for control_region in regions:
# Fit variables (inclusive)
for var in ['M3', 'angle_bl', 'M_bl', 'absolute_eta']:
print channel, var
controlTree = 'TTbar_plus_X_analysis/%s/%s/FitVariables' % (
channel, control_region)
bins = fit_variable_bin_edges[var]
xMin = bins[0]
xMax = bins[-1]
nBins = len(bins) - 1
histograms = get_histograms_from_trees(
trees=[controlTree],
branch=var,
weightBranch='EventWeight',
files=histogram_files,
nBins=nBins,
xMin=xMin,
xMax=xMax)
prepare_histograms(
histograms,
rebin=1,
scale_factor=measurement_config.luminosity_scale)
histograms_to_draw = [
histograms['data'][controlTree],
histograms['QCD'][controlTree],
histograms['V+Jets'][controlTree],
histograms['SingleTop'][controlTree],
histograms['TTJet'][controlTree]
def make_ttbarReco_plot( channel, x_axis_title, y_axis_title,
signal_region_tree,
control_region_tree,
branchName,
name_prefix, x_limits, nBins,
use_qcd_data_region = False,
y_limits = [],
y_max_scale = 1.2,
rebin = 1,
legend_location = ( 0.98, 0.78 ), cms_logo_location = 'right',
log_y = False,
legend_color = False,
ratio_y_limits = [0.3, 1.7],
normalise = False,
):
global output_folder, measurement_config, category, normalise_to_fit
global preliminary, norm_variable, sum_bins, b_tag_bin, histogram_files
# Input files, normalisations, tree/region names
qcd_data_region = ''
title = title_template % ( measurement_config.new_luminosity / 1000., measurement_config.centre_of_mass_energy )
normalisation = None
if channel == 'electron':
histogram_files['data'] = measurement_config.data_file_electron_trees
histogram_files['QCD'] = measurement_config.electron_QCD_MC_category_templates_trees[category]
if normalise_to_fit:
normalisation = normalisations_electron[norm_variable]
if use_qcd_data_region:
qcd_data_region = 'QCDConversions'
if channel == 'muon':
histogram_files['data'] = measurement_config.data_file_muon_trees
histogram_files['QCD'] = measurement_config.muon_QCD_MC_category_templates_trees[category]
if normalise_to_fit:
normalisation = normalisations_muon[norm_variable]
if use_qcd_data_region:
qcd_data_region = 'QCD non iso mu+jets ge3j'
histograms = get_histograms_from_trees( trees = [signal_region_tree, control_region_tree], branch = branchName, weightBranch = '1', files = histogram_files, nBins = nBins, xMin = x_limits[0], xMax = x_limits[-1] )
selection = 'SolutionCategory == 0'
histogramsNoSolution = get_histograms_from_trees( trees = [signal_region_tree], branch = branchName, weightBranch = '1', selection = selection, files = histogram_files, nBins = nBins, xMin = x_limits[0], xMax = x_limits[-1] )
selection = 'SolutionCategory == 1'
histogramsCorrect = get_histograms_from_trees( trees = [signal_region_tree], branch = branchName, weightBranch = '1', selection = selection, files = histogram_files, nBins = nBins, xMin = x_limits[0], xMax = x_limits[-1] )
selection = 'SolutionCategory == 2'
histogramsNotSL = get_histograms_from_trees( trees = [signal_region_tree], branch = branchName, weightBranch = '1', selection = selection, files = histogram_files, nBins = nBins, xMin = x_limits[0], xMax = x_limits[-1] )
selection = 'SolutionCategory == 3'
histogramsNotReco = get_histograms_from_trees( trees = [signal_region_tree], branch = branchName, weightBranch = '1', selection = selection, files = histogram_files, nBins = nBins, xMin = x_limits[0], xMax = x_limits[-1] )
selection = 'SolutionCategory > 3'
histogramsWrong = get_histograms_from_trees( trees = [signal_region_tree], branch = branchName, weightBranch = '1', selection = selection, files = histogram_files, nBins = nBins, xMin = x_limits[0], xMax = x_limits[-1] )
# Split histograms up into signal/control (?)
signal_region_hists = {}
inclusive_control_region_hists = {}
for sample in histograms.keys():
signal_region_hists[sample] = histograms[sample][signal_region_tree]
if use_qcd_data_region:
inclusive_control_region_hists[sample] = histograms[sample][control_region_tree]
prepare_histograms( histograms, rebin = 1, scale_factor = measurement_config.luminosity_scale )
prepare_histograms( histogramsNoSolution, rebin = 1, scale_factor = measurement_config.luminosity_scale )
prepare_histograms( histogramsCorrect, rebin = 1, scale_factor = measurement_config.luminosity_scale )
prepare_histograms( histogramsNotSL, rebin = 1, scale_factor = measurement_config.luminosity_scale )
prepare_histograms( histogramsNotReco, rebin = 1, scale_factor = measurement_config.luminosity_scale )
prepare_histograms( histogramsWrong, rebin = 1, scale_factor = measurement_config.luminosity_scale )
qcd_from_data = signal_region_hists['QCD']
# Which histograms to draw, and properties
histograms_to_draw = [signal_region_hists['data'], qcd_from_data,
signal_region_hists['V+Jets'],
signal_region_hists['SingleTop'],
histogramsNoSolution['TTJet'][signal_region_tree],
histogramsNotSL['TTJet'][signal_region_tree],
histogramsNotReco['TTJet'][signal_region_tree],
histogramsWrong['TTJet'][signal_region_tree],
histogramsCorrect['TTJet'][signal_region_tree]
]
histogram_lables = ['data', 'QCD', 'V+Jets', 'Single-Top',
samples_latex['TTJet'] + ' - no solution',
samples_latex['TTJet'] + ' - not SL',
samples_latex['TTJet'] + ' - not reconstructible',
samples_latex['TTJet'] + ' - wrong reco',
samples_latex['TTJet'] + ' - correct',
]
histogram_colors = ['black', 'yellow', 'green', 'magenta',
'black',
'burlywood',
'chartreuse',
'blue',
'red'
]
histogram_properties = Histogram_properties()
histogram_properties.name = name_prefix + b_tag_bin
if category != 'central':
histogram_properties.name += '_' + category
histogram_properties.title = title
histogram_properties.x_axis_title = x_axis_title
histogram_properties.y_axis_title = y_axis_title
histogram_properties.x_limits = x_limits
histogram_properties.y_limits = y_limits
histogram_properties.y_max_scale = y_max_scale
histogram_properties.xerr = None
# workaround for rootpy issue #638
histogram_properties.emptybins = True
if b_tag_bin:
histogram_properties.additional_text = channel_latex[channel] + ', ' + b_tag_bins_latex[b_tag_bin]
else:
histogram_properties.additional_text = channel_latex[channel]
histogram_properties.legend_location = legend_location
histogram_properties.cms_logo_location = cms_logo_location
histogram_properties.preliminary = preliminary
histogram_properties.set_log_y = log_y
histogram_properties.legend_color = legend_color
if ratio_y_limits:
histogram_properties.ratio_y_limits = ratio_y_limits
if normalise_to_fit:
histogram_properties.mc_error = get_normalisation_error( normalisation )
histogram_properties.mc_errors_label = 'fit uncertainty'
else:
histogram_properties.mc_error = mc_uncertainty
histogram_properties.mc_errors_label = 'MC unc.'
# Actually draw histograms
make_data_mc_comparison_plot( histograms_to_draw, histogram_lables, histogram_colors,
histogram_properties, save_folder = output_folder,
show_ratio = False, normalise = normalise,
)
histogram_properties.name += '_with_ratio'
loc = histogram_properties.legend_location
# adjust legend location as it is relative to canvas!
histogram_properties.legend_location = ( loc[0], loc[1] + 0.05 )
make_data_mc_comparison_plot( histograms_to_draw, histogram_lables, histogram_colors,
histogram_properties, save_folder = output_folder,
show_ratio = True, normalise = normalise,
)
def make_plot(
channel,
x_axis_title,
y_axis_title,
signal_region_tree,
control_region_tree,
branchName,
name_prefix,
x_limits,
nBins,
use_qcd_data_region=False,
compare_qcd_signal_with_data_control=False,
y_limits=[],
y_max_scale=1.3,
rebin=1,
legend_location=(0.98, 0.78),
cms_logo_location='right',
log_y=False,
legend_color=False,
ratio_y_limits=[0.3, 2.5],
normalise=False,
):
global output_folder, measurement_config, category, normalise_to_fit
global preliminary, norm_variable, sum_bins, b_tag_bin, histogram_files
controlToCompare = []
if 'electron' in channel:
controlToCompare = ['QCDConversions', 'QCD non iso e+jets']
elif 'muon' in channel:
controlToCompare = ['QCD iso > 0.3', 'QCD 0.12 < iso <= 0.3']
histogramsToCompare = {}
for qcd_data_region in controlToCompare:
print 'Doing ', qcd_data_region
# Input files, normalisations, tree/region names
title = title_template % (measurement_config.new_luminosity,
measurement_config.centre_of_mass_energy)
normalisation = None
weightBranchSignalRegion = 'EventWeight'
if 'electron' in channel:
histogram_files[
'data'] = measurement_config.data_file_electron_trees
histogram_files[
'QCD'] = measurement_config.electron_QCD_MC_category_templates_trees[
category]
if normalise_to_fit:
normalisation = normalisations_electron[norm_variable]
# if use_qcd_data_region:
# qcd_data_region = 'QCDConversions'
# # qcd_data_region = 'QCD non iso e+jets'
if not 'QCD' in channel and not 'NPU' in branchName:
weightBranchSignalRegion += ' * ElectronEfficiencyCorrection'
if 'muon' in channel:
histogram_files['data'] = measurement_config.data_file_muon_trees
histogram_files[
'QCD'] = measurement_config.muon_QCD_MC_category_templates_trees[
category]
if normalise_to_fit:
normalisation = normalisations_muon[norm_variable]
# if use_qcd_data_region:
# qcd_data_region = 'QCD iso > 0.3'
if not 'QCD' in channel and not 'NPU' in branchName:
weightBranchSignalRegion += ' * MuonEfficiencyCorrection'
if not "_NPUNoWeight" in name_prefix:
weightBranchSignalRegion += ' * PUWeight'
if not "_NBJetsNoWeight" in name_prefix:
weightBranchSignalRegion += ' * BJetWeight'
selection = '1'
if branchName == 'abs(lepton_eta)':
selection = 'lepton_eta > -10'
else:
selection = '%s >= 0' % branchName
# if 'QCDConversions' in signal_region_tree:
# selection += '&& isTightElectron'
# print selection
histograms = get_histograms_from_trees(
trees=[signal_region_tree, control_region_tree],
branch=branchName,
weightBranch=weightBranchSignalRegion,
files=histogram_files,
nBins=nBins,
xMin=x_limits[0],
xMax=x_limits[-1],
selection=selection)
histograms_QCDControlRegion = None
if use_qcd_data_region:
qcd_control_region = signal_region_tree.replace(
'Ref selection', qcd_data_region)
histograms_QCDControlRegion = get_histograms_from_trees(
trees=[qcd_control_region],
branch=branchName,
weightBranch='EventWeight',
files=histogram_files,
nBins=nBins,
xMin=x_limits[0],
xMax=x_limits[-1],
selection=selection)
# Split histograms up into signal/control (?)
signal_region_hists = {}
control_region_hists = {}
for sample in histograms.keys():
signal_region_hists[sample] = histograms[sample][
signal_region_tree]
if compare_qcd_signal_with_data_control:
if sample is 'data':
signal_region_hists[sample] = histograms[sample][
control_region_tree]
elif sample is 'QCD':
signal_region_hists[sample] = histograms[sample][
signal_region_tree]
else:
del signal_region_hists[sample]
if use_qcd_data_region:
control_region_hists[sample] = histograms_QCDControlRegion[
sample][qcd_control_region]
# Prepare histograms
if normalise_to_fit:
# only scale signal region to fit (results are invalid for control region)
prepare_histograms(
signal_region_hists,
rebin=rebin,
scale_factor=measurement_config.luminosity_scale,
normalisation=normalisation)
elif normalise_to_data:
totalMC = 0
for sample in signal_region_hists:
if sample is 'data': continue
totalMC += signal_region_hists[sample].Integral()
newScale = signal_region_hists['data'].Integral() / totalMC
prepare_histograms(
signal_region_hists,
rebin=rebin,
scale_factor=newScale,
)
else:
print measurement_config.luminosity_scale
prepare_histograms(
signal_region_hists,
rebin=rebin,
scale_factor=measurement_config.luminosity_scale)
prepare_histograms(
control_region_hists,
rebin=rebin,
scale_factor=measurement_config.luminosity_scale)
# Use qcd from data control region or not
qcd_from_data = None
if use_qcd_data_region:
qcd_from_data = clean_control_region(
control_region_hists,
subtract=['TTJet', 'V+Jets', 'SingleTop'])
# Normalise control region correctly
nBins = signal_region_hists['QCD'].GetNbinsX()
n, error = signal_region_hists['QCD'].integral(0,
nBins + 1,
error=True)
n_qcd_predicted_mc_signal = ufloat(n, error)
n, error = control_region_hists['QCD'].integral(0,
nBins + 1,
error=True)
n_qcd_predicted_mc_control = ufloat(n, error)
n, error = qcd_from_data.integral(0, nBins + 1, error=True)
n_qcd_control_region = ufloat(n, error)
if not n_qcd_control_region == 0:
dataDrivenQCDScale = n_qcd_predicted_mc_signal / n_qcd_predicted_mc_control
print 'Overall scale : ', dataDrivenQCDScale
qcd_from_data.Scale(dataDrivenQCDScale.nominal_value)
signalToControlScale = n_qcd_predicted_mc_signal / n_qcd_control_region
dataToMCscale = n_qcd_control_region / n_qcd_predicted_mc_control
print "Signal to control :", signalToControlScale
print "QCD scale : ", dataToMCscale
else:
qcd_from_data = signal_region_hists['QCD']
# Which histograms to draw, and properties
histograms_to_draw = []
histogram_lables = []
histogram_colors = []
if compare_qcd_signal_with_data_control:
histograms_to_draw = [signal_region_hists['data'], qcd_from_data]
histogram_lables = ['data', 'QCD']
histogram_colors = ['black', 'yellow']
else:
histograms_to_draw = [
signal_region_hists['data'], qcd_from_data,
signal_region_hists['V+Jets'],
signal_region_hists['SingleTop'], signal_region_hists['TTJet']
]
histogram_lables = [
'data', 'QCD', 'V+Jets', 'Single-Top', samples_latex['TTJet']
]
histogram_colors = [
colours['data'], colours['QCD'], colours['V+Jets'],
colours['Single-Top'], colours['TTJet']
]
print list(qcd_from_data.y())
histogramsToCompare[qcd_data_region] = qcd_from_data
print histogramsToCompare
histogram_properties = Histogram_properties()
histogram_properties.name = 'QCD_control_region_comparison_' + channel + '_' + branchName
histogram_properties.title = title
histogram_properties.x_axis_title = x_axis_title
histogram_properties.y_axis_title = y_axis_title
histogram_properties.x_limits = x_limits
histogram_properties.y_limits = y_limits
histogram_properties.mc_error = 0.0
histogram_properties.legend_location = (0.98, 0.78)
histogram_properties.ratio_y_limits = ratio_y_limits
if 'electron' in channel:
make_control_region_comparison(
histogramsToCompare['QCDConversions'],
histogramsToCompare['QCD non iso e+jets'],
name_region_1='Conversions',
name_region_2='Non Iso',
histogram_properties=histogram_properties,
save_folder=output_folder)
elif 'muon' in channel:
make_control_region_comparison(
histogramsToCompare['QCD iso > 0.3'],
histogramsToCompare['QCD 0.12 < iso <= 0.3'],
name_region_1='QCD iso > 0.3',
name_region_2='QCD 0.12 < iso <= 0.3',
histogram_properties=histogram_properties,
save_folder=output_folder)
def make_plot( channel, x_axis_title, y_axis_title,
signal_region_tree,
control_region_tree,
branchName,
name_prefix, x_limits, nBins,
use_qcd_data_region = False,
compare_qcd_signal_with_data_control = False,
y_limits = [],
y_max_scale = 1.3,
rebin = 1,
legend_location = ( 0.98, 0.78 ), cms_logo_location = 'right',
log_y = False,
legend_color = False,
ratio_y_limits = [0.3, 2.5],
normalise = False,
):
global output_folder, measurement_config, category, normalise_to_fit
global preliminary, norm_variable, sum_bins, b_tag_bin, histogram_files
controlToCompare = []
if 'electron' in channel :
controlToCompare = ['QCDConversions', 'QCD non iso e+jets']
elif 'muon' in channel :
controlToCompare = ['QCD iso > 0.3', 'QCD 0.12 < iso <= 0.3']
histogramsToCompare = {}
for qcd_data_region in controlToCompare:
print 'Doing ',qcd_data_region
# Input files, normalisations, tree/region names
title = title_template % ( measurement_config.new_luminosity, measurement_config.centre_of_mass_energy )
normalisation = None
weightBranchSignalRegion = 'EventWeight'
if 'electron' in channel:
histogram_files['data'] = measurement_config.data_file_electron_trees
histogram_files['QCD'] = measurement_config.electron_QCD_MC_category_templates_trees[category]
if normalise_to_fit:
normalisation = normalisations_electron[norm_variable]
# if use_qcd_data_region:
# qcd_data_region = 'QCDConversions'
# # qcd_data_region = 'QCD non iso e+jets'
if not 'QCD' in channel and not 'NPU' in branchName:
weightBranchSignalRegion += ' * ElectronEfficiencyCorrection'
if 'muon' in channel:
histogram_files['data'] = measurement_config.data_file_muon_trees
histogram_files['QCD'] = measurement_config.muon_QCD_MC_category_templates_trees[category]
if normalise_to_fit:
normalisation = normalisations_muon[norm_variable]
# if use_qcd_data_region:
# qcd_data_region = 'QCD iso > 0.3'
if not 'QCD' in channel and not 'NPU' in branchName:
weightBranchSignalRegion += ' * MuonEfficiencyCorrection'
if not "_NPUNoWeight" in name_prefix:
weightBranchSignalRegion += ' * PUWeight'
if not "_NBJetsNoWeight" in name_prefix:
weightBranchSignalRegion += ' * BJetWeight'
selection = '1'
if branchName == 'abs(lepton_eta)' :
selection = 'lepton_eta > -10'
else:
selection = '%s >= 0' % branchName
# if 'QCDConversions' in signal_region_tree:
# selection += '&& isTightElectron'
# print selection
histograms = get_histograms_from_trees( trees = [signal_region_tree, control_region_tree], branch = branchName, weightBranch = weightBranchSignalRegion, files = histogram_files, nBins = nBins, xMin = x_limits[0], xMax = x_limits[-1], selection = selection )
histograms_QCDControlRegion = None
if use_qcd_data_region:
qcd_control_region = signal_region_tree.replace( 'Ref selection', qcd_data_region )
histograms_QCDControlRegion = get_histograms_from_trees( trees = [qcd_control_region], branch = branchName, weightBranch = 'EventWeight', files = histogram_files, nBins = nBins, xMin = x_limits[0], xMax = x_limits[-1], selection = selection )
# Split histograms up into signal/control (?)
signal_region_hists = {}
control_region_hists = {}
for sample in histograms.keys():
signal_region_hists[sample] = histograms[sample][signal_region_tree]
if compare_qcd_signal_with_data_control:
if sample is 'data':
signal_region_hists[sample] = histograms[sample][control_region_tree]
elif sample is 'QCD' :
signal_region_hists[sample] = histograms[sample][signal_region_tree]
else:
del signal_region_hists[sample]
if use_qcd_data_region:
control_region_hists[sample] = histograms_QCDControlRegion[sample][qcd_control_region]
# Prepare histograms
if normalise_to_fit:
# only scale signal region to fit (results are invalid for control region)
prepare_histograms( signal_region_hists, rebin = rebin,
scale_factor = measurement_config.luminosity_scale,
normalisation = normalisation )
elif normalise_to_data:
totalMC = 0
for sample in signal_region_hists:
if sample is 'data' : continue
totalMC += signal_region_hists[sample].Integral()
newScale = signal_region_hists['data'].Integral() / totalMC
prepare_histograms( signal_region_hists, rebin = rebin,
scale_factor = newScale,
)
else:
print measurement_config.luminosity_scale
prepare_histograms( signal_region_hists, rebin = rebin,
scale_factor = measurement_config.luminosity_scale )
prepare_histograms( control_region_hists, rebin = rebin,
scale_factor = measurement_config.luminosity_scale )
# Use qcd from data control region or not
qcd_from_data = None
if use_qcd_data_region:
qcd_from_data = clean_control_region( control_region_hists,
subtract = ['TTJet', 'V+Jets', 'SingleTop'] )
# Normalise control region correctly
nBins = signal_region_hists['QCD'].GetNbinsX()
n, error = signal_region_hists['QCD'].integral(0,nBins+1,error=True)
n_qcd_predicted_mc_signal = ufloat( n, error)
n, error = control_region_hists['QCD'].integral(0,nBins+1,error=True)
n_qcd_predicted_mc_control = ufloat( n, error)
n, error = qcd_from_data.integral(0,nBins+1,error=True)
n_qcd_control_region = ufloat( n, error)
if not n_qcd_control_region == 0:
dataDrivenQCDScale = n_qcd_predicted_mc_signal / n_qcd_predicted_mc_control
print 'Overall scale : ',dataDrivenQCDScale
qcd_from_data.Scale( dataDrivenQCDScale.nominal_value )
signalToControlScale = n_qcd_predicted_mc_signal / n_qcd_control_region
dataToMCscale = n_qcd_control_region / n_qcd_predicted_mc_control
print "Signal to control :",signalToControlScale
print "QCD scale : ",dataToMCscale
else:
qcd_from_data = signal_region_hists['QCD']
# Which histograms to draw, and properties
histograms_to_draw = []
histogram_lables = []
histogram_colors = []
if compare_qcd_signal_with_data_control :
histograms_to_draw = [signal_region_hists['data'], qcd_from_data ]
histogram_lables = ['data', 'QCD']
histogram_colors = ['black', 'yellow']
else :
histograms_to_draw = [signal_region_hists['data'], qcd_from_data,
signal_region_hists['V+Jets'],
signal_region_hists['SingleTop'],
signal_region_hists['TTJet']]
histogram_lables = ['data', 'QCD', 'V+Jets', 'Single-Top', samples_latex['TTJet']]
histogram_colors = [colours['data'], colours['QCD'], colours['V+Jets'], colours['Single-Top'], colours['TTJet'] ]
print list(qcd_from_data.y())
histogramsToCompare[qcd_data_region] = qcd_from_data
print histogramsToCompare
histogram_properties = Histogram_properties()
histogram_properties.name = 'QCD_control_region_comparison_' + channel + '_' + branchName
histogram_properties.title = title
histogram_properties.x_axis_title = x_axis_title
histogram_properties.y_axis_title = y_axis_title
histogram_properties.x_limits = x_limits
histogram_properties.y_limits = y_limits
histogram_properties.mc_error = 0.0
histogram_properties.legend_location = ( 0.98, 0.78 )
histogram_properties.ratio_y_limits = ratio_y_limits
if 'electron' in channel:
make_control_region_comparison(histogramsToCompare['QCDConversions'], histogramsToCompare['QCD non iso e+jets'],
name_region_1='Conversions', name_region_2='Non Iso',
histogram_properties=histogram_properties, save_folder=output_folder)
elif 'muon' in channel:
make_control_region_comparison(histogramsToCompare['QCD iso > 0.3'], histogramsToCompare['QCD 0.12 < iso <= 0.3'],
name_region_1='QCD iso > 0.3', name_region_2='QCD 0.12 < iso <= 0.3',
histogram_properties=histogram_properties, save_folder=output_folder)
regions = ['QCD non iso mu+jets']
elif channel == 'EPlusJets':
regions = ['QCD non iso e+jets', 'QCDConversions']
for control_region in regions :
# Fit variables (inclusive)
for var in ['M3', 'angle_bl', 'M_bl', 'absolute_eta']:
print channel,var
controlTree = 'TTbar_plus_X_analysis/%s/%s/FitVariables' % ( channel, control_region )
bins = fit_variable_bin_edges[var]
xMin = bins[0]
xMax = bins[-1]
nBins = len(bins) -1
histograms = get_histograms_from_trees( trees = [controlTree], branch = var, weightBranch = 'EventWeight', files = histogram_files, nBins = nBins, xMin = xMin, xMax = xMax )
prepare_histograms( histograms, rebin = 1, scale_factor = measurement_config.luminosity_scale )
histograms_to_draw = [histograms['data'][controlTree], histograms['QCD'][controlTree],
histograms['V+Jets'][controlTree],
histograms['SingleTop'][controlTree], histograms['TTJet'][controlTree]]
histogram_lables = ['data', 'QCD', 'V+Jets', 'Single-Top', samples_latex['TTJet']]
histogram_colors = ['black', 'yellow', 'green', 'magenta', 'red']
histogram_properties = Histogram_properties()
histogram_properties.name = 'QCD_nonIso_%s_%s' % (channel, var)
if control_region == 'QCDConversions' :
histogram_properties.name = 'QCD_Conversions_%s_%s' % (channel, var)
if category != 'central':
histogram_properties.name += '_' + category
def get_histograms(channel,
input_files,
variable,
met_systematic,
met_type,
variable_bin,
b_tag_bin,
treePrefix,
weightBranch,
rebin=1,
fit_variable='absolute_eta',
scale_factors=None):
global b_tag_bin_VJets, fit_variables
global electron_control_region, muon_control_region
boundaries = measurement_config.fit_boundaries[fit_variable]
histograms = {}
tree = measurement_config.tree_path_templates[channel]
control_tree = measurement_config.tree_path_control_templates[channel]
# Put together weight
fullWeight = 'EventWeight'
if weightBranch != '':
fullWeight += ' * %s' % weightBranch
# Work out bin of variable
variableForSelection = variable
minVar = variable_bin.split('-')[0]
maxVar = variable_bin.split('-')[-1]
selection = ''
if maxVar != 'inf':
selection = '%s >= %s && %s < %s' % (variableForSelection, minVar,
variableForSelection, maxVar)
else:
selection = '%s >= %s' % (variableForSelection, minVar)
bins = fit_variable_bin_edges[fit_variable]
xMin = bins[0]
xMax = bins[-1]
nBins = len(bins) - 1
# Get data files here, without any systematic variations
data_files = {sample: input_files[sample] for sample in ['data']}
histograms_data = get_histograms_from_trees(trees=[tree],
branch=fit_variable,
selection=selection,
weightBranch=fullWeight,
files=data_files,
nBins=nBins,
xMin=xMin,
xMax=xMax)
# Now work out tree/variable for MC
# Identical for data if central, different for systematics
tree = tree + treePrefix
if met_systematic:
if variable == 'MET':
variableForSelection = 'MET_METUncertainties[%i]' % met_systematics[
met_systematic]
elif variable == 'ST':
variableForSelection = 'ST_METUncertainties[%i]' % met_systematics[
met_systematic]
# Work out selection again for MC, as variable (e.g. MET) could be different after systematic variation
if maxVar != 'inf':
selection = '%s >= %s && %s < %s' % (variableForSelection, minVar,
variableForSelection, maxVar)
else:
selection = '%s >= %s' % (variableForSelection, minVar)
# Get exclusive templates for MC
input_files_exclusive = {
sample: input_files[sample]
for sample in ['TTJet', 'SingleTop', 'V+Jets', 'QCD']
}
# Get inclusive template for these (i.e. don't split up fit variable in bins of MET or whatever)
input_files_inclusive = {
sample: input_files[sample]
for sample in ['V+Jets']
}
# # Get control templates for QCD only, and inclusive
# input_files_control = input_files
# Get necessary histograms
# Signal, binned by e.g. MET, HT etc.
histograms_exclusive = get_histograms_from_trees(
trees=[tree],
branch=fit_variable,
selection=selection,
weightBranch=fullWeight,
files=input_files_exclusive,
nBins=nBins,
xMin=xMin,
xMax=xMax)
# Signal, not binned. For V+Jets template
histograms_inclusive = get_histograms_from_trees(
trees=[tree],
branch=fit_variable,
weightBranch=fullWeight,
files=input_files_inclusive,
nBins=nBins,
xMin=xMin,
xMax=xMax)
# Control, not binned. For QCD template
histograms_control_inclusive = get_histograms_from_trees(
trees=[control_tree],
branch=fit_variable,
weightBranch=fullWeight,
files=input_files,
nBins=nBins,
xMin=xMin,
xMax=xMax)
# Currently needed, as get_histograms_from_trees returns the histograms as part of a more complicated structure
for histogram in histograms_data:
for d in histograms_data[histogram]:
histograms_data[histogram] = histograms_data[histogram][d].Clone()
for histogram in histograms_exclusive:
for d in histograms_exclusive[histogram]:
histograms_exclusive[histogram] = histograms_exclusive[histogram][
d].Clone()
for histogram in histograms_inclusive:
for d in histograms_inclusive[histogram]:
histograms_inclusive[histogram] = histograms_inclusive[histogram][
d].Clone()
for histogram in histograms_control_inclusive:
for d in histograms_control_inclusive[histogram]:
histograms_control_inclusive[
histogram] = histograms_control_inclusive[histogram][d].Clone(
)
# Put all histograms into one dictionary
histograms = {}
histograms.update(histograms_exclusive)
# Always use central data sample
histograms['data'] = histograms_data['data']
# Get QCD distribution from data
# histograms['QCD'] = get_data_derived_qcd(histograms_control_inclusive, histograms_exclusive['QCD'])
# histograms['V+Jets'] = get_inclusive_histogram( histograms_inclusive['V+Jets'], histograms['V+Jets'] )
# normalise histograms
if not measurement_config.luminosity_scale == 1.0:
for sample, histogram in histograms.iteritems():
if sample == 'data':
continue
histogram.Scale(measurement_config.luminosity_scale)
# # apply normalisation scale factors for rate-changing systematics
if scale_factors:
for source, factor in scale_factors.iteritems():
for sample, histogram in histograms.iteritems():
if 'luminosity' in source:
if sample is 'data':
# Skip data for luminosity systematic
continue
else:
histogram.Scale(factor)
# For cross section systematics, only change normalisation of relevant sample
elif sample in source:
histogram.Scale(factor)
return histograms
def get_histograms( channel, input_files, variable, met_type, variable_bin,
b_tag_bin, rebin = 1, fit_variable = 'absolute_eta',
scale_factors = None ):
global b_tag_bin_VJets, fit_variables
global electron_control_region, muon_control_region
boundaries = measurement_config.fit_boundaries[fit_variable]
histograms = {}
tree = measurement_config.tree_path_templates[channel]
control_tree = measurement_config.tree_path_control_templates[channel]
print variable, fit_variable
# fit_variable_name = ''
# fit_variable_name_data = ''
# ht_fill_list, other_fill_list = None, None
# if fit_variable == 'absolute_eta':
# ht_fill_list = ( analysis_type[channel], variable_bin, channel + '_' + fit_variable )
# other_fill_list = ( analysis_type[channel], met_type, variable_bin, channel + '_' + fit_variable )
# else:
# ht_fill_list = ( analysis_type[channel], variable_bin, fit_variable )
# other_fill_list = ( analysis_type[channel], met_type, variable_bin, fit_variable )
# if variable == 'HT':
# fit_variable_name = fit_variable_template % ht_fill_list
# fit_variable_name_data = fit_variable_name
# else:
# fit_variable_name = fit_variable_template % other_fill_list
# if 'JetRes' in met_type:
# fit_variable_name_data = fit_variable_name.replace( 'JetResDown', '' )
# fit_variable_name_data = fit_variable_name_data.replace( 'JetResUp', '' )
# if 'patPFMet' in met_type:
# fit_variable_name = fit_variable_name.replace( 'patPFMet', 'PFMET' )
# else:
# fit_variable_name_data = fit_variable_name
# Work out bin of variable
minVar = variable_bin.split('-')[0]
maxVar = variable_bin.split('-')[-1]
if maxVar != 'inf' :
selection = '%s >= %s && %s < %s' % ( variable, minVar, variable, maxVar)
else :
selection = '%s >= %s' % ( variable, minVar )
# Get inclusive template for these (i.e. don't split up fit variable in bins of MET or whatever)
input_files_inclusive = { sample : input_files[sample] for sample in ['V+Jets'] }
# # Get control templates for QCD only, and inclusive
# input_files_control = input_files
print selection, fit_variable
bins = fit_variable_bin_edges[fit_variable]
xMin = bins[0]
xMax = bins[-1]
nBins = len(bins) -1
# Get necessary histograms
# Signal, binned by e.g. MET, HT etc.
histograms_exclusive = get_histograms_from_trees( trees = [tree], branch = fit_variable, selection = selection, weightBranch = 'EventWeight', files = input_files, nBins = nBins, xMin = xMin, xMax = xMax )
# Signal, not binned. For V+Jets template
histograms_inclusive = get_histograms_from_trees( trees = [tree], branch = fit_variable, weightBranch = 'EventWeight', files = input_files_inclusive, nBins = nBins, xMin = xMin, xMax = xMax )
# Control, not binned. For QCD template
histograms_control_inclusive = get_histograms_from_trees( trees = [control_tree], branch = fit_variable, weightBranch = 'EventWeight', files = input_files, nBins = nBins, xMin = xMin, xMax = xMax )
# Currently needed, as get_histograms_from_trees returns the histograms as part of a more complicated structure
for histogram in histograms_exclusive:
for d in histograms_exclusive[histogram]:
histograms_exclusive[histogram] = histograms_exclusive[histogram][d].Clone()
for histogram in histograms_inclusive:
for d in histograms_inclusive[histogram]:
histograms_inclusive[histogram] = histograms_inclusive[histogram][d].Clone()
for histogram in histograms_control_inclusive:
for d in histograms_control_inclusive[histogram]:
histograms_control_inclusive[histogram] = histograms_control_inclusive[histogram][d].Clone()
# Put all histograms into one dictionary
histograms = {}
histograms.update(histograms_exclusive)
# Get QCD distribution from data
histograms['QCD'] = get_data_derived_qcd(histograms_control_inclusive, histograms_exclusive['QCD'])
histograms['V+Jets'] = get_inclusive_histogram( histograms_inclusive['V+Jets'], histograms['V+Jets'] )
# normalise histograms
if not measurement_config.luminosity_scale == 1.0:
for sample, histogram in histograms.iteritems():
if sample == 'data':
continue
histogram.Scale( measurement_config.luminosity_scale )
# # apply normalisation scale factors for rate-changing systematics
# if scale_factors:
# for source, factor in scale_factors.iteritems():
# if 'luminosity' in source:
# for sample, histogram in histograms.iteritems():
# if sample == 'data':
# continue
# histogram.Scale( factor )
# for sample, histogram in histograms.iteritems():
# if sample in source:
# histogram.Scale( factor )
return histograms
def get_histograms( channel, input_files, variable, met_systematic, met_type, variable_bin,
b_tag_bin,
treePrefix, weightBranch,
rebin = 1, fit_variable = 'absolute_eta',
scale_factors = None ):
global b_tag_bin_VJets, fit_variables
global electron_control_region, muon_control_region
boundaries = measurement_config.fit_boundaries[fit_variable]
histograms = {}
tree = measurement_config.tree_path_templates[channel]
control_tree = measurement_config.tree_path_control_templates[channel]
# Put together weight
fullWeight = 'EventWeight'
if weightBranch != '' :
fullWeight += ' * %s' % weightBranch
# Work out bin of variable
variableForSelection = variable
minVar = variable_bin.split('-')[0]
maxVar = variable_bin.split('-')[-1]
selection = ''
if maxVar != 'inf' :
selection = '%s >= %s && %s < %s' % ( variableForSelection, minVar, variableForSelection, maxVar)
else :
selection = '%s >= %s' % ( variableForSelection, minVar )
bins = fit_variable_bin_edges[fit_variable]
xMin = bins[0]
xMax = bins[-1]
nBins = len(bins) -1
# Get data files here, without any systematic variations
data_files = { sample : input_files[sample] for sample in ['data'] }
histograms_data = get_histograms_from_trees( trees = [tree], branch = fit_variable, selection = selection, weightBranch = fullWeight, files = data_files, nBins = nBins, xMin = xMin, xMax = xMax )
# Now work out tree/variable for MC
# Identical for data if central, different for systematics
tree = tree + treePrefix
if met_systematic:
if variable == 'MET':
variableForSelection = 'MET_METUncertainties[%i]' % met_systematics[met_systematic]
elif variable == 'ST':
variableForSelection = 'ST_METUncertainties[%i]' % met_systematics[met_systematic]
# Work out selection again for MC, as variable (e.g. MET) could be different after systematic variation
if maxVar != 'inf' :
selection = '%s >= %s && %s < %s' % ( variableForSelection, minVar, variableForSelection, maxVar)
else :
selection = '%s >= %s' % ( variableForSelection, minVar )
# Get exclusive templates for MC
input_files_exclusive = { sample : input_files[sample] for sample in ['TTJet', 'SingleTop', 'V+Jets', 'QCD'] }
# Get inclusive template for these (i.e. don't split up fit variable in bins of MET or whatever)
input_files_inclusive = { sample : input_files[sample] for sample in ['V+Jets'] }
# # Get control templates for QCD only, and inclusive
# input_files_control = input_files
# Get necessary histograms
# Signal, binned by e.g. MET, HT etc.
histograms_exclusive = get_histograms_from_trees( trees = [tree], branch = fit_variable, selection = selection, weightBranch = fullWeight, files = input_files_exclusive, nBins = nBins, xMin = xMin, xMax = xMax )
# Signal, not binned. For V+Jets template
histograms_inclusive = get_histograms_from_trees( trees = [tree], branch = fit_variable, weightBranch = fullWeight, files = input_files_inclusive, nBins = nBins, xMin = xMin, xMax = xMax )
# Control, not binned. For QCD template
histograms_control_inclusive = get_histograms_from_trees( trees = [control_tree], branch = fit_variable, weightBranch = fullWeight, files = input_files, nBins = nBins, xMin = xMin, xMax = xMax )
# Currently needed, as get_histograms_from_trees returns the histograms as part of a more complicated structure
for histogram in histograms_data:
for d in histograms_data[histogram]:
histograms_data[histogram] = histograms_data[histogram][d].Clone()
for histogram in histograms_exclusive:
for d in histograms_exclusive[histogram]:
histograms_exclusive[histogram] = histograms_exclusive[histogram][d].Clone()
for histogram in histograms_inclusive:
for d in histograms_inclusive[histogram]:
histograms_inclusive[histogram] = histograms_inclusive[histogram][d].Clone()
for histogram in histograms_control_inclusive:
for d in histograms_control_inclusive[histogram]:
histograms_control_inclusive[histogram] = histograms_control_inclusive[histogram][d].Clone()
# Put all histograms into one dictionary
histograms = {}
histograms.update(histograms_exclusive)
# Always use central data sample
histograms['data'] = histograms_data['data']
# Get QCD distribution from data
# histograms['QCD'] = get_data_derived_qcd(histograms_control_inclusive, histograms_exclusive['QCD'])
# histograms['V+Jets'] = get_inclusive_histogram( histograms_inclusive['V+Jets'], histograms['V+Jets'] )
# normalise histograms
if not measurement_config.luminosity_scale == 1.0:
for sample, histogram in histograms.iteritems():
if sample == 'data':
continue
histogram.Scale( measurement_config.luminosity_scale )
# # apply normalisation scale factors for rate-changing systematics
if scale_factors:
for source, factor in scale_factors.iteritems():
for sample, histogram in histograms.iteritems():
if 'luminosity' in source:
if sample is 'data':
# Skip data for luminosity systematic
continue
else:
histogram.Scale( factor )
# For cross section systematics, only change normalisation of relevant sample
elif sample in source :
histogram.Scale( factor )
return histograms
def make_ttbarReco_plot(
channel,
x_axis_title,
y_axis_title,
signal_region_tree,
control_region_tree,
branchName,
name_prefix,
x_limits,
nBins,
use_qcd_data_region=False,
y_limits=[],
y_max_scale=1.2,
rebin=1,
legend_location=(0.98, 0.78),
cms_logo_location='right',
log_y=False,
legend_color=False,
ratio_y_limits=[0.3, 1.7],
normalise=False,
):
global output_folder, measurement_config, category, normalise_to_fit
global preliminary, norm_variable, sum_bins, b_tag_bin, histogram_files
# Input files, normalisations, tree/region names
qcd_data_region = ''
title = title_template % (measurement_config.new_luminosity / 1000.,
measurement_config.centre_of_mass_energy)
normalisation = None
if channel == 'electron':
histogram_files['data'] = measurement_config.data_file_electron_trees
histogram_files[
'QCD'] = measurement_config.electron_QCD_MC_category_templates_trees[
category]
if normalise_to_fit:
normalisation = normalisations_electron[norm_variable]
if use_qcd_data_region:
qcd_data_region = 'QCDConversions'
if channel == 'muon':
histogram_files['data'] = measurement_config.data_file_muon_trees
histogram_files[
'QCD'] = measurement_config.muon_QCD_MC_category_templates_trees[
category]
if normalise_to_fit:
normalisation = normalisations_muon[norm_variable]
if use_qcd_data_region:
qcd_data_region = 'QCD non iso mu+jets ge3j'
histograms = get_histograms_from_trees(
trees=[signal_region_tree, control_region_tree],
branch=branchName,
weightBranch='1',
files=histogram_files,
nBins=nBins,
xMin=x_limits[0],
xMax=x_limits[-1])
selection = 'SolutionCategory == 0'
histogramsNoSolution = get_histograms_from_trees(
trees=[signal_region_tree],
branch=branchName,
weightBranch='1',
selection=selection,
files=histogram_files,
nBins=nBins,
xMin=x_limits[0],
xMax=x_limits[-1])
selection = 'SolutionCategory == 1'
histogramsCorrect = get_histograms_from_trees(trees=[signal_region_tree],
branch=branchName,
weightBranch='1',
selection=selection,
files=histogram_files,
nBins=nBins,
xMin=x_limits[0],
xMax=x_limits[-1])
selection = 'SolutionCategory == 2'
histogramsNotSL = get_histograms_from_trees(trees=[signal_region_tree],
branch=branchName,
weightBranch='1',
selection=selection,
files=histogram_files,
nBins=nBins,
xMin=x_limits[0],
xMax=x_limits[-1])
selection = 'SolutionCategory == 3'
histogramsNotReco = get_histograms_from_trees(trees=[signal_region_tree],
branch=branchName,
weightBranch='1',
selection=selection,
files=histogram_files,
nBins=nBins,
xMin=x_limits[0],
xMax=x_limits[-1])
selection = 'SolutionCategory > 3'
histogramsWrong = get_histograms_from_trees(trees=[signal_region_tree],
branch=branchName,
weightBranch='1',
selection=selection,
files=histogram_files,
nBins=nBins,
xMin=x_limits[0],
xMax=x_limits[-1])
# Split histograms up into signal/control (?)
signal_region_hists = {}
inclusive_control_region_hists = {}
for sample in histograms.keys():
signal_region_hists[sample] = histograms[sample][signal_region_tree]
if use_qcd_data_region:
inclusive_control_region_hists[sample] = histograms[sample][
control_region_tree]
prepare_histograms(histograms,
rebin=1,
scale_factor=measurement_config.luminosity_scale)
prepare_histograms(histogramsNoSolution,
rebin=1,
scale_factor=measurement_config.luminosity_scale)
prepare_histograms(histogramsCorrect,
rebin=1,
scale_factor=measurement_config.luminosity_scale)
prepare_histograms(histogramsNotSL,
rebin=1,
scale_factor=measurement_config.luminosity_scale)
prepare_histograms(histogramsNotReco,
rebin=1,
scale_factor=measurement_config.luminosity_scale)
prepare_histograms(histogramsWrong,
rebin=1,
scale_factor=measurement_config.luminosity_scale)
qcd_from_data = signal_region_hists['QCD']
# Which histograms to draw, and properties
histograms_to_draw = [
signal_region_hists['data'], qcd_from_data,
signal_region_hists['V+Jets'], signal_region_hists['SingleTop'],
histogramsNoSolution['TTJet'][signal_region_tree],
histogramsNotSL['TTJet'][signal_region_tree],
histogramsNotReco['TTJet'][signal_region_tree],
histogramsWrong['TTJet'][signal_region_tree],
histogramsCorrect['TTJet'][signal_region_tree]
]
histogram_lables = [
'data',
'QCD',
'V+Jets',
'Single-Top',
samples_latex['TTJet'] + ' - no solution',
samples_latex['TTJet'] + ' - not SL',
samples_latex['TTJet'] + ' - not reconstructible',
samples_latex['TTJet'] + ' - wrong reco',
samples_latex['TTJet'] + ' - correct',
]
histogram_colors = [
'black', 'yellow', 'green', 'magenta', 'black', 'burlywood',
'chartreuse', 'blue', 'red'
]
histogram_properties = Histogram_properties()
histogram_properties.name = name_prefix + b_tag_bin
if category != 'central':
histogram_properties.name += '_' + category
histogram_properties.title = title
histogram_properties.x_axis_title = x_axis_title
histogram_properties.y_axis_title = y_axis_title
histogram_properties.x_limits = x_limits
histogram_properties.y_limits = y_limits
histogram_properties.y_max_scale = y_max_scale
histogram_properties.xerr = None
# workaround for rootpy issue #638
histogram_properties.emptybins = True
if b_tag_bin:
histogram_properties.additional_text = channel_latex[
channel] + ', ' + b_tag_bins_latex[b_tag_bin]
else:
histogram_properties.additional_text = channel_latex[channel]
histogram_properties.legend_location = legend_location
histogram_properties.cms_logo_location = cms_logo_location
histogram_properties.preliminary = preliminary
histogram_properties.set_log_y = log_y
histogram_properties.legend_color = legend_color
if ratio_y_limits:
histogram_properties.ratio_y_limits = ratio_y_limits
if normalise_to_fit:
histogram_properties.mc_error = get_normalisation_error(normalisation)
histogram_properties.mc_errors_label = 'fit uncertainty'
else:
histogram_properties.mc_error = mc_uncertainty
histogram_properties.mc_errors_label = 'MC unc.'
# Actually draw histograms
make_data_mc_comparison_plot(
histograms_to_draw,
histogram_lables,
histogram_colors,
histogram_properties,
save_folder=output_folder,
show_ratio=False,
normalise=normalise,
)
histogram_properties.name += '_with_ratio'
loc = histogram_properties.legend_location
# adjust legend location as it is relative to canvas!
histogram_properties.legend_location = (loc[0], loc[1] + 0.05)
make_data_mc_comparison_plot(
histograms_to_draw,
histogram_lables,
histogram_colors,
histogram_properties,
save_folder=output_folder,
show_ratio=True,
normalise=normalise,
)
