def setstyle(self):
# Delete previous PostScript plots and set Canvas options
gSystem.Exec('rm -f ' + 'D0.pdf')
gSystem.Exec('rm -f ' + 'Fit.pdf')
gStyle.SetCanvasBorderMode(0)
gStyle.SetCanvasColor(0)
gStyle.SetStatBorderSize(1)
gStyle.SetStatColor(0)
Z_ExtraEl_LepBDT_MC_TTbar_hist_EB.Write()
Z_ExtraEl_LepBDT_MC_TTbar_hist_EE.Write()
Z_ExtraMu_LepBDT_MC_TTbar_hist.Write()
Z_ExtraMu_LepBDT_MC_TTbar_hist_MB.Write()
Z_ExtraMu_LepBDT_MC_TTbar_hist_ME.Write()
LepBDT_MC_TTbar_outFile.Close()
print "MC TTbar histo file created!"
# ********************
# ****************************************
# create output directory
# ****************************************
outputDir = "LepBDTdistrib_DATAvsMC_" + str(period) + "_" + str(treeText)
gSystem.Exec("mkdir -p " + outputDir)
print "Output directory created!"
# **************************
# read data histos from file
# **************************
histoDATA_input = TFile.Open("LepBDTdistrib_DATA_" + period + "_" + treeText +
".root")
print 'Reading file', histoDATA_input.GetName(), '...'
LepBDTDATA_list = []
LepBDTDATA_list.append(histoDATA_input.Get('Z_ele_1st_LepBDT_hist'))
LepBDTDATA_list.append(histoDATA_input.Get('Z_ele_1st_LepBDT_hist_EB'))
LepBDTDATA_list.append(histoDATA_input.Get('Z_ele_1st_LepBDT_hist_EE'))
LepBDTDATA_list.append(histoDATA_input.Get('Z_mu_1st_LepBDT_hist'))
ut.set_margin_lbtr(gPad, 0.1, 0.1, 0.015, 0.15)
#gPad.SetLogz()
gPad.SetGrid()
hEnThetaTag.SetMinimum(0)
hEnThetaTag.SetMaximum(1)
hEnThetaTag.SetContour(300)
hEnThetaTag.Draw("colz")
ut.invert_col(rt.gPad)
can.SaveAs("01fig.pdf")
#acc_el_en_theta_tag
#_____________________________________________________________________________
if __name__ == "__main__":
gROOT.SetBatch()
gStyle.SetPadTickX(1)
gStyle.SetFrameLineWidth(2)
main()
#beep when done
gSystem.Exec("mplayer computerbeep_1.mp3 > /dev/null 2>&1")
print 'Input files with Fit values read!'
#****************************************************************************
# make output directories
outDir_fit = "FitResults_" + str(period) + "_" + str(treeText)
if(applyPU2017):
outDir_ZPlots = "ZPlots_" + str(period) + "_" + str(treeText) + "_2017PU"
else:
outDir_ZPlots = "ZPlots_" + str(period) + "_" + str(treeText)
outDir_LeptonPlots = "LeptonPlots_" + str(period) + "_" + str(treeText)
gSystem.Exec("mkdir -p " + outDir_fit)
gSystem.Exec("mkdir -p " + outDir_ZPlots)
gSystem.Exec("mkdir -p " + outDir_LeptonPlots)
print "Output directories created!"
data = TFile(inputROOT)
RunNum_B = []
LumiNum_B = []
RunNum_E = []
LumiNum_E = []
recorded = []
# Read the input JSON file and store it
ReadJSON(inputTXT, RunNum_B, LumiNum_B, RunNum_E, LumiNum_E, recorded)
#period = "data2018"
# *****************************
if (period == "data2016"):
lumiText = "35.92 fb^{-1}"
elif (period == "data2017"):
lumiText = "41.53 fb^{-1}"
elif (period == "data2018"):
lumiText = "59.74 fb^{-1}"
else:
print("Error: wrong option!")
# create output directory
DIR = "/afs/cern.ch/work/e/elfontan/private/HZZ/RUN2_Legacy/CMSSW_10_2_15/src/ZZAnalysis/AnalysisStep/test/hzz4l_ValidationPlots/" + period + "_IDchecks_jets_issues_ZTree/"
gSystem.Exec("mkdir -p " + DIR)
print "Output directory created: " + str(DIR)
# Open file and get histos
filename = "f_" + period
filename = TFile.Open(DIR + "leadingJet_etaDistributions_" + period +
"_ZTree.root")
h_noID_data = filename.Get("leadingJet_Eta_noID_data")
h_jetID_data = filename.Get("leadingJet_Eta_jetID_data")
h_PUID_data = filename.Get("leadingJet_Eta_PUID_data")
h_noID_MC = filename.Get("leadingJet_Eta_noID_MC")
h_jetID_MC = filename.Get("leadingJet_Eta_jetID_MC")
h_PUID_MC = filename.Get("leadingJet_Eta_PUID_MC")
c_data = ROOT.TCanvas()
c_data.cd()
def main():
try:
# retrive command line options
shortopts = "w:m:i:j:f:g:t:o:a:vgh?"
longopts = ["weight_fold=", "methods=", "inputfilesig=", "inputfilebkg=", "friendinputfilesig=", "friendinputfilebkg=", "inputtrees=", "outputfile=", "verbose", "gui", "help", "usage"]
opts, args = getopt.getopt( sys.argv[1:], shortopts, longopts )
except getopt.GetoptError:
# print help information and exit:
print "ERROR: unknown options in argument %s" % sys.argv[1:]
usage()
sys.exit(1)
infnameSig = DEFAULT_INFNAMESIG
infnameBkg = DEFAULT_INFNAMEBKG
friendfnameSig = DEFAULT_FRIENDNAMESIG
friendfnameBkg = DEFAULT_FRIENDNAMEBKG
treeNameSig = DEFAULT_TREESIG
treeNameBkg = DEFAULT_TREEBKG
outfname = DEFAULT_OUTFNAME
methods = DEFAULT_METHODS
weight_fold = "weights"
verbose = False
gui = False
addedcuts = ""
for o, a in opts:
if o in ("-?", "-h", "--help", "--usage"):
usage()
sys.exit(0)
elif o in ("-w", "--weight_fold"):
weight_fold = a
elif o in ("-m", "--methods"):
methods = a
elif o in ("-i", "--inputfilesig"):
infnameSig = a
elif o in ("-j", "--inputfilebkg"):
infnameBkg = a
elif o in ("-f", "--friendinputfilesig"):
friendfnameSig = a
elif o in ("-g", "--friendinputfilebkg"):
friendfnameBkg = a
elif o in ("-o", "--outputfile"):
outfname = a
elif o in ("-a", "--addedcuts"):
addedcuts = a
elif o in ("-t", "--inputtrees"):
a.strip()
trees = a.rsplit( ' ' )
trees.sort()
trees.reverse()
if len(trees)-trees.count('') != 2:
print "ERROR: need to give two trees (each one for signal and background)"
print trees
sys.exit(1)
treeNameSig = trees[0]
treeNameBkg = trees[1]
elif o in ("-v", "--verbose"):
verbose = True
elif o in ("-g", "--gui"):
gui = True
# Print methods
mlist = methods.replace(' ',',').split(',')
print "=== TMVAClassification: use method(s)..."
for m in mlist:
if m.strip() != '':
print "=== - <%s>" % m.strip()
# Print the file
print "Using file " + infnameSig + " for signal..."
print "Using file " + infnameBkg + " for background..."
# Import ROOT classes
from ROOT import gSystem, gROOT, gApplication, TFile, TTree, TCut
# check ROOT version, give alarm if 5.18
print "ROOT version is " + str(gROOT.GetVersionCode())
if gROOT.GetVersionCode() >= 332288 and gROOT.GetVersionCode() < 332544:
print "*** You are running ROOT version 5.18, which has problems in PyROOT such that TMVA"
print "*** does not run properly (function calls with enums in the argument are ignored)."
print "*** Solution: either use CINT or a C++ compiled version (see TMVA/macros or TMVA/examples),"
print "*** or use another ROOT version (e.g., ROOT 5.19)."
sys.exit(1)
# Logon not automatically loaded through PyROOT (logon loads TMVA library) load also GUI
gROOT.SetMacroPath( "./" )
## SO I TAKE DEFAULT FORM ROOT# gROOT.Macro ( "./TMVAlogon.C" )
#! gROOT.LoadMacro ( "./TMVAGui.C" )
# Import TMVA classes from ROOT
from ROOT import TMVA
# Output file
outputFile = TFile( outfname, 'RECREATE' )
# Create instance of TMVA factory (see TMVA/macros/TMVAClassification.C for more factory options)
# All TMVA output can be suppressed by removing the "!" (not) in
# front of the "Silent" argument in the option string
factory = TMVA.Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification" )
# Set verbosity
factory.SetVerbose( verbose )
# If you wish to modify default settings
# (please check "src/Config.h" to see all available global options)
# gConfig().GetVariablePlotting()).fTimesRMS = 8.0
(TMVA.gConfig().GetIONames()).fWeightFileDir = weight_fold;
# Define the input variables that shall be used for the classifier training
# note that you may also use variable expressions, such as: "3*var1/var2*abs(var3)"
# [all types of expressions that can also be parsed by TTree::Draw( "expression" )]
factory.AddVariable( "dR_l1l2", "dR_l1l2", "", 'F' )
factory.AddVariable( "dR_b1b2", "dR_b1b2", "", 'F' )
factory.AddVariable( "dR_bl", "dR_bl", "", 'F' )
factory.AddVariable( "dR_l1l2b1b2", "dR_l1l2b1b2", "", 'F' )
factory.AddVariable( "MINdR_bl", "MINdR_bl", "", 'F' )
factory.AddVariable( "dphi_l1l2b1b2", "dphi_l1l2b1b2", "", 'F' )
factory.AddVariable( "mass_l1l2", "mass_l1l2", "", 'F' )
factory.AddVariable( "mass_b1b2", "mass_b1b2", "", 'F' )
factory.AddVariable( "mass_trans", "mass_trans", "", 'F' )
factory.AddVariable( "MT2", "MT2", "", 'F' )
factory.AddVariable( "pt_b1b2", "pt_b1b2", "", 'F' )
#factory.AddVariable( "MMC_h2mass_MaxBin", "MMC_h2mass_MaxBin", "", 'F' )
#factory.AddVariable( "MMC_h2mass_RMS", "MMC_h2mass_RMS", "", 'F' )
#factory.AddVariable( "MMC_h2mass_prob", "MMC_h2mass_prob", "", 'F' )
# You can add so-called "Spectator variables", which are not used in the MVA training,
# but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
# input variables, the response values of all trained MVAs, and the spectator variables
# factory.AddSpectator( "spec1:=var1*2", "Spectator 1", "units", 'F' )
# factory.AddSpectator( "spec2:=var1*3", "Spectator 2", "units", 'F' )
# Read input data
if gSystem.AccessPathName( infnameSig ) != 0 or gSystem.AccessPathName( infnameBkg ): gSystem.Exec( "wget http://root.cern.ch/files/" + infname )
inputSig = TFile.Open( infnameSig )
inputBkg = TFile.Open( infnameBkg )
# Get the signal and background trees for training
signal = inputSig.Get( treeNameSig )
background = inputBkg.Get( treeNameBkg )
##signal.AddFriend( "eleIDdir/isoT1 = eleIDdir/T1", friendfnameSig )
##background.AddFriend( "eleIDdir/isoT1 = eleIDdir/T1", friendfnameBkg )
# Global event weights (see below for setting event-wise weights)
signalWeight = 1.
backgroundWeight = 1.
#I don't think there's a general answer to this. The safest 'default'
#is to use the envent weight such that you have equal amounts of signal
#and background
#for the training, otherwise for example: if you look for a rare
#signal and you use the weight to scale the number of events according
#to the expected ratio of signal and background
#according to the luminosity... the classifier sees hardly any signal
#events and "thinks" .. Oh I just classify everything background and do
#a good job!
#
#One can try to 'optimize' the training a bit more in either 'high
#purity' or 'high efficiency' by choosing different weights, but as I
#said, there's no fixed rule. You'd have
#to 'try' and see if you get better restults by playing with the weights.
# ====== register trees ====================================================
#
# the following method is the prefered one:
# you can add an arbitrary number of signal or background trees
factory.AddSignalTree ( signal, signalWeight )
factory.AddBackgroundTree( background, backgroundWeight )
# To give different trees for training and testing, do as follows:
# factory.AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" )
# factory.AddSignalTree( signalTestTree, signalTestWeight, "Test" )
# Use the following code instead of the above two or four lines to add signal and background
# training and test events "by hand"
# NOTE that in this case one should not give expressions (such as "var1+var2") in the input
# variable definition, but simply compute the expression before adding the event
#
# # --- begin ----------------------------------------------------------
#
# ... *** please lookup code in TMVA/macros/TMVAClassification.C ***
#
# # --- end ------------------------------------------------------------
#
# ====== end of register trees ==============================================
# Set individual event weights (the variables must exist in the original TTree)
# for signal : factory.SetSignalWeightExpression ("weight1*weight2");
# for background: factory.SetBackgroundWeightExpression("weight1*weight2");
# Apply additional cuts on the signal and background sample.
# example for cut: mycut = TCut( "abs(var1)<0.5 && abs(var2-0.5)<1" )
#mycutSig = TCut( "nu1and2_diBaxis_t>-900 && met_diBaxis_t>-900&& hasb1jet && hasb2jet && hasMET && hasGenMET && hasdRljet && hastwomuons" )
mycutSig = TCut( addedcuts )
#mycutBkg = TCut( "event_n%2!=0 && " + addedcuts )
mycutBkg = TCut( addedcuts )
#mycutBkg = TCut( "nu1and2_diBaxis_t>-900 && met_diBaxis_t>-900&& hasb1jet && hasb2jet && hasMET && hasGenMET && hasdRljet && hastwomuons" )
print mycutSig
# Here, the relevant variables are copied over in new, slim trees that are
# used for TMVA training and testing
# "SplitMode=Random" means that the input events are randomly shuffled before
# splitting them into training and test samples
factory.PrepareTrainingAndTestTree( mycutSig, mycutBkg,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" )
# --------------------------------------------------------------------------------------------------
# ---- Book MVA methods
#
# please lookup the various method configuration options in the corresponding cxx files, eg:
# src/MethoCuts.cxx, etc, or here: http://tmva.sourceforge.net/optionRef.html
# it is possible to preset ranges in the option string in which the cut optimisation should be done:
# "...:CutRangeMin[2]=-1:CutRangeMax[2]=1"...", where [2] is the third input variable
# Cut optimisation
if "Cuts" in mlist:
factory.BookMethod( TMVA.Types.kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:VarProp[0]=FMax:VarProp[1]=FMin" )
if "CutsD" in mlist:
factory.BookMethod( TMVA.Types.kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate" )
if "CutsPCA" in mlist:
factory.BookMethod( TMVA.Types.kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA" )
if "CutsGA" in mlist:
factory.BookMethod( TMVA.Types.kCuts, "CutsGA",
"H:!V:FitMethod=GA:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95:VarProp[0]=FMin:VarProp[1]=FMax" )
if "CutsSA" in mlist:
factory.BookMethod( TMVA.Types.kCuts, "CutsSA",
"!H:!V:FitMethod=SA:EffSel:MaxCalls=150000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" )
# Likelihood ("naive Bayes estimator")
if "Likelihood" in mlist:
factory.BookMethod( TMVA.Types.kLikelihood, "Likelihood",
"H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" )
# Decorrelated likelihood
if "LikelihoodD" in mlist:
factory.BookMethod( TMVA.Types.kLikelihood, "LikelihoodD",
"!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=Decorrelate" )
# PCA-transformed likelihood
if "LikelihoodPCA" in mlist:
factory.BookMethod( TMVA.Types.kLikelihood, "LikelihoodPCA",
"!H:!V:!TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmooth=5:NAvEvtPerBin=50:VarTransform=PCA" )
# Use a kernel density estimator to approximate the PDFs
if "LikelihoodKDE" in mlist:
factory.BookMethod( TMVA.Types.kLikelihood, "LikelihoodKDE",
"!H:!V:!TransformOutput:PDFInterpol=KDE:KDEtype=Gauss:KDEiter=Adaptive:KDEFineFactor=0.3:KDEborder=None:NAvEvtPerBin=50" )
# Use a variable-dependent mix of splines and kernel density estimator
if "LikelihoodMIX" in mlist:
factory.BookMethod( TMVA.Types.kLikelihood, "LikelihoodMIX",
"!H:!V:!TransformOutput:PDFInterpolSig[0]=KDE:PDFInterpolBkg[0]=KDE:PDFInterpolSig[1]=KDE:PDFInterpolBkg[1]=KDE:PDFInterpolSig[2]=Spline2:PDFInterpolBkg[2]=Spline2:PDFInterpolSig[3]=Spline2:PDFInterpolBkg[3]=Spline2:KDEtype=Gauss:KDEiter=Nonadaptive:KDEborder=None:NAvEvtPerBin=50" )
# Test the multi-dimensional probability density estimator
# here are the options strings for the MinMax and RMS methods, respectively:
# "!H:!V:VolumeRangeMode=MinMax:DeltaFrac=0.2:KernelEstimator=Gauss:GaussSigma=0.3" );
# "!H:!V:VolumeRangeMode=RMS:DeltaFrac=3:KernelEstimator=Gauss:GaussSigma=0.3" );
if "PDERS" in mlist:
factory.BookMethod( TMVA.Types.kPDERS, "PDERS",
"!H:!V:NormTree=T:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600" )
if "PDERSD" in mlist:
factory.BookMethod( TMVA.Types.kPDERS, "PDERSD",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=Decorrelate" )
if "PDERSPCA" in mlist:
factory.BookMethod( TMVA.Types.kPDERS, "PDERSPCA",
"!H:!V:VolumeRangeMode=Adaptive:KernelEstimator=Gauss:GaussSigma=0.3:NEventsMin=400:NEventsMax=600:VarTransform=PCA" )
# Multi-dimensional likelihood estimator using self-adapting phase-space binning
if "PDEFoam" in mlist:
factory.BookMethod( TMVA.Types.kPDEFoam, "PDEFoam",
"!H:!V:SigBgSeparate=F:TailCut=0.001:VolFrac=0.0666:nActiveCells=500:nSampl=2000:nBin=5:Nmin=100:Kernel=None:Compress=T" )
if "PDEFoamBoost" in mlist:
factory.BookMethod( TMVA.Types.kPDEFoam, "PDEFoamBoost",
"!H:!V:Boost_Num=30:Boost_Transform=linear:SigBgSeparate=F:MaxDepth=4:UseYesNoCell=T:DTLogic=MisClassificationError:FillFoamWithOrigWeights=F:TailCut=0:nActiveCells=500:nBin=20:Nmin=400:Kernel=None:Compress=T" )
# K-Nearest Neighbour classifier (KNN)
if "KNN" in mlist:
factory.BookMethod( TMVA.Types.kKNN, "KNN",
"H:nkNN=20:ScaleFrac=0.8:SigmaFact=1.0:Kernel=Gaus:UseKernel=F:UseWeight=T:!Trim" )
# H-Matrix (chi2-squared) method
if "HMatrix" in mlist:
factory.BookMethod( TMVA.Types.kHMatrix, "HMatrix", "!H:!V" )
# Linear discriminant (same as Fisher discriminant)
if "LD" in mlist:
factory.BookMethod( TMVA.Types.kLD, "LD", "H:!V:VarTransform=None:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" )
# Fisher discriminant (same as LD)
if "Fisher" in mlist:
factory.BookMethod( TMVA.Types.kFisher, "Fisher", "H:!V:Fisher:CreateMVAPdfs:PDFInterpolMVAPdf=Spline2:NbinsMVAPdf=50:NsmoothMVAPdf=10" )
# Fisher with Gauss-transformed input variables
if "FisherG" in mlist:
factory.BookMethod( TMVA.Types.kFisher, "FisherG", "H:!V:VarTransform=Gauss" )
# Composite classifier: ensemble (tree) of boosted Fisher classifiers
if "BoostedFisher" in mlist:
factory.BookMethod( TMVA.Types.kFisher, "BoostedFisher",
"H:!V:Boost_Num=20:Boost_Transform=log:Boost_Type=AdaBoost:Boost_AdaBoostBeta=0.2" )
# Function discrimination analysis (FDA) -- test of various fitters - the recommended one is Minuit (or GA or SA)
if "FDA_MC" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_MC",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:SampleSize=100000:Sigma=0.1" );
if "FDA_GA" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_GA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:PopSize=300:Cycles=3:Steps=20:Trim=True:SaveBestGen=1" );
if "FDA_SA" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_SA",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=SA:MaxCalls=15000:KernelTemp=IncAdaptive:InitialTemp=1e+6:MinTemp=1e-6:Eps=1e-10:UseDefaultScale" );
if "FDA_MT" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_MT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=2:UseImprove:UseMinos:SetBatch" );
if "FDA_GAMT" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_GAMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=GA:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:Cycles=1:PopSize=5:Steps=5:Trim" );
if "FDA_MCMT" in mlist:
factory.BookMethod( TMVA.Types.kFDA, "FDA_MCMT",
"H:!V:Formula=(0)+(1)*x0+(2)*x1+(3)*x2+(4)*x3:ParRanges=(-1,1)(-10,10);(-10,10);(-10,10);(-10,10):FitMethod=MC:Converger=MINUIT:ErrorLevel=1:PrintLevel=-1:FitStrategy=0:!UseImprove:!UseMinos:SetBatch:SampleSize=20" );
# TMVA ANN: MLP (recommended ANN) -- all ANNs in TMVA are Multilayer Perceptrons
if "MLP" in mlist:
factory.BookMethod( TMVA.Types.kMLP, "MLP", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator" )
if "MLPBFGS" in mlist:
factory.BookMethod( TMVA.Types.kMLP, "MLPBFGS", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:!UseRegulator" )
if "MLPBNN" in mlist:
factory.BookMethod( TMVA.Types.kMLP, "MLPBNN", "H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:TrainingMethod=BFGS:UseRegulator" ) # BFGS training with bayesian regulators
# CF(Clermont-Ferrand)ANN
if "CFMlpANN" in mlist:
factory.BookMethod( TMVA.Types.kCFMlpANN, "CFMlpANN", "!H:!V:NCycles=2000:HiddenLayers=N+1,N" ) # n_cycles:#nodes:#nodes:...
# Tmlp(Root)ANN
if "TMlpANN" in mlist:
factory.BookMethod( TMVA.Types.kTMlpANN, "TMlpANN", "!H:!V:NCycles=200:HiddenLayers=N+1,N:LearningMethod=BFGS:ValidationFraction=0.3" ) #n_cycles:#nodes:#nodes:...
# Support Vector Machine
if "SVM" in mlist:
factory.BookMethod( TMVA.Types.kSVM, "SVM", "Gamma=0.25:Tol=0.001:VarTransform=Norm" )
# Boosted Decision Trees
if "BDTG" in mlist:
factory.BookMethod( TMVA.Types.kBDT, "BDTG",
"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5" )
if "BDT" in mlist:
factory.BookMethod( TMVA.Types.kBDT, "BDT",
"!H:!V:NTrees=850:nEventsMin=150:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" )
if "BDTB" in mlist:
factory.BookMethod( TMVA.Types.kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning" )
if "BDTD" in mlist:
factory.BookMethod( TMVA.Types.kBDT, "BDTD",
"!H:!V:NTrees=400:nEventsMin=400:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning:VarTransform=Decorrelate" )
# RuleFit -- TMVA implementation of Friedman's method
if "RuleFit" in mlist:
factory.BookMethod( TMVA.Types.kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.0:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" )
# --------------------------------------------------------------------------------------------------
# ---- Now you can tell the factory to train, test, and evaluate the MVAs.
# Train MVAs
factory.TrainAllMethods()
# Test MVAs
factory.TestAllMethods()
# Evaluate MVAs
factory.EvaluateAllMethods()
# Save the output.
outputFile.Close()
print "=== wrote root file %s\n" % outfname
print "=== TMVAClassification is done!\n"
# open the GUI for the result macros
if( gui ):
gROOT.ProcessLine( "TMVAGui(\"%s\")" % outfname )
# keep the ROOT thread running
gApplication.Run()
# period = "data2017"
period = "data2018"
# *****************************
lumiText = '16.6 fb^{-1}'
#******************************
if (ZZTree): treeText = "ZZTree"
elif (CRZLTree): treeText = "CRZLTree"
elif (ZTree): treeText = "ZTree"
else: print("Error: wrong option!")
#******************************
# create output directory
OutputPath = "SipDistrib_DATAvsMC_" + str(period) + "_" + str(treeText)
gSystem.Exec("mkdir -p " + OutputPath)
print "Output directory created!"
# *** DATA ***
#read histos from data file
histoDATA_input = TFile.Open("SipDistrib_DATA_" + str(period) + "_" +
str(treeText) + ".root")
print 'Reading file', histoDATA_input.GetName(), '...'
SipDATA = []
SipDATA.append(histoDATA_input.Get('SIP leading ele'))
SipDATA.append(histoDATA_input.Get('SIP leading ele in ECAL Barrel'))
SipDATA.append(histoDATA_input.Get('SIP leading ele in ECAL Endcap'))
out.Close()
#main
#_____________________________________________________________________________
if __name__ == "__main__":
gROOT.SetBatch()
gStyle.SetPadTickX(1)
gStyle.SetFrameLineWidth(2)
main()
#beep when finished
#gSystem.Exec("mplayer ../computerbeep_1.mp3 > /dev/null 2>&1")
gSystem.Exec("mplayer ../input_ok_3_clean.mp3 > /dev/null 2>&1")
def main():
#testing macro for bin centers from the data
gROOT.SetBatch()
#range for |t|
ptmin = 0.
ptmax = 0.109 # 0.109 0.01 for interference range
#default binning
ptbin = 0.004 # 0.004 0.0005 for interference range
#long bins at high |t|
ptmid = 0.06 # 0.08, value > ptmax will switch it off 0.06
ptlon = 0.01 # 0.01
#mass interval
mmin = 2.8
mmax = 3.2
#data
basedir = "../../../star-upc-data/ana/muDst/muDst_run1/sel5"
infile = "ana_muDst_run1_all_sel5z.root"
#open the inputs
inp = TFile.Open(basedir + "/" + infile)
tree = inp.Get("jRecTree")
#evaluate binning
bins = ut.get_bins_vec_2pt(ptbin, ptlon, ptmin, ptmax, ptmid)
#load the data
strsel = "jRecM>{0:.3f} && jRecM<{1:.3f}".format(mmin, mmax)
#input pT^2
hPt = ut.prepare_TH1D_vec("hPt", bins)
tree.Draw("jRecPt*jRecPt >> hPt", strsel)
#bin centers from the data
cen_tree = get_centers_from_tree(hPt, tree, strsel)
#print
cen_toyMC = get_centers_from_toyMC(hPt)
for i in xrange(len(cen_tree)):
#print i, cen_tree[i], cen_toyMC[i], cen_tree[i] - cen_toyMC[i]
pass
#gr = get_data_graph(hPt, cen_tree)
gr = get_data_graph(hPt, cen_toyMC)
#plot the distribution
can = ut.box_canvas()
frame = ut.prepare_TH1D("frame", ptbin, ptmin, ptmax)
#ut.set_margin_lbtr(gPad, 0.1, 0.09, 0.03, 0.03)
ut.set_margin_lbtr(gPad, 0.1, 0.09, 0.055, 0.03)
gPad.SetLogy()
frame.SetMaximum(310)
#frame.SetMinimum(1.e-6)
frame.SetMinimum(3)
#frame.SetMinimum(1e-5) # 3e-5
frame.Draw()
#hPt.Draw("e1same")
gr.Draw("epsame")
ut.invert_col(gPad)
can.SaveAs("01fig.pdf")
#beep when finished
gSystem.Exec("mplayer ../computerbeep_1.mp3 > /dev/null 2>&1")
def main():
gROOT.SetBatch()
#range for |t|
ptmin = 0.
ptmax = 0.109 # 0.109 0.01 for interference range
#default binning
ptbin = 0.004 # 0.004 0.0005 for interference range
#long bins at high |t|
ptmid = 0.06 # 0.08, value > ptmax will switch it off 0.06
ptlon = 0.01 # 0.01
#short bins at low |t|
ptlow = 0.01
ptshort = 0.0005
#mass interval
mmin = 2.8
mmax = 3.2
#dy = 2. # rapidity interval, for integrated sigma
dy = 1.
ngg = 131 # number of gamma-gamma from mass fit
lumi = 13871.907 # lumi in inv. ub
#correction to luminosity for ana/triggered events
ratio_ana = 3420950. / 3694000
#scale the lumi for |z| around nominal bunch crossing
ratio_zdc_vtx = 0.502
Reta = 0.503 # pseudorapidity preselection
#Reta = 1.
trg_eff = 0.67 # bemc trigger efficiency
ratio_tof = 1.433 # tof correction to efficiency
bbceff = 0.97 # BBC veto inefficiency
zdc_acc = 0.49 # ZDC acceptance to XnXn 0.7
#zdc_acc = 1.
br = 0.05971 # dielectrons branching ratio
#data
basedir = "../../../star-upc-data/ana/muDst/muDst_run1/sel5"
infile = "ana_muDst_run1_all_sel5z.root"
#MC
basedir_sl = "../../../star-upc-data/ana/starsim/slight14e/sel5"
#infile_sl = "ana_slight14e1x2_s6_sel5z.root"
infile_sl = "ana_slight14e1x3_s6_sel5z.root"
#
basedir_sart = "../../../star-upc-data/ana/starsim/sartre14a/sel5"
infile_sart = "ana_sartre14a1_sel5z_s6_v2.root"
#
basedir_bgen = "../../../star-upc-data/ana/starsim/bgen14a/sel5"
infile_bgen = "ana_bgen14a1_v0_sel5z_s6.root"
#infile_bgen = "ana_bgen14a2_sel5z_s6.root"
#
basedir_gg = "../../../star-upc-data/ana/starsim/slight14e/sel5"
infile_gg = "ana_slight14e2x1_sel5_nzvtx.root"
#model predictions
gSlight = load_starlight(dy)
gSartre = load_sartre()
gFlat = loat_flat_pt2()
gMS = load_ms()
gCCK = load_cck()
#open the inputs
inp = TFile.Open(basedir + "/" + infile)
tree = inp.Get("jRecTree")
#
inp_gg = TFile.Open(basedir_gg + "/" + infile_gg)
tree_gg = inp_gg.Get("jRecTree")
#
inp_sl = TFile.Open(basedir_sl + "/" + infile_sl)
tree_sl_gen = inp_sl.Get("jGenTree")
#
inp_sart = TFile.Open(basedir_sart + "/" + infile_sart)
tree_sart_gen = inp_sart.Get("jGenTree")
#
inp_bgen = TFile.Open(basedir_bgen + "/" + infile_bgen)
tree_bgen_gen = inp_bgen.Get("jGenTree")
#evaluate binning
#print "bins:", ut.get_nbins(ptbin, ptmin, ptmax)
bins = ut.get_bins_vec_2pt(ptbin, ptlon, ptmin, ptmax, ptmid)
#bins = ut.get_bins_vec_3pt(ptshort, ptbin, ptlon, ptmin, ptmax, ptlow, ptmid)
#print "bins2:", bins.size()-1
#load the data
strsel = "jRecM>{0:.3f} && jRecM<{1:.3f}".format(mmin, mmax)
hPt = ut.prepare_TH1D_vec("hPt", bins)
tree.Draw("jRecPt*jRecPt >> hPt", strsel)
#distribution for bin centers
hPtCen = hPt.Clone("hPtCen")
#gamma-gamma component
hPtGG = ut.prepare_TH1D_vec("hPtGG", bins)
tree_gg.Draw("jRecPt*jRecPt >> hPtGG", strsel)
#normalize the gamma-gamma component
ut.norm_to_num(hPtGG, ngg, rt.kGreen)
#incoherent functional shape
func_incoh_pt2 = TF1("func_incoh", "[0]*exp(-[1]*x)", 0., 10.)
func_incoh_pt2.SetParameters(873.04, 3.28)
#fill incoherent histogram from functional shape
hPtIncoh = ut.prepare_TH1D_vec("hPtIncoh", bins)
ut.fill_h1_tf(hPtIncoh, func_incoh_pt2, rt.kRed)
#print "Entries before gamma-gamma and incoherent subtraction:", hPt.GetEntries()
#subtract gamma-gamma and incoherent components
hPt.Sumw2()
hPt.Add(hPtGG, -1)
#print "Gamma-gamma entries:", hPtGG.Integral()
#print "Entries after gamma-gamma subtraction:", hPt.Integral()
#print "Incoherent entries:", hPtIncoh.Integral()
hPt.Add(hPtIncoh, -1)
#print "Entries after all subtraction:", hPt.Integral()
#scale the luminosity
lumi_scaled = lumi * ratio_ana * ratio_zdc_vtx
#print "lumi_scaled:", lumi_scaled
#denominator for deconvoluted distribution, conversion ub to mb
den = Reta * br * zdc_acc * trg_eff * bbceff * ratio_tof * lumi_scaled * 1000. * dy
#deconvolution
deconv_min = bins[0]
deconv_max = bins[bins.size() - 1]
deconv_nbin = bins.size() - 1
gROOT.LoadMacro("fill_response_matrix.C")
#Starlight response
#resp_sl = RooUnfoldResponse(deconv_nbin, deconv_min, deconv_max, deconv_nbin, deconv_min, deconv_max)
resp_sl = RooUnfoldResponse(hPt, hPt)
rt.fill_response_matrix(tree_sl_gen, resp_sl)
#
unfold_sl = RooUnfoldBayes(resp_sl, hPt, 15)
#unfold_sl = RooUnfoldSvd(resp_sl, hPt, 15)
hPtSl = unfold_sl.Hreco()
#ut.set_H1D(hPtSl)
#apply the denominator and bin width
ut.norm_to_den_w(hPtSl, den)
#Sartre response
#resp_sart = RooUnfoldResponse(deconv_nbin, deconv_min, deconv_max, deconv_nbin, deconv_min, deconv_max)
#resp_sart = RooUnfoldResponse(hPt, hPt)
#rt.fill_response_matrix(tree_sart_gen, resp_sart)
#
#unfold_sart = RooUnfoldBayes(resp_sart, hPt, 10)
#hPtSart = unfold_sart.Hreco()
#ut.set_H1D(hPtSart)
#hPtSart.SetMarkerStyle(21)
#Flat pT^2 response
#resp_bgen = RooUnfoldResponse(deconv_nbin, deconv_min, deconv_max, deconv_nbin, deconv_min, deconv_max)
resp_bgen = RooUnfoldResponse(hPt, hPt)
rt.fill_response_matrix(tree_bgen_gen, resp_bgen)
#
unfold_bgen = RooUnfoldBayes(resp_bgen, hPt, 14)
hPtFlat = unfold_bgen.Hreco()
#ut.set_H1D(hPtFlat)
#apply the denominator and bin width
ut.norm_to_den_w(hPtFlat, den)
#hPtFlat.SetMarkerStyle(22)
#hPtFlat.SetMarkerSize(1.3)
#systematical errors
err_zdc_acc = 0.1
err_bemc_eff = 0.03
#sys_err = rt.TMath.Sqrt(err_zdc_acc*err_zdc_acc + err_bemc_eff*err_bemc_eff)
sys_err = err_zdc_acc * err_zdc_acc + err_bemc_eff * err_bemc_eff
#print "Total sys err:", sys_err
hSys = ut.prepare_TH1D_vec("hSys", bins)
hSys.SetOption("E2")
hSys.SetFillColor(rt.kOrange + 1)
hSys.SetLineColor(rt.kOrange)
for ibin in xrange(1, hPtFlat.GetNbinsX() + 1):
hSys.SetBinContent(ibin, hPtFlat.GetBinContent(ibin))
sig_sl = hPtSl.GetBinContent(ibin)
sig_fl = hPtFlat.GetBinContent(ibin)
err_deconv = TMath.Abs(sig_fl - sig_sl) / sig_fl
#print "err_deconv", err_deconv
#sys_err += err_deconv*err_deconv
sys_err_sq = sys_err + err_deconv * err_deconv
sys_err_bin = TMath.Sqrt(sys_err_sq)
stat_err = hPtFlat.GetBinError(ibin) / hPtFlat.GetBinContent(ibin)
tot_err = TMath.Sqrt(stat_err * stat_err + sys_err_sq)
#hSys.SetBinError(ibin, hPtFlat.GetBinContent(ibin)*err_deconv)
hSys.SetBinError(ibin, hPtFlat.GetBinContent(ibin) * sys_err_bin)
#hPtFlat.SetBinError(ibin, hPtFlat.GetBinContent(ibin)*tot_err)
#draw the results
gStyle.SetPadTickX(1)
gStyle.SetFrameLineWidth(2)
#frame for models plot only
frame = ut.prepare_TH1D("frame", ptbin, ptmin, ptmax)
can = ut.box_canvas()
#ut.set_margin_lbtr(gPad, 0.1, 0.09, 0.03, 0.03)
ut.set_margin_lbtr(gPad, 0.1, 0.09, 0.055, 0.01)
ytit = "d#it{#sigma}/d#it{t}d#it{y} (mb/(GeV/c)^{2})"
xtit = "|#kern[0.3]{#it{t}}| ((GeV/c)^{2})"
ut.put_yx_tit(frame, ytit, xtit, 1.4, 1.2)
frame.SetMaximum(11)
#frame.SetMinimum(1.e-6)
#frame.SetMinimum(2e-4)
frame.SetMinimum(1e-5) # 3e-5
frame.Draw()
#hSys.Draw("e2same")
#bin center points from data
#gSig = apply_centers(hPtFlat, hPtCen)
gSig = fixed_centers(hPtFlat)
ut.set_graph(gSig)
#hPtSl.Draw("e1same")
#hPtSart.Draw("e1same")
#hPtFlat.Draw("e1same")
#put model predictions
#gSartre.Draw("lsame")
#gFlat.Draw("lsame")
gMS.Draw("lsame")
gCCK.Draw("lsame")
gSlight.Draw("lsame")
gSig.Draw("P")
frame.Draw("same")
gPad.SetLogy()
cleg = ut.prepare_leg(0.1, 0.96, 0.14, 0.01, 0.035)
cleg.AddEntry(
None,
"Au+Au #rightarrow J/#psi + Au+Au + XnXn, #sqrt{#it{s}_{#it{NN}}} = 200 GeV",
"")
cleg.Draw("same")
leg = ut.prepare_leg(0.45, 0.82, 0.18, 0.1, 0.035)
leg.AddEntry(None, "#bf{|#kern[0.3]{#it{y}}| < 1}", "")
hx = ut.prepare_TH1D("hx", 1, 0, 1)
leg.AddEntry(hx, "STAR")
hx.Draw("same")
leg.Draw("same")
#legend for models
mleg = ut.prepare_leg(0.68, 0.76, 0.3, 0.16, 0.035)
#mleg = ut.prepare_leg(0.68, 0.8, 0.3, 0.12, 0.035)
mleg.AddEntry(gSlight, "STARLIGHT", "l")
mleg.AddEntry(gMS, "MS", "l")
mleg.AddEntry(gCCK, "CCK-hs", "l")
#mleg.AddEntry(gSartre, "Sartre", "l")
#mleg.AddEntry(gFlat, "Flat #it{p}_{T}^{2}", "l")
mleg.Draw("same")
#legend for deconvolution method
dleg = ut.prepare_leg(0.3, 0.75, 0.2, 0.18, 0.035)
#dleg = ut.prepare_leg(0.3, 0.83, 0.2, 0.1, 0.035)
dleg.AddEntry(None, "Unfolding with:", "")
dleg.AddEntry(hPtSl, "Starlight", "p")
#dleg.AddEntry(hPtSart, "Sartre", "p")
dleg.AddEntry(hPtFlat, "Flat #it{p}_{T}^{2}", "p")
#dleg.Draw("same")
ut.invert_col(rt.gPad)
can.SaveAs("01fig.pdf")
#to prevent 'pure virtual method called'
gPad.Close()
#save the cross section to output file
out = TFile("sigma.root", "recreate")
gSig.Write("sigma")
out.Close()
#beep when finished
gSystem.Exec("mplayer ../computerbeep_1.mp3 > /dev/null 2>&1")
hEff.Draw("AP")
#hEff.Draw()
fitFunc.Draw("same")
desc.draw()
leg.Draw("same")
ut.invert_col(rt.gPad)
can.SaveAs("01fig.pdf")
#to prevent 'pure virtual method called'
gPad.Close()
#remove the temporary
outfile.Close()
gSystem.Exec("rm -f "+outnam)
#beep when finished
gSystem.Exec("mplayer ../computerbeep_1.mp3 > /dev/null 2>&1")