fill_opts=fill_opts,
error_opts=error_opts,
)
# DATA plotting
hist.plot1d(h1[data].integrate('region', region),
ax=ax,
clear=False,
error_opts=data_err_opts)
# -- Ratio Plot
hist.plotratio(
num=h1[data].integrate('region', region).sum("dataset"),
denom=h1[notdata].integrate('region', region).sum("dataset"),
ax=rax,
error_opts=data_err_opts,
denom_fill_opts={},
guide_opts={},
unc="num",
)
np.set_printoptions(suppress=True)
rax.set_ylabel("Data/MC")
rax.set_ylim(0, 2)
ax._get_lines.prop_cycler = ax._get_patches_for_fill.prop_cycler
ax.autoscale(axis="x", tight=True)
ax.set_ylim(ymin, ymax)
ax.set_xlim(xmin, xmax)
order=processes)
#hist.plot1d(histogram[signal], overlay="dataset", ax=ax, overflow=bins[name]['overflow'], line_opts={'linewidth':3}, clear=False)
#hist.plot1d(histogram['750_1_scan'], overlay="dataset", ax=ax, overflow=bins[name]['overflow'], line_opts={'linewidth':3}, clear=False)
hist.plot1d(histogram['1000_1_scan'],
overlay="dataset",
ax=ax,
overflow=bins[name]['overflow'],
line_opts={'linewidth': 3},
clear=False)
if usePseudoData:
# build ratio
hist.plotratio(num=histogram['pseudodata'].sum("dataset"),
denom=histogram[notdata].sum("dataset"),
ax=rax,
error_opts=data_err_opts,
denom_fill_opts={},
guide_opts={},
unc='num',
overflow=bins[name]['overflow'])
for l in ['linear', 'log']:
if usePseudoData:
saveFig(fig,
ax,
rax,
plotDir,
name,
scale=l,
shape=False,
y_max=y_max)
else:
def sf_1d(acc, tag, regex, outputrootfile):
outdir = './output/'
if not os.path.exists(outdir):
os.makedirs(outdir)
fig, (ax, rax) = plt.subplots(2, 1, figsize=(7,7), gridspec_kw={"height_ratios": (3, 1)}, sharex=True)
# new_ax = hist.Bin('vpt','LHE V $p_{T}$ (GeV)',list(range(100,500,50)) + list(range(500,1000,100)) + list(range(1000,2000,250)))
pt_types = ['stat1']
if tag in ['dy','wjet']:
pt_types.append('dress')
new_ax = hist.Bin('vpt','V $p_{T}$ (GeV)',list(range(100,800,100))+list(range(800,1200,200))+list(range(1200,2800,800)))
else:
new_ax = hist.Bin('vpt','V $p_{T}$ (GeV)',[200,250]+list(range(300,800,100))+list(range(800,1400,200)))
overflow = 'none'
for pt_type in pt_types:
for selection in ['inclusive','monojet','vbf']:
dist = f'gen_vpt_{selection}_{pt_type}'
acc.load(dist)
h = copy.deepcopy(acc[dist])
h = h.rebin(h.axis('vpt'), new_ax)
if selection == 'monojet':
h = h.integrate(h.axis("jpt"))
if selection == 'vbf':
h = h.integrate(h.axis("jpt"))
h = h.integrate(h.axis("mjj"))
h = merge_extensions(h, acc, reweight_pu=False)
scale_xs_lumi(h)
h = merge_datasets(h)
h = h[re.compile(regex)]
hist.plot1d(
h,
overlay='dataset',
overflow=overflow,
binwnorm=True,
ax=ax)
lo = h[re.compile('.*HT.*')].integrate('dataset')
nlo = h[re.compile('.*(LHE|amc).*')].integrate('dataset')
hist.plotratio(nlo, lo,
ax=rax,
denom_fill_opts={},
guide_opts={},
unc='num',
overflow=overflow,
error_opts=data_err_opts,
label='2017 NLO/LO ratio'
)
# if tag in ['dy','wjet']:
old = get_old_kfac(tag)
old_x = 0.5*(old.bins[:,0]+old.bins[:,1])
rax.plot(old_x, old.values,'ob-', label='2016 QCD k fac')
rax.plot(old_x, old.values * pdfwgt_sf(old_x),'or-', label='2016 x ad-hoc DY pdfwgt SF')
ax.set_yscale('log')
ax.set_ylim(1e-3,1e6)
rax.set_ylim(0,2)
rax.legend()
fig.savefig(pjoin(outdir,f'{tag}_{dist}.pdf'))
sf_x = lo.axis('vpt').edges(overflow=overflow)
sf_y = nlo.values(overflow=overflow)[()] / lo.values(overflow=overflow)[()]
outputrootfile[f'{tag}_{pt_type}_{selection}'] = (sf_y,sf_x)
def plot_recoil(acc, region_tag="1m", dataset='SingleMuon', year=2018, tag="test", distribution="recoil"):
h = acc[distribution]
h = merge_extensions(h)
# h = scale_to_xs(h, acc)
h = merge_datasets(h)
newbin = hist.Bin(distribution,f"{distribution} (GeV)",np.array(list(range(0,400,20)) + list(range(400,1100,100))))
h = h.rebin(h.axis(distribution), newbin)
ds = f'{dataset}_{year}'
h = h.project(h.axis('dataset'), ds)
# print(h)
hnum = h.project(h.axis('region'),f'tr_{region_tag}_num')
hden = h.project(h.axis('region'),f'tr_{region_tag}_den')
# print(hden, hnum)
# Recoil plot
try:
fig, ax,_ = hist.plot1d(hnum, binwnorm=True)
except KeyError:
print(f'ERROR: {region_tag}, {dataset}, {year}')
return
hist.plot1d(hden, ax=ax, clear=False, binwnorm=True)
plt.yscale('log')
plt.gca().set_ylim(0.1,1e6)
outdir = f"./output/{tag}"
if not os.path.exists(outdir):
os.makedirs(outdir)
fig.savefig(pjoin(outdir, f'{distribution}_{region_tag}_{dataset}_{year}.pdf'))
with open(pjoin(outdir,f'table_{region_tag}_{dataset}_{year}.txt'),"w") as f:
f.write(content_table(hnum, hden) + "\n")
plt.close(fig)
# Efficiency
fig, ax,_ = hist.plotratio(hnum, hden,
guide_opts={},
unc='clopper-pearson',
error_opts=markers('data')
)
ax.set_ylim(0,1.1)
ax.set_xlim(0,xmax)
ax.set_ylabel("Efficiency")
plt.text(1., 1., r"$\approx$ %.1f fb$^{-1}$ (13 TeV)" % lumi(year),
fontsize=16,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes
)
plt.text(0., 1., f'{region_tag}, {year}',
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes
)
plt.text(1., 0., f'{trgname(year, tag)}',
fontsize=10,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes
)
plt.plot([0,xmax],[0.95,0.95],'r-')
fig.savefig(pjoin(outdir, f'eff_{region_tag}_{dataset}_{year}.pdf'))
plt.close(fig)
density=True
)
ax.autoscale(axis='x', tight=True)
#ax.set_ylim(0, None)
ax.set_ylim(1e-8,1e1)
ax.set_yscale('log')
ax.set_xlabel(None)
leg = ax.legend()
# now we build the ratio plot
hist.plotratio(
num=numerator,
denom=denominator,
ax=rax,
error_opts=data_err_opts,
denom_fill_opts={},
guide_opts={},
unc='num'
)
rax.set_ylabel('Ratio')
rax.set_ylim(0,2)
# add some labels
cms = plt.text(0., 1., u"CMS Simulation work",
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes
)
lumi = plt.text(1., 1., r"137 fb$^{-1}$ (13 TeV)",
list(range(80, 800, 40)) + list(range(800, 2000, 100)))
h = h.rebin(h.axis('vpt'), new_ax)
print(h)
fig, (ax, rax) = plt.subplots(2,
1,
figsize=(7, 7),
gridspec_kw={"height_ratios": (3, 1)},
sharex=True)
hist.plot1d(h,
overlay='type',
overflow='all',
ax=ax,
clear=False,
binwnorm=True)
ax.legend()
hist.plotratio(h['dilepton'].integrate('type'),
h['nano'].integrate('type'),
ax=rax,
denom_fill_opts={},
guide_opts={},
unc='num',
overflow='all',
error_opts=data_err_opts,
label='status 1 dilepton / LHE',
clear=False)
# rax.set_ylim(0.9,1.1)
fig.savefig('test_lhe.pdf')
def probefilter(dataset_type="inclusive"):
fig, ax = plt.subplots(
2, 1,
figsize=(10,
12)) #, gridspec_kw={"height_ratios": (3, 1)}, sharex=True)
plt.style.use(mplhep.style.ROOT)
h_bu_truthpt = histograms["Bu"]["TruthBuToKMuMu_pt"].integrate(
f"dataset", (f"Bu2KJpsi2KMuMu_{dataset_type}"))
h_bu_truthpt.axis("selection").index(
"inclusive").label = r"$B_u$, inclusive"
h_bu_truthpt.axis("selection").index(
"probefilter").label = r"$B_u$, emul. probe filter"
hist.plot1d(h_bu_truthpt[(["inclusive"]), :],
ax=ax[0],
clear=False,
overlay="selection",
line_opts={
"color": "red",
"linestyle": "-"
})
hist.plot1d(h_bu_truthpt[(["probefilter"]), :],
ax=ax[0],
clear=False,
overlay="selection",
line_opts={
"color": "red",
"linestyle": "--"
})
h_bs_truthpt = histograms["Bs"]["TruthBsToKKMuMu_pt"].integrate(
"dataset", (f"Bs2PhiJpsi2KKMuMu_{dataset_type}"))
h_bs_truthpt.axis("selection").index(
"inclusive").label = r"$B_s$, inclusive"
h_bs_truthpt.axis("selection").index(
"probefilter").label = r"$B_s$, emul. probe filter"
hist.plot1d(h_bs_truthpt[(["inclusive", "probefilter"]), :],
ax=ax[0],
clear=False,
overlay="selection",
line_opts={
"color": "blue",
"linestyle": "-"
})
#hist.plot1d(h_bs_truthpt[(["probefilter"]),:], ax=ax[0], clear=False, overlay="selection", line_opts={"color":"blue", "linestyle":"--"})
h_bd_truthpt = histograms["Bd"]["TruthBdToKPiMuMu_pt"].integrate(
"dataset", (f"Bd2KstarJpsi2KPiMuMu_{dataset_type}"))
h_bd_truthpt.axis("selection").index(
"inclusive").label = r"$B_d$, inclusive"
h_bd_truthpt.axis("selection").index(
"probefilter").label = r"$B_d$, emul. probe filter"
hist.plot1d(h_bd_truthpt[(["inclusive", "probefilter"]), :],
ax=ax[0],
clear=False,
overlay="selection",
line_opts={
"color": "green",
"linestyle": "-"
})
h_bu_truthpt_inclusive = h_bu_truthpt.integrate("selection", ("inclusive"))
h_bu_truthpt_probefilter = h_bu_truthpt.integrate("selection",
("probefilter"))
h_bu_truthpt_probefilter.label = "Efficiency"
hist.plotratio(
num=h_bu_truthpt_probefilter,
denom=h_bu_truthpt_inclusive,
ax=ax[1],
unc="clopper-pearson",
clear=False,
error_opts={
'color': 'red',
'marker': '.'
},
)
h_bs_truthpt_inclusive = h_bs_truthpt.integrate("selection", ("inclusive"))
h_bs_truthpt_probefilter = h_bs_truthpt.integrate("selection",
("probefilter"))
h_bs_truthpt_probefilter.label = "Efficiency"
hist.plotratio(
num=h_bs_truthpt_probefilter,
denom=h_bs_truthpt_inclusive,
ax=ax[1],
unc="clopper-pearson",
clear=False,
error_opts={
'color': 'blue',
'marker': '.'
},
)
h_bd_truthpt_inclusive = h_bd_truthpt.integrate("selection", ("inclusive"))
h_bd_truthpt_probefilter = h_bd_truthpt.integrate("selection",
("probefilter"))
h_bd_truthpt_probefilter.label = "Efficiency"
hist.plotratio(
num=h_bd_truthpt_probefilter,
denom=h_bd_truthpt_inclusive,
ax=ax[1],
unc="clopper-pearson",
clear=False,
error_opts={
'color': 'green',
'marker': '.'
},
)
ax[0].set_yscale("log")
ax[0].set_ylim(1., 1.e6)
if dataset_type == "inclusive":
ax[1].set_yscale("log")
ax[1].set_ylim(0.001, 0.2)
ax[0].legend(fontsize=14)
plt.tight_layout()
fig.savefig(
f"{figure_directory}/probefilter_efficiency_{dataset_type}.png")
def Stack(self, hname={}, xtit='', ytit=''):
''' prName can be a list of histograms or a dictionary 'histoName : xtit' '''
if isinstance(hname, dict):
for k in hname:
self.Stack(k, hname[k], ytit)
return
if isinstance(hname, list):
for k in hname:
self.Stack(k, xtit, ytit)
return
density = False
binwnorm = None
plt.rcParams.update(self.textParams)
if self.doData(hname) and self.doRatio:
fig, (ax,
rax) = plt.subplots(2,
1,
figsize=(7, 7),
gridspec_kw={"height_ratios": (3, 1)},
sharex=True)
fig.subplots_adjust(hspace=.07)
else:
fig, ax = plt.subplots(1, 1, figsize=(
7, 7)) #, gridspec_kw={"height_ratios": (3, 1)}, sharex=True)
# Colors
from cycler import cycler
colors = self.GetColors(self.bkglist)
if self.invertStack:
_n = len(h.identifiers(overlay)) - 1
colors = colors[_n::-1]
ax.set_prop_cycle(cycler(color=colors))
fill_opts = self.fill_opts
error_opts = self.error_opts
data_err_opts = self.data_err_opts
if not self.doStack:
error_opts = None
fill_opts = None
if self.invertStack and type(h._axes[0]) == hist.hist_tools.Cat:
h._axes[0]._sorted.reverse()
h = self.GetHistogram(hname, self.bkglist)
h.scale(1000. * self.lumi)
hist.plot1d(h,
overlay="process",
ax=ax,
clear=False,
stack=self.doStack,
density=density,
line_opts=None,
fill_opts=fill_opts,
error_opts=error_opts,
binwnorm=binwnorm)
if self.doData(hname):
hData = self.GetHistogram(hname, self.dataName)
hist.plot1d(hData,
ax=ax,
clear=False,
error_opts=data_err_opts,
binwnorm=binwnorm)
ydata = hData.values(overflow='all')
ax.autoscale(axis='x', tight=True)
ax.set_ylim(0, None)
ax.set_xlabel(None)
if self.doLegend:
leg_anchor = (1., 1.)
leg_loc = 'upper left'
handles, labels = ax.get_legend_handles_labels()
if self.doData(hname):
handles = handles[-1:] + handles[:-1]
labels = ['Data'] + labels[:-1]
ax.legend(handles,
labels) #,bbox_to_anchor=leg_anchor,loc=leg_loc)
if self.doData(hname) and self.doRatio:
hist.plotratio(hData,
h.sum("process"),
clear=False,
ax=rax,
error_opts=data_err_opts,
denom_fill_opts={},
guide_opts={},
unc='num')
rax.set_ylabel(self.yRatioTit)
rax.set_ylim(self.ratioRange[0], self.ratioRange[1])
if self.doLogY:
ax.set_yscale("log")
ax.set_ylim(1, ax.get_ylim()[1] * 5)
if not self.xRange is None: ax.set_xlim(xRange[0], xRange[1])
if not self.yRange is None: ax.set_ylim(yRange[0], yRange[1])
# Labels
CMS = plt.text(0.,
1.,
r"$\bf{CMS}$ Preliminary",
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
lumi = plt.text(1.,
1.,
r"%1.1f %s (%s)" %
(self.lumi, self.lumiunit, self.sqrts),
fontsize=20,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
if not self.region is None:
lab = plt.text(0.03,
.98,
self.region,
fontsize=16,
horizontalalignment='left',
verticalalignment='top',
transform=ax.transAxes)
ax.set_ylim(0, ax.get_ylim()[1] * 1.1)
# Save
os.system('mkdir -p %s' % self.outpath)
fig.savefig(os.path.join(self.outpath, hname + '.png'))
def plot_datamc(outputs):
bkg, data = outputs['bkg'], outputs['data']
fill_opts = {'edgecolor': (0, 0, 0, 0.3), 'alpha': 0.8}
error_opts = {
'label': 'Stat. Unc.',
'hatch': 'xxx',
'facecolor': 'none',
'edgecolor': (0, 0, 0, .5),
'linewidth': 0
}
data_err_opts = {
'linestyle': 'none',
'marker': '.',
'markersize': 10.,
'color': 'k',
'elinewidth': 1,
'emarker': '_'
}
CHANNELS = ['2mu2e', '4mu']
res = {}
for i, chan in enumerate(CHANNELS, start=1):
res[chan] = fig, (axes, raxes) = plt.subplots(
2,
2,
figsize=(16, 8),
gridspec_kw={"height_ratios": (4, 1)},
sharex=True)
fig.subplots_adjust(hspace=.07, wspace=0.1)
hist.plot1d(bkg['pt_cat'].integrate('channel', slice(i,
i + 1)).integrate(
'njet',
slice(0, 4)),
overlay='cat',
ax=axes[0],
stack=True,
overflow='over',
line_opts=None,
fill_opts=fill_opts,
error_opts=error_opts)
hist.plot1d(data['pt_cat'].integrate('channel',
slice(i, i + 1)).integrate(
'njet', slice(0, 4)),
overlay='cat',
ax=axes[0],
overflow='over',
clear=False,
error_opts=data_err_opts)
hist.plot1d(bkg['pt_cat'].integrate('channel', slice(
i, i + 1)).integrate('njet', slice(4, 10), overflow='over'),
overlay='cat',
ax=axes[1],
stack=True,
overflow='over',
line_opts=None,
fill_opts=fill_opts,
error_opts=error_opts)
hist.plot1d(data['pt_cat'].integrate('channel', slice(
i, i + 1)).integrate('njet', slice(4, 10), overflow='over'),
overlay='cat',
ax=axes[1],
overflow='over',
clear=False,
error_opts=data_err_opts)
for ax in axes:
ax.autoscale(axis='both', tight=True)
ax.set_yscale('symlog')
ax.set_xlabel(None)
ax.set_ylabel(ax.get_ylabel(), y=1.0, ha="right")
ax.text(1,
1,
'59.74/fb (13TeV)',
ha='right',
va='bottom',
transform=ax.transAxes)
axes[0].set_title(f'[{chan}|CR] leptonJets pT, N(AK4PFCHS)<4',
x=0.0,
ha="left")
axes[1].set_title(f'[{chan}|CR] leptonJets pT, N(AK4PFCHS)>=4',
x=0.0,
ha="left")
hist.plotratio(data['pt_cat'].integrate('channel', slice(
i, i + 1)).integrate('njet', slice(0, 4)).sum('cat'),
bkg['pt_cat'].integrate('channel', slice(
i, i + 1)).integrate('njet', slice(0,
4)).sum('cat'),
ax=raxes[0],
overflow='over',
error_opts=data_err_opts,
unc='num',
denom_fill_opts={},
guide_opts={})
hist.plotratio(data['pt_cat'].integrate(
'channel', slice(i, i + 1)).integrate('njet',
slice(4, 10),
overflow='over').sum('cat'),
bkg['pt_cat'].integrate('channel', slice(
i, i + 1)).integrate('njet',
slice(4, 10),
overflow='over').sum('cat'),
ax=raxes[1],
overflow='over',
error_opts=data_err_opts,
unc='num',
denom_fill_opts={},
guide_opts={})
for rax in raxes:
rax.set_ylabel('Data/MC')
rax.set_ylim(0, 2)
rax.set_xlabel(rax.get_xlabel(), x=1.0, ha="right")
return res
axis,
histogram,
notdata, [], [],
overflow=bins[name]['overflow'],
rebin=bins[name]['bins'],
ratio=False,
scales=scales)
if useData:
# build ratio
hist.plotratio(
num=histogram['Data'].sum("dataset"),
denom=histogram[notdata].sum("dataset"),
ax=rax,
error_opts=data_err_opts,
denom_fill_opts=
None, # triggers this: https://github.com/CoffeaTeam/coffea/blob/master/coffea/hist/plot.py#L376
guide_opts={},
unc='num',
#unc=None,
overflow=bins[name]['overflow'])
if 'upHists' in bins[name]:
addUncertainties(rax,
axis,
histogram,
notdata,
[output[x] for x in bins[name]['upHists']],
[output[x] for x in bins[name]['downHists']],
overflow=bins[name]['overflow'],
rebin=bins[name]['bins'],
h1['DY'],
ax=ax,
clear=False,
stack=True,
fill_opts=fill_opts,
error_opts=error_opts,
)
# DATA plotting
hist.plot1d(h1['Egamma_RunAB'], ax=ax, clear=False, error_opts=data_err_opts)
# Ratio Plot
hist.plotratio(num=h1['Egamma_RunAB'].sum("dataset"),
denom=h1['DY'].sum("dataset"),
ax=rax,
error_opts=data_err_opts,
denom_fill_opts={},
guide_opts={},
unc='num')
rax.set_ylabel('Data/MC')
rax.set_ylim(0, 2)
ax._get_lines.prop_cycler = ax._get_patches_for_fill.prop_cycler
ax.autoscale(axis='x', tight=True)
ax.set_ylim(ymin, ymax)
ax.set_xlim(xmin, xmax)
ax.set_xlabel('')
#ax.set_yscale('log')
#rax.set_xlabel('# of Priamary vertex')
print("Styling top")
ax1.set_xlim(0., 1000.)
ax1.set_ylim(0.1, 100000.)
ax1.set_yscale("log")
print("Integrating for ratio")
h_zpt_pdfwgtT = stuff["h_zpt"].integrate("dataset", ("WJetsToQQ_pdfwgt"))
h_zpt_pdfwgtF = stuff["h_zpt"].integrate("dataset", ("WJetsToQQ"))
print("Plotting bottom")
hist.plotratio(h_zpt_pdfwgtT,
h_zpt_pdfwgtF,
ax=ax2,
unc="poisson-ratio",
error_opts={
'color': 'blue',
'marker': '.'
},
guide_opts={
'xmin': 0.,
'xmax': 1000.
})
ax2.set_xlim(0., 1000.)
plt.tight_layout()
print("Saving")
fig1.savefig("pdfwgt_Vpt.png")
fig2, ax = plt.subplots()
hist.plot1d(stuff["h_genjetAK8_mass"], overlay="dataset", ax=ax)
fig2.savefig("pdfwgt_genjetAK8mass.png")
def plot_recoil(acc,
xmax=1e3,
ymin=0,
ymax=1.1,
region_tag="1m",
dataset='SingleMuon',
year=2018,
tag="test",
distribution="recoil",
axis_name=None,
noscale=False,
jeteta_config=None,
output_format='pdf'):
# Select and prepare histogram
h = copy.deepcopy(acc[distribution])
h = merge_extensions(h,
acc,
reweight_pu=('nopu' in distribution),
noscale=noscale)
if not noscale:
scale_xs_lumi(h)
h = merge_datasets(h)
# Rebinning
axis_name = distribution if not axis_name else axis_name
if 'photon' in distribution:
newbin = hist.Bin(
axis_name, f"{axis_name} (GeV)",
np.array(
list(range(0, 250, 10)) + list(range(250, 400, 50)) +
list(range(400, 1100, 100))))
elif distribution == 'mjj':
newbin = hist.Bin(
axis_name, r'$M_{jj}$ (GeV)',
np.array(
list(range(200, 600, 200)) + list(range(600, 1500, 300)) +
[1500, 2000, 2750, 3500]))
else:
newbin = hist.Bin(
axis_name, f"{axis_name} (GeV)",
np.array(list(range(0, 500, 25)) + list(range(500, 1100, 100))))
h = h.rebin(h.axis(axis_name), newbin)
ds = f'{dataset}_{year}'
# Pick dataset and regions
h = h.integrate(h.axis('dataset'), ds)
if jeteta_config:
hnum = h.integrate(h.axis('region'),
f'tr_{region_tag}_num_{jeteta_config}')
hden = h.integrate(h.axis('region'),
f'tr_{region_tag}_den_{jeteta_config}')
else:
hnum = h.integrate(h.axis('region'), f'tr_{region_tag}_num')
hden = h.integrate(h.axis('region'), f'tr_{region_tag}_den')
# Recoil plot
try:
fig, ax, _ = hist.plot1d(hnum, binwnorm=True)
except KeyError:
pprint(h.axis('region').identifiers())
print(f'ERROR: {region_tag}, {dataset}, {year}')
return
hist.plot1d(hden, ax=ax, clear=False, binwnorm=True)
plt.yscale('log')
plt.gca().set_ylim(0.1, 1e6)
outdir = f"./output/{tag}"
if not os.path.exists(outdir):
os.makedirs(outdir)
outname = f'{region_tag}{"_noscale_" if noscale else "_"}{distribution}_{dataset}_{year}{"_"+jeteta_config if jeteta_config else ""}'
fig.savefig(pjoin(outdir, f'{outname}.{output_format}'))
with open(pjoin(outdir, f'table_{outname}.txt'), "w") as f:
f.write(content_table(hnum, hden, axis_name) + "\n")
plt.close(fig)
# Efficiency plot
fig, ax, _ = hist.plotratio(hnum,
hden,
guide_opts={},
unc='clopper-pearson',
error_opts=markers('data'))
ax.set_ylim(ymin, ymax)
ax.set_xlim(0, xmax)
ax.set_ylabel("Efficiency")
plt.text(1.,
1.,
r"%.1f fb$^{-1}$ (13 TeV)" % lumi_by_region(region_tag, year),
fontsize=16,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
plt.text(1.,
0.95,
f'{jeteta_config if jeteta_config else ""}',
fontsize=12,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
plt.text(0.,
1.,
f'{region_tag}, {year}',
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
plt.text(1.,
0.,
f'{trgname(year, tag)}',
fontsize=10,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
if 'g_' in region_tag:
plt.plot([215, 215], [0.8, 1.1], 'r-')
plt.plot([0, xmax], [0.95, 0.95], 'r-')
fig.savefig(pjoin(outdir, f'eff_{outname}.pdf'))
plt.close(fig)
def make_plot(acc,
region,
distribution,
year,
data,
mc,
signal=None,
outdir='./output/stack/',
integrate=None,
ylim=None,
xlim=None,
rylim=None,
tag=None,
output_format='pdf',
ratio=True):
"""Creates a data vs MC comparison plot
:param acc: Accumulator (processor output)
:type acc: coffea.processor.accumulator
"""
# Rebin
s = Style()
h = copy.deepcopy(acc[distribution])
assert (h)
try:
newax = s.get_binning(distribution, region)
h = h.rebin(h.axis(newax.name), newax)
except KeyError:
pass
# Integrate over an extra axis
inte_tag = ""
if integrate:
(inte_axis, inte_low, inte_high) = integrate
h = h.integrate(inte_axis,
slice(inte_low,
inte_high)) #can add an overflow option here
inte_tag += "_" + inte_axis + "_" + str(inte_low) + "_" + str(
inte_high)
# Pick the region we want to look at
# E.g. cr_2m_j = Di-Muon control region with monojet selection
h = h.integrate(h.axis('region'), region)
# Plotting
# Add ratio plot at the bottom if specified (default)
# Otherwise just plot the histogram
if ratio:
fig, (ax, rax) = plt.subplots(2,
1,
figsize=(7, 7),
gridspec_kw={"height_ratios": (3, 1)},
sharex=True)
else:
fig, ax = plt.subplots(1, 1, figsize=(7, 5))
data_err_opts = {
'linestyle': 'none',
'marker': '.',
'markersize': 10.,
'color': 'k',
'elinewidth': 1,
}
signal_err_opts = {
'linestyle': 'none',
'marker': '.',
'markersize': 10.,
'color': 'r',
'elinewidth': 1,
}
# Plot single muon data
# Note the syntax we use to pick the data set
if data:
hist.plot1d(h[data],
overlay='dataset',
error_opts=data_err_opts,
ax=ax,
overflow='all',
binwnorm=True)
if signal:
fig, ax, _ = hist.plot1d(h[signal],
overlay='dataset',
error_opts=signal_err_opts,
ax=ax,
overflow='all',
binwnorm=True)
# Plot MC background samples
# Here we use a regular expression to match
# data sets we want
hist.plot1d(h[mc],
overlay='dataset',
stack=True,
clear=False,
overflow='all',
ax=ax,
binwnorm=True)
# Apply correct colors to BG histograms
handles, labels = ax.get_legend_handles_labels()
for handle, label in zip(handles, labels):
col = None
for k, v in colors.items():
if re.match(k, label):
col = v
break
if col:
handle.set_color(col)
handle.set_linestyle('-')
handle.set_edgecolor('k')
# Update legend
try:
region_name = s.region_names[region]
except KeyError:
region_name = region
ax.legend(title=region_name, ncol=1)
# Ratio plot
if data:
hist.plotratio(h[data].integrate('dataset'),
h[mc].integrate('dataset'),
ax=rax,
denom_fill_opts={},
guide_opts={},
unc='num',
overflow='all',
error_opts=data_err_opts)
ax.text(1.,
0.,
distribution,
fontsize=10,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
fig.text(1.,
1.,
f'{lumi(year)} fb$^{{-1}}$ ({year})',
fontsize=14,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
fig.text(0.,
1.,
'$\\bf{CMS}$ internal',
fontsize=14,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
# Aesthetics
ax.set_yscale("log")
ax.set_ylabel('Events / Bin width')
plot_settings = style.plot_settings()
if region in plot_settings.keys():
plot_settings = plot_settings[region]
if distribution in plot_settings.keys():
plot_settings = plot_settings[distribution]
if ylim:
ax.set_ylim(ylim[0], ylim[1])
elif 'ylim' in plot_settings.keys():
ax.set_ylim(plot_settings['ylim'])
else:
ax.set_ylim(1e-1, 1e6)
if xlim:
ax.set_xlim(xlim[0], xlim[1])
elif 'xlim' in plot_settings.keys():
ax.set_xlim(plot_settings['xlim'])
if ratio:
if rylim:
rax.set_ylim(*rylim)
else:
rax.set_ylim(0.75, 1.25)
loc1 = matplotlib.ticker.MultipleLocator(base=0.2)
loc2 = matplotlib.ticker.MultipleLocator(base=0.1)
rax.yaxis.set_major_locator(loc1)
rax.yaxis.set_minor_locator(loc2)
rax.grid(axis='y', which='minor', linestyle='--')
rax.grid(axis='y', which='major', linestyle='--')
rax.set_ylabel('Data / MC')
if not os.path.exists(outdir):
os.makedirs(outdir)
for form in output_format.split(','):
outpath = pjoin(
outdir,
f"{region}_{distribution}{inte_tag}_{tag + '_' if tag else ''}{year}.{form}"
)
fig.savefig(outpath)
print(f"Saved plot file in {outpath}")
plt.close('all')
def makePlot(output,
histo,
axis,
bins=None,
data=[],
normalize=True,
log=False,
save=False,
axis_label=None,
ratio_range=None,
upHists=[],
downHists=[],
shape=False,
ymax=False,
new_colors=colors,
new_labels=my_labels,
order=None,
signals=[],
omit=[],
lumi=60.0,
binwnorm=None,
overlay=None,
use_label=True,
y_axis_label='Events'):
if save:
finalizePlotDir('/'.join(save.split('/')[:-1]))
mc_sel = re.compile(
'(?!(%s))' %
('|'.join(data + omit))) if len(data + omit) > 0 else re.compile('')
data_sel = re.compile('|'.join(data))
bkg_sel = re.compile(
'(?!(%s))' %
('|'.join(data + signals + omit))) if len(data + signals +
omit) > 0 else re.compile('')
if histo is None:
processes = [p[0] for p in output.values().keys() if not p[0] in data]
histogram = output.copy()
else:
processes = [
p[0] for p in output[histo].values().keys() if not p[0] in data
]
histogram = output[histo].copy()
histogram = histogram.project(axis, 'dataset')
if overlay: overlay = overlay.project(axis, 'dataset')
if bins:
histogram = histogram.rebin(axis, bins)
if overlay: overlay = overlay.rebin(axis, bins)
y_max = histogram[bkg_sel].sum("dataset").values(overflow='over')[()].max()
print(histogram[bkg_sel].sum("dataset").values(overflow='over')[()].max())
MC_total = histogram[bkg_sel].sum("dataset").values(
overflow='over')[()].sum()
Data_total = 0
if data:
Data_total = histogram[data_sel].sum("dataset").values(
overflow='over')[()].sum()
#observation = histogram[data[0]].sum('dataset').copy()
#first = True
#for d in data:
# print (d)
# if not first:
# observation.add(histogram[d].sum('dataset'))
# print ("adding")
# first = False
print("Data:", round(Data_total, 0), "MC:", round(MC_total, 2))
if normalize and data_sel:
scales = {process: Data_total / MC_total for process in processes}
histogram.scale(scales, axis='dataset')
else:
scales = {}
if shape:
scales = {
process: 1 / histogram[process].sum("dataset").values(
overflow='over')[()].sum()
for process in processes
}
histogram.scale(scales, axis='dataset')
if data:
fig, (ax, rax) = plt.subplots(2,
1,
figsize=(10, 10),
gridspec_kw={"height_ratios": (3, 1)},
sharex=True)
else:
fig, ax = plt.subplots(1, 1, figsize=(10, 10))
if signals:
for sig in signals:
ax = hist.plot1d(histogram[sig],
overlay="dataset",
ax=ax,
stack=False,
overflow='over',
clear=False,
line_opts=line_opts,
fill_opts=None,
binwnorm=binwnorm)
if overlay:
ax = hist.plot1d(overlay,
overlay="dataset",
ax=ax,
stack=False,
overflow='over',
clear=False,
line_opts=line_opts,
fill_opts=None,
binwnorm=binwnorm)
if shape:
ax = hist.plot1d(histogram[bkg_sel],
overlay="dataset",
ax=ax,
stack=False,
overflow='over',
clear=False,
line_opts=line_opts,
fill_opts=None,
binwnorm=binwnorm)
else:
ax = hist.plot1d(histogram[bkg_sel],
overlay="dataset",
ax=ax,
stack=True,
overflow='over',
clear=False,
line_opts=None,
fill_opts=fill_opts,
order=(order if order else processes),
binwnorm=binwnorm)
if data:
ax = hist.plot1d(histogram[data_sel].sum("dataset"),
ax=ax,
overflow='over',
error_opts=data_err_opts,
clear=False,
binwnorm=binwnorm)
#ax = hist.plot1d(observation, ax=ax, overflow='over', error_opts=data_err_opts, clear=False)
hist.plotratio(
num=histogram[data_sel].sum("dataset"),
denom=histogram[bkg_sel].sum("dataset"),
ax=rax,
error_opts=data_err_opts,
denom_fill_opts=
None, # triggers this: https://github.com/CoffeaTeam/coffea/blob/master/coffea/hist/plot.py#L376
guide_opts={},
unc='num',
#unc=None,
overflow='over')
handles, labels = ax.get_legend_handles_labels()
updated_labels = []
for handle, label in zip(handles, labels):
try:
if label is None or label == 'None':
updated_labels.append("Observation")
handle.set_color('#000000')
else:
updated_labels.append(new_labels[label])
handle.set_color(new_colors[label])
except:
pass
if data:
if ratio_range:
rax.set_ylim(*ratio_range)
else:
rax.set_ylim(0.1, 1.9)
rax.set_ylabel('Obs./Pred.')
if axis_label:
rax.set_xlabel(axis_label)
ax.set_xlabel(axis_label)
ax.set_ylabel(y_axis_label)
if not binwnorm:
if not shape:
addUncertainties(ax,
axis,
histogram,
bkg_sel,
[output[histo + '_' + x] for x in upHists],
[output[histo + '_' + x] for x in downHists],
overflow='over',
rebin=bins,
ratio=False,
scales=scales)
if data:
addUncertainties(rax,
axis,
histogram,
bkg_sel,
[output[histo + '_' + x] for x in upHists],
[output[histo + '_' + x] for x in downHists],
overflow='over',
rebin=bins,
ratio=True,
scales=scales)
if log:
ax.set_yscale('log')
y_mult = 1.7 if not log else 100
if ymax:
ax.set_ylim(0.01, ymax)
else:
y_max = y_max * y_mult * (Data_total /
MC_total) if data else y_max * y_mult
ax.set_ylim(0.01, y_max if not shape else 2)
#if binwnorm: ax.set_ylim(0.5)
ax.legend(
loc='upper right',
ncol=2,
borderaxespad=0.0,
labels=updated_labels,
handles=handles,
)
plt.subplots_adjust(hspace=0)
if use_label:
if len(data) > 0:
fig.text(0.0,
0.995,
'$\\bf{CMS}$ Preliminary',
fontsize=25,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
else:
fig.text(0.0,
0.995,
'$\\bf{CMS}$ Simulation',
fontsize=25,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
fig.text(0.6,
0.995,
r'$%.1f\ fb^{-1}$ (13 TeV)' % (lumi),
fontsize=25,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
if normalize:
fig.text(0.55,
0.65,
'Data/MC = %s' % round(Data_total / MC_total, 2),
fontsize=20,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
if save:
#finalizePlotDir(outdir)
fig.savefig("{}.pdf".format(save))
fig.savefig("{}.png".format(save))
#fig.savefig(save)
print("Figure saved in:", save)
def test_plotratio():
# histogram creation and manipulation
from coffea import hist
# matplotlib
import matplotlib.pyplot as plt
plt.switch_backend("agg")
lepton_kinematics = fill_lepton_kinematics()
# Add some pseudodata to a pt histogram so we can make a nice data/mc plot
pthist = lepton_kinematics.sum("eta")
bin_values = pthist.axis("pt").centers()
poisson_means = pthist.sum("flavor").values()[()]
values = np.repeat(bin_values, np.random.poisson(poisson_means))
pthist.fill(flavor="pseudodata", pt=values)
# Set nicer labels, by accessing the string bins' label property
pthist.axis("flavor").index("electron").label = "e Flavor"
pthist.axis("flavor").index("muon").label = r"$\mu$ Flavor"
pthist.axis("flavor").index(
"pseudodata").label = r"Pseudodata from e/$\mu$"
# using regular expressions on flavor name to select just the data
# another method would be to fill a separate data histogram
import re
notdata = re.compile("(?!pseudodata)")
# make a nice ratio plot
plt.rcParams.update({
"font.size": 14,
"axes.titlesize": 18,
"axes.labelsize": 18,
"xtick.labelsize": 12,
"ytick.labelsize": 12,
})
fig, (ax, rax) = plt.subplots(2,
1,
figsize=(7, 7),
gridspec_kw={"height_ratios": (3, 1)},
sharex=True)
fig.subplots_adjust(hspace=0.07)
# Here is an example of setting up a color cycler to color the various fill patches
# http://colorbrewer2.org/#type=qualitative&scheme=Paired&n=6
from cycler import cycler
colors = ["#a6cee3", "#1f78b4", "#b2df8a", "#33a02c", "#fb9a99", "#e31a1c"]
ax.set_prop_cycle(cycler(color=colors))
fill_opts = {"edgecolor": (0, 0, 0, 0.3), "alpha": 0.8}
error_opts = {
"label": "Stat. Unc.",
"hatch": "///",
"facecolor": "none",
"edgecolor": (0, 0, 0, 0.5),
"linewidth": 0,
}
data_err_opts = {
"linestyle": "none",
"marker": ".",
"markersize": 10.0,
"color": "k",
"elinewidth": 1,
}
hist.plot1d(
pthist[notdata],
overlay="flavor",
ax=ax,
clear=False,
stack=True,
line_opts=None,
fill_opts=fill_opts,
error_opts=error_opts,
)
hist.plot1d(
pthist["pseudodata"],
overlay="flavor",
ax=ax,
clear=False,
error_opts=data_err_opts,
)
ax.autoscale(axis="x", tight=True)
ax.set_ylim(0, None)
ax.set_xlabel(None)
ax.legend()
hist.plotratio(
pthist["pseudodata"].sum("flavor"),
pthist[notdata].sum("flavor"),
ax=rax,
error_opts=data_err_opts,
denom_fill_opts={},
guide_opts={},
unc="num",
)
rax.set_ylabel("Ratio")
rax.set_ylim(0, 2)
plt.text(
0.0,
1.0,
"☕",
fontsize=28,
horizontalalignment="left",
verticalalignment="bottom",
transform=ax.transAxes,
)
plt.text(
1.0,
1.0,
r"1 fb$^{-1}$ (?? TeV)",
fontsize=16,
horizontalalignment="right",
verticalalignment="bottom",
transform=ax.transAxes,
)
def ratio_plot(num, denom):
# make a nice ratio plot, adjusting some font sizes
plt.rcParams.update({
'font.size': 16,
'axes.titlesize': 18,
'axes.labelsize': 18,
'xtick.labelsize': 14,
'ytick.labelsize': 14
})
fig, (ax, rax) = plt.subplots(
nrows=2,
ncols=1,
figsize=(10,10),
gridspec_kw={"height_ratios": (3, 1)},
sharex=True
)
fig.subplots_adjust(hspace=.07)
# Here is an example of setting up a color cycler to color the various fill patches
# We get the colors from this useful utility: http://colorbrewer2.org/
from cycler import cycler
colors = ['#a6cee3','#1f78b4','#b2df8a','#33a02c','#fb9a99','#e31a1c','#fdbf6f','#ff7f00','#cab2d6','#6a3d9a']
ax.set_prop_cycle(cycler(color=colors))
fill_opts = {
'edgecolor': (0,0,0,0.3),
'alpha': 0.8
}
error_opts = {
'label': 'Stat. Unc.',
'hatch': '///',
'facecolor': 'none',
'edgecolor': (0,0,0,.5),
'linewidth': 0
}
data_err_opts = {
'linestyle': 'none',
'marker': '.',
'markersize': 10.,
'color': 'k',
'elinewidth': 1,
}
# plot the MC first
hist.plot1d(
num,
ax=ax,
clear=False,
line_opts=None,
fill_opts=fill_opts,
error_opts=error_opts
)
# now the pseudodata, setting clear=False to avoid overwriting the previous plot
hist.plot1d(
denom,
ax=ax,
clear=False,
fill_opts=fill_opts,
error_opts=error_opts
)
ax.autoscale(axis='x', tight=True)
ax.set_ylim(0, None)
ax.set_xlabel(None)
# now we build the ratio plot
hist.plotratio(
num=num,
denom=denom,
ax=rax,
error_opts=data_err_opts,
denom_fill_opts={},
guide_opts={},
unc='num'
)
rax.set_ylabel('Ratio')
rax.set_ylim(0, 15)
return ax, rax
def drawSolo(h,
sel,
var_name,
var_label,
plottitle,
lumifb,
vars_cut,
regionsel,
savename,
plotData=False,
plotDensity=False):
#printyield(h,['zqq','wqq'],['qcd'],'n2ddt')
#printyield(h,['zqq','wqq'],['qcd'],'in_v3_ddt')
#printyield(h,['zqq','wqq'],['qcd'],'gruddt')
exceptions = ['process', var_name]
for var, val in vars_cut.items():
exceptions.append(var)
if (regionsel is not ''):
exceptions.append('region')
x = h.sum(*[ax for ax in h.axes() if ax.name not in exceptions],
overflow='allnan')
mc = h.remove([
'JetHT',
'SingleMuon',
], 'process')
mc_processes = ['zqq', 'wqq', 'qcd', 'st', 'wlnu',
'tt'] #'tttoleptonic','tttosemileptonic','tttohadronic']
data_processes = [
'SingleMuon',
'JetHT',
]
if 'signal' in regionsel:
data = h.remove(
mc_processes + ['SingleMuon'], 'process'
) # if 'signal' in regionsel else mc_processes + ['JetHT'],'process')
mc = h.remove([
'JetHT',
'SingleMuon',
], 'process')
#kfactor = QCDkfactor(data,mc)
x.scale({'qcd': 0.9}, 'process')
print('applying QCD k factor:', kfactor)
for reg in regionsel:
print('integrating ', reg)
x = x.integrate('region', reg)
#x.remove([p for p in h.axis('process').identifiers() if reg not in str(p)], 'region')
if 'vselection' in regionsel:
print(x.integrate('process', 'SingleMuon').values()[()])
data = np.sum(x.integrate('process', 'SingleMuon').values()[()])
ttyield = np.sum(x.integrate('process', 'tt').values()[()])
qcdyield = np.sum(x.integrate('process', 'qcd').values()[()])
wlnuyield = np.sum(x.integrate('process', 'wlnu').values()[()])
styield = np.sum(x.integrate('process', 'st').values()[()])
ttkfac = (data - qcdyield - wlnuyield - styield) / ttyield
x.scale({'tt': ttkfac}, 'process')
print('applying tt k factor', ttkfac)
for var, val in vars_cut.items():
if var != var_name:
print('integrating ', var, val[0], val[1])
x = x.integrate(var, slice(val[0], val[1]), overflow='none')
#x = x.remove(['noselection','signal'] if 'ttbar' in regionsel else ['ttbar_muoncontrol'] ,'region')
#print(x.axis('region').identifiers())
#x = x.sum('region')
if var_name in vars_cut.keys():
x = x[:, vars_cut[var_name][0]:vars_cut[var_name][1]]
xaxis = var_name
x.axis(xaxis).label = var_label
mc = x.remove(data_processes, 'process')
mc.axis('process').sorting = 'integral'
data = x.remove(
mc_processes +
['SingleMuon'] if 'signal' in regionsel else mc_processes + ['JetHT'],
'process')
for ih, hkey in enumerate(mc.identifiers('process')):
mc.identifiers('process')[ih].label = process_latex[hkey.name]
if plotData:
fig, (ax, rax) = plt.subplots(nrows=2,
ncols=1,
figsize=(11, 11),
gridspec_kw={"height_ratios": (3, 1)},
sharex=True)
fig.subplots_adjust(hspace=.02)
else:
fig, ax = plt.subplots()
hist.plot1d(mc,
overlay='process',
ax=ax,
stack=True if not plotDensity else False,
clear=False,
fill_opts=fill_opts,
error_opts=err_opts if not plotDensity else None,
overflow='allnan',
density=plotDensity)
tot = mc.sum('process')
#hist.plot1d(tot,
# clear=False,
# fill_opts=fill_tot_opts,
# )
if plotData:
hist.plot1d(data,
overlay='process',
ax=ax,
clear=False,
error_opts=data_err_opts,
overflow='allnan')
hist.plotratio(num=data.sum('process'),
denom=tot,
ax=rax,
clear=False,
overflow='allnan',
error_opts=data_err_opts,
unc='num')
rax.set_ylabel('Data/MC')
rax.set_ylim(0, 2)
ax.set_ylabel('Events')
ax.autoscale(axis='y', tight=False)
#ax.set_xlim(20, 200)
#ax.ticklabel_format(axis='x', style='sci')
old_handles, old_labels = ax.get_legend_handles_labels()
leg = ax.legend(handles=old_handles,
labels=old_labels,
title=r'$%s$' % plottitle if plottitle else None,
loc='upper right',
title_fontsize=14,
fontsize=12,
facecolor='white',
framealpha=0.2)
lumi = plt.text(1.,
1.,
r"%.1f fb$^{-1}$ (13 TeV)" % lumifb,
fontsize=16,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
cmstext = plt.text(0.,
1.,
"CMS",
fontsize=20,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes,
fontweight='bold')
if plotData:
addtext = plt.text(0.085,
1.,
"Preliminary",
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes,
style='italic')
else:
addtext = plt.text(0.085,
1.,
"Simulation Preliminary",
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes,
style='italic')
#hep.cms.cmslabel(ax, data=False, paper=False, year='2017')
print("solo_%s_%s_%s_lumi%i.pdf" % (sel, var_name, savename, lumifb))
fig.savefig("solo_%s_%s_%s_lumi%i.pdf" % (sel, var_name, savename, lumifb))
fig.savefig("solo_%s_%s_%s_lumi%i.png" % (sel, var_name, savename, lumifb))
ax.semilogy()
minvals = []
#for xd in x.values():
# minvals.append(min(np.trim_zeros(x.values()[xd])))
#decsplit = str(min(minvals)).split('.')
#if (int(decsplit[0])==0):
# logmin = 0.1**float(len(decsplit[1])-len(decsplit[1].lstrip('0'))+2)
#else:
# logmin = 10.**float(len(decsplit[0])-1)
ax.set_ylim(0.1 if plotDensity else 0.1, None)
print("solo_%s_%s_%s_lumi%i_logy.pdf" % (sel, var_name, savename, lumifb))
fig.savefig("solo_%s_%s_%s_lumi%i_logy.pdf" %
(sel, var_name, savename, lumifb))
fig.savefig("solo_%s_%s_%s_lumi%i_logy.png" %
(sel, var_name, savename, lumifb))
def recoseleff_tag():
for btype in ["Bu", "Bs", "Bd"]:
fig, ax = plt.subplots(2, 1, figsize=(
10, 12)) #, gridspec_kw={"height_ratios": (3, 1)}, sharex=True)
plt.style.use(mplhep.style.ROOT)
if btype == "Bu":
h_truthpt = histograms["Bu"]["TruthBuToKMuMu_pt"].integrate(
"dataset", ["Bu2KJpsi2KMuMu_inclusive"])
elif btype == "Bs":
h_truthpt = histograms["Bs"]["TruthBsToKKMuMu_pt"].integrate(
"dataset", ["Bs2PhiJpsi2KKMuMu_inclusive"])
elif btype == "Bd":
h_truthpt = histograms["Bd"]["TruthBdToKPiMuMu_pt"].integrate(
"dataset", ["Bd2KstarJpsi2KPiMuMu_inclusive"])
else:
sys.exit(1)
# Legend entries
h_truthpt.axis("selection").index("inclusive").label = "Inclusive"
h_truthpt.axis("selection").index("matched").label = "Reco matched"
h_truthpt.axis("selection").index(
"matched_sel").label = "Reco matched * selection"
h_truthpt.axis("selection").index(
"matched_tag").label = "Reco matched * selection * tag"
# Top plot
hist.plot1d(h_truthpt[(["inclusive"]), :],
ax=ax[0],
clear=False,
overlay="selection",
line_opts={"color": "black"})
hist.plot1d(h_truthpt[(["matched"]), :],
ax=ax[0],
clear=False,
overlay="selection",
line_opts={"color": "red"})
hist.plot1d(h_truthpt[(["matched_sel"]), :],
ax=ax[0],
clear=False,
overlay="selection",
line_opts={"color": "green"})
hist.plot1d(h_truthpt[(["matched_tag"]), :],
ax=ax[0],
clear=False,
overlay="selection",
line_opts={"color": "blue"})
ax[0].set_ylim(1., 1.e6)
ax[0].set_yscale("log")
# Bottom plot
h_truthpt_inclusive = h_truthpt.integrate("selection", (["inclusive"]))
h_truthpt_matched = h_truthpt.integrate("selection", (["matched"]))
h_truthpt_matched_sel = h_truthpt.integrate("selection",
(["matched_sel"]))
h_truthpt_matched_probe = h_truthpt.integrate("selection",
(["matched_tag"]))
h_truthpt_matched.label = "Efficiency"
hist.plotratio(
num=h_truthpt_matched,
denom=h_truthpt_inclusive,
ax=ax[1],
unc="clopper-pearson",
clear=True,
error_opts={
'color': 'red',
'marker': '.'
},
)
h_truthpt_matched_sel.label = "Efficiency"
hist.plotratio(
num=h_truthpt_matched_sel,
denom=h_truthpt_inclusive,
ax=ax[1],
unc="clopper-pearson",
clear=False,
error_opts={
'color': 'green',
'marker': '.'
},
)
h_truthpt_matched_probe.label = "Efficiency"
hist.plotratio(
num=h_truthpt_matched_probe,
denom=h_truthpt_inclusive,
ax=ax[1],
unc="clopper-pearson",
clear=False,
error_opts={
'color': 'blue',
'marker': '.'
},
)
ax[0].legend(fontsize=14)
ax[1].set_ylim(0., 0.4)
plt.tight_layout()
fig.savefig(f"{figure_directory}/recosel_efficiency_tag_{btype}.png")
def make_plot(acc,
region,
distribution,
year,
data,
mc,
signal=None,
outdir='./output/stack/',
integrate=None,
ylim=None,
xlim=None,
rylim=None,
tag=None,
output_format='pdf',
ratio=True,
mcscale=1):
"""Creates a data vs MC comparison plot
:param acc: Accumulator (processor output)
:type acc: coffea.processor.accumulator
"""
# Rebin
s = Style()
h = copy.deepcopy(acc[distribution])
if region.startswith("sr"):
h.scale(
{
ds: (mcscale if mc.match(ds) else 1)
for ds in map(str,
h.axis("dataset").identifiers())
},
axis='dataset')
assert (h)
try:
newax = s.get_binning(distribution, region)
h = h.rebin(h.axis(newax.name), newax)
except KeyError:
pass
# Integrate over an extra axis
inte_tag = ""
if integrate:
(inte_axis, inte_low, inte_high) = integrate
h = h.integrate(inte_axis,
slice(inte_low,
inte_high)) #can add an overflow option here
inte_tag += "_" + inte_axis + "_" + str(inte_low) + "_" + str(
inte_high)
# Pick the region we want to look at
# E.g. cr_2m_j = Di-Muon control region with monojet selection
h = h.integrate(h.axis('region'), region)
# Plotting
# Add ratio plot at the bottom if specified (default)
# Otherwise just plot the histogram
if ratio:
fig, (ax, rax) = plt.subplots(2,
1,
figsize=(7, 7),
gridspec_kw={"height_ratios": (3, 1)},
sharex=True)
else:
fig, ax = plt.subplots(1, 1, figsize=(7, 5))
data_err_opts = {
'linestyle': 'none',
'marker': '.',
'markersize': 10.,
'color': 'k',
'elinewidth': 1,
}
signal_err_opts = {
#'linestyle':'-',
'color': 'crimson',
'elinewidth': 1,
}
# Plot single muon data
# Note the syntax we use to pick the data set
if data:
hist.plot1d(h[data],
overlay='dataset',
error_opts=data_err_opts,
ax=ax,
overflow='all',
binwnorm=1)
if signal:
hist.plot1d(h[signal],
overlay='dataset',
error_opts=signal_err_opts,
ax=ax,
overflow='all',
binwnorm=1,
clear=False)
# Plot MC background samples
# Here we use a regular expression to match
# data sets we want
if mc != None:
hist.plot1d(h[mc],
overlay='dataset',
stack=True,
clear=False,
overflow='all',
ax=ax,
binwnorm=1)
# Apply correct colors to BG histograms
handles, labels = ax.get_legend_handles_labels()
new_labels = []
for handle, label in zip(handles, labels):
col = None
for k, v in colors.items():
if re.match(k, label):
col = v
break
if col:
handle.set_color(col)
handle.set_linestyle('-')
handle.set_edgecolor('k')
l = None
channel = channel_name(region)
# Pick the proper legend labels for the channel
if channel == 'VBF':
legend_labels_to_use = legend_labels['VBF']
elif channel in ['Monojet', 'Mono-V']:
legend_labels_to_use = legend_labels['Monojet/Mono-V']
# Add in the common labels
legend_labels_to_use.update(legend_labels['Common'])
for k, v in legend_labels_to_use.items():
if re.match(k, label):
l = v
new_labels.append(l if l else label)
# Update legend
try:
region_name = s.region_names[region]
except KeyError:
region_name = region
ax.legend(title=region_name, ncol=2, handles=handles, labels=new_labels)
# Ratio plot
if data and ratio:
hist.plotratio(h[data].integrate('dataset'),
h[mc].integrate('dataset'),
ax=rax,
denom_fill_opts={},
guide_opts={},
unc='num',
overflow='all',
error_opts=data_err_opts)
ax.text(1.,
0.,
distribution,
fontsize=10,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
fig.text(0.,
1.,
'$\\bf{CMS}$ internal',
fontsize=14,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
fig.text(1.,
1.,
f'{channel_name(region)}, {lumi(year):.1f} fb$^{{-1}}$ ({year})',
fontsize=14,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
# Aesthetics
ax.set_yscale("log")
ax.set_ylabel('Events / GeV')
plot_settings = style.plot_settings()
if region in plot_settings.keys():
plot_settings = plot_settings[region]
if distribution in plot_settings.keys():
plot_settings = plot_settings[distribution]
if ylim:
if ylim == "auto":
width = np.diff([x for x in h.axes()
if "dataset" not in x.name][0].edges())
vmc = h[mc].integrate("dataset").values()[()] / width
try:
vdata = h[data].integrate("dataset").values()[()] / width
except:
vdata = vmc
if signal:
vsig = h[signal].integrate("dataset").values()[()] / width
else:
vsig = vmc
ax.set_ylim(
0.5 * min([
np.min(vmc[vmc > 0]),
np.min(vdata[vdata > 0]),
np.min(vsig[vsig > 0])
]),
1e2 *
max([np.max(vmc), np.max(vdata),
np.min(vsig)]),
)
else:
ax.set_ylim(ylim[0], ylim[1])
elif 'ylim' in plot_settings.keys():
ax.set_ylim(plot_settings['ylim'])
else:
ax.set_ylim(1e-1, 1e6)
if xlim:
ax.set_xlim(xlim[0], xlim[1])
elif 'xlim' in plot_settings.keys():
ax.set_xlim(plot_settings['xlim'])
if ratio:
if rylim:
rax.set_ylim(*rylim)
else:
rax.set_ylim(0.5, 1.5)
loc1 = matplotlib.ticker.MultipleLocator(base=0.2)
loc2 = matplotlib.ticker.MultipleLocator(base=0.1)
rax.yaxis.set_major_locator(loc1)
rax.yaxis.set_minor_locator(loc2)
rax.grid(axis='y', which='minor', linestyle='--')
rax.grid(axis='y', which='major', linestyle='--')
rax.set_ylabel('Data / MC')
if not os.path.exists(outdir):
os.makedirs(outdir)
for form in output_format.split(','):
outpath = pjoin(
outdir,
f"{region}_{distribution}{inte_tag}_{tag + '_' if tag else ''}{year}.{form}"
)
fig.savefig(outpath)
print(f"Saved plot file in {outpath}")
plt.close('all')
def test_plotratio():
# histogram creation and manipulation
from coffea import hist
# matplotlib
import matplotlib as mpl
mpl.use('Agg')
import matplotlib.pyplot as plt
lepton_kinematics = fill_lepton_kinematics()
# Add some pseudodata to a pt histogram so we can make a nice data/mc plot
pthist = lepton_kinematics.sum('eta')
bin_values = pthist.axis('pt').centers()
poisson_means = pthist.sum('flavor').values()[()]
values = np.repeat(bin_values, np.random.poisson(poisson_means))
pthist.fill(flavor='pseudodata', pt=values)
# Set nicer labels, by accessing the string bins' label property
pthist.axis('flavor').index('electron').label = 'e Flavor'
pthist.axis('flavor').index('muon').label = r'$\mu$ Flavor'
pthist.axis('flavor').index(
'pseudodata').label = r'Pseudodata from e/$\mu$'
# using regular expressions on flavor name to select just the data
# another method would be to fill a separate data histogram
import re
notdata = re.compile('(?!pseudodata)')
# make a nice ratio plot
plt.rcParams.update({
'font.size': 14,
'axes.titlesize': 18,
'axes.labelsize': 18,
'xtick.labelsize': 12,
'ytick.labelsize': 12
})
fig, (ax, rax) = plt.subplots(2,
1,
figsize=(7, 7),
gridspec_kw={"height_ratios": (3, 1)},
sharex=True)
fig.subplots_adjust(hspace=.07)
# Here is an example of setting up a color cycler to color the various fill patches
# http://colorbrewer2.org/#type=qualitative&scheme=Paired&n=6
from cycler import cycler
colors = ['#a6cee3', '#1f78b4', '#b2df8a', '#33a02c', '#fb9a99', '#e31a1c']
ax.set_prop_cycle(cycler(color=colors))
fill_opts = {'edgecolor': (0, 0, 0, 0.3), 'alpha': 0.8}
error_opts = {
'label': 'Stat. Unc.',
'hatch': '///',
'facecolor': 'none',
'edgecolor': (0, 0, 0, .5),
'linewidth': 0
}
data_err_opts = {
'linestyle': 'none',
'marker': '.',
'markersize': 10.,
'color': 'k',
'elinewidth': 1,
'emarker': '_'
}
hist.plot1d(pthist[notdata],
overlay="flavor",
ax=ax,
clear=False,
stack=True,
line_opts=None,
fill_opts=fill_opts,
error_opts=error_opts)
hist.plot1d(pthist['pseudodata'],
overlay="flavor",
ax=ax,
clear=False,
error_opts=data_err_opts)
ax.autoscale(axis='x', tight=True)
ax.set_ylim(0, None)
ax.set_xlabel(None)
leg = ax.legend()
hist.plotratio(pthist['pseudodata'].sum("flavor"),
pthist[notdata].sum("flavor"),
ax=rax,
error_opts=data_err_opts,
denom_fill_opts={},
guide_opts={},
unc='num')
rax.set_ylabel('Ratio')
rax.set_ylim(0, 2)
coffee = plt.text(0.,
1.,
u"☕",
fontsize=28,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
lumi = plt.text(1.,
1.,
r"1 fb$^{-1}$ (?? TeV)",
fontsize=16,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
clear=False,
#error_opts = styles.data_err_opts
)
ax.autoscale(axis='x', tight=True)
ax.set_ylim(0, None)
ax.set_xlabel(None)
ax.set_ylabel('Counts')
#leg = ax.legend()
if not args.isSig:
cofplt.plotratio(grouped['data'].sum("process"),
grouped[mc].sum("process"),
ax=rax,
error_opts=styles.data_err_opts,
denom_fill_opts={},
guide_opts={},
unc='num')
rax.set_ylabel('Ratio')
rax.set_xlabel(x_title)
rax.set_ylim(0, 2)
rax.set_yticks([0, 0.5, 1, 1.5, 2])
lumi = plt.text(1.,
1., f'{year["lumi"]/1000}'
r" fb$^{-1}$ (13 TeV)",
fontsize=16,
horizontalalignment='right',
verticalalignment='bottom',
def plotWithRatio(h,
hData,
overlay,
invertStack=True,
lumi=35.9,
label="CMS Preliminary",
colors=None,
ratio=[0.5, 1.5],
xRange=None,
yRange=None,
logY=False,
extraText=None):
# make a nice ratio plot
plt.rcParams.update({
'font.size': 14,
'axes.titlesize': 18,
'axes.labelsize': 18,
'xtick.labelsize': 12,
'ytick.labelsize': 12
})
if not hData is None:
fig, (ax, rax) = plt.subplots(2,
1,
figsize=(7, 7),
gridspec_kw={"height_ratios": (3, 1)},
sharex=True)
fig.subplots_adjust(hspace=.07)
else:
fig, ax = plt.subplots(1, 1, figsize=(
7, 7)) #, gridspec_kw={"height_ratios": (3, 1)}, sharex=True)
# Here is an example of setting up a color cycler to color the various fill patches
# http://colorbrewer2.org/#type=qualitative&scheme=Paired&n=6
from cycler import cycler
if colors is None:
colors = [
'#a6cee3', '#1f78b4', '#b2df8a', '#33a02c', '#fb9a99', '#e31a1c',
'#fdbf6f', '#ff7f00', '#cab2d6', '#6a3d9a', '#ffff99', '#b15928'
]
# colors = ['#a6cee3','#1f78b4','#b2df8a','#33a02c','#fb9a99','#e31a1c','#fdbf6f','#ff7f00','#cab2d6','#6a3d9a']
if invertStack:
_n = len(h.identifiers(overlay)) - 1
colors = colors[_n::-1]
ax.set_prop_cycle(cycler(color=colors))
fill_opts = {'edgecolor': (0, 0, 0, 0.3), 'alpha': 0.8}
error_opts = {
'label': 'Stat. Unc.',
'hatch': '///',
'facecolor': 'none',
'edgecolor': (0, 0, 0, .5),
'linewidth': 0
}
data_err_opts = {
'linestyle': 'none',
'marker': '.',
'markersize': 10.,
'color': 'k',
'elinewidth': 1,
'emarker': '_'
}
if invertStack:
h._axes[0]._sorted.reverse()
hist.plot1d(
h,
overlay=overlay,
# invertStack=True,
ax=ax,
clear=False,
stack=True,
line_opts=None,
fill_opts=fill_opts,
error_opts=error_opts)
if invertStack:
h._axes[0]._sorted.reverse()
if not hData is None:
hist.plot1d(hData,
overlay=overlay,
ax=ax,
clear=False,
error_opts=data_err_opts)
ax.autoscale(axis='x', tight=True)
ax.set_ylim(0, None)
ax.set_xlabel(None)
if invertStack:
handles, labels = ax.get_legend_handles_labels()
if hData is None:
handles = handles[-2::-1] + handles[-1:-2:-1]
labels = labels[-2::-1] + labels[-1:-2:-1]
else:
handles = handles[-1:-2:-1] + handles[-3::-1] + handles[-2:-3:-1]
labels = labels[-1:-2:-1] + labels[-3::-1] + labels[-2:-3:-1]
ax.legend(handles, labels, bbox_to_anchor=(1., 1.), loc='upper left')
else:
leg = ax.legend(loc='upper right')
ax.legend(bbox_to_anchor=(1., 1.))
if not hData is None:
hist.plotratio(hData.sum(overlay),
h.sum(overlay),
ax=rax,
error_opts=data_err_opts,
denom_fill_opts={},
guide_opts={},
unc='num')
rax.set_ylabel('Ratio')
rax.set_ylim(ratio[0], ratio[1])
if logY:
ax.set_yscale("log")
ax.set_ylim(1, ax.get_ylim()[1] * 5)
if not xRange is None:
ax.set_xlim(xRange[0], xRange[1])
if not yRange is None:
ax.set_ylim(yRange[0], yRange[1])
CMS = plt.text(0.,
1.,
r"$\bf{CMS}$ Preliminary",
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
if not extraText is None:
extraLabel = plt.text(0.02,
.99,
extraText,
fontsize=16,
horizontalalignment='left',
verticalalignment='top',
transform=ax.transAxes)
ax.set_ylim(0, ax.get_ylim()[1] * 1.1)
lumi = plt.text(1.,
1.,
r"%.1f fb$^{-1}$ (13 TeV)" % (lumi),
fontsize=16,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
def makePlot(output, histo, axis, bins=None, mc_sel=bkgonly, data_sel='MuonEG', normalize=True, log=False, save=False, axis_label=None, ratio_range=None, upHists=[], downHists=[], shape=False, ymax=False, new_colors=colors, new_labels=my_labels, order=None):
if save:
finalizePlotDir( '/'.join(save.split('/')[:-1]) )
if histo is None:
processes = [ p[0] for p in output.values().keys() if not p[0]=='MuonEG' ]
histogram = output.copy()
else:
processes = [ p[0] for p in output[histo].values().keys() if not p[0]=='MuonEG' ]
histogram = output[histo].copy()
histogram = histogram.project(axis, 'dataset')
if bins:
histogram = histogram.rebin(axis, bins)
y_max = histogram[mc_sel].sum("dataset").values(overflow='over')[()].max()
MC_total = histogram[mc_sel].sum("dataset").values(overflow='over')[()].sum()
Data_total = 0
if data_sel:
Data_total = histogram[data_sel].sum("dataset").values(overflow='over')[()].sum()
print ("Data:", round(Data_total,0), "MC:", round(MC_total,2))
if normalize and data_sel:
scales = { process: Data_total/MC_total for process in processes }
histogram.scale(scales, axis='dataset')
else:
scales = {}
if shape:
scales = { process: 1/histogram[process].sum("dataset").values(overflow='over')[()].sum() for process in processes }
histogram.scale(scales, axis='dataset')
if data_sel:
fig, (ax, rax) = plt.subplots(2,1,figsize=(10,10), gridspec_kw={"height_ratios": (3, 1)}, sharex=True)
else:
fig, ax = plt.subplots(1,1,figsize=(10,10) )
if shape:
ax = hist.plot1d(histogram[mc_sel], overlay="dataset", ax=ax, stack=False, overflow='over', clear=False, line_opts=line_opts, fill_opts=None)
else:
ax = hist.plot1d(histogram[mc_sel], overlay="dataset", ax=ax, stack=True, overflow='over', clear=False, line_opts=None, fill_opts=fill_opts, order=(order if order else processes))
if data_sel:
ax = hist.plot1d(histogram[data_sel], overlay="dataset", ax=ax, overflow='over', error_opts=data_err_opts, clear=False)
hist.plotratio(
num=histogram[data_sel].sum("dataset"),
denom=histogram[mc_sel].sum("dataset"),
ax=rax,
error_opts=data_err_opts,
denom_fill_opts=None, # triggers this: https://github.com/CoffeaTeam/coffea/blob/master/coffea/hist/plot.py#L376
guide_opts={},
unc='num',
#unc=None,
overflow='over'
)
handles, labels = ax.get_legend_handles_labels()
updated_labels = []
for handle, label in zip(handles, labels):
#print (label)
try:
updated_labels.append(new_labels[label])
if not label=='MuonEG':
handle.set_color(new_colors[label])
except:
pass
if data_sel:
if ratio_range:
rax.set_ylim(*ratio_range)
else:
rax.set_ylim(0.1,1.9)
rax.set_ylabel('Obs./Pred.')
if axis_label:
rax.set_xlabel(axis_label)
ax.set_xlabel(axis_label)
ax.set_ylabel('Events')
if not shape:
addUncertainties(ax, axis, histogram, mc_sel, [output[histo+'_'+x] for x in upHists], [output[histo+'_'+x] for x in downHists], overflow='over', rebin=bins, ratio=False, scales=scales)
if data_sel:
addUncertainties(rax, axis, histogram, mc_sel, [output[histo+'_'+x] for x in upHists], [output[histo+'_'+x] for x in downHists], overflow='over', rebin=bins, ratio=True, scales=scales)
if log:
ax.set_yscale('log')
y_mult = 1.3 if not log else 100
if ymax:
ax.set_ylim(0.01, ymax)
else:
ax.set_ylim(0.01,y_max*y_mult if not shape else 2)
ax.legend(
loc='upper right',
ncol=2,
borderaxespad=0.0,
labels=updated_labels,
handles=handles,
)
plt.subplots_adjust(hspace=0)
fig.text(0.0, 0.995, '$\\bf{CMS}$ Preliminary', fontsize=20, horizontalalignment='left', verticalalignment='bottom', transform=ax.transAxes )
fig.text(0.8, 0.995, '13 TeV', fontsize=20, horizontalalignment='left', verticalalignment='bottom', transform=ax.transAxes )
if normalize:
fig.text(0.55, 0.65, 'Data/MC = %s'%round(Data_total/MC_total,2), fontsize=20, horizontalalignment='left', verticalalignment='bottom', transform=ax.transAxes )
if save:
#finalizePlotDir(outdir)
fig.savefig("{}.pdf".format(save))
fig.savefig("{}.png".format(save))
#fig.savefig(save)
print ("Figure saved in:", save)
print(iset)
print(icat)
title = iset + ' mistag ' + icat
filename = 'mistag_' + iset + '_' + icat + '.' + 'png'
print(outputs_unweighted[iset]['numerator'])
Numerator = outputs_unweighted[iset]['numerator'].integrate(
'anacat', icat).integrate('dataset', iset)
Denominator = outputs_unweighted[iset]['denominator'].integrate(
'anacat', icat).integrate('dataset', iset)
print(Numerator)
print(Denominator)
mistag = hist.plotratio(num=Numerator,
denom=Denominator,
error_opts={
'marker': '.',
'markersize': 10.,
'color': 'k',
'elinewidth': 1
},
unc='num')
plt.title(title)
plt.ylim(bottom=0, top=0.12)
plt.xlim(left=100, right=2500)
# ---- Better mistag plots are made in 'TTbarResCoffea_MistagAnalysis-BkgEst' python script ---- #
# ---- However, if one wants to save these raw plots, they may uncomment the following 5 lines ---- #
#plt.xticks(np.array([0, 500, 600, 700]))
#mistag.set_xscale('function', functions=(forward, inverse))
#mistag.set_xscale('log')
#plt.savefig(SaveDirectory+filename, bbox_inches="tight")
output = processor.run_uproot_job(
sigDS_2mu2e,
treename='ffNtuplizer/ffNtuple',
processor_instance=MuEffiResoProcessor(),
executor=processor.futures_executor,
executor_args=dict(workers=12, flatten=False),
chunksize=500000,
)
fig, ax = plt.subplots(figsize=(8, 6))
hist.plotratio(num=output['lxy'][longdecay].sum('dataset').integrate(
'reco', 'true'),
denom=output['lxy'][longdecay].sum('dataset').integrate(
'reco', 'inclusive'),
overflow='over',
error_opts={
'marker': 'o',
},
ax=ax,
label='PFMu+DSAMu')
hist.plotratio(num=output['lxy-pf'][longdecay].sum('dataset').integrate(
'reco', 'true'),
denom=output['lxy-pf'][longdecay].sum('dataset').integrate(
'reco', 'inclusive'),
overflow='over',
error_opts={
'marker': 'o',
'color': 'tab:red',
'fillstyle': 'none',
},
ax=ax,
sigDS,
treename='ffNtuplizer/ffNtuple',
processor_instance=MuLJVtxProcessor(),
executor=processor.futures_executor,
executor_args=dict(workers=12, flatten=False),
chunksize=500000,
)
## vertex efficiency
fig, ax = plt.subplots(figsize=(8, 6))
hist.plotratio(
num=output['vertexgood'][longdecay].sum('dataset').integrate(
'reco', 'vertexed'),
denom=output['vertexgood'][longdecay].sum('dataset').integrate(
'reco', 'inclusive'),
error_opts={
'marker': 'o',
'xerr': [5 / 2, 65 / 2, 630 / 2]
},
ax=ax,
)
ax.set_xscale('symlog')
ax.autoscale(axis='both', tight=True)
ax.set_ylim([0.9, 1.02])
ax.set_yticks(np.arange(0.9, 1.02, 0.02))
ax.set_xticks([0, 1, 2, 3, 4, 5, 10, 20, 30, 50, 70, 100, 300, 500, 700])
ax.set_xticklabels([
'0', '$10^0$', '2', '3', '4', '5', '$10^1$', '20', '30', '50', '70',
'$10^2$', '300', '500', '700'
])
ax.grid(axis='y', ls='--')
def plotWithRatio(h,
hData,
overlay,
stacked=True,
density=False,
invertStack=True,
lumi=35.9,
label="CMS Preliminary",
colors=None,
ratioRange=[0.5, 1.5],
xRange=None,
yRange=None,
logY=False,
extraText=None,
leg='upper right',
binwnorm=None):
# make a nice ratio plot
plt.rcParams.update({
'font.size': 14,
'axes.titlesize': 18,
'axes.labelsize': 18,
'xtick.labelsize': 12,
'ytick.labelsize': 12
})
if not hData is None:
fig, (ax, rax) = plt.subplots(2,
1,
figsize=(7, 7),
gridspec_kw={"height_ratios": (3, 1)},
sharex=True)
fig.subplots_adjust(hspace=.07)
else:
fig, ax = plt.subplots(1, 1, figsize=(
7, 7)) #, gridspec_kw={"height_ratios": (3, 1)}, sharex=True)
# Here is an example of setting up a color cycler to color the various fill patches
# http://colorbrewer2.org/#type=qualitative&scheme=Paired&n=6
from cycler import cycler
if not colors is None:
if invertStack:
_n = len(h.identifiers(overlay)) - 1
colors = colors[_n::-1]
ax.set_prop_cycle(cycler(color=colors))
fill_opts = {'edgecolor': (0, 0, 0, 0.3), 'alpha': 0.8}
error_opts = {
'label': 'Stat. Unc.',
'hatch': '///',
'facecolor': 'none',
'edgecolor': (0, 0, 0, .5),
'linewidth': 0
}
if not stacked:
error_opts = None
fill_opts = None
data_err_opts = {
'linestyle': 'none',
'marker': '.',
'markersize': 10.,
'color': 'k',
'elinewidth': 1,
# 'emarker': '_'
}
if invertStack:
if type(h._axes[0]) == hist.hist_tools.Cat:
h._axes[0]._sorted.reverse()
hist.plot1d(h,
overlay=overlay,
ax=ax,
clear=False,
stack=stacked,
density=density,
line_opts=None,
fill_opts=fill_opts,
error_opts=error_opts,
binwnorm=binwnorm)
# if invertStack:
# if type(h._axes[0])==hist.hist_tools.Cat:
# h._axes[0]._sorted.reverse()
if not hData is None:
hist.plot1d(
hData,
# overlay=overlay,
ax=ax,
clear=False,
error_opts=data_err_opts,
binwnorm=binwnorm)
ax.autoscale(axis='x', tight=True)
ax.set_ylim(0, None)
if not binwnorm is None:
ax.set_ylabel(f"<Counts/{binwnorm}>")
if '[' in ax.get_xlabel():
units = ax.get_xlabel().split('[')[-1].split(']')[0]
ax.set_ylabel(f"<Counts / {binwnorm} {units}>")
ax.set_xlabel(None)
if leg == "right":
leg_anchor = (1., 1.)
leg_loc = 'upper left'
elif leg == "upper right":
leg_anchor = (1., 1.)
leg_loc = 'upper right'
elif leg == "upper left":
leg_anchor = (0., 1.)
leg_loc = 'upper left'
if not leg is None:
handles, labels = ax.get_legend_handles_labels()
if not hData is None:
handles = handles[-1:] + handles[:-1]
labels = ['Data'] + labels[:-1]
ax.legend(handles, labels, bbox_to_anchor=leg_anchor, loc=leg_loc)
if not hData is None:
hist.plotratio(hData,
h.sum(overlay),
ax=rax,
error_opts=data_err_opts,
denom_fill_opts={},
guide_opts={},
unc='num')
rax.set_ylabel('Ratio')
rax.set_ylim(ratioRange[0], ratioRange[1])
if logY:
ax.set_yscale("log")
ax.set_ylim(1, ax.get_ylim()[1] * 5)
if not xRange is None:
ax.set_xlim(xRange[0], xRange[1])
if not yRange is None:
ax.set_ylim(yRange[0], yRange[1])
CMS = plt.text(0.,
1.,
r"$\bf{CMS}$ Preliminary",
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
if not extraText is None:
extraLabel = plt.text(0.02,
.99,
extraText,
fontsize=16,
horizontalalignment='left',
verticalalignment='top',
transform=ax.transAxes)
ax.set_ylim(0, ax.get_ylim()[1] * 1.1)
lumi = plt.text(1.,
1.,
r"%.1f fb$^{-1}$ (13 TeV)" % (lumi),
fontsize=16,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
def plot_data_mc(self, inclusive, channel, region, fig, var, gs, year='2016', normalize=True, logy=True, get_rates=False, mc_factor=1, save_to=''):
variable = get_variable(var)
data_sources = {
'data': ['data', 'data_A', 'data_B','data_C','data_D','data_E','data_F','data_G','data_H']
}
bkg_sources_by_region = {
"z-peak": {
'DY': ['dy_0j', 'dy_1j', 'dy_2j'],
'EWK': ['ewk_lljj_mll50_mjj120'],
'TTbar + Single Top':['ttjets_dl',\
'ttjets_sl',\
'ttw', 'ttz', 'st_tw_top', 'st_tw_antitop'],
'VV + VVV': ['ww_2l2nu', 'wz_2l2q', 'wz_1l1nu2q', 'wz_3lnu', 'www','wwz','wzz','zzz'],
},
"h-sidebands" : {
'DY': [ 'dy_m105_160_amc', 'dy_m105_160_vbf_amc'],
'EWK': [self.ewk_name],
'TTbar + Single Top':['ttjets_dl',\
'ttjets_sl',\
'ttw', 'ttz', 'st_tw_top', 'st_tw_antitop'],
'VV + VVV': ['ww_2l2nu', 'wz_2l2q', 'wz_1l1nu2q', 'wz_3lnu', 'www','wwz','wzz','zzz'],
},
"h-peak": {
'DY': [ 'dy_m105_160_amc', 'dy_m105_160_vbf_amc'],
'EWK': [self.ewk_name],
'TTbar + Single Top':['ttjets_dl',\
'ttjets_sl',\
'ttw', 'ttz', 'st_tw_top', 'st_tw_antitop'],
'VV + VVV': ['ww_2l2nu', 'wz_2l2q', 'wz_1l1nu2q', 'wz_3lnu', 'www','wwz','wzz','zzz'],
}
}
all_bkg_sources = {
'DY': ['dy', 'dy_0j', 'dy_1j', 'dy_2j', 'dy_m105_160_amc', 'dy_m105_160_vbf_amc', 'dy_m105_160_mg', 'dy_m105_160_vbf_mg'],
'EWK': ['ewk_lljj_mll50_mjj120','ewk_lljj_mll105_160', 'ewk_lljj_mll105_160_ptj0'],
'TTbar + Single Top':['ttjets_dl', 'ttjets_sl', 'ttw', 'ttz', 'st_tw_top', 'st_tw_antitop'],
'VV + VVV': ['ww_2l2nu', 'wz_2l2q', 'wz_1l1nu2q', 'wz_3lnu', 'www','wwz','wzz','zzz'],
}
bkg_sources = {}
accumulators_copy = {}
if inclusive:
bkg_sources = all_bkg_sources
# accumulators_copy[self.weight_option] = self.accumulators[var].sum('region')[:,channel,self.weight_option].copy()
accumulators_copy[self.weight_option] = self.accumulators[var][:,:,channel,self.weight_option].copy()
for syst in self.syst_sources:
accumulators_copy[f'{syst}_up'] = self.accumulators[var].sum('region')[:,channel,f'{syst}_up'].copy()
accumulators_copy[f'{syst}_down'] = self.accumulators[var].sum('region')[:,channel,f'{syst}_down'].copy()
else:
bkg_sources = bkg_sources_by_region[region]
# print(region, channel,self.accumulators[var][:,region,channel,self.weight_option].values())
accumulators_copy[self.weight_option] = self.accumulators[var][:,region, channel, self.weight_option].copy()
for syst in self.syst_sources:
accumulators_copy[f'{syst}_up'] = self.accumulators[var][:,region, channel, f'{syst}_up'].copy()
accumulators_copy[f'{syst}_down'] = self.accumulators[var][:,region, channel, f'{syst}_down'].copy()
all_bkg = []
for group, bkgs in bkg_sources.items():
for b in bkgs:
all_bkg.append(b)
if b not in self.weights_by_ds.keys():
self.weights_by_ds[b] = 1
integrals = {}
rescale = {}
if get_rates:
for b in all_bkg+data_sources['data']+[self.ggh_name, self.vbf_name]:
accum = accumulators_copy[self.weight_option][b].sum('region').sum('channel').sum('dataset').values()
if not accum: continue
integrals[b] = accum[(self.weight_option,)].sum()
rescale[b] = self.norms[region][b]/integrals[b]
for syst in accumulators_copy.keys():
if get_rates:
accumulators_copy[syst].scale(rescale, axis='dataset')
accumulators_copy[syst].scale(self.weights_by_ds, axis='dataset')
if inclusive:
if var=="dimuon_mass":
data = accumulators_copy[self.weight_option][:, ['h-sidebands', 'z-peak'], :,self.weight_option].sum('region').sum('channel').sum('syst').group('dataset', hist.Cat("dataset", "Dataset"), data_sources)
else:
data = accumulators_copy[self.weight_option].sum('region').sum('channel').sum('syst').group('dataset', hist.Cat("dataset", "Dataset"), data_sources)
accumulators_copy[self.weight_option] = accumulators_copy[self.weight_option].sum('region')
bkg = accumulators_copy[self.weight_option].sum('channel').sum('syst').group('dataset', hist.Cat("dataset", "Dataset"), bkg_sources)
ggh = accumulators_copy[self.weight_option][self.ggh_name].sum('channel').sum('syst')
vbf = accumulators_copy[self.weight_option][self.vbf_name].sum('channel').sum('syst')
else:
data = accumulators_copy[self.weight_option].sum('region').sum('channel').sum('syst').group('dataset', hist.Cat("dataset", "Dataset"), data_sources)
bkg = accumulators_copy[self.weight_option].sum('region').sum('channel').sum('syst').group('dataset', hist.Cat("dataset", "Dataset"), bkg_sources)
ggh = accumulators_copy[self.weight_option][self.ggh_name].sum('region').sum('channel').sum('syst')
vbf = accumulators_copy[self.weight_option][self.vbf_name].sum('region').sum('channel').sum('syst')
if get_rates:
self.datasets[region] = all_bkg+data_sources['data']+[self.ggh_name, self.vbf_name]
for b in self.datasets[region]:
if b in [i[0] for i in list(accumulators_copy[self.weight_option].values().keys())]:
histogram = accumulators_copy[self.weight_option][b].sum('region').sum('channel').sum('dataset').values()[(self.weight_option,)]*mc_factor
sumw2 = list(accumulators_copy[self.weight_option][b].sum('region').sum('channel').sum('dataset')._sumw2.values())[0]*mc_factor
self.hist_dict[region][b] = {'hist':histogram, 'sumw2':sumw2}
self.hist_syst[region][b] = {}
self.rates[region][b] = histogram.sum()
for syst in self.syst_sources:
hist_up = accumulators_copy[f'{syst}_up'][b].sum('region').sum('channel').sum('dataset').values()[(syst+'_up',)]*mc_factor
sumw2_up = list(accumulators_copy[f'{syst}_up'][b].sum('region').sum('channel').sum('dataset')._sumw2.values())[0]*mc_factor
hist_down = accumulators_copy[f'{syst}_down'][b].sum('region').sum('channel').sum('dataset').values()[(syst+'_down',)]*mc_factor
sumw2_down = list(accumulators_copy[f'{syst}_down'][b].sum('region').sum('channel').sum('dataset')._sumw2.values())[0]*mc_factor
self.hist_syst[region][b][syst+"Up"] = {'hist':hist_up, 'sumw2':sumw2_up}
self.hist_syst[region][b][syst+"Down"] = {'hist':hist_down, 'sumw2':sumw2_down}
data_is_valid = data.sum(var).sum('dataset').values()
bkg_is_valid = bkg.sum(var).sum('dataset').values()
bkgs_by_source = bkg.sum(var).values()
print(bkgs_by_source)
# print(bkg_is_valid)
ggh_is_valid = ggh.sum(var).sum('dataset').values()
vbf_is_valid = vbf.sum(var).sum('dataset').values()
bkg.axis('dataset').sorting = 'integral' # sort backgrounds by event yields
if normalize and data_is_valid and bkg_is_valid:
data_int = data.sum(var).sum('dataset').values()[()].sum()
bkg_int = bkg.sum(var).sum('dataset').values()[()].sum()
bkg_sf = data_int/bkg_int
bkg.scale(bkg_sf)
print(bkg_sf)
if bkg_is_valid:
bkg.scale(mc_factor)
print(f'Total bkg: {bkg_is_valid[()]}')
if ggh_is_valid:
ggh.scale(mc_factor)
print(f'Total ggh: {ggh_is_valid[()]}')
if vbf_is_valid:
vbf.scale(mc_factor)
print(f'Total vbf: {vbf_is_valid[()]}')
if data_is_valid:
print(f'Total data: {data_is_valid[()]}')
data_opts = {'color': 'k', 'marker': '.', 'markersize':15}
stack_fill_opts = {'alpha': 0.8, 'edgecolor':(0,0,0)}
stack_error_opts = {'label':'Stat. unc.','facecolor':(0,0,0,.4), 'hatch':'', 'linewidth': 0}
if save_to:
fig.clf()
plotsize=12
ratio_plot_size = 0.25
fig.set_size_inches(plotsize, plotsize*(1+ratio_plot_size))
gs = fig.add_gridspec(2, 1, height_ratios=[(1-ratio_plot_size),ratio_plot_size], hspace = .05)
# Top panel: Data vs. MC plot
plt1 = fig.add_subplot(gs[0])
if bkg_is_valid:
try:
ax_bkg = hist.plot1d(bkg, ax=plt1, overlay='dataset', overflow='all', stack=True, fill_opts=stack_fill_opts, error_opts=stack_error_opts)
except:
ax_bkg = hist.plot1d(bkg, ax=plt1, overlay='dataset', overflow='all', stack=False, fill_opts=stack_fill_opts, error_opts=stack_error_opts)
# draw signal histograms one by one manually because set_prop_cycle didn't work for changing color map
if ggh_is_valid:
ax_ggh = hist.plot1d(ggh, overlay='dataset', overflow='all', line_opts={'linewidth':2, 'color':'lime'}, error_opts=None)
if vbf_is_valid:
ax_vbf = hist.plot1d(vbf, overlay='dataset', overflow='all', line_opts={'linewidth':2, 'color':'b'}, error_opts=None)
if data_is_valid:
ax_data = hist.plot1d(data, overlay='dataset', overflow='all', line_opts=None, error_opts=data_opts)
lbl = hep.cms.cmslabel(ax=plt1, data=True, paper=False, year=year)
else:
lbl = hep.cms.cmslabel(ax=plt1, data=False, paper=False, year=year)
if logy:
plt1.set_yscale('log')
plt1.set_ylim(0.001, 1e8)
# else:
# plt1.set_ylim(0., 1e5)
plt1.set_xlabel('')
if 'dnn_score' in var:
plt1.set_xlim(0, parameters["dnn_max"][year])
elif 'dimuon_mass' not in var:
plt1.set_xlim(variable.xmin, variable.xmax)
plt1.tick_params(axis='x', labelbottom=False)
plt1.legend(prop={'size': 'xx-small'})
# Bottom panel: Data/MC ratio plot
plt2 = fig.add_subplot(gs[1], sharex=plt1)
if data_is_valid and bkg_is_valid:
num = data.sum('dataset')
denom = bkg.sum('dataset')
ax = hist.plotratio(num=num, ax=plt2,
denom=denom,
error_opts=data_opts, denom_fill_opts={}, guide_opts={},
unc='num')
plt2.axhline(1, ls='--')
plt2.set_ylim([0.6,1.4])
plt2.set_ylabel('Data/MC')
lbl = plt2.get_xlabel()
lbl = lbl if lbl else var
if inclusive:
plt2.set_xlabel(f'{lbl}, inclusive, {channel} channel')
else:
plt2.set_xlabel(f'{lbl}, {region}, {channel} channel')
if save_to:
if inclusive:
fig.savefig(save_to+f"{var}_{channel}_inclusive_{self.suffix}_{self.year}.png")
print(f"Saving {var}_{channel}_inclusive_{self.suffix}_{self.year}.png")
else:
fig.savefig(save_to+f"{var}_{channel}_{region}_{self.suffix}_{self.year}.png")
print(f"Saving {var}_{channel}_{region}_{self.suffix}_{self.year}.png")
hists['deltar'].fill(sample=str_all, h1=hvec.pt, weight=weightsW)
hists['deltar'].fill(sample=str_8, h1=hvec.pt[ak8_4q], weight=weightsW[ak8_4q])
hists['deltar'].fill(sample=str_15, h1=hvec.pt[ak15_4q], weight=weightsW[ak15_4q])
# hists['genHiggsPt'].fill(sample='HH4b full', h1=higgs_pt[:, 0], weight=weights['fullHH4b'])
fig, (axs, rax) = plt.subplots(2, 1, gridspec_kw={"height_ratios": (3, 1)}, sharex=True)
hist.plot1d(hists['deltar'], line_opts=line_opts, ax=axs)
axs.set_xlabel(None)
# axs.set_ylim(0, 5)
axs.legend(fancybox=True, shadow=True, frameon=True, prop={'size': 16})
data_err_opts_c['color'] = 'blue'
hist.plotratio(hists['deltar'][str_8].sum('sample'), hists['deltar'][str_all].sum('sample'), ax=rax, error_opts=data_err_opts_c, unc='num', clear=False, label='0.8')
data_err_opts_c['color'] = 'orange'
hist.plotratio(hists['deltar'][str_15].sum('sample'), hists['deltar'][str_all].sum('sample'), ax=rax, error_opts=data_err_opts_c, unc='num', clear=False, label='1.5')
rax.legend(fancybox=True, shadow=True, frameon=True, prop={'size': 16})
rax.set_ylabel("captured/total")
rax.set_ylim(0, 1)
rax.grid(which='both')
plt.savefig('figs/deltar.pdf', bbox_inches='tight')
plt.show()
