def getSkimmedEvents(files):
totalInitialEvents = 0
for file in files:
skimHist = get_histogram_from_file( pathToSkimHist, file )
firstBinContent = list(skimHist.y())[0]
totalInitialEvents += firstBinContent
return totalInitialEvents
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 make_scatter_plot( input_file, histogram, bin_edges, channel, variable, title ):
global output_folder, output_formats, options
scatter_plot = get_histogram_from_file( histogram, input_file )
# Finding max value in scatterplot for colourmap normalisation
max_bin = scatter_plot.GetMaximumBin()
max_bin_content = scatter_plot.GetBinContent(max_bin)
norm = mpl.colors.LogNorm(vmin = 1, vmax = int(max_bin_content+1))
# scatter_plot.Rebin2D( 5, 5 )
x_limits = [bin_edges[variable][0], bin_edges[variable][-1]]
y_limits = x_limits
x_title = 'Reconstructed $' + variables_latex[variable] + '$ [GeV]'
y_title = 'Generated $' + variables_latex[variable] + '$ [GeV]'
save_as_name = channel + '_' + variable + '_' + str(options.CoM) + 'TeV'
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
im = rplt.imshow( scatter_plot, axes = ax0, cmap = my_cmap, norm=norm )
colorbar = plt.colorbar( im )
colorbar.ax.tick_params( **CMS.axis_label_major )
# draw lines at bin edges values
for edge in bin_edges[variable]:
# do not inclue first and last values
if ( edge != bin_edges[variable][0] ) and ( edge != bin_edges[variable][-1] ):
plt.axvline( x = edge, color = 'red', linewidth = 4, alpha = 0.5 )
plt.axhline( y = edge, color = 'red', linewidth = 4, alpha = 0.5 )
ax0.set_xlim( x_limits )
ax0.set_ylim( y_limits )
plt.tick_params( **CMS.axis_label_major )
plt.tick_params( **CMS.axis_label_minor )
plt.xlabel( x_title, CMS.x_axis_title )
plt.ylabel( y_title, CMS.y_axis_title )
plt.title( title, CMS.title )
plt.tight_layout()
for output_format in output_formats:
plt.savefig( output_folder + save_as_name + '.' + output_format )
def read_sample(self, sample):
if self.samples[sample].has_key('input'):
i = self.samples[sample]['input']
if isinstance(i, dict):
i = Input(**self.samples[sample]['input'])
self.histograms[sample] = i.read()
return
input_file = self.samples[sample]['input_file']
if self.samples[sample].has_key('hist'):
hist = self.samples[sample]['hist']
self.histograms[sample] = get_histogram_from_file(
hist, input_file)
def __set_unfolding_histograms__( self ):
# at the moment only one file is supported for the unfolding input
files = set(
[self.truth['file'],
self.gen_vs_reco['file'],
self.measured['file']]
)
if len( files ) > 1:
print "Currently not supported to have different files for truth, gen_vs_reco and measured"
sys.exit()
input_file = files.pop()
visiblePS = self.phaseSpace
t, m, r, f = get_unfold_histogram_tuple(
File(input_file),
self.variable,
self.channel,
centre_of_mass = self.centre_of_mass_energy,
ttbar_xsection=self.measurement_config.ttbar_xsection,
luminosity=self.measurement_config.luminosity,
load_fakes = True,
visiblePS = visiblePS
)
self.h_truth = asrootpy ( t )
self.h_response = asrootpy ( r )
self.h_measured = asrootpy ( m )
self.h_fakes = asrootpy ( f )
self.h_refolded = None
data_file = self.data['file']
if data_file.endswith('.root'):
self.h_data = get_histogram_from_file(self.data['histogram'], self.data['file'])
elif data_file.endswith('.json') or data_file.endswith('.txt'):
data_key = self.data['histogram']
# assume configured bin edges
edges = []
edges = reco_bin_edges_vis[self.variable]
json_input = read_tuple_from_file(data_file)
if data_key == "": # JSON file == histogram
self.h_data = value_error_tuplelist_to_hist(json_input, edges)
else:
self.h_data = value_error_tuplelist_to_hist(json_input[data_key], edges)
else:
print 'Unkown file extension', data_file.split('.')[-1]
def __set_unfolding_histograms__( self ):
# at the moment only one file is supported for the unfolding input
files = set( [self.truth['file'],
self.gen_vs_reco['file'],
self.measured['file']]
)
if len( files ) > 1:
print "Currently not supported to have different files for truth, gen_vs_reco and measured"
sys.exit()
input_file = files.pop()
visiblePS = False
if self.phaseSpace == 'VisiblePS':
visiblePS = True
t, m, r, f = get_unfold_histogram_tuple( File(input_file),
self.variable,
self.channel,
centre_of_mass = self.centre_of_mass_energy,
ttbar_xsection=self.measurement_config.ttbar_xsection,
luminosity=self.measurement_config.luminosity,
load_fakes = True,
visiblePS = visiblePS
)
self.h_truth = asrootpy ( t )
self.h_response = asrootpy ( r )
self.h_measured = asrootpy ( m )
self.h_fakes = asrootpy ( f )
data_file = self.data['file']
if data_file.endswith('.root'):
self.h_data = get_histogram_from_file(self.data['histogram'], self.data['file'])
elif data_file.endswith('.json') or data_file.endswith('.txt'):
data_key = self.data['histogram']
# assume configured bin edges
edges = []
edges = reco_bin_edges_vis[self.variable]
json_input = read_tuple_from_file(data_file)
if data_key == "": # JSON file == histogram
self.h_data = value_error_tuplelist_to_hist(json_input, edges)
else:
self.h_data = value_error_tuplelist_to_hist(json_input[data_key], edges)
else:
print 'Unkown file extension', data_file.split('.')[-1]
def read(self):
if not self.isValid():
raise ValueError('Inputs are not valid {0}'.format(self.error))
if self.hist_name:
self.hist = get_histogram_from_file(
self.hist_name, self.file)
if self.tree_name:
self.hist = get_histogram_from_tree(
tree=self.tree_name,
branch=self.branch,
weight_branches=self.weight_branches,
selection=self.selection,
input_file=self.file,
**self.kwargs
)
self.hist.Scale(self.lumi_scale * self.scale)
return self.hist
