class Test(unittest.TestCase):
def setUp(self):
# create histograms
h_bkg1_1 = Hist(100, 40, 200, title='Background')
h_signal_1 = h_bkg1_1.Clone(title='Signal')
h_data_1 = h_bkg1_1.Clone(title='Data')
# fill the histograms with our distributions
map(h_bkg1_1.Fill, x1)
map(h_signal_1.Fill, x2)
map(h_data_1.Fill, x1_obs)
map(h_data_1.Fill, x2_obs)
histograms_1 = {'signal': h_signal_1,
'bkg1': h_bkg1_1,
# 'data': h_data_1
}
fit_data_1 = FitData(h_data_1, histograms_1, fit_boundaries=(40, 200))
self.single_fit_collection = FitDataCollection()
self.single_fit_collection.add( fit_data_1 )
# self.roofitFitter = RooFitFit(histograms_1, dataLabel='data', fit_boundries=(40, 200))
self.roofitFitter = RooFitFit(self.single_fit_collection)
def tearDown(self):
pass
def test_normalisation(self):
normalisation = self.roofitFitter.normalisation
self.assertAlmostEqual(normalisation["data"], N_data, delta=sqrt(N_data))
self.assertAlmostEqual(normalisation["bkg1"], N_bkg1, delta=sqrt(N_bkg1))
self.assertAlmostEqual(normalisation["signal"], N_signal, delta=sqrt(N_signal))
def test_signal_result(self):
self.roofitFitter.fit()
results = self.roofitFitter.readResults()
self.assertAlmostEqual(N_signal_obs, results['signal'][0], delta=2 * results['signal'][1])
self.assertAlmostEqual(N_bkg1_obs, results['bkg1'][0], delta=2 * results['bkg1'][1])
def test_constraints(self):
self.single_fit_collection.set_normalisation_constraints({'signal': 0.8, 'bkg1': 0.5})
self.roofitFitter = RooFitFit(self.single_fit_collection)
# self.roofitFitter.set_fit_constraints({'signal': 0.8, 'bkg1': 0.5})
self.roofitFitter.fit()
results = self.roofitFitter.readResults()
self.assertAlmostEqual(N_signal_obs, results['signal'][0], delta=2 * results['signal'][1])
self.assertAlmostEqual(N_bkg1_obs, results['bkg1'][0], delta=2 * results['bkg1'][1])
class Test(unittest.TestCase):
def setUp(self):
# create histograms
h_bkg1_1 = Hist(100, 40, 200, title='Background')
h_signal_1 = h_bkg1_1.Clone(title='Signal')
h_data_1 = h_bkg1_1.Clone(title='Data')
# fill the histograms with our distributions
map(h_bkg1_1.Fill, x1)
map(h_signal_1.Fill, x2)
map(h_data_1.Fill, x1_obs)
map(h_data_1.Fill, x2_obs)
histograms_1 = {
'signal': h_signal_1,
'bkg1': h_bkg1_1,
# 'data': h_data_1
}
fit_data_1 = FitData(h_data_1, histograms_1, fit_boundaries=(40, 200))
self.single_fit_collection = FitDataCollection()
self.single_fit_collection.add(fit_data_1)
# self.roofitFitter = RooFitFit(histograms_1, dataLabel='data', fit_boundries=(40, 200))
self.roofitFitter = RooFitFit(self.single_fit_collection)
def tearDown(self):
pass
def test_normalisation(self):
normalisation = self.roofitFitter.normalisation
self.assertAlmostEqual(normalisation["data"],
N_data,
delta=sqrt(N_data))
self.assertAlmostEqual(normalisation["bkg1"],
N_bkg1,
delta=sqrt(N_bkg1))
self.assertAlmostEqual(normalisation["signal"],
N_signal,
delta=sqrt(N_signal))
def test_signal_result(self):
self.roofitFitter.fit()
results = self.roofitFitter.readResults()
self.assertAlmostEqual(N_signal_obs,
results['signal'][0],
delta=2 * results['signal'][1])
self.assertAlmostEqual(N_bkg1_obs,
results['bkg1'][0],
delta=2 * results['bkg1'][1])
def test_constraints(self):
self.single_fit_collection.set_normalisation_constraints({
'signal': 0.8,
'bkg1': 0.5
})
self.roofitFitter = RooFitFit(self.single_fit_collection)
# self.roofitFitter.set_fit_constraints({'signal': 0.8, 'bkg1': 0.5})
self.roofitFitter.fit()
results = self.roofitFitter.readResults()
self.assertAlmostEqual(N_signal_obs,
results['signal'][0],
delta=2 * results['signal'][1])
self.assertAlmostEqual(N_bkg1_obs,
results['bkg1'][0],
delta=2 * results['bkg1'][1])
def get_fitted_normalisation_from_ROOT( channel, input_files, variable, met_type, b_tag_bin, scale_factors = None ):
'''
Retrieves the number of ttbar events from fits to one or more distribution
(fit_variables) for each bin in the variable.
'''
global use_fitter, measurement_config, verbose, fit_variables, options
# results and initial values are the same across different fit variables
# templates are not
results = {}
initial_values = {}
templates = {fit_variable: {} for fit_variable in fit_variables}
for variable_bin in variable_bins_ROOT[variable]:
fitter = None
fit_data_collection = FitDataCollection()
for fit_variable in fit_variables:
histograms = get_histograms( channel,
input_files,
variable = variable,
met_type = met_type,
variable_bin = variable_bin,
b_tag_bin = b_tag_bin,
rebin = measurement_config.rebin[fit_variable],
fit_variable = fit_variable,
scale_factors = scale_factors,
)
# create data sets
h_fit_variable_signal = None
mc_histograms = None
if options.make_combined_signal:
if measurement_config.include_higgs:
h_fit_variable_signal = histograms['TTJet'] + histograms['SingleTop'] + histograms['Higgs']
else:
h_fit_variable_signal = histograms['TTJet'] + histograms['SingleTop']
mc_histograms = {
'signal' : h_fit_variable_signal,
'V+Jets': histograms['V+Jets'],
'QCD': histograms['QCD'],
}
else:
mc_histograms = {
'TTJet': histograms['TTJet'],
'SingleTop': histograms['SingleTop'],
'V+Jets': histograms['V+Jets'],
'QCD': histograms['QCD'],
}
h_data = histograms['data']
if options.closure_test:
ct_type = options.closure_test_type
ct_norm = closure_tests[ct_type]
h_data = histograms['TTJet'] * ct_norm['TTJet'] + histograms['SingleTop'] * ct_norm['SingleTop'] + histograms['V+Jets'] * ct_norm['V+Jets'] + histograms['QCD'] * ct_norm['QCD']
fit_data = FitData( h_data,
mc_histograms,
fit_boundaries = measurement_config.fit_boundaries[fit_variable] )
fit_data_collection.add( fit_data, name = fit_variable )
if options.enable_constraints:
fit_data_collection.set_normalisation_constraints( {'QCD': 2.0, 'V+Jets': 0.5} )
if use_fitter == 'RooFit':
fitter = RooFitFit( fit_data_collection )
elif use_fitter == 'Minuit':
fitter = Minuit( fit_data_collection, verbose = verbose )
else: # not recognised
sys.stderr.write( 'Do not recognise fitter "%s". Using default (Minuit).\n' % fitter )
fitter = Minuit ( fit_data_collection )
if verbose:
print "FITTING: " + channel + '_' + variable + '_' + variable_bin + '_' + met_type + '_' + b_tag_bin
fitter.fit()
fit_results = fitter.readResults()
normalisation = fit_data_collection.mc_normalisation( fit_variables[0] )
normalisation_errors = fit_data_collection.mc_normalisation_errors( fit_variables[0] )
if options.make_combined_signal:
N_ttbar_before_fit = histograms['TTJet'].Integral()
N_SingleTop_before_fit = histograms['SingleTop'].Integral()
N_ttbar_error_before_fit = sum(histograms['TTJet'].yerravg())
N_SingleTop_error_before_fit = sum(histograms['SingleTop'].yerravg())
N_Higgs_before_fit = 0
N_Higgs_error_before_fit = 0
if measurement_config.include_higgs:
N_Higgs_before_fit = histograms['Higgs'].Integral()
N_Higgs_error_before_fit = sum(histograms['Higgs'].yerravg())
if (N_SingleTop_before_fit != 0):
TTJet_SingleTop_ratio = (N_ttbar_before_fit + N_Higgs_before_fit) / N_SingleTop_before_fit
else:
print 'Bin ', variable_bin, ': ttbar/singleTop ratio undefined for %s channel! Setting to 0.' % channel
TTJet_SingleTop_ratio = 0
N_ttbar_all, N_SingleTop = decombine_result(fit_results['signal'], TTJet_SingleTop_ratio)
if (N_Higgs_before_fit != 0):
TTJet_Higgs_ratio = N_ttbar_before_fit/ N_Higgs_before_fit
else:
TTJet_Higgs_ratio = 0
N_ttbar, N_Higgs = decombine_result(N_ttbar_all, TTJet_Higgs_ratio)
fit_results['TTJet'] = N_ttbar
fit_results['SingleTop'] = N_SingleTop
fit_results['Higgs'] = N_Higgs
normalisation['TTJet'] = N_ttbar_before_fit
normalisation['SingleTop'] = N_SingleTop_before_fit
normalisation['Higgs'] = N_Higgs_before_fit
normalisation_errors['TTJet'] = N_ttbar_error_before_fit
normalisation_errors['SingleTop'] = N_SingleTop_error_before_fit
normalisation_errors['Higgs'] = N_Higgs_error_before_fit
if results == {}: # empty
initial_values['data'] = [( normalisation['data'], normalisation_errors['data'] )]
for fit_variable in fit_variables:
templates[fit_variable]['data'] = [fit_data_collection.vectors( fit_variable )['data']]
for sample in fit_results.keys():
results[sample] = [fit_results[sample]]
initial_values[sample] = [( normalisation[sample], normalisation_errors[sample] )]
if sample in ['TTJet', 'SingleTop', 'Higgs'] and options.make_combined_signal:
continue
for fit_variable in fit_variables:
templates[fit_variable][sample] = [fit_data_collection.vectors( fit_variable )[sample]]
else:
initial_values['data'].append( [normalisation['data'], normalisation_errors['data']] )
for fit_variable in fit_variables:
templates[fit_variable]['data'].append( fit_data_collection.vectors( fit_variable )['data'] )
for sample in fit_results.keys():
results[sample].append( fit_results[sample] )
initial_values[sample].append( [normalisation[sample], normalisation_errors[sample]] )
if sample in ['TTJet', 'SingleTop', 'Higgs'] and options.make_combined_signal:
continue
for fit_variable in fit_variables:
templates[fit_variable][sample].append( fit_data_collection.vectors( fit_variable )[sample] )
# print "results = ", results
return results, initial_values, templates
def get_fitted_normalisation_from_ROOT(channel,
input_files,
variable,
met_systematic,
met_type,
b_tag_bin,
treePrefix,
weightBranch,
scale_factors=None):
'''
Retrieves the number of ttbar events from fits to one or more distribution
(fit_variables) for each bin in the variable.
'''
global use_fitter, measurement_config, verbose, fit_variables, options
# results and initial values are the same across different fit variables
# templates are not
results = {}
initial_values = {}
templates = {fit_variable: {} for fit_variable in fit_variables}
for variable_bin in variable_bins_ROOT[variable]:
fitter = None
fit_data_collection = FitDataCollection()
for fit_variable in fit_variables:
histograms = get_histograms(
channel,
input_files,
variable=variable,
met_systematic=met_systematic,
met_type=met_type,
variable_bin=variable_bin,
b_tag_bin=b_tag_bin,
rebin=measurement_config.rebin[fit_variable],
fit_variable=fit_variable,
scale_factors=scale_factors,
treePrefix=treePrefix,
weightBranch=weightBranch,
)
# create data sets
h_fit_variable_signal = None
mc_histograms = None
# if options.make_combined_signal:
# h_fit_variable_signal = histograms['TTJet'] + histograms['SingleTop']
# mc_histograms = {
# 'signal' : h_fit_variable_signal,
# 'V+Jets': histograms['V+Jets'],
# 'QCD': histograms['QCD'],
# }
# else:
mc_histograms = {
'TTJet': histograms['TTJet'],
'SingleTop': histograms['SingleTop'],
'V+Jets': histograms['V+Jets'],
'QCD': histograms['QCD'],
}
h_data = histograms['data']
# if options.closure_test:
# ct_type = options.closure_test_type
# ct_norm = closure_tests[ct_type]
# h_data = histograms['TTJet'] * ct_norm['TTJet'] + histograms['SingleTop'] * ct_norm['SingleTop'] + histograms['V+Jets'] * ct_norm['V+Jets'] + histograms['QCD'] * ct_norm['QCD']
fit_data = FitData(
h_data,
mc_histograms,
fit_boundaries=measurement_config.fit_boundaries[fit_variable])
fit_data_collection.add(fit_data, name=fit_variable)
# if options.enable_constraints:
# fit_data_collection.set_normalisation_constraints( {'QCD': 2.0, 'V+Jets': 0.5} )
if use_fitter == 'RooFit':
fitter = RooFitFit(fit_data_collection)
elif use_fitter == 'Minuit':
fitter = Minuit(fit_data_collection, verbose=verbose)
else: # not recognised
sys.stderr.write(
'Do not recognise fitter "%s". Using default (Minuit).\n' %
fitter)
fitter = Minuit(fit_data_collection)
if verbose:
print "FITTING: " + channel + '_' + variable + '_' + variable_bin + '_' + met_type + '_' + b_tag_bin
fitter.fit()
fit_results = fitter.readResults()
normalisation = fit_data_collection.mc_normalisation(fit_variables[0])
normalisation_errors = fit_data_collection.mc_normalisation_errors(
fit_variables[0])
# if options.make_combined_signal:
# N_ttbar_before_fit = histograms['TTJet'].Integral()
# N_SingleTop_before_fit = histograms['SingleTop'].Integral()
# N_ttbar_error_before_fit = sum(histograms['TTJet'].yerravg())
# N_SingleTop_error_before_fit = sum(histograms['SingleTop'].yerravg())
# N_Higgs_before_fit = 0
# N_Higgs_error_before_fit = 0
# if measurement_config.include_higgs:
# N_Higgs_before_fit = histograms['Higgs'].Integral()
# N_Higgs_error_before_fit = sum(histograms['Higgs'].yerravg())
# if (N_SingleTop_before_fit != 0):
# TTJet_SingleTop_ratio = (N_ttbar_before_fit + N_Higgs_before_fit) / N_SingleTop_before_fit
# else:
# print 'Bin ', variable_bin, ': ttbar/singleTop ratio undefined for %s channel! Setting to 0.' % channel
# TTJet_SingleTop_ratio = 0
# N_ttbar_all, N_SingleTop = decombine_result(fit_results['signal'], TTJet_SingleTop_ratio)
# if (N_Higgs_before_fit != 0):
# TTJet_Higgs_ratio = N_ttbar_before_fit/ N_Higgs_before_fit
# else:
# TTJet_Higgs_ratio = 0
# N_ttbar, N_Higgs = decombine_result(N_ttbar_all, TTJet_Higgs_ratio)
# fit_results['TTJet'] = N_ttbar
# fit_results['SingleTop'] = N_SingleTop
# fit_results['Higgs'] = N_Higgs
# normalisation['TTJet'] = N_ttbar_before_fit
# normalisation['SingleTop'] = N_SingleTop_before_fit
# normalisation['Higgs'] = N_Higgs_before_fit
# normalisation_errors['TTJet'] = N_ttbar_error_before_fit
# normalisation_errors['SingleTop'] = N_SingleTop_error_before_fit
# normalisation_errors['Higgs'] = N_Higgs_error_before_fit
if results == {}: # empty
initial_values['data'] = [(normalisation['data'],
normalisation_errors['data'])]
for fit_variable in fit_variables:
templates[fit_variable]['data'] = [
fit_data_collection.vectors(fit_variable)['data']
]
for sample in fit_results.keys():
results[sample] = [fit_results[sample]]
initial_values[sample] = [(normalisation[sample],
normalisation_errors[sample])]
if sample in ['TTJet', 'SingleTop', 'Higgs'
] and options.make_combined_signal:
continue
for fit_variable in fit_variables:
templates[fit_variable][sample] = [
fit_data_collection.vectors(fit_variable)[sample]
]
else:
initial_values['data'].append(
[normalisation['data'], normalisation_errors['data']])
for fit_variable in fit_variables:
templates[fit_variable]['data'].append(
fit_data_collection.vectors(fit_variable)['data'])
for sample in fit_results.keys():
results[sample].append(fit_results[sample])
initial_values[sample].append(
[normalisation[sample], normalisation_errors[sample]])
if sample in ['TTJet', 'SingleTop', 'Higgs'
] and options.make_combined_signal:
continue
for fit_variable in fit_variables:
templates[fit_variable][sample].append(
fit_data_collection.vectors(fit_variable)[sample])
# print results
# print "results = ", results
# print 'templates = ',templates
return results, initial_values, templates