def plot_bias_in_all_bins(biases, mean_bias, centre_of_mass, channel, variable,
tau_value, output_folder, output_formats, bin_edges):
h_bias = Hist(bin_edges, type='D')
n_bins = h_bias.nbins()
assert len(biases) == n_bins
for i, bias in enumerate(biases):
h_bias.SetBinContent(i + 1, bias)
histogram_properties = Histogram_properties()
name_mpt = 'bias_{0}_{1}_{2}TeV'
histogram_properties.name = name_mpt.format(variable, channel,
centre_of_mass)
histogram_properties.y_axis_title = 'Bias'
histogram_properties.x_axis_title = latex_labels.variables_latex[variable]
title = 'pull distribution mean \& sigma for {0}'.format(tau_value)
histogram_properties.title = title
histogram_properties.y_limits = [0, 10]
histogram_properties.xerr = True
compare_measurements(
models={'Mean bias': make_line_hist(bin_edges, mean_bias)},
measurements={'Bias': h_bias},
show_measurement_errors=True,
histogram_properties=histogram_properties,
save_folder=output_folder,
save_as=output_formats)
def plot_bias_in_all_bins(biases, mean_bias, centre_of_mass, channel, variable,
tau_value, output_folder, output_formats, bin_edges):
h_bias = Hist(bin_edges, type='D')
n_bins = h_bias.nbins()
assert len(biases) == n_bins
for i, bias in enumerate(biases):
h_bias.SetBinContent(i+1, bias)
histogram_properties = Histogram_properties()
name_mpt = 'bias_{0}_{1}_{2}TeV'
histogram_properties.name = name_mpt.format(
variable,
channel,
centre_of_mass
)
histogram_properties.y_axis_title = 'Bias'
histogram_properties.x_axis_title = latex_labels.variables_latex[variable]
title = 'pull distribution mean \& sigma for {0}'.format(tau_value)
histogram_properties.title = title
histogram_properties.y_limits = [0, 10]
histogram_properties.xerr = True
compare_measurements(
models={
'Mean bias':make_line_hist(bin_edges, mean_bias)
},
measurements={
'Bias': h_bias
},
show_measurement_errors=True,
histogram_properties=histogram_properties,
save_folder=output_folder,
save_as=output_formats)
def plot_bias(unfolded_and_truths, variable, channel, come, method):
hp = Histogram_properties()
hp.name = 'Bias_{channel}_{variable}_at_{come}TeV'.format(
channel=channel,
variable=variable,
come=come,
)
v_latex = latex_labels.variables_latex[variable]
unit = ''
if variable in ['HT', 'ST', 'MET', 'WPT', 'lepton_pt']:
unit = ' [GeV]'
hp.x_axis_title = v_latex + unit
# plt.ylabel( r, CMS.y_axis_title )
hp.y_axis_title = 'Unfolded / Truth'
hp.y_limits = [0.92, 1.08]
hp.title = 'Bias for {variable}'.format(variable=v_latex)
output_folder = 'plots/unfolding/bias_test/'
measurements = { 'Central' : unfolded_and_truths['Central']['bias'] }
models = {}
for sample in unfolded_and_truths:
if sample == 'Central' : continue
models[sample] = unfolded_and_truths[sample]['bias']
compare_measurements(
models = models,
measurements = measurements,
show_measurement_errors=True,
histogram_properties=hp,
save_folder=output_folder,
save_as=['pdf'],
match_models_to_measurements = True)
def plot_results(results):
'''
Takes results fo the form:
{centre-of-mass-energy: {
channel : {
variable : {
fit_variable : {
test : { sample : []},
}
}
}
}
}
'''
global options
output_base = 'plots/fit_checks/chi2'
for COMEnergy in results.keys():
tmp_result_1 = results[COMEnergy]
for channel in tmp_result_1.keys():
tmp_result_2 = tmp_result_1[channel]
for variable in tmp_result_2.keys():
tmp_result_3 = tmp_result_2[variable]
for fit_variable in tmp_result_3.keys():
tmp_result_4 = tmp_result_3[fit_variable]
# histograms should be {sample: {test : histogram}}
histograms = {}
for test, chi2 in tmp_result_4.iteritems():
for sample in chi2.keys():
if not histograms.has_key(sample):
histograms[sample] = {}
# reverse order of test and sample
histograms[sample][test] = value_tuplelist_to_hist(
chi2[sample], bin_edges_vis[variable])
for sample in histograms.keys():
hist_properties = Histogram_properties()
hist_properties.name = sample.replace('+',
'') + '_chi2'
hist_properties.title = '$\\chi^2$ distribution for fit output (' + sample + ')'
hist_properties.x_axis_title = '$' + latex_labels.variables_latex[
variable] + '$ [TeV]'
hist_properties.y_axis_title = '$\chi^2 = \\left({N_{fit}} - N_{{exp}}\\right)^2$'
hist_properties.set_log_y = True
hist_properties.y_limits = (1e-20, 1e20)
path = output_base + '/' + COMEnergy + 'TeV/' + channel + '/' + variable + '/' + fit_variable + '/'
if options.test:
path = output_base + '/test/'
measurements = {}
for test, histogram in histograms[sample].iteritems():
measurements[test.replace('_', ' ')] = histogram
compare_measurements(
{},
measurements,
show_measurement_errors=False,
histogram_properties=hist_properties,
save_folder=path,
save_as=['pdf'])
def plot_results ( results ):
'''
Takes results fo the form:
{centre-of-mass-energy: {
channel : {
variable : {
fit_variable : {
test : { sample : []},
}
}
}
}
}
'''
global options
output_base = 'plots/fit_checks/chi2'
for COMEnergy in results.keys():
tmp_result_1 = results[COMEnergy]
for channel in tmp_result_1.keys():
tmp_result_2 = tmp_result_1[channel]
for variable in tmp_result_2.keys():
tmp_result_3 = tmp_result_2[variable]
for fit_variable in tmp_result_3.keys():
tmp_result_4 = tmp_result_3[fit_variable]
# histograms should be {sample: {test : histogram}}
histograms = {}
for test, chi2 in tmp_result_4.iteritems():
for sample in chi2.keys():
if not histograms.has_key(sample):
histograms[sample] = {}
# reverse order of test and sample
histograms[sample][test] = value_tuplelist_to_hist(chi2[sample], bin_edges_vis[variable])
for sample in histograms.keys():
hist_properties = Histogram_properties()
hist_properties.name = sample.replace('+', '') + '_chi2'
hist_properties.title = '$\\chi^2$ distribution for fit output (' + sample + ')'
hist_properties.x_axis_title = '$' + latex_labels.variables_latex[variable] + '$ [TeV]'
hist_properties.y_axis_title = '$\chi^2 = \\left({N_{fit}} - N_{{exp}}\\right)^2$'
hist_properties.set_log_y = True
hist_properties.y_limits = (1e-20, 1e20)
path = output_base + '/' + COMEnergy + 'TeV/' + channel + '/' + variable + '/' + fit_variable + '/'
if options.test:
path = output_base + '/test/'
measurements = {}
for test, histogram in histograms[sample].iteritems():
measurements[test.replace('_',' ')] = histogram
compare_measurements({},
measurements,
show_measurement_errors = False,
histogram_properties = hist_properties,
save_folder = path,
save_as = ['pdf'])
def plot_bias(unfolded_and_truths, variable, channel, come, method, prefix, plot_systematics=False):
hp = Histogram_properties()
hp.name = 'Bias_{prefix}_{channel}_{variable}_at_{come}TeV'.format(
prefix=prefix,
channel=channel,
variable=variable,
come=come,
)
v_latex = latex_labels.variables_latex[variable]
unit = ''
if variable in ['HT', 'ST', 'MET', 'WPT', 'lepton_pt']:
unit = ' [GeV]'
hp.x_axis_title = v_latex + unit
# plt.ylabel( r, CMS.y_axis_title )
hp.y_axis_title = 'Unfolded / Truth'
hp.y_limits = [0.7, 1.5]
hp.title = 'Bias for {variable}'.format(variable=v_latex)
hp.legend_location = (0.98, 0.95)
output_folder = 'plots/unfolding/bias_test/'
measurements = {}
# measurements = { 'Central' : unfolded_and_truths['Central']['bias'] }
# for bin in range(0, unfolded_and_truths['Central']['bias'].GetNbinsX() + 1 ):
# unfolded_and_truths['Central']['bias'].SetBinError(bin,0)
models = OrderedDict()
lineStyles = []
for sample in unfolded_and_truths:
if sample == 'Central' or sample == 'Nominal':
lineStyles.append('dashed')
else:
lineStyles.append('dotted')
models[sample] = unfolded_and_truths[sample]['bias']
if plot_systematics:
models['systematicsup'], models['systematicsdown'] = get_systematics(variable,channel,come,method)
lineStyles.append('solid')
lineStyles.append('solid')
compare_measurements(
models = models,
measurements = measurements,
show_measurement_errors=True,
histogram_properties=hp,
save_folder=output_folder,
save_as=['pdf'],
line_styles_for_models = lineStyles,
match_models_to_measurements = True
)
def plot_fit_results(fit_results, centre_of_mass, channel, variable, k_value,
tau_value, output_folder, output_formats, bin_edges):
h_mean = Hist(bin_edges, type='D')
h_sigma = Hist(bin_edges, type='D')
n_bins = h_mean.nbins()
assert len(fit_results) == n_bins
mean_abs_pull = 0
for i, fr in enumerate(fit_results):
mean_abs_pull += abs(fr.mean)
h_mean.SetBinContent(i + 1, fr.mean)
h_mean.SetBinError(i + 1, fr.meanError)
h_sigma.SetBinContent(i + 1, fr.sigma)
h_sigma.SetBinError(i + 1, fr.sigmaError)
mean_abs_pull /= n_bins
histogram_properties = Histogram_properties()
name_mpt = 'pull_distribution_mean_and_sigma_{0}_{1}_{2}TeV'
histogram_properties.name = name_mpt.format(
variable,
channel,
centre_of_mass
)
histogram_properties.y_axis_title = r'$\mu_{\text{pull}}$ ($\sigma_{\text{pull}}$)'
histogram_properties.x_axis_title = latex_labels.variables_latex[variable]
histogram_properties.legend_location = (0.98, 0.48)
value = get_value_title(k_value, tau_value)
title = 'pull distribution mean \& sigma for {0}'.format(tau_value)
histogram_properties.title = title
histogram_properties.y_limits = [-2, 2]
histogram_properties.xerr = True
compare_measurements(
models={
# 'mean $|\mu|$':make_line_hist(bin_edges,mean_abs_pull),
'ideal $\mu$': make_line_hist(bin_edges, 0),
'ideal $\sigma$': make_line_hist(bin_edges, 1),
},
measurements={
r'$\mu_{\text{pull}}$': h_mean,
r'$\sigma_{\text{pull}}$': h_sigma
},
show_measurement_errors=True,
histogram_properties=histogram_properties,
save_folder=output_folder,
save_as=output_formats)
def plot_bias(unfolded_and_truths, variable, channel, come, method):
hp = Histogram_properties()
hp.name = 'Bias_{channel}_{variable}_at_{come}TeV'.format(
channel=channel,
variable=variable,
come=come,
)
v_latex = latex_labels.variables_latex[variable]
unit = ''
if variable in ['HT', 'ST', 'MET', 'WPT', 'lepton_pt']:
unit = ' [GeV]'
hp.x_axis_title = v_latex + unit
# plt.ylabel( r, CMS.y_axis_title )
hp.y_axis_title = 'Unfolded / Truth'
hp.y_limits = [0.85, 1.15]
hp.title = 'Bias for {variable}'.format(variable=v_latex)
output_folder = 'plots/unfolding/bias_test/'
measurements = { 'Central' : unfolded_and_truths['Central']['bias'] }
for bin in range(0, unfolded_and_truths['Central']['bias'].GetNbinsX() + 1 ):
unfolded_and_truths['Central']['bias'].SetBinError(bin,0)
# central_truth = unfolded_and_truths['Central']['truth']
# for label, hists in unfolded_and_truths.iteritems():
# truth = hists['truth']
# print label
# for i,j in zip( list(truth.y()), list(central_truth.y())) :
# print abs(1-i/j)*100
models = {}
for sample in unfolded_and_truths:
if sample == 'Central' : continue
models[sample] = unfolded_and_truths[sample]['bias']
compare_measurements(
models = models,
measurements = measurements,
show_measurement_errors=True,
histogram_properties=hp,
save_folder=output_folder,
save_as=['pdf'],
match_models_to_measurements = True)
def plot_fit_results(fit_results, centre_of_mass, channel, variable, k_value,
tau_value, output_folder, output_formats, bin_edges):
h_mean = Hist(bin_edges, type='D')
h_sigma = Hist(bin_edges, type='D')
n_bins = h_mean.nbins()
assert len(fit_results) == n_bins
mean_abs_pull = 0
for i, fr in enumerate(fit_results):
mean_abs_pull += abs(fr.mean)
h_mean.SetBinContent(i + 1, fr.mean)
h_mean.SetBinError(i + 1, fr.meanError)
h_sigma.SetBinContent(i + 1, fr.sigma)
h_sigma.SetBinError(i + 1, fr.sigmaError)
mean_abs_pull /= n_bins
histogram_properties = Histogram_properties()
name_mpt = 'pull_distribution_mean_and_sigma_{0}_{1}_{2}TeV'
histogram_properties.name = name_mpt.format(variable, channel,
centre_of_mass)
histogram_properties.y_axis_title = r'$\mu_{\text{pull}}$ ($\sigma_{\text{pull}}$)'
histogram_properties.x_axis_title = latex_labels.variables_latex[variable]
histogram_properties.legend_location = (0.98, 0.48)
value = get_value_title(k_value, tau_value)
title = 'pull distribution mean \& sigma for {0}'.format(tau_value)
histogram_properties.title = title
histogram_properties.y_limits = [-2, 2]
histogram_properties.xerr = True
compare_measurements(
models={
# 'mean $|\mu|$':make_line_hist(bin_edges,mean_abs_pull),
'ideal $\mu$': make_line_hist(bin_edges, 0),
'ideal $\sigma$': make_line_hist(bin_edges, 1),
},
measurements={
r'$\mu_{\text{pull}}$': h_mean,
r'$\sigma_{\text{pull}}$': h_sigma
},
show_measurement_errors=True,
histogram_properties=histogram_properties,
save_folder=output_folder,
save_as=output_formats)
def do_shape_check(channel, control_region_1, control_region_2, variable, normalisation, title, x_title, y_title, x_limits, y_limits,
name_region_1='conversions' , name_region_2='non-isolated electrons', name_region_3='fit results', rebin=1):
global b_tag_bin
# QCD shape comparison
if channel == 'electron':
histograms = get_histograms_from_files([control_region_1, control_region_2], histogram_files)
region_1 = histograms[channel][control_region_1].Clone() - histograms['TTJet'][control_region_1].Clone() - histograms['V+Jets'][control_region_1].Clone() - histograms['SingleTop'][control_region_1].Clone()
region_2 = histograms[channel][control_region_2].Clone() - histograms['TTJet'][control_region_2].Clone() - histograms['V+Jets'][control_region_2].Clone() - histograms['SingleTop'][control_region_2].Clone()
region_1.Rebin(rebin)
region_2.Rebin(rebin)
histogram_properties = Histogram_properties()
histogram_properties.name = 'QCD_control_region_comparison_' + channel + '_' + variable + '_' + b_tag_bin
histogram_properties.title = title + ', ' + b_tag_bins_latex[b_tag_bin]
histogram_properties.x_axis_title = x_title
histogram_properties.y_axis_title = 'arbitrary units/(0.1)'
histogram_properties.x_limits = x_limits
histogram_properties.y_limits = y_limits[0]
histogram_properties.mc_error = 0.0
histogram_properties.legend_location = 'upper right'
make_control_region_comparison(region_1, region_2,
name_region_1=name_region_1, name_region_2=name_region_2,
histogram_properties=histogram_properties, save_folder=output_folder)
# QCD shape comparison to fit results
histograms = get_histograms_from_files([control_region_1], histogram_files)
region_1_tmp = histograms[channel][control_region_1].Clone() - histograms['TTJet'][control_region_1].Clone() - histograms['V+Jets'][control_region_1].Clone() - histograms['SingleTop'][control_region_1].Clone()
region_1 = rebin_asymmetric(region_1_tmp, bin_edges_vis[variable])
fit_results_QCD = normalisation[variable]['QCD']
region_2 = value_error_tuplelist_to_hist(fit_results_QCD, bin_edges_vis[variable])
histogram_properties = Histogram_properties()
histogram_properties.name = 'QCD_control_region_comparison_' + channel + '_' + variable + '_fits_with_conversions_' + b_tag_bin
histogram_properties.title = title + ', ' + b_tag_bins_latex[b_tag_bin]
histogram_properties.x_axis_title = x_title
histogram_properties.y_axis_title = 'arbitrary units/(0.1)'
histogram_properties.x_limits = x_limits
histogram_properties.y_limits = y_limits[1]
histogram_properties.mc_error = 0.0
histogram_properties.legend_location = 'upper right'
make_control_region_comparison(region_1, region_2,
name_region_1=name_region_1, name_region_2=name_region_3,
histogram_properties=histogram_properties, save_folder=output_folder)
histograms = get_histograms_from_files([control_region_2], histogram_files)
region_1_tmp = histograms[channel][control_region_2].Clone() - histograms['TTJet'][control_region_2].Clone() - histograms['V+Jets'][control_region_2].Clone() - histograms['SingleTop'][control_region_2].Clone()
region_1 = rebin_asymmetric(region_1_tmp, bin_edges_vis[variable])
fit_results_QCD = normalisation[variable]['QCD']
region_2 = value_error_tuplelist_to_hist(fit_results_QCD, bin_edges_vis[variable])
histogram_properties = Histogram_properties()
histogram_properties.name = 'QCD_control_region_comparison_' + channel + '_' + variable + '_fits_with_noniso_' + b_tag_bin
histogram_properties.title = title + ', ' + b_tag_bins_latex[b_tag_bin]
histogram_properties.x_axis_title = x_title
histogram_properties.y_axis_title = 'arbitrary units/(0.1)'
histogram_properties.x_limits = x_limits
histogram_properties.y_limits = y_limits[1]
histogram_properties.mc_error = 0.0
histogram_properties.legend_location = 'upper right'
make_control_region_comparison(region_1, region_2,
name_region_1=name_region_2, name_region_2=name_region_3,
histogram_properties=histogram_properties, save_folder=output_folder)
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,
)
# plot with matplotlib
plot_with_plotting_script = True
if plot_with_plotting_script:
properties = Histogram_properties()
properties.name = 'matplotlib_hist'
properties.x_axis_title = 'Mass'
properties.y_axis_title = 'Events'
make_data_mc_comparison_plot( [h3, h1, h2], ['data', 'background', 'signal'], ['black', 'green', 'red'], properties )
properties.name += '_with_ratio'
make_data_mc_comparison_plot( [h3, h1, h2], ['data', 'background', 'signal'], ['black', 'green', 'red'], properties, show_ratio = True )
properties.name = 'matplotlib_hist_comparison'
properties.y_limits = [0, 0.4]
make_control_region_comparison( h1, h2, 'background', 'signal', properties )
else:
fig = plt.figure(figsize=(14, 10), dpi=300)#, facecolor='white')
axes = plt.axes()
axes.xaxis.set_minor_locator(AutoMinorLocator())
axes.yaxis.set_minor_locator(AutoMinorLocator())
# axes.yaxis.set_major_locator(MultipleLocator(20))
axes.tick_params(which='major', labelsize=15, length=8)
axes.tick_params(which='minor', length=4)
rplt.errorbar(h3, xerr=False, emptybins=False, axes=axes, zorder = 4)
rplt.hist(stack, stacked=True, axes=axes, zorder = 1)
plt.xlabel('Mass', position=(1., 0.), ha='right')
plt.ylabel('Events', position=(0., 1.), va='bottom', ha='right')
plt.legend(numpoints=1)
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 plotHistograms(
histogram_files,
var_to_plot,
output_folder):
'''
'''
global measurement_config
weightBranchSignalRegion = 'EventWeight * PUWeight * BJetWeight'
weightBranchControlRegion = 'EventWeight'
# Names of QCD regions to use
qcd_data_region = ''
qcd_data_region_electron = 'QCD non iso e+jets'
qcd_data_region_muon = 'QCD non iso mu+jets 1p5to3'
sr_e_tree = 'TTbar_plus_X_analysis/EPlusJets/Ref selection/AnalysisVariables'
sr_mu_tree = 'TTbar_plus_X_analysis/MuPlusJets/Ref selection/AnalysisVariables'
cr_e_tree = 'TTbar_plus_X_analysis/EPlusJets/{}/AnalysisVariables'.format(qcd_data_region_electron)
cr_mu_tree = 'TTbar_plus_X_analysis/MuPlusJets/{}/AnalysisVariables'.format(qcd_data_region_muon)
print "Trees : "
print "\t {}".format(sr_e_tree)
print "\t {}".format(sr_mu_tree)
print "\t {}".format(cr_e_tree)
print "\t {}".format(cr_mu_tree)
histogram_files_electron = dict(histogram_files)
histogram_files_electron['data'] = measurement_config.data_file_electron
histogram_files_electron['QCD'] = measurement_config.electron_QCD_MC_trees
histogram_files_muon = dict(histogram_files)
histogram_files_muon['data'] = measurement_config.data_file_muon
histogram_files_muon['QCD'] = measurement_config.muon_QCD_MC_trees
signal_region_hists = {}
control_region_hists = {}
for var in var_to_plot:
selectionSignalRegion = '{} >= 0'.format(var)
# Print all the weights applied to this plot
print "Variable : {}".format(var)
print "Weight applied : {}".format(weightBranchSignalRegion)
print "Selection applied : {}".format(selectionSignalRegion)
histograms_electron = get_histograms_from_trees(
trees = [sr_e_tree],
branch = var,
weightBranch = weightBranchSignalRegion + ' * ElectronEfficiencyCorrection',
files = histogram_files_electron,
nBins = 20,
xMin = control_plots_bins[var][0],
xMax = control_plots_bins[var][-1],
selection = selectionSignalRegion
)
histograms_muon = get_histograms_from_trees(
trees = [sr_mu_tree],
branch = var,
weightBranch = weightBranchSignalRegion + ' * MuonEfficiencyCorrection',
files = histogram_files_muon,
nBins = 20,
xMin = control_plots_bins[var][0],
xMax = control_plots_bins[var][-1],
selection = selectionSignalRegion
)
histograms_electron_QCDControlRegion = get_histograms_from_trees(
trees = [cr_e_tree],
branch = var,
weightBranch = weightBranchControlRegion,
files = histogram_files_electron,
nBins = 20,
xMin = control_plots_bins[var][0],
xMax = control_plots_bins[var][-1],
selection = selectionSignalRegion
)
histograms_muon_QCDControlRegion = get_histograms_from_trees(
trees = [cr_mu_tree],
branch = var,
weightBranch = weightBranchControlRegion,
files = histogram_files_muon,
nBins = 20,
xMin = control_plots_bins[var][0],
xMax = control_plots_bins[var][-1],
selection = selectionSignalRegion
)
# Combine the electron and muon histograms
for sample in histograms_electron:
h_electron = histograms_electron[sample][sr_e_tree]
h_muon = histograms_muon[sample][sr_mu_tree]
h_qcd_electron = histograms_electron_QCDControlRegion[sample][cr_e_tree]
h_qcd_muon = histograms_muon_QCDControlRegion[sample][cr_mu_tree]
signal_region_hists[sample] = h_electron + h_muon
control_region_hists[sample] = h_qcd_electron + h_qcd_muon
# NORMALISE TO LUMI
prepare_histograms(
signal_region_hists,
scale_factor = measurement_config.luminosity_scale
)
prepare_histograms(
control_region_hists,
scale_factor = measurement_config.luminosity_scale
)
# BACKGROUND SUBTRACTION FOR QCD
qcd_from_data = None
qcd_from_data = clean_control_region(
control_region_hists,
subtract = ['TTJet', 'V+Jets', 'SingleTop']
)
# DATA DRIVEN QCD
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)
dataDrivenQCDScale = n_qcd_predicted_mc_signal / n_qcd_predicted_mc_control
qcd_from_data.Scale( dataDrivenQCDScale.nominal_value )
signal_region_hists['QCD'] = qcd_from_data
# PLOTTING
histograms_to_draw = []
histogram_lables = []
histogram_colors = []
histograms_to_draw = [
# signal_region_hists['data'],
# qcd_from_data,
# signal_region_hists['V+Jets'],
signal_region_hists['SingleTop'],
signal_region_hists['ST_s'],
signal_region_hists['ST_t'],
signal_region_hists['ST_tW'],
signal_region_hists['STbar_t'],
signal_region_hists['STbar_tW'],
# signal_region_hists['TTJet'],
]
histogram_lables = [
'data',
# 'QCD',
# 'V+Jets',
# 'Single-Top',
'ST-s',
'ST-t',
'ST-tW',
'STbar-t',
'STbar-tW',
# samples_latex['TTJet'],
]
histogram_colors = [
colours['data'],
# colours['QCD'],
# colours['V+Jets'],
# colours['Single-Top'],
colours['ST_s'],
colours['ST_t'],
colours['ST_tW'],
colours['STbar_t'],
colours['STbar_tW'],
# colours['TTJet'],
]
# Find maximum y of samples
maxData = max( list(signal_region_hists['SingleTop'].y()) )
y_limits = [0, maxData * 1.5]
log_y = False
if log_y:
y_limits = [0.1, maxData * 100 ]
# Lumi title of plots
title_template = '%.1f fb$^{-1}$ (%d TeV)'
title = title_template % ( measurement_config.new_luminosity/1000., measurement_config.centre_of_mass_energy )
x_axis_title = '$%s$ [GeV]' % variables_latex[var]
y_axis_title = 'Events/(%i GeV)' % binWidth(control_plots_bins[var])
# More histogram settings to look semi decent
histogram_properties = Histogram_properties()
histogram_properties.name = var + '_with_ratio'
histogram_properties.title = title
histogram_properties.x_axis_title = x_axis_title
histogram_properties.y_axis_title = y_axis_title
histogram_properties.x_limits = control_plots_bins[var]
histogram_properties.y_limits = y_limits
histogram_properties.y_max_scale = 1.4
histogram_properties.xerr = None
histogram_properties.emptybins = True
histogram_properties.additional_text = channel_latex['combined']
histogram_properties.legend_location = ( 0.9, 0.73 )
histogram_properties.cms_logo_location = 'left'
histogram_properties.preliminary = True
histogram_properties.set_log_y = log_y
histogram_properties.legend_color = False
histogram_properties.ratio_y_limits = [0.1,1.9]
if log_y: histogram_properties.name += '_logy'
loc = histogram_properties.legend_location
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,
)
histogram_properties.name = var + '_ST_TTJet_Shape'
if log_y: histogram_properties.name += '_logy'
histogram_properties.y_axis_title = 'Normalised Distribution'
histogram_properties.y_limits = [0,0.5]
make_shape_comparison_plot(
shapes = [
signal_region_hists['TTJet'],
signal_region_hists['ST_t'],
signal_region_hists['ST_tW'],
signal_region_hists['ST_s'],
signal_region_hists['STbar_t'],
signal_region_hists['STbar_tW'],
],
names = [
samples_latex['TTJet'],
'Single-Top t channel',
'Single-Top tW channel',
'Single-Top s channel',
'Single-AntiTop t channel',
'Single-AntiTop tW channel',
],
colours = [
colours['TTJet'],
colours['ST_t'],
colours['ST_tW'],
colours['ST_s'],
colours['STbar_t'],
colours['STbar_tW'],
],
histogram_properties = histogram_properties,
save_folder = output_folder,
fill_area = False,
add_error_bars = False,
save_as = ['pdf'],
make_ratio = True,
alpha = 1,
)
print_output(signal_region_hists, output_folder, var, 'combined')
return
def make_correlation_plot_from_file( channel, variable, fit_variables, CoM, title, x_title, y_title, x_limits, y_limits, rebin = 1, save_folder = 'plots/fitchecks/', save_as = ['pdf', 'png'] ):
# global b_tag_bin
parameters = ["TTJet", "SingleTop", "V+Jets", "QCD"]
parameters_latex = []
for template in parameters:
parameters_latex.append(samples_latex[template])
input_file = open( "logs/01_%s_fit_%dTeV_%s.log" % ( variable, CoM, fit_variables ), "r" )
# cycle through the lines in the file
for line_number, line in enumerate( input_file ):
# for now, only make plots for the fits for the central measurement
if "central" in line:
# matrix we want begins 11 lines below the line with the measurement ("central")
line_number = line_number + 11
break
input_file.close()
#Note: For some reason, the fit outputs the correlation matrix with the templates in the following order:
#parameter1: QCD
#parameter2: SingleTop
#parameter3: TTJet
#parameter4: V+Jets
for variable_bin in variable_bins_ROOT[variable]:
weights = {}
if channel == 'electron':
#formula to calculate the number of lines below "central" to access in each loop
number_of_lines_down = (variable_bins_ROOT[variable].index( variable_bin ) * 12)
#Get QCD correlations
matrix_line = linecache.getline( "logs/01_%s_fit_%dTeV_%s.log" % ( variable, CoM, fit_variables ), line_number + number_of_lines_down )
weights["QCD_QCD"] = matrix_line.split()[2]
weights["QCD_SingleTop"] = matrix_line.split()[3]
weights["QCD_TTJet"] = matrix_line.split()[4]
weights["QCD_V+Jets"] = matrix_line.split()[5]
#Get SingleTop correlations
matrix_line = linecache.getline( "logs/01_%s_fit_%dTeV_%s.log" % ( variable, CoM, fit_variables ), line_number + number_of_lines_down + 1 )
weights["SingleTop_QCD"] = matrix_line.split()[2]
weights["SingleTop_SingleTop"] = matrix_line.split()[3]
weights["SingleTop_TTJet"] = matrix_line.split()[4]
weights["SingleTop_V+Jets"] = matrix_line.split()[5]
#Get TTJet correlations
matrix_line = linecache.getline( "logs/01_%s_fit_%dTeV_%s.log" % ( variable, CoM, fit_variables ), line_number + number_of_lines_down + 2 )
weights["TTJet_QCD"] = matrix_line.split()[2]
weights["TTJet_SingleTop"] = matrix_line.split()[3]
weights["TTJet_TTJet"] = matrix_line.split()[4]
weights["TTJet_V+Jets"] = matrix_line.split()[5]
#Get V+Jets correlations
matrix_line = linecache.getline( "logs/01_%s_fit_%dTeV_%s.log" % ( variable, CoM, fit_variables ), line_number + number_of_lines_down + 3 )
weights["V+Jets_QCD"] = matrix_line.split()[2]
weights["V+Jets_SingleTop"] = matrix_line.split()[3]
weights["V+Jets_TTJet"] = matrix_line.split()[4]
weights["V+Jets_V+Jets"] = matrix_line.split()[5]
if channel == 'muon':
#formula to calculate the number of lines below "central" to access in each bin loop
number_of_lines_down = ( len( variable_bins_ROOT [variable] ) * 12 ) + ( variable_bins_ROOT[variable].index( variable_bin ) * 12 )
#Get QCD correlations
matrix_line = linecache.getline( "logs/01_%s_fit_%dTeV_%s.log" % ( variable, CoM, fit_variables ), line_number + number_of_lines_down )
weights["QCD_QCD"] = matrix_line.split()[2]
weights["QCD_SingleTop"] = matrix_line.split()[3]
weights["QCD_TTJet"] = matrix_line.split()[4]
weights["QCD_V+Jets"] = matrix_line.split()[5]
#Get SingleTop correlations
matrix_line = linecache.getline( "logs/01_%s_fit_%dTeV_%s.log" % ( variable, CoM, fit_variables ), line_number + number_of_lines_down + 1 )
weights["SingleTop_QCD"] = matrix_line.split()[2]
weights["SingleTop_SingleTop"] = matrix_line.split()[3]
weights["SingleTop_TTJet"] = matrix_line.split()[4]
weights["SingleTop_V+Jets"] = matrix_line.split()[5]
#Get TTJet correlations
matrix_line = linecache.getline( "logs/01_%s_fit_%dTeV_%s.log" % ( variable, CoM, fit_variables ), line_number + number_of_lines_down + 2 )
weights["TTJet_QCD"] = matrix_line.split()[2]
weights["TTJet_SingleTop"] = matrix_line.split()[3]
weights["TTJet_TTJet"] = matrix_line.split()[4]
weights["TTJet_V+Jets"] = matrix_line.split()[5]
#Get V+Jets correlations
matrix_line = linecache.getline( "logs/01_%s_fit_%dTeV_%s.log" % ( variable, CoM, fit_variables ), line_number + number_of_lines_down + 3 )
weights["V+Jets_QCD"] = matrix_line.split()[2]
weights["V+Jets_SingleTop"] = matrix_line.split()[3]
weights["V+Jets_TTJet"] = matrix_line.split()[4]
weights["V+Jets_V+Jets"] = matrix_line.split()[5]
#Create histogram
histogram_properties = Histogram_properties()
histogram_properties.title = title
histogram_properties.name = 'Correlations_' + channel + '_' + variable + '_' + variable_bin
histogram_properties.y_axis_title = y_title
histogram_properties.x_axis_title = x_title
histogram_properties.y_limits = y_limits
histogram_properties.x_limits = x_limits
histogram_properties.mc_error = 0.0
histogram_properties.legend_location = 'upper right'
#initialise 2D histogram
a = Hist2D( 4, 0, 4, 4, 0, 4 )
#fill histogram
for i in range( len( parameters ) ):
for j in range( len( parameters ) ):
a.fill( float( i ), float( j ), float( weights["%s_%s" % ( parameters[i], parameters[j] )] ) )
# create figure
plt.figure( figsize = CMS.figsize, dpi = CMS.dpi, facecolor = CMS.facecolor )
# make subplot(?)
fig, ax = plt.subplots( nrows = 1, ncols = 1 )
rplt.hist2d( a )
plt.subplots_adjust( right = 0.8 )
#Set labels and formats for titles and axes
plt.ylabel( histogram_properties.y_axis_title )
plt.xlabel( histogram_properties.x_axis_title )
plt.title( histogram_properties.title )
x_limits = histogram_properties.x_limits
y_limits = histogram_properties.y_limits
ax.set_xticklabels( parameters_latex )
ax.set_yticklabels( parameters_latex )
ax.set_xticks( [0.5, 1.5, 2.5, 3.5] )
ax.set_yticks( [0.5, 1.5, 2.5, 3.5] )
plt.setp( ax.get_xticklabels(), visible = True )
plt.setp( ax.get_yticklabels(), visible = True )
#create and draw colour bar to the right of the main plot
im = rplt.imshow( a, axes = ax, vmin = -1.0, vmax = 1.0 )
#set location and dimensions (left, lower, width, height)
cbar_ax = fig.add_axes( [0.85, 0.10, 0.05, 0.8] )
fig.colorbar( im, cax = cbar_ax )
for xpoint in range( len( parameters ) ):
for ypoint in range( len( parameters ) ):
correlation_value = weights["%s_%s" % ( parameters[xpoint], parameters[ypoint] )]
ax.annotate( correlation_value, xy = ( xpoint + 0.5, ypoint + 0.5 ), ha = 'center', va = 'center', bbox = dict( fc = 'white', ec = 'none' ) )
for save in save_as:
plt.savefig( save_folder + histogram_properties.name + '.' + save )
plt.close(fig)
plt.close('all')
def do_shape_check(channel,
control_region_1,
control_region_2,
variable,
normalisation,
title,
x_title,
y_title,
x_limits,
y_limits,
name_region_1='conversions',
name_region_2='non-isolated electrons',
name_region_3='fit results',
rebin=1):
global b_tag_bin
# QCD shape comparison
if channel == 'electron':
histograms = get_histograms_from_files(
[control_region_1, control_region_2], histogram_files)
region_1 = histograms[channel][control_region_1].Clone(
) - histograms['TTJet'][control_region_1].Clone(
) - histograms['V+Jets'][control_region_1].Clone(
) - histograms['SingleTop'][control_region_1].Clone()
region_2 = histograms[channel][control_region_2].Clone(
) - histograms['TTJet'][control_region_2].Clone(
) - histograms['V+Jets'][control_region_2].Clone(
) - histograms['SingleTop'][control_region_2].Clone()
region_1.Rebin(rebin)
region_2.Rebin(rebin)
histogram_properties = Histogram_properties()
histogram_properties.name = 'QCD_control_region_comparison_' + channel + '_' + variable + '_' + b_tag_bin
histogram_properties.title = title + ', ' + b_tag_bins_latex[b_tag_bin]
histogram_properties.x_axis_title = x_title
histogram_properties.y_axis_title = 'arbitrary units/(0.1)'
histogram_properties.x_limits = x_limits
histogram_properties.y_limits = y_limits[0]
histogram_properties.mc_error = 0.0
histogram_properties.legend_location = 'upper right'
make_control_region_comparison(
region_1,
region_2,
name_region_1=name_region_1,
name_region_2=name_region_2,
histogram_properties=histogram_properties,
save_folder=output_folder)
# QCD shape comparison to fit results
histograms = get_histograms_from_files([control_region_1],
histogram_files)
region_1_tmp = histograms[channel][control_region_1].Clone(
) - histograms['TTJet'][control_region_1].Clone(
) - histograms['V+Jets'][control_region_1].Clone(
) - histograms['SingleTop'][control_region_1].Clone()
region_1 = rebin_asymmetric(region_1_tmp, bin_edges_vis[variable])
fit_results_QCD = normalisation[variable]['QCD']
region_2 = value_error_tuplelist_to_hist(fit_results_QCD,
bin_edges_vis[variable])
histogram_properties = Histogram_properties()
histogram_properties.name = 'QCD_control_region_comparison_' + channel + '_' + variable + '_fits_with_conversions_' + b_tag_bin
histogram_properties.title = title + ', ' + b_tag_bins_latex[b_tag_bin]
histogram_properties.x_axis_title = x_title
histogram_properties.y_axis_title = 'arbitrary units/(0.1)'
histogram_properties.x_limits = x_limits
histogram_properties.y_limits = y_limits[1]
histogram_properties.mc_error = 0.0
histogram_properties.legend_location = 'upper right'
make_control_region_comparison(
region_1,
region_2,
name_region_1=name_region_1,
name_region_2=name_region_3,
histogram_properties=histogram_properties,
save_folder=output_folder)
histograms = get_histograms_from_files([control_region_2], histogram_files)
region_1_tmp = histograms[channel][control_region_2].Clone(
) - histograms['TTJet'][control_region_2].Clone(
) - histograms['V+Jets'][control_region_2].Clone(
) - histograms['SingleTop'][control_region_2].Clone()
region_1 = rebin_asymmetric(region_1_tmp, bin_edges_vis[variable])
fit_results_QCD = normalisation[variable]['QCD']
region_2 = value_error_tuplelist_to_hist(fit_results_QCD,
bin_edges_vis[variable])
histogram_properties = Histogram_properties()
histogram_properties.name = 'QCD_control_region_comparison_' + channel + '_' + variable + '_fits_with_noniso_' + b_tag_bin
histogram_properties.title = title + ', ' + b_tag_bins_latex[b_tag_bin]
histogram_properties.x_axis_title = x_title
histogram_properties.y_axis_title = 'arbitrary units/(0.1)'
histogram_properties.x_limits = x_limits
histogram_properties.y_limits = y_limits[1]
histogram_properties.mc_error = 0.0
histogram_properties.legend_location = 'upper right'
make_control_region_comparison(region_1,
region_2,
name_region_1=name_region_2,
name_region_2=name_region_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)
def plotHistograms(histogram_files, var_to_plot, output_folder):
'''
'''
global measurement_config
weightBranchSignalRegion = 'EventWeight * PUWeight * BJetWeight'
weightBranchControlRegion = 'EventWeight'
# Names of QCD regions to use
qcd_data_region = ''
qcd_data_region_electron = 'QCD non iso e+jets'
qcd_data_region_muon = 'QCD non iso mu+jets 1p5to3'
sr_e_tree = 'TTbar_plus_X_analysis/EPlusJets/Ref selection/AnalysisVariables'
sr_mu_tree = 'TTbar_plus_X_analysis/MuPlusJets/Ref selection/AnalysisVariables'
cr_e_tree = 'TTbar_plus_X_analysis/EPlusJets/{}/AnalysisVariables'.format(
qcd_data_region_electron)
cr_mu_tree = 'TTbar_plus_X_analysis/MuPlusJets/{}/AnalysisVariables'.format(
qcd_data_region_muon)
print "Trees : "
print "\t {}".format(sr_e_tree)
print "\t {}".format(sr_mu_tree)
print "\t {}".format(cr_e_tree)
print "\t {}".format(cr_mu_tree)
histogram_files_electron = dict(histogram_files)
histogram_files_electron['data'] = measurement_config.data_file_electron
histogram_files_electron['QCD'] = measurement_config.electron_QCD_MC_trees
histogram_files_muon = dict(histogram_files)
histogram_files_muon['data'] = measurement_config.data_file_muon
histogram_files_muon['QCD'] = measurement_config.muon_QCD_MC_trees
signal_region_hists = {}
control_region_hists = {}
for var in var_to_plot:
selectionSignalRegion = '{} >= 0'.format(var)
# Print all the weights applied to this plot
print "Variable : {}".format(var)
print "Weight applied : {}".format(weightBranchSignalRegion)
print "Selection applied : {}".format(selectionSignalRegion)
histograms_electron = get_histograms_from_trees(
trees=[sr_e_tree],
branch=var,
weightBranch=weightBranchSignalRegion +
' * ElectronEfficiencyCorrection',
files=histogram_files_electron,
nBins=20,
xMin=control_plots_bins[var][0],
xMax=control_plots_bins[var][-1],
selection=selectionSignalRegion)
histograms_muon = get_histograms_from_trees(
trees=[sr_mu_tree],
branch=var,
weightBranch=weightBranchSignalRegion +
' * MuonEfficiencyCorrection',
files=histogram_files_muon,
nBins=20,
xMin=control_plots_bins[var][0],
xMax=control_plots_bins[var][-1],
selection=selectionSignalRegion)
histograms_electron_QCDControlRegion = get_histograms_from_trees(
trees=[cr_e_tree],
branch=var,
weightBranch=weightBranchControlRegion,
files=histogram_files_electron,
nBins=20,
xMin=control_plots_bins[var][0],
xMax=control_plots_bins[var][-1],
selection=selectionSignalRegion)
histograms_muon_QCDControlRegion = get_histograms_from_trees(
trees=[cr_mu_tree],
branch=var,
weightBranch=weightBranchControlRegion,
files=histogram_files_muon,
nBins=20,
xMin=control_plots_bins[var][0],
xMax=control_plots_bins[var][-1],
selection=selectionSignalRegion)
# Combine the electron and muon histograms
for sample in histograms_electron:
h_electron = histograms_electron[sample][sr_e_tree]
h_muon = histograms_muon[sample][sr_mu_tree]
h_qcd_electron = histograms_electron_QCDControlRegion[sample][
cr_e_tree]
h_qcd_muon = histograms_muon_QCDControlRegion[sample][cr_mu_tree]
signal_region_hists[sample] = h_electron + h_muon
control_region_hists[sample] = h_qcd_electron + h_qcd_muon
# NORMALISE TO LUMI
prepare_histograms(signal_region_hists,
scale_factor=measurement_config.luminosity_scale)
prepare_histograms(control_region_hists,
scale_factor=measurement_config.luminosity_scale)
# BACKGROUND SUBTRACTION FOR QCD
qcd_from_data = None
qcd_from_data = clean_control_region(
control_region_hists, subtract=['TTJet', 'V+Jets', 'SingleTop'])
# DATA DRIVEN QCD
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)
dataDrivenQCDScale = n_qcd_predicted_mc_signal / n_qcd_predicted_mc_control
qcd_from_data.Scale(dataDrivenQCDScale.nominal_value)
signal_region_hists['QCD'] = qcd_from_data
# PLOTTING
histograms_to_draw = []
histogram_lables = []
histogram_colors = []
histograms_to_draw = [
# signal_region_hists['data'],
# qcd_from_data,
# signal_region_hists['V+Jets'],
signal_region_hists['SingleTop'],
signal_region_hists['ST_s'],
signal_region_hists['ST_t'],
signal_region_hists['ST_tW'],
signal_region_hists['STbar_t'],
signal_region_hists['STbar_tW'],
# signal_region_hists['TTJet'],
]
histogram_lables = [
'data',
# 'QCD',
# 'V+Jets',
# 'Single-Top',
'ST-s',
'ST-t',
'ST-tW',
'STbar-t',
'STbar-tW',
# samples_latex['TTJet'],
]
histogram_colors = [
colours['data'],
# colours['QCD'],
# colours['V+Jets'],
# colours['Single-Top'],
colours['ST_s'],
colours['ST_t'],
colours['ST_tW'],
colours['STbar_t'],
colours['STbar_tW'],
# colours['TTJet'],
]
# Find maximum y of samples
maxData = max(list(signal_region_hists['SingleTop'].y()))
y_limits = [0, maxData * 1.5]
log_y = False
if log_y:
y_limits = [0.1, maxData * 100]
# Lumi title of plots
title_template = '%.1f fb$^{-1}$ (%d TeV)'
title = title_template % (measurement_config.new_luminosity / 1000.,
measurement_config.centre_of_mass_energy)
x_axis_title = '$%s$ [GeV]' % variables_latex[var]
y_axis_title = 'Events/(%i GeV)' % binWidth(control_plots_bins[var])
# More histogram settings to look semi decent
histogram_properties = Histogram_properties()
histogram_properties.name = var + '_with_ratio'
histogram_properties.title = title
histogram_properties.x_axis_title = x_axis_title
histogram_properties.y_axis_title = y_axis_title
histogram_properties.x_limits = control_plots_bins[var]
histogram_properties.y_limits = y_limits
histogram_properties.y_max_scale = 1.4
histogram_properties.xerr = None
histogram_properties.emptybins = True
histogram_properties.additional_text = channel_latex['combined']
histogram_properties.legend_location = (0.9, 0.73)
histogram_properties.cms_logo_location = 'left'
histogram_properties.preliminary = True
histogram_properties.set_log_y = log_y
histogram_properties.legend_color = False
histogram_properties.ratio_y_limits = [0.1, 1.9]
if log_y: histogram_properties.name += '_logy'
loc = histogram_properties.legend_location
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,
)
histogram_properties.name = var + '_ST_TTJet_Shape'
if log_y: histogram_properties.name += '_logy'
histogram_properties.y_axis_title = 'Normalised Distribution'
histogram_properties.y_limits = [0, 0.5]
make_shape_comparison_plot(
shapes=[
signal_region_hists['TTJet'],
signal_region_hists['ST_t'],
signal_region_hists['ST_tW'],
signal_region_hists['ST_s'],
signal_region_hists['STbar_t'],
signal_region_hists['STbar_tW'],
],
names=[
samples_latex['TTJet'],
'Single-Top t channel',
'Single-Top tW channel',
'Single-Top s channel',
'Single-AntiTop t channel',
'Single-AntiTop tW channel',
],
colours=[
colours['TTJet'],
colours['ST_t'],
colours['ST_tW'],
colours['ST_s'],
colours['STbar_t'],
colours['STbar_tW'],
],
histogram_properties=histogram_properties,
save_folder=output_folder,
fill_area=False,
add_error_bars=False,
save_as=['pdf'],
make_ratio=True,
alpha=1,
)
print_output(signal_region_hists, output_folder, var, 'combined')
return
def drawHistograms( dictionaryOfHistograms, uncertaintyBand, config, channel, variable ) :
histograms_to_draw = [
dictionaryOfHistograms['Data'],
dictionaryOfHistograms['QCD'],
dictionaryOfHistograms['V+Jets'],
dictionaryOfHistograms['SingleTop'],
dictionaryOfHistograms['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'],
]
# Find maximum y of samples
maxData = max( list(histograms_to_draw[0].y()) )
y_limits = [0, maxData * 1.4]
# More histogram settings to look semi decent
histogram_properties = Histogram_properties()
histogram_properties.name = '{channel}_{variable}'.format(channel = channel, variable=variable)
histogram_properties.title = '$%.1f$ fb$^{-1}$ (%d TeV)' % ( config.new_luminosity/1000., config.centre_of_mass_energy )
histogram_properties.x_axis_title = variables_latex[variable]
histogram_properties.y_axis_title = 'Events'
if variable in ['HT', 'ST', 'MET', 'WPT', 'lepton_pt']:
histogram_properties.y_axis_title = 'Events / {binWidth} GeV'.format( binWidth=binWidth )
histogram_properties.x_axis_title = '{variable} (GeV)'.format( variable = variables_latex[variable] )
histogram_properties.x_limits = [ reco_bin_edges[0], reco_bin_edges[-1] ]
histogram_properties.y_limits = y_limits
histogram_properties.y_max_scale = 1.3
histogram_properties.xerr = None
# workaround for rootpy issue #638
histogram_properties.emptybins = True
histogram_properties.additional_text = channel_latex[channel.lower()]
histogram_properties.legend_location = ( 0.9, 0.73 )
histogram_properties.cms_logo_location = 'left'
histogram_properties.preliminary = True
# histogram_properties.preliminary = False
histogram_properties.set_log_y = False
histogram_properties.legend_color = False
histogram_properties.ratio_y_limits = [0.5, 1.5]
# Draw histogram with ratio plot
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 = 'plots/control_plots_with_systematic/',
show_ratio = True,
normalise = False,
systematics_for_ratio = uncertaintyBand,
systematics_for_plot = uncertaintyBand,
)
histogram_properties.set_log_y = True
histogram_properties.y_limits = [0.1, y_limits[-1]*100 ]
histogram_properties.legend_location = ( 0.9, 0.9 )
histogram_properties.name += '_logY'
make_data_mc_comparison_plot(
histograms_to_draw,
histogram_lables,
histogram_colors,
histogram_properties,
save_folder = 'plots/control_plots_with_systematic/logY/',
show_ratio = True,
normalise = False,
systematics_for_ratio = uncertaintyBand,
systematics_for_plot = uncertaintyBand,
)
def make_correlation_plot_from_file(channel,
variable,
fit_variables,
CoM,
title,
x_title,
y_title,
x_limits,
y_limits,
rebin=1,
save_folder='plots/fitchecks/',
save_as=['pdf', 'png']):
# global b_tag_bin
parameters = ["TTJet", "SingleTop", "V+Jets", "QCD"]
parameters_latex = []
for template in parameters:
parameters_latex.append(samples_latex[template])
input_file = open(
"logs/01_%s_fit_%dTeV_%s.log" % (variable, CoM, fit_variables), "r")
# cycle through the lines in the file
for line_number, line in enumerate(input_file):
# for now, only make plots for the fits for the central measurement
if "central" in line:
# matrix we want begins 11 lines below the line with the measurement ("central")
line_number = line_number + 11
break
input_file.close()
#Note: For some reason, the fit outputs the correlation matrix with the templates in the following order:
#parameter1: QCD
#parameter2: SingleTop
#parameter3: TTJet
#parameter4: V+Jets
for variable_bin in variable_bins_ROOT[variable]:
weights = {}
if channel == 'electron':
#formula to calculate the number of lines below "central" to access in each loop
number_of_lines_down = (
variable_bins_ROOT[variable].index(variable_bin) * 12)
#Get QCD correlations
matrix_line = linecache.getline(
"logs/01_%s_fit_%dTeV_%s.log" % (variable, CoM, fit_variables),
line_number + number_of_lines_down)
weights["QCD_QCD"] = matrix_line.split()[2]
weights["QCD_SingleTop"] = matrix_line.split()[3]
weights["QCD_TTJet"] = matrix_line.split()[4]
weights["QCD_V+Jets"] = matrix_line.split()[5]
#Get SingleTop correlations
matrix_line = linecache.getline(
"logs/01_%s_fit_%dTeV_%s.log" % (variable, CoM, fit_variables),
line_number + number_of_lines_down + 1)
weights["SingleTop_QCD"] = matrix_line.split()[2]
weights["SingleTop_SingleTop"] = matrix_line.split()[3]
weights["SingleTop_TTJet"] = matrix_line.split()[4]
weights["SingleTop_V+Jets"] = matrix_line.split()[5]
#Get TTJet correlations
matrix_line = linecache.getline(
"logs/01_%s_fit_%dTeV_%s.log" % (variable, CoM, fit_variables),
line_number + number_of_lines_down + 2)
weights["TTJet_QCD"] = matrix_line.split()[2]
weights["TTJet_SingleTop"] = matrix_line.split()[3]
weights["TTJet_TTJet"] = matrix_line.split()[4]
weights["TTJet_V+Jets"] = matrix_line.split()[5]
#Get V+Jets correlations
matrix_line = linecache.getline(
"logs/01_%s_fit_%dTeV_%s.log" % (variable, CoM, fit_variables),
line_number + number_of_lines_down + 3)
weights["V+Jets_QCD"] = matrix_line.split()[2]
weights["V+Jets_SingleTop"] = matrix_line.split()[3]
weights["V+Jets_TTJet"] = matrix_line.split()[4]
weights["V+Jets_V+Jets"] = matrix_line.split()[5]
if channel == 'muon':
#formula to calculate the number of lines below "central" to access in each bin loop
number_of_lines_down = (len(variable_bins_ROOT[variable]) * 12) + (
variable_bins_ROOT[variable].index(variable_bin) * 12)
#Get QCD correlations
matrix_line = linecache.getline(
"logs/01_%s_fit_%dTeV_%s.log" % (variable, CoM, fit_variables),
line_number + number_of_lines_down)
weights["QCD_QCD"] = matrix_line.split()[2]
weights["QCD_SingleTop"] = matrix_line.split()[3]
weights["QCD_TTJet"] = matrix_line.split()[4]
weights["QCD_V+Jets"] = matrix_line.split()[5]
#Get SingleTop correlations
matrix_line = linecache.getline(
"logs/01_%s_fit_%dTeV_%s.log" % (variable, CoM, fit_variables),
line_number + number_of_lines_down + 1)
weights["SingleTop_QCD"] = matrix_line.split()[2]
weights["SingleTop_SingleTop"] = matrix_line.split()[3]
weights["SingleTop_TTJet"] = matrix_line.split()[4]
weights["SingleTop_V+Jets"] = matrix_line.split()[5]
#Get TTJet correlations
matrix_line = linecache.getline(
"logs/01_%s_fit_%dTeV_%s.log" % (variable, CoM, fit_variables),
line_number + number_of_lines_down + 2)
weights["TTJet_QCD"] = matrix_line.split()[2]
weights["TTJet_SingleTop"] = matrix_line.split()[3]
weights["TTJet_TTJet"] = matrix_line.split()[4]
weights["TTJet_V+Jets"] = matrix_line.split()[5]
#Get V+Jets correlations
matrix_line = linecache.getline(
"logs/01_%s_fit_%dTeV_%s.log" % (variable, CoM, fit_variables),
line_number + number_of_lines_down + 3)
weights["V+Jets_QCD"] = matrix_line.split()[2]
weights["V+Jets_SingleTop"] = matrix_line.split()[3]
weights["V+Jets_TTJet"] = matrix_line.split()[4]
weights["V+Jets_V+Jets"] = matrix_line.split()[5]
#Create histogram
histogram_properties = Histogram_properties()
histogram_properties.title = title
histogram_properties.name = 'Correlations_' + channel + '_' + variable + '_' + variable_bin
histogram_properties.y_axis_title = y_title
histogram_properties.x_axis_title = x_title
histogram_properties.y_limits = y_limits
histogram_properties.x_limits = x_limits
histogram_properties.mc_error = 0.0
histogram_properties.legend_location = 'upper right'
#initialise 2D histogram
a = Hist2D(4, 0, 4, 4, 0, 4)
#fill histogram
for i in range(len(parameters)):
for j in range(len(parameters)):
a.fill(
float(i), float(j),
float(weights["%s_%s" % (parameters[i], parameters[j])]))
# create figure
plt.figure(figsize=CMS.figsize, dpi=CMS.dpi, facecolor=CMS.facecolor)
# make subplot(?)
fig, ax = plt.subplots(nrows=1, ncols=1)
rplt.hist2d(a)
plt.subplots_adjust(right=0.8)
#Set labels and formats for titles and axes
plt.ylabel(histogram_properties.y_axis_title)
plt.xlabel(histogram_properties.x_axis_title)
plt.title(histogram_properties.title)
x_limits = histogram_properties.x_limits
y_limits = histogram_properties.y_limits
ax.set_xticklabels(parameters_latex)
ax.set_yticklabels(parameters_latex)
ax.set_xticks([0.5, 1.5, 2.5, 3.5])
ax.set_yticks([0.5, 1.5, 2.5, 3.5])
plt.setp(ax.get_xticklabels(), visible=True)
plt.setp(ax.get_yticklabels(), visible=True)
#create and draw colour bar to the right of the main plot
im = rplt.imshow(a, axes=ax, vmin=-1.0, vmax=1.0)
#set location and dimensions (left, lower, width, height)
cbar_ax = fig.add_axes([0.85, 0.10, 0.05, 0.8])
fig.colorbar(im, cax=cbar_ax)
for xpoint in range(len(parameters)):
for ypoint in range(len(parameters)):
correlation_value = weights["%s_%s" % (parameters[xpoint],
parameters[ypoint])]
ax.annotate(correlation_value,
xy=(xpoint + 0.5, ypoint + 0.5),
ha='center',
va='center',
bbox=dict(fc='white', ec='none'))
for save in save_as:
plt.savefig(save_folder + histogram_properties.name + '.' + save)
plt.close(fig)
plt.close('all')
plot_with_plotting_script = True
if plot_with_plotting_script:
properties = Histogram_properties()
properties.name = "matplotlib_hist"
properties.x_axis_title = "Mass"
properties.y_axis_title = "Events"
make_data_mc_comparison_plot([h3, h1, h2], ["data", "background", "signal"], ["black", "green", "red"], properties)
properties.name += "_with_ratio"
make_data_mc_comparison_plot(
[h3, h1, h2], ["data", "background", "signal"], ["black", "green", "red"], properties, show_ratio=True
)
properties.name = "matplotlib_hist_comparison"
properties.y_limits = [0, 0.4]
make_control_region_comparison(h1, h2, "background", "signal", properties)
else:
fig = plt.figure(figsize=(14, 10), dpi=300) # , facecolor='white')
axes = plt.axes()
axes.xaxis.set_minor_locator(AutoMinorLocator())
axes.yaxis.set_minor_locator(AutoMinorLocator())
# axes.yaxis.set_major_locator(MultipleLocator(20))
axes.tick_params(which="major", labelsize=15, length=8)
axes.tick_params(which="minor", length=4)
rplt.errorbar(h3, xerr=False, emptybins=False, axes=axes, zorder=4)
rplt.hist(stack, stacked=True, axes=axes, zorder=1)
plt.xlabel("Mass", position=(1.0, 0.0), ha="right")
plt.ylabel("Events", position=(0.0, 1.0), va="bottom", ha="right")
plt.legend(numpoints=1)
