def __init__(self, outputdir='./', defaults={}, styles={}):
''' Initialize the BasePlotter
outputdir is where histograms will be saved.
defaults provides basic configuration of the plotter. Most of the options
can be anyway overridden by the specific command in case one exception
to the general rule is needed. Available defaults:
- clone : (bool, default True) chooses the clone policy. If true histograms
will be cloned before being styled and drawn
- show_title : (bool, default False) shows the histogram title in the canvas
- name_canvas: (bool, default False) name the canvas after the histogram.name it is drawn inside
- save: (dict, default {'png' : True, 'pdf' : True, 'dotc' : False,
'dotroot' : False, 'json' : False} set the formats to which save the canvas
styles provides the plotter a look-up table of styles to be applied to the histograms in
the form key : style. Key is a POSIX regular expression that is matched to the
histogram title.
'''
self.outputdir = outputdir
self.base_out_dir = outputdir
self.canvas = plotting.Canvas(800, 800, name='adsf', title='asdf')
self.set_canvas_style(self.canvas)
self.canvas.cd()
self.pad = plotting.Pad(0., 0., 1., 1.) #ful-size pad
self.pad.Draw()
self.set_canvas_style(self.pad)
self.pad.cd()
self.lower_pad = None
self.keep = []
self.defaults = defaults
self.styles = styles
self.label_factor = None
BasePlotter.set_canvas_style(self.canvas)
self.set_style()
def dual_pad_format(self):
if self.lower_pad is None:
self.canvas.cd()
self.canvas.SetCanvasSize(self.canvas.GetWw(),
int(self.canvas.GetWh() * 1.3))
self.set_canvas_style(self.canvas)
self.pad.SetPad(0, 0.33, 1., 1.)
self.set_canvas_style(self.pad)
self.pad.SetBottomMargin(0.001)
self.pad.Draw()
self.canvas.cd()
#create lower pad
self.lower_pad = plotting.Pad(0, 0., 1., 0.33)
self.set_canvas_style(self.lower_pad)
self.lower_pad.Draw()
self.lower_pad.cd()
self.pad.cd()
self.lower_pad.SetTopMargin(0.005)
self.lower_pad.SetGridy(True)
self.lower_pad.SetBottomMargin(self.lower_pad.GetBottomMargin() *
3)
labelSizeFactor1 = (self.pad.GetHNDC() +
self.lower_pad.GetHNDC()) / self.pad.GetHNDC()
labelSizeFactor2 = (self.pad.GetHNDC() + self.lower_pad.GetHNDC()
) / self.lower_pad.GetHNDC()
mm = min(labelSizeFactor1, labelSizeFactor2)
return labelSizeFactor1 / mm, labelSizeFactor2 / mm
def reset(self):
'''hard graphic reset'''
del self.canvas
del self.pad
del self.lower_pad
self.keep = []
self.canvas = plotting.Canvas(name='adsf', title='asdf')
self.canvas.cd()
self.pad = plotting.Pad('up', 'up', 0., 0., 1., 1.) #ful-size pad
self.pad.Draw()
self.pad.cd()
self.lower_pad = None
def reset(self):
'''hard graphic reset'''
del self.canvas
del self.pad
del self.lower_pad
self.keep = []
self.canvas = plotting.Canvas(800, 800, name='adsf', title='asdf')
BasePlotter.set_canvas_style(self.canvas)
self.canvas.cd()
self.pad = plotting.Pad(0., 0., 1., 1.) #ful-size pad
self.pad.Draw()
BasePlotter.set_canvas_style(self.pad)
self.pad.cd()
self.lower_pad = None
self.label_factor = None
def __init__(self,
files,
lumifiles,
outputdir,
blinder=None,
forceLumi=-1):
''' Initialize the Plotter object
Files should be a list of SAMPLE_NAME.root files.
Lumifiles should contain floats giving the effective luminosity of
each of the files.
If [blinder] is not None, it will be applied to the data view.
'''
self.outputdir = outputdir
self.views = data_views(files, lumifiles, forceLumi)
self.canvas = plotting.Canvas(name='adsf', title='asdf')
self.canvas.cd()
self.pad = plotting.Pad('up', 'up', 0., 0., 1., 1.) #ful-size pad
self.pad.Draw()
self.pad.cd()
self.lower_pad = None
if blinder:
# Keep the unblinded data around if desired.
self.views['data']['unblinded_view'] = self.views['data']['view']
# Apply a blinding function
self.views['data']['view'] = blinder(self.views['data']['view'])
self.data = self.views['data']['view']
self.keep = []
# List of MC sample names to use. Can be overridden.
self.mc_samples = [
'Zjets_M50',
'WplusJets_madgraph',
'TTplusJets_madgraph',
'WZ*',
'ZZ*',
'WW*',
]
file_to_map = filter(lambda x: x.startswith('data_'),
self.views.keys())[0]
if not file_to_map: #no data here!
file_to_map = self.views.keys()[0]
#from pdb import set_trace; set_trace()
self.file_dir_structure = Plotter.map_dir_structure(
self.views[file_to_map]['file'])
def add_ratio_plot(self,
data_hist,
mc_stack,
x_range=None,
ratio_range=0.2):
#resize the canvas and the pad to fit the second pad
self.canvas.SetCanvasSize(self.canvas.GetWw(),
int(self.canvas.GetWh() * 1.3))
self.canvas.cd()
self.pad.SetPad(0, 0.33, 1., 1.)
self.pad.Draw()
self.canvas.cd()
#create lower pad
self.lower_pad = plotting.Pad('low', 'low', 0, 0., 1., 0.33)
self.lower_pad.Draw()
self.lower_pad.cd()
mc_hist = None
if isinstance(mc_stack, plotting.HistStack):
mc_hist = sum(mc_stack.GetHists())
else:
mc_hist = mc_stack
data_clone = data_hist.Clone()
data_clone.Divide(mc_hist)
if not x_range:
nbins = data_clone.GetNbinsX()
x_range = (data_clone.GetBinLowEdge(1),
data_clone.GetBinLowEdge(nbins) +
data_clone.GetBinWidth(nbins))
else:
data_clone.GetXaxis().SetRangeUser(*x_range)
ref_function = ROOT.TF1('f', "1.", *x_range)
ref_function.SetLineWidth(3)
ref_function.SetLineStyle(2)
data_clone.Draw('ep')
if ratio_range:
data_clone.GetYaxis().SetRangeUser(1 - ratio_range,
1 + ratio_range)
ref_function.Draw('same')
self.keep.append(data_clone)
self.keep.append(ref_function)
self.pad.cd()
return data_clone
def add_ratio_plot(self,
data_hist,
mc_distribution,
x_range=None,
ratio_range=0.2,
quote_errors=False):
'''Adds a ratio plot under the main pad, with same x range'''
mc_hist = mc_distribution
if isinstance(mc_hist, HistStack):
mc_hist = sum(mc_hist.GetHists())
quote_errors = False
#resize the canvas and the pad to fit the second pad
self.canvas.SetCanvasSize(self.canvas.GetWw(),
int(self.canvas.GetWh() * 1.3))
self.canvas.cd()
self.pad.SetPad(0, 0.33, 1., 1.)
self.pad.Draw()
self.canvas.cd()
#create lower pad
self.lower_pad = plotting.Pad('low', 'low', 0, 0., 1., 0.33)
self.lower_pad.Draw()
self.lower_pad.cd()
nbins = data_hist.GetNbinsX()
#make ratio, but use only data errors
data_clone = data_hist.Clone()
for ibin in range(1, nbins + 1):
d_cont = data_clone.GetBinContent(ibin)
d_err = data_clone.GetBinError(ibin)
m_cont = mc_hist.GetBinContent(ibin)
d_cont = (d_cont - m_cont) / m_cont if m_cont else -10.
d_err = d_err / m_cont if m_cont else 0.
data_clone.SetBinContent(ibin, d_cont)
data_clone.SetBinError(ibin, d_err)
data_clone.Draw('ep')
self.keep.append(data_clone)
if ratio_range:
data_clone.GetYaxis().SetRangeUser(-ratio_range, ratio_range)
#reference line
if not x_range:
nbins = data_clone.GetNbinsX()
x_range = (data_clone.GetBinLowEdge(1),
data_clone.GetBinLowEdge(nbins) +
data_clone.GetBinWidth(nbins))
else:
data_clone.GetXaxis().SetRangeUser(*x_range)
ref_function = ROOT.TF1('f', "0.", *x_range)
ref_function.SetLineWidth(3)
ref_function.SetLineStyle(2)
ref_function.Draw('same')
self.keep.append(ref_function)
if quote_errors:
err_histo = mc_hist.Clone()
err_histo.SetMarkerStyle(0)
err_histo.SetLineColor(1)
err_histo.SetFillColor(1)
for ibin in range(1, nbins + 1):
cont = err_histo.GetBinContent(ibin)
err = err_histo.GetBinError(ibin)
err = err / cont if cont else 0.
err_histo.SetBinContent(ibin, 0)
err_histo.SetBinError(ibin, err)
err_histo.Draw('pe2 same') #was pe
self.keep.append(err_histo)
self.pad.cd()
return data_clone
def run_module(**kwargs):
args = Struct(**kwargs)
mkdir(args.out)
canvas = plotting.Canvas()
pars_regex = None
if args.pars_regex:
pars_regex = re.compile(args.pars_regex)
sample_regex = None
if args.sample_regex:
sample_regex = re.compile(args.sample_regex)
pars_out_regex = None
if args.pars_out_regex:
pars_out_regex = re.compile(args.pars_out_regex)
sample_out_regex = None
if args.sample_out_regex:
sample_out_regex = re.compile(args.sample_out_regex)
output_file = io.root_open('%s/output.root' % args.out, 'recreate')
fpars_tdir = output_file.mkdir('floating_pars')
pulls_tdir = output_file.mkdir('postfit_pulls')
failed_fits = set()
fit_statuses = plotting.Hist(10, -1.5, 8.5)
with io.root_open(args.mlfit) as mlfit:
failed_results = []
passes_results = []
pars = {}
yields = {}
first = True
toys = [i.GetName() for i in mlfit.keys() if i.GetName().startswith('toy_')] if not args.oneshot else [None]
log.info('examining %i toys' % len(toys))
prefit_nuis = None
if args.useprefit:
prefit_nuis = ArgSet(mlfit.nuisances_prefit)
nfailed = 0
for toy in toys:
toy_dir = mlfit.Get(toy) if not args.oneshot else mlfit
keys = set([i.GetName() for i in toy_dir.GetListOfKeys()])
if 'norm_fit_s' not in keys or 'fit_s' not in keys:
log.error('Fit %s failed to produce output!' % toy)
failed_fits.add(toy)
continue
norms = ArgSet(
toy_dir.Get(
'norm_fit_s'
)
)
norms = [i for i in norms]
fit_result = toy_dir.Get(
'fit_s'
)
fit_pars = ArgList(fit_result.floatParsFinal())
if first:
first = False
for i in fit_pars:
if pars_regex and not pars_regex.match(i.GetName()): continue
if pars_out_regex and pars_out_regex.match(i.GetName()): continue
pars[i.GetName()] = []
for i in norms:
if sample_regex and not sample_regex.match(i.GetName()): continue
if sample_out_regex and sample_out_regex.match(i.GetName()): continue
yields[i.GetName()] = []
fit_statuses.Fill(fit_result.status())
fit_failed = any(i.getError() == 0 for i in fit_pars) or fit_result.status() != 0
if fit_failed:
log.error('Fit %s failed to converge properly. It has status %i!' % (toy, fit_result.status()))
nfailed+=1
failed_fits.add(toy)
failed_results.append(fit_result)
continue
passes_results.append(fit_result)
for i in norms:
if i.GetName() in yields:
yields[i.GetName()].append(i)
for i in fit_pars:
if i.GetName() in pars:
pars[i.GetName()].append(i)
if nfailed:
log.error('There were %i fit failed!' % nfailed)
with open('%s/info.txt' % args.out, 'w') as info:
info.write('There were %i fit failed!\n' % nfailed)
fit_statuses.Draw()
canvas.SaveAs('%s/fit_status.png' % args.out)
if not args.nopars:
#Plots the post-fit distribution of the POI and nuisances
out = os.path.join(args.out, 'floating_parameters')
mkdir(out)
for i, j in yields.iteritems():
make_hist(i, j, out, prefix='yield_')
for i, j in pars.iteritems():
make_hist(i, j, out, prefix='par_')
if not args.postpulls:
#Plots the post-fit pulls (nuisance(post) - nuisance(pre))/unc(post)
pulls_dir = os.path.join(args.out, 'postfit_pulls')
mkdir(pulls_dir)
ROOT.gStyle.SetOptFit(11111)
singlenames=set()
for name,value in pars.iteritems():
if pars_regex and not pars_regex.match(name): continue
if pars_out_regex and pars_out_regex.match(i): continue
singlenames.add(get_key(name))
pulls_mean_summary={}
pulls_sigma_summary={}
deltas_mean_summary={}
deltas_sigma_summary={}
for name in singlenames:
nbins = 0
for fullname in pars:
if name in fullname:
nbins = nbins + 1
#print name, nbins
try:
hist = plotting.Hist(nbins, 0.5,nbins+0.5, name = "%s_pull_mean_summary" %name)
pulls_mean_summary[name] = hist
hist = plotting.Hist(nbins, 0.5,nbins+0.5, name = "%s_pull_sigma_summary" %name)
pulls_sigma_summary[name] = hist
hist = plotting.Hist(nbins, 0.5,nbins+0.5, name = "%s_delta_mean_summary" %name)
deltas_mean_summary[name] = hist
hist = plotting.Hist(nbins, 0.5,nbins+0.5, name = "%s_delta_sigma_summary" %name)
deltas_sigma_summary[name] = hist
except:
set_trace()
pulls_mean_summary[ 'all'] = plotting.Hist(len(pars), 0.5, len(pars)+0.5, name = "all_pull_mean_summary" )
pulls_sigma_summary[ 'all'] = plotting.Hist(len(pars), 0.5, len(pars)+0.5, name = "all_pull_sigma_summary" )
deltas_mean_summary[ 'all'] = plotting.Hist(len(pars), 0.5, len(pars)+0.5, name = "all_delta_mean_summary" )
deltas_sigma_summary['all'] = plotting.Hist(len(pars), 0.5, len(pars)+0.5, name = "all_delta_sigma_summary")
for i, j in pars.iteritems():
make_post_distributions(i, j, pulls_dir, pulls_mean_summary, pulls_sigma_summary, prefix='pull_',
dist='pull', prefit=prefit_nuis, tdir=pulls_tdir, skipFit=args.skipFit)
make_post_distributions(i, j, pulls_dir, deltas_mean_summary, deltas_sigma_summary, prefix='delta_',
dist='delta', prefit=prefit_nuis, tdir=pulls_tdir, skipFit=args.skipFit)
for name,histo in pulls_mean_summary.iteritems():
canvas = plotting.Canvas()
histo.Draw()
canvas.Update()
line = ROOT.TLine(histo.GetBinLowEdge(1),0,histo.GetBinLowEdge(histo.GetNbinsX()+1),0)
line.SetLineColor(2)
line.Draw("same")
canvas.Update()
canvas.SaveAs('%s/%s.png' % (pulls_dir,histo.GetName()))
canvas.SaveAs('%s/%s.pdf' % (pulls_dir,histo.GetName()))
pulls_tdir.WriteObject(histo, histo.GetName())
for name,histo in pulls_sigma_summary.iteritems():
canvas = plotting.Canvas()
histo.Draw()
canvas.Update()
line = ROOT.TLine(histo.GetBinLowEdge(1),1,histo.GetBinLowEdge(histo.GetNbinsX()+1),1)
line.SetLineColor(2)
line.Draw("same")
canvas.Update()
canvas.SaveAs('%s/%s.png' % (pulls_dir,histo.GetName()))
canvas.SaveAs('%s/%s.pdf' % (pulls_dir,histo.GetName()))
pulls_tdir.WriteObject(histo, histo.GetName())
for name,histo in deltas_mean_summary.iteritems():
canvas = plotting.Canvas()
histo.Draw()
canvas.Update()
line = ROOT.TLine(histo.GetBinLowEdge(1),0,histo.GetBinLowEdge(histo.GetNbinsX()+1),0)
line.SetLineColor(2)
line.Draw("same")
canvas.Update()
canvas.SaveAs('%s/%s.png' % (pulls_dir,histo.GetName()))
canvas.SaveAs('%s/%s.pdf' % (pulls_dir,histo.GetName()))
pulls_tdir.WriteObject(histo, histo.GetName())
for name,histo in deltas_sigma_summary.iteritems():
histo.Draw()
canvas.Update()
#line = ROOT.TLine(histo.GetBinLowEdge(1),1,histo.GetBinLowEdge(histo.GetNbinsX()+1),1)
#line.Draw("same")
canvas.Update()
canvas.SaveAs('%s/%s.png' % (pulls_dir,histo.GetName()))
canvas.SaveAs('%s/%s.pdf' % (pulls_dir,histo.GetName()))
pulls_tdir.WriteObject(histo, histo.GetName())
if not args.noshapes:
#Overlays the prefit values of the different shapes with the envelope of
#what is fitted by the toys
out = os.path.join(args.out, 'shapes')
mkdir(out)
biased_shapes={}
if args.biasFile:
with io.root_open(args.biasFile) as biased:
biased_dir= biased.prefit \
if hasattr(biased, 'prefit') else \
None
ROOT.TH1.AddDirectory(False)
for key in biased_dir.keys():
biased_shapes[key.name] = asrootpy(key.ReadObj().Clone())
with io.root_open(args.harvested) as harvest:
has_prefit = hasattr(harvest, 'prefit')
prefit = harvest.prefit if has_prefit else None
toys = EnvelopeView(
*[harvest.get(i.GetName()).get(args.variable)
for i in harvest.keys()
if i.GetName().startswith('toy_')
and (i.GetName() not in failed_fits) ]
)
#shapes = [i.GetName() for i in prefit.keys()] #FIXME! should not depend on prefit!
first_toy = [i.GetName() for i in harvest.keys() if i.GetName().startswith('toy_')][0]
not_shapes = set('correlation_matrix')
shapes = [i.GetName() for i in harvest.get(first_toy).get(args.variable).keys() if i.GetName() not in not_shapes]
for shape in shapes:
canvas = plotting.Canvas()
canvas.SetCanvasSize( canvas.GetWw(), int(canvas.GetWh()*1.3) )
upper_pad = plotting.Pad(0, 0.33, 1., 1.)
lower_pad = plotting.Pad(0, 0., 1., 0.33)
upper_pad.set_bottom_margin(0.001)
lower_pad.set_top_margin(0.005)
lower_pad.set_bottom_margin(lower_pad.get_bottom_margin()*3)
upper_pad.Draw()
lower_pad.Draw()
upper_pad.cd()
biased_shape = biased_shapes.get(shape, None)
toy_shape = toys.Get(shape)
pre_shape = None
legend = plotting.Legend(
3+int(has_prefit)+int(bool(biased_shape)),
rightmargin=0.07, topmargin=0.05, leftmargin=0.45)
legend.SetBorderSize(0)
if biased_shape:
biased_shape.title = 'true shape'
biased_shape.legendstyle = 'p'
biased_shape.inlegend = True
biased_shape.drawstyle = 'p'
if has_prefit:
pre_shape = prefit.Get(shape)
pre_shape.title = 'input shape'
pre_shape.legendstyle = 'p'
pre_shape.drawstyle = 'p'
if biased_shape:
pre_shape.legendstyle = 'l'
pre_shape.drawstyle = 'hist'
pre_shape.linecolor = 'blue'
pre_shape.fillstyle = 0
toy_shape.Draw()
if has_prefit:
pre_shape.Draw('same')
if biased_shape:
biased_shape.Draw('same')
legend.AddEntry(toy_shape.two_sigma)
legend.AddEntry(toy_shape.one_sigma)
legend.AddEntry(toy_shape.median)
if has_prefit:
legend.AddEntry(pre_shape)
if biased_shape:
legend.AddEntry(biased_shape)
legend.Draw()
#compute pulls
pulls = None
labelSizeFactor2 = (upper_pad.GetHNDC()+lower_pad.GetHNDC()) / lower_pad.GetHNDC()
labelSizeFactor1 = (upper_pad.GetHNDC()+lower_pad.GetHNDC()) / upper_pad.GetHNDC()
label_factor = labelSizeFactor2/labelSizeFactor1
if has_prefit or biased_shape:
lower_pad.cd()
ref_histo = biased_shape if biased_shape else pre_shape
pulls = toy_shape.median.Clone()
pulls.Reset()
for ref, toy, pull in zip(ref_histo, toy_shape, pulls):
if toy.error == (0.0, 0.0): continue
abs_pull = toy.median-ref.value
#pick correct side of the errors
err = toy.error[1] if abs_pull < 0 else toy.error[0]
pull.value = abs_pull/err
pulls.xaxis.title = args.variable
pulls.yaxis.title = 'pulls'
pulls.set_label_size(ROOT.gStyle.GetLabelSize()*label_factor, "XYZ")
pulls.set_title_size(ROOT.gStyle.GetTitleSize()*label_factor, "XYZ")
pulls.yaxis.set_title_offset(pulls.GetYaxis().GetTitleOffset()/label_factor)
pulls.Draw()
canvas.Update()
canvas.SaveAs('%s/%s.png' % (out, shape))
canvas.SaveAs('%s/%s.pdf' % (out, shape))
with open(os.path.join(out, '%s.json' % shape), 'w') as jfile:
jfile.write(toy_shape.json())
output_file.Close()
