def photon_sf_plot(tag):
for year in [2017, 2018]:
opts = markers('data')
# opts['markersize'] = 5
# opts['fillstyle'] = 'none'
opts.pop('emarker', '')
fig = plt.gcf()
ax = plt.gca()
x, y, yerr = {}, {}, {}
fnum = f'output/{tag}/table_g_HLT_PFHT1050_photon_pt0_JetHT_{year}.txt'
fden = f'output/{tag}/table_g_HLT_PFHT590_photon_pt0_GJets_HT_MLM_{year}.txt'
xnum, _, ynum, yerrnum = get_xy(fnum)
xden, _, yden, yerrden = get_xy(fden)
x = xnum
y = ynum / yden
dy = ratio_unc(ynum, yden, yerrnum, yerrden)
ax.errorbar(x, y, yerr=dy, label=f'{year}', **opts)
# for f in files: plot(f)
outdir = f"./output/{tag}"
# ax.set_ylim(0.9,1)
ax.legend()
ax.set_ylabel("Data / MC SF")
ax.xaxis.set_major_locator(MultipleLocator(200))
ax.xaxis.set_minor_locator(MultipleLocator(50))
ax.yaxis.set_major_locator(MultipleLocator(0.05))
ax.yaxis.set_minor_locator(MultipleLocator(0.01))
ax.set_ylim(0.95, 1.02)
ax.grid(1)
# rax.set_ylim(0.95,1.05)
# rax.yaxis.set_major_locator(MultipleLocator(0.05))
# rax.yaxis.set_minor_locator(MultipleLocator(0.01))
# rax.grid(1)
# rax.set_xlabel("Recoil or $p_{T}^{miss}$ (GeV)")
# rax.set_ylabel(r"Ratio to single-$\mu$")
# rax.plot([0,1000],[0.99,0.99],color='blue')
# rax.plot([0,1000],[1.01,1.01],color='blue')
# rax.plot([250,250],[0.95,0.95],color='blue')
ax.plot([215, 215], [0.9, 1.1], color='red', zorder=-1)
plt.text(1.,
1.,
r"%.1f fb$^{-1}$ (13 TeV)" % lumi(year),
fontsize=16,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
plt.text(0.,
1.,
f'{year}',
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
fig.savefig(pjoin(outdir, f'photon_sf_{year}.pdf'))
fig.clear()
plt.close(fig)
def region_comparison_plot(tag):
for year in [2017,2018]:
regions = ['1m', '2m', '1e','1m_hlt','2m_hlt']
opts = markers('data')
opts['markersize'] = 5.
opts['fillstyle'] = 'none'
emarker = opts.pop('emarker', '')
fig, ax, rax = fig_ratio()
x, y, yerr = {}, {}, {}
for region in regions:
if region.endswith('e'):
file = f'output/{tag}/table_{region}_EGamma_{year}.txt'
else:
file = f'output/{tag}/table_{region}_SingleMuon_{year}.txt'
x[region], y[region], yerr[region] = get_xy(file)
opts['color'] = colors[region]
ax.errorbar(x[region], y[region], yerr=yerr[region],label=f'{region} region', **opts)
# opts.pop('elinewidth')
if region=='1m':
continue
rax.errorbar(x['1m'], y[region]/y['1m'], yerr[region]/y['1m'], **opts)
# for f in files: plot(f)
outdir = f"./output/{tag}"
# ax.set_ylim(0.9,1)
ax.legend()
ax.set_ylabel("Efficiency")
ax.xaxis.set_major_locator(MultipleLocator(200))
ax.xaxis.set_minor_locator(MultipleLocator(50))
ax.yaxis.set_major_locator(MultipleLocator(0.05))
ax.yaxis.set_minor_locator(MultipleLocator(0.01))
ax.set_ylim(0.9,1.02)
ax.grid(1)
rax.set_ylim(0.9,1.1)
rax.grid(1)
rax.set_xlabel("Recoil or $p_{T}^{miss}$ (GeV)")
rax.set_ylabel(r"Ratio to single-$\mu$")
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'{year}',
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes
)
fig.savefig(pjoin(outdir, f'region_comparison_data_{year}.pdf'))
fig.clear()
plt.close(fig)
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)
def sf_comparison_plot(tag):
for year in [2017,2018]:
regions = ['1m', '2m', '1m_hlt', '2m_hlt']
opts = markers('data')
opts['markersize'] = 5
opts['fillstyle'] = 'none'
emarker = opts.pop('emarker', '')
fig, ax, rax = fig_ratio()
x, y, yerr = {}, {}, {}
for region in regions:
if '1e' in region:
fnum = f'output/{tag}/table_{region}_EGamma_{year}.txt'
fden = f'output/{tag}/table_{region}_WJetsToLNu-MLM_{year}.txt'
elif '1m' in region:
fnum = f'output/{tag}/table_{region}_SingleMuon_{year}.txt'
fden = f'output/{tag}/table_{region}_WJetsToLNu-MLM_{year}.txt'
elif '2m' in region:
fnum = f'output/{tag}/table_{region}_SingleMuon_{year}.txt'
fden = f'output/{tag}/table_{region}_DYNJetsToLL_M-50-MLM_{year}.txt'
xnum, ynum, yerrnum = get_xy(fnum)
xden, yden, yerrden = get_xy(fden)
x[region] = xnum
y[region] = ynum / yden
yerr[region] = ratio_unc(ynum, yden, yerrnum, yerrden)
opts['color'] = colors[region]
opts['marker'] = region_marker[region]
ax.errorbar(x[region], y[region], yerr=yerr[region],label=f'{region} region', **opts)
# opts.pop('elinewidth')
if region=='1m':
continue
rax.errorbar(x['1m'], y[region]/y['1m'], ratio_unc(y[region],y['1m'],yerr[region],yerr['1m']), **opts)
# for f in files: plot(f)
outdir = f"./output/{tag}"
# ax.set_ylim(0.9,1)
ax.legend()
ax.set_ylabel("Data / MC SF")
ax.xaxis.set_major_locator(MultipleLocator(200))
ax.xaxis.set_minor_locator(MultipleLocator(50))
ax.yaxis.set_major_locator(MultipleLocator(0.05))
ax.yaxis.set_minor_locator(MultipleLocator(0.01))
ax.set_ylim(0.9,1.1)
ax.grid(1)
rax.set_ylim(0.95,1.05)
rax.yaxis.set_major_locator(MultipleLocator(0.05))
rax.yaxis.set_minor_locator(MultipleLocator(0.01))
rax.grid(1)
rax.set_xlabel("Recoil or $p_{T}^{miss}$ (GeV)")
rax.set_ylabel(r"Ratio to single-$\mu$")
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'{year}',
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes
)
fig.savefig(pjoin(outdir, f'sf_comparison_{year}.pdf'))
fig.clear()
plt.close(fig)
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 data_mc_comparison_plot(tag,
ymin=0,
ymax=1.1,
distribution='recoil',
jeteta_config=None,
output_format='pdf'):
if 'gamma' in tag:
regions = [
'g_HLT_PFHT1050', 'g_HLT_PFHT590', 'g_HLT_PFHT680',
'g_HLT_PFHT780', 'g_HLT_PFHT890'
]
elif 'recoil' in tag:
regions = ['1m', '2m']
else:
regions = ['1m', '2m', '1e', '2m_hlt']
opts = markers('data')
# opts['markersize'] = 5
# opts['fillstyle'] = 'none'
emarker = opts.pop('emarker', '')
outdir = f"./output/{tag}"
outpath = pjoin(outdir, f'trig_sf.root')
try:
outfile = uproot.recreate(outpath)
except OSError:
outfile = uproot.update(outpath)
for year in [2017, 2018]:
for region in regions:
fig, ax, rax = fig_ratio()
if '1e' in region:
fnum = f'output/{tag}/table_{region}_met_EGamma_{year}.txt'
fden = f'output/{tag}/table_{region}_met_WJetsToLNu_HT_MLM_{year}.txt'
xlabel = "$p_{T}^{miss}$ (GeV)"
elif '1m' in region:
fnum = f'output/{tag}/table_{region}_recoil_SingleMuon_{year}{"_"+jeteta_config if jeteta_config else ""}.txt'
fden = f'output/{tag}/table_{region}_recoil_WJetsToLNu_HT_MLM_{year}{"_"+jeteta_config if jeteta_config else ""}.txt'
xlabel = "Recoil (GeV)"
elif '2m' in region:
fnum = f'output/{tag}/table_{region}_recoil_SingleMuon_{year}{"_"+jeteta_config if jeteta_config else ""}.txt'
fden = f'output/{tag}/table_{region}_recoil_VDYJetsToLL_M-50_HT_MLM_{year}{"_"+jeteta_config if jeteta_config else ""}.txt'
xlabel = "Recoil (GeV)"
elif 'g_' in region:
fnum = f'output/{tag}/table_{region}_photon_pt0_JetHT_{year}.txt'
fden = f'output/{tag}/table_{region}_photon_pt0_GJets_HT_MLM_{year}.txt'
xlabel = "Photon $p_{T}$ (GeV)"
if not os.path.exists(fnum):
print(f"File not found {fnum}")
continue
if not os.path.exists(fden):
print(f"File not found {fden}")
continue
xnum, xedgnum, ynum, yerrnum = get_xy(fnum)
xden, xedgden, yden, yerrden = get_xy(fden)
xsf = xnum
ysf = ynum / yden
ysferr = ratio_unc(ynum, yden, yerrnum, yerrden)
opts['color'] = 'k'
ax.errorbar(xnum,
ynum,
yerr=yerrnum,
label=f'Data, {region} region',
**opts)
opts['color'] = 'r'
ax.errorbar(xden,
yden,
yerr=yerrden,
label=f'MC, {region} region',
**opts)
# rax.plot([0,1000],[0.98,0.98],color='blue')
# rax.plot([0,1000],[0.99,0.99],color='blue',linestyle='--')
if 'g_' in region:
ax.plot([215, 215], [0.9, 1.1], color='blue')
rax.plot([215, 215], [0.95, 1.05], color='blue')
elif distribution == 'recoil':
ax.plot([250, 250], [0.0, 1.1], color='blue')
rax.plot([250, 250], [0.95, 1.05], color='blue')
else:
ax.plot([250, 250], [0.9, 1.1], color='blue')
rax.plot([250, 250], [0.95, 1.05], color='blue')
opts['color'] = 'k'
rax.errorbar(xsf, ysf, ysferr, **opts)
ax.legend()
ax.set_ylabel("Efficiency")
ax.xaxis.set_major_locator(MultipleLocator(200))
ax.xaxis.set_minor_locator(MultipleLocator(50))
ax.set_ylim(ymin, ymax)
ax.grid(1)
if distribution == 'mjj':
ax.yaxis.set_major_locator(MultipleLocator(0.05))
ax.yaxis.set_minor_locator(MultipleLocator(0.01))
elif distribution == 'recoil':
ax.yaxis.set_major_locator(MultipleLocator(0.1))
ax.yaxis.set_minor_locator(MultipleLocator(0.05))
rax.set_xlabel(xlabel)
rax.set_ylabel("Data / MC SF")
rax.set_ylim(0.95, 1.05)
rax.yaxis.set_major_locator(MultipleLocator(0.05))
rax.yaxis.set_minor_locator(MultipleLocator(0.01))
rax.grid(1)
plt.text(1.,
1.,
r"$\approx$ %.1f fb$^{-1}$ (13 TeV)" %
lumi_by_region(region, 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'{year}',
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
fig.savefig(
pjoin(
outdir,
f'data_mc_comparison_{region}_{year}{"_"+jeteta_config if jeteta_config else ""}.{output_format}'
))
fig.clear()
plt.close(fig)
vals = np.array(sorted(list(set(list(xedgnum.flatten())))))
ysf[np.isnan(ysf) | np.isinf(np.abs(ysf))] = 1
outfile[f'{tag}_{region}_{year}'] = (ysf, vals)
def plot_scalefactors(tag,
ymin=0.9,
ymax=1.1,
distribution='recoil',
output_format='pdf'):
regions = ['1m', '2m']
opts = markers('data')
emarker = opts.pop('emarker', '')
outdir = f"./output/{tag}"
jeteta_configs = [
'two_central_jets', 'two_forward_jets',
'one_jet_forward_one_jet_central'
]
for year in [2017, 2018]:
for region in regions:
fig, ax = plt.subplots(1, 1)
ynum = {}
yden = {}
yerrnum = {}
yerrden = {}
ysf = {}
ysferr = {}
for jeteta_config in jeteta_configs:
print(f'{year}, {region}, {jeteta_config}')
if region == '1m':
fnum = f'output/{tag}/table_{region}_recoil_SingleMuon_{year}_{jeteta_config}.txt'
fden = f'output/{tag}/table_{region}_recoil_WJetsToLNu_HT_MLM_{year}_{jeteta_config}.txt'
xlabel = f"{distribution} (GeV)"
elif region == '2m':
fnum = f'output/{tag}/table_{region}_recoil_SingleMuon_{year}_{jeteta_config}.txt'
fden = f'output/{tag}/table_{region}_recoil_VDYJetsToLL_M-50_HT_MLM_{year}_{jeteta_config}.txt'
xlabel = f"{distribution} (GeV)"
if not os.path.exists(fnum):
print(f"File not found {fnum}")
continue
if not os.path.exists(fden):
print(f"File not found {fden}")
continue
xnum, xedgnum, ynum[f'{jeteta_config}'], yerrnum[
f'{jeteta_config}'] = get_xy(fnum)
xden, xedgden, yden[f'{jeteta_config}'], yerrden[
f'{jeteta_config}'] = get_xy(fden)
xsf = xnum
ysf[f'{jeteta_config}'] = ynum[f'{jeteta_config}'] / yden[
f'{jeteta_config}']
ysferr[f'{jeteta_config}'] = ratio_unc(
ynum[f'{jeteta_config}'], yden[f'{jeteta_config}'],
yerrnum[f'{jeteta_config}'], yerrden[f'{jeteta_config}'])
# Only consider the values above 250 GeV
if distribution == 'recoil':
recoil_cut = xedgnum[0] >= 250
xsf = xsf[recoil_cut]
ysferr_new = {}
ysferr_new['two_central_jets'] = [
ysferr['two_central_jets'][0][recoil_cut],
ysferr['two_central_jets'][1][recoil_cut]
]
ysferr_new['two_forward_jets'] = [
ysferr['two_forward_jets'][0][recoil_cut],
ysferr['two_forward_jets'][1][recoil_cut]
]
ysferr_new['one_jet_forward_one_jet_central'] = [
ysferr['one_jet_forward_one_jet_central'][0][recoil_cut],
ysferr['one_jet_forward_one_jet_central'][1][recoil_cut]
]
opts['color'] = 'k'
ax.errorbar(xsf,
ysf['two_central_jets'][recoil_cut],
yerr=ysferr_new['two_central_jets'],
label=f'Two central jets',
**opts)
opts['color'] = 'g'
ax.errorbar(xsf,
ysf['two_forward_jets'][recoil_cut],
yerr=ysferr_new['two_forward_jets'],
label=f'Two forward jets',
**opts)
opts['color'] = 'r'
ax.errorbar(xsf,
ysf['one_jet_forward_one_jet_central'][recoil_cut],
yerr=ysferr_new['one_jet_forward_one_jet_central'],
label=f'Mixed',
**opts)
ax.legend()
ax.set_ylabel('Data / MC SF')
ax.set_xlabel(f'{distribution.capitalize()} (GeV)')
ax.set_ylim(ymin, ymax)
ax.grid(1)
ax.xaxis.set_major_locator(MultipleLocator(200))
ax.xaxis.set_minor_locator(MultipleLocator(50))
ax.yaxis.set_major_locator(MultipleLocator(0.05))
ax.yaxis.set_minor_locator(MultipleLocator(0.01))
plt.text(1.,
1.,
r"$\approx$ %.1f fb$^{-1}$ (13 TeV)" %
lumi_by_region(region, year),
fontsize=16,
horizontalalignment='right',
verticalalignment='bottom',
transform=ax.transAxes)
plt.text(0.,
1.,
f'{year} {region}',
fontsize=16,
horizontalalignment='left',
verticalalignment='bottom',
transform=ax.transAxes)
fig.savefig(
pjoin(outdir,
f'scale_factors_{region}_{year}.{output_format}'))
fig.clear()
plt.close(fig)