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': '-',
'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
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:
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 plot(inpath):
indir = os.path.abspath(inpath)
# The processor output is stored in an
# 'accumulator', which in our case is
# just a dictionary holding all the histograms
# Put all your *coffea files into 'indir' and
# pass the directory as an argument here.
# All input files in the directory will
# automatically be found, merged and read.
# The merging only happens the first time
# you run over a specific set of inputs.
acc = dir_archive(inpath, serialized=True, compression=0, memsize=1e3)
# Get a settings dictionary that details
# which plots to make for each region,
# what the axis limits are, etc
# Can add plots by extending the dictionary
# Or modify axes ranges, etc
settings = plot_settings()
merged = set()
# Separate plots per year
for year in [2017, 2018]:
# The data to be used for each region
# Muon regions use MET,
# electron+photon regions use EGamma
# ( EGamma = SingleElectron+SinglePhoton for 2017)
data = {
'sr_vbf': None,
'cr_1m_vbf': f'MET_{year}',
'cr_2m_vbf': f'MET_{year}',
'cr_1e_vbf': f'EGamma_{year}',
'cr_2e_vbf': f'EGamma_{year}',
'cr_g_vbf': f'EGamma_{year}',
}
# Same for MC selection
# Match datasets by regular expressions
# Here for LO V samples (HT binned)
mc_lo = {
'sr_vbf':
re.compile(
f'(ZJetsToNuNu.*|EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*|.*WJetsToLNu.*HT.*).*{year}'
),
'cr_1m_vbf':
re.compile(
f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*|.*WJetsToLNu.*HT.*).*{year}'
),
'cr_1e_vbf':
re.compile(
f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*|.*WJetsToLNu.*HT.*).*{year}'
),
'cr_2m_vbf':
re.compile(
f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*).*{year}'
),
'cr_2e_vbf':
re.compile(
f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*).*{year}'
),
'cr_g_vbf':
re.compile(f'(GJets_(HT|SM).*|QCD_HT.*|WJetsToLNu.*HT.*).*{year}'),
}
# Want to compare LO and NLO,
# so do same thing for NLO V samples
# All non-V samples remain the same
mc_nlo = {
'sr_vbf':
re.compile(
f'(ZJetsToNuNu.*|EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*|.*WJetsToLNu.*FXFX.*).*{year}'
),
'cr_1m_vbf':
re.compile(
f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DY.*FXFX.*|.*WJetsToLNu.*FXFX.*).*{year}'
),
'cr_1e_vbf':
re.compile(
f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DY.*FXFX.*|.*WJetsToLNu.*FXFX.*).*{year}'
),
'cr_2m_vbf':
re.compile(
f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DY.*FXFX.*).*{year}'
),
'cr_2e_vbf':
re.compile(
f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DY.*FXFX.*).*{year}'
),
'cr_g_vbf':
re.compile(f'(GJets_(HT|SM).*|QCD_HT.*|W.*FXFX.*).*{year}'),
}
regions = list(mc_lo.keys())
# Remove signal region, no need in ratio plots
regions.remove('sr_vbf')
# Make control region ratio plots for both
# LO and NLO. Can be skipped if you only
# want data / MC agreement plots.
outdir = f'./output/{os.path.basename(indir)}/ratios'
# Load ingredients from cache
acc.load('mjj')
acc.load('sumw')
acc.load('sumw_pileup')
acc.load('nevents')
cr_ratio_plot(acc,
year=year,
tag='losf',
outdir=outdir,
mc=mc_lo,
regions=regions,
distribution='mjj')
cr_ratio_plot(acc,
year=year,
tag='nlo',
outdir=outdir,
mc=mc_nlo,
regions=regions,
distribution='mjj')
# Data / MC plots are made here
# Loop over all regions
for region in mc_lo.keys():
ratio = True if region != 'sr_vbf' else False
# Make separate output direcotry for each region
outdir = f'./output/{os.path.basename(indir)}/{region}'
# Settings for this region
plotset = settings[region]
# Loop over the distributions
for distribution in plotset.keys():
# Load from cache
if not distribution in merged:
acc.load(distribution)
if not distribution in acc.keys():
print(
f"WARNING: Distribution {distribution} not found in input files."
)
continue
acc[distribution] = merge_extensions(
acc[distribution],
acc,
reweight_pu=not ('nopu' in distribution))
scale_xs_lumi(acc[distribution])
acc[distribution] = merge_datasets(acc[distribution])
acc[distribution].axis('dataset').sorting = 'integral'
merged.add(distribution)
try:
# The heavy lifting of making a plot is hidden
# in make_plot. We call it once using the LO MC
make_plot(
acc,
region=region,
distribution=distribution,
year=year,
data=data[region],
mc=mc_lo[region],
ylim=plotset[distribution].get('ylim', None),
xlim=plotset[distribution].get('xlim', None),
tag='losf',
outdir=f'./output/{os.path.basename(indir)}/{region}',
output_format='pdf',
ratio=ratio)
# And then we also call it for the NLO MC
# The output files will be named according to the 'tag'
# argument, so we will be able to tell them apart.
make_plot(
acc,
region=region,
distribution=distribution,
year=year,
data=data[region],
mc=mc_nlo[region],
ylim=plotset[distribution].get('ylim', None),
xlim=plotset[distribution].get('xlim', None),
tag='nlo',
outdir=f'./output/{os.path.basename(indir)}/{region}',
output_format='pdf',
ratio=ratio)
except KeyError:
continue
def plot(args):
indir = os.path.abspath(args.inpath)
# The processor output is stored in an
# 'accumulator', which in our case is
# just a dictionary holding all the histograms
# Put all your *coffea files into 'indir' and
# pass the directory as an argument here.
# All input files in the directory will
# automatically be found, merged and read.
# The merging only happens the first time
# you run over a specific set of inputs.
acc = dir_archive(args.inpath, serialized=True, compression=0, memsize=1e3)
# Get a settings dictionary that details
# which plots to make for each region,
# what the axis limits are, etc
# Can add plots by extending the dictionary
# Or modify axes ranges, etc
settings = plot_settings()
merged = set()
# Separate plots per year
for year in [2017, 2018]:
# The data to be used for each region
# Muon regions use MET,
# electron+photon regions use EGamma
# ( EGamma = SingleElectron+SinglePhoton for 2017)
data = {
'sr_vbf': f'MET_{year}',
'cr_1m_vbf': f'MET_{year}',
'cr_2m_vbf': f'MET_{year}',
'cr_1e_vbf': f'EGamma_{year}',
'cr_2e_vbf': f'EGamma_{year}',
'cr_g_vbf': f'EGamma_{year}',
}
# Same for MC selection
# Match datasets by regular expressions
# Here for LO V samples (HT binned)
mc_lo = {
'sr_vbf':
re.compile(
f'(ZJetsToNuNu.*|EW.*|Top_FXFX.*|Diboson.*|.*DYJetsToLL_M-50_HT_MLM.*|.*WJetsToLNu.*HT.*).*{year}'
),
'cr_1m_vbf':
re.compile(
f'(EWKW.*|Top_FXFX.*|Diboson.*|.*DYJetsToLL_M-50_HT_MLM.*|.*WJetsToLNu.*HT.*).*{year}'
),
'cr_1e_vbf':
re.compile(
f'(EWKW.*|Top_FXFX.*|Diboson.*|.*DYJetsToLL_M-50_HT_MLM.*|.*WJetsToLNu.*HT.*).*{year}'
),
'cr_2m_vbf':
re.compile(
f'(EWKZ.*ZToLL.*|Top_FXFX.*|Diboson.*|.*DYJetsToLL_M-50_HT_MLM.*).*{year}'
),
'cr_2e_vbf':
re.compile(
f'(EWKZ.*ZToLL.*|Top_FXFX.*|Diboson.*|.*DYJetsToLL_M-50_HT_MLM.*).*{year}'
),
'cr_g_vbf':
re.compile(
f'(GJets_(DR-0p4|SM).*|QCD_data.*|WJetsToLNu.*HT.*).*{year}'),
}
# Load ingredients from cache
acc.load('sumw')
acc.load('sumw_pileup')
acc.load('nevents')
# Data / MC plots are made here
# Loop over all regions
for region in mc_lo.keys():
if not re.match(args.region, region):
continue
# Plot ratio pads for all regions (now that we're unblinded)
ratio = True
# Make separate output direcotry for each region
outdir = f'./output/{os.path.basename(indir)}/{region}'
# Settings for this region
plotset = settings[region]
# Loop over the distributions
for distribution in plotset.keys():
if not re.match(args.distribution, distribution):
continue
# Load from cache
if not distribution in merged:
acc.load(distribution)
if not distribution in acc.keys():
print(
f"WARNING: Distribution {distribution} not found in input files."
)
continue
acc[distribution] = merge_extensions(
acc[distribution],
acc,
reweight_pu=not ('nopu' in distribution))
scale_xs_lumi(acc[distribution])
acc[distribution] = merge_datasets(acc[distribution])
acc[distribution].axis('dataset').sorting = 'integral'
merged.add(distribution)
try:
# The heavy lifting of making a plot is hidden
# in make_plot. We call it once using the LO MC
imc = mc_lo[region]
if "cr_g" in region and distribution != "recoil":
imc = re.compile(
imc.pattern.replace('QCD_data', 'QCD.*HT'))
make_plot(
acc,
region=region,
distribution=distribution,
year=year,
data=data[region],
mc=imc,
ylim=plotset[distribution].get('ylim', None),
xlim=plotset[distribution].get('xlim', None),
tag='losf',
outdir=f'./output/{os.path.basename(indir)}/{region}',
output_format='pdf',
ratio=ratio)
except KeyError:
continue
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,
'emarker': '_'
}
signal_err_opts = {
'linestyle': 'none',
'marker': '.',
'markersize': 10.,
'color': 'r',
'elinewidth': 1,
'emarker': '_'
}
# Plot single muon data
# Note the syntax we use to pick the data set
if data:
fig, ax, _ = 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
_, _, primitives = hist.plot1d(h[mc],
overlay='dataset',
stack=True,
clear=False,
overflow='all',
ax=ax,
binwnorm=True)
for name, ps in primitives.items():
name = str(name)
col = None
for k, v in colors.items():
if re.match(k, name):
col = v
break
for item in ps:
if col:
item.set_facecolor(col)
item.set_linestyle('-')
item.set_edgecolor('k')
# 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)
outpath = pjoin(
outdir,
f"{region}_{distribution}{inte_tag}_{tag + '_' if tag else ''}{year}.{output_format}"
)
fig.savefig(outpath)
print(f"Saved plot file in {outpath}")
plt.close('all')
