def GetSingleMuHistograms(self):
#this_analyses = ["trigmu_highmass_CSVTM", "trigmu_lowmass_CSVTM", "trigmubbh_highmass_CSVTM", "trigmubbl_lowmass_CSVTM", "trigmubbll_lowmass_CSVTM", "trigmu24i_lowmass_CSVTM", "trigmu24ibbl_lowmass_CSVTM", "trigmu24ibbll_lowmass_CSVTM", "trigmu40_lowmass_CSVTM", "trigmu40bbl_lowmass_CSVTM", "trigmu40bbll_lowmass_CSVTM"]
this_analyses = ["trigmu24i_lowmass_CSVTM", "trigmu24ibbl_lowmass_CSVTM"]
this_analyses.extend(["trigmu24i_highmass_CSVTM", "trigmu24ibbh_highmass_CSVTM"])
for analysis in this_analyses:
print "Opening " + analysis_config.get_b_histogram_filename(analysis, "SingleMu_2012")
f = ROOT.TFile(analysis_config.get_b_histogram_filename(analysis, "SingleMu_2012"), "READ")
self._mjj_histograms_fine[analysis] = f.Get("BHistograms/h_pfjet_mjj")
self._mjj_histograms_fine[analysis].SetName("h_" + analysis + "_mjj_fine")
self._mjj_histograms_fine[analysis].SetDirectory(0)
self._mjj_histograms[analysis] = histogram_tools.rebin_histogram(self._mjj_histograms_fine[analysis], self._mass_bins, normalization_bin_width=1)
self._mjj_histograms[analysis].SetName("h_" + analysis + "_mjj")
self._mjj_histograms[analysis].SetDirectory(0)
if not "highmass" in analysis:
self._mjj_histograms_csvorder[analysis] = f.Get("BHistograms/h_pfjet_mjj_csvorder")
self._mjj_histograms_csvorder[analysis].SetName("h_" + analysis + "_mjj_csvorder")
self._mjj_histograms_csvorder[analysis].SetDirectory(0)
self._mjj_histograms_csvorder[analysis] = histogram_tools.rebin_histogram(self._mjj_histograms_csvorder[analysis], self._mass_bins, normalization_bin_width=1)
self._mjj_histograms_vetothirdjet[analysis] = f.Get("BHistograms/h_pfjet_mjj_vetothirdjet")
self._mjj_histograms_vetothirdjet[analysis].SetName("h_" + analysis + "_mjj_vetothirdjet")
self._mjj_histograms_vetothirdjet[analysis].SetDirectory(0)
self._mjj_histograms_vetothirdjet[analysis] = histogram_tools.rebin_histogram(self._mjj_histograms_vetothirdjet[analysis], self._mass_bins, normalization_bin_width=1)
if "bbll" in analysis:
self._mjj_histograms_fine[analysis].Scale(1.7) # Prescale for singlemu + 60/53. The prescale was not computer for these analyses.
self._mjj_histograms[analysis].Scale(1.7) # Prescale for singlemu + 60/53. The prescale was not computer for these analyses.
self._mjj_histograms_fine[analysis].Rebin(5)
self._analyses.append(analysis)
f.Close()
def RunBHistogramsBackground(analysis, sample, files_per_job=1, retar=False, data_source=None):
# Create working directory and cd
start_directory = os.getcwd()
working_directory = dijet_directory + "/data/EightTeeEeVeeBee/BHistograms/condor/submit_" + analysis + "_" + sample
os.system("mkdir -pv " + working_directory)
os.chdir(working_directory)
command = "condor_cmsRun"
if retar:
command += " --retar "
#input_txt = open("tmp.txt", 'w')
#input_txt.write(analysis_config.files_QCDBEventTree[sample] + "\n")
#input_txt.close()
command += " --file-list=" + analysis_config.files_QCDBEventTree[sample] + " "
command += " --files-per-job=" + str(files_per_job)
command += " --submit-file=submit_" + analysis + "_" + sample + ".jdl "
#command += " --output-file=" + output_prefix + "_" + sample + ".root "
command += " --output-tag=BHistograms_" + sample + " "
command += " --run "
command += " " + dijet_directory + "/CMSSW_5_3_32_patch3/src/MyTools/RootUtils/scripts/cmsRun_wrapper.sh " + analysis_config.analysis_cfgs[analysis]
command += " dataSource=simulation "
command += " dataType=background "
#command += "inputFiles=" + os.path.basename(input_files[sample])
output_filename = os.path.basename(analysis_config.get_b_histogram_filename(analysis, sample)).replace(".root", "_\$\(Cluster\)_\$\(Process\).root")
command += " outputFile=" + os.path.basename(analysis_config.get_b_histogram_filename(analysis, sample)).replace(".root", "_\$\(Cluster\)_\$\(Process\).root")
print command
os.system(command)
os.system("rm -f tmp.txt")
postprocessing_file = open('postprocessing.sh', 'w')
postprocessing_file.write("#!/bin/bash\n")
postprocessing_file.write("hadd " + working_directory + "/" + os.path.basename(analysis_config.get_b_histogram_filename(analysis, sample)) + " " + output_filename.replace("_\$\(Cluster\)_\$\(Process\)", "*") + "\n")
postprocessing_file.close()
# cd back
os.chdir(start_directory)
def __init__(self, numerator_analysis, denominator_analysis, samples):
print "[OfflineBTagPlots::__init__] Initializing with sr = " + sr + ", samples = ",
print samples
self._samples = samples
self._numerator_analysis = numerator_analysis
self._denominator_analysis = denominator_analysis
self._input_files = {"numerator":{}, "denominator":{}}
for sample in self._samples:
# For trigjetht, have to cobble together the frankenhist later.
if not (numerator_analysis == "trigjetht_eta1p7_CSVTM" or numerator_analysis == "trigjetht_eta2p2_CSVTM"):
print "Numerator input file = " + analysis_config.get_b_histogram_filename(self._numerator_analysis, sample)
self._input_files["numerator"][sample] = TFile(analysis_config.get_b_histogram_filename(self._numerator_analysis, sample))
if not (denominator_analysis == "trigjetht_eta1p7" or denominator_analysis == "trigjetht_eta2p2"):
print "Denominator input file = " + analysis_config.get_b_histogram_filename(self._denominator_analysis, sample)
self._input_files["denominator"][sample] = TFile(analysis_config.get_b_histogram_filename(self._denominator_analysis, sample))
def RunBHistogramsBackground(analysis,
sample,
files_per_job=1,
retar=False,
data_source=None):
# Create working directory and cd
start_directory = os.getcwd()
working_directory = dijet_directory + "/data/EightTeeEeVeeBee/BHistograms/condor/submit_" + analysis + "_" + sample
os.system("mkdir -pv " + working_directory)
os.chdir(working_directory)
command = "condor_cmsRun"
if retar:
command += " --retar "
#input_txt = open("tmp.txt", 'w')
#input_txt.write(analysis_config.files_QCDBEventTree[sample] + "\n")
#input_txt.close()
command += " --file-list=" + analysis_config.files_QCDBEventTree[
sample] + " "
command += " --files-per-job=" + str(files_per_job)
command += " --submit-file=submit_" + analysis + "_" + sample + ".jdl "
#command += " --output-file=" + output_prefix + "_" + sample + ".root "
command += " --output-tag=BHistograms_" + sample + " "
command += " --run "
command += " " + dijet_directory + "/CMSSW_5_3_32_patch3/src/MyTools/RootUtils/scripts/cmsRun_wrapper.sh " + analysis_config.analysis_cfgs[
analysis]
command += " dataSource=simulation "
command += " dataType=background "
#command += "inputFiles=" + os.path.basename(input_files[sample])
output_filename = os.path.basename(
analysis_config.get_b_histogram_filename(analysis, sample)).replace(
".root", "_\$\(Cluster\)_\$\(Process\).root")
command += " outputFile=" + os.path.basename(
analysis_config.get_b_histogram_filename(analysis, sample)).replace(
".root", "_\$\(Cluster\)_\$\(Process\).root")
print command
os.system(command)
os.system("rm -f tmp.txt")
postprocessing_file = open('postprocessing.sh', 'w')
postprocessing_file.write("#!/bin/bash\n")
postprocessing_file.write(
"hadd " + working_directory + "/" + os.path.basename(
analysis_config.get_b_histogram_filename(analysis, sample)) + " " +
output_filename.replace("_\$\(Cluster\)_\$\(Process\)", "*") + "\n")
postprocessing_file.close()
# cd back
os.chdir(start_directory)
def signal_acc_eff():
for analysis in ["trigbbh_CSVTM", "trigbbl_CSVTM"]:
if "bbl" in analysis:
mjj_range = [296, 1246]
elif "bbh" in analysis:
mjj_range = [526, 1455]
for model in ["Hbb", "RSG", "ZPrime"]:
for mass in [350, 400, 500, 600, 750, 900, 1200]:
if analysis == "trigbbh_CSVTM" and mass == 350:
continue
f = TFile(
analysis_config.get_b_histogram_filename(
analysis,
analysis_config.simulation.get_signal_tag(
model, mass, "FULLSIM"),
), "READ")
nevents = (f.Get("BHistograms/h_sample_nevents")).Integral()
h_mjj = f.Get("BHistograms/h_pfjet_mjj")
low_bin = h_mjj.GetXaxis().FindBin(mjj_range[0] + 1.e-5)
high_bin = h_mjj.GetXaxis().FindBin(mjj_range[1] - 1.e-5)
nsignal = h_mjj.Integral(low_bin, high_bin)
if nevents > 0:
acceff = 1. * nsignal / nevents
else:
acceff = 0.
print analysis + "\t&\t" + model + "\t&\t" + str(
mass) + "\t&\t" + str(nsignal) + "\t&\t" + str(
nevents) + "\t&\t" + str(acceff) + "\t\\\\\n"
def GetBJetPlusXHistograms(self):
this_analyses = ["trigbbh_CSVTM", "trigbbl_CSVTM", "trigbbll_CSVTM", "trigbbh_trigbbl_CSVTM"]
this_samples = ["BJetPlusX_2012", "BJetPlusX_2012BCD"]
for analysis in this_analyses:
for sample in this_samples:
name = analysis + "_" + sample
f = ROOT.TFile(analysis_config.get_b_histogram_filename(analysis, sample), "READ")
self._mjj_histograms_fine[name] = f.Get("BHistograms/h_pfjet_mjj")
self._mjj_histograms_fine[name].SetName("h_" + name + "_mjj_fine")
self._mjj_histograms_fine[name].SetDirectory(0)
self._mjj_histograms[name] = histogram_tools.rebin_histogram(self._mjj_histograms_fine[name], self._mass_bins, normalization_bin_width=1)
self._mjj_histograms[name].SetName("h_" + name + "_mjj")
self._mjj_histograms[name].SetDirectory(0)
self._mjj_histograms_csvorder[name] = f.Get("BHistograms/h_pfjet_mjj_csvorder")
self._mjj_histograms_csvorder[name].SetName("h_" + name + "_mjj_csvorder")
self._mjj_histograms_csvorder[name].SetDirectory(0)
self._mjj_histograms_csvorder[name] = histogram_tools.rebin_histogram(self._mjj_histograms_csvorder[name], self._mass_bins, normalization_bin_width=1)
self._mjj_histograms_vetothirdjet[name] = f.Get("BHistograms/h_pfjet_mjj_vetothirdjet")
self._mjj_histograms_vetothirdjet[name].SetName("h_" + name + "_mjj_vetothirdjet")
self._mjj_histograms_vetothirdjet[name].SetDirectory(0)
self._mjj_histograms_vetothirdjet[name] = histogram_tools.rebin_histogram(self._mjj_histograms_vetothirdjet[name], self._mass_bins, normalization_bin_width=1)
self._mjj_histograms_fine[name].Rebin(5)
self._analyses.append(name)
f.Close()
if "bbll" in analysis:
self._mjj_histograms[name].Scale(1.7)
self._mjj_histograms_fine[name].Scale(1.7)
def GetJetHTHistogram(self):
for sr_name in ["highmass", "lowmass"]:
analyses = {}
HT_slices = []
for mass in xrange(200, 600, 50):
HT_slices.append("HT" + str(mass))
analyses["HT" + str(mass)] = "trigjetht" + str(mass)
if sr_name == "lowmass":
analyses["HT" + str(mass)] += "_eta1p7"
analyses["HT" + str(mass)] += "_CSVTM"
sample = "JetHT_2012BCD"
HT_slice_histograms = {}
for HT_slice in HT_slices:
f = TFile(analysis_config.get_b_histogram_filename(analyses[HT_slice], sample), "READ")
HT_slice_histograms[HT_slice] = f.Get("BHistograms/h_pfjet_mjj")
print "On file " + analysis_config.get_b_histogram_filename(analyses[HT_slice], sample)
HT_slice_histograms[HT_slice].SetName(HT_slice_histograms[HT_slice].GetName() + "_" + analyses[HT_slice])
HT_slice_histograms[HT_slice].SetDirectory(0)
f.Close()
HT_slices.append("HTUnprescaled")
unprescaled_analysis_name = "trigjetht"
if sr_name == "lowmass":
unprescaled_analysis_name += "_eta1p7"
unprescaled_analysis_name += "_CSVTM"
analyses["HTUnprescaled"] = unprescaled_analysis_name
f_unprescaled = TFile(analysis_config.get_b_histogram_filename(unprescaled_analysis_name, sample), "READ")
HT_slice_histograms["HTUnprescaled"] = f_unprescaled.Get("BHistograms/h_pfjet_mjj")
HT_slice_histograms["HTUnprescaled"].SetName(HT_slice_histograms["HTUnprescaled"].GetName() + "_" + analyses["HTUnprescaled"])
HT_slice_histograms["HTUnprescaled"].SetDirectory(0)
f_unprescaled.Close()
ranges = {
"HT200":[220, 386],
"HT250":[386, 489],
"HT300":[489, 526],
"HT350":[526, 606],
"HT400":[606, 649],
"HT450":[649, 740],
"HT500":[740, 788],
"HT550":[788, 890],
#"HT650":[800, 890],
"HTUnprescaled":[890, 2000]
}
self._analyses.append("JetHT")
self._mjj_histograms_fine["JetHT"] = self.FrankenHist(HT_slices, HT_slice_histograms, ranges)
self._mjj_histograms["JetHT"] = histogram_tools.rebin_histogram(self._mjj_histograms_fine["JetHT"], self._mass_bins, normalization_bin_width=1)
self._mjj_histograms_fine["JetHT"].Rebin(5)
def __init__(self, numerator_analysis, denominator_analysis, samples):
print "[OfflineBTagPlots::__init__] Initializing with sr = " + sr + ", samples = ",
print samples
self._samples = samples
self._numerator_analysis = numerator_analysis
self._denominator_analysis = denominator_analysis
self._input_files = {"numerator": {}, "denominator": {}}
for sample in self._samples:
# For trigjetht, have to cobble together the frankenhist later.
if not (numerator_analysis == "trigjetht_eta1p7_CSVTM"
or numerator_analysis == "trigjetht_eta2p2_CSVTM"):
print "Numerator input file = " + analysis_config.get_b_histogram_filename(
self._numerator_analysis, sample)
self._input_files["numerator"][sample] = TFile(
analysis_config.get_b_histogram_filename(
self._numerator_analysis, sample))
if not (denominator_analysis == "trigjetht_eta1p7"
or denominator_analysis == "trigjetht_eta2p2"):
print "Denominator input file = " + analysis_config.get_b_histogram_filename(
self._denominator_analysis, sample)
self._input_files["denominator"][sample] = TFile(
analysis_config.get_b_histogram_filename(
self._denominator_analysis, sample))
"QCD_Pt-800to1000_TuneZ2star_8TeV_pythia6",
"QCD_Pt-1000to1400_TuneZ2star_8TeV_pythia6",
"QCD_Pt-1400to1800_TuneZ2star_8TeV_pythia6",
"QCD_Pt-1800_TuneZ2star_8TeV_pythia6"
]
analyses = [
"NoTrigger_eta2p2", "NoTrigger_eta2p2_CSVTM", "NoTrigger_eta1p7",
"NoTrigger_eta1p7_CSVTM", "trigbbl_CSVTM", "trigbbh_CSVTM"
]
lumi = 19710.
for analysis in analyses:
first = True
output_file = TFile(
analysis_config.get_b_histogram_filename(
analysis, "QCD_TuneZ2star_8TeV_pythia6"), "RECREATE")
output_directory = output_file.mkdir("BHistograms")
histograms = {}
for sample in qcd_samples:
input_file = TFile(
analysis_config.get_b_histogram_filename(analysis, sample), "READ")
input_directory = input_file.Get("BHistograms")
input_directory.cd()
xsec = analysis_config.simulation.background_cross_sections[sample]
normalization = xsec * lumi / input_file.Get(
"BHistograms/h_sample_nevents").Integral()
for key in gDirectory.GetListOfKeys():
key.Print()
if "TH1" in key.GetClassName() or "TH2" in key.GetClassName():
hist = key.ReadObj()
hist.Scale(normalization)
args = parser.parse_args()
print args
if args.ht:
analyses = {}
names = []
for mass in xrange(200, 700, 50):
if mass == 600:
continue
names.append("HT" + str(mass))
analyses["HT" + str(mass)] = "trigjetht" + str(mass)
sample = "JetHT_2012BCD"
histograms = {}
for name in names:
f = TFile(
analysis_config.get_b_histogram_filename(
analyses[name], sample), "READ")
#histograms[name] = mjj_common.apply_dijet_binning_normalized(f.Get("BHistograms/h_pfjet_mjj"))
print "[debug] For name " + name + ", input events = " + str(
f.Get("BHistograms/h_input_nevents").GetEntries())
print "[debug] \tPrescale = " + str(
f.Get("BHistograms/h_pass_nevents_weighted").GetBinContent(1) /
f.Get("BHistograms/h_pass_nevents").GetBinContent(1))
histograms[name] = f.Get("BHistograms/h_pfjet_mjj").Rebin(20)
histograms[name].SetName(histograms[name].GetName() + "_" + name)
histograms[name].SetDirectory(0)
f.Close()
ht_threshold_plot(names,
histograms,
save_tag="jetht_thresholds",
x_range=[0., 1200.],
logy=True)
style_counter = 0
for name in names:
histograms[name].SetLineWidth(2)
histograms[name].SetLineColor(seaborn.GetColorRoot("dark", style_counter))
histograms[name].Draw("hist same")
#histograms[name].Draw("hist same")
l.AddEntry(histograms[name], name, "pl")
style_counter += 1
l.Draw()
c.SaveAs(analysis_config.figure_directory + "/" + c.GetName() + ".pdf")
if __name__ == "__main__":
for model in ["Hbb", "RSG"]:
for mass_point in [600, 750, 900, 1200]:
f1 = TFile(analysis_config.get_b_histogram_filename("trigbbh_CSVTM", analysis_config.simulation.get_signal_tag(model, mass_point, "FULLSIM")), "READ")
f2 = TFile(analysis_config.get_b_histogram_filename("trigbbh_CSVTM_bfat", analysis_config.simulation.get_signal_tag(model, mass_point, "FULLSIM")))
histograms = {}
histograms["ak5"] = f1.Get("BHistograms/h_pfjet_mjj")
histograms["ak5"].SetName("h_ak5_" + model + "_" + str(mass_point))
histograms["ak5"].SetDirectory(0)
histograms["Fat, #DeltaR=1.1, p_{T}=30 GeV"] = f1.Get("BHistograms/h_fatjet_mjj")
histograms["Fat, #DeltaR=1.1, p_{T}=30 GeV"].SetName("h_fat1p1_" + model + "_" + str(mass_point))
histograms["Fat, #DeltaR=1.1, p_{T}=30 GeV"].SetDirectory(0)
histograms["Fat, #DeltaR=0.8, p_{T}=15 GeV"] = f2.Get("BHistograms/h_fatjet_mjj")
histograms["Fat, #DeltaR=0.8, p_{T}=15 GeV"].SetName("h_fat0p8_" + model + "_" + str(mass_point))
histograms["Fat, #DeltaR=0.8, p_{T}=15 GeV"].SetDirectory(0)
data_samples = args.data_samples.split(",")
signal_samples = []
if args.signal_samples == "all":
for signal_model in ["Hbb", "RSG"]:
for mass in [600, 750, 900, 1200]:
signal_samples.append(analysis_config.simulation.get_signal_tag(signal_model, mass, "FULLSIM"))
elif args.signal_samples:
signal_samples = args.signal_samples.split(",")
f_data = {}
f_signal = {}
for analysis in analyses:
f_data[analysis] = {}
for data_sample in data_samples:
f_data[analysis][data_sample] = TFile(analysis_config.get_b_histogram_filename(analysis, data_sample), "READ")
f_signal[analysis] = {}
for signal_sample in signal_samples:
f_signal[analysis][signal_sample] = TFile(analysis_config.get_b_histogram_filename(analysis, signal_sample), "READ")
if args.mjj:
for analysis in analyses:
for data_sample in data_samples:
save_file = TFile("/uscms/home/dryu/Dijets/data/EightTeeEeVeeBee/Results/mjj_fits_" + analysis + "_" + data_sample + ".root", "RECREATE")
if "trigbbl" in analysis:
fit_minima = {"pfjet":419.1}
elif "trigbbh" in analysis:
fit_minima = {"pfjet":526.1}
for jet_type in ["pfjet"]:
data_hist = f_data[analysis][data_sample].Get("BHistograms/h_" + jet_type + "_mjj")
import CMSDIJET.QCDAnalysis.mjj_fits
from CMSDIJET.QCDAnalysis.mjj_fits import *
import CMSDIJET.QCDAnalysis.analysis_configuration_8TeV as analysis_config
import CMSDIJET.QCDAnalysis.mjj_common as mjj_common
from CMSDIJET.QCDAnalysis.plots import AnalysisComparisonPlot
def f8(seq): # Dave Kirby
# Order preserving
seen = set()
return [x for x in seq if x not in seen and not seen.add(x)]
if __name__ == "__main__":
for analysis in ["lowmass", "highmass"]:
if analysis == "highmass":
f_bjetplusx = TFile(analysis_config.get_b_histogram_filename("trigbbh_CSVTM", "BJetPlusX_2012"), "READ")
f_singlemu = TFile(analysis_config.get_b_histogram_filename("mu_highmass_CSVTM", "SingleMu_2012"), "READ")
else:
f_bjetplusx = TFile(analysis_config.get_b_histogram_filename("trigbbl_CSVTM", "BJetPlusX_2012BCD"), "READ")
f_singlemu = TFile(analysis_config.get_b_histogram_filename("mu_lowmass_CSVTM", "SingleMu_2012"), "READ")
print "[debug] For BJetsPlusX_2012, input events = " + str(f_bjetplusx.Get("BHistograms/h_input_nevents").GetEntries())
print "[debug] For SingleMu_2012, input events = " + str(f_singlemu.Get("BHistograms/h_input_nevents").GetEntries())
bjetplusx_histogram = f_bjetplusx.Get("BHistograms/h_pfjet_mjj").Rebin(25)
bjetplusx_histogram.SetDirectory(0)
f_bjetplusx.Close()
singlemu_histogram = f_singlemu.Get("BHistograms/h_pfjet_mjj").Rebin(25)
singlemu_histogram.SetDirectory(0)
f_singlemu.Close()
# Normalize the histograms above 450 GeV
norm_low_bin = bjetplusx_histogram.GetXaxis().FindBin(450)
def RunBHistogramsSignal(analysis, sample, files_per_job=1, retar=False, data_source=None):
# Create working directory and cd
start_directory = os.getcwd()
working_directory = dijet_directory + "/data/EightTeeEeVeeBee/BHistograms/condor/submit_" + analysis + "_" + sample
os.system("mkdir -pv " + working_directory)
os.chdir(working_directory)
method = "csub"
if method == "csub":
input_files_txt = open(analysis_config.files_QCDBEventTree[sample], 'r')
input_files = [line.strip() for line in input_files_txt]
input_files_txt.close()
bash_script_path = working_directory + "/run_" + analysis + "_" + sample + ".sh"
bash_script = open(bash_script_path, 'w')
bash_script.write("#!/bin/bash\n")
bash_script.write("input_files=( " + " ".join([os.path.basename(x) for x in input_files]) + " )\n")
output_filename = os.path.basename(analysis_config.get_b_histogram_filename(analysis, sample)).replace(".root", "_$1.root")
bash_script.write("cmsRun "
+ os.path.basename(analysis_config.analysis_cfgs[analysis])
+ " dataSource=simulation"
+ " dataType=signal"
+ " signalMass=" + str(analysis_config.simulation.signal_sample_masses[sample])
+ " outputFile=" + output_filename
+ " inputFiles=file:${input_files[$1]}\n"
)
bash_script.close()
submit_command = "csub " + bash_script_path + " --cmssw "
if not retar:
submit_command += " --no_retar"
submit_command += " -F " + ",".join(input_files) + "," + analysis_config.analysis_cfgs[analysis] + " -n " + str(len(input_files))
os.system(submit_command)
else:
command = "condor_cmsRun"
if retar:
command += " --retar "
#input_txt = open("tmp.txt", 'w')
#input_txt.write(analysis_config.files_QCDBEventTree[sample] + "\n")
#input_txt.close()
command += " --file-list=" + analysis_config.files_QCDBEventTree[sample] + " "
command += " --files-per-job=" + str(files_per_job)
command += " --submit-file=submit_" + analysis + "_" + sample + ".jdl "
#command += " --output-file=" + output_prefix + "_" + sample + ".root "
command += " --output-tag=BHistograms_" + sample + " "
command += " --run "
command += " " + dijet_directory + "/CMSSW_5_3_32_patch3/src/MyTools/RootUtils/scripts/cmsRun_wrapper.sh " + analysis_config.analysis_cfgs[analysis]
command += " dataSource=simulation "
command += " dataType=signal "
command += " signalMass=" + str(analysis_config.simulation.signal_sample_masses[sample]) + " "
#command += "inputFiles=" + os.path.basename(input_files[sample])
if "ZPrime" in sample:
command += " bottomOnly=true "
output_filename = os.path.basename(analysis_config.get_b_histogram_filename(analysis, sample)).replace(".root", "_\$\(Cluster\)_\$\(Process\).root")
command += " outputFile=" + os.path.basename(analysis_config.get_b_histogram_filename(analysis, sample)).replace(".root", "_\$\(Cluster\)_\$\(Process\).root")
print command
os.system(command)
os.system("rm -f tmp.txt")
postprocessing_file = open('postprocessing.sh', 'w')
postprocessing_file.write("#!/bin/bash\n")
postprocessing_file.write("hadd " + working_directory + "/" + os.path.basename(analysis_config.get_b_histogram_filename(analysis, sample)) + " " + output_filename.replace("_\$\(Cluster\)_\$\(Process\)", "*").replace("$1", "*") + "\n")
postprocessing_file.close()
# cd back
os.chdir(start_directory)
print "\t\\label{table:X}\n",
print "\\end{tabular}\n",
print "\\end{table}\n",
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(description = 'Make tables from cutflow histograms')
#parser.add_argument('analysis', type=str, help='Analysis name')
#parser.add_argument('sample', type=str, help='Sample name')
args = parser.parse_args()
analyses = ["trigbbl_CSVTM", "trigbbh_CSVTM"]
samples = ["BJetPlusX_2012"]
for model in ["Hbb", "RSG"]:
for mass in [400, 500, 600, 750, 900, 1200]:
samples.append(analysis_config.simulation.get_signal_tag(model, mass, "FULLSIM"))
for analysis in analyses:
headers = []
cutflow_histograms = {}
for sample in samples:
headers.append(sample)
f = TFile(analysis_config.get_b_histogram_filename(analysis, sample), "READ")
cutflow_histograms[sample] = f.Get("BHistograms/CutFlowCounter_QCDEventSelector").Clone()
cutflow_histograms[sample].SetDirectory(0)
f.Close()
histogram_to_table(headers, cutflow_histograms, normalize=False, txt_file=analysis_config.figure_directory + "/cutflow_" + analysis + ".tex")
histogram_to_table(headers, cutflow_histograms, normalize=True, txt_file=analysis_config.figure_directory + "/cuteff_" + analysis + ".tex")
seaborn.GetColorRoot("dark", style_counter))
histograms[name].Draw("hist same")
#histograms[name].Draw("hist same")
l.AddEntry(histograms[name], name, "pl")
style_counter += 1
l.Draw()
c.SaveAs(analysis_config.figure_directory + "/" + c.GetName() + ".pdf")
if __name__ == "__main__":
for model in ["Hbb", "RSG"]:
for mass_point in [600, 750, 900, 1200]:
f1 = TFile(
analysis_config.get_b_histogram_filename(
"trigbbh_CSVTM",
analysis_config.simulation.get_signal_tag(
model, mass_point, "FULLSIM")), "READ")
f2 = TFile(
analysis_config.get_b_histogram_filename(
"trigbbh_CSVTM_bfat",
analysis_config.simulation.get_signal_tag(
model, mass_point, "FULLSIM")))
histograms = {}
histograms["ak5"] = f1.Get("BHistograms/h_pfjet_mjj")
histograms["ak5"].SetName("h_ak5_" + model + "_" + str(mass_point))
histograms["ak5"].SetDirectory(0)
histograms["Fat, #DeltaR=1.1, p_{T}=30 GeV"] = f1.Get(
"BHistograms/h_fatjet_mjj")
histograms["Fat, #DeltaR=1.1, p_{T}=30 GeV"].SetName(
"trigbbl_CSVTM": [400, 500, 600, 750],
"trigbbh_CSVTM": [600, 750, 900, 1200]
}
if args.mjj:
for analysis in analyses:
names = []
histograms = {}
colors = {}
styles = {}
for model in models:
color_counter = 0
for mass in masses[analysis]:
f = TFile(
analysis_config.get_b_histogram_filename(
analysis,
analysis_config.simulation.get_signal_tag(
model, mass, "FULLSIM")))
if model == "Hbb":
name = "H, m=" + str(mass) + " GeV"
elif model == "RSG":
name = "G, m=" + str(mass) + " GeV"
names.append(name)
histograms[name] = f.Get("BHistograms/h_pfjet_mjj")
histograms[name].SetDirectory(0)
histograms[name].Rebin(25)
histograms[name].Scale(1. / histograms[name].Integral())
f.Close()
if model == "Hbb":
styles[name] = 2
elif model == "RSG":
styles[name] = 3
plotter = OfflineBTagPlots(numerator_analysis, denominator_analysis, ["SingleMu_2012"])
plotter.EfficiencyPlot(var="mjj", logy=True, binning=dijet_binning, save_tag="_" + wp + "_" + sr + "_onbtag_singlemu", ratio_range=[0.,0.1], x_range=[0., 2000.], legend_position="topright", numerator_legend="With online b-tag", denominator_legend="Without online b-tag", ratio_title="Online b-tag efficiency (no offline CSV)")
if args.do_jetht:
for sr in ["lowmass", "highmass"]:
if sr == "lowmass":
numerator_analysis = "trigjetht_eta1p7_CSVTM"
denominator_analysis = "trigjetht_eta1p7"
else:
numerator_analysis = "trigjetht_eta2p2_CSVTM"
denominator_analysis = "trigjetht_eta2p2"
plotter = OfflineBTagPlots(numerator_analysis, denominator_analysis, ["JetHT_2012BCD"])
plotter.FrankenEfficiencyPlot(logy=True, binning=dijet_binning, save_tag="_JetHT_CSVTM_" + sr, ratio_range=[0.,0.01], x_range=[0., 2000.], legend_position="topright", numerator_legend="With offline b-tag", denominator_legend="Without offline b-tag", ratio_title="Offline b-tag efficiency)")
#for ht_slice in [200, 250, 300, 350, 400, 450, 500, 550, 650]:
# if sr == "lowmass":
# numerator_analysis = "trigjetht" + str(ht_slice) + "_eta1p7_CSVTM"
# denominator_analysis = "trigjetht" + str(ht_slice) + "_eta1p7"
# else:
# numerator_analysis = "trigjetht" + str(ht_slice) + "_CSVTM"
# denominator_analysis = "trigjetht" + str(ht_slice)
# plotter = OfflineBTagPlots(numerator_analysis, denominator_analysis, ["JetHT_2012BCD"])
# plotter.EfficiencyPlot(var="mjj", logy=True, binning=dijet_binning, save_tag="_CSVTM_" + sr + "_jetht" + str(ht_slice), ratio_range=[0.,0.01], x_range=[0., 2000.], legend_position="topright", numerator_legend="With offline b-tag", denominator_legend="Without offline b-tag", ratio_title="Offline b-tag efficiency", prescaled=True)
if args.do_singlejet:
for analysis in ["trigbbl_CSVTM", "trigbbh_CSVTM"]:
f = TFile(analysis_config.get_b_histogram_filename(analysis, "BJetPlusX_2012"), "READ")
h_mjj = histogram_tools.rebin_histogram(f.Get("BHistograms/h_pfjet_mjj"), dijet_binning)
h_mjj_btagcorr = histogram_tools.rebin_histogram(f.Get("BHistograms/h_pfjet_mjj_btagcorr"), dijet_binning)
EfficiencyPlot(h_mjj, h_mjj_btagcorr, name_num="No correction", name_den="b tag correction", logy=True, save_directory=analysis_config.figure_directory + "/OfflineBTag", save_tag="from_singlejet_"+analysis)
def FrankenEfficiencyPlot(self, logy=True, binning=None, simple_rebin=None, save_tag="", x_range=None, ratio_range=None, legend_position="topright", numerator_legend=None, denominator_legend=None, ratio_title=None):
ht_slices = ["HT200","HT250","HT300","HT350","HT400","HT450","HT500","HT550","HTUnprescaled"] # HT650
if self._numerator_analysis == "trigjetht_eta1p7_CSVTM":
numerator_analyses = {
"HT200":"trigjetht200_eta1p7_CSVTM",
"HT250":"trigjetht250_eta1p7_CSVTM",
"HT300":"trigjetht300_eta1p7_CSVTM",
"HT350":"trigjetht350_eta1p7_CSVTM",
"HT400":"trigjetht400_eta1p7_CSVTM",
"HT450":"trigjetht450_eta1p7_CSVTM",
"HT500":"trigjetht500_eta1p7_CSVTM",
"HT550":"trigjetht550_eta1p7_CSVTM",
#"HT650":"trigjetht650_eta1p7_CSVTM",
"HTUnprescaled":"trigjetht_eta1p7_CSVTM"
}
elif self._numerator_analysis == "trigjetht_eta2p2_CSVTM":
numerator_analyses = {
"HT200":"trigjetht200_CSVTM",
"HT250":"trigjetht250_CSVTM",
"HT300":"trigjetht300_CSVTM",
"HT350":"trigjetht350_CSVTM",
"HT400":"trigjetht400_CSVTM",
"HT450":"trigjetht450_CSVTM",
"HT500":"trigjetht500_CSVTM",
"HT550":"trigjetht550_CSVTM",
#"HT650":"trigjetht650_CSVTM",
"HTUnprescaled":"trigjetht_CSVTM"
}
else:
print "[OfflineBTagPlots::FrankenEfficiencyPlot] ERROR : numerator analysis must be trigjetht_eta1p7_CSVTM or trigjetht_eta2p2_CSVTM"
sys.exit(1)
if self._denominator_analysis == "trigjetht_eta1p7":
denominator_analyses = {
"HT200":"trigjetht200_eta1p7",
"HT250":"trigjetht250_eta1p7",
"HT300":"trigjetht300_eta1p7",
"HT350":"trigjetht350_eta1p7",
"HT400":"trigjetht400_eta1p7",
"HT450":"trigjetht450_eta1p7",
"HT500":"trigjetht500_eta1p7",
"HT550":"trigjetht550_eta1p7",
#"HT650":"trigjetht650_eta1p7",
"HTUnprescaled":"trigjetht_eta1p7"
}
elif self._denominator_analysis == "trigjetht_eta2p2":
denominator_analyses = {
"HT200":"trigjetht200",
"HT250":"trigjetht250",
"HT300":"trigjetht300",
"HT350":"trigjetht350",
"HT400":"trigjetht400",
"HT450":"trigjetht450",
"HT500":"trigjetht500",
"HT550":"trigjetht550",
#"HT650":"trigjetht650",
"HTUnprescaled":"trigjetht"
}
else:
print "[OfflineBTagPlots::FrankenEfficiencyPlot] ERROR : denominator analysis must be trigjetht_eta1p7 or trigjetht_eta2p2"
sys.exit(1)
ht_ranges = {
"HT200":[220, 386],
"HT250":[386, 489],
"HT300":[489, 526],
"HT350":[526, 606],
"HT400":[606, 649],
"HT450":[649, 740],
"HT500":[740, 788],
"HT550":[788, 890],
#"HT650":[890, 2000],
"HTUnprescaled":[890, 2000]
}
numerator_histogram = None
denominator_histogram = None
for sample in self._samples:
print "[EfficiencyPlot] DEBUG : Sample " + sample
numerator_slice_histograms = {}
denominator_slice_histograms = {}
for slice_name in ht_slices:
print slice_name
print analysis_config.get_b_histogram_filename(numerator_analyses[slice_name], sample)
numerator_file = TFile(analysis_config.get_b_histogram_filename(numerator_analyses[slice_name], sample), "READ")
print analysis_config.get_b_histogram_filename(denominator_analyses[slice_name], sample)
denominator_file = TFile(analysis_config.get_b_histogram_filename(denominator_analyses[slice_name], sample), "READ")
# Check input nevents
num_nevents = numerator_file.Get("BHistograms/h_input_nevents").Integral()
den_nevents = denominator_file.Get("BHistograms/h_input_nevents").Integral()
if num_nevents != den_nevents:
# Allow tiny differences...?
if abs((num_nevents - den_nevents) / den_nevents) < 0.001:
print "[EfficiencyPlot] ERROR : Small inconsistency between number of events between numerator and denominator. I'm going to rescale away the difference, but you may want to fix this."
numerator_normalization = den_nevents / num_nevents
denominator_normalization = 1.
else:
print "[EfficiencyPlot] ERROR : Inconsistent number of events between numerator and denominator. Results would be wrong, so I'm aborting."
print "[EfficiencyPlot] ERROR : \tNumerator = " + str(numerator_file.Get("BHistograms/h_input_nevents").Integral())
print "[EfficiencyPlot] ERROR : \tDenominator = " + str(denominator_file.Get("BHistograms/h_input_nevents").Integral())
sys.exit(1)
else:
numerator_normalization = 1.
denominator_normalization = 1.
numerator_slice_histograms[slice_name] = numerator_file.Get("BHistograms/h_pfjet_mjj")
numerator_slice_histograms[slice_name].SetName("h_pfjet_mjj_num_" + slice_name + "_" + sample)
numerator_slice_histograms[slice_name].SetDirectory(0)
numerator_slice_histograms[slice_name].Scale(numerator_normalization)
denominator_slice_histograms[slice_name] = denominator_file.Get("BHistograms/h_pfjet_mjj")
denominator_slice_histograms[slice_name].SetName("h_pfjet_mjj_den_" + slice_name + "_" + sample)
denominator_slice_histograms[slice_name].SetDirectory(0)
denominator_slice_histograms[slice_name].Scale(denominator_normalization)
numerator_file.Close()
denominator_file.Close()
# Make frankenhist
this_numerator_histogram = self.FrankenHist(ht_slices, numerator_slice_histograms, ht_ranges)
this_denominator_histogram = self.FrankenHist(ht_slices, denominator_slice_histograms, ht_ranges)
if not numerator_histogram:
numerator_histogram = this_numerator_histogram.Clone()
numerator_histogram.SetName(numerator_histogram.GetName() + save_tag + "_num_" + str(time.time()))
denominator_histogram = this_denominator_histogram.Clone()
denominator_histogram.SetName(denominator_histogram.GetName() + save_tag + "_num_" + str(time.time()))
else:
numerator_histogram.Add(this_numerator_histogram)
denominator_histogram.Add(this_denominator_histogram)
# Rebin
if binning:
numerator_histogram = histogram_tools.rebin_histogram(numerator_histogram, binning)
denominator_histogram = histogram_tools.rebin_histogram(denominator_histogram, binning)
elif simple_rebin:
numerator_histogram.Rebin(simple_rebin)
denominator_histogram.Rebin(simple_rebin)
cname = "c_offline_btag_eff_mjj"
if logy:
cname += "_log"
c = TCanvas(cname, "Offline b-tag #epsilon", 800, 1000)
top = TPad("top", "top", 0., 0.5, 1., 1.)
top.SetBottomMargin(0.02)
if logy:
top.SetLogy()
top.Draw()
top.cd()
frame_top = numerator_histogram.Clone()
frame_top.Reset()
if x_range:
frame_top.GetXaxis().SetRangeUser(x_range[0], x_range[1])
if logy:
y_min = 0.1
y_max = max(numerator_histogram.GetMaximum(), denominator_histogram.GetMaximum()) * 10.
else:
y_min = 0.
y_max = max(numerator_histogram.GetMaximum(), denominator_histogram.GetMaximum()) * 1.5
frame_top.SetMinimum(y_min)
frame_top.SetMaximum(y_max)
frame_top.GetXaxis().SetLabelSize(0)
frame_top.GetXaxis().SetTitleSize(0)
if binning:
#frame_top.GetYaxis().SetTitle("Events / 1 GeV")
frame_top.GetYaxis().SetTitle("Events")
else:
frame_top.GetYaxis().SetTitle("Events")
frame_top.Draw("axis")
print "numerator integral = " + str(numerator_histogram.Integral())
print "denominator integral = " + str(denominator_histogram.Integral())
numerator_histogram.SetMarkerStyle(20)
numerator_histogram.SetMarkerColor(seaborn.GetColorRoot("default", 0))
numerator_histogram.SetLineColor(seaborn.GetColorRoot("default", 0))
numerator_histogram.Draw("same")
denominator_histogram.SetMarkerStyle(24)
denominator_histogram.SetMarkerColor(seaborn.GetColorRoot("default", 2))
denominator_histogram.SetLineColor(seaborn.GetColorRoot("default", 2))
denominator_histogram.Draw("same")
if legend_position == "topright":
l = TLegend(0.6, 0.6, 0.85, 0.8)
elif legend_position == "bottomright":
l = TLegend(0.6, 0.2, 0.85, 0.4)
l.SetFillColor(0)
l.SetBorderSize(0)
if numerator_legend:
l.AddEntry(numerator_histogram, numerator_legend)
else:
l.AddEntry(numerator_histogram, "CSVT+CSVM")
if denominator_legend:
l.AddEntry(denominator_histogram, denominator_legend)
else:
l.AddEntry(denominator_histogram, "No CSV")
l.Draw()
c.cd()
bottom = TPad("bottom", "bottom", 0., 0., 1., 0.5)
bottom.SetTopMargin(0.01)
bottom.SetBottomMargin(0.2)
bottom.Draw()
bottom.cd()
ratio_histogram = numerator_histogram.Clone()
ratio_histogram.Reset()
if x_range:
ratio_histogram.GetXaxis().SetRangeUser(x_range[0], x_range[1])
ratio_histogram.SetName(numerator_histogram.GetName() + "_ratio_" + save_tag + str(time.time()))
ratio_histogram.SetDirectory(0)
for bin in xrange(1, numerator_histogram.GetNbinsX() + 1):
# Undo bin normalization
if numerator_histogram.GetBinError(bin) > 0 and denominator_histogram.GetBinError(bin) > 0:
num_unnormalized = (numerator_histogram.GetBinContent(bin))**2 / (numerator_histogram.GetBinError(bin))**2
den_unnormalized = (denominator_histogram.GetBinContent(bin))**2 / (denominator_histogram.GetBinError(bin))**2
num = numerator_histogram.GetBinContent(bin)
den = denominator_histogram.GetBinContent(bin)
ratio = 1. * num_unnormalized / den_unnormalized
ratio_err = sqrt(ratio * (1. - ratio) / den_unnormalized)
#ratio_err = max(sqrt(ratio * (1. - ratio) / den), 1./den)
else:
ratio = 0.
ratio_err = 0.
ratio_histogram.SetBinContent(bin, ratio)
ratio_histogram.SetBinError(bin, ratio_err)
ratio_histogram.SetMarkerSize(1)
ratio_histogram.SetMarkerColor(kBlack)
ratio_histogram.SetLineColor(kBlack)
ratio_histogram.SetLineWidth(2)
ratio_histogram.GetXaxis().SetTitle("m_{jj} [GeV]")
if ratio_title:
ratio_histogram.GetYaxis().SetTitle(ratio_title)
else:
ratio_histogram.GetYaxis().SetTitle("Offline 2#timesb-tag efficiency")
if ratio_range:
ratio_histogram.SetMinimum(ratio_range[0])
ratio_histogram.SetMaximum(ratio_range[1])
else:
ratio_histogram.SetMinimum(0.)
ratio_histogram.SetMaximum(1.)
ratio_histogram.Draw()
c.cd()
c.SaveAs(analysis_config.figure_directory + "/OfflineBTag/" + c.GetName() + save_tag + ".pdf")
ROOT.SetOwnership(c, False)
ROOT.SetOwnership(top, False)
ROOT.SetOwnership(bottom, False)
denominator_legend="Without offline b-tag",
ratio_title="Offline b-tag efficiency)")
#for ht_slice in [200, 250, 300, 350, 400, 450, 500, 550, 650]:
# if sr == "lowmass":
# numerator_analysis = "trigjetht" + str(ht_slice) + "_eta1p7_CSVTM"
# denominator_analysis = "trigjetht" + str(ht_slice) + "_eta1p7"
# else:
# numerator_analysis = "trigjetht" + str(ht_slice) + "_CSVTM"
# denominator_analysis = "trigjetht" + str(ht_slice)
# plotter = OfflineBTagPlots(numerator_analysis, denominator_analysis, ["JetHT_2012BCD"])
# plotter.EfficiencyPlot(var="mjj", logy=True, binning=dijet_binning, save_tag="_CSVTM_" + sr + "_jetht" + str(ht_slice), ratio_range=[0.,0.01], x_range=[0., 2000.], legend_position="topright", numerator_legend="With offline b-tag", denominator_legend="Without offline b-tag", ratio_title="Offline b-tag efficiency", prescaled=True)
if args.do_singlejet:
for analysis in ["trigbbl_CSVTM", "trigbbh_CSVTM"]:
f = TFile(
analysis_config.get_b_histogram_filename(
analysis, "BJetPlusX_2012"), "READ")
h_mjj = histogram_tools.rebin_histogram(
f.Get("BHistograms/h_pfjet_mjj"), dijet_binning)
h_mjj_btagcorr = histogram_tools.rebin_histogram(
f.Get("BHistograms/h_pfjet_mjj_btagcorr"), dijet_binning)
EfficiencyPlot(h_mjj,
h_mjj_btagcorr,
name_num="No correction",
name_den="b tag correction",
logy=True,
save_directory=analysis_config.figure_directory +
"/OfflineBTag",
save_tag="from_singlejet_" + analysis)
ROOT.SetOwnership(c, False)
ROOT.SetOwnership(top, False)
ROOT.SetOwnership(bottom, False)
if __name__ == "__main__":
for analysis in ["trigbbh_CSVTM", "trigbbl_CSVTM"]:
for model in ["Hbb", "RSG"]:
if analysis == "trigbbh_CSVTM":
masses = [600, 750, 900, 1200]
elif analysis == "trigbbl_CSVTM":
masses = [400, 500, 600]
for mass in masses:
print "On " + model + " / " + str(mass)
signal_file = TFile(analysis_config.get_b_histogram_filename(analysis, analysis_config.simulation.get_signal_tag(model, mass, "FULLSIM")), "READ")
signal_histogram = signal_file.Get("BHistograms/h_nminusone_PFDijetMaxDeltaEta_vs_PFMjj")
xsec = 1. # 1 pb placeholder
ngenevt = signal_file.Get("BHistograms/h_input_nevents").Integral()
signal_histogram.Scale(19700. * xsec / ngenevt)
print "Background file " + analysis_config.get_b_histogram_filename(analysis, "BJetPlusX_2012")
background_file = TFile(analysis_config.get_b_histogram_filename(analysis, "BJetPlusX_2012"), "READ")
background_histogram = background_file.Get("BHistograms/h_nminusone_PFDijetMaxDeltaEta_vs_PFMjj")
signal_histogram_mjj = signal_histogram.ProjectionY()
signal_fit_results = DoSignalFit(signal_histogram_mjj, fit_range=[mass-150., mass+150.])
signal_x0 = signal_fit_results["fit"].GetParameter(2)
signal_sigma = signal_fit_results["fit"].GetParameter(3)
print "\tWindow = [" + str(signal_x0 - signal_sigma) + ", " + str(signal_x0 + signal_sigma) + "]"
analyses = ["trigbbl_CSVTM", "trigbbh_CSVTM"]
masses = {
"trigbbl_CSVTM":[400, 500, 600, 750],
"trigbbh_CSVTM":[600, 750, 900, 1200]
}
if args.mjj:
for analysis in analyses:
names = []
histograms = {}
colors = {}
styles = {}
for model in models:
color_counter = 0
for mass in masses[analysis]:
f = TFile(analysis_config.get_b_histogram_filename(analysis, analysis_config.simulation.get_signal_tag(model, mass, "FULLSIM")))
if model == "Hbb":
name = "H, m=" + str(mass) + " GeV"
elif model == "RSG":
name = "G, m=" + str(mass) + " GeV"
names.append(name)
histograms[name] = f.Get("BHistograms/h_pfjet_mjj")
histograms[name].SetDirectory(0)
histograms[name].Rebin(25)
histograms[name].Scale(1. / histograms[name].Integral())
f.Close()
if model == "Hbb":
styles[name] = 2
elif model == "RSG":
styles[name] = 3
colors[name] = seaborn.GetColorRoot("dark", color_counter)
gROOT.SetBatch(True)
gStyle.SetOptStat(0)
gStyle.SetOptTitle(0)
gSystem.Load("~/Dijets/CMSSW_5_3_32_patch3/lib/slc6_amd64_gcc472/libMyToolsRootUtils.so")
import CMSDIJET.QCDAnalysis.analysis_configuration_8TeV as analysis_config
sys.path.append("/uscms/home/dryu/Dijets/CMSSW_5_3_32_patch3/python/MyTools/RootUtils")
import histogram_tools
seaborn = Root.SeabornInterface()
seaborn.Initialize()
print "Loading histograms"
analyses = ["trigmu_highmass_CSVTM", "trigmu_lowmass_CSVTM", "trigmubbh_highmass_CSVTM", "trigmubbl_lowmass_CSVTM", "trigmubbll_lowmass_CSVTM"]
files = {}
for analysis in analyses:
files[analysis] = ROOT.TFile(analysis_config.get_b_histogram_filename(analysis, "SingleMu_2012"), "READ")
from array import array
mass_bins = array("d", [1, 3, 6, 10, 16, 23, 31, 40, 50, 61, 74, 88, 103, 119, 137, 156, 176, 197, 220, 244, 270, 296, 325, 354, 386, 419, 453, 489, 526, 565, 606, 649, 693, 740, 788, 838, 890, 944, 1000, 1058, 1118, 1181, 1246, 1313, 1383, 1455, 1530, 1607, 1687, 1770, 1856, 1945, 2037, 2132, 2231, 2332, 2438, 2546, 2659, 2775, 2895, 3019, 3147, 3279, 3416, 3558, 3704, 3854, 4010, 4171, 4337, 4509, 4686, 4869, 5058, 5253, 5455, 5663, 5877, 6099, 6328, 6564, 6808, 7060, 7320, 7589, 7866, 8000])
variables = ["mjj", "pt1", "pt2", "pt_btag1", "pt_btag2"]
histograms = {}
for analysis in analyses:
histograms[analysis] = {}
for variable in variables:
histograms[analysis][variable] = files[analysis].Get("BHistograms/h_pfjet_" + variable)
histograms[analysis][variable].SetName("h_" + analysis + "_" + variable)
histograms[analysis][variable].SetDirectory(0)
if analysis == "trigmubbll_lowmass":
histograms[analysis][variable].Scale(1.7) # Prescale
if variable == "mjj":
def RunBHistogramsSignal(analysis,
sample,
files_per_job=1,
retar=False,
data_source=None):
# Create working directory and cd
start_directory = os.getcwd()
working_directory = dijet_directory + "/data/EightTeeEeVeeBee/BHistograms/condor/submit_" + analysis + "_" + sample
os.system("mkdir -pv " + working_directory)
os.chdir(working_directory)
method = "csub"
if method == "csub":
input_files_txt = open(analysis_config.files_QCDBEventTree[sample],
'r')
input_files = [line.strip() for line in input_files_txt]
input_files_txt.close()
bash_script_path = working_directory + "/run_" + analysis + "_" + sample + ".sh"
bash_script = open(bash_script_path, 'w')
bash_script.write("#!/bin/bash\n")
bash_script.write("input_files=( " +
" ".join([os.path.basename(x)
for x in input_files]) + " )\n")
output_filename = os.path.basename(
analysis_config.get_b_histogram_filename(analysis,
sample)).replace(
".root", "_$1.root")
bash_script.write(
"cmsRun " +
os.path.basename(analysis_config.analysis_cfgs[analysis]) +
" dataSource=simulation" + " dataType=signal" + " signalMass=" +
str(analysis_config.simulation.signal_sample_masses[sample]) +
" outputFile=" + output_filename +
" inputFiles=file:${input_files[$1]}\n")
bash_script.close()
submit_command = "csub " + bash_script_path + " --cmssw "
if not retar:
submit_command += " --no_retar"
submit_command += " -F " + ",".join(
input_files
) + "," + analysis_config.analysis_cfgs[analysis] + " -n " + str(
len(input_files))
os.system(submit_command)
else:
command = "condor_cmsRun"
if retar:
command += " --retar "
#input_txt = open("tmp.txt", 'w')
#input_txt.write(analysis_config.files_QCDBEventTree[sample] + "\n")
#input_txt.close()
command += " --file-list=" + analysis_config.files_QCDBEventTree[
sample] + " "
command += " --files-per-job=" + str(files_per_job)
command += " --submit-file=submit_" + analysis + "_" + sample + ".jdl "
#command += " --output-file=" + output_prefix + "_" + sample + ".root "
command += " --output-tag=BHistograms_" + sample + " "
command += " --run "
command += " " + dijet_directory + "/CMSSW_5_3_32_patch3/src/MyTools/RootUtils/scripts/cmsRun_wrapper.sh " + analysis_config.analysis_cfgs[
analysis]
command += " dataSource=simulation "
command += " dataType=signal "
command += " signalMass=" + str(
analysis_config.simulation.signal_sample_masses[sample]) + " "
#command += "inputFiles=" + os.path.basename(input_files[sample])
if "ZPrime" in sample:
command += " bottomOnly=true "
output_filename = os.path.basename(
analysis_config.get_b_histogram_filename(
analysis,
sample)).replace(".root", "_\$\(Cluster\)_\$\(Process\).root")
command += " outputFile=" + os.path.basename(
analysis_config.get_b_histogram_filename(
analysis, sample)).replace(
".root", "_\$\(Cluster\)_\$\(Process\).root")
print command
os.system(command)
os.system("rm -f tmp.txt")
postprocessing_file = open('postprocessing.sh', 'w')
postprocessing_file.write("#!/bin/bash\n")
postprocessing_file.write(
"hadd " + working_directory + "/" + os.path.basename(
analysis_config.get_b_histogram_filename(analysis, sample)) + " " +
output_filename.replace("_\$\(Cluster\)_\$\(Process\)", "*").replace(
"$1", "*") + "\n")
postprocessing_file.close()
# cd back
os.chdir(start_directory)
ROOT.SetOwnership(bottom, False)
if __name__ == "__main__":
for analysis in ["trigbbh_CSVTM", "trigbbl_CSVTM"]:
for model in ["Hbb", "RSG"]:
if analysis == "trigbbh_CSVTM":
masses = [600, 750, 900, 1200]
elif analysis == "trigbbl_CSVTM":
masses = [400, 500, 600]
for mass in masses:
print "On " + model + " / " + str(mass)
signal_file = TFile(
analysis_config.get_b_histogram_filename(
analysis,
analysis_config.simulation.get_signal_tag(
model, mass, "FULLSIM")), "READ")
signal_histogram = signal_file.Get(
"BHistograms/h_nminusone_PFDijetMaxDeltaEta_vs_PFMjj")
xsec = 1. # 1 pb placeholder
ngenevt = signal_file.Get(
"BHistograms/h_input_nevents").Integral()
signal_histogram.Scale(19700. * xsec / ngenevt)
print "Background file " + analysis_config.get_b_histogram_filename(
analysis, "BJetPlusX_2012")
background_file = TFile(
analysis_config.get_b_histogram_filename(
analysis, "BJetPlusX_2012"), "READ")
background_histogram = background_file.Get(
"BHistograms/h_nminusone_PFDijetMaxDeltaEta_vs_PFMjj")
def RunBHistogramsEOS(analysis, sample, files_per_job=20, retar=False, data_source=None):
if not data_source:
print "[RunBHistogramsEOS] ERROR : Please specify data_source = collision_data or simulation"
sys.exit(1)
# Create working directory and cd
start_directory = os.getcwd()
working_directory = dijet_directory + "/data/EightTeeEeVeeBee/BHistograms/condor/submit_" + analysis + "_" + sample
os.system("mkdir -pv " + working_directory)
os.chdir(working_directory)
# Get input file list
input_files_txt = file(analysis_config.files_QCDBEventTree[sample], 'r')
input_files = [line.strip() for line in input_files_txt]
input_files_txt.close()
method = "csub"
if method == "csub":
input_files_txt = open(analysis_config.files_QCDBEventTree[sample], 'r')
input_files = [line.strip() for line in input_files_txt]
input_files_txt.close()
# Recalculate files_per_job to split evenly
n_jobs = int(math.ceil(1. * len(input_files) / files_per_job))
files_per_job = int(math.ceil(1. * len(input_files) / n_jobs))
bash_script_path = working_directory + "/run_" + analysis + "_" + sample + ".sh"
bash_script = open(bash_script_path, 'w')
bash_script.write("#!/bin/bash\n")
bash_script.write("input_files=( " + " ".join(input_files) + " )\n")
bash_script.write("files_per_job=" + str(files_per_job) + "\n")
bash_script.write("first_file_index=$(($1*$files_per_job))\n")
bash_script.write("max_file_index=$((${#input_files[@]}-1))\n")
bash_script.write("if [ $(($first_file_index+$files_per_job-1)) -gt $max_file_index ]; then\n")
bash_script.write(" files_per_job=$(($max_file_index-$first_file_index+1))\n")
bash_script.write("fi\n")
bash_script.write("declare -a this_input_files=(${input_files[@]:$first_file_index:$files_per_job})\n")
bash_script.write("function join { local IFS=\"$1\"; shift; echo \"$*\"; }\n")
bash_script.write("this_input_files_string=\"$(join , ${this_input_files[@]})\"\n")
bash_script.write("echo \"Input files:\"\n")
bash_script.write("echo $this_input_files_string\n")
output_filename = os.path.basename(analysis_config.get_b_histogram_filename(analysis, sample).replace(".root", "_$1.root"))
bash_script.write("cmsRun "
+ os.path.basename(analysis_config.analysis_cfgs[analysis])
+ " dataSource=" + data_source
+ " dataType=data"
+ " outputFile=" + output_filename
+ " inputFiles=$this_input_files_string\n"
)
bash_script.close()
submit_command = "csub " + bash_script_path + " --cmssw "
if not retar:
submit_command += " --no_retar"
print "[debug] This job will have " + str(len(input_files)) + " / " + str(files_per_job) + " = " + str(n_jobs) + " jobs"
submit_command += " -F " + "," + analysis_config.analysis_cfgs[analysis] + " -n " + str(n_jobs)
os.system(submit_command)
else:
file_index = 0
subjob_index = 0
subjob_output_filenames = []
while file_index < len(file_list):
this_job_files = []
while file_index < len(file_list) and len(this_job_files) < files_per_job:
this_job_files.append(file_list[file_index].rstrip())
file_index += 1
if len(this_job_files) < 1:
continue
command = "echo \"condor_cmsRun"
if retar:
command += " --retar "
command += " --submit-file=submit_" + analysis + "_" + sample + ".subjob" + str(subjob_index) + ".jdl "
command += " --output-tag=BHistograms_" + sample + ".subjob" + str(subjob_index) + " "
command += " --run " + dijet_directory + "/CMSSW_5_3_32_patch3/src/MyTools/RootUtils/scripts/cmsRun_wrapper.sh " + analysis_config.analysis_cfgs[analysis]
command += " dataSource=" + data_source
command += " dataType=data inputFiles="
for input_file in this_job_files:
command += input_file + ","
command = command.rstrip(",")
command += "\""
subjob_output_filename = os.path.basename(analysis_config.get_b_histogram_filename(analysis, sample) + ".subjob" + str(subjob_index))
command += " outputFile=" + subjob_output_filename
subjob_output_filenames.append(subjob_output_filename)
#print command
os.system(command)
subjob_index += 1
# Postprocessing script
merge_command = "hadd " + analysis_config.get_b_histogram_filename(analysis, sample) + " " + working_directory + "/" + os.path.basename(analysis_config.get_b_histogram_filename(analysis, sample)).replace(".root", "_*.root")
postprocessing_file = open('postprocessing.py', 'w')
postprocessing_file.write("import os\n")
postprocessing_file.write("import sys\n")
postprocessing_file.write("import glob\n")
postprocessing_file.write("log_files = glob.glob(\"" + working_directory + "/*stderr\")\n")
postprocessing_file.write("failed_logs = []\n")
postprocessing_file.write("for log_file in log_files:\n")
postprocessing_file.write("\tlog_file_handle = open(log_file, 'r')\n")
postprocessing_file.write("\tfor line in log_file_handle:\n")
postprocessing_file.write("\t\tif \"FAILURE\" in line:\n")
postprocessing_file.write("\t\t\tfailed_logs.append(log_file)\n")
postprocessing_file.write("if len(failed_logs) == 0:\n")
postprocessing_file.write("\tos.system(\"" + merge_command + "\")\n")
postprocessing_file.write("else:\n")
postprocessing_file.write("\tprint(\"Some jobs failed. You need to retry them.\")\n")
postprocessing_file.write("\tfor failed_log in failed_logs:\n")
postprocessing_file.write("\t\tprint failed_log\n")
postprocessing_file.close()
# cd back
os.chdir(start_directory)
def FrankenEfficiencyPlot(self,
logy=True,
binning=None,
simple_rebin=None,
save_tag="",
x_range=None,
ratio_range=None,
legend_position="topright",
numerator_legend=None,
denominator_legend=None,
ratio_title=None):
ht_slices = [
"HT200", "HT250", "HT300", "HT350", "HT400", "HT450", "HT500",
"HT550", "HTUnprescaled"
] # HT650
if self._numerator_analysis == "trigjetht_eta1p7_CSVTM":
numerator_analyses = {
"HT200": "trigjetht200_eta1p7_CSVTM",
"HT250": "trigjetht250_eta1p7_CSVTM",
"HT300": "trigjetht300_eta1p7_CSVTM",
"HT350": "trigjetht350_eta1p7_CSVTM",
"HT400": "trigjetht400_eta1p7_CSVTM",
"HT450": "trigjetht450_eta1p7_CSVTM",
"HT500": "trigjetht500_eta1p7_CSVTM",
"HT550": "trigjetht550_eta1p7_CSVTM",
#"HT650":"trigjetht650_eta1p7_CSVTM",
"HTUnprescaled": "trigjetht_eta1p7_CSVTM"
}
elif self._numerator_analysis == "trigjetht_eta2p2_CSVTM":
numerator_analyses = {
"HT200": "trigjetht200_CSVTM",
"HT250": "trigjetht250_CSVTM",
"HT300": "trigjetht300_CSVTM",
"HT350": "trigjetht350_CSVTM",
"HT400": "trigjetht400_CSVTM",
"HT450": "trigjetht450_CSVTM",
"HT500": "trigjetht500_CSVTM",
"HT550": "trigjetht550_CSVTM",
#"HT650":"trigjetht650_CSVTM",
"HTUnprescaled": "trigjetht_CSVTM"
}
else:
print "[OfflineBTagPlots::FrankenEfficiencyPlot] ERROR : numerator analysis must be trigjetht_eta1p7_CSVTM or trigjetht_eta2p2_CSVTM"
sys.exit(1)
if self._denominator_analysis == "trigjetht_eta1p7":
denominator_analyses = {
"HT200": "trigjetht200_eta1p7",
"HT250": "trigjetht250_eta1p7",
"HT300": "trigjetht300_eta1p7",
"HT350": "trigjetht350_eta1p7",
"HT400": "trigjetht400_eta1p7",
"HT450": "trigjetht450_eta1p7",
"HT500": "trigjetht500_eta1p7",
"HT550": "trigjetht550_eta1p7",
#"HT650":"trigjetht650_eta1p7",
"HTUnprescaled": "trigjetht_eta1p7"
}
elif self._denominator_analysis == "trigjetht_eta2p2":
denominator_analyses = {
"HT200": "trigjetht200",
"HT250": "trigjetht250",
"HT300": "trigjetht300",
"HT350": "trigjetht350",
"HT400": "trigjetht400",
"HT450": "trigjetht450",
"HT500": "trigjetht500",
"HT550": "trigjetht550",
#"HT650":"trigjetht650",
"HTUnprescaled": "trigjetht"
}
else:
print "[OfflineBTagPlots::FrankenEfficiencyPlot] ERROR : denominator analysis must be trigjetht_eta1p7 or trigjetht_eta2p2"
sys.exit(1)
ht_ranges = {
"HT200": [220, 386],
"HT250": [386, 489],
"HT300": [489, 526],
"HT350": [526, 606],
"HT400": [606, 649],
"HT450": [649, 740],
"HT500": [740, 788],
"HT550": [788, 890],
#"HT650":[890, 2000],
"HTUnprescaled": [890, 2000]
}
numerator_histogram = None
denominator_histogram = None
for sample in self._samples:
print "[EfficiencyPlot] DEBUG : Sample " + sample
numerator_slice_histograms = {}
denominator_slice_histograms = {}
for slice_name in ht_slices:
print slice_name
print analysis_config.get_b_histogram_filename(
numerator_analyses[slice_name], sample)
numerator_file = TFile(
analysis_config.get_b_histogram_filename(
numerator_analyses[slice_name], sample), "READ")
print analysis_config.get_b_histogram_filename(
denominator_analyses[slice_name], sample)
denominator_file = TFile(
analysis_config.get_b_histogram_filename(
denominator_analyses[slice_name], sample), "READ")
# Check input nevents
num_nevents = numerator_file.Get(
"BHistograms/h_input_nevents").Integral()
den_nevents = denominator_file.Get(
"BHistograms/h_input_nevents").Integral()
if num_nevents != den_nevents:
# Allow tiny differences...?
if abs((num_nevents - den_nevents) / den_nevents) < 0.001:
print "[EfficiencyPlot] ERROR : Small inconsistency between number of events between numerator and denominator. I'm going to rescale away the difference, but you may want to fix this."
numerator_normalization = den_nevents / num_nevents
denominator_normalization = 1.
else:
print "[EfficiencyPlot] ERROR : Inconsistent number of events between numerator and denominator. Results would be wrong, so I'm aborting."
print "[EfficiencyPlot] ERROR : \tNumerator = " + str(
numerator_file.Get(
"BHistograms/h_input_nevents").Integral())
print "[EfficiencyPlot] ERROR : \tDenominator = " + str(
denominator_file.Get(
"BHistograms/h_input_nevents").Integral())
sys.exit(1)
else:
numerator_normalization = 1.
denominator_normalization = 1.
numerator_slice_histograms[slice_name] = numerator_file.Get(
"BHistograms/h_pfjet_mjj")
numerator_slice_histograms[slice_name].SetName(
"h_pfjet_mjj_num_" + slice_name + "_" + sample)
numerator_slice_histograms[slice_name].SetDirectory(0)
numerator_slice_histograms[slice_name].Scale(
numerator_normalization)
denominator_slice_histograms[
slice_name] = denominator_file.Get(
"BHistograms/h_pfjet_mjj")
denominator_slice_histograms[slice_name].SetName(
"h_pfjet_mjj_den_" + slice_name + "_" + sample)
denominator_slice_histograms[slice_name].SetDirectory(0)
denominator_slice_histograms[slice_name].Scale(
denominator_normalization)
numerator_file.Close()
denominator_file.Close()
# Make frankenhist
this_numerator_histogram = self.FrankenHist(
ht_slices, numerator_slice_histograms, ht_ranges)
this_denominator_histogram = self.FrankenHist(
ht_slices, denominator_slice_histograms, ht_ranges)
if not numerator_histogram:
numerator_histogram = this_numerator_histogram.Clone()
numerator_histogram.SetName(numerator_histogram.GetName() +
save_tag + "_num_" +
str(time.time()))
denominator_histogram = this_denominator_histogram.Clone()
denominator_histogram.SetName(denominator_histogram.GetName() +
save_tag + "_num_" +
str(time.time()))
else:
numerator_histogram.Add(this_numerator_histogram)
denominator_histogram.Add(this_denominator_histogram)
# Rebin
if binning:
numerator_histogram = histogram_tools.rebin_histogram(
numerator_histogram, binning)
denominator_histogram = histogram_tools.rebin_histogram(
denominator_histogram, binning)
elif simple_rebin:
numerator_histogram.Rebin(simple_rebin)
denominator_histogram.Rebin(simple_rebin)
cname = "c_offline_btag_eff_mjj"
if logy:
cname += "_log"
c = TCanvas(cname, "Offline b-tag #epsilon", 800, 1000)
top = TPad("top", "top", 0., 0.5, 1., 1.)
top.SetBottomMargin(0.02)
if logy:
top.SetLogy()
top.Draw()
top.cd()
frame_top = numerator_histogram.Clone()
frame_top.Reset()
if x_range:
frame_top.GetXaxis().SetRangeUser(x_range[0], x_range[1])
if logy:
y_min = 0.1
y_max = max(numerator_histogram.GetMaximum(),
denominator_histogram.GetMaximum()) * 10.
else:
y_min = 0.
y_max = max(numerator_histogram.GetMaximum(),
denominator_histogram.GetMaximum()) * 1.5
frame_top.SetMinimum(y_min)
frame_top.SetMaximum(y_max)
frame_top.GetXaxis().SetLabelSize(0)
frame_top.GetXaxis().SetTitleSize(0)
if binning:
#frame_top.GetYaxis().SetTitle("Events / 1 GeV")
frame_top.GetYaxis().SetTitle("Events")
else:
frame_top.GetYaxis().SetTitle("Events")
frame_top.Draw("axis")
print "numerator integral = " + str(numerator_histogram.Integral())
print "denominator integral = " + str(denominator_histogram.Integral())
numerator_histogram.SetMarkerStyle(20)
numerator_histogram.SetMarkerColor(seaborn.GetColorRoot("default", 0))
numerator_histogram.SetLineColor(seaborn.GetColorRoot("default", 0))
numerator_histogram.Draw("same")
denominator_histogram.SetMarkerStyle(24)
denominator_histogram.SetMarkerColor(seaborn.GetColorRoot(
"default", 2))
denominator_histogram.SetLineColor(seaborn.GetColorRoot("default", 2))
denominator_histogram.Draw("same")
if legend_position == "topright":
l = TLegend(0.6, 0.6, 0.85, 0.8)
elif legend_position == "bottomright":
l = TLegend(0.6, 0.2, 0.85, 0.4)
l.SetFillColor(0)
l.SetBorderSize(0)
if numerator_legend:
l.AddEntry(numerator_histogram, numerator_legend)
else:
l.AddEntry(numerator_histogram, "CSVT+CSVM")
if denominator_legend:
l.AddEntry(denominator_histogram, denominator_legend)
else:
l.AddEntry(denominator_histogram, "No CSV")
l.Draw()
c.cd()
bottom = TPad("bottom", "bottom", 0., 0., 1., 0.5)
bottom.SetTopMargin(0.01)
bottom.SetBottomMargin(0.2)
bottom.Draw()
bottom.cd()
ratio_histogram = numerator_histogram.Clone()
ratio_histogram.Reset()
if x_range:
ratio_histogram.GetXaxis().SetRangeUser(x_range[0], x_range[1])
ratio_histogram.SetName(numerator_histogram.GetName() + "_ratio_" +
save_tag + str(time.time()))
ratio_histogram.SetDirectory(0)
for bin in xrange(1, numerator_histogram.GetNbinsX() + 1):
# Undo bin normalization
if numerator_histogram.GetBinError(
bin) > 0 and denominator_histogram.GetBinError(bin) > 0:
num_unnormalized = (numerator_histogram.GetBinContent(
bin))**2 / (numerator_histogram.GetBinError(bin))**2
den_unnormalized = (denominator_histogram.GetBinContent(
bin))**2 / (denominator_histogram.GetBinError(bin))**2
num = numerator_histogram.GetBinContent(bin)
den = denominator_histogram.GetBinContent(bin)
ratio = 1. * num_unnormalized / den_unnormalized
ratio_err = sqrt(ratio * (1. - ratio) / den_unnormalized)
#ratio_err = max(sqrt(ratio * (1. - ratio) / den), 1./den)
else:
ratio = 0.
ratio_err = 0.
ratio_histogram.SetBinContent(bin, ratio)
ratio_histogram.SetBinError(bin, ratio_err)
ratio_histogram.SetMarkerSize(1)
ratio_histogram.SetMarkerColor(kBlack)
ratio_histogram.SetLineColor(kBlack)
ratio_histogram.SetLineWidth(2)
ratio_histogram.GetXaxis().SetTitle("m_{jj} [GeV]")
if ratio_title:
ratio_histogram.GetYaxis().SetTitle(ratio_title)
else:
ratio_histogram.GetYaxis().SetTitle(
"Offline 2#timesb-tag efficiency")
if ratio_range:
ratio_histogram.SetMinimum(ratio_range[0])
ratio_histogram.SetMaximum(ratio_range[1])
else:
ratio_histogram.SetMinimum(0.)
ratio_histogram.SetMaximum(1.)
ratio_histogram.Draw()
c.cd()
c.SaveAs(analysis_config.figure_directory + "/OfflineBTag/" +
c.GetName() + save_tag + ".pdf")
ROOT.SetOwnership(c, False)
ROOT.SetOwnership(top, False)
ROOT.SetOwnership(bottom, False)
sys.path.append(
"/uscms/home/dryu/Dijets/CMSSW_5_3_32_patch3/python/MyTools/RootUtils")
import histogram_tools
seaborn = Root.SeabornInterface()
seaborn.Initialize()
print "Loading histograms"
analyses = [
"trigmu_highmass_CSVTM", "trigmu_lowmass_CSVTM",
"trigmubbh_highmass_CSVTM", "trigmubbl_lowmass_CSVTM",
"trigmubbll_lowmass_CSVTM"
]
files = {}
for analysis in analyses:
files[analysis] = ROOT.TFile(
analysis_config.get_b_histogram_filename(analysis, "SingleMu_2012"),
"READ")
from array import array
mass_bins = array("d", [
1, 3, 6, 10, 16, 23, 31, 40, 50, 61, 74, 88, 103, 119, 137, 156, 176, 197,
220, 244, 270, 296, 325, 354, 386, 419, 453, 489, 526, 565, 606, 649, 693,
740, 788, 838, 890, 944, 1000, 1058, 1118, 1181, 1246, 1313, 1383, 1455,
1530, 1607, 1687, 1770, 1856, 1945, 2037, 2132, 2231, 2332, 2438, 2546,
2659, 2775, 2895, 3019, 3147, 3279, 3416, 3558, 3704, 3854, 4010, 4171,
4337, 4509, 4686, 4869, 5058, 5253, 5455, 5663, 5877, 6099, 6328, 6564,
6808, 7060, 7320, 7589, 7866, 8000
])
variables = ["mjj", "pt1", "pt2", "pt_btag1", "pt_btag2"]
histograms = {}
if __name__ == "__main__":
for model in ["Hbb", "RSG"]:
#for analysis_base in ["trigbbh", "trigbbl"]:
for analysis_base in ["trigbbl", "trigbbh"]:
if analysis_base == "trigbbh":
masses = [600, 750, 900, 1200]
elif analysis_base == "trigbbl":
masses = [400, 600, 750, 900]
analyses = [analysis_base + "_" + x for x in ["CSVL", "CSVM", "CSVT", "CSVTL", "CSVTM", "CSVML"]]
for mass in masses:
signal_histograms = {}
data_histograms = {}
for analysis in analyses:
signal_sample = analysis_config.simulation.get_signal_tag(model, mass, "FULLSIM")
#print "Signal file: " + analysis_config.get_b_histogram_filename(analysis, signal_sample)
signal_histogram_file = TFile(analysis_config.get_b_histogram_filename(analysis, signal_sample), "READ")
#print "Data file: " + analysis_config.get_b_histogram_filename(analysis, "BJetPlusX_2012")
data_histogram_file = TFile(analysis_config.get_b_histogram_filename(analysis, "BJetPlusX_2012"), "READ")
signal_histograms[analysis] = signal_histogram_file.Get("BHistograms/h_pfjet_mjj")
if not signal_histograms[analysis]:
print "ERROR : Couldn't find signal histogram BHistograms/h_pfjet_mjj in file " + analysis_config.get_b_histogram_filename(analysis, signal_sample)
continue
signal_histograms[analysis].SetDirectory(0)
ngenevt = signal_histogram_file.Get("BHistograms/h_input_nevents").Integral()
xsec = 1. # 1 pb placeholder
signal_histograms[analysis].Scale(19700. * xsec / ngenevt)
print "[debug] Data file " + analysis_config.get_b_histogram_filename(analysis, "BJetPlusX_2012")
data_histograms[analysis] = data_histogram_file.Get("BHistograms/h_pfjet_mjj")
data_histograms[analysis].SetDirectory(0)
if not data_histograms[analysis]:
print "ERROR : Couldn't find data histogram"
def RunBHistogramsEOS(analysis,
sample,
files_per_job=20,
retar=False,
data_source=None):
if not data_source:
print "[RunBHistogramsEOS] ERROR : Please specify data_source = collision_data or simulation"
sys.exit(1)
# Create working directory and cd
start_directory = os.getcwd()
working_directory = dijet_directory + "/data/EightTeeEeVeeBee/BHistograms/condor/submit_" + analysis + "_" + sample
os.system("mkdir -pv " + working_directory)
os.chdir(working_directory)
# Get input file list
input_files_txt = file(analysis_config.files_QCDBEventTree[sample], 'r')
input_files = [line.strip() for line in input_files_txt]
input_files_txt.close()
method = "csub"
if method == "csub":
input_files_txt = open(analysis_config.files_QCDBEventTree[sample],
'r')
input_files = [line.strip() for line in input_files_txt]
input_files_txt.close()
# Recalculate files_per_job to split evenly
n_jobs = int(math.ceil(1. * len(input_files) / files_per_job))
files_per_job = int(math.ceil(1. * len(input_files) / n_jobs))
bash_script_path = working_directory + "/run_" + analysis + "_" + sample + ".sh"
bash_script = open(bash_script_path, 'w')
bash_script.write("#!/bin/bash\n")
bash_script.write("input_files=( " + " ".join(input_files) + " )\n")
bash_script.write("files_per_job=" + str(files_per_job) + "\n")
bash_script.write("first_file_index=$(($1*$files_per_job))\n")
bash_script.write("max_file_index=$((${#input_files[@]}-1))\n")
bash_script.write(
"if [ $(($first_file_index+$files_per_job-1)) -gt $max_file_index ]; then\n"
)
bash_script.write(
" files_per_job=$(($max_file_index-$first_file_index+1))\n")
bash_script.write("fi\n")
bash_script.write(
"declare -a this_input_files=(${input_files[@]:$first_file_index:$files_per_job})\n"
)
bash_script.write(
"function join { local IFS=\"$1\"; shift; echo \"$*\"; }\n")
bash_script.write(
"this_input_files_string=\"$(join , ${this_input_files[@]})\"\n")
bash_script.write("echo \"Input files:\"\n")
bash_script.write("echo $this_input_files_string\n")
output_filename = os.path.basename(
analysis_config.get_b_histogram_filename(analysis, sample).replace(
".root", "_$1.root"))
bash_script.write(
"cmsRun " +
os.path.basename(analysis_config.analysis_cfgs[analysis]) +
" dataSource=" + data_source + " dataType=data" + " outputFile=" +
output_filename + " inputFiles=$this_input_files_string\n")
bash_script.close()
submit_command = "csub " + bash_script_path + " --cmssw "
if not retar:
submit_command += " --no_retar"
print "[debug] This job will have " + str(
len(input_files)) + " / " + str(files_per_job) + " = " + str(
n_jobs) + " jobs"
submit_command += " -F " + "," + analysis_config.analysis_cfgs[
analysis] + " -n " + str(n_jobs)
os.system(submit_command)
else:
file_index = 0
subjob_index = 0
subjob_output_filenames = []
while file_index < len(file_list):
this_job_files = []
while file_index < len(file_list) and len(
this_job_files) < files_per_job:
this_job_files.append(file_list[file_index].rstrip())
file_index += 1
if len(this_job_files) < 1:
continue
command = "echo \"condor_cmsRun"
if retar:
command += " --retar "
command += " --submit-file=submit_" + analysis + "_" + sample + ".subjob" + str(
subjob_index) + ".jdl "
command += " --output-tag=BHistograms_" + sample + ".subjob" + str(
subjob_index) + " "
command += " --run " + dijet_directory + "/CMSSW_5_3_32_patch3/src/MyTools/RootUtils/scripts/cmsRun_wrapper.sh " + analysis_config.analysis_cfgs[
analysis]
command += " dataSource=" + data_source
command += " dataType=data inputFiles="
for input_file in this_job_files:
command += input_file + ","
command = command.rstrip(",")
command += "\""
subjob_output_filename = os.path.basename(
analysis_config.get_b_histogram_filename(analysis, sample) +
".subjob" + str(subjob_index))
command += " outputFile=" + subjob_output_filename
subjob_output_filenames.append(subjob_output_filename)
#print command
os.system(command)
subjob_index += 1
# Postprocessing script
merge_command = "hadd " + analysis_config.get_b_histogram_filename(
analysis, sample) + " " + working_directory + "/" + os.path.basename(
analysis_config.get_b_histogram_filename(
analysis, sample)).replace(".root", "_*.root")
postprocessing_file = open('postprocessing.py', 'w')
postprocessing_file.write("import os\n")
postprocessing_file.write("import sys\n")
postprocessing_file.write("import glob\n")
postprocessing_file.write("log_files = glob.glob(\"" + working_directory +
"/*stderr\")\n")
postprocessing_file.write("failed_logs = []\n")
postprocessing_file.write("for log_file in log_files:\n")
postprocessing_file.write("\tlog_file_handle = open(log_file, 'r')\n")
postprocessing_file.write("\tfor line in log_file_handle:\n")
postprocessing_file.write("\t\tif \"FAILURE\" in line:\n")
postprocessing_file.write("\t\t\tfailed_logs.append(log_file)\n")
postprocessing_file.write("if len(failed_logs) == 0:\n")
postprocessing_file.write("\tos.system(\"" + merge_command + "\")\n")
postprocessing_file.write("else:\n")
postprocessing_file.write(
"\tprint(\"Some jobs failed. You need to retry them.\")\n")
postprocessing_file.write("\tfor failed_log in failed_logs:\n")
postprocessing_file.write("\t\tprint failed_log\n")
postprocessing_file.close()
# cd back
os.chdir(start_directory)
parser.add_argument('--btag_mc_notrig', action='store_true', help='Make online B tag efficiency plot from MC')
args = parser.parse_args()
print args
if args.ht:
analyses = {}
names = []
for mass in xrange(200, 700, 50):
if mass == 600:
continue
names.append("HT" + str(mass))
analyses["HT" + str(mass)] = "trigjetht" + str(mass)
sample = "JetHT_2012BCD"
histograms = {}
for name in names:
f = TFile(analysis_config.get_b_histogram_filename(analyses[name], sample), "READ")
#histograms[name] = mjj_common.apply_dijet_binning_normalized(f.Get("BHistograms/h_pfjet_mjj"))
print "[debug] For name " + name + ", input events = " + str(f.Get("BHistograms/h_input_nevents").GetEntries())
print "[debug] \tPrescale = " + str(f.Get("BHistograms/h_pass_nevents_weighted").GetBinContent(1) / f.Get("BHistograms/h_pass_nevents").GetBinContent(1))
histograms[name] = f.Get("BHistograms/h_pfjet_mjj").Rebin(20)
histograms[name].SetName(histograms[name].GetName() + "_" + name)
histograms[name].SetDirectory(0)
f.Close()
ht_threshold_plot(names, histograms, save_tag="jetht_thresholds", x_range=[0., 1200.], logy=True)
if args.btag:
f_jetht_save = TFile(analysis_config.dijet_directory + "/data/EightTeeEeVeeBee/TriggerEfficiency/trigeff_jetht_data.root", "RECREATE")
for sr in ["lowmass", "highmass"]:
ht_analyses = {}
names = []
for mass in xrange(200, 700, 50):
from ROOT import *
gSystem.Load("~/Dijets/CMSSW_5_3_32_patch3/lib/slc6_amd64_gcc472/libMyToolsRootUtils.so")
import CMSDIJET.QCDAnalysis.analysis_configuration_8TeV as analysis_config
# Combine the QCD MC samples with appropriate weights
qcd_samples = ["QCD_Pt-80to120_TuneZ2star_8TeV_pythia6","QCD_Pt-120to170_TuneZ2star_8TeV_pythia6","QCD_Pt-170to300_TuneZ2star_8TeV_pythia6","QCD_Pt-300to470_TuneZ2star_8TeV_pythia6","QCD_Pt-470to600_TuneZ2star_8TeV_pythia6","QCD_Pt-600to800_TuneZ2star_8TeV_pythia6","QCD_Pt-800to1000_TuneZ2star_8TeV_pythia6","QCD_Pt-1000to1400_TuneZ2star_8TeV_pythia6","QCD_Pt-1400to1800_TuneZ2star_8TeV_pythia6","QCD_Pt-1800_TuneZ2star_8TeV_pythia6"]
analyses = ["NoTrigger_eta2p2", "NoTrigger_eta2p2_CSVTM", "NoTrigger_eta1p7", "NoTrigger_eta1p7_CSVTM", "trigbbl_CSVTM", "trigbbh_CSVTM"]
lumi = 19710.
for analysis in analyses:
first = True
output_file = TFile(analysis_config.get_b_histogram_filename(analysis, "QCD_TuneZ2star_8TeV_pythia6"), "RECREATE")
output_directory = output_file.mkdir("BHistograms")
histograms = {}
for sample in qcd_samples:
input_file = TFile(analysis_config.get_b_histogram_filename(analysis, sample), "READ")
input_directory = input_file.Get("BHistograms")
input_directory.cd()
xsec = analysis_config.simulation.background_cross_sections[sample]
normalization = xsec * lumi / input_file.Get("BHistograms/h_sample_nevents").Integral()
for key in gDirectory.GetListOfKeys():
key.Print()
if "TH1" in key.GetClassName() or "TH2" in key.GetClassName():
hist = key.ReadObj()
hist.Scale(normalization)
if first:
histograms[hist.GetName()] = hist
histograms[hist.GetName()].SetDirectory(output_directory)
else:
histograms[hist.GetName()].Add(hist)