. so that the limit on r can be interpreted as a limit on the signal cross section
if args.correctTrigger:
trigger_efficiency_pdf = trigger_efficiency.get_pdf(args.analysis, mjj)
trigger_efficiency_formula = trigger_efficiency.get_formula(args.analysis, mjj)
else:
trigger_efficiency_pdf = trigger_efficiency.get_trivial_pdf(mjj)
trigger_efficiency_formula = trigger_efficiency.get_trivial_formula(mjj)
for mass in masses:
print ">> Creating datacard and workspace for %s resonance with m = %i GeV..."%(args.final_state, int(mass))
rooDataHist = RooDataHist('rooDatahist','rooDathist',RooArgList(mjj),hData)
if not args.fitSignal:
hSig = inputSig.Get( "h_" + args.final_state + "_" + str(int(mass)) )
if not hSig:
raise Exception("Couldn't find histogram " + "h_" + args.final_state + "_" + str(int(mass)) + " in file " + limit_config.get_resonance_shapes(args.analysis, args.model))
# normalize signal shape to the expected event yield (works even if input shapes are not normalized to unity)
hSig.Scale(signalCrossSection*lumi/hSig.Integral()) # divide by a number that provides roughly an r value of 1-10
rooSigHist = RooDataHist('rooSigHist','rooSigHist',RooArgList(mjj),hSig)
print 'Signal acceptance:', (rooSigHist.sumEntries()/hSig.Integral())
# If using fitted signal shapes, load the signal PDF
if args.fitSignal:
print "[create_datacards] Loading fitted signal PDFs from " + analysis_config.get_signal_fit_file(args.analysis, args.model, mass, "bukin", interpolated=(not mass in analysis_config.simulation.simulated_masses))
f_signal_pdfs = TFile(analysis_config.get_signal_fit_file(args.analysis, args.model, mass, "bukin", interpolated=(not mass in analysis_config.simulation.simulated_masses)), "READ")
w_signal = f_signal_pdfs.Get("w_signal")
input_parameters = signal_fits.get_parameters(w_signal.pdf("signal"))
# Make a new PDF with nuisance parameters
signal_pdf_notrig, signal_vars = signal_fits.make_signal_pdf_systematic("bukin", mjj, mass=mass)
signal_pdf_name = signal_pdf_notrig.GetName()
signal_pdf_notrig.SetName(signal_pdf_name + "_notrig")
#signal_pdf = RooProdPdf(signal_pdf_name, signal_pdf_name, signal_pdf_notrig, trigger_efficiency_pdf)
signal_pdf = RooEffProd(signal_pdf_name, signal_pdf_name, signal_pdf_notrig, trigger_efficiency_formula)
# Copy input parameter values
signal_vars["xp_0"].setVal(input_parameters["xp"][0])
signal_vars["xp_0"].setError(input_parameters["xp"][1])
signal_vars["xp_0"].setConstant()
signal_vars["sigp_0"].setVal(input_parameters["sigp"][0])
signal_vars["sigp_0"].setError(input_parameters["sigp"][1])
signal_vars["sigp_0"].setConstant()
signal_vars["xi_0"].setVal(input_parameters["xi"][0])
signal_vars["xi_0"].setError(input_parameters["xi"][1])
signal_vars["xi_0"].setConstant()
signal_vars["rho1_0"].setVal(input_parameters["rho1"][0])
signal_vars["rho1_0"].setError(input_parameters["rho1"][1])
signal_vars["rho1_0"].setConstant()
signal_vars["rho2_0"].setVal(input_parameters["rho2"][0])
signal_vars["rho2_0"].setError(input_parameters["rho2"][1])
signal_vars["rho2_0"].setConstant()
f_signal_pdfs.Close()
signal_parameters = {}
signal_pdfs_notrig = {}
signal_pdfs = {}
signal_norms = {}
background_pdfs = {}
background_pdfs_notrig = {}
background_parameters = {}
background_norms = {}
signal_epdfs = {}
background_epdfs = {}
models = {}
fit_results = {}
for fit_function in fit_functions:
print "[create_datacards] INFO : On fit function {}".format(fit_function)
if args.fitSignal:
# Make a copy of the signal PDF, so that each fitTo call uses its own copy.
# The copy should have all variables set constant.
#signal_pdfs[fit_function], signal_parameters[fit_function] = signal_fits.copy_signal_pdf("bukin", signal_pdf, mjj, tag=fit_function, include_systematics=True)
signal_pdfs_notrig[fit_function] = ROOT.RooBukinPdf(signal_pdf_notrig, signal_pdf_notrig.GetName() + "_" + fit_function)
signal_pdfs[fit_function] = RooEffProd(signal_pdf.GetName() + "_" + fit_function, signal_pdf.GetName() + "_" + fit_function, signal_pdfs_notrig[fit_function], trigger_efficiency_formula)
#signal_pdfs[fit_function] = RooProdPdf(signal_pdf.GetName() + "_" + fit_function, signal_pdf.GetName() + "_" + fit_function, signal_pdfs_notrig[fit_function], trigger_efficiency_pdf)
iterator = signal_pdfs_notrig[fit_function].getVariables().createIterator()
this_parameter = iterator.Next()
while this_parameter:
this_parameter.setConstant()
this_parameter = iterator.Next()
else:
signal_pdfs[fit_function] = RooHistPdf('signal_' + fit_function,'signal_' + fit_function, RooArgSet(mjj), rooSigHist)
signal_norms[fit_function] = RooRealVar('signal_norm_' + fit_function, 'signal_norm_' + fit_function, 0., 0., 1e+05)
if args.fitBonly:
signal_norms[fit_function].setConstant()
background_pdfs_notrig[fit_function], background_parameters[fit_function] = make_background_pdf(fit_function, mjj, collision_energy=8000.)
background_pdf_name = background_pdfs_notrig[fit_function].GetName()
background_pdfs_notrig[fit_function].SetName(background_pdf_name + "_notrig")
background_pdfs[fit_function] = RooEffProd(background_pdf_name, background_pdf_name, background_pdfs_notrig[fit_function], trigger_efficiency_formula)
#background_pdfs[fit_function] = RooProdPdf(background_pdf_name, background_pdf_name, background_pdfs_notrig[fit_function], trigger_efficiency_pdf)
#background_pdfs[fit_function] = background_pdfs_notrig[fit_function]
#background_pdfs[fit_function].SetName(background_pdf_name)
# Initial values
if "trigbbh" in args.analysis:
if fit_function == "f3":
background_parameters[fit_function]["p1"].setVal(55.)
background_parameters[fit_function]["p1"].setMin(20.)
background_parameters[fit_function]["p2"].setVal(8.)
elif fit_function == "f4":
background_parameters[fit_function]["p1"].setVal(28.)
background_parameters[fit_function]["p2"].setVal(-22.)
background_parameters[fit_function]["p3"].setVal(10.)
elif "trigbbl" in args.analysis:
if fit_function == "f3":
background_parameters[fit_function]["p1"].setVal(82.)
background_parameters[fit_function]["p1"].setMin(60.)
background_parameters[fit_function]["p2"].setVal(8.)
elif fit_function == "f4":
background_parameters[fit_function]["p1"].setVal(41.)
background_parameters[fit_function]["p2"].setVal(-45.)
background_parameters[fit_function]["p3"].setVal(10.)
data_integral = hData.Integral(hData.GetXaxis().FindBin(float(args.massMin)),hData.GetXaxis().FindBin(float(args.massMax)))
background_norms[fit_function] = RooRealVar('background_' + fit_function + '_norm', 'background_' + fit_function + '_norm', data_integral, 0., 1.e8)
signal_epdfs[fit_function] = RooExtendPdf('esignal_' + fit_function, 'esignal_' + fit_function, signal_pdfs[fit_function], signal_norms[fit_function])
background_epdfs[fit_function] = RooExtendPdf('ebackground_' + fit_function, 'ebackground_' + fit_function, background_pdfs[fit_function], background_norms[fit_function])
models[fit_function] = RooAddPdf('model_' + fit_function, 's+b', RooArgList(background_epdfs[fit_function], signal_epdfs[fit_function]))
if args.runFit:
print "[create_datacards] INFO : Starting fit with function {}".format(fit_function)
fit_results[fit_function] = models[fit_function].fitTo(rooDataHist, RooFit.Save(kTRUE), RooFit.Extended(kTRUE), RooFit.Strategy(args.fitStrategy), RooFit.Verbose(0))
print "[create_datacards] INFO : Done with fit {}. Printing results.".format(fit_function)
fit_results[fit_function].Print()
print "[create_datacards] DEBUG : End args.runFit if block."
# needed if want to evaluate limits without background systematics
if args.fixBkg:
background_norms[fit_function].setConstant()
for par_name, par in background_parameters[fit_function].iteritems():
par.setConstant()
# -----------------------------------------
#signal_pdfs_syst = {}
# JES and JER uncertainties
if args.fitSignal:
print "[create_datacards] INFO : Getting signal PDFs from " + analysis_config.get_signal_fit_file(args.analysis, args.model, mass, "bukin", interpolated=(not mass in analysis_config.simulation.simulated_masses))
f_signal_pdfs = TFile(analysis_config.get_signal_fit_file(args.analysis, args.model, mass, "bukin", interpolated=(not mass in analysis_config.simulation.simulated_masses)))
w_signal = f_signal_pdfs.Get("w_signal")
if "jes" in systematics:
xp_central = signal_vars["xp_0"].getVal()
#print w_signal.pdf("signal__JESUp")
#print signal_fits.get_parameters(w_signal.pdf("signal__JESUp"))
xp_up = signal_fits.get_parameters(w_signal.pdf("signal__JESUp"))["xpJESUp"][0]
xp_down = signal_fits.get_parameters(w_signal.pdf("signal__JESDown"))["xpJESDown"][0]
signal_vars["dxp"].setVal(max(abs(xp_up - xp_central), abs(xp_down - xp_central)))
if signal_vars["dxp"].getVal() > 2 * mass * 0.1:
print "[create_datacards] WARNING : Large dxp value. dxp = {}, xp_down = {}, xp_central = {}, xp_up = {}".format(signal_vars["dxp"].getVal(), xp_down, xp_central, xp_up)
signal_vars["alpha_jes"].setVal(0.)
signal_vars["alpha_jes"].setConstant(False)
else:
signal_vars["dxp"].setVal(0.)
signal_vars["alpha_jes"].setVal(0.)
signal_vars["alpha_jes"].setConstant()
signal_vars["dxp"].setError(0.)
signal_vars["dxp"].setConstant()
if "jer" in systematics:
sigp_central = signal_vars["sigp_0"].getVal()
sigp_up = signal_fits.get_parameters(w_signal.pdf("signal__JERUp"))["sigpJERUp"][0]
sigp_down = signal_fits.get_parameters(w_signal.pdf("signal__JERDown"))["sigpJERDown"][0]
signal_vars["dsigp"].setVal(max(abs(sigp_up - sigp_central), abs(sigp_down - sigp_central)))
signal_vars["alpha_jer"].setVal(0.)
signal_vars["alpha_jer"].setConstant(False)
else:
signal_vars["dsigp"].setVal(0.)
signal_vars["alpha_jer"].setVal(0.)
signal_vars["alpha_jer"].setConstant()
signal_vars["dsigp"].setError(0.)
signal_vars["dsigp"].setConstant()
#for variation in ["JERUp", "JERDown"]:
# signal_pdfs_syst[variation] = w_signal.pdf("signal__" + variation)
#for variation, pdf in signal_pdfs_syst.iteritems():
# signal_parameters = pdf.getVariables()
# iter = signal_parameters.createIterator()
# var = iter.Next()
# while var:
# var.setConstant()
# var = iter.Next()
f_signal_pdfs.Close()
else:
# dictionaries holding systematic variations of the signal shape
hSig_Syst = {}
hSig_Syst_DataHist = {}
sigCDF = TGraph(hSig.GetNbinsX()+1)
if "jes" in systematics or "jer" in systematics:
sigCDF.SetPoint(0,0.,0.)
integral = 0.
for i in range(1, hSig.GetNbinsX()+1):
x = hSig.GetXaxis().GetBinLowEdge(i+1)
integral = integral + hSig.GetBinContent(i)
sigCDF.SetPoint(i,x,integral)
if "jes" in systematics:
hSig_Syst['JESUp'] = copy.deepcopy(hSig)
hSig_Syst['JESDown'] = copy.deepcopy(hSig)
if "jer" in systematics:
hSig_Syst['JERUp'] = copy.deepcopy(hSig)
hSig_Syst['JERDown'] = copy.deepcopy(hSig)
# reset signal histograms
for key in hSig_Syst.keys():
hSig_Syst[key].Reset()
hSig_Syst[key].SetName(hSig_Syst[key].GetName() + '_' + key)
# produce JES signal shapes
if "jes" in systematics:
for i in range(1, hSig.GetNbinsX()+1):
xLow = hSig.GetXaxis().GetBinLowEdge(i)
xUp = hSig.GetXaxis().GetBinLowEdge(i+1)
jes = 1. - systematics["jes"]
xLowPrime = jes*xLow
xUpPrime = jes*xUp
hSig_Syst['JESUp'].SetBinContent(i, sigCDF.Eval(xUpPrime) - sigCDF.Eval(xLowPrime))
jes = 1. + systematics["jes"]
xLowPrime = jes*xLow
xUpPrime = jes*xUp
hSig_Syst['JESDown'].SetBinContent(i, sigCDF.Eval(xUpPrime) - sigCDF.Eval(xLowPrime))
hSig_Syst_DataHist['JESUp'] = RooDataHist('hSig_JESUp','hSig_JESUp',RooArgList(mjj),hSig_Syst['JESUp'])
hSig_Syst_DataHist['JESDown'] = RooDataHist('hSig_JESDown','hSig_JESDown',RooArgList(mjj),hSig_Syst['JESDown'])
# produce JER signal shapes
if "jer" in systematics:
for i in range(1, hSig.GetNbinsX()+1):
xLow = hSig.GetXaxis().GetBinLowEdge(i)
xUp = hSig.GetXaxis().GetBinLowEdge(i+1)
jer = 1. - systematics["jer"]
xLowPrime = jer*(xLow-float(mass))+float(mass)
xUpPrime = jer*(xUp-float(mass))+float(mass)
hSig_Syst['JERUp'].SetBinContent(i, sigCDF.Eval(xUpPrime) - sigCDF.Eval(xLowPrime))
jer = 1. + systematics["jer"]
xLowPrime = jer*(xLow-float(mass))+float(mass)
xUpPrime = jer*(xUp-float(mass))+float(mass)
hSig_Syst['JERDown'].SetBinContent(i, sigCDF.Eval(xUpPrime) - sigCDF.Eval(xLowPrime))
hSig_Syst_DataHist['JERUp'] = RooDataHist('hSig_JERUp','hSig_JERUp',RooArgList(mjj),hSig_Syst['JERUp'])
hSig_Syst_DataHist['JERDown'] = RooDataHist('hSig_JERDown','hSig_JERDown',RooArgList(mjj),hSig_Syst['JERDown'])
# -----------------------------------------
# create a datacard and corresponding workspace
postfix = (('_' + args.postfix) if args.postfix != '' else '')
wsName = 'workspace_' + args.final_state + '_m' + str(mass) + postfix + '.root'
w = RooWorkspace('w','workspace')
if args.fitSignal:
signal_pdf.SetName("signal")
getattr(w,'import')(signal_pdf,RooFit.Rename("signal"))
# Create a norm variable "signal_norm" which normalizes the PDF to unity.
norm = args.lumi
#signal_norm = ROOT.RooRealVar("signal_norm", "signal_norm", 1. / norm, 0.1 / norm, 10. / norm)
#if args.analysis == "trigbbh_CSVTM" and mass >= 1100:
signal_norm = ROOT.RooRealVar("signal_norm", "signal_norm", norm/100., norm/100. / 10., norm * 10.)
#else:
# signal_norm = ROOT.RooRealVar("signal_norm", "signal_norm", norm, norm / 10., norm * 10.)
print "[create_datacards] INFO : Set signal norm to {}".format(signal_norm.getVal())
signal_norm.setConstant()
getattr(w,'import')(signal_norm,ROOT.RooCmdArg())
#if "jes" in systematics:
# getattr(w,'import')(signal_pdfs_syst['JESUp'],RooFit.Rename("signal__JESUp"))
# getattr(w,'import')(signal_pdfs_syst['JESDown'],RooFit.Rename("signal__JESDown"))
#if "jer" in systematics:
# getattr(w,'import')(signal_pdfs_syst['JERUp'],RooFit.Rename("signal__JERUp"))
# getattr(w,'import')(signal_pdfs_syst['JERDown'],RooFit.Rename("signal__JERDown"))
else:
getattr(w,'import')(rooSigHist,RooFit.Rename("signal"))
if "jes" in systematics:
getattr(w,'import')(hSig_Syst_DataHist['JESUp'],RooFit.Rename("signal__JESUp"))
getattr(w,'import')(hSig_Syst_DataHist['JESDown'],RooFit.Rename("signal__JESDown"))
if "jer" in systematics:
getattr(w,'import')(hSig_Syst_DataHist['JERUp'],RooFit.Rename("signal__JERUp"))
getattr(w,'import')(hSig_Syst_DataHist['JERDown'],RooFit.Rename("signal__JERDown"))
if args.decoBkg:
getattr(w,'import')(background_deco,ROOT.RooCmdArg())
else:
for fit_function in fit_functions:
print "Importing background PDF"
print background_pdfs[fit_function]
background_pdfs[fit_function].Print()
getattr(w,'import')(background_pdfs[fit_function],ROOT.RooCmdArg(),RooFit.Rename("background_" + fit_function), RooFit.RecycleConflictNodes())
w.pdf("background_" + fit_function).Print()
getattr(w,'import')(background_norms[fit_function],ROOT.RooCmdArg(),RooFit.Rename("background_" + fit_function + "_norm"))
getattr(w,'import')(fit_results[fit_function])
getattr(w,'import')(signal_norms[fit_function],ROOT.RooCmdArg())
if args.fitBonly:
getattr(w,'import')(models[fit_function],ROOT.RooCmdArg(),RooFit.RecycleConflictNodes())
getattr(w,'import')(rooDataHist,RooFit.Rename("data_obs"))
w.Print()
print "Starting save"
if args.output_path:
if not os.path.isdir( os.path.join(os.getcwd(),args.output_path) ):
os.mkdir( os.path.join(os.getcwd(),args.output_path) )
print "[create_datacards] INFO : Writing workspace to file {}".format(os.path.join(args.output_path,wsName))
w.writeToFile(os.path.join(args.output_path,wsName))
else:
print "[create_datacards] INFO : Writing workspace to file {}".format(limit_config.get_workspace_filename(args.analysis, args.model, mass, fitBonly=args.fitBonly, fitSignal=args.fitSignal, correctTrigger=args.correctTrigger))
w.writeToFile(limit_config.get_workspace_filename(args.analysis, args.model, mass, fitBonly=args.fitBonly, fitSignal=args.fitSignal, correctTrigger=args.correctTrigger))
# Clean up
for name, obj in signal_norms.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_pdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_pdfs_notrig.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_norms.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in signal_pdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in signal_pdfs_notrig.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in signal_epdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_epdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in fit_results.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, dict_l2 in background_parameters.iteritems():
for name2, obj in dict_l2.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in models.iteritems():
if obj:
obj.IsA().Destructor(obj)
rooDataHist.IsA().Destructor(rooDataHist)
w.IsA().Destructor(w)
# Make datacards only if S+B fitted
if not args.fitBonly:
beffUnc = 0.3
boffUnc = 0.06
for fit_function in fit_functions:
if args.output_path:
dcName = 'datacard_' + args.final_state + '_m' + str(mass) + postfix + '_' + fit_function + '.txt'
print "[create_datacards] INFO : Writing datacard to file {}".format(os.path.join(args.output_path,dcName))
datacard = open(os.path.join(args.output_path,dcName),'w')
else:
print "[create_datacards] INFO : Writing datacard to file {}".format(limit_config.get_datacard_filename(args.analysis, args.model, mass, fit_function, fitSignal=args.fitSignal, correctTrigger=args.correctTrigger))
datacard = open(limit_config.get_datacard_filename(args.analysis, args.model, mass, fit_function, fitSignal=args.fitSignal, correctTrigger=args.correctTrigger), 'w')
datacard.write('imax 1\n')
datacard.write('jmax 1\n')
datacard.write('kmax *\n')
datacard.write('---------------\n')
if ("jes" in systematics or "jer" in systematics) and not args.fitSignal:
if args.output_path:
datacard.write('shapes * * '+wsName+' w:$PROCESS w:$PROCESS__$SYSTEMATIC\n')
else:
datacard.write('shapes * * '+os.path.basename(limit_config.get_workspace_filename(args.analysis, args.model, mass, fitSignal=args.fitSignal, correctTrigger=args.correctTrigger))+' w:$PROCESS w:$PROCESS__$SYSTEMATIC\n')
else:
if args.output_path:
datacard.write('shapes * * '+wsName+' w:$PROCESS\n')
else:
datacard.write('shapes * * '+os.path.basename(limit_config.get_workspace_filename(args.analysis, args.model, mass, fitSignal=args.fitSignal, correctTrigger=args.correctTrigger))+' w:$PROCESS\n')
datacard.write('---------------\n')
datacard.write('bin 1\n')
datacard.write('observation -1\n')
datacard.write('------------------------------\n')
datacard.write('bin 1 1\n')
datacard.write('process signal background_' + fit_function + '\n')
datacard.write('process 0 1\n')
if args.fitSignal:
datacard.write('rate 1 1\n')
else:
datacard.write('rate -1 1\n')
datacard.write('------------------------------\n')
datacard.write('lumi lnN %f -\n'%(1.+systematics["luminosity"]))
datacard.write('beff lnN %f -\n'%(1.+beffUnc))
datacard.write('boff lnN %f -\n'%(1.+boffUnc))
#datacard.write('bkg lnN - 1.03\n')
if args.fitSignal:
if "jes" in systematics:
datacard.write("alpha_jes param 0.0 1.0\n")
if "jer" in systematics:
datacard.write("alpha_jer param 0.0 1.0\n")
else:
if "jes" in systematics:
datacard.write('JES shape 1 -\n')
if "jer" in systematics:
datacard.write('JER shape 1 -\n')
# flat parameters --- flat prior
datacard.write('background_' + fit_function + '_norm flatParam\n')
if args.decoBkg:
datacard.write('deco_eig1 flatParam\n')
datacard.write('deco_eig2 flatParam\n')
else:
for par_name, par in background_parameters[fit_function].iteritems():
datacard.write(fit_function + "_" + par_name + ' flatParam\n')
datacard.close()
print "[create_datacards] INFO : Done with this datacard"
#print '>> Datacards and workspaces created and stored in %s/'%( os.path.join(os.getcwd(),args.output_path) )
print "All done."
fit_functions = ["dijet4"]
#gen_functions = ["f1", "f2", "f4", "f5"]
#fit_functions = ["f1"]
for mass in masses[analysis]:
names = []
gen_datacards = {}
fit_datacards = {}
gen_workspaces = {}
fit_workspaces = {}
top_name = model + "_" + analysis + "/m" + str(mass) + "_mu" + str(args.mu)
job_names = []
for f_gen in gen_functions:
for f_fit in fit_functions:
name = model + "_" + analysis + "_m" + str(mass) + "_gen_" + f_gen + "_fit_" + f_fit + "_mu" + str(args.mu)
job_names.append(name)
gen_datacards[name] = limit_config.get_datacard_filename(analysis, model, mass, f_gen, correctTrigger=False, useMCTrigger=False, qcd=False, fitTrigger=True, fitBonly=False)
gen_workspaces[name] = limit_config.get_workspace_filename(analysis, model, mass, correctTrigger=False, useMCTrigger=False, qcd=False, fitTrigger=True, fitBonly=False)
fit_datacards[name] = limit_config.get_datacard_filename(analysis, model, mass, f_fit, correctTrigger=False, useMCTrigger=False, qcd=False, fitTrigger=True, fitBonly=False)
fit_workspaces[name] = limit_config.get_workspace_filename(analysis, model, mass, correctTrigger=False, useMCTrigger=False, qcd=False, fitTrigger=True, fitBonly=False)
#gen_datacards[name] = datacard_folders[model][analysis] + "/datacard_qq_m" + str(mass) + "_" + f_gen + ".txt"
#gen_workspaces[name] = datacard_folders[model][analysis] + "/workspace_qq_m" + str(mass) + ".root"
#fit_datacards[name] = datacard_folders[model][analysis] + "/datacard_qq_m" + str(mass) + "_" + f_fit + ".txt"
#fit_workspaces[name] = datacard_folders[model][analysis] + "/workspace_qq_m" + str(mass) + ".root"
run_many_bias_studies(top_name, job_names, gen_datacards=gen_datacards, fit_datacards=fit_datacards, gen_workspaces=gen_workspaces, fit_workspaces=fit_workspaces, n_toys=args.n_toys, mu=job_mu_values[model][analysis][mass], dry_run=args.dry_run)
if args.retry:
for model in models:
for analysis in analyses:
for mass in masses[analysis]:
names = []
gen_datacards = {}
def main():
# input parameters
parser = ArgumentParser(
description=
'Script that runs limit calculation for specified mass points')
parser.add_argument("-M",
"--method",
dest="method",
required=True,
choices=[
'MaxLikelihoodFit', 'ProfileLikelihood',
'HybridNew', 'Asymptotic', 'MarkovChainMC'
],
help="Method to calculate upper limits",
metavar="METHOD")
parser.add_argument('--analyses',
type=str,
default="trigbbh_CSVTM,trigbbl_CSVTM",
help="Analysis names")
parser.add_argument('--models',
type=str,
default="Hbb,RSG,ZPrime",
help="Model names")
parser.add_argument(
'--qcd',
action='store_true',
help="Use QCD instead of data (assumes no trigger emulation)")
parser.add_argument(
'--correctTrigger',
action='store_true',
help=
"Use model with trigger correction (has to have been specified in create_datacards.py)"
)
parser.add_argument('--useMCTrigger',
action='store_true',
help="Use MC trigger")
parser.add_argument(
'--fitTrigger',
action='store_true',
help=
"Use model with trigger fit (has to have been specified in create_datacards.py)"
)
parser.add_argument(
'--fitOffB',
action='store_true',
help=
"Include a parametrization of offline b-tag efficiency in background PDF"
)
parser.add_argument('--fit_function',
type=str,
default="f4",
help="Name of central fit function")
#parser.add_argument("-d", "--datacards_path", dest="datacards_path", required=True,
# help="Path to datacards and workspaces",
# metavar="DATA_HISTNAME")
#parser.add_argument("-f", "--final_state", dest="final_state", required=True,
# help="Final state (e.g. qq, qg, gg)",
# metavar="FINAL_STATE")
#parser.add_argument("-o", "--output_path", dest="output_path",
# default='logs',
# help="Output path where log files will be stored (default: %(default)s)",
# metavar="OUTPUT_PATH")
parser.add_argument("--rMin",
dest="rMin",
type=float,
help="Minimum value for the signal strength")
parser.add_argument("--rMax",
dest="rMax",
type=float,
help="Maximum value for the signal strength")
parser.add_argument(
"--rPrior",
action="store_true",
help="Take rMin and rMax from a previous iteration of limit setting.")
parser.add_argument("--rRelAcc",
dest="rRelAcc",
type=float,
help="rRelAcc")
parser.add_argument("--rAbsAcc",
dest="rAbsAcc",
type=float,
help="rAbsAcc")
parser.add_argument("--level",
dest="level",
type=float,
help="Exp from grid level")
parser.add_argument("--toysH",
dest="toysH",
type=int,
help="Number of Toy MC extractions for HybridNew")
parser.add_argument("--toys",
dest="toys",
type=int,
help="Number of Toy MC extractions, not for HybridNew")
parser.add_argument(
"--tries",
dest="tries",
type=int,
default=10,
help="Number of times to run the MCMC (default: %(default)i)")
parser.add_argument("--robustFit",
dest="robustFit",
action='store_true',
help="combine robustFit option")
parser.add_argument(
"--proposal",
dest="proposal",
default='ortho',
help="Proposal function for MCMC (default: %(default)s)")
parser.add_argument("--noSyst",
dest="noSyst",
default=False,
action="store_true",
help="Run without systematic uncertainties")
parser.add_argument("--picky",
dest="picky",
default=False,
action="store_true",
help="combine picky mode")
parser.add_argument("--saveHybridResult",
action="store_true",
help="--saveHybridResult")
parser.add_argument("--strictBounds",
dest="strictBounds",
default=False,
action="store_true",
help="Strict bounds on rMax")
parser.add_argument(
"--testStat",
type=str,
help=
"Test statistics: LEP, TEV, LHC (previously known as Atlas), Profile.")
parser.add_argument("--freezeNuisances",
dest="freezeNuisances",
type=str,
help="Freeze nuisance parameters")
parser.add_argument("--noHint",
dest="noHint",
default=False,
action="store_true",
help="Do not run the hint method")
parser.add_argument("--significance",
dest="significance",
default=False,
action="store_true",
help="Calculate significance instead of limits")
parser.add_argument("--frequentist",
dest="freq",
default=False,
action="store_true",
help="Frequentist hybridnew")
parser.add_argument("--fork",
dest="forkvar",
default=False,
action="store_true",
help="More cores")
parser.add_argument("--fitStrategy",
dest="fitStrategy",
type=int,
help="Fit strategy (default: %(default).1f)")
parser.add_argument("--condor",
dest="condor",
default=False,
action="store_true",
help="Batch process using Condor")
parser.add_argument(
"--no_retar",
dest='no_retar',
action="store_true",
help=
"If --condor is specified, this specifies no retar of src directory (use cached copy)"
)
parser.add_argument(
"--postfix",
dest="postfix",
default='',
help=
"Postfix for the input and output file names (default: %(default)s)")
parser.add_argument("--hnsig",
dest="hnsig",
default=False,
action="store_true",
help="HybridNew Significance calc")
parser.add_argument("--hnsig2",
dest="hnsig2",
default=False,
action="store_true",
help="HybridNew Significance calc")
parser.add_argument("--minimizerTolerance",
dest="minimizerTolerance",
type=float,
help="--minimizerTolerance option for combine")
parser.add_argument("--minimizerAlgoForMinos",
dest="minimizerAlgoForMinos",
type=str,
help="--minimizerAlgoForMinos option for combine")
parser.add_argument("--minimizerToleranceForMinos",
dest="minimizerToleranceForMinos",
type=float,
help="--minimizerToleranceForMinos option for combine")
parser.add_argument('-v',
'--verbose',
type=int,
help='Verbosity of combine')
parser.add_argument(
'-m',
'--masses',
type=str,
help=
'Manually specify masses (comma-separated list). Otherwise, taken from limit_configuration.'
)
parser.add_argument("--preFitValue",
type=float,
help="preFitValue option for combine")
parser.add_argument("--fitBonly",
action="store_true",
help="Use workspace created with fitBonly option")
#mass_group = parser.add_mutually_exclusive_group(required=True)
#mass_group.add_argument("--mass",
# type=int,
# nargs = '*',
# default = 1000,
# help="Mass can be specified as a single value or a whitespace separated list (default: %(default)i)"
# )
#mass_group.add_argument("--massrange",
# type=int,
# nargs = 3,
# help="Define a range of masses to be produced. Format: min max step",
# metavar = ('MIN', 'MAX', 'STEP')
# )
#mass_group.add_argument("--masslist",
# help = "List containing mass information"
# )
args = parser.parse_args()
analyses = args.analyses.split(",")
models = args.models.split(",")
# check if the output directory exists
#if not os.path.isdir( os.path.join(os.getcwd(), args.output_path) ):
# os.mkdir( os.path.join(os.getcwd(), args.output_path) )
#print os.getcwd()
# mass points for which resonance shapes will be produced
#masses = []
#if args.massrange != None:
# MIN, MAX, STEP = args.massrange
# masses = range(MIN, MAX+STEP, STEP)
#elif args.masslist != None:
# # A mass list was provided
# print "Will create mass list according to", args.masslist
# masslist = __import__(args.masslist.replace(".py",""))
# masses = masslist.masses
#else:
# masses = args.mass
# ## sort masses
#masses.sort()
masses = {}
if args.masses:
for analysis in analyses:
masses[analysis] = [int(x) for x in args.masses.split(",")]
else:
masses = limit_config.limit_signal_masses
method = args.method
if args.significance and method != 'ProfileLikelihood' and method != 'HybridNew':
print "** ERROR: ** For significance calculation the ProfileLikelihood or HybridNew method has to be used. Aborting."
sys.exit(1)
options = ''
if args.significance:
options = options + ' --significance'
if args.freq:
options = options + ' --frequentist'
if args.hnsig:
options = options + ' --significance --saveToys --fullBToys --saveHybridResult -T 500 -i 100 -s 123457'
if args.hnsig2:
options = options + ' --significance --readHybridResult --toysFile=input.root --expectedFromGrid=0.5'
if args.forkvar:
options = options + ' --fork 4'
if args.testStat:
options = options + ' --testStat ' + args.testStat
if args.level != None:
options = options + ' --expectedFromGrid=%f' % (args.level)
if args.fitStrategy:
options = options + ' --minimizerStrategy %i' % (args.fitStrategy)
if args.noSyst:
options = options + ' --systematics 0'
if args.freezeNuisances:
options = options + ' --freezeNuisances ' + args.freezeNuisances
if args.picky:
options = options + ' --picky '
if args.saveHybridResult:
options = options + " -- saveHybridResult "
if args.strictBounds:
options = options + ' --strictBounds '
if args.rAbsAcc:
options = options + " --rAbsAcc " + str(args.rAbsAcc) + " "
if args.rRelAcc:
options = options + " --rRelAcc " + str(args.rRelAcc) + " "
if args.verbose:
options = options + ' -v' + str(args.verbose)
if method != 'ProfileLikelihood' and method != 'MaxLikelihoodFit' and args.rMax == None and not args.noHint and not args.significance:
options = options + ' --hintMethod ProfileLikelihood'
if method == 'HybridNew' and args.toysH != None:
options = options + ' --toysH %i' % (args.toysH)
if args.toys:
options = options + ' --toys ' + str(args.toys)
if args.robustFit:
options = options + ' --robustFit 1'
if args.minimizerTolerance:
options += " --minimizerTolerance " + str(
args.minimizerTolerance) + " "
if args.minimizerAlgoForMinos:
options += " --minimizerAlgoForMinos " + str(
args.minimizerAlgoForMinos) + " "
if args.minimizerToleranceForMinos:
options += " --minimizerToleranceForMinos " + str(
args.minimizerToleranceForMinos) + " "
if args.preFitValue:
options += " --preFitValue " + str(args.preFitValue) + " "
if args.rPrior:
# Take rMin and rMax from +/-2 sigma estimates from a previous iteration. This has to be done per-job, so do it later.
pass
else:
if args.rMin != None:
options = options + ' --rMin %f' % (args.rMin)
if args.rMax != None:
options = options + ' --rMax %f' % (args.rMax)
if method == 'MarkovChainMC':
options = options + ' --tries %i --proposal %s' % (args.tries,
args.proposal)
prefix = 'limits'
if args.significance:
prefix = 'significance'
elif method == 'MaxLikelihoodFit':
prefix = 'signal_xs'
postfix = (('_' + args.postfix) if args.postfix != '' else '')
if args.noSyst:
postfix += "_noSyst"
if args.freezeNuisances:
postfix += "_" + args.freezeNuisances.replace(",", "_")
if args.fitTrigger:
postfix += "_fitTrigger"
if args.correctTrigger:
postfix += "_correctTrigger"
if args.useMCTrigger:
postfix += "_useMCTrigger"
if args.fitOffB:
postfix += "_fitOffB"
if args.qcd:
postfix += "_qcd"
if args.fitBonly:
postfix += "_fitBonly"
datacards_path = limit_config.paths["datacards"]
output_path = limit_config.paths["combine_logs"]
condor_path = limit_config.paths["condor"]
# change to the appropriate directory
if args.condor:
os.chdir(output_path)
else:
os.chdir(datacards_path)
first = True
for analysis in analyses:
for model in models:
for mass in masses[analysis]:
logName = '{}_{}_{}_{}_m{}{}_{}.log'.format(
prefix, method, analysis, model, int(mass), postfix,
args.fit_function)
job_name = "%s_%s_m%i%s_%s" % (analysis, model, int(mass),
postfix, args.fit_function)
run_options = options + ' --name _%s_%s_m%i%s_%s --mass %i' % (
analysis, model, int(mass), postfix, args.fit_function,
int(mass))
if args.rPrior:
run_options += " --rMin " + str(
limit_config.limit_m2sigma_estimates[analysis][model]
[mass] / 5. * 100.)
run_options += " --rMax " + str(
limit_config.limit_p2sigma_estimates[analysis][model]
[mass] * 5. * 100.)
if method == "MaxLikelihoodFit":
# Save shapes and plots
run_options += " --saveWithUncertainties --saveShapes --plots --out plots_" + job_name
if args.condor:
cmd = "combine -M %s %s %s 2>&1 | tee %s" % (
method, run_options,
os.path.basename(
limit_config.get_datacard_filename(
analysis,
model,
mass,
args.fit_function,
correctTrigger=args.correctTrigger,
useMCTrigger=args.useMCTrigger,
qcd=args.qcd,
fitTrigger=args.fitTrigger,
fitBonly=args.fitBonly,
fitOffB=args.fitOffB)),
os.path.basename(
os.path.join(('' if args.condor else output_path),
logName)))
else:
cmd = "combine -M %s %s %s 2>&1 | tee %s" % (
method, run_options,
limit_config.get_datacard_filename(
analysis,
model,
mass,
args.fit_function,
correctTrigger=args.correctTrigger,
useMCTrigger=args.useMCTrigger,
qcd=args.qcd,
fitTrigger=args.fitTrigger,
fitBonly=args.fitBonly,
fitOffB=args.fitOffB),
os.path.join(
('' if args.condor else output_path), logName))
# if using Condor
if args.condor:
#submission_dir = limit_config.paths["condor"]
submission_dir = limit_config.paths["combine_logs"]
start_dir = os.getcwd()
os.chdir(submission_dir)
# create the executable script
bash_script_path = os.path.join(
submission_dir, 'run_%s_%s_%s_m%i%s.sh' %
(method, analysis, model, int(mass), postfix))
#bash_content = bash_template
#bash_content = re.sub('DUMMY_CMD',cmd,bash_content)
bash_script = open(bash_script_path, 'w')
bash_script.write("echo '" + cmd + "'\n")
if method == "MaxLikelihoodFit":
bash_script.write("mkdir -pv plots_" + job_name + "\n")
bash_script.write(cmd)
bash_script.close()
# Create the condor command
condor_command = "csub " + bash_script_path
files_to_transfer = []
files_to_transfer.append(bash_script_path)
files_to_transfer.append(
limit_config.get_datacard_filename(
analysis,
model,
mass,
args.fit_function,
correctTrigger=args.correctTrigger,
useMCTrigger=args.useMCTrigger,
qcd=args.qcd,
fitTrigger=args.fitTrigger,
fitBonly=args.fitBonly,
fitOffB=args.fitOffB))
files_to_transfer.append(
limit_config.get_workspace_filename(
analysis,
model,
mass,
correctTrigger=args.correctTrigger,
useMCTrigger=args.useMCTrigger,
qcd=args.qcd,
fitTrigger=args.fitTrigger,
fitBonly=args.fitBonly,
fitOffB=args.fitOffB))
condor_command += " -F " + ",".join(files_to_transfer)
condor_command += " -l combine_{}_\$\(Cluster\)_\$\(Process\).log".format(
logName)
condor_command += " -s submit_combine_{}_{}_{}.jdl".format(
analysis, model, mass)
condor_command += " -d " + submission_dir
if method == "MaxLikelihoodFit":
condor_command += " -o plots_" + job_name + " "
condor_command += " --cmssw"
if not first or args.no_retar:
condor_command += " --no_retar "
print ">> Submitting job for %s %s resonance with m = %i GeV..." % (
analysis, model, int(mass))
print "Submission command: "
print condor_command
os.system(condor_command)
print "---------------------------------------------------------------------------"
os.chdir(start_dir)
else:
print ">> Running combine for %s %s resonance with m = %i GeV..." % (
analysis, model, int(mass))
print "---------------------------------------------------------------------------"
if method == "MaxLikelihoodFit":
os.system("mkdir -pv plots_" + job_name)
print "Running: " + cmd + "\n"
os.system(cmd)
if first:
first = False
def main():
# usage description
usage = "Example: ./scripts/createDatacards.py --inputData inputs/rawhistV7_Run2015D_scoutingPFHT_UNBLINDED_649_838_JEC_HLTplusV7_Mjj_cor_smooth.root --dataHistname mjj_mjjcor_gev --inputSig inputs/ResonanceShapes_gg_13TeV_Scouting_Spring15.root -f gg -o datacards -l 1866 --lumiUnc 0.027 --massrange 1000 1500 50 --runFit --p1 5 --p2 7 --p3 0.4 --massMin 838 --massMax 2037 --fitStrategy 2"
# input parameters
parser = ArgumentParser(
description=
'Script that creates combine datacards and corresponding RooFit workspaces',
epilog=usage)
parser.add_argument("analysis", type=str, help="Analysis name")
parser.add_argument("model", type=str, help="Model (Hbb, RSG)")
#parser.add_argument("--inputData", dest="inputData", required=True,
# help="Input data spectrum",
# metavar="INPUT_DATA")
parser.add_argument("--dataHistname",
dest="dataHistname",
type=str,
default="h_data",
help="Data histogram name",
metavar="DATA_HISTNAME")
#parser.add_argument("--inputSig", dest="inputSig", required=True,
# help="Input signal shapes",
# metavar="INPUT_SIGNAL")
parser.add_argument("-f",
"--final_state",
dest="final_state",
default="qq",
help="Final state (e.g. qq, qg, gg)",
metavar="FINAL_STATE")
parser.add_argument("--fit_functions",
dest="fit_functions",
default="f1,f2,f3,f4,f5",
help="List of fit functions")
#parser.add_argument("-f2", "--type", dest="atype", required=True, help="Type (e.g. hG, lG, hR, lR)")
parser.add_argument(
"-o",
"--output_path",
dest="output_path",
help=
"Output path where datacards and workspaces will be stored. If not specified, this is derived from limit_configuration.",
metavar="OUTPUT_PATH")
parser.add_argument("--correctTrigger",
dest="correctTrigger",
action='store_true',
help="Include trigger correction in PDF")
parser.add_argument(
"-l",
"--lumi",
dest="lumi",
default=19700.,
type=float,
help="Integrated luminosity in pb-1 (default: %(default).1f)",
metavar="LUMI")
parser.add_argument(
"--massMin",
dest="massMin",
default=500,
type=int,
help=
"Lower bound of the mass range used for fitting (default: %(default)s)",
metavar="MASS_MIN")
parser.add_argument(
"--massMax",
dest="massMax",
default=1200,
type=int,
help=
"Upper bound of the mass range used for fitting (default: %(default)s)",
metavar="MASS_MAX")
parser.add_argument(
"--fitSignal",
action="store_true",
help=
"Use signal fitted shapes (CB+Voigtian) instead of histogram templates"
)
#parser.add_argument("--lumiUnc", dest="lumiUnc",
# required=True, type=float,
# help="Relative uncertainty in the integrated luminosity",
# metavar="LUMI_UNC")
#parser.add_argument("--jesUnc", dest="jesUnc",
# type=float,
# help="Relative uncertainty in the jet energy scale",
# metavar="JES_UNC")
#parser.add_argument("--jerUnc", dest="jerUnc",
# type=float,
# help="Relative uncertainty in the jet energy resolution",
# metavar="JER_UNC")
parser.add_argument(
"--sqrtS",
dest="sqrtS",
default=8000.,
type=float,
help="Collision center-of-mass energy (default: %(default).1f)",
metavar="SQRTS")
parser.add_argument("--fixP3",
dest="fixP3",
default=False,
action="store_true",
help="Fix the fit function p3 parameter")
parser.add_argument("--runFit",
dest="runFit",
default=False,
action="store_true",
help="Run the fit")
parser.add_argument("--fitBonly",
dest="fitBonly",
default=False,
action="store_true",
help="Run B-only fit")
parser.add_argument("--fixBkg",
dest="fixBkg",
default=False,
action="store_true",
help="Fix all background parameters")
parser.add_argument("--decoBkg",
dest="decoBkg",
default=False,
action="store_true",
help="Decorrelate background parameters")
parser.add_argument("--fitStrategy",
dest="fitStrategy",
type=int,
default=1,
help="Fit strategy (default: %(default).1f)")
parser.add_argument("--debug",
dest="debug",
default=False,
action="store_true",
help="Debug printout")
parser.add_argument(
"--postfix",
dest="postfix",
default='',
help="Postfix for the output file names (default: %(default)s)")
parser.add_argument("--pyes",
dest="pyes",
default=False,
action="store_true",
help="Make files for plots")
parser.add_argument("--jyes",
dest="jyes",
default=False,
action="store_true",
help="Make files for JES/JER plots")
parser.add_argument(
"--pdir",
dest="pdir",
default='testarea',
help="Name a directory for the plots (default: %(default)s)")
parser.add_argument("--chi2",
dest="chi2",
default=False,
action="store_true",
help="Compute chi squared")
parser.add_argument("--widefit",
dest="widefit",
default=False,
action="store_true",
help="Fit with wide bin hist")
mass_group = parser.add_mutually_exclusive_group(required=True)
mass_group.add_argument(
"--mass",
type=int,
nargs='*',
default=1000,
help=
"Mass can be specified as a single value or a whitespace separated list (default: %(default)i)"
)
mass_group.add_argument(
"--massrange",
type=int,
nargs=3,
help="Define a range of masses to be produced. Format: min max step",
metavar=('MIN', 'MAX', 'STEP'))
mass_group.add_argument("--masslist",
help="List containing mass information")
args = parser.parse_args()
fit_functions = args.fit_functions.split(",")
# mass points for which resonance shapes will be produced
masses = []
if args.fitBonly:
masses.append(750)
else:
if args.massrange != None:
MIN, MAX, STEP = args.massrange
masses = range(MIN, MAX + STEP, STEP)
elif args.masslist != None:
# A mass list was provided
print "Will create mass list according to", args.masslist
masslist = __import__(args.masslist.replace(".py", ""))
masses = masslist.masses
else:
masses = args.mass
# sort masses
masses.sort()
# import ROOT stuff
from ROOT import gStyle, TFile, TH1F, TH1D, TGraph, kTRUE, kFALSE, TCanvas, TLegend, TPad, TLine
from ROOT import RooHist, RooRealVar, RooDataHist, RooArgList, RooArgSet, RooAddPdf, RooProdPdf, RooEffProd, RooFit, RooGenericPdf, RooWorkspace, RooMsgService, RooHistPdf, RooExtendPdf
if not args.debug:
RooMsgService.instance().setSilentMode(kTRUE)
RooMsgService.instance().setStreamStatus(0, kFALSE)
RooMsgService.instance().setStreamStatus(1, kFALSE)
# input data file
#inputData = TFile(limit_config.get_data_input(args.analysis))
# input data histogram
#hData = inputData.Get(args.dataHistname)
#hData.SetDirectory(0)
data_file = TFile(
analysis_config.get_b_histogram_filename(args.analysis,
"BJetPlusX_2012"))
hData = data_file.Get("BHistograms/h_pfjet_mjj")
hData.SetDirectory(0)
# input sig file
if not args.fitSignal:
print "[create_datacards] INFO : Opening resonance shapes file at " + limit_config.get_resonance_shapes(
args.analysis, args.model)
inputSig = TFile(
limit_config.get_resonance_shapes(args.analysis, args.model),
"READ")
sqrtS = args.sqrtS
# mass variable
mjj = RooRealVar('mjj', 'mjj', float(args.massMin), float(args.massMax))
# integrated luminosity and signal cross section
lumi = args.lumi
signalCrossSection = 1. # set to 1. so that the limit on r can be interpreted as a limit on the signal cross section
if args.correctTrigger:
trigger_efficiency_pdf = trigger_efficiency.get_pdf(args.analysis, mjj)
trigger_efficiency_formula = trigger_efficiency.get_formula(
args.analysis, mjj)
else:
trigger_efficiency_pdf = trigger_efficiency.get_trivial_pdf(mjj)
trigger_efficiency_formula = trigger_efficiency.get_trivial_formula(
mjj)
for mass in masses:
print ">> Creating datacard and workspace for %s resonance with m = %i GeV..." % (
args.final_state, int(mass))
rooDataHist = RooDataHist('rooDatahist', 'rooDathist', RooArgList(mjj),
hData)
if not args.fitSignal:
hSig = inputSig.Get("h_" + args.final_state + "_" + str(int(mass)))
if not hSig:
raise Exception("Couldn't find histogram " + "h_" +
args.final_state + "_" + str(int(mass)) +
" in file " +
limit_config.get_resonance_shapes(
args.analysis, args.model))
# normalize signal shape to the expected event yield (works even if input shapes are not normalized to unity)
hSig.Scale(
signalCrossSection * lumi / hSig.Integral()
) # divide by a number that provides roughly an r value of 1-10
rooSigHist = RooDataHist('rooSigHist', 'rooSigHist',
RooArgList(mjj), hSig)
print 'Signal acceptance:', (rooSigHist.sumEntries() /
hSig.Integral())
# If using fitted signal shapes, load the signal PDF
if args.fitSignal:
print "[create_datacards] Loading fitted signal PDFs from " + analysis_config.get_signal_fit_file(
args.analysis,
args.model,
mass,
"bukin",
interpolated=(not mass
in analysis_config.simulation.simulated_masses))
f_signal_pdfs = TFile(
analysis_config.get_signal_fit_file(
args.analysis,
args.model,
mass,
"bukin",
interpolated=(
not mass
in analysis_config.simulation.simulated_masses)),
"READ")
w_signal = f_signal_pdfs.Get("w_signal")
input_parameters = signal_fits.get_parameters(
w_signal.pdf("signal"))
# Make a new PDF with nuisance parameters
signal_pdf_notrig, signal_vars = signal_fits.make_signal_pdf_systematic(
"bukin", mjj, mass=mass)
signal_pdf_name = signal_pdf_notrig.GetName()
signal_pdf_notrig.SetName(signal_pdf_name + "_notrig")
#signal_pdf = RooProdPdf(signal_pdf_name, signal_pdf_name, signal_pdf_notrig, trigger_efficiency_pdf)
signal_pdf = RooEffProd(signal_pdf_name, signal_pdf_name,
signal_pdf_notrig,
trigger_efficiency_formula)
# Copy input parameter values
signal_vars["xp_0"].setVal(input_parameters["xp"][0])
signal_vars["xp_0"].setError(input_parameters["xp"][1])
signal_vars["xp_0"].setConstant()
signal_vars["sigp_0"].setVal(input_parameters["sigp"][0])
signal_vars["sigp_0"].setError(input_parameters["sigp"][1])
signal_vars["sigp_0"].setConstant()
signal_vars["xi_0"].setVal(input_parameters["xi"][0])
signal_vars["xi_0"].setError(input_parameters["xi"][1])
signal_vars["xi_0"].setConstant()
signal_vars["rho1_0"].setVal(input_parameters["rho1"][0])
signal_vars["rho1_0"].setError(input_parameters["rho1"][1])
signal_vars["rho1_0"].setConstant()
signal_vars["rho2_0"].setVal(input_parameters["rho2"][0])
signal_vars["rho2_0"].setError(input_parameters["rho2"][1])
signal_vars["rho2_0"].setConstant()
f_signal_pdfs.Close()
signal_parameters = {}
signal_pdfs_notrig = {}
signal_pdfs = {}
signal_norms = {}
background_pdfs = {}
background_pdfs_notrig = {}
background_parameters = {}
background_norms = {}
signal_epdfs = {}
background_epdfs = {}
models = {}
fit_results = {}
for fit_function in fit_functions:
print "[create_datacards] INFO : On fit function {}".format(
fit_function)
if args.fitSignal:
# Make a copy of the signal PDF, so that each fitTo call uses its own copy.
# The copy should have all variables set constant.
#signal_pdfs[fit_function], signal_parameters[fit_function] = signal_fits.copy_signal_pdf("bukin", signal_pdf, mjj, tag=fit_function, include_systematics=True)
signal_pdfs_notrig[fit_function] = ROOT.RooBukinPdf(
signal_pdf_notrig,
signal_pdf_notrig.GetName() + "_" + fit_function)
signal_pdfs[fit_function] = RooEffProd(
signal_pdf.GetName() + "_" + fit_function,
signal_pdf.GetName() + "_" + fit_function,
signal_pdfs_notrig[fit_function],
trigger_efficiency_formula)
#signal_pdfs[fit_function] = RooProdPdf(signal_pdf.GetName() + "_" + fit_function, signal_pdf.GetName() + "_" + fit_function, signal_pdfs_notrig[fit_function], trigger_efficiency_pdf)
iterator = signal_pdfs_notrig[fit_function].getVariables(
).createIterator()
this_parameter = iterator.Next()
while this_parameter:
this_parameter.setConstant()
this_parameter = iterator.Next()
else:
signal_pdfs[fit_function] = RooHistPdf(
'signal_' + fit_function, 'signal_' + fit_function,
RooArgSet(mjj), rooSigHist)
signal_norms[fit_function] = RooRealVar(
'signal_norm_' + fit_function, 'signal_norm_' + fit_function,
0., 0., 1e+05)
if args.fitBonly:
signal_norms[fit_function].setConstant()
background_pdfs_notrig[fit_function], background_parameters[
fit_function] = make_background_pdf(fit_function,
mjj,
collision_energy=8000.)
background_pdf_name = background_pdfs_notrig[fit_function].GetName(
)
background_pdfs_notrig[fit_function].SetName(background_pdf_name +
"_notrig")
background_pdfs[fit_function] = RooEffProd(
background_pdf_name, background_pdf_name,
background_pdfs_notrig[fit_function],
trigger_efficiency_formula)
#background_pdfs[fit_function] = RooProdPdf(background_pdf_name, background_pdf_name, background_pdfs_notrig[fit_function], trigger_efficiency_pdf)
#background_pdfs[fit_function] = background_pdfs_notrig[fit_function]
#background_pdfs[fit_function].SetName(background_pdf_name)
# Initial values
if "trigbbh" in args.analysis:
if fit_function == "f3":
background_parameters[fit_function]["p1"].setVal(55.)
background_parameters[fit_function]["p1"].setMin(20.)
background_parameters[fit_function]["p2"].setVal(8.)
elif fit_function == "f4":
background_parameters[fit_function]["p1"].setVal(28.)
background_parameters[fit_function]["p2"].setVal(-22.)
background_parameters[fit_function]["p3"].setVal(10.)
elif "trigbbl" in args.analysis:
if fit_function == "f3":
background_parameters[fit_function]["p1"].setVal(82.)
background_parameters[fit_function]["p1"].setMin(60.)
background_parameters[fit_function]["p2"].setVal(8.)
elif fit_function == "f4":
background_parameters[fit_function]["p1"].setVal(41.)
background_parameters[fit_function]["p2"].setVal(-45.)
background_parameters[fit_function]["p3"].setVal(10.)
data_integral = hData.Integral(
hData.GetXaxis().FindBin(float(args.massMin)),
hData.GetXaxis().FindBin(float(args.massMax)))
background_norms[fit_function] = RooRealVar(
'background_' + fit_function + '_norm',
'background_' + fit_function + '_norm', data_integral, 0.,
1.e8)
signal_epdfs[fit_function] = RooExtendPdf(
'esignal_' + fit_function, 'esignal_' + fit_function,
signal_pdfs[fit_function], signal_norms[fit_function])
background_epdfs[fit_function] = RooExtendPdf(
'ebackground_' + fit_function, 'ebackground_' + fit_function,
background_pdfs[fit_function], background_norms[fit_function])
models[fit_function] = RooAddPdf(
'model_' + fit_function, 's+b',
RooArgList(background_epdfs[fit_function],
signal_epdfs[fit_function]))
if args.runFit:
print "[create_datacards] INFO : Starting fit with function {}".format(
fit_function)
fit_results[fit_function] = models[fit_function].fitTo(
rooDataHist, RooFit.Save(kTRUE), RooFit.Extended(kTRUE),
RooFit.Strategy(args.fitStrategy), RooFit.Verbose(0))
print "[create_datacards] INFO : Done with fit {}. Printing results.".format(
fit_function)
fit_results[fit_function].Print()
print "[create_datacards] DEBUG : End args.runFit if block."
# needed if want to evaluate limits without background systematics
if args.fixBkg:
background_norms[fit_function].setConstant()
for par_name, par in background_parameters[
fit_function].iteritems():
par.setConstant()
# -----------------------------------------
#signal_pdfs_syst = {}
# JES and JER uncertainties
if args.fitSignal:
print "[create_datacards] INFO : Getting signal PDFs from " + analysis_config.get_signal_fit_file(
args.analysis,
args.model,
mass,
"bukin",
interpolated=(not mass
in analysis_config.simulation.simulated_masses))
f_signal_pdfs = TFile(
analysis_config.get_signal_fit_file(
args.analysis,
args.model,
mass,
"bukin",
interpolated=(
not mass
in analysis_config.simulation.simulated_masses)))
w_signal = f_signal_pdfs.Get("w_signal")
if "jes" in systematics:
xp_central = signal_vars["xp_0"].getVal()
#print w_signal.pdf("signal__JESUp")
#print signal_fits.get_parameters(w_signal.pdf("signal__JESUp"))
xp_up = signal_fits.get_parameters(
w_signal.pdf("signal__JESUp"))["xpJESUp"][0]
xp_down = signal_fits.get_parameters(
w_signal.pdf("signal__JESDown"))["xpJESDown"][0]
signal_vars["dxp"].setVal(
max(abs(xp_up - xp_central), abs(xp_down - xp_central)))
if signal_vars["dxp"].getVal() > 2 * mass * 0.1:
print "[create_datacards] WARNING : Large dxp value. dxp = {}, xp_down = {}, xp_central = {}, xp_up = {}".format(
signal_vars["dxp"].getVal(), xp_down, xp_central,
xp_up)
signal_vars["alpha_jes"].setVal(0.)
signal_vars["alpha_jes"].setConstant(False)
else:
signal_vars["dxp"].setVal(0.)
signal_vars["alpha_jes"].setVal(0.)
signal_vars["alpha_jes"].setConstant()
signal_vars["dxp"].setError(0.)
signal_vars["dxp"].setConstant()
if "jer" in systematics:
sigp_central = signal_vars["sigp_0"].getVal()
sigp_up = signal_fits.get_parameters(
w_signal.pdf("signal__JERUp"))["sigpJERUp"][0]
sigp_down = signal_fits.get_parameters(
w_signal.pdf("signal__JERDown"))["sigpJERDown"][0]
signal_vars["dsigp"].setVal(
max(abs(sigp_up - sigp_central),
abs(sigp_down - sigp_central)))
signal_vars["alpha_jer"].setVal(0.)
signal_vars["alpha_jer"].setConstant(False)
else:
signal_vars["dsigp"].setVal(0.)
signal_vars["alpha_jer"].setVal(0.)
signal_vars["alpha_jer"].setConstant()
signal_vars["dsigp"].setError(0.)
signal_vars["dsigp"].setConstant()
#for variation in ["JERUp", "JERDown"]:
# signal_pdfs_syst[variation] = w_signal.pdf("signal__" + variation)
#for variation, pdf in signal_pdfs_syst.iteritems():
# signal_parameters = pdf.getVariables()
# iter = signal_parameters.createIterator()
# var = iter.Next()
# while var:
# var.setConstant()
# var = iter.Next()
f_signal_pdfs.Close()
else:
# dictionaries holding systematic variations of the signal shape
hSig_Syst = {}
hSig_Syst_DataHist = {}
sigCDF = TGraph(hSig.GetNbinsX() + 1)
if "jes" in systematics or "jer" in systematics:
sigCDF.SetPoint(0, 0., 0.)
integral = 0.
for i in range(1, hSig.GetNbinsX() + 1):
x = hSig.GetXaxis().GetBinLowEdge(i + 1)
integral = integral + hSig.GetBinContent(i)
sigCDF.SetPoint(i, x, integral)
if "jes" in systematics:
hSig_Syst['JESUp'] = copy.deepcopy(hSig)
hSig_Syst['JESDown'] = copy.deepcopy(hSig)
if "jer" in systematics:
hSig_Syst['JERUp'] = copy.deepcopy(hSig)
hSig_Syst['JERDown'] = copy.deepcopy(hSig)
# reset signal histograms
for key in hSig_Syst.keys():
hSig_Syst[key].Reset()
hSig_Syst[key].SetName(hSig_Syst[key].GetName() + '_' + key)
# produce JES signal shapes
if "jes" in systematics:
for i in range(1, hSig.GetNbinsX() + 1):
xLow = hSig.GetXaxis().GetBinLowEdge(i)
xUp = hSig.GetXaxis().GetBinLowEdge(i + 1)
jes = 1. - systematics["jes"]
xLowPrime = jes * xLow
xUpPrime = jes * xUp
hSig_Syst['JESUp'].SetBinContent(
i,
sigCDF.Eval(xUpPrime) - sigCDF.Eval(xLowPrime))
jes = 1. + systematics["jes"]
xLowPrime = jes * xLow
xUpPrime = jes * xUp
hSig_Syst['JESDown'].SetBinContent(
i,
sigCDF.Eval(xUpPrime) - sigCDF.Eval(xLowPrime))
hSig_Syst_DataHist['JESUp'] = RooDataHist(
'hSig_JESUp', 'hSig_JESUp', RooArgList(mjj),
hSig_Syst['JESUp'])
hSig_Syst_DataHist['JESDown'] = RooDataHist(
'hSig_JESDown', 'hSig_JESDown', RooArgList(mjj),
hSig_Syst['JESDown'])
# produce JER signal shapes
if "jer" in systematics:
for i in range(1, hSig.GetNbinsX() + 1):
xLow = hSig.GetXaxis().GetBinLowEdge(i)
xUp = hSig.GetXaxis().GetBinLowEdge(i + 1)
jer = 1. - systematics["jer"]
xLowPrime = jer * (xLow - float(mass)) + float(mass)
xUpPrime = jer * (xUp - float(mass)) + float(mass)
hSig_Syst['JERUp'].SetBinContent(
i,
sigCDF.Eval(xUpPrime) - sigCDF.Eval(xLowPrime))
jer = 1. + systematics["jer"]
xLowPrime = jer * (xLow - float(mass)) + float(mass)
xUpPrime = jer * (xUp - float(mass)) + float(mass)
hSig_Syst['JERDown'].SetBinContent(
i,
sigCDF.Eval(xUpPrime) - sigCDF.Eval(xLowPrime))
hSig_Syst_DataHist['JERUp'] = RooDataHist(
'hSig_JERUp', 'hSig_JERUp', RooArgList(mjj),
hSig_Syst['JERUp'])
hSig_Syst_DataHist['JERDown'] = RooDataHist(
'hSig_JERDown', 'hSig_JERDown', RooArgList(mjj),
hSig_Syst['JERDown'])
# -----------------------------------------
# create a datacard and corresponding workspace
postfix = (('_' + args.postfix) if args.postfix != '' else '')
wsName = 'workspace_' + args.final_state + '_m' + str(
mass) + postfix + '.root'
w = RooWorkspace('w', 'workspace')
if args.fitSignal:
signal_pdf.SetName("signal")
getattr(w, 'import')(signal_pdf, RooFit.Rename("signal"))
# Create a norm variable "signal_norm" which normalizes the PDF to unity.
norm = args.lumi
#signal_norm = ROOT.RooRealVar("signal_norm", "signal_norm", 1. / norm, 0.1 / norm, 10. / norm)
#if args.analysis == "trigbbh_CSVTM" and mass >= 1100:
signal_norm = ROOT.RooRealVar("signal_norm", "signal_norm",
norm / 100., norm / 100. / 10.,
norm * 10.)
#else:
# signal_norm = ROOT.RooRealVar("signal_norm", "signal_norm", norm, norm / 10., norm * 10.)
print "[create_datacards] INFO : Set signal norm to {}".format(
signal_norm.getVal())
signal_norm.setConstant()
getattr(w, 'import')(signal_norm, ROOT.RooCmdArg())
#if "jes" in systematics:
# getattr(w,'import')(signal_pdfs_syst['JESUp'],RooFit.Rename("signal__JESUp"))
# getattr(w,'import')(signal_pdfs_syst['JESDown'],RooFit.Rename("signal__JESDown"))
#if "jer" in systematics:
# getattr(w,'import')(signal_pdfs_syst['JERUp'],RooFit.Rename("signal__JERUp"))
# getattr(w,'import')(signal_pdfs_syst['JERDown'],RooFit.Rename("signal__JERDown"))
else:
getattr(w, 'import')(rooSigHist, RooFit.Rename("signal"))
if "jes" in systematics:
getattr(w, 'import')(hSig_Syst_DataHist['JESUp'],
RooFit.Rename("signal__JESUp"))
getattr(w, 'import')(hSig_Syst_DataHist['JESDown'],
RooFit.Rename("signal__JESDown"))
if "jer" in systematics:
getattr(w, 'import')(hSig_Syst_DataHist['JERUp'],
RooFit.Rename("signal__JERUp"))
getattr(w, 'import')(hSig_Syst_DataHist['JERDown'],
RooFit.Rename("signal__JERDown"))
if args.decoBkg:
getattr(w, 'import')(background_deco, ROOT.RooCmdArg())
else:
for fit_function in fit_functions:
print "Importing background PDF"
print background_pdfs[fit_function]
background_pdfs[fit_function].Print()
getattr(w,
'import')(background_pdfs[fit_function],
ROOT.RooCmdArg(),
RooFit.Rename("background_" + fit_function),
RooFit.RecycleConflictNodes())
w.pdf("background_" + fit_function).Print()
getattr(w, 'import')(background_norms[fit_function],
ROOT.RooCmdArg(),
RooFit.Rename("background_" +
fit_function + "_norm"))
getattr(w, 'import')(fit_results[fit_function])
getattr(w, 'import')(signal_norms[fit_function],
ROOT.RooCmdArg())
if args.fitBonly:
getattr(w, 'import')(models[fit_function],
ROOT.RooCmdArg(),
RooFit.RecycleConflictNodes())
getattr(w, 'import')(rooDataHist, RooFit.Rename("data_obs"))
w.Print()
print "Starting save"
if args.output_path:
if not os.path.isdir(os.path.join(os.getcwd(), args.output_path)):
os.mkdir(os.path.join(os.getcwd(), args.output_path))
print "[create_datacards] INFO : Writing workspace to file {}".format(
os.path.join(args.output_path, wsName))
w.writeToFile(os.path.join(args.output_path, wsName))
else:
print "[create_datacards] INFO : Writing workspace to file {}".format(
limit_config.get_workspace_filename(
args.analysis,
args.model,
mass,
fitBonly=args.fitBonly,
fitSignal=args.fitSignal,
correctTrigger=args.correctTrigger))
w.writeToFile(
limit_config.get_workspace_filename(
args.analysis,
args.model,
mass,
fitBonly=args.fitBonly,
fitSignal=args.fitSignal,
correctTrigger=args.correctTrigger))
# Clean up
for name, obj in signal_norms.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_pdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_pdfs_notrig.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_norms.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in signal_pdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in signal_pdfs_notrig.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in signal_epdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_epdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in fit_results.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, dict_l2 in background_parameters.iteritems():
for name2, obj in dict_l2.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in models.iteritems():
if obj:
obj.IsA().Destructor(obj)
rooDataHist.IsA().Destructor(rooDataHist)
w.IsA().Destructor(w)
# Make datacards only if S+B fitted
if not args.fitBonly:
beffUnc = 0.3
boffUnc = 0.06
for fit_function in fit_functions:
if args.output_path:
dcName = 'datacard_' + args.final_state + '_m' + str(
mass) + postfix + '_' + fit_function + '.txt'
print "[create_datacards] INFO : Writing datacard to file {}".format(
os.path.join(args.output_path, dcName))
datacard = open(os.path.join(args.output_path, dcName),
'w')
else:
print "[create_datacards] INFO : Writing datacard to file {}".format(
limit_config.get_datacard_filename(
args.analysis,
args.model,
mass,
fit_function,
fitSignal=args.fitSignal,
correctTrigger=args.correctTrigger))
datacard = open(
limit_config.get_datacard_filename(
args.analysis,
args.model,
mass,
fit_function,
fitSignal=args.fitSignal,
correctTrigger=args.correctTrigger), 'w')
datacard.write('imax 1\n')
datacard.write('jmax 1\n')
datacard.write('kmax *\n')
datacard.write('---------------\n')
if ("jes" in systematics
or "jer" in systematics) and not args.fitSignal:
if args.output_path:
datacard.write('shapes * * ' + wsName +
' w:$PROCESS w:$PROCESS__$SYSTEMATIC\n')
else:
datacard.write('shapes * * ' + os.path.basename(
limit_config.get_workspace_filename(
args.analysis,
args.model,
mass,
fitSignal=args.fitSignal,
correctTrigger=args.correctTrigger)) +
' w:$PROCESS w:$PROCESS__$SYSTEMATIC\n')
else:
if args.output_path:
datacard.write('shapes * * ' + wsName +
' w:$PROCESS\n')
else:
datacard.write('shapes * * ' + os.path.basename(
limit_config.get_workspace_filename(
args.analysis,
args.model,
mass,
fitSignal=args.fitSignal,
correctTrigger=args.correctTrigger)) +
' w:$PROCESS\n')
datacard.write('---------------\n')
datacard.write('bin 1\n')
datacard.write('observation -1\n')
datacard.write('------------------------------\n')
datacard.write('bin 1 1\n')
datacard.write('process signal background_' +
fit_function + '\n')
datacard.write('process 0 1\n')
if args.fitSignal:
datacard.write('rate 1 1\n')
else:
datacard.write('rate -1 1\n')
datacard.write('------------------------------\n')
datacard.write('lumi lnN %f -\n' %
(1. + systematics["luminosity"]))
datacard.write('beff lnN %f -\n' % (1. + beffUnc))
datacard.write('boff lnN %f -\n' % (1. + boffUnc))
#datacard.write('bkg lnN - 1.03\n')
if args.fitSignal:
if "jes" in systematics:
datacard.write("alpha_jes param 0.0 1.0\n")
if "jer" in systematics:
datacard.write("alpha_jer param 0.0 1.0\n")
else:
if "jes" in systematics:
datacard.write('JES shape 1 -\n')
if "jer" in systematics:
datacard.write('JER shape 1 -\n')
# flat parameters --- flat prior
datacard.write('background_' + fit_function +
'_norm flatParam\n')
if args.decoBkg:
datacard.write('deco_eig1 flatParam\n')
datacard.write('deco_eig2 flatParam\n')
else:
for par_name, par in background_parameters[
fit_function].iteritems():
datacard.write(fit_function + "_" + par_name +
' flatParam\n')
datacard.close()
print "[create_datacards] INFO : Done with this datacard"
#print '>> Datacards and workspaces created and stored in %s/'%( os.path.join(os.getcwd(),args.output_path) )
print "All done."
r_max = args.r_max
else:
r_max = limit_p2sigma * 100 * 3.
print "Using r in [{}, {}]".format(r_min, r_max)
#min_logr = log(r_min, 10)
#max_logr = log(r_max, 10)
#logr_values = [min_logr + ((max_logr - min_logr)*i/(args.n_points - 1)) for i in range(args.n_points)]
r_values = [
r_min + ((r_max - r_min) * i / (args.n_points - 1))
for i in range(args.n_points)
]
name = "grid_{}_{}_{}_{}".format(analysis, model, mass,
postfix)
datacard = limit_config.get_datacard_filename(
analysis,
model,
mass,
args.fit_function,
fitSignal=True)
workspace = limit_config.get_workspace_filename(
analysis, model, mass, fitSignal=True)
setup_grid(name,
datacard,
workspace,
r_values,
run=True,
toysH=args.toysH,
iterations=args.iterations,
fork=args.fork)
if args.merge:
from joblib import Parallel, delayed
limit_p2sigma = limit_config.limit_p2sigma_estimates[analysis][model][mass]
limit_m2sigma = limit_config.limit_m2sigma_estimates[analysis][model][mass]
limit_range = limit_p2sigma - limit_m2sigma
if args.r_min:
r_min = args.r_min
else:
r_min = limit_m2sigma * 100 / 3.
if args.r_max:
r_max = args.r_max
else:
r_max = limit_p2sigma * 100 * 3.
print "Using r in [{}, {}]".format(r_min, r_max)
#min_logr = log(r_min, 10)
#max_logr = log(r_max, 10)
#logr_values = [min_logr + ((max_logr - min_logr)*i/(args.n_points - 1)) for i in range(args.n_points)]
r_values = [r_min + ((r_max - r_min)*i/(args.n_points-1)) for i in range(args.n_points)]
name = "grid_{}_{}_{}_{}".format(analysis, model, mass, postfix)
datacard = limit_config.get_datacard_filename(analysis, model, mass, args.fit_function, fitSignal=True)
workspace = limit_config.get_workspace_filename(analysis, model, mass, fitSignal=True)
setup_grid(name, datacard, workspace, r_values, run=True, toysH=args.toysH, iterations=args.iterations, fork=args.fork)
if args.merge:
from joblib import Parallel, delayed
for analysis in analyses:
if args.mass:
masses = [args.mass]
else:
masses = limit_config.limit_signal_masses[analysis]
Parallel(n_jobs=4)(delayed(merge)(analysis, model, mass, args.fit_function) for mass in masses for model in models)
def main():
# input parameters
parser = ArgumentParser(description='Script that runs limit calculation for specified mass points')
parser.add_argument("-M", "--method", dest="method", required=True,
choices=['MaxLikelihoodFit', 'ProfileLikelihood', 'HybridNew', 'Asymptotic', 'MarkovChainMC'],
help="Method to calculate upper limits",
metavar="METHOD")
parser.add_argument('--analyses', type=str, default="trigbbh_CSVTM,trigbbl_CSVTM", help="Analysis names")
parser.add_argument('--models', type=str, default="Hbb,RSG,ZPrime", help="Model names")
parser.add_argument('--qcd', action='store_true', help="Use QCD instead of data (assumes no trigger emulation)")
parser.add_argument('--correctTrigger', action='store_true', help="Use model with trigger correction (has to have been specified in create_datacards.py)")
parser.add_argument('--useMCTrigger', action='store_true', help="Use MC trigger")
parser.add_argument('--fitTrigger', action='store_true', help="Use model with trigger fit (has to have been specified in create_datacards.py)")
parser.add_argument('--fitOffB', action='store_true', help="Include a parametrization of offline b-tag efficiency in background PDF")
parser.add_argument('--fit_function', type=str, default="f4", help="Name of central fit function")
#parser.add_argument("-d", "--datacards_path", dest="datacards_path", required=True,
# help="Path to datacards and workspaces",
# metavar="DATA_HISTNAME")
#parser.add_argument("-f", "--final_state", dest="final_state", required=True,
# help="Final state (e.g. qq, qg, gg)",
# metavar="FINAL_STATE")
#parser.add_argument("-o", "--output_path", dest="output_path",
# default='logs',
# help="Output path where log files will be stored (default: %(default)s)",
# metavar="OUTPUT_PATH")
parser.add_argument("--rMin", dest="rMin", type=float, help="Minimum value for the signal strength")
parser.add_argument("--rMax", dest="rMax", type=float, help="Maximum value for the signal strength")
parser.add_argument("--rPrior", action="store_true", help="Take rMin and rMax from a previous iteration of limit setting.")
parser.add_argument("--rRelAcc", dest="rRelAcc", type=float, help="rRelAcc")
parser.add_argument("--rAbsAcc", dest="rAbsAcc", type=float, help="rAbsAcc")
parser.add_argument("--level", dest="level", type=float, help="Exp from grid level")
parser.add_argument("--toysH", dest="toysH", type=int, help="Number of Toy MC extractions for HybridNew")
parser.add_argument("--toys", dest="toys", type=int, help="Number of Toy MC extractions, not for HybridNew")
parser.add_argument("--tries", dest="tries", type=int, default=10, help="Number of times to run the MCMC (default: %(default)i)")
parser.add_argument("--robustFit", dest="robustFit", action='store_true', help="combine robustFit option")
parser.add_argument("--proposal", dest="proposal", default='ortho', help="Proposal function for MCMC (default: %(default)s)")
parser.add_argument("--noSyst", dest="noSyst", default=False, action="store_true", help="Run without systematic uncertainties")
parser.add_argument("--picky", dest="picky", default=False, action="store_true", help="combine picky mode")
parser.add_argument("--saveHybridResult", action="store_true", help="--saveHybridResult")
parser.add_argument("--strictBounds", dest="strictBounds", default=False, action="store_true", help="Strict bounds on rMax")
parser.add_argument("--testStat", type=str, help="Test statistics: LEP, TEV, LHC (previously known as Atlas), Profile.")
parser.add_argument("--freezeNuisances", dest="freezeNuisances", type=str, help="Freeze nuisance parameters")
parser.add_argument("--noHint", dest="noHint", default=False, action="store_true", help="Do not run the hint method")
parser.add_argument("--significance", dest="significance", default=False, action="store_true", help="Calculate significance instead of limits")
parser.add_argument("--frequentist", dest="freq", default=False, action="store_true", help="Frequentist hybridnew")
parser.add_argument("--fork", dest="forkvar", default=False, action="store_true", help="More cores")
parser.add_argument("--fitStrategy", dest="fitStrategy", type=int, help="Fit strategy (default: %(default).1f)")
parser.add_argument("--condor", dest="condor", default=False, action="store_true", help="Batch process using Condor")
parser.add_argument("--no_retar", dest='no_retar', action="store_true", help="If --condor is specified, this specifies no retar of src directory (use cached copy)")
parser.add_argument("--postfix", dest="postfix", default='', help="Postfix for the input and output file names (default: %(default)s)")
parser.add_argument("--hnsig", dest="hnsig", default=False, action="store_true", help="HybridNew Significance calc")
parser.add_argument("--hnsig2", dest="hnsig2", default=False, action="store_true", help="HybridNew Significance calc")
parser.add_argument("--minimizerTolerance", dest="minimizerTolerance", type=float, help="--minimizerTolerance option for combine")
parser.add_argument("--minimizerAlgoForMinos", dest="minimizerAlgoForMinos", type=str, help="--minimizerAlgoForMinos option for combine")
parser.add_argument("--minimizerToleranceForMinos", dest="minimizerToleranceForMinos", type=float, help="--minimizerToleranceForMinos option for combine")
parser.add_argument('-v', '--verbose', type=int, help='Verbosity of combine')
parser.add_argument('-m', '--masses', type=str, help='Manually specify masses (comma-separated list). Otherwise, taken from limit_configuration.')
parser.add_argument("--preFitValue", type=float, help="preFitValue option for combine")
parser.add_argument("--fitBonly", action="store_true", help="Use workspace created with fitBonly option")
#mass_group = parser.add_mutually_exclusive_group(required=True)
#mass_group.add_argument("--mass",
# type=int,
# nargs = '*',
# default = 1000,
# help="Mass can be specified as a single value or a whitespace separated list (default: %(default)i)"
# )
#mass_group.add_argument("--massrange",
# type=int,
# nargs = 3,
# help="Define a range of masses to be produced. Format: min max step",
# metavar = ('MIN', 'MAX', 'STEP')
# )
#mass_group.add_argument("--masslist",
# help = "List containing mass information"
# )
args = parser.parse_args()
analyses = args.analyses.split(",")
models = args.models.split(",")
# check if the output directory exists
#if not os.path.isdir( os.path.join(os.getcwd(), args.output_path) ):
# os.mkdir( os.path.join(os.getcwd(), args.output_path) )
#print os.getcwd()
# mass points for which resonance shapes will be produced
#masses = []
#if args.massrange != None:
# MIN, MAX, STEP = args.massrange
# masses = range(MIN, MAX+STEP, STEP)
#elif args.masslist != None:
# # A mass list was provided
# print "Will create mass list according to", args.masslist
# masslist = __import__(args.masslist.replace(".py",""))
# masses = masslist.masses
#else:
# masses = args.mass
# ## sort masses
#masses.sort()
masses = {}
if args.masses:
for analysis in analyses:
masses[analysis] = [int(x) for x in args.masses.split(",")]
else:
masses = limit_config.limit_signal_masses
method = args.method
if args.significance and method != 'ProfileLikelihood' and method != 'HybridNew':
print "** ERROR: ** For significance calculation the ProfileLikelihood or HybridNew method has to be used. Aborting."
sys.exit(1)
options = ''
if args.significance:
options = options + ' --significance'
if args.freq:
options = options + ' --frequentist'
if args.hnsig:
options = options + ' --significance --saveToys --fullBToys --saveHybridResult -T 500 -i 100 -s 123457'
if args.hnsig2:
options = options + ' --significance --readHybridResult --toysFile=input.root --expectedFromGrid=0.5'
if args.forkvar:
options = options + ' --fork 4'
if args.testStat:
options = options + ' --testStat ' + args.testStat
if args.level != None:
options = options + ' --expectedFromGrid=%f'%(args.level)
if args.fitStrategy:
options = options + ' --minimizerStrategy %i'%(args.fitStrategy)
if args.noSyst:
options = options + ' --systematics 0'
if args.freezeNuisances:
options = options + ' --freezeNuisances ' + args.freezeNuisances
if args.picky:
options = options + ' --picky '
if args.saveHybridResult:
options = options + " -- saveHybridResult "
if args.strictBounds:
options = options + ' --strictBounds '
if args.rAbsAcc:
options = options + " --rAbsAcc " + str(args.rAbsAcc) + " "
if args.rRelAcc:
options = options + " --rRelAcc " + str(args.rRelAcc) + " "
if args.verbose:
options = options + ' -v' + str(args.verbose)
if method != 'ProfileLikelihood' and method != 'MaxLikelihoodFit' and args.rMax == None and not args.noHint and not args.significance:
options = options + ' --hintMethod ProfileLikelihood'
if method == 'HybridNew' and args.toysH != None:
options = options + ' --toysH %i'%(args.toysH)
if args.toys:
options = options + ' --toys ' + str(args.toys)
if args.robustFit:
options = options + ' --robustFit 1'
if args.minimizerTolerance:
options += " --minimizerTolerance " + str(args.minimizerTolerance) + " "
if args.minimizerAlgoForMinos:
options += " --minimizerAlgoForMinos " + str(args.minimizerAlgoForMinos) + " "
if args.minimizerToleranceForMinos:
options += " --minimizerToleranceForMinos " + str(args.minimizerToleranceForMinos) + " "
if args.preFitValue:
options += " --preFitValue " + str(args.preFitValue) + " "
if args.rPrior:
# Take rMin and rMax from +/-2 sigma estimates from a previous iteration. This has to be done per-job, so do it later.
pass
else:
if args.rMin != None:
options = options + ' --rMin %f'%(args.rMin)
if args.rMax != None:
options = options + ' --rMax %f'%(args.rMax)
if method == 'MarkovChainMC':
options = options + ' --tries %i --proposal %s'%(args.tries, args.proposal)
prefix = 'limits'
if args.significance:
prefix = 'significance'
elif method == 'MaxLikelihoodFit':
prefix = 'signal_xs'
postfix = (('_' + args.postfix) if args.postfix != '' else '')
if args.noSyst:
postfix += "_noSyst"
if args.freezeNuisances:
postfix += "_" + args.freezeNuisances.replace(",", "_")
if args.fitTrigger:
postfix += "_fitTrigger"
if args.correctTrigger:
postfix += "_correctTrigger"
if args.useMCTrigger:
postfix += "_useMCTrigger"
if args.fitOffB:
postfix += "_fitOffB"
if args.qcd:
postfix += "_qcd"
if args.fitBonly:
postfix += "_fitBonly"
datacards_path = limit_config.paths["datacards"]
output_path = limit_config.paths["combine_logs"]
condor_path = limit_config.paths["condor"]
# change to the appropriate directory
if args.condor:
os.chdir(output_path)
else:
os.chdir(datacards_path)
first = True
for analysis in analyses:
for model in models:
for mass in masses[analysis]:
logName = '{}_{}_{}_{}_m{}{}_{}.log'.format(prefix, method, analysis, model, int(mass), postfix,args.fit_function)
job_name = "%s_%s_m%i%s_%s"%(analysis, model, int(mass),postfix,args.fit_function)
run_options = options + ' --name _%s_%s_m%i%s_%s --mass %i'%(analysis, model, int(mass),postfix,args.fit_function,int(mass))
if args.rPrior:
run_options += " --rMin " + str(limit_config.limit_m2sigma_estimates[analysis][model][mass] / 5. * 100.)
run_options += " --rMax " + str(limit_config.limit_p2sigma_estimates[analysis][model][mass] * 5. * 100.)
if method == "MaxLikelihoodFit":
# Save shapes and plots
run_options += " --saveWithUncertainties --saveShapes --plots --out plots_" + job_name
if args.condor:
cmd = "combine -M %s %s %s 2>&1 | tee %s"%(
method,
run_options,
os.path.basename(limit_config.get_datacard_filename(analysis, model, mass, args.fit_function, correctTrigger=args.correctTrigger, useMCTrigger=args.useMCTrigger, qcd=args.qcd, fitTrigger=args.fitTrigger, fitBonly=args.fitBonly, fitOffB=args.fitOffB)),
os.path.basename(os.path.join(('' if args.condor else output_path),logName)))
else:
cmd = "combine -M %s %s %s 2>&1 | tee %s"%(
method,
run_options,
limit_config.get_datacard_filename(analysis, model, mass, args.fit_function, correctTrigger=args.correctTrigger, useMCTrigger=args.useMCTrigger, qcd=args.qcd, fitTrigger=args.fitTrigger, fitBonly=args.fitBonly, fitOffB=args.fitOffB),
os.path.join(('' if args.condor else output_path),logName))
# if using Condor
if args.condor:
#submission_dir = limit_config.paths["condor"]
submission_dir = limit_config.paths["combine_logs"]
start_dir = os.getcwd()
os.chdir(submission_dir)
# create the executable script
bash_script_path = os.path.join(submission_dir,'run_%s_%s_%s_m%i%s.sh'%(method,analysis,model,int(mass),postfix))
#bash_content = bash_template
#bash_content = re.sub('DUMMY_CMD',cmd,bash_content)
bash_script = open(bash_script_path,'w')
bash_script.write("echo '" + cmd + "'\n")
if method == "MaxLikelihoodFit":
bash_script.write("mkdir -pv plots_" + job_name + "\n")
bash_script.write(cmd)
bash_script.close()
# Create the condor command
condor_command = "csub " + bash_script_path
files_to_transfer = []
files_to_transfer.append(bash_script_path)
files_to_transfer.append(limit_config.get_datacard_filename(analysis, model, mass, args.fit_function, correctTrigger=args.correctTrigger, useMCTrigger=args.useMCTrigger, qcd=args.qcd, fitTrigger=args.fitTrigger, fitBonly=args.fitBonly, fitOffB=args.fitOffB))
files_to_transfer.append(limit_config.get_workspace_filename(analysis, model, mass, correctTrigger=args.correctTrigger, useMCTrigger=args.useMCTrigger, qcd=args.qcd, fitTrigger=args.fitTrigger, fitBonly=args.fitBonly, fitOffB=args.fitOffB))
condor_command += " -F " + ",".join(files_to_transfer)
condor_command += " -l combine_{}_\$\(Cluster\)_\$\(Process\).log".format(logName)
condor_command += " -s submit_combine_{}_{}_{}.jdl".format(analysis, model, mass)
condor_command += " -d " + submission_dir
if method == "MaxLikelihoodFit":
condor_command += " -o plots_" + job_name + " "
condor_command += " --cmssw"
if not first or args.no_retar:
condor_command += " --no_retar "
print ">> Submitting job for %s %s resonance with m = %i GeV..."%(analysis,model, int(mass))
print "Submission command: "
print condor_command
os.system(condor_command)
print "---------------------------------------------------------------------------"
os.chdir(start_dir)
else:
print ">> Running combine for %s %s resonance with m = %i GeV..."%(analysis, model, int(mass))
print "---------------------------------------------------------------------------"
if method == "MaxLikelihoodFit":
os.system("mkdir -pv plots_" + job_name)
print "Running: " + cmd + "\n"
os.system(cmd)
if first:
first = False
def run_single_mass(args, mass):
print "[run_single_mass] INFO : Creating datacard and workspace for m = %i GeV..."%(int(mass))
if args.fit_functions == "all":
#fit_functions = ["dijet4", "dijet5", "modexp4", "polyx6", "atlas4", "atlas5", "polypower4", "rational3", "rational4"]
fit_functions = ["dijet4", "modexp4", "polyx6", "polypower4"]
else:
fit_functions = args.fit_functions.split(",")
# import ROOT stuff
from ROOT import gStyle, TFile, TH1F, TH1D, TGraph, kTRUE, kFALSE, TCanvas, TLegend, TPad, TLine
from ROOT import RooHist, RooRealVar, RooDataHist, RooArgList, RooArgSet, RooAddPdf, RooProdPdf, RooEffProd, RooFit, RooGenericPdf, RooWorkspace, RooMsgService, RooHistPdf, RooExtendPdf, RooFormulaVar
if not args.debug:
RooMsgService.instance().setSilentMode(kTRUE)
RooMsgService.instance().setStreamStatus(0,kFALSE)
RooMsgService.instance().setStreamStatus(1,kFALSE)
# Stuff
mjj = RooRealVar('mjj','mjj',float(args.massMin),float(args.massMax))
lumi = args.lumi
signalCrossSection = 1. # Set to 1 so that the limit on r can be interpreted as a limit on the signal cross section
# Input data file
if args.qcd:
data_sample = "QCD_TuneZ2star_8TeV_pythia6"
elif "trigbb" in args.analysis:
data_sample = "BJetPlusX_2012"
elif "trigmu" in args.analysis:
data_sample = "SingleMu_2012"
data_file_path = analysis_config.get_b_histogram_filename(args.analysis, data_sample)
if args.condor:
data_file_path = os.path.basename(data_file_path)
data_file = TFile(data_file_path)
hData_notrigcorr = data_file.Get("BHistograms/h_pfjet_mjj")
hData_notrigcorr.SetDirectory(0)
hData_name = hData_notrigcorr.GetName()
hData_notrigcorr.SetName(hData_name + "_notrigcorr")
# Trigger correction on data
if args.fitTrigger:
# Make trigger correction objects
trigeff_pt_formula, trigeff_vars = trigger_efficiency.get_var_formula(args.analysis, mjj)
trigeff_btag_var = RooRealVar("trigeff_btag", "trigeff_btag", 0., 1.)
trigeff_btag_var.setVal(trigger_efficiency.online_btag_eff[args.analysis][0])
trigeff_btag_var.setConstant()
trigeff_btag_formula = RooFormulaVar("trigeff_btag_formula", "@0", RooArgList(trigeff_btag_var))
#trigeff_btag_var.setConstant()
trigeff_total_formula = RooFormulaVar("trigeff_total_formula", "@0*@1", RooArgList(trigeff_btag_var, trigeff_pt_formula))
#for trigeff_var_name, trigeff_var in trigeff_vars.iteritems():
# trigeff_var.setConstant()
if args.correctTrigger:
# Apply trigger correction to data histogram
hData = CorrectTriggerEfficiency(hData_notrigcorr, args.analysis)
# Still need b-tagging efficiency to scale the MC
if not args.useMCTrigger:
trigeff_btag_var = RooRealVar("trigeff_btag", "trigeff_btag", 0., 1.)
trigeff_btag_var.setVal(trigger_efficiency.online_btag_eff[args.analysis][0])
trigeff_btag_var.setConstant()
trigeff_btag_formula = RooFormulaVar("trigeff_btag_formula", "@0", RooArgList(trigeff_btag_var))
# Use a RooRealVar instead! You want to be able to apply a systematic in combine.
# trigeff_btag_formula = RooFormulaVar("trigeff_btag_formula", str(trigger_efficiency.online_btag_eff[args.analysis][0]), RooArgList())
else:
hData = hData_notrigcorr
if args.qcd:
# For QCD, scale the histogram by the online b-tag trigger efficiency.
if args.analysis == "NoTrigger_eta1p7_CSVTM":
trigeff_btag_formula = RooFormulaVar("trigeff_btag_formula", str(trigger_efficiency.online_btag_eff["trigbbl_CSVTM"][0]), RooArgList())
elif args.analysis == "NoTrigger_eta2p2_CSVTM":
trigeff_btag_formula = RooFormulaVar("trigeff_btag_formula", str(trigger_efficiency.online_btag_eff["trigbbh_CSVTM"][0]), RooArgList())
if args.analysis == "NoTrigger_eta1p7_CSVTM":
hData.Scale(trigger_efficiency.online_btag_eff["trigbbl_CSVTM"][0])
elif args.analysis == "NoTrigger_eta2p2_CSVTM":
hData.Scale(trigger_efficiency.online_btag_eff["trigbbh_CSVTM"][0])
else:
print "[create_datacards_parallel] ERROR : QCD fit requested, but analysis != NoTrigger_etaXpY_CSVTM. I don't know what to do!"
sys.exit(1)
hData.SetName(hData_name)
rooDataHist = RooDataHist('rooDatahist','rooDatahist',RooArgList(mjj),hData)
if args.correctTrigger:
rooDataHist_notrigcorr = RooDataHist("rooDatahist_notrigcorr", "rooDatahist_notrigcorr", RooArgList(mjj), hData_notrigcorr)
# Get signal pdf * btag efficiency
if args.useMCTrigger:
signal_pdf_file = analysis_config.get_signal_fit_file(args.analysis, args.model, mass, "bukin", interpolated=(not mass in analysis_config.simulation.simulated_masses))
if args.condor:
signal_pdf_file = os.path.basename(signal_pdf_file)
print "[create_datacards] Loading fitted signal PDFs from " + signal_pdf_file
f_signal_pdfs = TFile(signal_pdf_file, "READ")
f_signal_pdfs.Print()
w_signal = f_signal_pdfs.Get("w_signal")
w_signal.Print()
bukin_pdf = w_signal.pdf("signal_bukin")
bukin_pdf.Print()
else:
if args.analysis == "trigbbl_CSVTM" or args.analysis == "NoTrigger_eta1p7_CSVTM":
notrig_analysis = "NoTrigger_eta1p7_CSVTM"
elif args.analysis == "trigbbh_CSVTM" or args.analysis == "NoTrigger_eta2p2_CSVTM":
notrig_analysis = "NoTrigger_eta2p2_CSVTM"
elif args.analysis == "trigbbl_CSVM" or args.analysis == "NoTrigger_eta1p7_CSVM":
notrig_analysis = "NoTrigger_eta1p7_CSVM"
elif args.analysis == "trigbbh_CSVM" or args.analysis == "NoTrigger_eta2p2_CSVM":
notrig_analysis = "NoTrigger_eta2p2_CSVM"
else:
print "[run_single_mass] ERROR : I don't know a no-trigger variant of analysis {}. Please make one, or specify --useMCTrigger.".format(args.analysis)
sys.exit(1)
print analysis_config.simulation.simulated_masses
signal_pdf_file = analysis_config.get_signal_fit_file(notrig_analysis, args.model, mass, "bukin", interpolated=(not mass in analysis_config.simulation.simulated_masses))
print "[create_datacards] Loading fitted signal PDFs from " + signal_pdf_file
if args.condor:
signal_pdf_file = os.path.basename(signal_pdf_file)
f_signal_pdfs = TFile(signal_pdf_file, "READ")
w_signal = f_signal_pdfs.Get("w_signal")
bukin_pdf = w_signal.pdf("signal")
bukin_pdf.SetName("signal_bukin")
input_signal_parameters = signal_fits.get_parameters(bukin_pdf)
# Make a new PDF with nuisance parameters
signal_pdf_notrig, signal_vars = signal_fits.make_signal_pdf_systematic("bukin", mjj, mass=mass)
signal_pdf_name = signal_pdf_notrig.GetName()
signal_pdf_notrig.SetName(signal_pdf_name + "_notrig")
# Add trigger efficiency
if args.useMCTrigger:
if args.fitTrigger:
# Online b-tagging eff incorporated in Bukin/acceptance, so signal pdf = Bukin * pT efficiency
signal_pdf = RooEffProd("signal", "signal", signal_pdf_notrig, trigeff_pt_formula)
elif args.correctTrigger:
# Signal PDF = bukin; b-tag efficiency already included in normalization
signal_pdf = signal_pdf_notrig
signal_pdf.SetName(signal_pdf_name)
else:
if args.fitTrigger:
# Signal PDF = bukin * total trigger efficiency
signal_pdf = RooEffProd("signal", "signal", signal_pdf_notrig, trigeff_total_formula)
elif args.correctTrigger:
if args.useMCTrigger:
signal_pdf = signal_pdf_notrig
signal_pdf.SetName("signal")
else:
# Signal PDF = bukin * btag efficiency
signal_pdf = RooEffProd("signal", "signal", signal_pdf_notrig, trigeff_btag_formula)
elif args.qcd:
# Signal PDF = bukin * btag efficiency
# Same as correctTrigger
signal_pdf = RooEffProd("signal", "signal", signal_pdf_notrig, trigeff_btag_formula)
# Copy input parameter values
signal_vars["xp_0"].setVal(input_signal_parameters["xp"][0])
signal_vars["xp_0"].setError(input_signal_parameters["xp"][1])
signal_vars["xp_0"].setConstant()
signal_vars["sigp_0"].setVal(input_signal_parameters["sigp"][0])
signal_vars["sigp_0"].setError(input_signal_parameters["sigp"][1])
signal_vars["sigp_0"].setConstant()
signal_vars["xi_0"].setVal(input_signal_parameters["xi"][0])
signal_vars["xi_0"].setError(input_signal_parameters["xi"][1])
signal_vars["xi_0"].setConstant()
signal_vars["rho1_0"].setVal(input_signal_parameters["rho1"][0])
signal_vars["rho1_0"].setError(input_signal_parameters["rho1"][1])
signal_vars["rho1_0"].setConstant()
signal_vars["rho2_0"].setVal(input_signal_parameters["rho2"][0])
signal_vars["rho2_0"].setError(input_signal_parameters["rho2"][1])
signal_vars["rho2_0"].setConstant()
f_signal_pdfs.Close()
signal_parameters = {}
signal_pdfs_notrig = {}
signal_pdfs = {}
signal_norms = {}
background_pdfs = {}
background_pdfs_notrig = {}
background_parameters = {}
background_norms = {}
signal_epdfs = {}
background_epdfs = {}
models = {}
fit_results = {}
if args.fitOffB:
# Load RooHistPdf
if "bbl" in args.analysis or "eta1p7" in args.analysis:
eta_region = "eta1p7"
offline_btag_eff_vars = {
"p0":RooRealVar("offline_btag_eff_p0", "offline_btag_eff_p0", 6.78251e-03, 6.78251e-03 - 10.*7.66906e-05, 6.78251e-03 + 10.*7.66906e-05),
"p1":RooRealVar("offline_btag_eff_p1", "offline_btag_eff_p1", -9.55614e-06, -9.55614e-06 - 10.*1.04286e-07, -9.55614e-06 + 10.*1.04286e-07),
"p2":RooRealVar("offline_btag_eff_p2", "offline_btag_eff_p2", 4.39468e-09, 4.39468e-09 - 1.e-07, 4.39468e-09 + 1.e-07),
}
offline_btag_eff_formula = RooFormulaVar("offline_btag_eff", "max(@0+(@1*@3)+(@2*@3*@3), 0.)", RooArgList(offline_btag_eff_vars["p0"], offline_btag_eff_vars["p1"], offline_btag_eff_vars["p2"], mjj))
elif "bbh" in args.analysis or "eta2p2" in args.analysis:
eta_region = "eta2p2"
offline_btag_eff_vars = {
"p0":RooRealVar("offline_btag_eff_p0", "offline_btag_eff_p0", -1.72721e-03, -1.72721e-03 - 10.*3.04992e-05, -1.72721e-03 + 10.*3.04992e-05),
"p1":RooRealVar("offline_btag_eff_p1", "offline_btag_eff_p1", 1.72562e-06, 1.72562e-06 - 10.*3.23472e-08, 1.72562e-06 + 10.*3.23472e-08),
"p2":RooRealVar("offline_btag_eff_p2", "offline_btag_eff_p2", 8.74866e-03, 8.74866e-03 - 10.*7.81413e-05, 8.74866e-03 + 10.*7.81413e-05),
"p3":RooRealVar("offline_btag_eff_p3", "offline_btag_eff_p3", -1.67123e-03, -1.67123e-03 - 10.*4.30607e-05, -1.67123e-03 + 10.*4.30607e-05),
}
offline_btag_eff_formula = RooFormulaVar("offline_btag_eff", "max(@0+@1*@4+ @2*exp(@3*@4), 0.)", RooArgList(offline_btag_eff_vars["p0"],offline_btag_eff_vars["p1"],offline_btag_eff_vars["p2"],offline_btag_eff_vars["p3"], mjj))
#f_offline_btag_eff = TFile(analysis_config.get_offline_btag_file("CSVTM", eta_region))
#h_offline_btag_eff = f_offline_btag_eff.Get("h_offline_btag_eff")
#print h_offline_btag_eff
#offline_btag_eff_rdh = RooDataHist("rdh_offline_btag_eff", "rdh_offline_btag_eff", RooArgList(mjj), h_offline_btag_eff)
#offline_btag_eff_pdf = RooHistPdf("pdf_offline_btag_eff", "pdf_offline_btag_eff", RooArgSet(mjj), offline_btag_eff_rdh)
for fit_function in fit_functions:
print "[create_datacards] INFO : On fit function {}".format(fit_function)
# Make a copy of the signal PDF, so that each fitTo call uses its own copy.
# The copy should have all variables set constant.
#signal_pdfs[fit_function], signal_parameters[fit_function] = signal_fits.copy_signal_pdf("bukin", signal_pdf, mjj, tag=fit_function, include_systematics=True)
signal_pdfs_notrig[fit_function] = ROOT.RooBukinPdf(signal_pdf_notrig, signal_pdf_notrig.GetName() + "_" + fit_function)
iterator = signal_pdfs_notrig[fit_function].getVariables().createIterator()
this_parameter = iterator.Next()
while this_parameter:
this_parameter.setConstant()
this_parameter = iterator.Next()
# Add trigger efficiency
if args.useMCTrigger:
if args.fitTrigger:
signal_pdfs[fit_function] = RooEffProd(signal_pdf.GetName() + "_" + fit_function, signal_pdf.GetName() + "_" + fit_function, signal_pdfs_notrig[fit_function], trigeff_pt_formula)
else:
signal_pdfs[fit_function] = signal_pdfs_notrig[fit_function]
signal_pdfs[fit_functions].SetName(signal_pdf.GetName() + "_" + fit_function)
elif args.fitTrigger:
# Signal PDF = bukin * total trigger efficiency
signal_pdfs[fit_function] = RooEffProd(signal_pdf.GetName() + "_" + fit_function, signal_pdf.GetName() + "_" + fit_function, signal_pdfs_notrig[fit_function], trigeff_total_formula)
elif args.correctTrigger:
# Signal PDF = bukin * btag efficiency
signal_pdfs[fit_function] = RooEffProd(signal_pdf.GetName() + "_" + fit_function, signal_pdf.GetName() + "_" + fit_function, signal_pdfs_notrig[fit_function], trigeff_btag_formula)
elif args.qcd:
# Signal PDF = bukin * btag efficiency
signal_pdfs[fit_function] = RooEffProd(signal_pdf.GetName() + "_" + fit_function, signal_pdf.GetName() + "_" + fit_function, signal_pdfs_notrig[fit_function], trigeff_btag_formula)
signal_norms[fit_function] = RooRealVar('signal_norm_' + fit_function, 'signal_norm_' + fit_function, 0., 0., 1e+05)
if args.fitBonly:
signal_norms[fit_function].setConstant()
# Make background PDF
background_pdfs_notrig[fit_function], background_parameters[fit_function] = make_background_pdf(fit_function, mjj, collision_energy=8000.)
background_pdf_name = background_pdfs_notrig[fit_function].GetName()
background_pdfs_notrig[fit_function].SetName(background_pdf_name + "_notrig")
if args.fitTrigger and args.fitOffB:
background_pdf_intermediate = RooEffProd(background_pdf_name + "_intermediate", background_pdf_name + "_intermediate", background_pdfs_notrig[fit_function], offline_btag_eff_formula)
background_pdfs[fit_function] = RooEffProd(background_pdf_name, background_pdf_name, background_pdf_intermediate, trigeff_pt_formula)
elif args.fitTrigger and not args.fitOffB:
background_pdfs[fit_function] = RooEffProd(background_pdf_name, background_pdf_name, background_pdfs_notrig[fit_function], trigeff_pt_formula)
elif args.fitOffB and not args.fitTrigger:
background_pdfs[fit_function] = RooEffProd(background_pdf_name, background_pdf_name, background_pdfs_notrig[fit_function], offline_btag_eff_formula)
else:
background_pdfs[fit_function] = background_pdfs_notrig[fit_function]
background_pdfs[fit_function].SetName(background_pdf_name)
# Initial values
if "trigbbh" in args.analysis:
if fit_function == "dijet4":
if mass == 650:
background_parameters[fit_function]["p1"].setVal(-2.2473e+01)
background_parameters[fit_function]["p2"].setVal(1.4923e+01)
background_parameters[fit_function]["p3"].setVal(1.3077e+00)
else:
background_parameters[fit_function]["p1"].setVal(-13.5877235358)
background_parameters[fit_function]["p2"].setVal(14.0659901462)
background_parameters[fit_function]["p3"].setVal(1.24550474025)
background_parameters[fit_function]["p1"].setMin(-50.)
background_parameters[fit_function]["p1"].setMax(50.)
elif fit_function == "f2":
background_parameters[fit_function]["p1"].setVal(6.06731321562)
background_parameters[fit_function]["p2"].setVal(6.06264502704)
elif fit_function == "polypower3":
background_parameters[fit_function]["p1"].setVal(50.0270215343)
background_parameters[fit_function]["p2"].setVal(8.17180937688)
background_parameters[fit_function]["p1"].setMin(20.)
elif fit_function == "polypower4":
background_parameters[fit_function]["p1"].setVal(31.3765210572)
background_parameters[fit_function]["p2"].setVal(-22.5800092219)
background_parameters[fit_function]["p3"].setVal(9.94548656557)
elif fit_function == "f5":
background_parameters[fit_function]["p1"].setVal(5.51929170927)
background_parameters[fit_function]["p2"].setVal(4.25521547671)
elif fit_function == "f6":
background_parameters[fit_function]["p1"].setVal(35.)
background_parameters[fit_function]["p2"].setVal(-28.)
background_parameters[fit_function]["p3"].setVal(0.)
background_parameters[fit_function]["p4"].setVal(10.)
elif "trigbbl" in args.analysis:
if fit_function == "dijet4":
background_parameters[fit_function]["p1"].setVal(-32.4727133488)
background_parameters[fit_function]["p2"].setVal(18.7641649883)
background_parameters[fit_function]["p3"].setVal(1.84028034937)
elif fit_function == "f2":
background_parameters[fit_function]["p1"].setVal(4.96261586452)
background_parameters[fit_function]["p2"].setVal(19.0848105961)
if fit_function == "polypower3":
background_parameters[fit_function]["p1"].setVal(60.0000032579)
background_parameters[fit_function]["p2"].setVal(8.00317534363)
background_parameters[fit_function]["p1"].setMin(60.)
elif fit_function == "polypower4":
background_parameters[fit_function]["p1"].setVal(25.4109169544)
background_parameters[fit_function]["p2"].setVal(-42.56719661)
background_parameters[fit_function]["p3"].setVal(12.3295648189)
elif fit_function == "f5":
background_parameters[fit_function]["p1"].setVal(3.74859358646)
background_parameters[fit_function]["p2"].setVal(11.4366903839)
elif fit_function == "f6":
background_parameters[fit_function]["p1"].setVal(35.)
background_parameters[fit_function]["p2"].setVal(-43.)
background_parameters[fit_function]["p3"].setVal(0.)
background_parameters[fit_function]["p4"].setVal(10.)
data_integral = hData.Integral(hData.GetXaxis().FindBin(float(args.massMin)),hData.GetXaxis().FindBin(float(args.massMax)))
background_norms[fit_function] = RooRealVar('background_' + fit_function + '_norm', 'background_' + fit_function + '_norm', data_integral, 0., 1.e8)
signal_epdfs[fit_function] = RooExtendPdf('esignal_' + fit_function, 'esignal_' + fit_function, signal_pdfs[fit_function], signal_norms[fit_function])
background_epdfs[fit_function] = RooExtendPdf('ebackground_' + fit_function, 'ebackground_' + fit_function, background_pdfs[fit_function], background_norms[fit_function])
models[fit_function] = RooAddPdf('model_' + fit_function, 's+b', RooArgList(background_epdfs[fit_function], signal_epdfs[fit_function]))
if args.runFit and not args.dconly:
print "[create_datacards] INFO : Starting fit with function {}".format(fit_function)
models[fit_function].Print()
# Fix the trigger efficiency for this fit
if args.fitTrigger:
trigeff_vars["alpha_trigeff_p0"].setConstant(True)
trigeff_vars["alpha_trigeff_p1"].setConstant(True)
trigeff_btag_var.setConstant(True)
if args.fitOffB:
for var in offline_btag_eff_vars.values():
var.setConstant(True)
fit_results[fit_function] = models[fit_function].fitTo(rooDataHist, RooFit.Save(kTRUE), RooFit.Extended(kTRUE), RooFit.Strategy(args.fitStrategy), RooFit.Verbose(0))
print "[create_datacards] INFO : Done with fit {}. Printing results.".format(fit_function)
fit_results[fit_function].Print()
if args.fitTrigger:
# Current strategy: freeze the trigger nuisance parameters.
trigeff_vars["alpha_trigeff_p0"].setConstant(True)
trigeff_vars["alpha_trigeff_p1"].setConstant(True)
trigeff_btag_var.setConstant(True)
if args.fitOffB:
for var in offline_btag_eff_vars.values():
var.setConstant(False)
print "[create_datacards] DEBUG : End args.runFit if block."
# needed if want to evaluate limits without background systematics
if args.fixBkg:
background_norms[fit_function].setConstant()
for par_name, par in background_parameters[fit_function].iteritems():
par.setConstant()
# -----------------------------------------
# Set values of signal systematic variables
# JES and JER uncertainties
if "jes" in systematics:
xp_central = signal_vars["xp_0"].getVal()
xp_up = signal_fits.get_parameters(w_signal.pdf("signal__JESUp"))["xpJESUp"][0]
xp_down = signal_fits.get_parameters(w_signal.pdf("signal__JESDown"))["xpJESDown"][0]
signal_vars["dxp"].setVal(max(abs(xp_up - xp_central), abs(xp_down - xp_central)))
if signal_vars["dxp"].getVal() > 2 * mass * 0.1:
print "[create_datacards] WARNING : Large dxp value. dxp = {}, xp_down = {}, xp_central = {}, xp_up = {}".format(signal_vars["dxp"].getVal(), xp_down, xp_central, xp_up)
signal_vars["alpha_jes"].setVal(0.)
signal_vars["alpha_jes"].setConstant(False)
else:
signal_vars["dxp"].setVal(0.)
signal_vars["alpha_jes"].setVal(0.)
signal_vars["alpha_jes"].setConstant()
signal_vars["dxp"].setError(0.)
signal_vars["dxp"].setConstant()
if "jer" in systematics:
sigp_central = signal_vars["sigp_0"].getVal()
sigp_up = signal_fits.get_parameters(w_signal.pdf("signal__JERUp"))["sigpJERUp"][0]
sigp_down = signal_fits.get_parameters(w_signal.pdf("signal__JERDown"))["sigpJERDown"][0]
signal_vars["dsigp"].setVal(max(abs(sigp_up - sigp_central), abs(sigp_down - sigp_central)))
signal_vars["alpha_jer"].setVal(0.)
signal_vars["alpha_jer"].setConstant(False)
else:
signal_vars["dsigp"].setVal(0.)
signal_vars["alpha_jer"].setVal(0.)
signal_vars["alpha_jer"].setConstant()
signal_vars["dsigp"].setError(0.)
signal_vars["dsigp"].setConstant()
# -----------------------------------------
# create a datacard and corresponding workspace
postfix = (('_' + args.postfix) if args.postfix != '' else '')
wsName = 'workspace_' + args.final_state + '_m' + str(mass) + postfix + '.root'
if not args.dconly:
w = RooWorkspace('w','workspace')
signal_pdf.SetName("signal")
getattr(w,'import')(signal_pdf,RooFit.Rename("signal"))
norm = args.lumi
signal_norm = ROOT.RooRealVar("signal_norm", "signal_norm", norm/100., norm/100. / 10., norm * 10.)
print "[create_datacards] INFO : Set signal norm to {}".format(signal_norm.getVal())
signal_norm.setConstant()
getattr(w,'import')(signal_norm,ROOT.RooCmdArg())
for fit_function in fit_functions:
print "Importing background PDF"
print background_pdfs[fit_function]
background_pdfs[fit_function].Print()
getattr(w,'import')(background_pdfs[fit_function],ROOT.RooCmdArg(),RooFit.Rename("background_" + fit_function), RooFit.RecycleConflictNodes())
w.pdf("background_" + fit_function).Print()
getattr(w,'import')(background_norms[fit_function],ROOT.RooCmdArg(),RooFit.Rename("background_" + fit_function + "_norm"))
getattr(w,'import')(fit_results[fit_function])
getattr(w,'import')(signal_norms[fit_function],ROOT.RooCmdArg())
if args.fitBonly:
getattr(w,'import')(models[fit_function],ROOT.RooCmdArg(),RooFit.RecycleConflictNodes())
getattr(w,'import')(rooDataHist,RooFit.Rename("data_obs"))
if args.correctTrigger:
getattr(w,'import')(rooDataHist_notrigcorr, RooFit.Rename("data_obs_notrigcorr"))
w.Print()
print "Starting save"
if args.output_path:
if not os.path.isdir( os.path.join(os.getcwd(),args.output_path) ):
os.mkdir( os.path.join(os.getcwd(),args.output_path) )
workspace_output_path = os.path.join(args.output_path,wsName)
else:
workspace_output_path = limit_config.get_workspace_filename(args.analysis, args.model, mass, fitBonly=args.fitBonly, fitTrigger=args.fitTrigger, correctTrigger=args.correctTrigger, useMCTrigger=args.useMCTrigger, qcd=args.qcd, fitOffB=args.fitOffB)
if args.condor:
workspace_output_path = os.path.basename(workspace_output_path)
print "[create_datacards] INFO : Writing workspace to file {}".format(workspace_output_path)
w.writeToFile(workspace_output_path)
if args.correctTrigger:
f_workspace = TFile(workspace_output_path, "UPDATE")
hData.Write()
hData_notrigcorr.Write()
# Clean up
for name, obj in signal_norms.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_pdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_pdfs_notrig.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_norms.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in signal_pdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in signal_pdfs_notrig.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in signal_epdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in background_epdfs.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in fit_results.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, dict_l2 in background_parameters.iteritems():
for name2, obj in dict_l2.iteritems():
if obj:
obj.IsA().Destructor(obj)
for name, obj in models.iteritems():
if obj:
obj.IsA().Destructor(obj)
rooDataHist.IsA().Destructor(rooDataHist)
if not args.dconly:
w.IsA().Destructor(w)
# Make datacards only if S+B fitted
#beffUnc = 0.3
boffUnc = systematics["boff"][args.analysis][args.model].Eval(mass)
pdfUnc = systematics["pdfunc"][args.analysis][args.model].Eval(mass)
for fit_function in fit_functions:
if args.output_path:
dcName = 'datacard_' + args.final_state + '_m' + str(mass) + postfix + '_' + fit_function + '.txt'
datacard_output_path = os.path.join(args.output_path,dcName)
else:
datacard_output_path = limit_config.get_datacard_filename(args.analysis, args.model, mass, fit_function, fitTrigger=args.fitTrigger, correctTrigger=args.correctTrigger, useMCTrigger=args.useMCTrigger, qcd=args.qcd, fitOffB=args.fitOffB, fitBonly=args.fitBonly)
if args.condor:
datacard_output_path = os.path.basename(datacard_output_path)
print "[create_datacards] INFO : Writing datacard to file {}".format(datacard_output_path)
datacard = open(datacard_output_path, 'w')
datacard.write('imax 1\n')
datacard.write('jmax 1\n')
datacard.write('kmax *\n')
datacard.write('---------------\n')
if args.output_path:
datacard.write('shapes * * '+wsName+' w:$PROCESS\n')
else:
datacard.write('shapes * * '+os.path.basename(limit_config.get_workspace_filename(args.analysis, args.model, mass, fitTrigger=args.fitTrigger, correctTrigger=args.correctTrigger, useMCTrigger=args.useMCTrigger, qcd=args.qcd, fitOffB=args.fitOffB, fitBonly=args.fitBonly))+' w:$PROCESS\n')
datacard.write('---------------\n')
datacard.write('bin 1\n')
datacard.write('observation -1\n')
datacard.write('------------------------------\n')
datacard.write('bin 1 1\n')
datacard.write('process signal background_' + fit_function + '\n')
datacard.write('process 0 1\n')
datacard.write('rate 1 1\n')
datacard.write('------------------------------\n')
datacard.write('lumi lnN %f -\n'%(1.+systematics["luminosity"]))
if not args.useMCTrigger:
datacard.write('bon lnN %f -\n'%(1.+ (trigger_efficiency.online_btag_eff[args.analysis][2] / trigger_efficiency.online_btag_eff[args.analysis][0])))
else:
datacard.write('bon lnN %f -\n'%(1.+ systematics["bon"]))
#datacard.write('beff lnN %f -\n'%(1.+beffUnc))
datacard.write('boff lnN %f -\n'%(1.+boffUnc))
datacard.write('pdf lnN %f -\n'%(1.+pdfUnc))
#datacard.write('bkg lnN - 1.03\n')
if "jes" in systematics:
datacard.write("alpha_jes param 0.0 1.0\n")
if "jer" in systematics:
datacard.write("alpha_jer param 0.0 1.0\n")
if args.fitOffB:
if eta_region == "eta1p7":
datacard.write("offline_btag_eff_p0 param 6.78251e-03 3.82505e-04\n")
datacard.write("offline_btag_eff_p1 param -9.55614e-06 1.13679e-06\n")
datacard.write("offline_btag_eff_p2 param 4.39468e-09 7.90724e-10\n")
elif eta_region == "eta2p2":
datacard.write("offline_btag_eff_p0 param -1.72721e-03 3.04992e-05\n")
datacard.write("offline_btag_eff_p1 param 1.72562e-06 3.23472e-08\n")
datacard.write("offline_btag_eff_p2 param 8.74866e-03 7.81413e-05\n")
datacard.write("offline_btag_eff_p3 param -1.67123e-03 4.30607e-05\n")
# Current decision: don't put in nuisance parameters for trigger efficiency sigmoid. Impact is likely small.
#if args.fitTrigger:
# if "bbl" in args.analysis or "eta1p7" in args.analysis:
# datacard.write("alpha_trigeff_p0 param {} {}\n".format(0.0, 1.0))
# datacard.write("alpha_trigeff_p1 param {} {}\n".format(0.0, 1.0))
# Background fit parameters --- flat prior
datacard.write('background_' + fit_function + '_norm flatParam\n')
for par_name, par in background_parameters[fit_function].iteritems():
datacard.write(fit_function + "_" + par_name + ' flatParam\n')
datacard.close()
print "[create_datacards] INFO : Done with this datacard"
#print '>> Datacards and workspaces created and stored in %s/'%( os.path.join(os.getcwd(),args.output_path) )
print "Done with mass {}.".format(mass)