def clf_channels(self, clf,
category, region,
cuts=None,
bins=10,
limits=None,
mass=None,
mode=None,
systematics=True,
unblind=False,
hybrid_data=False,
no_signal_fixes=False,
uniform=False,
mva=False,
min_score=None,
max_score=None,
include_signal=True):
"""
Return a HistFactory Channel for each mass hypothesis
"""
log.info("constructing channels")
# determine min and max scores
scores_obj = self.get_scores(
clf, category, region, cuts=cuts,
masses=[mass], mode=mode,
systematics=systematics,
unblind=unblind)
data_scores = scores_obj.data_scores
bkg_scores = scores_obj.bkg_scores
all_sig_scores = scores_obj.all_sig_scores
if min_score is None:
min_score = scores_obj.min_score
if max_score is None:
max_score = scores_obj.max_score
if isinstance(bins, int):
if limits is not None:
low, high = limits
binning = Hist(bins, low, high, type='D')
else:
binning = Hist(bins, min_score, max_score, type='D')
else: # iterable
if bins[0] > min_score:
log.warning("min score is less than first edge "
"(will be underflow)")
if bins[-1] <= max_score:
log.warning("max score is greater than or equal to last edge "
"(will be overflow)")
binning = Hist(bins, type='D')
bkg_samples = []
for s, scores in bkg_scores:
hist_template = binning.Clone(
title=s.label,
**s.hist_decor)
sample = s.get_histfactory_sample(
hist_template, clf,
category, region,
min_score=min_score, max_score=max_score ,
cuts=cuts, scores=scores,
systematics=systematics,
uniform=uniform,
mva=mva)
bkg_samples.append(sample)
data_sample = None
if data_scores is not None:
hist_template = binning.Clone(
title=self.data.label,
**self.data.hist_decor)
data_sample = self.data.get_histfactory_sample(
hist_template, clf,
category, region,
cuts=cuts, scores=data_scores,
uniform=uniform)
if unblind is False:
# blind full histogram
data_sample.hist[:] = (0, 0)
elif (unblind is not True) and isinstance(unblind, int):
# blind highest N bins
data_sample.hist[-(unblind + 1):] = (0, 0)
elif isinstance(unblind, float):
# blind above a signal efficiency
max_unblind_score = efficiency_cut(
sum([histogram_scores(hist_template, scores)
for s, scores in all_sig_scores[mass]]), unblind)
blind_bin = hist_template.FindBin(max_unblind_score)
data_sample.hist[blind_bin:] = (0, 0)
# create signal HistFactory samples
sig_samples = []
if include_signal:
for s, scores in all_sig_scores[mass]:
hist_template = binning.Clone(
title=s.label,
**s.hist_decor)
sample = s.get_histfactory_sample(
hist_template, clf,
category, region,
cuts=cuts, scores=scores,
no_signal_fixes=no_signal_fixes,
systematics=systematics,
uniform=uniform,
mva=mva)
sig_samples.append(sample)
# replace data in blind bins with signal + background
if hybrid_data and (unblind is not True):
sum_sig_bkg = sum([s.hist for s in (bkg_samples + sig_samples)])
if unblind is False:
# replace full hist
data_sample.hist[:] = sum_sig_bkg[:]
elif isinstance(unblind, int):
# replace highest N bins
bin = -(unblind + 1)
data_sample.hist[bin:] = sum_sig_bkg[bin:]
elif isinstance(unblind, float):
data_sample.hist[blind_bin:] = sum_sig_bkg[blind_bin:]
# create channel for this mass point
channel = histfactory.make_channel(
'hh_{0}_{1}_{2}'.format(self.year % 1000, category.name, mass),
bkg_samples + sig_samples,
data=data_sample)
return scores_obj, channel
def plot_clf(
background_scores,
category,
signal_scores=None,
signal_scale=1.0,
data_scores=None,
name=None,
draw_histograms=True,
draw_data=False,
save_histograms=False,
hist_template=None,
bins=10,
min_score=0,
max_score=1,
signal_colors=cm.spring,
systematics=None,
unblind=False,
**kwargs
):
if hist_template is None:
if hasattr(bins, "__iter__"):
# variable width bins
hist_template = Hist(bins)
min_score = min(bins)
max_score = max(bins)
else:
hist_template = Hist(bins, min_score, max_score)
bkg_hists = []
for bkg, scores_dict in background_scores:
hist = hist_template.Clone(title=bkg.label)
scores, weight = scores_dict["NOMINAL"]
fill_hist(hist, scores, weight)
hist.decorate(**bkg.hist_decor)
hist.systematics = {}
for sys_term in scores_dict.keys():
if sys_term == "NOMINAL":
continue
sys_hist = hist_template.Clone()
scores, weight = scores_dict[sys_term]
fill_hist(sys_hist, scores, weight)
hist.systematics[sys_term] = sys_hist
bkg_hists.append(hist)
if signal_scores is not None:
sig_hists = []
for sig, scores_dict in signal_scores:
sig_hist = hist_template.Clone(title=sig.label)
scores, weight = scores_dict["NOMINAL"]
fill_hist(sig_hist, scores, weight)
sig_hist.decorate(**sig.hist_decor)
sig_hist.systematics = {}
for sys_term in scores_dict.keys():
if sys_term == "NOMINAL":
continue
sys_hist = hist_template.Clone()
scores, weight = scores_dict[sys_term]
fill_hist(sys_hist, scores, weight)
sig_hist.systematics[sys_term] = sys_hist
sig_hists.append(sig_hist)
else:
sig_hists = None
if data_scores is not None and draw_data and unblind is not False:
data, data_scores = data_scores
if isinstance(unblind, float):
if sig_hists is not None:
# unblind up to `unblind` % signal efficiency
sum_sig = sum(sig_hists)
cut = efficiency_cut(sum_sig, 0.3)
data_scores = data_scores[data_scores < cut]
data_hist = hist_template.Clone(title=data.label)
data_hist.decorate(**data.hist_decor)
fill_hist(data_hist, data_scores)
if unblind >= 1 or unblind is True:
log.info("Data events: %d" % sum(data_hist))
log.info("Model events: %f" % sum(sum(bkg_hists)))
for hist in bkg_hists:
log.info("{0} {1}".format(hist.GetTitle(), sum(hist)))
log.info("Data / Model: %f" % (sum(data_hist) / sum(sum(bkg_hists))))
else:
data_hist = None
if draw_histograms:
output_name = "event_bdt_score"
if name is not None:
output_name += "_" + name
for logy in (False, True):
draw(
data=data_hist,
model=bkg_hists,
signal=sig_hists,
signal_scale=signal_scale,
category=category,
name="BDT Score",
output_name=output_name,
show_ratio=data_hist is not None,
model_colors=None,
signal_colors=signal_colors,
systematics=systematics,
logy=logy,
**kwargs
)
return bkg_hists, sig_hists, data_hist
def clf_channels(self, clf,
category, region,
cuts=None,
bins=10,
limits=None,
mass=None,
mode=None,
systematics=True,
unblind=False,
hybrid_data=False,
no_signal_fixes=False,
uniform=False,
mva=False):
"""
Return a HistFactory Channel for each mass hypothesis
"""
log.info("constructing channels")
# determine min and max scores
scores_obj = self.get_scores(
clf, category, region, cuts=cuts,
masses=[mass], mode=mode,
systematics=systematics,
unblind=unblind)
data_scores = scores_obj.data_scores
bkg_scores = scores_obj.bkg_scores
all_sig_scores = scores_obj.all_sig_scores
min_score = scores_obj.min_score
max_score = scores_obj.max_score
if isinstance(bins, int):
if limits is not None:
low, high = limits
binning = Hist(bins, low, high, type='D')
else:
binning = Hist(bins, min_score, max_score, type='D')
else: # iterable
if bins[0] > min_score:
log.warning("min score is less than first edge "
"(will be underflow)")
if bins[-1] <= max_score:
log.warning("max score is greater than or equal to last edge "
"(will be overflow)")
binning = Hist(bins, type='D')
bkg_samples = []
for s, scores in bkg_scores:
hist_template = binning.Clone(
title=s.label,
**s.hist_decor)
sample = s.get_histfactory_sample(
hist_template, clf,
category, region,
cuts=cuts, scores=scores,
systematics=systematics,
uniform=uniform,
mva=mva)
bkg_samples.append(sample)
data_sample = None
if data_scores is not None:
hist_template = binning.Clone(
title=self.data.label,
**self.data.hist_decor)
data_sample = self.data.get_histfactory_sample(
hist_template, clf,
category, region,
cuts=cuts, scores=data_scores,
uniform=uniform)
if unblind is False:
# blind full histogram
data_sample.hist[:] = (0, 0)
elif (unblind is not True) and isinstance(unblind, int):
# blind highest N bins
data_sample.hist[-(unblind + 1):] = (0, 0)
elif isinstance(unblind, float):
# blind above a signal efficiency
max_unblind_score = efficiency_cut(
sum([histogram_scores(hist_template, scores)
for s, scores in all_sig_scores[mass]]), unblind)
blind_bin = hist_template.FindBin(max_unblind_score)
data_sample.hist[blind_bin:] = (0, 0)
# create signal HistFactory samples
sig_samples = []
for s, scores in all_sig_scores[mass]:
hist_template = binning.Clone(
title=s.label,
**s.hist_decor)
sample = s.get_histfactory_sample(
hist_template, clf,
category, region,
cuts=cuts, scores=scores,
no_signal_fixes=no_signal_fixes,
systematics=systematics,
uniform=uniform,
mva=mva)
sig_samples.append(sample)
# replace data in blind bins with signal + background
if hybrid_data and (unblind is not True):
sum_sig_bkg = sum([s.hist for s in (bkg_samples + sig_samples)])
if unblind is False:
# replace full hist
data_sample.hist[:] = sum_sig_bkg[:]
elif isinstance(unblind, int):
# replace highest N bins
bin = -(unblind + 1)
data_sample.hist[bin:] = sum_sig_bkg[bin:]
elif isinstance(unblind, float):
data_sample.hist[blind_bin:] = sum_sig_bkg[blind_bin:]
# create channel for this mass point
channel = histfactory.make_channel(
'hh_{0}_{1}_{2}'.format(self.year % 1000, category.name, mass),
bkg_samples + sig_samples,
data=data_sample)
return scores_obj, channel
def plot_clf(background_scores,
category,
signal_scores=None,
signal_scale=1.,
data_scores=None,
name=None,
draw_histograms=True,
draw_data=False,
save_histograms=False,
hist_template=None,
bins=10,
min_score=0,
max_score=1,
signal_colors=cm.spring,
systematics=None,
unblind=False,
**kwargs):
if hist_template is None:
if hasattr(bins, '__iter__'):
# variable width bins
hist_template = Hist(bins)
min_score = min(bins)
max_score = max(bins)
else:
hist_template = Hist(bins, min_score, max_score)
bkg_hists = []
for bkg, scores_dict in background_scores:
hist = hist_template.Clone(title=bkg.label)
scores, weight = scores_dict['NOMINAL']
fill_hist(hist, scores, weight)
hist.decorate(**bkg.hist_decor)
hist.systematics = {}
for sys_term in scores_dict.keys():
if sys_term == 'NOMINAL':
continue
sys_hist = hist_template.Clone()
scores, weight = scores_dict[sys_term]
fill_hist(sys_hist, scores, weight)
hist.systematics[sys_term] = sys_hist
bkg_hists.append(hist)
if signal_scores is not None:
sig_hists = []
for sig, scores_dict in signal_scores:
sig_hist = hist_template.Clone(title=sig.label)
scores, weight = scores_dict['NOMINAL']
fill_hist(sig_hist, scores, weight)
sig_hist.decorate(**sig.hist_decor)
sig_hist.systematics = {}
for sys_term in scores_dict.keys():
if sys_term == 'NOMINAL':
continue
sys_hist = hist_template.Clone()
scores, weight = scores_dict[sys_term]
fill_hist(sys_hist, scores, weight)
sig_hist.systematics[sys_term] = sys_hist
sig_hists.append(sig_hist)
else:
sig_hists = None
if data_scores is not None and draw_data and unblind is not False:
data, data_scores = data_scores
if isinstance(unblind, float):
if sig_hists is not None:
# unblind up to `unblind` % signal efficiency
sum_sig = sum(sig_hists)
cut = efficiency_cut(sum_sig, 0.3)
data_scores = data_scores[data_scores < cut]
data_hist = hist_template.Clone(title=data.label)
data_hist.decorate(**data.hist_decor)
fill_hist(data_hist, data_scores)
if unblind >= 1 or unblind is True:
log.info("Data events: %d" % sum(data_hist))
log.info("Model events: %f" % sum(sum(bkg_hists)))
for hist in bkg_hists:
log.info("{0} {1}".format(hist.GetTitle(), sum(hist)))
log.info("Data / Model: %f" %
(sum(data_hist) / sum(sum(bkg_hists))))
else:
data_hist = None
if draw_histograms:
output_name = 'event_bdt_score'
if name is not None:
output_name += '_' + name
for logy in (False, True):
draw(data=data_hist,
model=bkg_hists,
signal=sig_hists,
signal_scale=signal_scale,
category=category,
name="BDT Score",
output_name=output_name,
show_ratio=data_hist is not None,
model_colors=None,
signal_colors=signal_colors,
systematics=systematics,
logy=logy,
**kwargs)
return bkg_hists, sig_hists, data_hist
