def __init__(self, inputfile, year, ijob, njobs):
if inputfile.endswith('.txt'):
infiles = SplitUp(inputfile, njobs)[ijob - 1]
else:
infiles = inputfile
self.a = analyzer(infiles)
if inputfile.endswith('.txt'):
self.setname = inputfile.split('/')[-1].split('_')[0]
else:
self.setname = inputfile.split('/')[-1].split('_')[1]
self.year = year
self.ijob = ijob
self.njobs = njobs
self.config = OpenJSON('THconfig.json')
self.cuts = self.config['CUTS']
# self.dijetIdxs = [0,1]
self.trigs = {
16: ['HLT_PFHT800', 'HLT_PFHT900'],
17: ['HLT_PFHT1050', 'HLT_AK8PFJet500'],
18: [
'HLT_AK8PFJet400_TrimMass30', 'HLT_AK8PFHT850_TrimMass50',
'HLT_PFHT1050'
]
}
if 'Data' in inputfile:
self.a.isData = True
else:
self.a.isData = False
def __init__(self, tag, setname, year, filenames, cutstring=''):
super(BenchTIMBER, self).__init__(tag,
setname,
year,
filenames,
cutstring='')
self.a = analyzer(self.filenames)
if cutstring != '':
self.a.Cut("cutstring", cutstring)
self.a = AutoJME(self.a, "FatJet", year, "C")
self.outfilename = 'benchmark_out/TIMBER_' + self.tag + '.root'
def select(setname,year):
ROOT.ROOT.EnableImplicitMT(2) # Just use two threads - no need to kill the interactive nodes
# Initialize TIMBER analyzer
file_path = '%s/%s_bstar%s.root' %(rootfile_path,setname, year)
a = analyzer(file_path)
# Determine normalization weight
if not a.isData:
norm = helpers.getNormFactor(setname,year,config,a.genEventCount)
else:
norm = 1.
# Book actions on the RDataFrame
a.Cut('filters',a.GetFlagString(flags))
a.Cut('trigger',a.GetTriggerString(triggers))
a.Define('jetIdx','hemispherize(FatJet_phi, FatJet_jetId)') # need to calculate if we have two jets (with Id) that are back-to-back
a.Cut('nFatJets_cut','nFatJet > max(jetIdx[0],jetIdx[1])') # If we don't do this, we may try to access variables of jets that don't exist! (leads to seg fault)
a.Cut("hemis","(jetIdx[0] != -1)&&(jetIdx[1] != -1)") # cut on that calculation
a.Cut('pt_cut','FatJet_pt[jetIdx[0]] > 400 && FatJet_pt[jetIdx[1]] > 400')
a.Cut('eta_cut','abs(FatJet_eta[jetIdx[0]]) < 2.4 && abs(FatJet_eta[jetIdx[1]]) < 2.4')
a.Cut('mjet_cut','FatJet_msoftdrop[jetIdx[0]] > 50 && FatJet_msoftdrop[jetIdx[1]] > 50')
a.Cut('mtw_cut','analyzer::invariantMass(jetIdx[0],jetIdx[1],FatJet_pt,FatJet_eta,FatJet_phi,FatJet_msoftdrop) > 1200')
a.Define('lead_tau32','FatJet_tau2[jetIdx[0]] > 0 ? FatJet_tau3[jetIdx[0]]/FatJet_tau2[jetIdx[0]] : -1') # Conditional to make sure tau2 != 0 for division
a.Define('sublead_tau32','FatJet_tau2[jetIdx[1]] > 0 ? FatJet_tau3[jetIdx[1]]/FatJet_tau2[jetIdx[1]] : -1') # condition ? <do if true> : <do if false>
a.Define('lead_tau21','FatJet_tau1[jetIdx[0]] > 0 ? FatJet_tau2[jetIdx[0]]/FatJet_tau1[jetIdx[0]] : -1') # Conditional to make sure tau2 != 0 for division
a.Define('sublead_tau21','FatJet_tau1[jetIdx[1]] > 0 ? FatJet_tau2[jetIdx[1]]/FatJet_tau1[jetIdx[1]] : -1') # condition ? <do if true> : <do if false>
a.Define('norm',str(norm))
# Book a group to save the histograms
out = HistGroup("%s_%s"%(setname,year))
for varname in varnames.keys():
histname = '%s_%s_%s'%(setname,year,varname)
hist_tuple = (histname,histname,20,0,1) # Arguments for binning that you would normally pass to a TH1
hist = a.GetActiveNode().DataFrame.Histo1D(hist_tuple,varname,'norm') # Project dataframe into a histogram (hist name/binning tuple, variable to plot from dataframe, weight)
hist.GetValue() # This gets the actual TH1 instead of a pointer to the TH1
out.Add(varname,hist) # Add it to our group
# Return the group
return out
def select(setname, year):
ROOT.ROOT.EnableImplicitMT(
2) # Just use two threads - no need to kill the interactive nodes
# Initialize TIMBER analyzer
file_path = '%s/%s_bstar%s.root' % (rootfile_path, setname, year)
a = analyzer(file_path)
# Determine normalization weight
if not a.isData:
norm = helpers.getNormFactor(setname, year, config)
else:
norm = 1.
# Book actions on the RDataFrame
a.Cut('filters', a.GetFlagString(flags))
a.Cut('trigger', a.GetTriggerString(triggers))
a.Define(
'jetIdx', 'hemispherize(FatJet_phi, FatJet_jetId)'
) # need to calculate if we have two jets (with Id) that are back-to-back
a.Cut(
'nFatJets_cut', 'nFatJet > max(jetIdx[0],jetIdx[1])'
) # If we don't do this, we may try to access variables of jets that don't exist! (leads to seg fault)
a.Cut("hemis",
"(jetIdx[0] != -1)&&(jetIdx[1] != -1)") # cut on that calculation
a.Cut('pt_cut', 'FatJet_pt[jetIdx[0]] > 400 && FatJet_pt[jetIdx[1]] > 400')
a.Cut(
'eta_cut',
'abs(FatJet_eta[jetIdx[0]]) < 2.4 && abs(FatJet_eta[jetIdx[1]]) < 2.4')
a.Define('norm', str(norm))
#################################
# Build some variables for jets #
#################################
# Wtagging decision logic
# Returns 0 for no tag, 1 for lead tag, 2 for sublead tag, and 3 for both tag (which is physics-wise equivalent to 2)
wtag_str = "1*Wtag(FatJet_tau2[jetIdx[0]]/FatJet_tau1[jetIdx[0]],0,{0}, FatJet_msoftdrop[jetIdx[0]],65,105) + 2*Wtag(FatJet_tau2[jetIdx[1]]/FatJet_tau1[jetIdx[1]],0,{0}, FatJet_msoftdrop[jetIdx[1]],65,105)".format(
cuts['tau21'])
jets = VarGroup('jets')
jets.Add('wtag_bit', wtag_str)
jets.Add(
'top_bit', '(wtag_bit & 2)? 0: (wtag_bit & 1)? 1: -1'
) # (if wtag==3 or 2 (subleading w), top_index=0) else (if wtag==1, top_index=1) else (-1)
jets.Add('top_index', 'top_bit >= 0 ? jetIdx[top_bit] : -1')
jets.Add('w_index',
'top_index == 0 ? jetIdx[1] : top_index == 1 ? jetIdx[0] : -1')
# Calculate some new comlumns that we'd like to cut on (that were costly to do before the other filtering)
jets.Add(
"lead_vect",
"hardware::TLvector(FatJet_pt[jetIdx[0]],FatJet_eta[jetIdx[0]],FatJet_phi[jetIdx[0]],FatJet_msoftdrop[jetIdx[0]])"
)
jets.Add(
"sublead_vect",
"hardware::TLvector(FatJet_pt[jetIdx[1]],FatJet_eta[jetIdx[1]],FatJet_phi[jetIdx[1]],FatJet_msoftdrop[jetIdx[1]])"
)
jets.Add("deltaY", "abs(lead_vect.Rapidity()-sublead_vect.Rapidity())")
jets.Add("mtw", "hardware::invariantMass({lead_vect,sublead_vect})")
#########
# N - 1 #
#########
plotting_vars = VarGroup(
'plotting_vars') # assume leading is top and subleading is W
plotting_vars.Add("mtop", "FatJet_msoftdrop[jetIdx[0]]")
plotting_vars.Add("mW", "FatJet_msoftdrop[jetIdx[1]]")
plotting_vars.Add("tau32", "FatJet_tau3[jetIdx[0]]/FatJet_tau2[jetIdx[0]]")
plotting_vars.Add(
"subjet_btag",
"max(SubJet_btagDeepB[FatJet_subJetIdx1[jetIdx[0]]],SubJet_btagDeepB[FatJet_subJetIdx2[jetIdx[0]]])"
)
plotting_vars.Add("tau21", "FatJet_tau2[jetIdx[1]]/FatJet_tau1[jetIdx[1]]")
plotting_vars.Add("lead_jet_deepAK8_MD_WvsQCD",
"FatJet_deepTagMD_WvsQCD[jetIdx[0]]")
plotting_vars.Add("sublead_jet_deepAK8_MD_WvsQCD",
"FatJet_deepTagMD_WvsQCD[jetIdx[1]]")
plotting_vars.Add("lead_jet_deepAK8_MD_TvsQCD",
"FatJet_deepTagMD_TvsQCD[jetIdx[0]]")
plotting_vars.Add("sublead_jet_deepAK8_MD_TvsQCD",
"FatJet_deepTagMD_TvsQCD[jetIdx[1]]")
N_cuts = CutGroup('Ncuts') # cuts
N_cuts.Add("deltaY_cut", "deltaY<1.6")
N_cuts.Add("mtop_cut", "(mtop > 105.)&&(mtop < 220.)")
N_cuts.Add("mW_cut", "(mW > 65.)&&(mW < 105.)")
#N_cuts.Add("tau32_cut", "(tau32 > 0.0)&&(tau32 < %s)"%(cuts['tau32']))
#N_cuts.Add("subjet_btag_cut", "(subjet_btag > %s)&&(subjet_btag < 1.)"%(cuts['sjbtag']))
#N_cuts.Add("tau21_cut", "(tau21 > 0.0)&&(tau21 < %s)"%(cuts['tau21']))
N_cuts.Add("lead_jet_deepAK8_MD_WvsQCD_cut",
"lead_jet_deepAK8_MD_WvsQCD > 0.9")
N_cuts.Add("sublead_jet_deepAK8_MD_WvsQCD_cut",
"sublead_jet_deepAK8_MD_WvsQCD > 0.9")
N_cuts.Add("lead_jet_deepAK8_MD_TvsQCD_cut",
"lead_jet_deepAK8_MD_TvsQCD > 0.9")
N_cuts.Add("sublead_jet_deepAK8_MD_TvsQCD_cut",
"sublead_jet_deepAK8_MD_TvsQCD > 0.9")
# Organize N-1 of tagging variables when assuming top is always leading
nodeToPlot = a.Apply([jets, plotting_vars])
nminus1Nodes = a.Nminus1(
N_cuts, nodeToPlot
) # constructs N nodes with a different N-1 selection for each
nminus1Hists = HistGroup('nminus1Hists')
binning = {
'mtop': [25, 50, 300],
'mW': [25, 30, 270],
'tau32': [20, 0, 1],
'tau21': [20, 0, 1],
'subjet_btag': [20, 0, 1],
'deltaY': [20, 0, 2.0],
'lead_jet_deepAK8_MD_WvsQCD': [20, 0, 1],
'sublead_jet_deepAK8_MD_WvsQCD': [20, 0, 1],
'lead_jet_deepAK8_MD_TvsQCD': [20, 0, 1],
'sublead_jet_deepAK8_MD_TvsQCD': [20, 0, 1]
}
# Add hists to group and write out
for nkey in nminus1Nodes.keys():
if nkey == 'full': continue
var = nkey.replace('_cut', '').replace('minus_', '')
hist_tuple = (var, var, binning[var][0], binning[var][1],
binning[var][2])
hist = nminus1Nodes[nkey].DataFrame.Histo1D(hist_tuple, var, 'norm')
hist.GetValue()
nminus1Hists.Add(var, hist)
a.PrintNodeTree('exercises/nminus1_tree.dot')
# Return the group
return nminus1Hists
'''Plot the Missing ET for events that have an opposite-sign muon
pair mass in the range 60-120 GeV (double loop over single collection, math)'''
import time
start = time.time()
#---------------------
from TIMBER.Analyzer import analyzer
from TIMBER.Tools.Common import CompileCpp
CompileCpp('benchmark/ex.cc')
a = analyzer('examples/GluGluToHToTauTau_full.root')
a.Cut('twoMuons','nMuon>1')
a.Define('invMassMuMu','InvMassOppMuMu(Muon_pt, Muon_eta, Muon_phi, Muon_mass, Muon_charge)')
a.Cut('invMassMuMu_cut','Any(invMassMuMu > 60 && invMassMuMu < 120)')
h = a.DataFrame.Histo1D('MET_pt')
h.Draw('hist e')
#---------------------
print ('%s secs'%(time.time() - start))
def select(setname, year):
ROOT.ROOT.EnableImplicitMT(
2) # Just use two threads - no need to kill the interactive nodes
# Initialize TIMBER analyzer
file_path = '%s/%s_bstar%s.root' % (rootfile_path, setname, year)
a = analyzer(file_path)
# Determine normalization weight
if not a.isData:
# For MC we need to apply the xsec * lumi / NumberOfGeneratedEvents weight
# This function is a helper defined here: https://github.com/cmantill/BstarToTW_CMSDAS2021/blob/master/helpers.py#L5-L18
norm = helpers.getNormFactor(setname, year, config, a.genEventCount)
else:
norm = 1.
# Book actions on the RDataFrame
# First - we will cut on the filters we specified above
a.Cut('filters', a.GetFlagString(flags))
a.Cut('trigger', a.GetTriggerString(triggers))
# Second - we need to calculate if we have two jets (with Id) that are back-to-back
# The following function will check for jets in opposite hemispheres (of phi) that also pass a jetId
# it is defined here: https://github.com/cmantill/BstarToTW_CMSDAS2021/blob/master/bstar.cc#L17-L66
# so first we *define* jetIdx as the index of these two jets back-to-back - ordered by pT
a.Define('jetIdx', 'hemispherize(FatJet_phi, FatJet_jetId)')
# Third - we will perform a selection:
# by requiring at least two fat-jets (step 1) that are back to back (step 2) and that have a minimum pT of 400 (step 3)
# some of these functions used below such as max() and Sum() are defined in RDataFrame - see the cheatsheet: https://root.cern/doc/master/classROOT_1_1RDataFrame.html#cheatsheet
a.Cut(
'nFatJets_cut', 'nFatJet > max(jetIdx[0],jetIdx[1])'
) # (step 1) If we don't do this, we may try to access variables of jets that don't exist! (leads to seg fault)
a.Cut(
"hemis", "(jetIdx[0] != -1)&&(jetIdx[1] != -1)"
) # (step 2) we cut on the variable we just defined - so that both jet indices exist and are different that the default value -1
a.Cut(
'pt_cut',
'FatJet_pt[jetIdx[0]] > 400 && FatJet_pt[jetIdx[1]] > 400') # (step 3)
# Now we are ready to define our first variable to plot: lead_jetPt
a.Define('lead_jetPt', 'FatJet_pt[jetIdx[0]]')
#ADD SOFT DROP MASS
a.Define('lead_softdrop_mass', 'FatJet_msoftdrop[jetIdx[0]]')
# a.Cut('softdrop_cut','lead_softdrop_mass > 50')
#EX 2 ADD MORE VARS
# a.Define('lead_jet_pt','FatJet_pt[jetIdx[0]]')
a.Define('lead_jet_pt_nom', 'FatJet_pt_nom[jetIdx[0]]')
a.Define('lead_tau2', 'FatJet_tau2')
a.Define(
'lead_tau21',
'FatJet_tau1[jetIdx[0]] > 0 ? FatJet_tau2[jetIdx[0]]/FatJet_tau1[jetIdx[0]] : -1'
) #Don't divide by zero
a.Define(
'lead_tau32',
'FatJet_tau2[jetIdx[0]] > 0 ? FatJet_tau3[jetIdx[0]]/FatJet_tau2[jetIdx[0]] : -1'
)
a.Define('lead_deepAK8_Wscore', 'FatJet_deepTagMD_WvsQCD[jetIdx[0]]')
a.Define('lead_deepAK8_topscore', 'FatJet_deepTagMD_TvsQCD[jetIdx[0]]')
a.Define('sublead_softdrop_mass', 'FatJet_msoftdrop[jetIdx[1]]')
a.Define('sublead_jet_pt', 'FatJet_pt[jetIdx[1]]')
a.Define('sublead_jet_pt_nom', 'FatJet_pt_nom[jetIdx[1]]')
a.Define(
'sublead_tau21',
'FatJet_tau1[jetIdx[1]] > 0 ? FatJet_tau2[jetIdx[1]]/FatJet_tau1[jetIdx[1]] : -1'
)
a.Define(
'sublead_tau32',
'FatJet_tau2[jetIdx[1]] > 0 ? FatJet_tau3[jetIdx[1]]/FatJet_tau2[jetIdx[1]] : -1'
)
a.Define('sublead_deepAK8_Wscore', 'FatJet_deepTagMD_WvsQCD[jetIdx[1]]')
a.Define('sublead_deepAK8_topscore', 'FatJet_deepTagMD_TvsQCD[jetIdx[1]]')
a.Define(
'lead_vector',
'hardware::TLvector(FatJet_pt[jetIdx[0]],FatJet_eta[jetIdx[0]],FatJet_phi[jetIdx[0]],FatJet_mass[jetIdx[0]])'
)
a.Define(
'sublead_vector',
'hardware::TLvector(FatJet_pt[jetIdx[1]],FatJet_eta[jetIdx[1]],FatJet_phi[jetIdx[1]],FatJet_mass[jetIdx[1]])'
)
a.Define('invariantMass',
'hardware::invariantMass({lead_vector,sublead_vector})')
# To define our second variable, the number of loose b-jets, let's define the b-tagging working points
# These [loose, medium, tight] working points are for the DeepCSV variable (ranging between 0 and 1) - saved in NanoAOD as Jet_btagDeepB:
bcut = []
if year == '16':
bcut = [0.2217, 0.6321, 0.8953]
elif year == '17':
bcut = [0.1522, 0.4941, 0.8001]
elif year == '18':
bcut = [0.1241, 0.4184, 0.7571]
# Then, we use the Sum function of RDataFrame to count the number of AK4Jets with DeepCSV score larger than the loose WP
a.Define('nbjet_loose',
'Sum(Jet_btagDeepB > ' + str(bcut[0]) + ')') # DeepCSV loose WP
# Finally let's define the normalization weight of the sample as one variable as well
a.Define('norm', str(norm))
# A nice functionality of TIMBER is to print all the selections that we have done:
a.PrintNodeTree(plotdir + '/signal_tree.dot', verbose=True)
# Now we are ready to save histograms (in a HistGroup)
out = HistGroup("%s_%s" % (setname, year))
for varname in varnames.keys():
histname = '%s_%s_%s' % (setname, year, varname)
# Arguments for binning that you would normally pass to a TH1 (histname, histname, number of bins, min bin, max bin)
if "nbjet" in varname:
hist_tuple = (histname, histname, 10, 0, 10)
elif "lead_jet" in varname:
hist_tuple = (histname, histname, 30, 0, 3000)
elif "lead_softdrop" in varname:
hist_tuple = (histname, histname, 30, 0, 300)
elif "lead_tau21" in varname:
hist_tuple = (histname, histname, 30, 0, 1)
elif "lead_tau2" in varname:
hist_tuple = (histname, histname, 30, 0, 1)
elif "lead_tau32" in varname:
hist_tuple = (histname, histname, 30, 0, 1)
elif "lead_deepAK8_Wscore" in varname:
hist_tuple = (histname, histname, 30, 0, 1)
elif "lead_deepAK8_topscore" in varname:
hist_tuple = (histname, histname, 30, 0, 1)
elif "Mass" in varname:
hist_tuple = (histname, histname, 50, 0, 5000)
# print(varname)
# elif "Pt" in varname :
# hist_tuple = (histname,histname,30,400,2000)
# elif "msd" in varname :
# hist_tuple = (histname,histname,30,40,200)
# else:
# hist_tuple = (histname,histname,30,40,200)
hist = a.GetActiveNode().DataFrame.Histo1D(
hist_tuple, varname, 'norm'
) # Project dataframe into a histogram (hist name/binning tuple, variable to plot from dataframe, weight)
hist.GetValue(
) # This gets the actual TH1 instead of a pointer to the TH1
out.Add(varname, hist) # Add it to our group
# Return the group
return out
def setup_class(cls):
cls.a = analyzer('examples/GluGluToHToTauTau.root')
cls.a.Cut("test_cut1", "Jet_pt.size() > 0")
def select(setname, year):
ROOT.ROOT.EnableImplicitMT(
2) # Just use two threads - no need to kill the interactive nodes
# Initialize TIMBER analyzer
file_path = '%s/%s_bstar%s.root' % (rootfile_path, setname, year)
a = analyzer(file_path)
# Determine normalization weight
if not a.isData:
norm = helpers.getNormFactor(setname, year, config, a.genEventCount)
else:
norm = 1.
# Book actions on the RDataFrame
a.Cut('filters', a.GetFlagString(flags))
a.Cut('trigger', a.GetTriggerString(triggers))
a.Define(
'jetIdx', 'hemispherize(FatJet_phi, FatJet_jetId)'
) # need to calculate if we have two jets (with Id) that are back-to-back
a.Cut(
'nFatJets_cut', 'nFatJet > max(jetIdx[0],jetIdx[1])'
) # If we don't do this, we may try to access variables of jets that don't exist! (leads to seg fault)
a.Cut("hemis",
"(jetIdx[0] != -1)&&(jetIdx[1] != -1)") # cut on that calculation
a.Cut('pt_cut', 'FatJet_pt[jetIdx[0]] > 400 && FatJet_pt[jetIdx[1]] > 400')
a.Cut(
'eta_cut',
'abs(FatJet_eta[jetIdx[0]]) < 2.4 && abs(FatJet_eta[jetIdx[1]]) < 2.4')
a.Cut(
'mjet_cut',
'FatJet_msoftdrop[jetIdx[0]] > 50 && FatJet_msoftdrop[jetIdx[1]] > 50')
a.Define(
'lead_vector',
'hardware::TLvector(Jet_pt[jetIdx[0]],Jet_eta[jetIdx[0]],Jet_phi[jetIdx[0]],Jet_mass[jetIdx[0]])'
)
a.Define(
'sublead_vector',
'hardware::TLvector(Jet_pt[jetIdx[1]],Jet_eta[jetIdx[1]],Jet_phi[jetIdx[1]],Jet_mass[jetIdx[1]])'
)
a.Define('invariantMass',
'hardware::invariantMass({lead_vector,sublead_vector})')
a.Cut('mtw_cut', 'invariantMass > 1200')
a.Define(
'deltaphi',
'hardware::DeltaPhi(FatJet_phi[jetIdx[0]],FatJet_phi[jetIdx[1]])')
a.Define(
'lead_tau32',
'FatJet_tau2[jetIdx[0]] > 0 ? FatJet_tau3[jetIdx[0]]/FatJet_tau2[jetIdx[0]] : -1'
) # Conditional to make sure tau2 != 0 for division
a.Define(
'sublead_tau32',
'FatJet_tau2[jetIdx[1]] > 0 ? FatJet_tau3[jetIdx[1]]/FatJet_tau2[jetIdx[1]] : -1'
) # condition ? <do if true> : <do if false>
a.Define(
'lead_tau21',
'FatJet_tau1[jetIdx[0]] > 0 ? FatJet_tau2[jetIdx[0]]/FatJet_tau1[jetIdx[0]] : -1'
) # Conditional to make sure tau2 != 0 for division
a.Define(
'sublead_tau21',
'FatJet_tau1[jetIdx[1]] > 0 ? FatJet_tau2[jetIdx[1]]/FatJet_tau1[jetIdx[1]] : -1'
) # condition ? <do if true> : <do if false>
a.Define('lead_deepAK8_TvsQCD', 'FatJet_deepTag_TvsQCD[jetIdx[0]]')
a.Define('sublead_deepAK8_TvsQCD', 'FatJet_deepTag_TvsQCD[jetIdx[1]]')
a.Define('lead_deepAK8_WvsQCD', 'FatJet_deepTag_WvsQCD[jetIdx[0]]')
a.Define('sublead_deepAK8_WvsQCD', 'FatJet_deepTag_WvsQCD[jetIdx[1]]')
bcut = []
if year == '16':
bcut = [0.2217, 0.6321, 0.8953]
elif year == '17':
bcut = [0.1522, 0.4941, 0.8001]
elif year == '18':
bcut = [0.1241, 0.4184, 0.7571]
a.Define('nbjet_loose',
'Sum(Jet_btagDeepB > ' + str(bcut[0]) + ')') # DeepCSV loose WP
a.Define('nbjet_medium',
'Sum(Jet_btagDeepB > ' + str(bcut[1]) + ')') # DeepCSV medium WP
a.Define('nbjet_tight',
'Sum(Jet_btagDeepB > ' + str(bcut[2]) + ')') # DeepCSV tight WP
a.Define('lead_jetPt', 'FatJet_pt[jetIdx[0]]')
a.Define('sublead_jetPt', 'FatJet_pt[jetIdx[1]]')
a.Define('lead_softdrop_mass', 'FatJet_msoftdrop[jetIdx[0]]')
a.Define('sublead_softdrop_mass', 'FatJet_msoftdrop[jetIdx[1]]')
a.Define('norm', str(norm))
# Book a group to save the histograms
out = HistGroup("%s_%s" % (setname, year))
for varname in varnames.keys():
histname = '%s_%s_%s' % (setname, year, varname)
# Arguments for binning that you would normally pass to a TH1
if "nbjet" in varname:
hist_tuple = (histname, histname, 10, 0, 10)
elif "tau" in varname:
hist_tuple = (histname, histname, 20, 0, 1)
elif "Pt" in varname:
hist_tuple = (histname, histname, 30, 400, 1000)
elif "phi" in varname:
hist_tuple = (histname, histname, 30, -3.2, 3.2)
elif "softdrop_mass" in varname:
hist_tuple = (histname, histname, 30, 0, 300)
else:
hist_tuple = (histname, histname, 20, 0, 1)
hist = a.GetActiveNode().DataFrame.Histo1D(
hist_tuple, varname, 'norm'
) # Project dataframe into a histogram (hist name/binning tuple, variable to plot from dataframe, weight)
hist.GetValue(
) # This gets the actual TH1 instead of a pointer to the TH1
out.Add(varname, hist) # Add it to our group
# Return the group
return out
'''Plot the sum of the pT of jets with pT > 30 GeV that are not within 0.4 from any lepton with pt > 10 GeV (looping over two collections)'''
import time
start = time.time()
#---------------------
from TIMBER.Analyzer import analyzer
from TIMBER.Tools.Common import CompileCpp
CompileCpp('benchmark/ex.cc')
a = analyzer(
'examples/ttbar16_sample.root'
) # GluGlu sample is incomplete and missing electrons - this is a private stand in that must be replaced to work
a.MergeCollections("Lepton", ["Electron", "Muon"])
nearLep = 'CloseLepVeto (Lepton_pt, Lepton_eta, Lepton_phi, Jet_eta, Jet_phi)'
a.Define('goodJet_pt', 'Jet_pt[!(%s)]' % nearLep)
a.Define('goodJet_pt30', 'goodJet_pt[goodJet_pt > 30]')
a.Define('PtSum', 'Sum(goodJet_pt30)')
h = a.DataFrame.Histo1D('PtSum')
h.Draw('hist e')
#---------------------
print('%s secs' % (time.time() - start))
from TIMBER.Analyzer import analyzer import sys a = analyzer(sys.argv[1]) print(a.RunChain.genEventCount_) # print (a.RunChain.genEventSumw_) # print (a.RunChain.genEventSumw2_)
import ROOT
from TIMBER.Analyzer import analyzer
from TIMBER.Tools.AutoPU import MakePU
if __name__ == "__main__":
from argparse import ArgumentParser
parser = ArgumentParser()
parser.add_argument('-s',
type=str,
dest='setname',
action='store',
required=True,
help='Setname to process.')
parser.add_argument('-y',
type=str,
dest='era',
action='store',
required=True,
help='Year of set (16, 17, 18).')
args = parser.parse_args()
fullname = '%s_%s' % (args.setname, args.era)
out = ROOT.TFile.Open('THpileup_%s.root' % (fullname), 'RECREATE')
a = analyzer('raw_nano/%s.txt' % (fullname))
hptr = MakePU(a, args.era, ULflag=True)
hout = hptr.Clone()
out.WriteTObject(hout, fullname)
#h.Write()
out.Close()
def setup_class(cls):
cls.a = analyzer('examples/GluGluToHToTauTau.root')
