def makeDataFrame(self):
sample_dict = {}
samples_all, samples_singlefake, samples_doublefake = createSampleLists(analysis_dir=self.analysis_dir, server = self.server, channel=self.channel)
working_samples = samples_doublefake
working_samples = setSumWeights(working_samples)
print('###########################################################')
print('# measuring doublefakerake...')
print('# %d samples to be used:'%(len(working_samples)))
print('###########################################################')
for w in working_samples: print('{:<20}{:<20}'.format(*[w.name,('path: '+w.ana_dir)]))
chain = TChain('tree') #TChain'ing all data samples together
for i,s in enumerate(working_samples):
sample = working_samples[0]
file_name = '/'.join([sample.ana_dir, sample.dir_name, sample.tree_prod_name, 'tree.root'])
chain.Add(file_name)
dataframe = RDataFrame(chain)
weight = 'weight * lhe_weight'
dataframe = dataframe.Define('w',weight)\
.Define('ptCone',self.ptCone())\
.Define('abs_hnl_hn_vis_eta','abs(hnl_hn_vis_eta)')\
.Define('abs_hnl_hn_eta','abs(hnl_hn_eta)')\
.Define('abs_l1_eta','abs(l1_eta)')\
.Define('abs_l2_eta','abs(l2_eta)')\
.Define('abs_l1_jet_flavour_parton','abs(l1_jet_flavour_parton)')\
.Define('abs_l2_jet_flavour_parton','abs(l2_jet_flavour_parton)')\
return dataframe
def produceLightTree(sample='DY',ch='mmm'):
if ch == 'mmm':
d17B = data_B_mmm+suffix; d17C = data_C_mmm+suffix; d17D = data_D_mmm+suffix; d17E = data_E_mmm+suffix; d17F = data_F_mmm+suffix;
SFR_012_L = SFR_MMM_012_L
l2_tight = l2_m_tight
if ch == 'eem':
d17B = data_B_eem+suffix; d17C = data_C_eem+suffix; d17D = data_D_eem+suffix; d17E = data_E_eem+suffix; d17F = data_F_eem+suffix;
t = rt.TChain('tree')
if sample == 'DY':
t.Add(DY)
t.Add(DY_ext)
if sample == 'data':
t.Add(d17B)
#t.Add(d17C)
#t.Add(d17D)
#t.Add(d17E)
#t.Add(d17F)
print '\n\ttotal entries:', t.GetEntries()
df = RDF(t)
df1 = df.Define('LOOSE', '1 * (' + SFR_012_L + ' && hnl_dr_12 > 0.3 && hnl_dr_02 > 0.3 && abs(hnl_m_01 - 91.19) < 10 && hnl_q_01 == 0 )' )
df2 = df1.Define('TIGHT', '1 * (' + SFR_012_L + ' && hnl_dr_12 > 0.3 && hnl_dr_02 > 0.3 && abs(hnl_m_01 - 91.19) < 10 && hnl_q_01 == 0 && ' + l2_tight + ')' )
num_L = df2.Filter('LOOSE == 1').Count().GetValue()
print '\n\tloose entries in MR:', num_L
num_T = df2.Filter('TIGHT == 1').Count().GetValue()
print '\n\ttight entries in MR:', num_T
df2 = df2.Define('ptcone', PTCONEL2)
branchList = rt.vector('string')()
for br in ['event', 'lumi', 'run', 'LOOSE', 'TIGHT', 'l2_reliso_rho_03', 'l2_Medium', 'l2_eta', 'l2_pt', 'l2_dxy', 'l2_dz', 'ptcone']:
branchList.push_back(br)
df2.Snapshot('tree', saveDir+'/%s_%s_6_24B_Lcut_29_4.root'%(sample,ch), branchList)
nargs='+',
help="list of collections to make plots of")
args = parser.parse_args()
models = {
'm': (';m_{{{0}}} [GeV]; Events', 50, 0, 1000),
'pt': (';p_{{T,{0}}} [GeV]; Events', 50, 0, 1000),
'eta': (';#eta_{{{0}}}; Events', 15, -3., 3.),
'phi': (';#phi_{{{0}}}; Events', 20, -4., 4.)
}
outdir = 'plots'
if args.output:
outdir = args.output
rdf = RDataFrame("CollectionTree", args.infile)
rdf = rdf.Define('wgt', 'EventInfoAuxDyn.mcEventWeights[0]')
canv = TCanvas('c', '', 800, 600)
for coll in args.do:
coll = coll.split(':')
if len(coll) != 1 and len(coll) != 4:
print('collection should either be "name" or "name:nbins:xmin:xmax"')
continue
varsuff = ''
if 'fatjet' in coll[0]:
cname = 'AntiKt10TruthTrimmedPtFrac5SmallR20JetsAux'
elif 'jet' in coll[0]:
cname = 'AntiKt4TruthDressedWZJetsAux'
elif 'electron' in coll[0]:
def measureSFR(self, drawPlot = False):
sample_dict = {}
samples_all, samples_singlefake, samples_doublefake = createSampleLists(analysis_dir=self.analysis_dir, server = self.server, channel=self.channel)
working_samples = samples_singlefake
working_samples = setSumWeights(working_samples)
print('###########################################################')
print('# measuring singlefakerake...')
print('# %d samples to be used:'%(len(working_samples)))
print('###########################################################')
for w in working_samples: print('{:<20}{:<20}'.format(*[w.name,('path: '+w.ana_dir)]))
chain = TChain('tree') #TChain'ing all data samples together
for i,s in enumerate(working_samples):
sample = working_samples[0]
file_name = '/'.join([sample.ana_dir, sample.dir_name, sample.tree_prod_name, 'tree.root'])
chain.Add(file_name)
dataframe = RDataFrame(chain)
weight = 'weight * lhe_weight'
dataframe = dataframe.Define('w',weight)\
.Define('ptCone',self.ptCone())\
.Define('abs_hnl_hn_vis_eta','abs(hnl_hn_vis_eta)')\
.Define('abs_hnl_hn_eta','abs(hnl_hn_eta)')\
.Define('abs_l1_eta','abs(l1_eta)')\
.Define('abs_l2_eta','abs(l2_eta)')\
.Define('abs_l1_jet_flavour_parton','abs(l1_jet_flavour_parton)')\
.Define('abs_l2_jet_flavour_parton','abs(l2_jet_flavour_parton)')\
# bins_ptCone = np.array([5.,10., 20., 30., 40.,70., 2000])
# bins_eta = np.array([0., 0.8, 1.2, 2.4])
bins_ptCone = np.array([5.,10., 20., 30., 40.,70.])
bins_eta = np.array([0., 0.8, 1.2, 2.4])
selection_baseline = getSelection(self.channel,'MR_SF')
selection_LL_uncorrelated = '(' + ' & '\
.join([\
selection_baseline,\
getSelection(self.channel,'L_L_uncorrelated')\
]) + ')'
selection_TT_uncorrelated = '(' + ' & '\
.join([\
selection_baseline,\
getSelection(self.channel,'L_L_uncorrelated'),\
getSelection(self.channel,'T_T')\
]) + ')'
h_LL_uncorrelated = dataframe\
.Filter(selection_LL_uncorrelated)\
.Histo2D(('h_LL_uncorrelated','h_LL_uncorrelated',len(bins_ptCone)-1,bins_ptCone, len(bins_eta)-1, bins_eta),'ptCone','abs_hnl_hn_vis_eta','w')
#name the axis, also initiate the dataframe call
h_LL_uncorrelated.SetTitle(';ptCone [GeV]; dimuon #eta')
h_TT_uncorrelated = dataframe\
.Filter(selection_TT_uncorrelated)\
.Histo2D(('h_TT_uncorrelated','h_TT_uncorrelated',len(bins_ptCone)-1,bins_ptCone, len(bins_eta)-1, bins_eta),'ptCone','abs_hnl_hn_vis_eta','w')
#name the axis, also initiate the dataframe call
h_TT_uncorrelated.SetTitle(';ptCone [GeV]; dimuon #eta')
# preparing the histo and save it into a .root file
sfr_TH2_dir = '/home/dehuazhu/HNL/CMSSW_9_4_6_patch1/src/PlotFactory/DataBkgPlots/modules/DDE_singlefake.root'
sfr_hist = h_TT_uncorrelated.Clone()
# sfr_hist = h_LL_uncorrelated.Clone()
# sfrhist = h_baseline.Clone()
# sfr_hist.Divide(h_LL_uncorrelated.Clone())
# dfr_hist.SaveAs(sfr_TH2_dir) #uncomment this to save the TH2
# draw the histo if required
if drawPlot == True:
can = TCanvas('can', '')
# sfr_hist.Draw('colzTextE')
# sfr_hist.Draw('colz')
sfr_hist.Draw()
pf.showlumi('%d entries'%(sfr_hist.GetEntries()))
# pf.showlogopreliminary()
can.Update()
set_trace()
lb=train + validation,
ub=100)
}
########
# Main #
########
if __name__ == '__main__':
args = parse_input()
gInterpreter.Declare('auto rand_gen = TRandom3({});'.format(args.seed))
init_frame = RDataFrame(args.tree, args.ntp)
rand_frame = init_frame.Define('rand_split', 'rand_gen.Uniform(0, 100)')
if args.debug:
print('loaded {} with {} entries'.format(
args.ntp,
rand_frame.Count().GetValue()))
cuts = get_cuts(args.train_ratio, args.validation_ratio)
for sample, cut in cuts.items():
subsample_frame = rand_frame.Filter(cut)
output_ntp = join(args.output_dir,
'{}_{}.root'.format(get_filename(args.ntp), sample))
subsample_frame.Snapshot(args.tree, output_ntp)
if args.debug:
print('sample: {}, cuts: {}'.format(sample, cut))
gInterpreter.Declare('''
Int_t getBin(Double_t x, Double_t y, TH2D* histo) {
return histo->FindFixBin(x, y);
}
auto getWeight(Double_t x, Double_t y, TH2D* histo) {
auto binIdx = getBin(x, y, histo);
return histo->GetBinContent(binIdx);
}
''')
gInterpreter.Declare(f'auto histoNtp = new TFile("{histoNtpN}", "read");')
gInterpreter.Declare(f'auto histo = dynamic_cast<TH2D*>(histoNtp->Get("{histoN}"));')
dfInit = RDataFrame(mcTreeN, mcNtpN)
df = dfInit.Define('wjk_alt', 'getWeight(b_ownpv_ndof, ntracks, histo)').Define('wt', 'wpid*wtrk*wjk_alt')
# NOTE: This comes from the existing ntuple
mcRootBrs = df.AsNumpy(columns=['wjk_occ', 'wjk_alt'])
wtJkOccRoot = mcRootBrs['wjk_occ']
wtJkOccAltRoot = mcRootBrs['wjk_alt']
histoRootMdl = TH2DModel(
'histoRoot', 'histoRoot',
20, 1, 200, 20, 0, 450
)
histoRoot = df.Histo2D(histoRootMdl, 'b_ownpv_ndof', 'ntracks', 'wt')
##################
# Histo w/ numpy #