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')
h_bkg1_2 = h_bkg1_1.Clone(title='Background')
h_signal_2 = h_bkg1_1.Clone(title='Signal')
h_data_2 = 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)
map(h_bkg1_2.Fill, x3)
map(h_signal_2.Fill, x4)
map(h_data_2.Fill, x3_obs)
map(h_data_2.Fill, x4_obs)
h_data_1.Scale(data_scale)
h_data_2.Scale(data_scale)
histograms_1 = {'signal': h_signal_1, 'bkg1': h_bkg1_1}
histograms_2 = {'signal': h_signal_2, 'bkg1': h_bkg1_2}
fit_data_1 = FitData(h_data_1, histograms_1, fit_boundaries=(40, 200))
fit_data_2 = FitData(h_data_2, histograms_2, fit_boundaries=(40, 200))
single_fit_collection = FitDataCollection()
single_fit_collection.add(fit_data_1)
collection_1 = FitDataCollection()
collection_1.add(fit_data_1, 'var1')
collection_1.add(fit_data_2, 'var2')
collection_2 = FitDataCollection()
collection_2.add(fit_data_1, 'var1')
collection_2.add(fit_data_2, 'var2')
collection_2.set_normalisation_constraints({'bkg1': 0.5})
collection_3 = FitDataCollection()
collection_3.add(fit_data_1, 'var1')
collection_3.add(fit_data_2, 'var2')
collection_3.set_normalisation_constraints({'bkg1': 0.001})
self.minuit_fitter = Minuit(single_fit_collection)
self.minuit_fitter.fit()
self.simultaneous_fit = Minuit(collection_1)
self.simultaneous_fit.fit()
self.simultaneous_fit_with_constraints = Minuit(collection_2)
self.simultaneous_fit_with_constraints.fit()
self.simultaneous_fit_with_bad_constraints = Minuit(collection_3)
self.simultaneous_fit_with_bad_constraints.fit()
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' )
h_bkg1_2 = h_bkg1_1.Clone( title = 'Background' )
h_signal_2 = h_bkg1_1.Clone( title = 'Signal' )
h_data_2 = 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 )
map( h_bkg1_2.Fill, x3 )
map( h_signal_2.Fill, x4 )
map( h_data_2.Fill, x3_obs )
map( h_data_2.Fill, x4_obs )
h_data_1.Scale(data_scale)
h_data_2.Scale(data_scale)
self.histograms_1 = {'signal': h_signal_1,
'bkg1': h_bkg1_1}
self.histograms_2 = {'signal': h_signal_2,
'bkg1': h_bkg1_2}
self.histograms_3 = {'var1': h_signal_1,
'bkg1': h_bkg1_1}
self.fit_data_1 = FitData( h_data_1, self.histograms_1, fit_boundaries = ( x_min, x_max ))
self.fit_data_2 = FitData( h_data_2, self.histograms_2, fit_boundaries = ( x_min, x_max ))
self.fit_data_3 = FitData( h_data_1, self.histograms_3, fit_boundaries = ( x_min, x_max ))
self.collection_1 = FitDataCollection()
self.collection_1.add( self.fit_data_1, 'signal region' )
self.collection_1.add( self.fit_data_2, 'control region' )
self.collection_1.set_normalisation_constraints({'bkg1': 0.5})
self.collection_2 = FitDataCollection()
self.collection_2.add( self.fit_data_1 )
self.collection_2.add( self.fit_data_2 )
self.collection_2.set_normalisation_constraints({'bkg1': 0.5})
self.single_collection = FitDataCollection()
self.single_collection.add( self.fit_data_1 )
self.single_collection.set_normalisation_constraints({'bkg1': 0.5})
self.non_simultaneous_fit_collection = FitDataCollection()
self.non_simultaneous_fit_collection.add( self.fit_data_1 )
self.non_simultaneous_fit_collection.add( self.fit_data_3 )
self.h_data = h_data_1
self.h_bkg1 = h_bkg1_1
self.h_signal = h_signal_1
def simultaneous_fit(self, histograms):
from tools.Fitting import FitData, FitDataCollection, Minuit
print('not in production yet')
fitter = None
fit_data_collection = FitDataCollection()
for fit_variable in self.fit_variables:
mc_histograms = {
'TTJet': histograms['TTJet'],
'SingleTop': histograms['SingleTop'],
'V+Jets': histograms['V+Jets'],
'QCD': histograms['QCD'],
}
h_data = histograms['data']
fit_data = FitData(
h_data,
mc_histograms,
fit_boundaries=self.config.fit_boundaries[fit_variable])
fit_data_collection.add(fit_data, name=fit_variable)
fitter = Minuit(fit_data_collection)
fitter.fit()
fit_results = fitter.readResults()
normalisation = fit_data_collection.mc_normalisation(
self.fit_variables[0])
normalisation_errors = fit_data_collection.mc_normalisation_errors(
self.fit_variables[0])
print normalisation, normalisation_errors
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 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)
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' )
h_bkg1_2 = h_bkg1_1.Clone( title = 'Background' )
h_signal_2 = h_bkg1_1.Clone( title = 'Signal' )
h_data_2 = 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 )
map( h_bkg1_2.Fill, x3 )
map( h_signal_2.Fill, x4 )
map( h_data_2.Fill, x3_obs )
map( h_data_2.Fill, x4_obs )
h_data_1.Scale(data_scale)
h_data_2.Scale(data_scale)
self.histograms_1 = {'signal': h_signal_1,
'bkg1': h_bkg1_1}
self.histograms_2 = {'signal': h_signal_2,
'bkg1': h_bkg1_2}
self.histograms_3 = {'var1': h_signal_1,
'bkg1': h_bkg1_1}
self.fit_data_1 = FitData( h_data_1, self.histograms_1, fit_boundaries = ( x_min, x_max ))
self.fit_data_2 = FitData( h_data_2, self.histograms_2, fit_boundaries = ( x_min, x_max ))
self.fit_data_3 = FitData( h_data_1, self.histograms_3, fit_boundaries = ( x_min, x_max ))
self.collection_1 = FitDataCollection()
self.collection_1.add( self.fit_data_1, 'signal region' )
self.collection_1.add( self.fit_data_2, 'control region' )
self.collection_1.set_normalisation_constraints({'bkg1': 0.5})
self.collection_2 = FitDataCollection()
self.collection_2.add( self.fit_data_1 )
self.collection_2.add( self.fit_data_2 )
self.collection_2.set_normalisation_constraints({'bkg1': 0.5})
self.single_collection = FitDataCollection()
self.single_collection.add( self.fit_data_1 )
self.single_collection.set_normalisation_constraints({'bkg1': 0.5})
self.non_simultaneous_fit_collection = FitDataCollection()
self.non_simultaneous_fit_collection.add( self.fit_data_1 )
self.non_simultaneous_fit_collection.add( self.fit_data_3 )
self.h_data = h_data_1
self.h_bkg1 = h_bkg1_1
self.h_signal = h_signal_1
def tearDown( self ):
pass
def test_is_valid_for_simultaneous_fit( self ):
self.assertTrue( self.collection_1.is_valid_for_simultaneous_fit(), msg = 'has_same_n_samples: ' + str(self.collection_1.has_same_n_samples) + ', has_same_n_data: ' + str(self.collection_1.has_same_n_data) )
self.assertTrue( self.collection_2.is_valid_for_simultaneous_fit(), msg = 'has_same_n_samples: ' + str(self.collection_1.has_same_n_samples) + ', has_same_n_data: ' + str(self.collection_1.has_same_n_data) )
self.assertFalse( self.non_simultaneous_fit_collection.is_valid_for_simultaneous_fit() )
def test_samples( self ):
samples = sorted( self.histograms_1.keys() )
samples_from_fit_data = sorted( self.fit_data_1.samples )
samples_from_fit_data_collection = self.collection_1.mc_samples()
self.assertEqual( samples, samples_from_fit_data )
self.assertEqual( samples, samples_from_fit_data_collection )
def test_normalisation( self ):
normalisation = {name:adjust_overflow_to_limit(histogram, x_min, x_max).Integral() for name, histogram in self.histograms_1.iteritems()}
normalisation_from_fit_data = self.fit_data_1.normalisation
normalisation_from_single_collection = self.single_collection.mc_normalisation()
normalisation_from_collection = self.collection_1.mc_normalisation( 'signal region' )
normalisation_from_collection_1 = self.collection_1.mc_normalisation()['signal region']
for sample in normalisation.keys():
self.assertEqual( normalisation[sample], normalisation_from_fit_data[sample] )
self.assertEqual( normalisation[sample], normalisation_from_single_collection[sample] )
self.assertEqual( normalisation[sample], normalisation_from_collection[sample] )
self.assertEqual( normalisation[sample], normalisation_from_collection_1[sample] )
# data normalisation
normalisation = self.h_data.integral( overflow = True )
normalisation_from_fit_data = self.fit_data_1.n_data()
normalisation_from_single_collection = self.single_collection.n_data()
normalisation_from_collection = self.collection_1.n_data( 'signal region' )
normalisation_from_collection_1 = self.collection_1.n_data()['signal region']
self.assertEqual( normalisation, normalisation_from_fit_data )
self.assertEqual( normalisation, normalisation_from_single_collection )
self.assertEqual( normalisation, normalisation_from_collection )
self.assertEqual( normalisation, normalisation_from_collection_1 )
self.assertAlmostEqual(normalisation, self.collection_1.max_n_data(), delta = 1 )
def test_real_data( self ):
real_data = self.fit_data_1.real_data_histogram()
self.assertEqual( self.h_data.integral( overflow = True ), real_data.Integral() )
def test_overwrite_warning( self ):
c = FitDataCollection()
c.add( self.fit_data_1, 'var1' )
self.assertRaises( UserWarning, c.add, ( self.fit_data_1, 'var1' ) )
def test_vectors( self ):
h_signal = adjust_overflow_to_limit( self.h_signal, x_min, x_max )
h_signal.Scale(1/h_signal.Integral())
h_bkg1 = adjust_overflow_to_limit( self.h_bkg1, x_min, x_max )
h_bkg1.Scale(1/h_bkg1.Integral())
signal = list( h_signal.y() )
bkg1 = list( h_bkg1.y() )
v_from_fit_data = self.fit_data_1.vectors
v_from_single_collection = self.single_collection.vectors()
# v_from_collection = self.collection_1.vectors( 'signal region' )
# v_from_collection_1 = self.collection_1.vectors()['signal region']
self.assertEqual(signal, v_from_fit_data['signal'])
self.assertEqual(bkg1, v_from_fit_data['bkg1'])
self.assertEqual(signal, v_from_single_collection['signal'])
self.assertEqual(bkg1, v_from_single_collection['bkg1'])
def test_constraints(self):
constraint_from_single_collection = self.single_collection.constraints()['bkg1']
self.assertEqual(0.5, constraint_from_single_collection)
c = Canvas()
c.Divide(2)
c.cd(1)
h_data.Draw('PE')
h_t1.Draw('SAME HIST')
h_t2.Draw('SAME HIST')
h_t3.Draw('SAME HIST')
h_t4.Draw('SAME HIST')
templates = {}
if useT1: templates['t1'] = h_t1
if useT2: templates['t2'] = h_t2
if useT3: templates['t3'] = h_t3
if useT4: templates['t4'] = h_t4
fit_data = FitData(h_data, templates, fit_boundaries=(0, h_data.nbins()))
fit_collection = FitDataCollection()
fit_collection.add(fit_data)
minuit_fitter = Minuit(fit_collection, method='logLikelihood', verbose=True)
minuit_fitter.fit()
results = minuit_fitter.readResults()
c.cd(2)
ymax = h_data.GetBinContent(h_data.GetMaximumBin()) * 1.1
h_data.GetYaxis().SetRangeUser(0, ymax)
h_data.Draw('PE')
leg = Legend(nTemplates + 2)
leg.AddEntry(h_data, style='LEP')
h_data_2 = 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 )
map( h_bkg1_2.Fill, x3 )
map( h_signal_2.Fill, x4 )
map( h_data_2.Fill, x3_obs )
map( h_data_2.Fill, x4_obs )
h_data_1.Scale( data_scale )
h_data_2.Scale( data_scale )
histograms_1 = {'signal': h_signal_1,
'bkg1': h_bkg1_1}
histograms_2 = {'signal': h_signal_2,
'bkg1': h_bkg1_2}
fit_data_1 = FitData( h_data_1, histograms_1, fit_boundaries = ( 40, 200 ) )
fit_data_2 = FitData( h_data_2, histograms_2, fit_boundaries = ( 40, 200 ) )
single_fit_collection = FitDataCollection()
single_fit_collection.add( fit_data_1 )
m = IMinuit(single_fit_collection)
print describe(m.likelihood_3_samples, verbose=True)
print describe(m.likelihood_4_samples, verbose=True)
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
if fillDataRandom:
h_data[variable].FillRandom( dataFillingHistogram, int( absolute_eta_initialValues['data'][whichBinFromFile][0] ))
else:
h_data[variable] = dataFillingHistogram
# if useT1: templates[variable]['t1'].Scale(1)
# if useT2: templates[variable]['t2'].Scale(1)
# if useT3: templates[variable]['t3'].Scale(1)
# if useT4: templates[variable]['t4'].Scale(10/templates[variable]['t4'].Integral())
# h_data[variable] = h_t1[variable] * 1.3
# h_data[variable].Scale(absolute_eta_initialValues['data'][whichBinFromFile][0] / h_data[variable].Integral() )
blah = getInitialValueErrors( variable, whichBinFromFile )
# fitData[variable] = FitData( h_data[variable], templates[variable], fit_boundaries = ( 0, h_data[variable].nbins() ), normalisation_limits = blah )
fitData[variable] = FitData( h_data[variable], templates[variable], fit_boundaries = ( 0, h_data[variable].nbins() ) )
pass
# Prepare fit
fit_collection = FitDataCollection()
for variable in variables:
fit_collection.add( fitData[variable], variable)
# Perform fit
minuit_fitter = Minuit( fit_collection, method = 'logLikelihood', verbose = False )
minuit_fitter.fit()
# Do stuff after fit
results = minuit_fitter.readResults()
