def ttbarcheck():
indir = "input/21Aug_newsf"
acc = acc_from_dir(indir)
outdir = f'./output/{os.path.basename(indir)}/ttbar/fxfx_vs_mlm'
for year in [2017, 2018]:
data = re.compile(f'TTJets.*FXFX.*{year}')
mc = re.compile(f'TTJets.*MLM.*{year}')
region = 'cr_2m_j'
for distribution in ['recoil', 'ak4_pt0']:
make_plot(acc,
region=region,
distribution=distribution,
year=year,
data=data,
mc=mc,
ylim=(1e-3, 1e3),
outdir=outdir)
outdir = f'./output/{os.path.basename(indir)}/ttbar/fxfx_vs_pow'
for year in [2017, 2018]:
data = re.compile(f'TTJets.*FXFX.*{year}')
mc = re.compile(f'TT.*pow.*{year}')
region = 'cr_2m_j'
for distribution in ['recoil', 'ak4_pt0']:
make_plot(acc,
region=region,
distribution=distribution,
year=year,
data=data,
mc=mc,
ylim=(1e-3, 1e3),
outdir=outdir)
def data_mc_after_kfac():
indir = "input/21Aug_newsf"
acc = acc_from_dir(indir)
outdir = f'./output/{os.path.basename(indir)}'
for year in [2017, 2018]:
data = re.compile(f'MET_{year}')
mc = re.compile(
f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*){year}'
)
region = 'cr_2m_j'
for distribution in ['recoil', 'ak4_pt0']:
make_plot(acc,
region=region,
distribution=distribution,
year=year,
data=data,
mc=mc,
ylim=(1e-3, 1e3),
outdir=outdir)
data = re.compile(f'MET_{year}')
mc = re.compile(
f'(TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*|W.*HT.*).*{year}'
)
region = 'cr_1m_j'
for distribution in ['recoil', 'ak4_pt0']:
make_plot(acc,
region=region,
distribution=distribution,
year=year,
data=data,
mc=mc,
ylim=(1e-3, 1e5),
outdir=outdir)
def main():
indir = "input/2019-09-06_hem/"
acc = acc_from_dir(indir)
# for year in [2018]:
# data = re.compile(f'EGamma_{year}')
# mc = re.compile(f'(EW.*|TTJets.*|ZZ.*|ST.*|QCD_HT.*|WW.*|WZ.*|.*DYJetsToLL_M-50_HT_MLM.*|WJet.*HT.*){year}')
# for region in ['cr_1e_j','cr_1e_j_nohem', 'cr_2e_j','cr_1e_j_nohem']:
# for distribution in ['recoil','ak4_phi','electron_phi','ak4_pt0']:
# make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, outdir=f'./output/{os.path.basename(indir)}')
for year in [2018]:
data = re.compile(f'MET_{year}')
mc = re.compile(
f'(EW.*|TTJets.*|ZZ.*|ST.*|QCD_HT.*|WW.*|WZ.*|.*DYJetsToLL_M-50_HT_MLM.*|WJet.*HT.*){year}'
)
for region in ['cr_1m_j', 'cr_1m_j_nohem']:
for distribution in ['ak4_phi', 'recoil', 'ak4_pt0']:
make_plot(acc,
region=region,
distribution=distribution,
year=year,
data=data,
mc=mc,
outdir=f'./output/{os.path.basename(indir)}')
def cr_ratio():
indir=os.path.abspath('input/2019-09-09_gen_dilep_sf/')
acc = acc_from_dir(indir)
for year in [2017,2018]:
data = {
'cr_1m_j' : f'MET_{year}',
'cr_2m_j' : f'MET_{year}',
'cr_1e_j' : f'EGamma_{year}',
'cr_2e_j' : f'EGamma_{year}',
'cr_g_j' : f'EGamma_{year}',
}
mc_lo = {
'cr_1m_j' : re.compile(f'(TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*|W.*HT.*).*{year}'),
'cr_1e_j' : re.compile(f'(TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*|W.*HT.*).*{year}'),
'cr_2m_j' : re.compile(f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*).*{year}'),
'cr_2e_j' : re.compile(f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DYJetsToLL_M-50_HT_MLM.*).*{year}'),
'cr_g_j' : re.compile(f'(GJets.*|QCD_HT.*|W.*HT.*).*{year}'),
}
mc_nlo = {
'cr_1m_j' : re.compile(f'(TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DY.*FXFX.*|W.*FXFX.*).*{year}'),
'cr_1e_j' : re.compile(f'(TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DY.*FXFX.*|W.*FXFX.*).*{year}'),
'cr_2m_j' : re.compile(f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DY.*FXFX.*).*{year}'),
'cr_2e_j' : re.compile(f'(EW.*|TTJets.*FXFX.*|Diboson.*|ST.*|QCD_HT.*|.*DY.*FXFX.*).*{year}'),
'cr_g_j' : re.compile(f'(GJets.*|QCD_HT.*|W.*FXFX.*).*{year}'),
}
outdir = f'./output/{os.path.basename(indir)}/ratios'
cr_ratio_plot(acc, year=year,tag='losf',outdir=outdir, mc=mc_lo)
cr_ratio_plot(acc, year=year,tag='nlo',outdir=outdir, mc=mc_nlo)
for region in mc_lo.keys():
outdir = f'./output/{os.path.basename(indir)}/{region}'
plotset = plot_settings[region]
for distribution in plotset.keys():
make_plot(acc,
region=region,
distribution=distribution,
year=year,
data=data[region],
mc=mc_lo[region],
ylim=plot_settings['ylim'],
tag = 'losf',
outdir=f'./output/{os.path.basename(indir)}/{region}')
make_plot(acc,
region=region,
distribution=distribution,
year=year,
data=data[region],
mc=mc_nlo[region],
ylim=plot_settings['ylim'],
tag = 'nlo',
outdir=f'./output/{os.path.basename(indir)}/{region}')
def single_electron_plots():
for year in [2017, 2018]:
data = re.compile(f'EGamma_{year}')
mc = re.compile(f'(TTJets.*FXFX.*|ST.*|QCD_HT.*|Diboson.*|W.*HT.*).*{year}')
region='cr_1e_j'
for distribution in ['recoil','ak4_pt0','electron_pt','met']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, ylim=(1e-3,1e5), outdir=f'./output/{os.path.basename(indir)}/{region}')
for distribution in ['ak4_phi0','electron_phi']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, ylim=(1e4,1e5), outdir=f'./output/{os.path.basename(indir)}/{region}')
for distribution in ['ak4_eta0', 'electron_eta']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, xlim=(-3,3),ylim=(1e4,1e6), outdir=f'./output/{os.path.basename(indir)}/{region}')
for distribution in ['ak4_chf0','ak4_nhf0']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, xlim=(0,1),ylim=(1e3,1e8), outdir=f'./output/{os.path.basename(indir)}/{region}')
for distribution in ['electron_mt']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, xlim=(0,180),ylim=(1e1,1e5), outdir=f'./output/{os.path.basename(indir)}/{region}')
def main():
# indir = "../input/21Aug19_v4_pdfwgt"
# acc = acc_from_dir(indir)
# for year in [2017]:
# data = re.compile(f'MET_{year}')
# mc = re.compile(f'(EW.*|TTJets.*|ZZ.*|ST.*|QCD_HT.*|WW.*|WZ.*|.*DYJetsToLL_M-50_HT_MLM.*){year}')
# region='cr_2m_j'
# for distribution in ['recoil']:
# make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, ylim=(1e-3,1e3), outdir=f'./output/{os.path.basename(indir)}')
indir = "../../input/21Aug19_v2_newpu"
acc = acc_from_dir(indir)
for year in [2017]:
data = re.compile(f'MET_{year}')
mc = re.compile(
f'(EW.*|TTJets.*|ZZ.*|ST.*|QCD_HT.*|WW.*|WZ.*|.*DYJetsToLL_M-50_HT_MLM.*){year}'
)
region = 'cr_2m_j'
for distribution in ['recoil', 'ak4_pt0']:
make_plot(acc,
region=region,
distribution=distribution,
year=year,
data=data,
mc=mc,
ylim=(1e-3, 1e3),
outdir=f'./output/{os.path.basename(indir)}')
for year in [2017]:
data = re.compile(f'MET_{year}')
mc = re.compile(
f'(EW.*|TTJets.*|ZZ.*|ST.*|QCD_HT.*|WW.*|WZ.*|.*DYJetsToLL_M-50_HT_MLM.*){year}'
)
region = 'cr_2m_j'
for distribution in ['recoil', 'ak4_pt0']:
make_plot(acc,
region=region,
distribution=distribution,
year=year,
data=data,
mc=mc,
ylim=(1e-3, 1e3),
outdir=f'./output/{os.path.basename(indir)}/ttbarcheck')
def photon_plots():
for year in [2017, 2018]:
data = re.compile(f'EGamma_{year}')
mc = re.compile(f'(GJets.*|QCD_HT.*|W.*HT.*).*{year}')
region='cr_g_j'
for distribution in ['recoil','ak4_pt0','photon_pt0','met']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, ylim=(1e-3,1e5), outdir=f'./output/{os.path.basename(indir)}/{region}')
for distribution in ['ak4_phi0','photon_phi0']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, ylim=(4e4,5e5), outdir=f'./output/{os.path.basename(indir)}/{region}')
for distribution in ['ak4_eta0', 'photon_eta0']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, xlim=(-3,3),ylim=(1e4,1e6), outdir=f'./output/{os.path.basename(indir)}/{region}')
for distribution in ['ak4_chf0','ak4_nhf0']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, xlim=(0,1),ylim=(1e3,1e8), outdir=f'./output/{os.path.basename(indir)}/{region}')
def dielectron_plots():
for year in [2017,2018]:
data = re.compile(f'EGamma_{year}')
mc = re.compile(f'(EW.*|TTJets.*FXFX.*|ST.*|QCD_HT.*|Diboson.*|.*DYJetsToLL_M-50_HT_MLM.*){year}')
region='cr_2e_j'
for distribution in ['recoil','ak4_pt0','dielectron_mass','electron_pt', 'dielectron_pt','met']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, ylim=(1e-3,1e3), outdir=f'./output/{os.path.basename(indir)}/{region}')
for distribution in ['ak4_phi0','electron_phi','dielectron_mass']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, ylim=(1e1,1e5), outdir=f'./output/{os.path.basename(indir)}/{region}')
for distribution in ['ak4_eta0', 'electron_eta','dielectron_eta']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, xlim=(-3,3),ylim=(1e3,1e5), outdir=f'./output/{os.path.basename(indir)}/{region}')
for distribution in ['ak4_chf0','ak4_nhf0']:
make_plot(acc, region=region,distribution=distribution, year=year, data=data, mc=mc, xlim=(0,1),ylim=(1e2,1e6), outdir=f'./output/{os.path.basename(indir)}/{region}')
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 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
