def plot_data_mc(hists_mc, hist_data, name):
canv = ROOT.TCanvas()
p1 = ROOT.TPad("p1", "p1", 0, 0.3, 1, 1)
p1.Draw()
p1.SetTicks(1, 1);
p1.SetGrid();
p1.SetFillStyle(0);
p1.cd()
stacks_d = OrderedDict()
print "MC",hists_mc
print "VAL",hists_mc.values()
stacks_d["mc"] = hists_mc.values()
stacks_d["data"] = [hist_data]
stacks = plot_hists_stacked(
p1,
stacks_d,
x_label=var,
y_label="",
do_log_y=True
)
leg = legend([hist_data] + list(reversed(hists_mc.values())), styles=["p", "f"])
print canv, hist_data
print get_stack_total_hist(stacks["mc"])
ratio_pad, hratio = plot_data_mc_ratio(canv, get_stack_total_hist(stacks["mc"]), hist_data)
plot_info = PlotMetaInfo(
name,
"CUT",
"WEIGHT",
[infile],
subdir=fit.name,
comments=str(result[SIGNAL])
)
of.savePlot(canv, plot_info)
canv.Close()
def data_mc_plot(samples, plot_def, name, lepton_channel, lumi, weight, physics_processes, use_antiiso=False):
logger.info('Plot in progress %s' % name)
merge_cmds = PhysicsProcess.get_merge_dict(physics_processes) #The actual merge dictionary
var = plot_def['var']
#Id var is a list/tuple, assume
if not isinstance(var, basestring):
try:
if lepton_channel == 'ele':
var = var[0]
elif lepton_channel == 'mu':
var = var[1]
except Exception as e:
logger.error("Plot variable 'var' specification incorrect for multi-variable plot: %s" % str(var))
raise e
cut = None
if lepton_channel == 'ele':
cut = plot_def['elecut']
elif lepton_channel == 'mu':
cut = plot_def['mucut']
cut_str = str(cut)
plot_range = plot_def['range']
do_norm = False
if 'normalize' in plot_def.keys() and plot_def['normalize']:
do_norm = True
hists_mc = dict()
hists_data = dict()
for name, sample in samples.items():
logger.debug("Starting to plot %s" % name)
if sample.isMC:
hist = sample.drawHistogram(var, cut_str, weight=str(weight), plot_range=plot_range)
hist.Scale(sample.lumiScaleFactor(lumi))
hists_mc[sample.name] = hist
if do_norm:
Styling.mc_style_nostack(hists_mc[sample.name], sample.name)
else:
Styling.mc_style(hists_mc[sample.name], sample.name)
if "fitpars" in plot_def.keys():
rescale_to_fit(sample.name, hist, plot_def["fitpars"][lepton_channel])
elif "antiiso" in name and plot_def['estQcd'] and not use_antiiso:
# Make loose template
#Y U NO LOOP :) -JP
region = '2j1t'
if '2j0t' in plot_def['estQcd']: region='2j0t'
if '3j0t' in plot_def['estQcd']: region='3j0t'
if '3j1t' in plot_def['estQcd']: region='3j1t'
if '3j2t' in plot_def['estQcd']: region='3j2t'
qcd_extra_cut = Cuts.deltaR(0.3)*Cuts.antiiso(lepton_channel)
#Take the loose template with a good shape from the N-jet, M-tag, post lepton selection region with high statistics
qcd_loose_cut = cutlist[region]*cutlist['presel_'+lepton_channel]*qcd_extra_cut
#Take the template which can be correctly normalized from the actual region with inverted isolation cuts
qcd_cut = cut*qcd_extra_cut
hist_qcd_loose = sample.drawHistogram(var, str(qcd_loose_cut), weight="1.0", plot_range=plot_range)
hist_qcd = sample.drawHistogram(var, str(qcd_cut), weight="1.0", plot_range=plot_range)
logger.debug("Using the QCD scale factor %s: %.2f" % (plot_def['estQcd'], qcdScale[lepton_channel][plot_def['estQcd']]))
hist_qcd.Scale(qcdScale[lepton_channel][plot_def['estQcd']])
hist_qcd_loose.Scale(hist_qcd.Integral()/hist_qcd_loose.Integral())
if var=='cos_theta':
hist_qcd=hist_qcd_loose
sampn = "QCD"+sample.name
#Rescale the QCD histogram to the eta_lj fit
if "fitpars" in plot_def.keys():
rescale_to_fit(sampn, hist_qcd, plot_def["fitpars"][lepton_channel])
hists_mc[sampn] = hist_qcd
hists_mc[sampn].SetTitle('QCD')
if do_norm:
Styling.mc_style_nostack(hists_mc[sampn], 'QCD')
else:
Styling.mc_style(hists_mc[sampn], 'QCD')
#Real ordinary data in the isolated region
elif not "antiiso" in name or use_antiiso:
hist_data = sample.drawHistogram(var, cut_str, weight="1.0", plot_range=plot_range)
hist_data.SetTitle('Data')
Styling.data_style(hist_data)
hists_data[name] = hist_data
if len(hists_data.values())==0:
raise Exception("Couldn't draw the data histogram")
#Combine the subsamples to physical processes
hist_data = sum(hists_data.values())
merge_cmds['QCD']=["QCD"+merge_cmds['data'][0]]
order=['QCD']+PhysicsProcess.desired_plot_order
if plot_def['log']:
order = PhysicsProcess.desired_plot_order_log+['QCD']
merged_hists = merge_hists(hists_mc, merge_cmds, order=order)
if hist_data.Integral()<=0:
logger.error(hists_data)
logger.error("hist_data.entries = %d" % hist_data.GetEntries())
logger.error("hist_data.integral = %d" % hist_data.Integral())
raise Exception("Histogram for data was empty. Something went wrong, please check.")
if do_norm:
for k,v in merged_hists.items():
v.Scale(1./v.Integral())
hist_data.Scale(1./hist_data.Integral())
htot = sum(merged_hists.values())
chi2 = hist_data.Chi2Test(htot, "UW CHI2/NDF")
if chi2>20:#FIXME: uglyness
logger.error("The chi2 between data and MC is large (%s, chi2=%.2f). You may have errors with your samples!" %
(name, chi2)
)
logger.info("MC : %s" % " ".join(map(lambda x: "%.1f" % x, list(htot.y()))))
logger.info("DATA: %s" % " ".join(map(lambda x: "%.1f" % x, list(hist_data.y()))))
logger.info("diff: %s" % str(
" ".join(map(lambda x: "%.1f" % x, numpy.abs(numpy.array(list(htot.y())) - numpy.array(list(hist_data.y())))))
))
merged_hists_l = merged_hists.values()
PhysicsProcess.name_histograms(physics_processes, merged_hists)
leg_style = ['p','f']
if do_norm:
leg_style=['p','l']
leg = legend([hist_data] + list(reversed(merged_hists_l)), legend_pos=plot_def['labloc'], styles=leg_style)
canv = ROOT.TCanvas()
#Make the stacks
stacks_d = OrderedDict()
stacks_d["mc"] = merged_hists_l
stacks_d["data"] = [hist_data]
#label
xlab = plot_def['xlab']
if not isinstance(xlab, basestring):
if lepton_channel == 'ele':
xlab = xlab[0]
else:
xlab = xlab[1]
ylab = 'N / '+str((1.*(plot_range[2]-plot_range[1])/plot_range[0]))
if plot_def['gev']:
ylab+=' GeV'
fact = 1.5
if plot_def['log']:
fact = 10
plow=0.3
if do_norm:
plow=0
#Make a separate pad for the stack plot
p1 = ROOT.TPad("p1", "p1", 0, plow, 1, 1)
p1.Draw()
p1.SetTicks(1, 1);
p1.SetGrid();
p1.SetFillStyle(0);
p1.cd()
stacks = plot_hists_stacked(p1, stacks_d, x_label=xlab, y_label=ylab, max_bin_mult = fact, do_log_y = plot_def['log'], stack = (not do_norm))
#Put the the lumi box where the legend is not
boxloc = 'top-right'
if plot_def['labloc'] == 'top-right':
boxloc = 'top-left'
chan = 'Electron'
if lepton_channel == "mu":
chan = 'Muon'
additional_comments = ""
if 'cutname' in plot_def.keys():
additional_comments += ", " + plot_def['cutname'][lepton_channel]
lbox = lumi_textbox(lumi,
boxloc,
'preliminary',
chan + ' channel' + additional_comments
)
#Draw everything
lbox.Draw()
leg.Draw()
canv.Draw()
#Keep the handles just in case
canv.PAD1 = p1
canv.STACKS = stacks
canv.LEGEND = legend
canv.LUMIBOX = lbox
return canv, merged_hists, htot, hist_data
elif name == "SingleMu":
hist_data = sample.drawHistogram(var, cut_str, weight="1.0", plot_range=plot_range)
Styling.data_style(hist_data)
elif name == "SingleMu_aiso":
hist_qcd = sample.drawHistogram(var, cut_str, weight="1.0", plot_range=plot_range)
#hist_qcd.
pass
#Combine the subsamples to physical processes
merged_hists = merge_hists(hists_mc, merge_cmds).values()
#Some printout
for h in merged_hists + [hist_data]:
print h.GetName(), h.GetTitle(), h.Integral()
canv = ROOT.TCanvas()
stacks_d = OrderedDict()
stacks_d["mc"] = merged_hists
stacks_d["data"] = [hist_data]
stacks = plot_hists_stacked(canv, stacks_d)
canv.Draw()
#Create the dir if it doesn't exits
try:
os.mkdir("muon_out")
except OSError:
pass
canv.SaveAs("muon_out/test.pdf")
canv = ROOT.TCanvas("c", "c")
canv.SetWindowSize(500, 500)
canv.SetCanvasSize(600, 600)
#!!!!LOOK HERE!!!!!
#----
#Draw the stacked histograms
#----
stacks_d = OrderedDict(
) #<<< need to use OrderedDict to have data drawn last (dict does not preserve order)
stacks_d["mc"] = [h_mc1, h_mc2,
h_mc3] # <<< order is important here, mc1 is bottom-most
stacks_d["data"] = [h_d1]
stacks = plot_hists_stacked(canv,
stacks_d,
x_label="variable x [GeV]",
y_label="",
do_log_y=False)
#Draws the lumi box
from plots.common.utils import lumi_textbox
lumibox = lumi_textbox(19432)
#Draw the legend
from plots.common.legend import legend
leg = legend(
[h_d1, h_mc3, h_mc2, h_mc1
], # <<< need to reverse MC order here, mc3 is top-most
styles=["p", "f"],
width=0.25)
def data_mc_plot(pd):
hists = load_theta_format(pd.infile, styles)
for (variable, sample, systtype, systdir), hist in hists.items_flat():
#Scale all MC samples except QCD to the luminosity
if sample_types.is_mc(sample) and not sample=="qcd":
hist.Scale(pd.lumi)
if hasattr(pd, "rebin"):
hist.Rebin(pd.rebin)
if sample=="qcd" and hasattr(pd, "qcd_yield"):
hist.Scale(pd.qcd_yield / hist.Integral())
rescale_to_fit(sample, hist, pd.process_scale_factor)
hist.SetTitle(sample)
hist.SetName(sample)
#Assuming we only have 1 variable
hists = hists[pd.var]
hists_nominal = hists.pop("nominal")[None]
hists_nom_data = hists_nominal.pop('data')
hists_nom_mc = hists_nominal.values()
hists_syst = hists
hists_nom_data.SetTitle('data')
#A list of all the systematic up, down variation templates as 2-tuples
all_systs = [
]
all_systs = hists_syst.keys()
systs_to_consider = []
#See which systematics where asked to switch on
for syst in all_systs:
for sm in pd.systematics:
if re.match(sm, syst):
systs_to_consider.append(syst)
#The total nominal MC histogram
nom = sum(hists_nom_mc)
if pd.normalize:
ratio = hists_nom_data.Integral() / nom.Integral()
hists_nom_data.Scale(1.0/ratio)
#Get all the variated up/down total templates
#A list with all the up/down total templates
all_systs = []
sumsqs = []
logger.info("Considering systematics %s" % str(systs_to_consider))
for syst in systs_to_consider:
#A list with the up/down variated template for a particular systematic
totupdown = []
sumsq = []
for systdir in ["up", "down"]:
#Get all the templates corresponding to a systematic scenario and a variation
_hists = hists_syst[syst][systdir]
for k, h in _hists.items():
"""
Consider only the shape variation of the systematic,
hence the variated template is normalized to the corresponding
unvariated template.
"""
if pd.systematics_shapeonly:
if h.Integral()>0:
h.Scale(hists_nominal[k].Integral() / h.Integral())
#For the missing variated templates, use the nominal ones, but warn the user
present = set(_hists.keys())
all_mc = set(hists_nominal.keys())
missing = list(all_mc.difference(present))
for m in missing:
logger.warning("Missing systematic template for %s:%s" % (syst, systdir))
#Calculate the total variated template
tot = sum(_hists.values()) + sum([hists_nominal[m] for m in missing])
totupdown.append(tot)
sumsq.append(
math.sqrt(numpy.sum(numpy.power(numpy.array(list(nom.y())) - numpy.array(list(tot.y())), 2)))
)
logger.debug("Systematic %s: sumsq=%.2Eu, %.2Ed" % (syst, sumsq[0], sumsq[1]))
sumsqs.append((syst, max(sumsq)))
all_systs.append(
(syst, tuple(totupdown))
)
sumsqs = sorted(sumsqs, key=lambda x: x[1], reverse=True)
for syst, sumsq in sumsqs[0:7]:
logger.info("Systematic %s, %.4f" % (syst, sumsq))
#Calculate the total up/down variated templates by summing in quadrature
syst_stat_up, syst_stat_down = total_syst(
nom, all_systs,
)
for k, v in hists_nominal.items():
if hasattr(PhysicsProcess, k):
pp = getattr(PhysicsProcess, k)
v.SetTitle(pp.pretty_name)
else:
logger.warning("Not setting pretty name for %s" % k)
#If QCD is high-stats, put it in the bottom
plotorder = copy.copy(PhysicsProcess.desired_plot_order_mc)
if hists_nominal["qcd"].GetEntries()>100:
plotorder.pop(plotorder.index("qcd"))
plotorder.insert(0, "qcd")
stacks_d = OrderedDict()
stacks_d['mc'] = reorder(hists_nominal, plotorder)
stacks_d['data'] = [hists_nom_data]
#Systematic style
for s in [syst_stat_up, syst_stat_down]:
s.SetFillStyle(0)
s.SetLineWidth(3)
s.SetMarkerSize(0)
s.SetLineColor(ROOT.kBlue+2)
s.SetLineStyle('dashed')
s.SetTitle("stat. + syst.")
#c = ROOT.TCanvas("c", "c", 1000, 1000)
c = ROOT.TCanvas("c", "c")
p1 = ROOT.TPad("p1", "p1", 0, 0.3, 1, 1)
p1.Draw()
p1.SetTicks(1, 1);
p1.SetGrid();
p1.SetFillStyle(0);
p1.cd()
stacks = plot_hists_stacked(
p1, stacks_d,
x_label=pd.get_x_label(), max_bin_mult=pd.get_max_bin_mult(),
min_bin=pd.get_min_bin()
)
p1.SetLogy(pd.log)
syst_stat_up.Draw("SAME hist")
syst_stat_down.Draw("SAME hist")
ratio_pad, hratio = plot_data_mc_ratio(
c, hists_nom_data,
nom, syst_hists=(syst_stat_down, syst_stat_up), min_max=pd.get_ratio_minmax()
)
p1.cd()
leg = legend(
stacks_d['data'] +
list(reversed(stacks_d['mc'])) +
[syst_stat_up],
nudge_x=pd.legend_nudge_x,
nudge_y=pd.legend_nudge_y,
**pd.__dict__
)
lb = lumi_textbox(pd.lumi,
line2=pd.get_lumibox_comments(channel=pd.channel_pretty),
pos=pd.get_lumi_pos()
)
c.children = [p1, ratio_pad, stacks, leg, lb]
tot = 0
for k, v in hists_nominal.items():
print k, v.Integral(), v.GetEntries()
tot += v.Integral()
tot_data = hists_nom_data.Integral()
print "MC: %.2f Data: %.2f" % (tot, tot_data)
#import pdb; pdb.set_trace()
return c, (hists_nominal, hists_nom_data)
#Create the canvas
canv = ROOT.TCanvas("c", "c")
canv.SetWindowSize(500, 500)
canv.SetCanvasSize(600, 600)
#!!!!LOOK HERE!!!!!
#----
#Draw the stacked histograms
#----
stacks_d = OrderedDict() #<<< need to use OrderedDict to have data drawn last (dict does not preserve order)
stacks_d["mc"] = [h_mc1, h_mc2, h_mc3] # <<< order is important here, mc1 is bottom-most
stacks_d["data"] = [h_d1]
stacks = plot_hists_stacked(
canv,
stacks_d,
x_label="variable x [GeV]",
y_label="",
do_log_y=False
)
#Draws the lumi box
from plots.common.utils import lumi_textbox
lumibox = lumi_textbox(19432)
#Draw the legend
from plots.common.legend import legend
leg = legend(
[h_d1, h_mc3, h_mc2, h_mc1], # <<< need to reverse MC order here, mc3 is top-most
styles=["p", "f"],
width=0.25
)
