#Can handle more than one input ana file if needed, just add to list
inputFiles = [argv[1] + "/" + x for x in listdir(argv[1])]
vtxChain = TChain("VertexTree")
LEEChain = TChain("LEE1e1pTree")
angleChain = TChain("AngleAnalysis")
shapeChain = TChain("ShapeAnalysis")
gapChain = TChain("GapAnalysis")
dqdsChain = TChain("dQdSAnalysis")
matchChain = TChain("MatchAnalysis")
eventChain = TChain("EventVertexTree")
for infile in inputFiles:
vtxChain.Add(infile)
LEEChain.Add(infile)
angleChain.Add(infile)
shapeChain.Add(infile)
gapChain.Add(infile)
dqdsChain.Add(infile)
matchChain.Add(infile)
eventChain.Add(infile)
vtxChain.AddFriend(LEEChain)
vtxChain.AddFriend(angleChain)
vtxChain.AddFriend(shapeChain)
vtxChain.AddFriend(gapChain)
vtxChain.AddFriend(dqdsChain)
vtxChain.AddFriend(matchChain)
#!/usr/bin/env python
from ROOT import TFile, TTree, TH1F, TH1D, TH1, TCanvas, TChain, TGraphAsymmErrors, TMath, TH2D, TLorentzVector, AddressOf, gROOT, TNamed
import ROOT as ROOT
import os
import sys, optparse
from array import array
import math
import numpy as numpy_
ROOT.gROOT.LoadMacro("Loader.h+")
outfilename = "ntupleHistos.root"
ntuple = TChain("outTree")
ntuple.Add(sys.argv[1])
NEntries = ntuple.GetEntries()
if len(sys.argv) > 2:
#if sys.argv[2]=="test":
NEntries = int(sys.argv[2])
print "WARNING: Running in TEST MODE"
print 'NEntries = ' + str(NEntries)
h_z_ratio = TH1F('h_z_ratio', 'h_z_ratio', 100, 0, 40)
h_SubJet_csv = TH1F('h_SubJet_csv', 'h_SubJet_csv', 100, 0., 1.)
# h_trackSipdSig_3 =TH1F('h_trackSipdSig_3', 'h_trackSipdSig_3', 20,-10.,10.)
# h_trackSipdSig_2 =TH1F('h_trackSipdSig_2', 'h_trackSipdSig_2', 6,0.,6.)
# h_trackSipdSig_1 =TH1F('h_trackSipdSig_1', 'h_trackSipdSig_1', 80,0.,800.)
# h_trackSipdSig_0 =TH1F('h_trackSipdSig_0', 'h_trackSipdSig_0', 80,0.,400.)
# h_trackSipdSig_1_0 =TH1F('h_trackSipdSig_1_0', 'h_trackSipdSig_1_0', 80,0.,400.)
}
for dataType, dataFile, in dataTypes.iteritems():
for ch, hists in channel.iteritems():
filepath='' # Find appropriate file path
if dataType == 'MC': filepath = basepath+dataFile[0]
elif dataType == 'Data' and ch == 'E' : filepath = basepath+dataFile[0]
elif dataType == 'Data' and ch == 'Mu' : filepath = basepath+dataFile[1]
print dataType
print ch
print filepath
treepath = 'TTbar_plus_X_analysis/'+ch+'PlusJets/Cutflow/Cutflow' # Find appropriate tree
chain = TChain(treepath)
chain.Add(filepath)
nevent=0
for event in chain:
nevent=nevent+1
if nevent==10000 : break
tag = event.__getattr__("Cutflow") # Get list of cuts in bool form
passLastCut=True
for i, cut in enumerate(tag) : # Loop over list of cuts
if dataType == 'Data' : hist = hists[0] # Choose between MC and Data Histograms
elif dataType == 'MC' : hist = hists[1]
if (ch == 'Mu' and i >= 6) : cutName = Cuts[i+1] # Skip Conversion Label
def GetReweightedYieldAndError(condor_dir, process, channel, srcCTau, dstCTau,
limitType):
global printLock
if os.path.isfile('condor/' + condor_dir + '/' + process +
'.root') and not '_1cm_' in process:
return GetYieldAndError(condor_dir, process, channel)
realProcessName = process.replace(dstCTau, srcCTau)
if arguments.verbose:
printLock.acquire()
print 'Reweighting yield from ' + realProcessName + ' to ' + process + ' ...'
printLock.release()
chain = TChain(signal_channel_tree)
chain.Add('condor/' + condor_dir + '/' + realProcessName + '/hist_*.root')
lifetimeWeightName = 'eventvariable_lifetimeWeight_1000024_' + srcCTau + 'To' + dstCTau
realInputFile = TFile('condor/' + condor_dir + '/' + realProcessName +
'.root')
nGenerated = realInputFile.Get(
channel.replace('Plotter/Met Plots',
'CutFlowPlotter/eventCounter')).GetEntries()
crossSectionWeight = 1.0
if process != data_dataset:
crossSectionWeight *= lumi / nGenerated
if arguments.limitType == "higgsino":
crossSectionWeight *= float(signal_cross_sections_higgsino[
process.split('_')[1][:-3]]['value'])
elif arguments.limitType == "wino":
crossSectionWeight *= float(
signal_cross_sections[process.split('_')[2][:-3]]['value'])
totalWeight = 0.0
totalWeight2 = 0.0
for iEvent in range(chain.GetEntries()):
chain.GetEntry(iEvent)
if lifetimeWeightName == 'eventvariable_lifetimeWeight_1000024_10cmTo1cm':
lifetimeWeight = GetMissingLifetimeWeight(chain)
else:
lifetimeWeight = getattr(chain, lifetimeWeightName)
if chain.eventvariable_cTau_1000024_0 < 0:
printLock.acquire()
print 'WARNING: somehow event number ' + str(
iEvent
) + ' in sample ' + process + ' has no charginos at all! Ignoring this event...'
printLock.release()
continue # or lifetimeWeight = 0 really
thisWeight = crossSectionWeight * lifetimeWeight * chain.eventvariable_isrWeight * chain.eventvariable_grandOrWeight * chain.eventvariable_puScalingFactor
if arguments.era.startswith('2017_'):
thisWeight *= chain.eventvariable_L1ECALPrefiringWeight
totalWeight += thisWeight
totalWeight2 += thisWeight * thisWeight
yieldAndError = {
'yield':
totalWeight,
'rawYield':
chain.GetEntries(),
'error':
1.0 +
(math.sqrt(totalWeight2) / totalWeight) if totalWeight > 0.0 else 1.0,
'absError':
math.sqrt(totalWeight2) if totalWeight2 > 0.0 else 1.1,
'weight':
totalWeight / chain.GetEntries() if chain.GetEntries() > 0.0 else 0.0,
'acceptance':
totalWeight / nGenerated / crossSectionWeight,
'acceptanceError':
(math.sqrt(totalWeight2) if totalWeight2 > 0.0 else 1.1) / nGenerated /
crossSectionWeight,
}
return yieldAndError
def applyThresholdCut(dsNum):
""" ./plots2.py -thr [dsNum]
Create "after cuts" histograms for each dataset (similar to genRawHists)
Use a super fine binning and huge energy range for versatility.
Don't distinguish between enriched and natural detectors in 2D plots.
1. sum histogram 'hSum'
2. cpd vs energy 'hCPDE'
3. cpd vs run 'hCPDrun'
"""
threshCutE = 0.9 # require the mu to be at least this high to keep the channel
kpb = 0.01
eLo, eHi = 0., 15000.
nBins = int((eHi-eLo)/kpb)
chList = ds.GetGoodChanList(dsNum)
chList = [ch for ch in chList if ch!=692 and ch!=1232]
calDB = db.TinyDB('../calDB.json')
pars = db.Query()
hTot = TH1D("hTot","hTot",nBins,eLo,eHi)
hEnr = TH1D("hEnr","hEnr",nBins,eLo,eHi)
hNat = TH1D("hNat","hNat",nBins,eLo,eHi)
fList, fMissing, fNoThresh, fCut = [], [], [], []
dsPath = "/global/homes/w/wisecg/project/cuts/fs_rn_wf"
runLo, runHi = 0, 0
for bkgIdx in range(ds.dsMap[dsNum]+1):
if bkgIdx % 10 == 0 and bkgIdx > 0: print 100. * bkgIdx / float(ds.dsMap[dsNum]+1), "% done."
threshKey = "thresh_ds%d_bkgidx%d" % (dsNum, bkgIdx)
recList = calDB.search(pars.key == threshKey)
if len(recList)!=1:
print "Error: found too many records for key:",threshKey
for record in recList:
print record
return
threshDict = recList[0]['vals']
for chan in chList:
# save threshold information
chKey = u'%d' % chan
if chKey not in threshDict.keys():
fNoThresh.append([dsNum,bkgIdx,chan])
continue
mu, sig = threshDict[u'%d' % chan][0], threshDict[u'%d' % chan][1]
# save file paths
fName = "%s/fs_rn_wf-DS%d-%d-ch%d.root" % (dsPath, dsNum, bkgIdx, chan)
if os.path.isfile(fName) == True:
if 0. < mu < threshCutE:
fList.append(fName)
# print "ch %d bkgIdx %d mu %.2f sig %.2f" % (chan,bkgIdx,mu,sig)
else:
fCut.append(fName)
# print "ch %d bkgIdx %d mu %.2f sig %.2f" % (chan,bkgIdx,mu,sig)
else:
fMissing.append(fName)
continue
# calculate efficiency curve
thisErf = TF1("thisErf","0.5*(1+TMath::Erf((x-[0])/(TMath::Sqrt(2)*[1]) ))")
thisErf.SetParameter(0,mu)
thisErf.SetParameter(1,abs(sig))
fTmp = TFile(fName)
tTmp = fTmp.Get("skimTree")
tTmp.GetEntry(0)
if runLo==0: runLo = tTmp.run
tTmp.GetEntry(tTmp.GetEntries()-1)
if tTmp.run > runHi:
runHi = tTmp.run
cTmp = fTmp.Get("chanCut").GetTitle()
hTmp = wl.H1D(tTmp,nBins,eLo,eHi,"trapENFCal",cTmp,"hTmp","hTmp")
hTmp.Divide(thisErf)
hTot.Add(hTmp)
hTmpEnr = wl.H1D(tTmp,nBins,eLo,eHi,"trapENFCal",cTmp+" && isEnr && trapENFCal > %.1f" % mu,"hTmpEnr","hTmpEnr")
hTmpEnr.Divide(thisErf)
hEnr.Add(hTmpEnr)
hTmpNat = wl.H1D(tTmp,nBins,eLo,eHi,"trapENFCal",cTmp+" && !isEnr && trapENFCal > %.1f" % mu,"hTmpNat","hTmpNat")
hTmpNat.Divide(thisErf)
hNat.Add(hTmpNat)
print "DS-%d nFound: %d nMissing: %d nCut: %d nNoThresh: %d" % (dsNum,len(fList),len(fMissing),len(fCut),len(fNoThresh))
# save to a permanent place
fOut = TFile("../data/latThresh_DS%d.root" % dsNum, "RECREATE")
hTot.Write()
hEnr.Write()
hNat.Write()
# load the full chain w/ files passing threshold cut (but no efficiency correction applied.)
chainFSRNWF = TChain("skimTree")
[chainFSRNWF.Add(f) for f in fList]
hFSRNWF = wl.H1D(chainFSRNWF,nBins,eLo,eHi,"trapENFCal","","trapENFCal","","hFSRNWF")
cpdLo, cpdHi = 111, 175
if dsNum==4: cpdLo, cpdHi = 211, 275
if dsNum==5: cpdLo, cpdHi = 111, 275
nCPD = cpdHi - cpdLo
hCPDE = wl.H2D(chainFSRNWF,nBins,eLo,eHi,nCPD,cpdLo,cpdHi,"C*100+P*10+D:trapENFCal","","trapENFCal","CPD","CPD vs. E","hCPDE")
hCPDE.Write()
chainFSRNWF.GetEntry(0)
runLo = chainFSRNWF.run
chainFSRNWF.GetEntry(chainFSRNWF.GetEntries()-1)
runHi = chainFSRNWF.run
nRuns = runHi - runLo + 1
print "First run:",runLo,"Last run:",runHi
nRuns = runHi - runLo + 1
hCPDrun = wl.H2D(chainFSRNWF,nRuns,runLo,runHi,nCPD,cpdLo,cpdHi,"C*100+P*10+D:run","","run","CPD","CPD vs. run","hCPDrun")
hCPDrun.Write()
kpb = 0.1
rebinFactor = int(kpb/0.01)
hTot = hTot.Rebin(rebinFactor) # this creates a new histogram
hTot.GetXaxis().SetRangeUser(0.,12.)
c = TCanvas("c","Shan is pretty",800,600)
c.SetLogy(1)
hTot.SetMinimum(0.5)
hTot.SetLineColor(ROOT.kBlue)
hTot.SetTitle("")
hTot.GetXaxis().SetTitle("trapENFCal")
hTot.GetYaxis().SetTitle("Counts")
hTot.Draw("hist")
hFSRNWF = hFSRNWF.Rebin(rebinFactor)
hFSRNWF.GetXaxis().SetRangeUser(0.,12.)
hFSRNWF.SetLineColor(ROOT.kRed)
hFSRNWF.Draw("hist same")
leg = TLegend(0.7,0.75,0.89,0.89)
leg.AddEntry(hFSRNWF,"no thresh corr.","l")
leg.AddEntry(hTot,"w/ thresh","l")
leg.Draw("same")
c.Print("../plots/latThresh_DS%d.pdf" % dsNum)
fOut.Close()
from ROOT import TH1F, TH2F, TFile, TLorentzVector, TChain
# load FWLite C++ libraries
ROOT.gSystem.Load("libFWCoreFWLite.so")
ROOT.gSystem.Load("libDataFormatsFWLite.so")
ROOT.FWLiteEnabler.enable()
# load FWlite python libraries
from DataFormats.FWLite import Handle, Events
data_chain = TChain('events')
data_list = open(args.inFile, 'r')
data_files = data_list.readlines()
for i in data_files:
data_chain.Add(i.strip())
outfile = TFile(args.outFile, "recreate")
# Book histos
hlt_jet_pt = TH1F('hlt_jet_pt', 'hlt_jet_pt', 100, 0, 500)
hlt_jet_m = TH1F('hlt_jet_m', 'hlt_jet_m', 40, 0, 80)
hlt_HT = TH1F('hlt_HT', 'hlt_HT', 100, 0, 1800)
fj_jet_pt = TH1F('fj_jet_pt', 'fj_jet_pt', 100, 0, 500)
fj_jet_pt_low = TH1F('fj_jet_pt_low', 'fj_jet_pt_low', 50, 0, 20)
fj_jet_pt_high = TH1F('fj_jet_pt_high', 'fj_jet_pt_high', 100, 0, 500)
fj_jet_m = TH1F('fj_jet_m', 'fj_jet_m', 40, 0, 80)
fj_HT = TH1F('fj_HT', 'fj_HT', 100, 0, 1800)
fj_HT20 = TH1F('fj_HT20', 'fj_HT20', 100, 0, 1800)
def test_tree2array(self):
chain = TChain('tree')
chain.Add(self.ld('single1.root'))
self.check_single(tree2array(chain))
from ROOT import TROOT, TCanvas, TH1F, TChain, TLine
#constants
m_D_meson = 1869.65
m_D_meson_down = m_D_meson-100.0
m_D_meson_up = m_D_meson+100.0
err=30
halferr=err/2.0
# load files
chain= TChain('D2KSPiPiPi_DD/DecayTree')
chain.Add('DV_Prompt_D2Kshhh_2016_DT_0.root')
#you can add as many files as needed
print 'Number of entries: ' , chain.GetEntries()
#prints in the command line the number of entries
L0_set=('D_L0HadronDecision_TOS==1' or 'D_L0MuonDecision_Tis==1' or 'D_L0DiMuonDecision_Tis==1' or \
'D_L0ElectronDecision_Tis==1' or 'D_L0PhotonDecision_Tis==1')
Hlt1_set=('D_Hlt1TrackMVADecision_TOS==1' or 'D_Hlt1TwoTrackMVADecision_TOS==1')
trigger=L0_set and Hlt1_set
SignalWindow = 'D_M > 1839.65 ' and 'D_M < 1899.65 '
SideBand = ('D_M > 1754.65 ' and 'D_M < 1784.65 ') \
or ('D_M > 1954.65' and 'D_M < 1984.65')
#D_PT
h1_D_PT = TH1F("h1_D_PT", "D_PT", 100, 0, 20000)
#from 0 to 600000, 100 bins
if line.strip() and not '#' in line: # this skips empty lines
line = line.replace('/', '_').replace('_$(channel)', '').replace(
'_bkg', 'bkg').replace('_sig', 'sig')
id, sample = line.split(" ")
results.setdefault(sample.strip(), []).append(int(id.strip()))
#for key in results:
# print(key, results[key])
#print(results)
#print(results["bkg_Top_1"][0])
path = []
path_file = "/eos/atlas/user/a/ademaria/Slim_July_Production/mc_nom/"
for k, v in results.items():
Entries = []
for i in range(0, len(v)):
path = os.listdir(path_file)
fname = [f for f in path if str(results[k][i]) in f][0]
#print(fname)
root_path = path_file + "/" + fname
# root_files = [f1 for f1 in os.listdir(root_path) if f1.endswith('.root')]
root_files = os.listdir(root_path)
mychain1 = TChain("NOMINAL")
for rootname in root_files:
mychain1.Add(root_path + "/" + rootname)
Entries.append(mychain1.GetEntries())
#print(Entries)
TotEntries = sum(Entries)
#print ("%18s %d" %(k,int(TotEntries)))
out.write("%18s %d\n" % (k, int(TotEntries)))
#print(path)
out.close()
print "Input:", options.inputfile, "; Output:", outfilename
#outfilename= 'SkimmedTree.root'
skimmedTree = TChain("tree/treeMaker")
if isfarmout:
infile = open(inputfilename)
failcount = 0
for ifile in infile:
try:
f_tmp = TFile.Open(ifile.rstrip(), 'READ')
if f_tmp.IsZombie(): # or fileIsCorr(ifile.rstrip()):
failcount += 1
continue
skimmedTree.Add(ifile.rstrip())
except:
failcount += 1
if failcount > 0:
print "Could not read %d files. Skipping them." % failcount
if not isfarmout:
skimmedTree.Add(inputfilename)
#
# skimmedTree.Add(sys.argv[1])
def arctan(x, y):
corr = 0
if (x > 0 and y >= 0) or (x > 0 and y < 0):
plotbinning = [[70, 0.6, 1.6], [70, 0.6, 1.6], [70, 0.85, 1.45]]
#+++++++++++++++++++++++++++++++++++++++++++++++++++++++++
#+++++++++++++++++++++++++++++++++++++++++++++++++++++++++
#
pdfout = PDFPrinting(outputname)
outputfile = ROOT.TFile(outputname + ".root", "RECREATE")
outputfile.cd()
c1 = ROOT.TCanvas()
tree_sig = TChain("MVATree")
tree_bkg = TChain("MVATree")
samplesel = ""
for f in glob(ttHlocation + "/*.root"):
tree_sig.Add(f)
samplesel = "Evt_Odd == 1 &&"
for f in glob(ttbarlocation + "/*.root"):
tree_bkg.Add(f)
#---------------------------------------------------------
#--------------------- Signal Sample ---------------------
#---------------------------------------------------------
print "Processing Singnal Sample"
# Catplots for regression Bias
for ireg, reg in enumerate(regressions):
corrcatpT = CatPlots("Regression Output",
[0, 50, 75, 100, 150, 200, 300, 600], "Jet_Pt",
"Jet p_{T}", False, False, "ttHbb", plotbinning[ireg],
for iw, weight in enumerate(weightlist):
targetvoutput = TwoDplot("Target", "Output", [50, 0.6, 1.6],
[40, 0.7, 1.5])
targetvoutput.setAxisTitle("Target", "Output")
print "Processing weight", iw, "of", len(weightlist) - 1
print "Weight name:", weight.split("/")[-1]
tree = TChain("MVATree")
if sample is "Signal":
samplesel = ""
for f in glob(ttHlocation + "/*.root"):
tree.Add(f)
else:
samplesel = "Evt_Odd == 1 &&"
for f in glob(ttbarlocations[iw] + "/*.root"):
tree.Add(f)
if dotargetcomp:
partonvgenjet_ratio = TwoDplot("Parton", "GenJet", [50, 0.8, 1.2],
[50, 0.8, 1.2])
partonvgenjet_ratio.setAxisTitle("Parton p_{T} ratio",
"GenJet p_{T} ratio")
partonvgenjet_ratio.projecttoTwoDplot(
tree, "(" + prefix[iw] + "Jet_MatchedPartonPt/" + prefix[iw] +
"Jet_Pt):(" + prefix[iw] + "Jet_MatchedGenJetwNuPt/" + prefix[iw] +
"Jet_Pt)", "abs(" + prefix[iw] + "Jet_MatchedPartonFlav) == 5")
outfilename = 'SkimmedTree.root'
PUPPI = True
CA15 = False
## When running on farmout
#inputfilename = os.environ['INPUT']
#outfilename = os.environ['OUTPUT']
skimmedTree = TChain("tree/treeMaker")
##======use this for providing list of file======##
#infile = open(inputfilename)
#for ifile in infile:
# skimmedTree.Add(ifile.rstrip())
# samplename = WhichSample(inputfilename)
##======use this for providing list of file======##
skimmedTree.Add(sys.argv[1])
#samplename = WhichSample(sys.argv[1])
def AnalyzeDataSet():
NEntries = skimmedTree.GetEntries()
h_total = TH1F('h_total', 'h_total', 2, 0, 2)
h_total_mcweight = TH1F('h_total_mcweight', 'h_total_mcweight', 2, 0, 2)
outfile = TFile(outfilename, 'RECREATE')
outTree = TTree('outTree', 'tree branches')
st_runId = numpy_.zeros(1, dtype=int)
st_lumiSection = array('L', [0])
mu_data_samplenames.append('SingleMu_Run2016Hv2')
mu_data_samplenames.append('SingleMu_Run2016Hv3')
el_data_samplenames = []
el_data_samplenames.append('SingleEl_Run2016Bv2')
el_data_samplenames.append('SingleEl_Run2016C')
el_data_samplenames.append('SingleEl_Run2016D')
el_data_samplenames.append('SingleEl_Run2016E')
el_data_samplenames.append('SingleEl_Run2016F')
el_data_samplenames.append('SingleEl_Run2016G')
el_data_samplenames.append('SingleEl_Run2016Hv2')
el_data_samplenames.append('SingleEl_Run2016Hv3')
#data chains
mu_data_chain = TChain('tree')
for n in mu_data_samplenames:
mu_data_chain.Add(total_ttree_dir_path + n + '_skim_all.root')
el_data_chain = TChain('tree')
for n in el_data_samplenames:
el_data_chain.Add(total_ttree_dir_path + n + '_skim_all.root')
#set data chains
for channame in all_channels.keys():
if channame.find('_mu') != -1:
all_channels[channame].setDataChain(mu_data_chain)
elif channame.find('_el') != -1:
all_channels[channame].setDataChain(el_data_chain)
else:
print 'ERROR: failed to determine leptype for chain with name ' + channame
#skim data chains in parallel
# ROOT imports
from ROOT import TChain
# custom ROOT classes
from ROOT import alp, ComposableSelector, CounterOperator, JetFilterOperator, BTagFilterOperator, JetPairingOperator, DiJetPlotterOperator
from ROOT import BaseOperator, FolderOperator, EventWriterOperator
config = {"jets_branch_name": "Jets",
"hlt_names":[]}
selector = ComposableSelector(alp.Event)(0, json.dumps(config))
selector.addOperator(BaseOperator(alp.Event)())
selector.addOperator(CounterOperator(alp.Event)())
selector.addOperator(JetFilterOperator(alp.Event)(2.5, 30., 4))
selector.addOperator(CounterOperator(alp.Event)())
selector.addOperator(BTagFilterOperator(alp.Event)("pfCombinedInclusiveSecondaryVertexV2BJetTags", 0.800, 4))
selector.addOperator(CounterOperator(alp.Event)())
selector.addOperator(FolderOperator(alp.Event)("empty_one"))
selector.addOperator(JetPairingOperator(alp.Event)(4))
selector.addOperator(FolderOperator(alp.Event)("4CSVM"))
selector.addOperator(DiJetPlotterOperator(alp.Event)())
selector.addOperator(CounterOperator(alp.Event)())
selector.addOperator(EventWriterOperator(alp.Event)())
selector.addOperator(FolderOperator(alp.Event)("empty_two"))
tchain = TChain("ntuple/tree")
tchain.Add("/lustre/cmswork/hh/alpha_ntuples/v0_20161004/GluGluToHHTo4B_node_SM_13TeV-madgraph_v14-v1/0000/output.root")
tchain.Process(selector, "", 10000)
# Opening root file
#fname = glob("/pnfs/uboone/persistent/users/aschu/MC_BNB_Cosmic/prodgenie_bnb_nu_cosmic_uboone_v05_08_00_anatree.root")
#fname = glob("/pnfs/uboone/persistent/users/aschu/MEC/MECmerge.root")
#fname = glob("/pnfs/uboone/persistent/users/aschu/TEM/TEMmerge.root")
#fname = glob("/pnfs/uboone/scratch/users/mdeltutt/v05_11_00/anatree_bnb_cosmic_eventWeight_MACCQE_ccincl_wflash_2/*/ana_hist.root") # Ma CCQE Selection I
fname = glob(
"/pnfs/uboone/scratch/users/mdeltutt/v05_11_00/anatree_prodgenie_bnb_nu_cosmic_uboone_mcc7_reco2_reweightMACCQE/*/ana_hist.root"
) # Ma CCQE Selection II
#print "Input file: ", fname
# Creating TChain
chain = TChain("analysistree/anatree")
chainPOT = TChain("analysistree/pottree")
for f in fname:
chain.Add(f)
chainPOT.Add(f)
# Printing the number of entries
entries = chain.GetEntries()
entriesPOT = chainPOT.GetEntries()
print "Number of entries in the ANA tree: ", entries
print "Number of entries in the POT tree: ", entriesPOT
# Getting POT number
#NominalPOT = 6.0e20
TotalPOT = 0
for jentry in xrange(entriesPOT):
entry = chainPOT.GetEntry(jentry)
#print '{:e}'.format(float(chainPOT.pot))
TotalPOT += chainPOT.pot
nBins = 50
maxX = 3
minX = -maxX
maxY = 3
minY = -maxY
outfile = remainder[0]
datafile = open(remainder[1], "r")
dataFiles = []
for line in (raw.strip().split() for raw in datafile):
dataFiles.append(line[0])
dataevents = TChain("ntuple")
for i in range(len(dataFiles)):
dataevents.Add(dataFiles[i])
mcfile = open(remainder[2], "r")
mcFiles = []
for line in (raw.strip().split() for raw in mcfile):
mcFiles.append(line[0])
mcevents = TChain("ntuple")
for i in range(len(mcFiles)):
mcevents.Add(mcFiles[i])
apfile = open(remainder[3], "r")
apfiles = []
events = []
mass = []
config["xsec_br"] = samples[sname]["xsec_br"]
config["matcheff"] = samples[sname]["matcheff"]
config["kfactor"] = samples[sname]["kfactor"]
json_str = json.dumps(config)
#define selectors list
selector = ComposableSelector(alp.Event)(0, json_str)
selector.addOperator(BaseOperator(alp.Event)())
selector.addOperator(CounterOperator(alp.Event)())
selector.addOperator(MCTruthOperator(alp.Event)(0.5, True))
selector.addOperator(CounterOperator(alp.Event)())
selector.addOperator(FolderOperator(alp.Event)("pair"))
selector.addOperator(JetPlotterOperator(alp.Event)(btagAlgo,weights_v))
selector.addOperator(DiJetPlotterOperator(alp.Event)(weights_v))
selector.addOperator(EventWriterOperator(alp.Event)(json_str,weights_v))
#create tChain and process each files
tchain = TChain("pair/tree")
for File in files:
tchain.Add(File)
nev = numEvents if (numEvents > 0 and numEvents < tchain.GetEntries()) else tchain.GetEntries()
procOpt = "ofile=./"+sname+".root" if not oDir else "ofile="+oDir+"/"+sname+".root"
print "max numEv {}".format(nev)
tchain.Process(selector, procOpt, nev)
ns+=1
print "### processed {} samples ###".format(ns)
from ROOT import TFile, TChain, TH1F, TH3F, gDirectory, TCanvas, kRed
from geomUtil import isect_line_plane_v3
from glob import glob
bin_ang = 12
fidvol = 20
bin_len = 8
f = glob("../root_files/mucs_cry_overlay/*/ana_hist.root")
h_res_phi = TH1F("h_res_phi", "", 100, -10, 10)
h_res_theta = TH1F("h_res_theta", "", 100, -10, 10)
entry = TChain("analysistree/anatree")
for filename in f:
entry.Add(filename)
y_end = 116.5
p_no = [0, 1, 0]
p_co_tpc = [0, y_end, 0]
in_tpc = 0
mucs_reco = 0
reco = 0
total_mucs_reco = 0
decay = 0
ok = 0
entries = entry.GetEntries()
print(entries)
for event in range(entries):
import math
c1 = TCanvas("c1")
p1 = TPad("p1", "p1", 0.05, 0.05, 0.95, 0.95)
p1.Draw()
p1.cd()
red_lines = []
blue_lines = []
green_lines = []
red_lines_2D = []
blue_lines_2D = []
green_lines_2D = []
chain = TChain("events_pandoraCosmic")
chain.Add("../root_files/CORSIKA.root")
chain.Add("../root_files/MuCSRun7347_Group181_MergedTree.Root") #downstream
chain.Add("../root_files/MuCSRun7348_Group181_MergedTree.Root") #downstream
chain.Add("../root_files/MuCSRun7702_Group182_MergedTree.Root") #upstream
chain.Add("../root_files/MuCSRun7703_Group183_MergedTree.Root") #upstream
entries = chain.GetEntries()
print(entries)
for entry in range(entries):
ientry = chain.LoadTree(entry)
nb = chain.GetEntry(entry)
cosmic_pe = chain.flash_pe
l_mucs = chain.MuCS_TPC_len
if entry % 1000 == 0: print(entry)
def test_tree2rec(self):
chain = TChain('tree')
chain.Add(self.ld('single1.root'))
import tensorflow as tf
from tensorflow.python.keras import models as m
from tensorflow.python.keras import layers as l
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler
from sklearn.externals import joblib
from ROOT import TFile, TTree, TChain
print("All classes initialized successfully!!!")
sigChan = TChain("varTree")
sigChan.Add("signal.root")
bkgChan = TChain("varTree")
bkgChan.Add("background.root")
print("Data read from the trees. Printing out the contents.")
sigChan.Print()
bkgChan.Print()
sigSampleSize = sigChan.GetEntries()
bkgSampleSize = bkgChan.GetEntries()
sampleSize = sigSampleSize if sigSampleSize<bkgSampleSize else bkgSampleSize
sigFull = sigChan.AsMatrix()
print(sigFull[0])
print(sigFull.shape)
bkgFull = bkgChan.AsMatrix()
print(bkgFull.shape)
def optimizeCutOrder(dsNum):
""" ./plots2.py -ord [dsNum]
Optimize the order of reduction:
fs, rn, wf, fs+rn, fs+wf, rn+wf, fs+rn+wf
now I'm also thinking about applying the threshold cut to every file ...
... that will tell you how good the cuts are when we're above/below the detector threshold ... do I want that?
anyway, try it first without. (simpler.)
Results:
[raw, fs, rn, wf, fs+rn, fs+wf, fs+rn, rn+wf, fs+rn+wf]
DS1 outputs:
Int2: [330357.60, 606.30, 314160.80, 1359.80, 52.80, 21.70, 1358.30, 21.50]
Int5: [4362.90, 52.90, 1018.90, 54.90, 52.60, 30.50, 54.40, 30.20]
Int10: [1991.90, 75.20, 98.00, 63.40, 74.80, 52.10, 63.40, 52.10]
Int50: [94.20, 75.00, 90.70, 63.40, 74.90, 51.50, 63.40, 51.50]
Int250: [51.60, 42.50, 49.80, 39.20, 42.40, 35.80, 39.10, 35.70]
Reduction order (least to most, <2 kev): raw, rn, wf, rn+wf, fs, fs+rn, fs+wf, fs+rn+wf
Order to plot cut reductions:
raw, fs, fs+wf, fs+rn+wf.
Clearly fs is our best noise discriminator.
"""
int2, int5, int10, int50, int250 = [], [], [], [], []
kpb = 0.1
eLo, eHi = 0., 250.
nBins = int((eHi-eLo)/kpb)
fIn = TFile("../data/latRaw_DS%d.root" % dsNum)
hRaw = fIn.Get("hSum")
rebinFactor = int(kpb/0.01)
hRaw = hRaw.Rebin(rebinFactor)
getIntegralCounts(hRaw, int2, int5, int10, int50, int250)
fileFS = sorted(glob.glob("/global/homes/w/wisecg/project/cuts/fs/fitSlo-DS%d-*.root" % dsNum))
chainFS = TChain("skimTree")
[chainFS.Add(f) for f in fileFS]
hFS = wl.H1D(chainFS,nBins,eLo,eHi,"trapENFCal","","trapENFCal","","hFS")
getIntegralCounts(hFS, int2, int5, int10, int50, int250)
fileRN = sorted(glob.glob("/global/homes/w/wisecg/project/cuts/rn/riseNoise-DS%d-*.root" % dsNum))
chainRN = TChain("skimTree")
[chainRN.Add(f) for f in fileRN]
hRN = wl.H1D(chainRN,nBins,eLo,eHi,"trapENFCal","","trapENFCal","","hRN")
getIntegralCounts(hRN, int2, int5, int10, int50, int250)
fileWF = sorted(glob.glob("/global/homes/w/wisecg/project/cuts/wf/wfstd-DS%d-*.root" % dsNum))
chainWF = TChain("skimTree")
[chainWF.Add(f) for f in fileWF]
hWF = wl.H1D(chainWF,nBins,eLo,eHi,"trapENFCal","","trapENFCal","","hWF")
getIntegralCounts(hWF, int2, int5, int10, int50, int250)
fileFSRN = sorted(glob.glob("/global/homes/w/wisecg/project/cuts/fs_rn/fs_rn-DS%d-*.root" % dsNum))
chainFSRN = TChain("skimTree")
[chainFSRN.Add(f) for f in fileFSRN]
hFSRN = wl.H1D(chainFSRN,nBins,eLo,eHi,"trapENFCal","","trapENFCal","","hFSRN")
getIntegralCounts(hFSRN, int2, int5, int10, int50, int250)
fileFSWF = sorted(glob.glob("/global/homes/w/wisecg/project/cuts/fs_wf/fs_wf-DS%d-*.root" % dsNum))
chainFSWF = TChain("skimTree")
[chainFSWF.Add(f) for f in fileFSWF]
hFSWF = wl.H1D(chainFSWF,nBins,eLo,eHi,"trapENFCal","","trapENFCal","","hFSWF")
getIntegralCounts(hFSWF, int2, int5, int10, int50, int250)
fileRNWF = sorted(glob.glob("/global/homes/w/wisecg/project/cuts/rn_wf/rn_wf-DS%d-*.root" % dsNum))
chainRNWF = TChain("skimTree")
[chainRNWF.Add(f) for f in fileRNWF]
hRNWF = wl.H1D(chainRNWF,nBins,eLo,eHi,"trapENFCal","","trapENFCal","","hRNWF")
getIntegralCounts(hRNWF, int2, int5, int10, int50, int250)
fileFSRNWF = sorted(glob.glob("/global/homes/w/wisecg/project/cuts/fs_rn_wf/fs_rn_wf-DS%d-*.root" % dsNum))
chainFSRNWF = TChain("skimTree")
[chainFSRNWF.Add(f) for f in fileFSRNWF]
hFSRNWF = wl.H1D(chainFSRNWF,nBins,eLo,eHi,"trapENFCal","","trapENFCal","","hFSRNWF")
getIntegralCounts(hFSRNWF, int2, int5, int10, int50, int250)
# stackoverflow trick to make list printing prettier
class prettyfloat(float):
def __repr__(self): return "%.2f" % self
print "Int2:", map(prettyfloat, int2)
print "Int5:", map(prettyfloat, int5)
print "Int10:", map(prettyfloat, int10)
print "Int50:", map(prettyfloat, int50)
print "Int250:", map(prettyfloat, int250)
def Count(chan, trigs):
#deal with weights first
sumWeights = TChain("sumWeights")
sumWeights.Add("%stth*.root" % prepath)
weights = []
fCurrent_wt = 0
sampleNEvt = 0
nWeightEntries = sumWeights.GetEntries()
for a in range(nWeightEntries):
sumWeights.GetEntry(a)
totalEventsWeighted = getattr(sumWeights, 'totalEventsWeighted')
if sumWeights.GetTreeNumber() != fCurrent_wt:
fCurrent_wt = sumWeights.GetTreeNumber()
weights.append(sampleNEvt)
sampleNEvt = 0
sampleNEvt = sampleNEvt + totalEventsWeighted
if a == nWeightEntries - 1: weights.append(sampleNEvt) #last file
chain = TChain("nominal")
chain.Add("%stth*.root" % prepath)
nentries = chain.GetEntries()
chain.SetBranchStatus("*", 0)
chain.SetBranchStatus("Mll01", 1)
chain.SetBranchStatus("total_charge", 1)
chain.SetBranchStatus("lep_Pt_0", 1)
chain.SetBranchStatus("lep_Pt_1", 1)
chain.SetBranchStatus("lep_Eta_0", 1)
chain.SetBranchStatus("lep_Eta_1", 1)
chain.SetBranchStatus("lep_ID_0", 1)
chain.SetBranchStatus("lep_ID_1", 1)
chain.SetBranchStatus("lep_truthPdgId_0", 1)
chain.SetBranchStatus("lep_truthPdgId_1", 1)
chain.SetBranchStatus("lep_truthOrigin_0", 1)
chain.SetBranchStatus("lep_truthOrigin_1", 1)
chain.SetBranchStatus("lep_truthType_0", 1)
chain.SetBranchStatus("lep_truthType_1", 1)
chain.SetBranchStatus("lep_isQMisID_0", 1)
chain.SetBranchStatus("lep_isQMisID_1", 1)
chain.SetBranchStatus("nJets_OR_T_MV2c10_70", 1)
chain.SetBranchStatus("nJets_OR_T", 1)
chain.SetBranchStatus("lep_isTightLH_0", 1)
chain.SetBranchStatus("lep_isTightLH_1", 1)
chain.SetBranchStatus("lep_isLooseLH_0", 1)
chain.SetBranchStatus("lep_isLooseLH_1", 1)
chain.SetBranchStatus("lep_isolationFixedCutTight_0", 1)
chain.SetBranchStatus("lep_isolationFixedCutLoose_0", 1)
chain.SetBranchStatus("lep_isolationFixedCutTight_1", 1)
chain.SetBranchStatus("lep_isolationFixedCutLoose_1", 1)
chain.SetBranchStatus("lep_isolationFixedCutTightTrackOnly_0", 1)
chain.SetBranchStatus("lep_isolationFixedCutTightTrackOnly_1", 1)
chain.SetBranchStatus("HLT*", 1)
chain.SetBranchStatus("*type", 1)
chain.SetBranchStatus("RunYear", 1)
chain.SetBranchStatus("passEventCleaning", 1)
chain.SetBranchStatus("lep_isTrigMatch_0", 1)
chain.SetBranchStatus("lep_isTrigMatch_1", 1)
chain.SetBranchStatus("lep_isTrigMatchDLT_0", 1)
chain.SetBranchStatus("lep_isTrigMatchDLT_1", 1)
chain.SetBranchStatus("mcWeightOrg", 1)
chain.SetBranchStatus("pileupEventWeight_090", 1)
chain.SetBranchStatus("lepSFObjTight", 1)
chain.SetBranchStatus("lepSFTrigTight", 1)
chain.SetBranchStatus("JVT_EventWeight", 1)
chain.SetBranchStatus("SherpaNJetWeight", 1)
chain.SetBranchStatus("MV2c10_70_EventWeight", 1)
chain.SetBranchStatus("lep_chargeIDBDT*", 1)
chain.SetBranchStatus("nTaus_OR_Pt25", 1)
chain.SetBranchStatus("tau_JetBDTSigTight_0", 1)
chain.SetBranchStatus("tau_JetBDTSigTight_1", 1)
chain.SetBranchStatus("tau_tagWeightBin_0", 1)
chain.SetBranchStatus("tau_tagWeightBin_1", 1)
chain.SetBranchStatus("tau_passMuonOLR_0", 1)
chain.SetBranchStatus("tau_passMuonOLR_1", 1)
chain.SetBranchStatus("tau_passEleBDT_0", 1)
chain.SetBranchStatus("tau_passEleBDT_1", 1)
chain.SetBranchStatus("tau_charge_0", 1)
chain.SetBranchStatus("tau_charge_1", 1)
chain.SetBranchStatus("lep_ID_2", 1)
chain.SetBranchStatus("Mll02", 1)
chain.SetBranchStatus("lep_promptLeptonVeto_TagWeight_0", 1)
chain.SetBranchStatus("lep_promptLeptonVeto_TagWeight_1", 1)
chain.SetBranchStatus("lep_ambiguityType_0", 1)
chain.SetBranchStatus("lep_ambiguityType_1", 1)
#cuts
fCurrent = -1
chain.LoadTree(0)
cuts_sr = TTreeFormula("cuts_sr", chan, chain)
cuts_trig = TTreeFormula("cuts_trig", trigs, chain)
raw_evts, numevts = 0, 0
for evt in range(nentries):
#for event in chain:
#if evt%10000==0 : print evt
chain.GetEntry(evt)
#get current file
currentFileName = chain.GetCurrentFile().GetName()
RunYear = getattr(chain, "RunYear")
mcWeightOrg = getattr(chain, "mcWeightOrg")
pileupEventWeight_090 = getattr(chain, "pileupEventWeight_090")
lepSFObjTight = getattr(chain, "lepSFObjTight")
lepSFTrigTight = getattr(chain, "lepSFTrigTight")
JVT_EventWeight = getattr(chain, "JVT_EventWeight")
SherpaNJetWeight = getattr(chain, "SherpaNJetWeight")
MV2c10_70_EventWeight = getattr(chain, "MV2c10_70_EventWeight")
lumi = 1.0
if RunYear < 2016.5: lumi = 36074.6
if RunYear > 2016.5: lumi = 43813.7
if chain.GetTreeNumber() != fCurrent:
fCurrent = chain.GetTreeNumber()
cuts_sr.Notify()
cuts_trig.Notify()
if cuts_sr.EvalInstance() and cuts_trig.EvalInstance():
#if cuts_trig.EvalInstance():
if "341177" in currentFileName: weight = 0.05343
if "341270" in currentFileName: weight = 0.22276
if "341271" in currentFileName: weight = 0.23082
kfac, filEff = 1, 1
#weight=weight*kfac*filEff*mcWeightOrg*pileupEventWeight_090*lepSFObjTight*lepSFTrigTight*JVT_EventWeight*SherpaNJetWeight*MV2c10_70_EventWeight*lumi/weights[fCurrent]
weight = weight * kfac * filEff * mcWeightOrg * lepSFObjTight * lepSFTrigTight * JVT_EventWeight * SherpaNJetWeight * MV2c10_70_EventWeight * lumi / weights[
fCurrent]
#print xsec, kfac, filEff, event.mcWeightOrg,event.pileupEventWeight_090,event.lepSFObjTight,event.lepSFTrigTight,event.JVT_EventWeight,event.SherpaNJetWeight,event.MV2c10_70_EventWeight, lumi
raw_evts = raw_evts + 1
numevts = numevts + weight
print "%s(%.2f)" % (raw_evts, numevts)
def genRawHists(dsNum):
""" ./plots2.py -gen [dsNum]
Create "raw" LAT histograms for each dataset.
Use a super fine binning and huge energy range for versatility.
Don't distinguish between enriched and natural detectors.
1. sum histogram 'hSum'
2. cpd vs energy 'hCPDE'
3. cpd vs run 'hCPDrun'
Could also do channel-by-channel, bkgIdx by bkgIdx,
but hopefully the 2D CPD plots will be enough for diagnostics (can examine their bin contents).
Plus we can loop over the bins in the raw histo instead of re-drawing everything.
"""
print "Plots2 started:",time.strftime('%X %x %Z')
startT = time.clock()
kpb = 0.01
eLo, eHi = 0., 15000.
nBins = int((eHi-eLo)/kpb)
# build the file list sequentially
fList = []
dsPath = "/global/homes/w/wisecg/project/bg-lat"
for bkgIdx in range(ds.dsMap[dsNum]+1):
tmp = glob.glob("%s/latSkimDS%d_%d_*.root" % (dsPath, dsNum, bkgIdx))
nFiles = len(tmp)
for subIdx in range(nFiles):
fName = "%s/latSkimDS%d_%d_%d.root" % (dsPath, dsNum, bkgIdx, subIdx)
if os.path.isfile(fName) == True:
fList.append(fName)
else:
print "File doesn't exist, exiting ...",fName
return
# fList = fList[:2] # limit fList (debug only)
fCut = TFile(fList[0])
dcCut = fCut.Get("theCut").GetTitle()
dcCut += "&& gain==0"
ch = TChain("skimTree")
[ch.Add(f) for f in fList]
print "Generating DS-%d (%d entries)." % (dsNum,ch.GetEntries())
cpdLo, cpdHi = 111, 175
if dsNum==4: cpdLo, cpdHi = 211, 275
if dsNum==5: cpdLo, cpdHi = 111, 275
nCPD = cpdHi - cpdLo
ch.GetEntry(0)
runLo = ch.run
ch.GetEntry(ch.GetEntries()-1)
runHi = ch.run
nRuns = runHi - runLo + 1
print "First run:",runLo,"Last run:",runHi
fOut = TFile("../data/latRaw_DS%d.root" % dsNum,"RECREATE")
print "Generating sum spectrum. %.2f mins elapsed. %s" % ((time.clock()-startT)/60., time.strftime('%X %x %Z'))
h1 = wl.H1D(ch,nBins,eLo,eHi,"trapENFCal",dcCut,"trapENFCal","Counts","raw sum LAT spectrum","hSum")
h1.Write()
print "Generating CPD vs. E. %.2f mins elapsed. %s" % ((time.clock()-startT)/60., time.strftime('%X %x %Z'))
h2 = wl.H2D(ch,nBins,eLo,eHi,nCPD,cpdLo,cpdHi,"C*100+P*10+D:trapENFCal",dcCut,"trapENFCal","CPD","CPD vs. E","hCPDE")
h2.Write()
print "Generating CPD vs. run. %.2f mins elapsed. %s" % ((time.clock()-startT)/60., time.strftime('%X %x %Z'))
h3 = wl.H2D(ch,nRuns,runLo,runHi,nCPD,cpdLo,cpdHi,"C*100+P*10+D:run",dcCut,"run","CPD","CPD vs. run","hCPDrun")
h3.Write()
fOut.Close()
print "Time Elapsed:",(time.clock()-startT)/60.,"minutes."
print "Done at",time.strftime('%X %x %Z')
def makeNtuple_ttbar_ljets(inputFiles,
outputname,
treename="Delphes",
arrayFormat=None,
maxevents=None):
# inputs
infiles = getFileList(inputFiles)
chain = TChain(treename)
for finput in infiles:
chain.Add(finput)
nevents = chain.GetEntries()
print('Total number of entries:', nevents)
foutput = TFile(outputname + '.root', "recreate")
# tree
tree = TTree("ntuple", "ntuple")
# variables
variables = varTTbarLJets()
variables.set_up_branches(tree)
# loop over events
t_tree_start = time.time()
for ievt, event in enumerate(chain):
if maxevents is not None and ievt >= maxevents:
print("maxevents:", maxevents)
break
if not ievt % 10000:
print("processing event {}/{}".format(ievt, nevents))
if not passEventSelection(event):
continue
variables.set_default()
# event weight
variables.w[0] = event.Event[0].Weight
# partons
# top
t_afterFSR = getTopAfterFSR(event.Particle)
t_p4 = TLorentzVector()
t_p4.SetPxPyPzE(t_afterFSR.Px, t_afterFSR.Py, t_afterFSR.Pz,
t_afterFSR.E)
t_ishadronic = isHadronicTop(t_afterFSR, event.Particle)
variables.t_ishadronic[0] = t_ishadronic
W_fromT = getWfromTopDecay(t_afterFSR, event.Particle, afterFSR=True)
W_fromT_p4 = TLorentzVector()
W_fromT_p4.SetPxPyPzE(W_fromT.Px, W_fromT.Py, W_fromT.Pz, W_fromT.E)
# antitop
tbar_afterFSR = getAntiTopAfterFSR(event.Particle)
tbar_p4 = TLorentzVector()
tbar_p4.SetPxPyPzE(tbar_afterFSR.Px, tbar_afterFSR.Py,
tbar_afterFSR.Pz, tbar_afterFSR.E)
tbar_ishadronic = isHadronicTop(tbar_afterFSR, event.Particle)
variables.tbar_ishadronic[0] = tbar_ishadronic
W_fromTbar = getWfromTopDecay(tbar_afterFSR,
event.Particle,
afterFSR=True)
W_fromTbar_p4 = TLorentzVector()
W_fromTbar_p4.SetPxPyPzE(W_fromTbar.Px, W_fromTbar.Py, W_fromTbar.Pz,
W_fromTbar.E)
th_p4, tl_p4 = None, None
wh_p4, wl_p4 = None, None
if t_ishadronic and not tbar_ishadronic:
th_p4 = t_p4
tl_p4 = tbar_p4
wh_p4 = W_fromT_p4
wl_p4 = W_fromTbar_p4
elif not t_ishadronic and tbar_ishadronic:
th_p4 = tbar_p4
tl_p4 = t_p4
wh_p4 = W_fromTbar_p4
wl_p4 = W_fromT_p4
# veto events in boosted category
#if isBoostedTop(event, th_p4):
# continue
if th_p4 is not None:
variables.th_pt[0] = th_p4.Pt()
variables.th_eta[0] = th_p4.Eta()
variables.th_y[0] = th_p4.Rapidity()
variables.th_phi[0] = th_p4.Phi()
variables.th_m[0] = th_p4.M()
variables.th_e[0] = th_p4.E()
if tl_p4 is not None:
variables.tl_pt[0] = tl_p4.Pt()
variables.tl_eta[0] = tl_p4.Eta()
variables.tl_y[0] = tl_p4.Rapidity()
variables.tl_phi[0] = tl_p4.Phi()
variables.tl_m[0] = tl_p4.M()
variables.tl_e[0] = tl_p4.E()
if wh_p4 is not None:
variables.wh_pt[0] = wh_p4.Pt()
variables.wh_eta[0] = wh_p4.Eta()
variables.wh_phi[0] = wh_p4.Phi()
variables.wh_m[0] = wh_p4.M()
variables.wh_e[0] = wh_p4.E()
if wl_p4 is not None:
variables.wl_pt[0] = wl_p4.Pt()
variables.wl_eta[0] = wl_p4.Eta()
variables.wl_phi[0] = wl_p4.Phi()
variables.wl_m[0] = wl_p4.M()
variables.wl_e[0] = wl_p4.E()
# lepton
if passElectronCuts(event) and not passMuonCuts(event):
variables.lep_pt[0] = event.Electron[0].PT
variables.lep_eta[0] = event.Electron[0].Eta
variables.lep_phi[0] = event.Electron[0].Phi
variables.lep_pdgid[0] = -11 * event.Electron[0].Charge
elif passMuonCuts(event) and not passElectronCuts(event):
variables.lep_pt[0] = event.Muon[0].PT
variables.lep_eta[0] = event.Muon[0].Eta
variables.lep_phi[0] = event.Muon[0].Phi
variables.lep_pdgid[0] = -13 * event.Muon[0].Charge
# jets
variables.njets[0] = 0
variables.njets25[0] = 0
for i, jet in enumerate(event.Jet):
variables.njets[0] += 1
if jet.PT > 25.:
variables.njets25[0] += 1
if i == 0:
variables.j1_pt[0] = jet.PT
variables.j1_eta[0] = jet.Eta
variables.j1_phi[0] = jet.Phi
variables.j1_m[0] = jet.Mass
variables.j1_isbtag[0] = jet.BTag
if i == 1:
variables.j2_pt[0] = jet.PT
variables.j2_eta[0] = jet.Eta
variables.j2_phi[0] = jet.Phi
variables.j2_m[0] = jet.Mass
variables.j2_isbtag[0] = jet.BTag
if i == 2:
variables.j3_pt[0] = jet.PT
variables.j3_eta[0] = jet.Eta
variables.j3_phi[0] = jet.Phi
variables.j3_m[0] = jet.Mass
variables.j3_isbtag[0] = jet.BTag
if i == 3:
variables.j4_pt[0] = jet.PT
variables.j4_eta[0] = jet.Eta
variables.j4_phi[0] = jet.Phi
variables.j4_m[0] = jet.Mass
variables.j4_isbtag[0] = jet.BTag
if i == 4:
variables.j5_pt[0] = jet.PT
variables.j5_eta[0] = jet.Eta
variables.j5_phi[0] = jet.Phi
variables.j5_m[0] = jet.Mass
variables.j5_isbtag[0] = jet.BTag
if i == 5:
variables.j6_pt[0] = jet.PT
variables.j6_eta[0] = jet.Eta
variables.j6_phi[0] = jet.Phi
variables.j6_m[0] = jet.Mass
variables.j6_isbtag[0] = jet.BTag
# MET
variables.met_met[0] = event.MissingET[0].MET
variables.met_phi[0] = event.MissingET[0].Phi
tree.Fill()
t_tree_done = time.time()
print("Making flat nutple took {:.2f} seconds ({:.3f} ms/event)".format(
t_tree_done - t_tree_start,
(t_tree_done - t_tree_start) * 1000 / nevents))
print("Finish writing tree to file")
foutput.Write()
if arrayFormat is not None:
print("Save tree as array")
# convert tree to array
import resource
ROOT.ROOT.EnableImplicitMT()
usage = resource.getrusage(resource.RUSAGE_SELF).ru_maxrss
print("Current RAM usage: {:.3f} GB".format(usage * 1e-6))
t_arr_start = time.time()
ntuple_arr_dict = ROOT.RDataFrame(tree).AsNumpy()
t_arr_done = time.time()
print("Converting TTree took {:.2f} seconds".format(t_arr_done -
t_arr_start))
usage = resource.getrusage(resource.RUSAGE_SELF).ru_maxrss
print("Current RAM usage: {:.3f} GB".format(usage * 1e-6))
if arrayFormat == "npz":
np.savez(outputname + '.npz', **ntuple_arr)
elif arrayFormat == "h5":
import h5py
with h5py.File(outputname + '.h5', 'w') as hf:
for var_name, var_arr in ntuple_arr_dict.items():
hf.create_dataset(var_name, data=var_arr)
else:
raise RuntimeError("Current supported format: 'npz' or 'h5'")
def scrapeData():
from ROOT import TChain
ds, mod = 1, 1
print("Loading cut data ...")
bkg = dsi.BkgInfo()
cal = dsi.CalInfo()
nSub = bkg.dsMap()[ds]
chList = dsi.GetGoodChanList(ds)
calDB = db.TinyDB('../calDB.json')
pars = db.Query()
fsD, rnSD, rnCD = {}, {}, {}
nCal = cal.GetNCalIdxs(ds, mod)
for iC in range(nCal + 1):
fsD[iC] = dsi.getDBRecord("fitSlo_ds%d_idx%d_m%d_Peak" % (ds, iC, mod),
False, calDB, pars)
rnSD[iC] = dsi.getDBRecord(
"riseNoise_ds%d_idx%d_m%d_SoftPlus" % (ds, iC, mod), False, calDB,
pars)
rnCD[iC] = dsi.getDBRecord(
"riseNoise_ds%d_idx%d_m%d_Continuum" % (ds, iC, mod), False, calDB,
pars)
thD = {}
for iB in range(nSub + 1):
thD[iB] = dsi.getDBRecord("thresh_ds%d_bkgidx%d" % (ds, iB), False,
calDB, pars)
print("Looping over sub-ranges ...")
hitE, fSlo, chans, runs, fsCut, thMu, thSig = [], [], [], [], [], [], []
rise, riseCut = [], []
for sub in range(nSub + 1):
tc = TChain("skimTree")
fRaw = sorted(
glob.glob("%s/latSkimDS%d_%d_*.root" % (dsi.latDir, ds, sub)))
for f in fRaw:
tc.Add(f)
print("%d/%d %d" % (sub, nSub, tc.GetEntries()))
# for some reason range 44 in ds1 is corrupted?
n = tc.Draw("trapENFCal:fitSlo:channel:run", "", "goff")
if n == 0:
print("skipped", sub)
continue
# n = tc.Draw("run:channel:trapENFCal:fitSlo","","goff")
# t1, t2, t3, t4 = tc.GetV1(), tc.GetV2(), tc.GetV3(), tc.GetV4()
tn = ["run", "channel", "trapENFCal", "fitSlo", "riseNoise"]
vals = wl.GetVX(tc, tn, "")
t1, t2, t3, t4, t5 = vals["run"], vals["channel"], vals[
"trapENFCal"], vals["fitSlo"], vals["riseNoise"]
n = len(t1)
pRun = -1
for i in range(n):
run = int(t1[i])
if run != pRun:
cIdx = cal.GetCalIdx("ds%d_m%d" % (ds, mod), run)
bIdx = bkg.GetBkgIdx(ds, run)
tmpFS = fsD[cIdx]
tmpTH = thD[bIdx]
tmpRNC = rnCD[cIdx]
tmpRNS = rnSD[cIdx]
fsCutChan = list(tmpFS.keys())
thCutChan = list(tmpTH.keys())
rnCutChan = list(tmpRNC.keys())
pRun = run
chan = int(t2[i])
if chan not in chList: continue
if chan not in fsCutChan: continue
if chan not in thCutChan: continue
if chan not in rnCutChan: continue
fsVal = tmpFS[chan][2]
thVal = tmpTH[chan][0] + 3 * tmpTH[chan][1]
a = max(tmpRNS[chan][0], tmpRNC[chan][4])
b = tmpRNS[chan][1]
c = tmpRNS[chan][2]
d = tmpRNS[chan][3]
if d == 0: continue
rnVal = a + b * np.log(1 + np.exp(t3[i] - c / d))
hitE.append(t3[i])
fSlo.append(t4[i])
runs.append(run)
chans.append(chan)
fsCut.append(tmpFS[chan][2])
thMu.append(tmpTH[chan][0])
thSig.append(tmpTH[chan][1])
rise.append(t5[i])
riseCut.append(rnVal)
# # fCut = sorted(glob.glob("%s/results_v1/fs/fitSlo-DS%d-*.root" % (dsi.dataDir, dsNum)))
print(len(hitE))
np.savez("../data/sea-plt-2.npz", hitE, fSlo, chans, runs, fsCut, thMu,
thSig, rise, riseCut)
'''
from ROOT import gROOT, TChain
from rootpy.interactive import wait
from rootpy.plotting import Hist
import rootpy.plotting.root2matplotlib as rplt
import matplotlib.pyplot as plt
from dps.utils.plotting import make_plot, Histogram_properties
if __name__ == '__main__':
# file available on soolin:
input_file = "/hdfs/TopQuarkGroup/mc/8TeV/v11/NoSkimUnfolding/BLT/TTJets_MassiveBinDECAY_TuneZ2star_8TeV/TTJets_nTuple_53X_mc_merged.root"
# this file contains multiple trees. For now we will focus on the electron channel
target_tree = "rootTupleTreeEPlusJets/ePlusJetsTree"
gROOT.SetBatch(1)
chain = TChain(target_tree)
chain.Add(input_file)
# now, we want to be fast and just read one variabe
# first disable all variables
chain.SetBranchStatus("*", 0)
# now enable the one we are interested in:
chain.SetBranchStatus("unfolding.genMET", 1)
# We want to store this variable in a histogram
# 80 bins, from 0 to 400 (GeV)
h_gen_met = Hist(80, 0, 400)
# since we are planning to run over many events, let's cache the fill function
fill = h_gen_met.Fill
# ready to read all events
n_processed_events = 0
stop_at = 10**5 # this is enough for this example
def doSlimSMQCD(treeName,outputFile,inputFiles,year):
from ROOT import TChain
from ROOT import TFile
from ROOT import ROOT
#import rootlogon
ROOT.gROOT.SetBatch(1)
import sys
print ("sys.argv = ", sys.argv)
if not len(sys.argv)>=2:
raise Exception ("Must specify inputFiles as argument!")
#inputFiles = sys.argv[1].split(',')
inputFiles = inputFiles
print ("inputFiles = ", inputFiles)
#get main tree
ch = TChain(treeName)
for file in inputFiles:
ch.Add(file)
nEntries = ch.GetEntries()
#print ("nEntries = ", nEntries)
#*****set branches*****
#set branch status, at first, all off
ch.SetBranchStatus("*", 0)
from JetN2N.SlimSMQCDBranches import SlimSMQCDBranchesList
from JetN2N.SlimSMQCDBranches2011 import SlimSMQCDBranchesList2011
#event information
if year == '2011':
for branch in SlimSMQCDBranchesList2011:
print (branch)
ch.SetBranchStatus(branch,1)
else:
for branch in SlimSMQCDBranchesList:
print (branch)
ch.SetBranchStatus(branch,1)
#*****set branches end*****
#get trigger tree
chTri = TChain(treeName+"Meta/TrigConfTree")
for file in inputFiles:
chTri.Add(file)
if chTri.LoadTree(0) < 0:
chTri = 0
#get bunch tree
chBunch = TChain(treeName+"Meta/BunchConfTree")
for file in inputFiles:
chBunch.Add(file)
if chBunch.LoadTree(0) < 0:
chBunch = 0
#get cut flow tree
#chCutFlow = TChain(treeName+"Meta/CutFlowTree")
#for file in inputFiles:
# chCutFlow.Add(file)
# Write to new file
outFile = outputFile
newFile = TFile(outFile, "RECREATE")
#new tree
ch_new = ch.CloneTree(0)
# event counter
#cutName=["preD3PD","postD3PD","trigCut"]
#evnum=[0,0,0]
#weight=[0,0,0]
#event selection
for i in range(nEntries):
ch.GetEntry(i)
#evnum[1]+=1
#if hasattr(ch,"mcevt_weight") \
# and ch.mcevt_weight.size() !=0 \
# and ch.mcevt_weight[0].size() !=0:
# w=ch.mcevt_weight[0][0]
#else:
# w=1
#weight[1]+=w
ch_new.Fill()
#evnum[2]+=1
#weight[2]+=w
newFile.cd()
ch_new.Write()
#nEntriesNew = ch_new.GetEntries()
#print ("nEntriesForNewFile = ", nEntriesNew)
#check cut flow at D3PD level
#if chCutFlow.GetEntries() != 0:
# for i in range (chCutFlow.GetEntries()):
# chCutFlow.GetEntry(i)
# cutFlowName=chCutFlow.name
# for j in range(cutFlowName.size()):
# if cutName.at(j) == "AllExecutedEvents":
# evnum[0]+=chCutFlow.nAcceptedEvents.at(j)
# weight[0]+=chCutFlow.nWeightedAcceptedEvents.at(j)
#else:
# evnum[0]=evnum[1]
# weight[0]=weight[1]
#copy trigger meta data
newFile.cd()
newdir = newFile.mkdir( treeName+"Meta", treeName+"Meta" )
newdir.cd()
if chTri != 0:
chTri_new = chTri.CloneTree()
chTri_new.Write()
if chBunch != 0:
chBunch_new = chBunch.CloneTree()
chBunch_new.Write()
def xLoop(fileName, var = '', cut = '', weight = '1', treeName = 'Events', nSlots = 1, nbins = 0, bin0 = -1, binN = -1, bins = [], e0 = 0, nEvents = -1, histo = None, iChunk = -1):
# Read from dictionary
if isinstance(fileName, dict):
d = fileName
fileName = d['fileName']
var = d['var']
cut = d['cut']
weight = d['weight']
treeName = d['treeName']
nSlots = d['nSlots']
nbins = d['nbins']
bin0 = d['bin0']
binN = d['binN']
bins = d['bins']
e0 = d['e0']
nEvents = d['nEvents']
histo = d['histo']
iChunk = d['iChunk']
# Load the TChain
t = TChain(treeName)
if ',' in fileName:
files = fileName.replace(' ', '').split(',')
for f in files: t.Add(f)
else: t.Add(fileName)
nEntries = t.GetEntries()
if nEvents+e0 > nEntries: nEvents = nEntries-e0
elif nEvents == -1: nEvents = nEntries
nEv = -1
# Multiprocess...
iN = e0+nEvents
eventsPerChunk = float(iN-e0)/nSlots
if nSlots > 1:
inputs = []
pool = Pool(nSlots)
for i in range(nSlots):
first = e0+int(eventsPerChunk*(i))
last = e0+int(eventsPerChunk*(i+1))
nEv = last - first
print 'Chunk %i: [first, last] = [%i, %i]... nEvents = %i'%(i, first, last, nEv)
impi = {}
impi['fileName'] = fileName
impi['var'] = var
impi['cut'] = cut
impi['weight'] = weight
impi['treeName'] = treeName
impi['nSlots'] = 1
impi['nbins'] = nbins
impi['bin0'] = bin0
impi['binN'] = binN
impi['bins'] = bins
impi['e0'] = first
impi['nEvents'] = nEv
impi['histo'] = None if histo == None else histo.Clone("histo%i"%i)
impi['iChunk'] = i
inputs.append(impi)
print 'Starting the loop with %i nodes...'%nSlots
pool.map(xLoop, inputs)
pool.close()
pool.join()
return
# Prepare the histogram
if histo == None:
if bins == []:
histo = TH1F('histo', '', nbins, bin0, binN)
else :
ba = array('f', bins)
histo = TH1F('histo', '', bins, ba)
# Print some information
if iChunk == -1: print 'Starting the loop in event %i... runing on %i events of a total of %i'%(e0, nEvents, nEntries)
theCut = cut; theVar = var; theWeight = weight
if iChunk <= 0:
print ' Variable: %s'%theVar
print ' Cut : %s'%theCut
print ' Weight : %s'%theWeight
for iEv in range(e0, nEvents+e0):
t.GetEntry(iEv)
if not t.TNBtags >= 1: continue
nEv += 1
if iChunk == -1:
if nEv % 10000 == 0: print "[%i/%i] (%1.2f %s), event %i in tree"%(nEv, nEvents, float(nEv)/float(nEvents), '%', e0+nEv)
elif iChunk == 0:
ns = float(nEntries)/float(nEvents)
if nEv % 10000 == 0: print "[%i/%i] (%1.2f %s)"%(nEv*ns, nEntries, float(nEv)/float(nEvents), '%')
passCut = EvalExpForEvent(theCut, t)
val = EvalExpForEvent(theVar, t)
weight = EvalExpForEvent(theWeight, t)
if passCut: histo.Fill(val, weight)
if nEv >= nEvents: break
return histo
