def read_fit_templates_and_results_as_histograms( category, channel ):
global path_to_JSON, variable, met_type, phase_space
templates = read_data_from_JSON( path_to_JSON + '/fit_results/' + category + '/templates_' + channel + '_' + met_type + '.txt' )
data_values = read_data_from_JSON( path_to_JSON + '/fit_results/' + category + '/initial_values_' + channel + '_' + met_type + '.txt' )['data']
fit_results = read_data_from_JSON( path_to_JSON + '/fit_results/' + category + '/fit_results_' + channel + '_' + met_type + '.txt' )
fit_variables = templates.keys()
template_histograms = {fit_variable: {} for fit_variable in fit_variables}
fit_results_histograms = {fit_variable: {} for fit_variable in fit_variables}
variableBins = None
if phase_space == 'VisiblePS':
variableBins = variable_bins_visiblePS_ROOT
elif phase_space == 'FullPS':
variableBins = variable_bins_ROOT
for bin_i, variable_bin in enumerate( variableBins[variable] ):
for fit_variable in fit_variables:
h_template_data = value_tuplelist_to_hist( templates[fit_variable]['data'][bin_i], fit_variable_bin_edges[fit_variable] )
h_template_ttjet = value_tuplelist_to_hist( templates[fit_variable]['TTJet'][bin_i], fit_variable_bin_edges[fit_variable] )
h_template_singletop = value_tuplelist_to_hist( templates[fit_variable]['SingleTop'][bin_i], fit_variable_bin_edges[fit_variable] )
h_template_VJets = value_tuplelist_to_hist( templates[fit_variable]['V+Jets'][bin_i], fit_variable_bin_edges[fit_variable] )
h_template_QCD = value_tuplelist_to_hist( templates[fit_variable]['QCD'][bin_i], fit_variable_bin_edges[fit_variable] )
template_histograms[fit_variable][variable_bin] = {
'TTJet' : h_template_ttjet,
'SingleTop' : h_template_singletop,
'V+Jets':h_template_VJets,
'QCD':h_template_QCD
}
h_data = h_template_data.Clone()
h_ttjet = h_template_ttjet.Clone()
h_singletop = h_template_singletop.Clone()
h_VJets = h_template_VJets.Clone()
h_QCD = h_template_QCD.Clone()
data_normalisation = data_values[bin_i][0]
n_ttjet = fit_results['TTJet'][bin_i][0]
n_singletop = fit_results['SingleTop'][bin_i][0]
VJets_normalisation = fit_results['V+Jets'][bin_i][0]
QCD_normalisation = fit_results['QCD'][bin_i][0]
h_data.Scale( data_normalisation )
h_ttjet.Scale( n_ttjet )
h_singletop.Scale( n_singletop )
h_VJets.Scale( VJets_normalisation )
h_QCD.Scale( QCD_normalisation )
h_background = h_VJets + h_QCD + h_singletop
for bin_i_data in range( len( h_data ) ):
h_data.SetBinError( bin_i_data + 1, sqrt( h_data.GetBinContent( bin_i_data + 1 ) ) )
fit_results_histograms[fit_variable][variable_bin] = {
'data' : h_data,
'signal' : h_ttjet,
'background' : h_background
}
return template_histograms, fit_results_histograms
def read_fit_templates_and_results_as_histograms(category, channel):
global path_to_JSON, variable, met_type
templates = read_data_from_JSON(path_to_JSON + '/' + variable +
'/fit_results/' + category +
'/templates_' + channel + '_' + met_type +
'.txt')
data_values = read_data_from_JSON(path_to_JSON + '/' + variable +
'/fit_results/' + category +
'/initial_values_' + channel + '_' +
met_type + '.txt')['data']
fit_results = read_data_from_JSON(path_to_JSON + '/' + variable +
'/fit_results/' + category +
'/fit_results_' + channel + '_' +
met_type + '.txt')
template_histograms = {}
fit_results_histograms = {}
for bin_i, variable_bin in enumerate(variable_bins_ROOT[variable]):
h_template_data = value_tuplelist_to_hist(templates['data'][bin_i],
eta_bin_edges)
h_template_signal = value_tuplelist_to_hist(templates['signal'][bin_i],
eta_bin_edges)
h_template_VJets = value_tuplelist_to_hist(templates['V+Jets'][bin_i],
eta_bin_edges)
h_template_QCD = value_tuplelist_to_hist(templates['QCD'][bin_i],
eta_bin_edges)
template_histograms[variable_bin] = {
'signal': h_template_signal,
'V+Jets': h_template_VJets,
'QCD': h_template_QCD
}
h_data = h_template_data.Clone()
h_signal = h_template_signal.Clone()
h_VJets = h_template_VJets.Clone()
h_QCD = h_template_QCD.Clone()
data_normalisation = data_values[bin_i]
signal_normalisation = fit_results['signal'][bin_i][0]
VJets_normalisation = fit_results['V+Jets'][bin_i][0]
QCD_normalisation = fit_results['QCD'][bin_i][0]
h_data.Scale(data_normalisation)
h_signal.Scale(signal_normalisation)
h_VJets.Scale(VJets_normalisation)
h_QCD.Scale(QCD_normalisation)
h_background = h_VJets + h_QCD
for bin_i in range(len(h_data)):
h_data.SetBinError(bin_i + 1,
sqrt(h_data.GetBinContent(bin_i + 1)))
fit_results_histograms[variable_bin] = {
'data': h_data,
'signal': h_signal,
'background': h_background
}
return template_histograms, fit_results_histograms
def makePurityStabilityPlots(input_file, histogram, bin_edges, channel, variable, isVisiblePhaseSpace):
global output_folder, output_formats
hist = get_histogram_from_file( histogram, input_file )
print "bin edges contents : ", bin_edges
new_hist = rebin_2d( hist, bin_edges, bin_edges ).Clone()
# get_bin_content = hist.ProjectionX().GetBinContent
purities = calculate_purities( new_hist.Clone() )
stabilities = calculate_stabilities( new_hist.Clone() )
# n_events = [int( get_bin_content( i ) ) for i in range( 1, len( bin_edges ) )]
print "purities contents : ", purities
print "stabilities contents : ", stabilities
hist_stability = value_tuplelist_to_hist(stabilities, bin_edges)
hist_purity = value_tuplelist_to_hist(purities, bin_edges)
hist_purity.color = 'red'
hist_stability.color = 'blue'
hist_stability.linewidth = 4
hist_purity.linewidth = 4
x_limits = [bin_edges[0], bin_edges[-1]]
y_limits = [0,1]
plt.figure( figsize = ( 20, 16 ), dpi = 200, facecolor = 'white' )
ax0 = plt.axes()
ax0.minorticks_on()
# ax0.grid( True, 'major', linewidth = 2 )
# ax0.grid( True, 'minor' )
plt.tick_params( **CMS.axis_label_major )
plt.tick_params( **CMS.axis_label_minor )
ax0.xaxis.labelpad = 12
ax0.yaxis.labelpad = 12
rplt.hist( hist_stability , stacked=False, axes = ax0, cmap = my_cmap, vmin = 1, label = 'Stability' )
rplt.hist( hist_purity, stacked=False, axes = ax0, cmap = my_cmap, vmin = 1, label = 'Purity' )
ax0.set_xlim( x_limits )
ax0.set_ylim( y_limits )
plt.tick_params( **CMS.axis_label_major )
plt.tick_params( **CMS.axis_label_minor )
x_title = '$' + variables_latex[variable] + '$ [GeV]'
plt.xlabel( x_title, CMS.x_axis_title )
leg = plt.legend(loc=4,prop={'size':40})
plt.tight_layout()
plt.savefig('test.pdf')
save_as_name = 'purityStability_'+channel + '_' + variable + '_' + str(options.CoM) + 'TeV'
for output_format in output_formats:
plt.savefig( output_folder + save_as_name + '.' + output_format )
def read_fit_templates_and_results_as_histograms(category, channel):
global path_to_JSON, variable, met_type
templates = read_data_from_JSON(
path_to_JSON + "/" + variable + "/fit_results/" + category + "/templates_" + channel + "_" + met_type + ".txt"
)
data_values = read_data_from_JSON(
path_to_JSON
+ "/"
+ variable
+ "/fit_results/"
+ category
+ "/initial_values_"
+ channel
+ "_"
+ met_type
+ ".txt"
)["data"]
fit_results = read_data_from_JSON(
path_to_JSON + "/" + variable + "/fit_results/" + category + "/fit_results_" + channel + "_" + met_type + ".txt"
)
template_histograms = {}
fit_results_histograms = {}
for bin_i, variable_bin in enumerate(variable_bins_ROOT[variable]):
h_template_data = value_tuplelist_to_hist(templates["data"][bin_i], eta_bin_edges)
h_template_signal = value_tuplelist_to_hist(templates["signal"][bin_i], eta_bin_edges)
h_template_VJets = value_tuplelist_to_hist(templates["V+Jets"][bin_i], eta_bin_edges)
h_template_QCD = value_tuplelist_to_hist(templates["QCD"][bin_i], eta_bin_edges)
template_histograms[variable_bin] = {
"signal": h_template_signal,
"V+Jets": h_template_VJets,
"QCD": h_template_QCD,
}
h_data = h_template_data.Clone()
h_signal = h_template_signal.Clone()
h_VJets = h_template_VJets.Clone()
h_QCD = h_template_QCD.Clone()
data_normalisation = data_values[bin_i]
signal_normalisation = fit_results["signal"][bin_i][0]
VJets_normalisation = fit_results["V+Jets"][bin_i][0]
QCD_normalisation = fit_results["QCD"][bin_i][0]
h_data.Scale(data_normalisation)
h_signal.Scale(signal_normalisation)
h_VJets.Scale(VJets_normalisation)
h_QCD.Scale(QCD_normalisation)
h_background = h_VJets + h_QCD
for bin_i in range(len(h_data)):
h_data.SetBinError(bin_i + 1, sqrt(h_data.GetBinContent(bin_i + 1)))
fit_results_histograms[variable_bin] = {"data": h_data, "signal": h_signal, "background": h_background}
return template_histograms, fit_results_histograms
def compare_combine_before_after_unfolding_uncertainties():
file_template = 'data/normalisation/background_subtraction/13TeV/'
file_template += '{variable}/VisiblePS/central/'
file_template += 'unfolded_normalisation_{channel}_RooUnfoldSvd.txt'
variables = [
'MET', 'HT', 'ST', 'NJets', 'lepton_pt', 'abs_lepton_eta', 'WPT'
]
# variables = ['ST']
for variable in variables:
beforeUnfolding = file_template.format(
variable=variable, channel='combinedBeforeUnfolding')
afterUnfolding = file_template.format(variable=variable,
channel='combined')
data = read_data_from_JSON(beforeUnfolding)
before_unfolding = data['TTJet_measured']
beforeUnfolding_data = data['TTJet_unfolded']
afterUnfolding_data = read_data_from_JSON(
afterUnfolding)['TTJet_unfolded']
before_unfolding = [e / v * 100 for v, e in before_unfolding]
beforeUnfolding_data = [e / v * 100 for v, e in beforeUnfolding_data]
afterUnfolding_data = [e / v * 100 for v, e in afterUnfolding_data]
h_beforeUnfolding = value_tuplelist_to_hist(beforeUnfolding_data,
bin_edges_vis[variable])
h_afterUnfolding = value_tuplelist_to_hist(afterUnfolding_data,
bin_edges_vis[variable])
h_before_unfolding = value_tuplelist_to_hist(before_unfolding,
bin_edges_vis[variable])
properties = Histogram_properties()
properties.name = 'compare_combine_before_after_unfolding_uncertainties_{0}'.format(
variable)
properties.title = 'Comparison of unfolding uncertainties'
properties.path = 'plots'
properties.has_ratio = False
properties.xerr = True
properties.x_limits = (bin_edges_vis[variable][0],
bin_edges_vis[variable][-1])
properties.x_axis_title = variables_latex[variable]
properties.y_axis_title = 'relative uncertainty (\\%)'
properties.legend_location = (0.98, 0.95)
histograms = {
'Combine before unfolding': h_beforeUnfolding,
'Combine after unfolding': h_afterUnfolding,
# 'before unfolding': h_before_unfolding
}
plot = Plot(histograms, properties)
plot.draw_method = 'errorbar'
compare_histograms(plot)
def compare_unfolding_uncertainties():
file_template = '/hdfs/TopQuarkGroup/run2/dpsData/'
file_template += 'data/normalisation/background_subtraction/13TeV/'
file_template += '{variable}/VisiblePS/central/'
file_template += 'unfolded_normalisation_combined_RooUnfold{method}.txt'
variables = [
'MET', 'HT', 'ST', 'NJets', 'lepton_pt', 'abs_lepton_eta', 'WPT'
]
# variables = ['ST']
for variable in variables:
svd = file_template.format(variable=variable, method='Svd')
bayes = file_template.format(variable=variable, method='Bayes')
data = read_data_from_JSON(svd)
before_unfolding = data['TTJet_measured_withoutFakes']
svd_data = data['TTJet_unfolded']
bayes_data = read_data_from_JSON(bayes)['TTJet_unfolded']
before_unfolding = [e / v * 100 for v, e in before_unfolding]
svd_data = [e / v * 100 for v, e in svd_data]
bayes_data = [e / v * 100 for v, e in bayes_data]
h_svd = value_tuplelist_to_hist(svd_data, bin_edges_vis[variable])
h_bayes = value_tuplelist_to_hist(bayes_data, bin_edges_vis[variable])
h_before_unfolding = value_tuplelist_to_hist(before_unfolding,
bin_edges_vis[variable])
properties = Histogram_properties()
properties.name = 'compare_unfolding_uncertainties_{0}'.format(
variable)
properties.title = 'Comparison of unfolding uncertainties'
properties.path = 'plots'
properties.has_ratio = False
properties.xerr = True
properties.x_limits = (bin_edges_vis[variable][0],
bin_edges_vis[variable][-1])
properties.x_axis_title = variables_latex[variable]
properties.y_axis_title = 'relative uncertainty (\\%)'
properties.legend_location = (0.98, 0.95)
histograms = {
'SVD': h_svd,
'Bayes': h_bayes,
'before unfolding': h_before_unfolding
}
plot = Plot(histograms, properties)
plot.draw_method = 'errorbar'
compare_histograms(plot)
def compare_combine_before_after_unfolding_uncertainties():
file_template = 'data/normalisation/background_subtraction/13TeV/'
file_template += '{variable}/VisiblePS/central/'
file_template += 'unfolded_normalisation_{channel}_RooUnfoldSvd.txt'
variables = ['MET', 'HT', 'ST', 'NJets',
'lepton_pt', 'abs_lepton_eta', 'WPT']
# variables = ['ST']
for variable in variables:
beforeUnfolding = file_template.format(
variable=variable, channel='combinedBeforeUnfolding')
afterUnfolding = file_template.format(
variable=variable, channel='combined')
data = read_data_from_JSON(beforeUnfolding)
before_unfolding = data['TTJet_measured']
beforeUnfolding_data = data['TTJet_unfolded']
afterUnfolding_data = read_data_from_JSON(afterUnfolding)['TTJet_unfolded']
before_unfolding = [e / v * 100 for v, e in before_unfolding]
beforeUnfolding_data = [e / v * 100 for v, e in beforeUnfolding_data]
afterUnfolding_data = [e / v * 100 for v, e in afterUnfolding_data]
h_beforeUnfolding = value_tuplelist_to_hist(
beforeUnfolding_data, bin_edges_vis[variable])
h_afterUnfolding = value_tuplelist_to_hist(
afterUnfolding_data, bin_edges_vis[variable])
h_before_unfolding = value_tuplelist_to_hist(
before_unfolding, bin_edges_vis[variable])
properties = Histogram_properties()
properties.name = 'compare_combine_before_after_unfolding_uncertainties_{0}'.format(
variable)
properties.title = 'Comparison of unfolding uncertainties'
properties.path = 'plots'
properties.has_ratio = False
properties.xerr = True
properties.x_limits = (
bin_edges_vis[variable][0], bin_edges_vis[variable][-1])
properties.x_axis_title = variables_latex[variable]
properties.y_axis_title = 'relative uncertainty (\\%)'
properties.legend_location = (0.98, 0.95)
histograms = {'Combine before unfolding': h_beforeUnfolding, 'Combine after unfolding': h_afterUnfolding,
# 'before unfolding': h_before_unfolding
}
plot = Plot(histograms, properties)
plot.draw_method = 'errorbar'
compare_histograms(plot)
def compare_unfolding_uncertainties():
file_template = '/hdfs/TopQuarkGroup/run2/dpsData/'
file_template += 'data/normalisation/background_subtraction/13TeV/'
file_template += '{variable}/VisiblePS/central/'
file_template += 'unfolded_normalisation_combined_RooUnfold{method}.txt'
variables = ['MET', 'HT', 'ST', 'NJets',
'lepton_pt', 'abs_lepton_eta', 'WPT']
# variables = ['ST']
for variable in variables:
svd = file_template.format(
variable=variable, method='Svd')
bayes = file_template.format(
variable=variable, method='Bayes')
data = read_data_from_JSON(svd)
before_unfolding = data['TTJet_measured_withoutFakes']
svd_data = data['TTJet_unfolded']
bayes_data = read_data_from_JSON(bayes)['TTJet_unfolded']
before_unfolding = [e / v * 100 for v, e in before_unfolding]
svd_data = [e / v * 100 for v, e in svd_data]
bayes_data = [e / v * 100 for v, e in bayes_data]
h_svd = value_tuplelist_to_hist(
svd_data, bin_edges_vis[variable])
h_bayes = value_tuplelist_to_hist(
bayes_data, bin_edges_vis[variable])
h_before_unfolding = value_tuplelist_to_hist(
before_unfolding, bin_edges_vis[variable])
properties = Histogram_properties()
properties.name = 'compare_unfolding_uncertainties_{0}'.format(
variable)
properties.title = 'Comparison of unfolding uncertainties'
properties.path = 'plots'
properties.has_ratio = False
properties.xerr = True
properties.x_limits = (
bin_edges_vis[variable][0], bin_edges_vis[variable][-1])
properties.x_axis_title = variables_latex[variable]
properties.y_axis_title = 'relative uncertainty (\\%)'
properties.legend_location = (0.98, 0.95)
histograms = {'SVD': h_svd, 'Bayes': h_bayes,
'before unfolding': h_before_unfolding}
plot = Plot(histograms, properties)
plot.draw_method = 'errorbar'
compare_histograms(plot)
def run_test ( test_data ):
''' Used the test_data to fit the number of events for each process
'''
global config
data_scale = 1.2
fit_data_collection = FitDataCollection()
for fit_variable, fit_input in test_data.iteritems():
# create the histograms
mc_histograms = {}
for sample, h_input in fit_input.iteritems():
mc_histograms[sample] = value_tuplelist_to_hist( h_input['distribution'],
fit_variable_bin_edges[fit_variable] )
real_data = sum( mc_histograms[sample] for sample in mc_histograms.keys() )
# scale data so that the fit does not start in the minimum
real_data.Scale( data_scale )
fit_data = FitData( real_data, mc_histograms, fit_boundaries = config.fit_boundaries[fit_variable] )
fit_data_collection.add( fit_data, fit_variable )
# do fit
fitter = Minuit( fit_data_collection )
fitter.fit()
fit_results = fitter.results
# calculate chi2 for each sample
chi2_results = {}
for sample in fit_results.keys():
true_normalisation = fit_input[sample]['normalisation'] * data_scale
# fit_result, fit_error = fit_results[sample]
# chi2 = pow( true_normalisation - fit_result, 2 ) / pow( fit_error, 2 )
fit_result, _ = fit_results[sample]
chi2 = pow( true_normalisation - fit_result, 2 )
chi2_results[sample] = chi2
return chi2_results
def run_test(test_data):
''' Used the test_data to fit the number of events for each process
'''
global config
data_scale = 1.2
fit_data_collection = FitDataCollection()
for fit_variable, fit_input in test_data.iteritems():
# create the histograms
mc_histograms = {}
for sample, h_input in fit_input.iteritems():
mc_histograms[sample] = value_tuplelist_to_hist(
h_input['distribution'], fit_variable_bin_edges[fit_variable])
real_data = sum(mc_histograms[sample]
for sample in mc_histograms.keys())
# scale data so that the fit does not start in the minimum
real_data.Scale(data_scale)
fit_data = FitData(real_data,
mc_histograms,
fit_boundaries=config.fit_boundaries[fit_variable])
fit_data_collection.add(fit_data, fit_variable)
# do fit
fitter = Minuit(fit_data_collection)
fitter.fit()
fit_results = fitter.results
# calculate chi2 for each sample
chi2_results = {}
for sample in fit_results.keys():
true_normalisation = fit_input[sample]['normalisation'] * data_scale
# fit_result, fit_error = fit_results[sample]
# chi2 = pow( true_normalisation - fit_result, 2 ) / pow( fit_error, 2 )
fit_result, _ = fit_results[sample]
chi2 = pow(true_normalisation - fit_result, 2)
chi2_results[sample] = chi2
return chi2_results
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[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 read_fit_templates_and_results_as_histograms(category, channel):
global path_to_JSON, variable, met_type
templates = read_data_from_JSON(path_to_JSON + '/fit_results/' + category + '/templates_' + channel + '_' + met_type + '.txt')
data_values = read_data_from_JSON(path_to_JSON + '/fit_results/' + category + '/initial_values_' + channel + '_' + met_type + '.txt')['data']
fit_results = read_data_from_JSON(path_to_JSON + '/fit_results/' + category + '/fit_results_' + channel + '_' + met_type + '.txt')
template_histograms = {}
fit_results_histograms = {}
for bin_i, variable_bin in enumerate(variable_bins_ROOT[variable]):
h_template_data = value_tuplelist_to_hist(templates['data'][bin_i], eta_bin_edges)
h_template_signal = value_tuplelist_to_hist(templates['signal'][bin_i], eta_bin_edges)
h_template_VJets = value_tuplelist_to_hist(templates['V+Jets'][bin_i], eta_bin_edges)
h_template_QCD = value_tuplelist_to_hist(templates['QCD'][bin_i], eta_bin_edges)
template_histograms[variable_bin] = {
'signal':h_template_signal,
'V+Jets':h_template_VJets,
'QCD':h_template_QCD
}
h_data = h_template_data.Clone()
h_signal = h_template_signal.Clone()
h_VJets = h_template_VJets.Clone()
h_QCD = h_template_QCD.Clone()
data_normalisation = data_values[bin_i]
signal_normalisation = fit_results['signal'][bin_i][0]
VJets_normalisation = fit_results['V+Jets'][bin_i][0]
QCD_normalisation = fit_results['QCD'][bin_i][0]
h_data.Scale(data_normalisation)
h_signal.Scale(signal_normalisation)
h_VJets.Scale(VJets_normalisation)
h_QCD.Scale(QCD_normalisation)
h_background = h_VJets + h_QCD
for bin_i in range(len(h_data)):
h_data.SetBinError(bin_i+1, sqrt(h_data.GetBinContent(bin_i+1)))
fit_results_histograms[variable_bin] = {
'data':h_data,
'signal':h_signal,
'background':h_background
}
return template_histograms, fit_results_histograms
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[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 makePurityStabilityPlots(input_file, histogram, bin_edges, channel,
variable, isVisiblePhaseSpace):
global output_folder, output_formats
hist = get_histogram_from_file(histogram, input_file)
# get_bin_content = hist.ProjectionX().GetBinContent
purities = calculate_purities(hist.Clone())
stabilities = calculate_stabilities(hist.Clone())
# n_events = [int( get_bin_content( i ) ) for i in range( 1, len( bin_edges ) )]
hist_stability = value_tuplelist_to_hist(stabilities, bin_edges)
hist_purity = value_tuplelist_to_hist(purities, bin_edges)
hist_purity.color = 'red'
hist_stability.color = 'blue'
hist_stability.linewidth = 4
hist_purity.linewidth = 4
x_limits = [bin_edges[0], bin_edges[-1]]
y_limits = [0, 1]
plt.figure(figsize=(20, 16), dpi=200, facecolor='white')
ax0 = plt.axes()
ax0.minorticks_on()
# ax0.grid( True, 'major', linewidth = 2 )
# ax0.grid( True, 'minor' )
plt.tick_params(**CMS.axis_label_major)
plt.tick_params(**CMS.axis_label_minor)
ax0.xaxis.labelpad = 12
ax0.yaxis.labelpad = 12
rplt.hist(hist_stability,
stacked=False,
axes=ax0,
cmap=my_cmap,
vmin=1,
label='Stability')
rplt.hist(hist_purity,
stacked=False,
axes=ax0,
cmap=my_cmap,
vmin=1,
label='Purity')
ax0.set_xlim(x_limits)
ax0.set_ylim(y_limits)
plt.tick_params(**CMS.axis_label_major)
plt.tick_params(**CMS.axis_label_minor)
x_title = '$' + variables_latex[variable] + '$ [GeV]'
plt.xlabel(x_title, CMS.x_axis_title)
leg = plt.legend(loc=4, prop={'size': 40})
plt.tight_layout()
plt.savefig('test.pdf')
save_as_name = 'purityStability_' + channel + '_' + variable + '_' + str(
options.CoM) + 'TeV'
for output_format in output_formats:
plt.savefig(output_folder + save_as_name + '.' + output_format)
