def json(self):
self._compute_()
jret = []
for idx in xrange(1, self.nbins+1):
jbin = {
'median' : self.median_value(idx),
'one_sigma' : {'range' : self.one_sigma_range(idx)},
'two_sigma' : {'range' : self.two_sigma_range(idx)},
'label' : self.median_.GetXaxis().GetBinLabel(idx),
'low_edge' : self.median_.GetXaxis().GetBinLowEdge(idx),
'up_edge' : self.median_.GetXaxis().GetBinUpEdge(idx),
}
jbin['one_sigma']['val'] = max(
abs(i - jbin['median'])
for i in jbin['one_sigma']['range']
)
jbin['two_sigma']['val'] = max(
abs(i - jbin['median'])
for i in jbin['two_sigma']['range']
)
if jbin['median']:
jbin['one_sigma']['relative'] = jbin['one_sigma']['val']/jbin['median']
jbin['two_sigma']['relative'] = jbin['two_sigma']['val']/jbin['median']
else:
jbin['one_sigma']['relative'] = 0
jbin['two_sigma']['relative'] = 0
jret.append(jbin)
return prettyjson.dumps(jret)
def dump(self, fname):
json = {
'events' : self.evts,
'lumimap' : {}
}
for run, lumis in self.run_map.iteritems():
json['lumimap'][str(run)] = self.collapse(lumis)
with open(fname, 'w') as output:
output.write(prettyjson.dumps(json))
def save_card(self, name):
if not self.card:
raise RuntimeError('There is no card to save!')
self.card.normalize_signals()
self.card.save(name, self.outputdir)
self.card = None
binning_file = '%s/%s.binning.json' % (self.outputdir, name)
with open(binning_file, 'w') as json:
json.write(prettyjson.dumps(self.binning))
self.binning = {}
logging.info('binning saved in %s' % binning_file)
def save(self, filename, directory=''):
'save(self, name, directory=' ') saves the datacard and the shape file'
##
# Write datacard file
##
txt_name = os.path.join(directory, '%s.txt' % filename)
with open(txt_name, 'w') as txt:
for cmt in self.comments:
txt.write('## %s \n' % cmt)
separator = '-' * 40 + '\n'
ncategories = len(self.categories)
sample_category = self.categories.values()[0]
has_data = 'data_obs' in sample_category
samples = sample_category.keys()
samples = filter(lambda x: not self.shape_sys_naming.match(x),
samples)
#set_trace()
nsamples = len(samples)
if has_data:
nsamples -= 1
#HEADER
txt.write('imax %i number of categories \n' % ncategories)
txt.write('jmax %i number of samples minus one \n' %
(nsamples - 1))
txt.write('kmax * number of nuisance parameters \n')
#WHERE TO FIND THE SHAPES
txt.write(separator)
txt.write(
'shapes * * %s.root $CHANNEL/$PROCESS $CHANNEL/$PROCESS_$SYSTEMATIC \n'
% filename)
#DATA COUNT IN EACH CATEGORY (FIXME: ASSUMES YOU HAVE DATA)
txt.write(separator)
max_cat_name = max(max(len(i) for i in self.categories), 11) + 4
format = (''.join(['%-', str(max_cat_name), 's'
])) * (ncategories + 1) + '\n'
txt.write(format % tuple(['bin'] + self.categories.keys()))
txt.write(format % tuple(['observation'] + [
'%-7.1f' % i.data_obs.Integral()
for i in self.categories.itervalues()
]))
#SAMPLES TABLE
mcsamples = []
bkg_idx, sig_idx = 1, 0
for sample in samples:
if 'data_obs' == sample:
continue
if any(j.match(sample) for j in self.signals):
mcsamples.append((sample, sig_idx))
sig_idx -= 1
else:
mcsamples.append((sample, bkg_idx))
bkg_idx += 1
mcsamples = dict(mcsamples)
#WRITE RATE FOR EACH SAMPLE/CATEGORY
columns = ['header:%-30s']
bin_line = ['bin']
proc_num_line = ['process']
proc_name_line = ['process']
rate_line = ['rate']
rates = {}
for category, info in self.categories.iteritems():
rates[category] = {}
category_yield = 0
for sample, shape in info.iteritems():
if sample not in mcsamples: continue
width = max(len(category), len(sample), 7) + 4
format = ''.join(['%-', str(width), 's'])
columns.append('%s_%s:%s' % (category, sample, format))
bin_line.append(category)
proc_num_line.append(mcsamples[sample])
proc_name_line.append(sample)
rate = shape.Integral()
#keep the first 6 significant digits
if rate <= 0:
logging.error('Sample %s in category %s has a negative'
' number of expected events! (%f) \n'
'Clamping to zero' %
(sample, category, rate))
shape.Reset()
rate = 0.
#raise ValueError(
# 'Sample %s in category %s has a negative'
# ' number of expected events! (%f)' % (sample, category, rate)
# )
rates[category][sample] = rate
category_yield += rate
mag = max(int(math.log10(abs(rate))),
0) if rate != 0 else 0
float_format = '%.' + str(max(5 - mag, 0)) + 'f'
rate_line.append(float_format % rate)
if rate == 0:
logging.warning(
"Category %s does not have any expected event!" %
category)
#SYSTEMATICS TABLE
sys_table = Table(*columns, show_title=False, show_header=False)
sys_table.add_separator()
sys_table.add_line(*bin_line)
sys_table.add_line(*proc_num_line)
sys_table.add_line(*proc_name_line)
sys_table.add_line(*rate_line)
sys_table.add_separator()
param_sys = []
line = None
for sys_name, syst in self.systematics.iteritems():
if syst.type == 'param':
param_sys.append((sys_name, syst))
continue
line = sys_table.new_line()
line.header = '%s %s' % (sys_name, syst.type)
logging.debug('Adding systematic %s' % sys_name)
for category, info in self.categories.iteritems():
for sample, _ in info.iteritems():
if sample not in mcsamples: continue
if rates[category][sample] < 10.**-5:
line['%s_%s' % (category, sample)] = '-'
else:
line['%s_%s' % (category, sample)] = syst.effect(
category, sample)
if line is not None: del line
sys_table.add_separator()
txt.write('%s\n' % sys_table)
for sys_name, syst in param_sys:
txt.write('%s param %f %f\n' % (sys_name, syst.val, syst.unc))
logging.info('Written file %s' % txt_name)
##
# Write shape file
##
shape_name = os.path.join(directory, '%s.root' % filename)
with io.root_open(shape_name, 'recreate') as out:
for name, cat in self.categories.iteritems():
out.mkdir(name).cd()
for sample, shape in cat.iteritems():
shape.SetName(sample)
shape.SetTitle(sample)
shape.Write()
logging.info('Written file %s' % shape_name)
##
# if we normalized the signal to outsource the yields to a json file
# dump it too
##
if self.yields:
json_name = os.path.join(directory, '%s.json' % filename)
with open(json_name, 'w') as txt:
txt.write(prettyjson.dumps(self.yields))
#! /bin/env python
__doc__ = 'simple script to read a son file and dump part of it into a new json file'
import URAnalysis.Utilities.prettyjson as prettyjson
from argparse import ArgumentParser
parser = ArgumentParser(description=__doc__)
parser.add_argument('input', metavar='input.json', type=str, help='input json')
parser.add_argument('output',
metavar='output.json',
type=str,
help='Json output file name')
parser.add_argument(
'toget',
metavar='this:that',
type=str,
help='column-separated list of things to get, means json[this][that]')
#TODO ' futher syntax may be implemented to support list slicing and regex matching')
args = parser.parse_args()
json = prettyjson.loads(open(args.input).read())
chain = args.toget.split(':')
to_get = json
for i in chain:
to_get = to_get[i]
with open(args.output, 'w') as out:
out.write(prettyjson.dumps(to_get))
elif das_name.startswith('TO BE UPDATED -- '):
das_name = das_name.replace('TO BE UPDATED -- ', '')
_, prim_dset, prod, tier = tuple(das_name.split('/'))
if fnmatch(prod, args.newProd):
print "%s already matches! Skipping..." % sample['name']
continue
query = 'dataset dataset=%s status=%s' % \
('/'.join(['',prim_dset, args.newProd, tier]), 'VALID' if args.valid else '*')
newsamples = das.query(query, True)
print 'Availeble options'
for info in enumerate(newsamples):
print '[%d] %s' % info
print '[%d] None of the above' % len(newsamples)
idx = raw_input('Which should I pick? ')
while isinstance(idx, str):
try:
idx = int(idx)
except:
idx = raw_input('%s is not a number! plase repeat: ' % idx)
if idx == len(newsamples):
print "OK, I'm skipping the sample and putting a 'TO BE UPDATED -- ' before the old sample"
sample['DBSName'] = 'TO BE UPDATED -- %s' % das_name
else:
sample['DBSName'] = str(newsamples[idx])
with open(args.json, 'w') as out:
out.write(prettyjson.dumps(json))
def run_unfolder(itoy = 0, outdir = opts.dir, tau = opts.tau):
styles = {
'scan_overlay' : {
'markerstyle':[0, 29], 'linecolor':[1,1],
'markercolor':[1,2], 'drawstyle':['ALP', 'P'],
'markersize':[0,3]
},
'data_overlay' : {
'linestyle' : [1,0], 'markerstyle':[0,21],
'linecolor' : [2,1], 'markercolor':[2,1],
'drawstyle' : ['hist', 'p'], 'legendstyle' : ['l', 'p']
},
'dots' : {
'markerstyle' : 20, 'markersize' : 2,
'linestyle' : 0, 'drawstyle' : 'P'
},
'line' : {
'linestyle':1, 'markerstyle':0
},
}
plotter = BasePlotter(
outdir, defaults = {
'clone' : False,
'show_title' : True,
}
)
#canvas = plotting.Canvas(name='adsf', title='asdf')
if "toy" in opts.fit_file:
data_file_basedir = 'toy_' + str(itoy)
data_file_dir = data_file_basedir + '/' + opts.var
else:
data_file_dir = opts.var
xaxislabel = set_pretty_label(opts.var)
scale = 1.
if opts.no_area_constraint:
area_constraint='None'
else:
area_constraint='Area'
myunfolding = URUnfolding(regmode = opts.reg_mode, constraint = area_constraint)
## Migration matrix preprocessing
## remove oflow bins
var_dir = getattr(resp_file, opts.var)
migration_matrix = var_dir.migration_matrix
for bin in migration_matrix:
if bin.overflow:
bin.value = 0
bin.error = 0
myunfolding.matrix = migration_matrix
thruth_unscaled = var_dir.thruth_unscaled
reco_unscaled = var_dir.reco_unscaled
project_reco = 'X' if myunfolding.orientation == 'Vertical' else 'Y'
project_gen = 'Y' if myunfolding.orientation == 'Vertical' else 'X'
reco_project = rootpy.asrootpy(
getattr(migration_matrix, 'Projection%s' % project_reco)()
)
gen_project = rootpy.asrootpy(
getattr(migration_matrix, 'Projection%s' % project_gen)()
)
if gen_project.Integral() < thruth_unscaled.Integral():
eff_correction = ROOT.TGraphAsymmErrors(gen_project, thruth_unscaled)
elif gen_project.Integral() == thruth_unscaled.Integral():
eff_correction = None
else:
log.warning(
'Efficiency correction: The visible part of the migration matrix'
' has a larger integral than the full one! (%.3f vs. %.3f).\n'
'It might be a rounding error, but please check!'\
% (reco_project.Integral(), reco_unscaled.Integral())
)
eff_correction = None
if reco_project.Integral() < reco_unscaled.Integral():
purity_correction = ROOT.TGraphAsymmErrors(reco_project, reco_unscaled)
elif reco_project.Integral() == reco_unscaled.Integral():
purity_correction = None
else:
log.warning(
'Purity correction: The visible part of the migration matrix'
' has a larger integral than the full one! (%.3f vs. %.3f).\n'
'It might be a rounding error, but please check!'\
% (reco_project.Integral(), reco_unscaled.Integral())
)
purity_correction = None
#flush graphs into histograms (easier to handle)
eff_hist = gen_project.Clone()
eff_hist.reset()
eff_hist.name = 'eff_hist'
if eff_correction:
for idx in range(eff_correction.GetN()):
eff_hist[idx+1].value = eff_correction.GetY()[idx]
eff_hist[idx+1].error = max(
eff_correction.GetEYhigh()[idx],
eff_correction.GetEYlow()[idx]
)
else:
for b in eff_hist:
b.value = 1.
b.error = 0.
purity_hist = reco_project.Clone()
purity_hist.reset()
purity_hist.name = 'purity_hist'
if purity_correction:
for idx in range(purity_correction.GetN()):
bin.value = purity_correction.GetY()[idx]
bin.error = max(
purity_correction.GetEYhigh()[idx],
purity_correction.GetEYlow()[idx]
)
else:
for bin in purity_hist:
bin.value = 1.
bin.error = 0.
#Get measured histogram
measured = None
if opts.use_reco_truth:
log.warning("Using the MC reco distribution for the unfolding!")
measured = getattr(resp_file, opts.var).reco_distribution
else:
measured = getattr(data_file, data_file_dir).tt_right
measured_no_correction = measured.Clone()
measured_no_correction.name = 'measured_no_correction'
measured.name = 'measured'
measured.multiply(purity_hist)
myunfolding.measured = measured
#get gen-level distribution
gen_distro = getattr(resp_file, opts.var).true_distribution.Clone()
full_true = gen_distro.Clone()
full_true.name = 'complete_true_distro'
gen_distro.multiply(eff_hist)
gen_distro.name = 'true_distribution'
myunfolding.truth = gen_distro
if opts.cov_matrix != 'none':
if 'toy' in opts.fit_file:
input_cov_matrix = make_cov_matrix(
getattr(data_file, data_file_basedir).correlation_matrix,
getattr(data_file, data_file_dir).tt_right
)
input_corr_matrix = make_corr_matrix(
getattr(data_file, data_file_basedir).correlation_matrix,
getattr(data_file, data_file_dir).tt_right
)
else:
input_cov_matrix = make_cov_matrix(
data_file.correlation_matrix,
getattr(data_file, data_file_dir).tt_right
)
input_corr_matrix = make_corr_matrix(
data_file.correlation_matrix,
getattr(data_file, data_file_dir).tt_right
)
input_cov_matrix.name = 'input_cov_matrix'
input_corr_matrix.name = 'input_corr_matrix'
myunfolding.cov_matrix = input_cov_matrix
myunfolding.InitUnfolder()
hdata = myunfolding.measured # Duplicate. Remove!
#plot covariance matrix
plotter.pad.cd()
input_corr_matrix.SetStats(False)
input_corr_matrix.Draw('colz')
plotter.pad.SetLogz(True)
plotter.save('correlation_matrix.png')
#optimize
best_taus = {}
if tau >= 0:
best_taus['External'] = tau
else:
t_min, t_max = eval(opts.tau_range)
best_l, l_curve, graph_x, graph_y = myunfolding.DoScanLcurve(100, t_min, t_max)
best_taus['L_curve'] = best_l
l_curve.SetName('lcurve')
l_curve.name = 'lcurve'
graph_x.name = 'l_scan_x'
graph_y.name = 'l_scan_y'
l_tau = math.log10(best_l)
points = [(graph_x.GetX()[i], graph_x.GetY()[i], graph_y.GetY()[i])
for i in xrange(graph_x.GetN())]
best = [(x,y) for i, x, y in points if l_tau == i]
graph_best = plotting.Graph(1)
graph_best.SetPoint(0, *best[0])
plotter.reset()
plotter.overlay(
[l_curve, graph_best], **styles['scan_overlay']
)
plotter.canvas.name = 'L_curve'
info = plotter.make_text_box('#tau = %.5f' % best_l, 'NE')
#ROOT.TPaveText(0.65,1-canvas.GetTopMargin(),1-canvas.GetRightMargin(),0.999, "brNDC")
info.Draw()
canvas.Update()
plotter.set_subdir('L_curve')
plotter.save()
modes = ['RhoMax', 'RhoSquareAvg', 'RhoAvg']
for mode in modes:
plotter.set_subdir(mode)
best_tau, tau_curve, index_best = myunfolding.DoScanTau(100, t_min, t_max, mode)
best_taus[mode] = best_tau
tau_curve.SetName('%s_scan' % mode)
tau_curve.SetMarkerStyle(1)
points = [(tau_curve.GetX()[i], tau_curve.GetY()[i])
for i in xrange(tau_curve.GetN())]
best = [points[index_best]]
graph_best = plotting.Graph(1)
graph_best.SetPoint(0, *best[0])
plotter.overlay(
[tau_curve, graph_best], **styles['scan_overlay']
)
plotter.canvas.name = 'c'+tau_curve.GetName()
info = plotter.make_text_box('#tau = %.5f' % best_tau, 'NE')
#ROOT.TPaveText(0.65,1-canvas.GetTopMargin(),1-canvas.GetRightMargin(),0.999, "brNDC")
info.Draw()
plotter.save('Tau_curve')
#force running without regularization
best_taus['NoReg'] = 0
for name, best_tau in best_taus.iteritems():
log.info('best tau option for %s: %.3f' % (name, best_tau))
if opts.runHandmade:
#hand-made tau scan
plotter.set_subdir('Handmade')
unc_scan, bias_scan = myunfolding.scan_tau(
200, 10**-6, 50, os.path.join(outdir, 'Handmade', 'scan_info.root'))
bias_scan.name = 'Handmade'
bias_scan.title = 'Avg. Bias - Handmade'
plotter.plot(bias_scan, logx=True, logy=True, **styles['dots'])
plotter.save('bias_scan')
unc_scan.name = 'Handmade'
unc_scan.title = 'Avg. Unc. - Handmade'
plotter.plot(unc_scan, logx=True, logy=True, **styles['dots'])
plotter.save('unc_scan')
bias_points = [(bias_scan.GetX()[i], bias_scan.GetY()[i])
for i in xrange(bias_scan.GetN())]
unc_points = [(unc_scan.GetX()[i], unc_scan.GetY()[i])
for i in xrange(unc_scan.GetN())]
fom_scan = plotting.Graph(unc_scan.GetN())
for idx, info in enumerate(zip(bias_points, unc_points)):
binfo, uinfo = info
tau, bias = binfo
_, unc = uinfo
fom_scan.SetPoint(idx, tau, quad(bias, unc))
fom_scan.name = 'Handmade'
fom_scan.title = 'Figure of merit - Handmade'
plotter.plot(fom_scan, logx=True, logy=True, **styles['dots'])
plotter.save('fom_scan')
to_save = []
outfile = rootpy.io.root_open(os.path.join(outdir, opts.out),'recreate')
for name, best_tau in best_taus.iteritems():
plotter.set_subdir(name)
method_dir = outfile.mkdir(name)
myunfolding.tau = best_tau
hdata_unfolded = myunfolding.unfolded
#apply phase space efficiency corrections
hdata_unfolded_ps_corrected = hdata_unfolded.Clone()
hdata_unfolded_ps_corrected.Divide(eff_hist)
hdata_refolded = myunfolding.refolded
#apply purity corrections
hdata_refolded_wpurity = hdata_refolded.Clone()
error_matrix = myunfolding.ematrix_total
hcorrelations = myunfolding.rhoI_total
hbias = myunfolding.bias
#canvas = overlay(myunfolding.truth, hdata_unfolded)
myunfolding.truth.xaxis.title = xaxislabel
hdata_unfolded.xaxis.title = xaxislabel
n_neg_bins = 0
for ibin in range(1,hdata_unfolded.GetNbinsX()+1):
if hdata_unfolded.GetBinContent(ibin) < 0:
n_neg_bins = n_neg_bins + 1
hn_neg_bins = plotting.Hist(
2,-1, 1, name = 'nneg_bins',
title = 'Negative bins in ' + hdata_unfolded.GetName()+ ';Bin sign; N_{bins}'
)
hn_neg_bins.SetBinContent(1,n_neg_bins)
hn_neg_bins.SetBinContent(2,hdata_unfolded.GetNbinsX()-n_neg_bins)
plotter.plot(
hn_neg_bins, writeTo='unfolding_bins_sign', **styles['line']
)
leg = LegendDefinition(
title=name,
labels=['Truth','Unfolded'],
position='ne'
)
sumofpulls = 0
sumofratios = 0
for ibin in range(1,myunfolding.truth.GetNbinsX()+1):
binContent1 = myunfolding.truth.GetBinContent(ibin)
binContent2 = hdata_unfolded.GetBinContent(ibin)
binError1 = myunfolding.truth.GetBinError(ibin)
binError2 = hdata_unfolded.GetBinError(ibin)
error = sqrt(binError1*binError1 + binError2*binError2)
if error != 0:
pull = (binContent2-binContent1)/error
else:
pull = 9999
if binContent1 != 0:
ratio = binContent2/binContent1
sumofpulls = sumofpulls + pull
sumofratios = sumofratios + ratio
sumofpulls = sumofpulls / myunfolding.truth.GetNbinsX()
sumofratios = sumofratios / myunfolding.truth.GetNbinsX()
hsum_of_pulls = plotting.Hist(
1, 0, 1, name = 'sum_of_pulls_' + hdata_unfolded.GetName(),
title = 'Sum of pulls wrt truth for ' + hdata_unfolded.GetName()+ ';None; #Sigma(pulls) / N_{bins}'
)
hsum_of_pulls[1].value = sumofpulls
plotter.plot(hsum_of_pulls, writeTo='unfolding_sum_of_pulls', **styles['line'])
hsum_of_ratios = plotting.Hist(
1, 0, 1, name = 'sum_of_ratios_' + hdata_unfolded.GetName(),
title = 'Sum of ratios wrt truth for ' + hdata_unfolded.GetName()+ ';None; #Sigma(ratios) / N_{bins}'
)
hsum_of_ratios[1].value = sumofratios
plotter.plot(hsum_of_ratios, writeTo='unfolding_sum_of_ratios', **styles['line'])
plotter.overlay_and_compare(
[myunfolding.truth], hdata_unfolded,
legend_def=leg,
writeTo='unfolding_pull', **styles['data_overlay']
)
plotter.overlay_and_compare(
[myunfolding.truth], hdata_unfolded,
legend_def=leg, method='ratio',
writeTo='unfolding_ratio', **styles['data_overlay']
)
plotter.overlay_and_compare(
[full_true], hdata_unfolded_ps_corrected,
legend_def=leg,
writeTo='unfolding_pull', **styles['data_overlay']
)
plotter.overlay_and_compare(
[full_true], hdata_unfolded_ps_corrected,
legend_def=leg, method='ratio',
writeTo='unfolding_ratio', **styles['data_overlay']
)
nbins = myunfolding.measured.GetNbinsX()
input_distro = getattr(resp_file, opts.var).prefit_distribution
leg = LegendDefinition(title=name, position='ne')
myunfolding.measured.xaxis.title = xaxislabel
hdata_refolded.xaxis.title = xaxislabel
myunfolding.measured.drawstyle = 'e1'
style = {'linestyle':[1, 0], 'markerstyle':[20, 20],
'markercolor':[2,4], 'linecolor':[2,4],
'drawstyle' : ['hist', 'e1'], 'legendstyle' : ['l', 'p'],
'title' : ['Refolded', 'Reco']
}
plotter.overlay_and_compare(
[hdata_refolded], myunfolding.measured,
legend_def=leg,
writeTo='refolded_pull', **style
)
plotter.overlay_and_compare(
[hdata_refolded], myunfolding.measured,
legend_def=leg, method='ratio',
writeTo='refolded_ratio', **style
)
style = {'linestyle':[1,0,0], 'markerstyle':[20,21,21],
'markercolor':[2,4,1], 'linecolor':[2,4,1],
'drawstyle' : ['hist', 'e1', 'e1'], 'legendstyle' : ['l', 'p', 'p'],
'title' : ['Refolded', 'Reco', 'Input']
}
measured_no_correction.drawstyle = 'e1'
plotter.overlay_and_compare(
[hdata_refolded_wpurity, measured_no_correction], input_distro,
legend_def=leg,
writeTo='refolded_wpurity_pull', **style
)
plotter.overlay_and_compare(
[hdata_refolded_wpurity, measured_no_correction], input_distro,
legend_def=leg, method='ratio',
writeTo='refolded_wpurity_ratio', **style
)
method_dir.WriteTObject(hdata_unfolded, 'hdata_unfolded')
method_dir.WriteTObject(hdata_unfolded_ps_corrected, 'hdata_unfolded_ps_corrected')
method_dir.WriteTObject(hdata_refolded, 'hdata_refolded')
method_dir.WriteTObject(hdata_refolded_wpurity, 'hdata_refolded_wpurity')
method_dir.WriteTObject(error_matrix, 'error_matrix')
method_dir.WriteTObject(hbias, 'bias')
method_dir.WriteTObject(hn_neg_bins, 'hn_neg_bins')
method_dir.WriteTObject(hsum_of_pulls, 'hsum_of_pulls')
method_dir.WriteTObject(hsum_of_ratios, 'hsum_of_ratios')
htruth = myunfolding.truth
hmatrix = myunfolding.matrix
hmeasured = myunfolding.measured
#with rootpy.io.root_open(os.path.join(outdir, opts.out),'recreate') as outfile:
outfile.cd()
to_save.extend([
measured_no_correction,
eff_hist,
purity_hist,
full_true,
myunfolding.truth, ## 4
myunfolding.measured, ## 5
myunfolding.matrix,]) ## 6
if opts.tau < 0:
to_save.extend([
l_curve, ## 9
tau_curve, ## 10
graph_x,
graph_y
])
if opts.cov_matrix != 'none':
to_save.extend([input_cov_matrix])
to_save.extend([input_corr_matrix])
for i, j in enumerate(to_save):
log.debug('Saving %s as %s' % (j.name, j.GetName()))
j.Write()
getattr(resp_file, opts.var).reco_distribution.Write()
getattr(resp_file, opts.var).prefit_distribution.Write()
json = ROOT.TText(0., 0., prettyjson.dumps(best_taus))
outfile.WriteTObject(json, 'best_taus')
myunfolding.write_to(outfile, 'urunfolder')
outfile.Close()
parser = ArgumentParser(description=__doc__)
parser.add_argument('output', type=str)
parser.add_argument('inputs', type=str, nargs='+')
args = parser.parse_args()
if len(args.inputs) == 1:
shutil.copy(args.inputs[0], args.output)
else:
nevts = 0
nweighted = 0
sumw = None
partial = args.output.replace('.json', '.part.json')
tmp = args.output.replace('.json', '.tmp.json')
tmp2= args.output.replace('.json', '.tmp2.json')
with open(partial, 'w') as p:
p.write(prettyjson.dumps({}))
for jin in args.inputs:
jmap = prettyjson.loads(open(jin).read())
nevts += jmap['events']
nweighted += jmap['weightedEvents']
if 'sum_weights' in jmap:
if sumw is None:
sumw = [i for i in jmap['sum_weights']]:
else:
if len(jmap['sum_weights']) and len(sumw):
raise ValueError(
'I got a vector of size %d and'
' I was expecting it %d long' % (len(sumw), len(jmap['sum_weights'])))
for i in range(sumw):
sumw[i] += jmap['sum_weights']
def save(self,
filename,
png=True,
pdf=True,
dotc=False,
dotroot=False,
json=False,
verbose=False):
''' Save the current canvas contents to [filename] '''
self.pad.Draw()
self.canvas.Update()
if not os.path.exists(self.outputdir):
os.makedirs(self.outputdir)
if verbose:
print 'saving ' + os.path.join(self.outputdir, filename) + '.png'
if png:
self.canvas.SaveAs(os.path.join(self.outputdir, filename) + '.png')
if pdf:
self.canvas.SaveAs(os.path.join(self.outputdir, filename) + '.pdf')
if dotc:
self.canvas.SaveAs(os.path.join(self.outputdir, filename) + '.C')
if json:
jdict = {}
for obj in self.keep:
if isinstance(obj, ROOT.TH1):
jdict[obj.GetTitle()] = [
obj.GetBinContent(1),
obj.GetBinError(1)
]
if isinstance(obj, ROOT.THStack):
jdict['hist_stack'] = {}
for i in obj.GetHists():
jdict['hist_stack'][i.GetTitle()] = [
i.GetBinContent(1),
i.GetBinError(1)
]
with open(os.path.join(self.outputdir, filename) + '.json',
'w') as jout:
jout.write(prettyjson.dumps(jdict))
if dotroot:
outfile = ROOT.TFile.Open(
os.path.join(self.outputdir, filename) + '.root', 'recreate')
outfile.cd()
self.canvas.Write()
for obj in self.keep:
obj.Write()
#self.keep = []
self.reset()
outfile.Close()
#self.canvas = plotting.Canvas(name='adsf', title='asdf')
#self.canvas.cd()
#self.pad = plotting.Pad(0., 0., 1., 1.) #ful-size pad
#self.pad.cd()
if self.keep and self.lower_pad:
#pass
self.reset()
else:
# Reset keeps
self.keep = []
# Reset logx/y
self.canvas.SetLogx(False)
self.canvas.SetLogy(False)
def run_module(**kwargs):
args = Struct(**kwargs)
if not args.name:
args.name = args.var
results = [prettyjson.loads(open(i).read())[-1] for i in args.results]
#set_trace()
results.sort(key=lambda x: x['median'])
nevts_graph = plotting.Graph(len(results))
upbound_graph = plotting.Graph(len(results))
max_unc = 0.
bound_range = args.vrange #results[-1]['up_edge'] - results[0]['up_edge']
step = results[1]['up_edge'] - results[0]['up_edge']
#bound_range += step
bound_min = results[0]['up_edge'] - step
for idx, info in enumerate(results):
nevts_graph.SetPoint(idx, info['median'],
info["one_sigma"]["relative"])
upbound_graph.SetPoint(idx, info['up_edge'],
info["one_sigma"]["relative"])
if info["one_sigma"]["relative"] > max_unc:
max_unc = info["one_sigma"]["relative"]
canvas = plotting.Canvas()
nevts_graph.Draw('APL')
nevts_graph.GetXaxis().SetTitle('average number of events')
nevts_graph.GetYaxis().SetTitle('relative fit uncertainty')
canvas.SaveAs(os.path.join(args.outdir, 'nevts_%s.png' % args.name))
tf1 = Plotter.parse_formula(
'scale / (x - shift) + offset',
'scale[1,0,10000],shift[%.2f,%.2f,%.2f],offset[0, 0, 1]' %
(bound_min, bound_min - 2 * step, bound_min + step))
# ROOT.TF1('ret', '[0]/(x - [1])', -3, 1000)
tf1.SetRange(0, 1000)
tf1.SetLineColor(ROOT.EColor.kAzure)
tf1.SetLineWidth(3)
result = upbound_graph.Fit(tf1, 'MES') #WL
scale = tf1.GetParameter('scale')
shift = tf1.GetParameter('shift')
offset = tf1.GetParameter('offset')
upbound_graph.Draw('APL')
upbound_graph.GetXaxis().SetTitle('upper bin edge')
upbound_graph.GetYaxis().SetTitle('relative fit uncertainty')
if args.fullrange:
upbound_graph.GetYaxis().SetRangeUser(offset, max_unc * 1.2)
upbound_graph.GetXaxis().SetRangeUser(shift, (shift + bound_range) * 1.2)
delta = lambda x, y: ((x - shift) / bound_range)**2 + ((y - offset) /
(max_unc - offset))
points = ((bound_min + step) + i * (bound_range / 100.)
for i in xrange(100))
math_best_x = min(points, key=lambda x: delta(x, tf1.Eval(x)))
math_best_y = tf1.Eval(math_best_x)
## math_best_x = math.sqrt(scale*bound_range*(max_unc-offset))+shift
## math_best_y = tf1.Eval(math_best_x) #max_unc*math.sqrt(scale)+offset
best = min(results, key=lambda x: abs(x['up_edge'] - math_best_x))
upbound_best = plotting.Graph(1)
upbound_best.SetPoint(0, best['up_edge'], best["one_sigma"]["relative"])
upbound_best.markerstyle = 29
upbound_best.markersize = 3
upbound_best.markercolor = 2
upbound_best.Draw('P same')
print math_best_x, math_best_y
print best['up_edge'], best["one_sigma"]["relative"]
math_best = plotting.Graph(1)
math_best.SetPoint(0, math_best_x, math_best_y)
math_best.markerstyle = 29
math_best.markersize = 3
math_best.markercolor = ROOT.EColor.kAzure
math_best.Draw('P same')
canvas.SaveAs(os.path.join(args.outdir, 'upbound_%s.png' % args.name))
json = {'best': best['up_edge'], 'unc': best["one_sigma"]["relative"]}
with open(os.path.join(args.outdir, '%s.json' % args.name), 'w') as jfile:
jfile.write(prettyjson.dumps(json))
title='%s efficiencies' % qtype)
effs[qtype] = {}
for wpoint, jmap in jmaps.iteritems():
line = table.new_line()
line.WP = wpoint
isThere = ("lead_%sEff" % qtype) in wpoints[wpoint]
line.clead = 100 * wpoints[wpoint]["lead_%sEff" %
qtype] if isThere else 0.
line.csub = 100 * wpoints[wpoint]["sub_%sEff" %
qtype] if isThere else 0.
leff = compute_eff(jmap, 'leading', qtype)
seff = compute_eff(jmap, 'subleading', qtype)
teff = (leff + seff) / 2.
line.lead = leff * 100
line.sub = seff * 100
line.avg = teff * 100
line.diff = 100 * (leff - seff) / teff
effs[qtype][wpoint] = {
'leading': leff,
'subleading': seff,
'average': teff
}
del line
print '\n\n'
print table
with open('plots/%s/btageff/mc_effs.json' % jobid, 'w') as out:
out.write(prettyjson.dumps(effs))
vals.append(
(tdir, plotter.get_yields(50))
)
plotter.save(var)
if 'discriminant'in var:
plotter.mc_samples = plotter.generic_mcs
jmap = {}
for tdir, sams in vals:
for sam, lo, hi in sams:
if sam not in jmap:
jmap[sam] = {}
jmap[sam]['%s/%s' % (tdir, 'hi')] = hi
jmap[sam]['%s/%s' % (tdir, 'lo')] = lo
with open('yields.json', 'w') as out:
out.write(prettyjson.dumps(jmap))
if args.shapes or args.all:
for peak, dname in [('*', 'shapes'), ('Peak', 'shapes_peak'), ('Int', 'shapes_interference')]:
plotter.set_subdir(dname)
for mass in [400, 500, 600, 750]:
histos = []
for width, color in zip([5, 10, 25, 50], ['#f9a505', '#2aa198', '#0055ff', '#6666b3']):
htt_view = plotter.get_view('HtoTT_M%d_%dpc_%s' % (mass, width, peak))
histos.append(
sum(
htt_view.Get('%s/nosys/tight/MTHigh/m_tt' % i) \
for i in ['right', 'matchable', 'unmatchable', 'noslep']
)
)
histos[-1].Rebin(2)