def yieldstable(workspace, samples, channels, output_name, table_name, is_cr=False, show_before_fit=False, unblind=True):
if is_cr:
show_before_fit=True
normalization_factors = get_normalization_factors(workspace)
#sample_str = samples.replace(",","_")
from cmdLineUtils import cmdStringToListOfLists
samples_list = cmdStringToListOfLists(samples)
regions_list = [ '%s_cuts' % r for r in channels.split(",") ]
#samples_list = samples.split(",")
# call the function to calculate the numbers, or take numbers from pickle file
if workspace.endswith(".pickle"):
print "READING PICKLE FILE"
f = open(workspace, 'r')
m = pickle.load(f)
f.close()
else:
#m = YieldsTable.latexfitresults(workspace, regions_list, samples_list, 'obsData')
m = latexfitresults(workspace, regions_list, samples_list)
with open(output_name.replace('.tex', '.pickle'), 'w') as f:
pickle.dump(m, f)
regions_names = [ region.replace("_cuts", "").replace('_','\_') for region in m['names'] ]
field_names = [table_name,] + regions_names
align = ['l',] + [ 'r' for i in regions_names ]
samples_list_decoded = []
for isam, sample in enumerate(samples_list):
sampleName = getName(sample)
samples_list_decoded.append(sampleName)
samples_list = samples_list_decoded
tablel = LatexTable(field_names, align=align, env=True)
tablep = PrettyTable(field_names, align=align)
# number of observed events
if unblind:
row = ['Observed events',] + [ '%d' % n for n in m['nobs'] ]
else:
row = ['Observed events',] + [ '-' for n in m['nobs'] ]
tablel.add_row(row)
tablep.add_row(row)
tablel.add_line()
tablep.add_line()
#print the total fitted (after fit) number of events
# if the N_fit - N_error extends below 0, make the error physical , meaning extend to 0
rowl = ['Expected SM events', ]
rowp = ['Expected SM events', ]
for index, n in enumerate(m['TOTAL_FITTED_bkg_events']):
if (n - m['TOTAL_FITTED_bkg_events_err'][index]) > 0. :
rowl.append('$%.2f \pm %.2f$' % (n, m['TOTAL_FITTED_bkg_events_err'][index]))
rowp.append('%.2f ± %.2f' % (n, m['TOTAL_FITTED_bkg_events_err'][index]))
else:
#print "WARNING: negative symmetric error after fit extends below 0. for total bkg pdf: will print asymmetric error w/ truncated negative error reaching to 0."
rowl.append('$%.2f_{-%.2f}^{+%.2f}$' % (n, n, m['TOTAL_FITTED_bkg_events_err'][index]))
rowp.append('%.2f -%.2f +%.2f' % (n, n, m['TOTAL_FITTED_bkg_events_err'][index]))
tablel.add_row(rowl)
tablel.add_line()
tablep.add_row(rowp)
tablep.add_line()
map_listofkeys = m.keys()
# print fitted number of events per sample
# if the N_fit - N_error extends below 0, make the error physical , meaning extend to 0
for sample in samples_list:
for name in map_listofkeys:
rowl = []
rowp = []
if not "Fitted_events_" in name:
continue
sample_name = name.replace("Fitted_events_", "")
if sample_name != sample:
continue
rowl.append('%s' % labels_latex_dict.get(sample_name, sample_name).replace('_', '\_'))
rowp.append('%s' % labels_html_dict.get(sample_name, sample_name))
for index, n in enumerate(m[name]):
if ((n - m['Fitted_err_'+sample][index]) > 0.) or not abs(n) > 0.00001:
rowl.append('$%.2f \\pm %.2f$' % (n, m['Fitted_err_'+sample][index]))
rowp.append('%.2f ± %.2f' % (n, m['Fitted_err_'+sample][index]))
else:
#print "WARNING: negative symmetric error after fit extends below 0. for sample", sample, " will print asymmetric error w/ truncated negative error reaching to 0."
rowl.append('$%.2f_{-%.2f}^{+%.2f}$' % (n, n, m['Fitted_err_'+sample][index]))
rowp.append('%.2f -%.2f +%.2f' % (n, n, m['Fitted_err_'+sample][index]))
tablel.add_row(rowl)
tablep.add_row(rowp)
tablel.add_line()
tablep.add_line()
# print the total expected (before fit) number of events
if show_before_fit:
# if the N_fit - N_error extends below 0, make the error physical , meaning extend to 0
rowl = ['Before SM events',]
rowp = ['(before fit) SM events',]
total_before = []
purity_before = []
for index, n in enumerate(m['TOTAL_MC_EXP_BKG_events']):
if regions_names[index].startswith('CR'):
total_before.append(n)
rowl.append('$%.2f$' % n)
rowp.append('%.2f' % n)
tablel.add_row(rowl)
tablel.add_line()
tablep.add_row(rowp)
tablep.add_line()
map_listofkeys = m.keys()
# print expected number of events per sample
# if the N_fit - N_error extends below 0, make the error physical , meaning extend to 0
for sample in samples_list:
for name in map_listofkeys:
rowl = []
rowp = []
if "MC_exp_events_" in name and sample in name:
sample_name = name.replace("MC_exp_events_","")
if sample_name != sample:
continue
rowl.append('(before fit) %s' % labels_latex_dict.get(sample_name, sample_name).replace('_', '\_'))
rowp.append('(before fit) %s' % labels_html_dict.get(sample_name, sample_name))
for index, n in enumerate(m[name]):
if regions_names[index] == 'CRQ' and sample == 'photonjet':
purity_before.append(n)
if regions_names[index] == 'CRW' and sample == 'wgamma':
purity_before.append(n)
if regions_names[index] == 'CRT' and sample == 'ttbarg':
purity_before.append(n)
rowl.append('$%.2f$' % n)
rowp.append('%.2f' % n)
tablel.add_row(rowl)
tablep.add_row(rowp)
tablel.add_line()
tablep.add_line()
if show_before_fit and all([r.startswith('CR') for r in regions_names]) and normalization_factors is not None:
tablel.add_row(['', '', '', ''])
tablel.add_line()
tablep.add_row(['', '', '', ''])
tablep.add_line()
# purity
rowl = ['Background purity',]
rowp = ['Background purity',]
for index, region in enumerate(regions_names):
purity = int(purity_before[index]/total_before[index] * 100.)
rowl.append('$%i\%%$' % purity)
rowp.append('%i%%' % purity)
tablel.add_row(rowl)
tablel.add_line()
tablep.add_row(rowp)
tablep.add_line()
# normalization
rowl = ['Normalization factor ($\mu$)',]
rowp = ['Normalization factor (mu)',]
for region in regions_names:
rowl.append('$%.2f \pm %.2f$' % normalization_factors[region])
rowp.append('%.2f ± %.2f' % normalization_factors[region])
tablel.add_row(rowl)
tablel.add_line()
tablep.add_row(rowp)
tablep.add_line()
tablel.save_tex(output_name)
with open(output_name.replace('.tex', '.html'), 'w+') as f:
f.write(tablep.get_html_string())
def systable(workspace, samples, channels, output_name):
chan_str = channels.replace(",","_")
chan_list = channels.split(",")
chosen_sample = False
if samples:
sample_str = samples.replace(",","_") + "_"
from cmdLineUtils import cmdStringToListOfLists
sample_list = cmdStringToListOfLists(samples)
chosen_sample = True
show_percent = True
doAsym = True
result_name = 'RooExpandedFitResult_afterFit'
skip_list = ['sqrtnobsa', 'totbkgsysa', 'poisqcderr','sqrtnfitted','totsyserr','nfitted']
chan_sys = {}
orig_chan_list = list(chan_list)
chan_list = []
# calculate the systematics breakdown for each channel/region given in chanList
# choose whether to use method-1 or method-2
# choose whether calculate systematic for full model or just a sample chosen by user
for chan in orig_chan_list:
if not chosen_sample:
reg_sys = latexfitresults(workspace, chan, '', result_name, 'obsData', doAsym)
chan_sys[chan] = reg_sys
chan_list.append(chan)
else:
for sample in sample_list:
sample_name = getName(sample)
reg_sys = latexfitresults(workspace, chan, sample, result_name, 'obsData', doAsym)
chan_sys[chan+"_"+sample_name] = reg_sys
chan_list.append(chan+"_"+sample_name)
# write out LaTeX table by calling function from SysTableTex.py function tablefragment
#line_chan_sys_tight = tablefragment(chanSys,chanList,skiplist,chanStr,showPercent)
if not chosen_sample:
field_names = ['\\textbf{Uncertainties}',] + [ '\\textbf{%s}' % reg for reg in chan_list ]
elif len(sample_list) == 1:
sample_label = labels_latex_dict.get(getName(sample_list[0]), getName(sample_list[0]))
field_names = ['\\textbf{Uncertainties (%s)}' % sample_label ] + [ '\\textbf{%s}' % (reg.split('_')[0]) for reg in chan_list ]
else:
field_names = ['\\textbf{Uncertainties}',] + [ '\\textbf{%s (%s)}' % (reg.split('_')[0], reg.split('_')[1]) for reg in chan_list ]
align = ['l',] + [ 'r' for i in chan_list ]
tablel = LatexTable(field_names, align=align, env=True)
# print the total fitted (after fit) number of events
row = ['Total background expectation',]
for region in chan_list:
row.append("$%.2f$" % chan_sys[region]['nfitted'])
tablel.add_row(row)
tablel.add_line()
# print sqrt(N_obs) - for comparison with total systematic
row = ['Total statistical $(\\sqrt{N_\\mathrm{exp}})$',]
for region in chan_list:
row.append("$\\pm %.2f$" % chan_sys[region]['sqrtnfitted'])
tablel.add_row(row)
# print total systematic uncertainty
row = [ 'Total background systematic', ]
for region in chan_list:
percentage = chan_sys[region]['totsyserr']/chan_sys[region]['nfitted'] * 100.0
row.append("$\\pm %.2f\ [%.2f\%%]$" % (chan_sys[region]['totsyserr'], percentage))
tablel.add_row(row)
tablel.add_line()
tablel.add_line()
# print systematic uncertainty per floated parameter (or set of parameters, if requested)
d = chan_sys[chan_list[0]]
m_listofkeys = sorted(d.iterkeys(), key=lambda k: d[k], reverse=True)
# uncertanties dict
unc_dict = dict()
unc_order = []
for name in m_listofkeys:
if name in skip_list:
continue
printname = name.replace('syserr_','')
#slabel = label.split('_')
#label = 'MC stat. (%s)' % slabel[2]
# skip negligible uncertainties in all requested regions:
zero = True
for index, region in enumerate(chan_list):
percentage = chan_sys[region][name]/chan_sys[region]['nfitted'] * 100.0
if ('%.4f' % chan_sys[region][name]) != '0.0000' and ('%.2f' % percentage) != '0.00':
zero = False
if zero:
continue
# Parameter name -> parameter label
if printname.startswith('gamma_stat'):
label = 'MC stat.'
elif printname.startswith('gamma_shape_JFAKE_STAT_jfake'):
label = 'jet $\\to\\gamma$ fakes stat.'
elif printname.startswith('gamma_shape_EFAKE_STAT_efake'):
label = '$e\\to\\gamma$ fakes stat.'
else:
if printname in systdict and systdict[printname]:
label = systdict[printname]
else:
label = printname
# Fill dict
for index, region in enumerate(chan_list):
if printname.startswith('gamma') and not region.split('_')[0] in printname:
continue
if not label in unc_dict:
unc_dict[label] = []
unc_order.append(label)
if not show_percent:
unc_dict[label].append("$\\pm %.2f$" % chan_sys[region][name])
else:
percentage = chan_sys[region][name]/chan_sys[region]['nfitted'] * 100.0
if percentage < 1:
unc_dict[label].append("$\\pm %.2f\ [%.2f\%%]$" % (chan_sys[region][name], percentage))
else:
unc_dict[label].append("$\\pm %.2f\ [%.1f\%%]$" % (chan_sys[region][name], percentage))
# fill table
for label in unc_order:
tablel.add_row([label,] + unc_dict[label])
tablel.add_line()
tablel.save_tex(output_name)
def yieldstable(workspace,
samples,
channels,
output_name,
table_name='',
show_before_fit=False,
unblind=True,
show_cr_info=False,
cr_dict={}):
if show_cr_info:
show_before_fit = True
normalization_factors = get_normalization_factors(workspace)
samples_list = cmdStringToListOfLists(samples)
regions_list = ['%s_cuts' % r for r in channels.split(",")]
# call the function to calculate the numbers, or take numbers from pickle file
if workspace.endswith(".pickle"):
print "Reading from pickle file"
f = open(workspace, 'r')
m = pickle.load(f)
f.close()
else:
#m = YieldsTable.latexfitresults(workspace, regions_list, samples_list, 'obsData')
m = latexfitresults(workspace, regions_list, samples_list)
with open(output_name.replace('.tex', '.pickle'), 'w') as f:
pickle.dump(m, f)
regions_names = [
region.replace("_cuts", "").replace('_', '\_') for region in m['names']
]
field_names = [
table_name,
] + regions_names
align = [
'l',
] + ['r' for i in regions_names]
samples_list_decoded = []
for isam, sample in enumerate(samples_list):
sampleName = getName(sample)
samples_list_decoded.append(sampleName)
samples_list = samples_list_decoded
tablel = LatexTable(field_names, align=align, env=True)
# number of observed events
if unblind:
row = [
'Observed events',
] + ['%d' % n for n in m['nobs']]
else:
row = [
'Observed events',
] + ['-' for n in m['nobs']]
tablel.add_row(row)
tablel.add_line()
# Total fitted (after fit) number of events
# if the N_fit - N_error extends below 0, make the error physical, meaning extend to 0
rowl = [
'Expected SM events',
]
for index, n in enumerate(m['TOTAL_FITTED_bkg_events']):
if (n - m['TOTAL_FITTED_bkg_events_err'][index]) > 0.:
rowl.append('$%.2f \pm %.2f$' %
(n, m['TOTAL_FITTED_bkg_events_err'][index]))
else:
rowl.append('$%.2f_{-%.2f}^{+%.2f}$' %
(n, n, m['TOTAL_FITTED_bkg_events_err'][index]))
tablel.add_row(rowl)
tablel.add_line()
map_listofkeys = m.keys()
# After fit number of events per sample (if the N_fit-N_error extends below 0, make the error physical, meaning extend to 0)
for sample in samples_list:
for name in map_listofkeys:
rowl = []
if not "Fitted_events_" in name:
continue
sample_name = name.replace("Fitted_events_", "")
if sample_name != sample:
continue
rowl.append('%s' % labels_latex_dict.get(
sample_name, sample_name).replace('_', '\_'))
for index, n in enumerate(m[name]):
if ((n - m['Fitted_err_' + sample][index]) >
0.) or not abs(n) > 0.00001:
rowl.append('$%.2f \\pm %.2f$' %
(n, m['Fitted_err_' + sample][index]))
else:
rowl.append('$%.2f_{-%.2f}^{+%.2f}$' %
(n, n, m['Fitted_err_' + sample][index]))
tablel.add_row(rowl)
tablel.add_line()
# Total expected (before fit) number of events
if show_before_fit:
# if the N_fit - N_error extends below 0, make the error physical, meaning extend to 0
rowl = [
'Before fit SM events',
]
total_before = {}
purity_before = {}
for index, n in enumerate(m['TOTAL_MC_EXP_BKG_events']):
reg_name = regions_names[index]
if cr_dict and reg_name in cr_dict:
total_before[reg_name] = n
rowl.append('$%.2f$' % n)
tablel.add_row(rowl)
tablel.add_line()
map_listofkeys = m.keys()
# Expected number of events per sample (if the N_fit - N_error extends below 0, make the error physical, meaning extend to 0)
for sample in samples_list:
for name in map_listofkeys:
rowl = []
if "MC_exp_events_" in name and sample in name:
sample_name = name.replace("MC_exp_events_", "")
if sample_name != sample:
continue
rowl.append('Before fit %s' % labels_latex_dict.get(
sample_name, sample_name).replace('_', '\_'))
for index, n in enumerate(m[name]):
reg_name = regions_names[index]
if cr_dict and reg_name in cr_dict and sample == cr_dict[
reg_name]:
purity_before[reg_name] = n
rowl.append('$%.2f$' % n)
tablel.add_row(rowl)
tablel.add_line()
if show_cr_info and normalization_factors is not None:
tablel.add_row(['' for i in range(len(regions_names) + 1)])
tablel.add_line()
# purity
rowl = [
'Background purity',
]
for region in regions_names:
try:
purity = int(
round(purity_before[region] / total_before[region] * 100.))
rowl.append('$%i\%%$' % purity)
except:
rowl.append('-')
tablel.add_row(rowl)
tablel.add_line()
# normalization
rowl = [
'Normalization factor ($\mu$)',
]
for region in regions_names:
try:
rowl.append('$%.2f \pm %.2f$' % normalization_factors[region])
except:
rowl.append('-')
tablel.add_row(rowl)
tablel.add_line()
tablel.save_tex(output_name)