def Evaluate(outdir):
sys.stdout = open(outdir + '/tmva.log', 'w')
# Output file
output = TFile(outdir + '/tmva.root', '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("TMVARuleFit", output, "!V:!Silent:Color" )
# Set the variables use for the analysis
input = open(outdir + '/inputvars.txt')
for variable in input.readlines():
factory.AddVariable(variable[:-1], 'F')
# Set the weight directory
TMVA.gConfig().GetIONames().fWeightFileDir = outdir + "/weights"
# Limit the creation of correlation plots
TMVA.gConfig().GetVariablePlotting().fMaxNumOfAllowedVariablesForScatterPlots = 20
# Set the input file with signal and background events
factory.SetInputTrees(
outdir + '/signals.txt',
outdir + '/backgrounds.txt'
)
cutsig = TCut('')
cutbkg = TCut('')
factory.PrepareTrainingAndTestTree( cutsig, cutbkg, "SplitMode=Random:NormMode=NumEvents:!V" )
factory.BookMethod( TMVA.Types.kRuleFit, "RuleFit",
"H:!V:RuleFitModule=RFTMVA:Model=ModRuleLinear:MinImp=0.00001:RuleMinDist=0.001:NTrees=20:fEventsMin=0.01:fEventsMax=0.5:GDTau=-1.:GDTauPrec=0.01:GDStep=0.01:GDNSteps=10000:GDErrScale=1.02" )
# Train MVAs
factory.TrainAllMethods()
# Test MVAs
factory.TestAllMethods()
# Evaluate MVAs
factory.EvaluateAllMethods()
# Save the output.
output.Close()
def fit(self, X, y, X_test=None, y_test=None, weights=None, weights_test=None, signal_label=None, **kwargs):
# (re)configure settings since deleting a previous Factory resets all
# this. This is poor design, TMVA.
config = TMVA.gConfig()
config.GetIONames().fWeightFileDir = self.tmpdir
config.SetSilent(True)
config.SetDrawProgressBar(False)
self.factory.DeleteAllMethods()
extra_kwargs = dict()
if self.task == "Regression":
func = rnp.tmva.add_regression_events
else:
func = rnp.tmva.add_classification_events
extra_kwargs["signal_label"] = signal_label
# test exceptions
assert_raises(TypeError, func, object(), X, y)
assert_raises(ValueError, func, self.factory, X, y[: y.shape[0] / 2])
if weights is not None:
assert_raises(ValueError, func, self.factory, X, y, weights=weights[: weights.shape[0] / 2])
assert_raises(ValueError, func, self.factory, X, y, weights=weights[:, np.newaxis])
assert_raises(ValueError, func, self.factory, [[[1, 2]]], [1])
assert_raises(ValueError, func, self.factory, [[1, 2]], [[[1]]])
func(self.factory, X, y, weights=weights, **extra_kwargs)
if X_test is None:
X_test = X
y_test = y
weights_test = weights
func(self.factory, X_test, y_test, weights=weights_test, test=True, **extra_kwargs)
self.factory.PrepareTrainingAndTestTree(TCut("1"), "NormMode=EqualNumEvents")
options = []
for param, value in kwargs.items():
if value is True:
options.append(param)
elif value is False:
options.append("!{0}".format(param))
else:
options.append("{0}={1}".format(param, value))
options = ":".join(options)
self.factory.BookMethod(self.method, self.method, options)
self.factory.TrainAllMethods()
def fit(self, X, y, X_test=None, y_test=None,
weights=None, weights_test=None,
signal_label=None, **kwargs):
# (re)configure settings since deleting a previous Factory resets all
# this. This is poor design, TMVA.
config = TMVA.gConfig()
config.GetIONames().fWeightFileDir = self.tmpdir
config.SetSilent(True)
config.SetDrawProgressBar(False)
self.factory.DeleteAllMethods()
extra_kwargs = dict()
if self.task == 'Regression':
func = rnp.tmva.add_regression_events
else:
func = rnp.tmva.add_classification_events
extra_kwargs['signal_label'] = signal_label
# test exceptions
assert_raises(TypeError, func, object(), X, y)
assert_raises(ValueError, func,
self.factory, X, y[:y.shape[0] / 2])
if weights is not None:
assert_raises(ValueError, func, self.factory, X, y,
weights=weights[:weights.shape[0]/2])
assert_raises(ValueError, func, self.factory, X, y,
weights=weights[:, np.newaxis])
assert_raises(ValueError, func, self.factory, [[[1, 2]]], [1])
assert_raises(ValueError, func, self.factory, [[1, 2]], [[[1]]])
func(self.factory, X, y, weights=weights, **extra_kwargs)
if X_test is not None and y_test is not None:
func(self.factory, X_test, y_test,
weights=weights_test, test=True, **extra_kwargs)
self.factory.PrepareTrainingAndTestTree(
TCut('1'), 'NormMode=EqualNumEvents')
options = ':'.join(['{0}={1}'.format(param, value)
for param, value in kwargs.items()])
if options:
options = ':' + options
self.factory.BookMethod(self.method, self.method, options)
self.factory.TrainAllMethods()
def main():
try:
# retrive command line options
shortopts = "m:i:n:d:k:l:t:o:vh?"
longopts = [
"methods=", "inputfile=", "nTrees=", "maxDepth=", "mass=",
"varListKey=", "inputtrees=", "outputfile=", "verbose", "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)
infname = DEFAULT_INFNAME
treeNameSig = DEFAULT_TREESIG
treeNameBkg = DEFAULT_TREEBKG
outfname = DEFAULT_OUTFNAME
methods = DEFAULT_METHODS
nTrees = DEFAULT_NTREES
mDepth = DEFAULT_MDEPTH
mass = DEFAULT_MASS
varListKey = DEFAULT_VARLISTKEY
verbose = True
for o, a in opts:
if o in ("-?", "-h", "--help", "--usage"):
usage()
sys.exit(0)
elif o in ("-m", "--methods"):
methods = a
elif o in ("-d", "--maxDepth"):
mDepth = a
elif o in ("-k", "--mass"):
mass = a
elif o in ("-l", "--varListKey"):
varListKey = a
elif o in ("-i", "--inputfile"):
infname = a
elif o in ("-n", "--nTrees"):
nTrees = a
elif o in ("-o", "--outputfile"):
outfname = 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
varList = varsList.varList[varListKey]
nVars = str(len(varList)) + 'vars'
Note = methods + '_' + varListKey + '_' + nVars + '_mDepth' + mDepth + '_M' + mass
outfname = "weights/TMVA_" + Note + ".root"
# Print methods
mlist = methods.replace(' ', ',').split(',')
print "=== TMVAClassification: use method(s)..."
for m in mlist:
if m.strip() != '':
print "=== - <%s>" % m.strip()
# Import ROOT classes
from ROOT import gSystem, gROOT, gApplication, TFile, TTree, TCut
# check ROOT version, give alarm if 5.18
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( "./" )
# 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" )
factory = TMVA.Factory(
"TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;: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 = "weights/" + Note
# 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" )]
for iVar in varList:
if iVar[0] == 'NJets_singleLepCalc':
factory.AddVariable(iVar[0], iVar[1], iVar[2], 'I')
else:
factory.AddVariable(iVar[0], iVar[1], iVar[2], '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
inputDir = varsList.inputDir
print 'mass point ' + mass
infname = "ChargedHiggs_HplusTB_HplusToTB_M-%s_13TeV_amcatnlo_pythia8_hadd.root" % (
mass)
iFileSig = TFile.Open(inputDir + infname)
sigChain = iFileSig.Get("ljmet")
# os.exits(1)
#BDT machinary
factory.AddSignalTree(sigChain)
bkg_list = []
bkg_trees_list = []
hist_list = []
weightsList = []
for i in range(len(varsList.bkg)):
bkg_list.append(TFile.Open(inputDir + varsList.bkg[i]))
print inputDir + varsList.bkg[i]
bkg_trees_list.append(bkg_list[i].Get("ljmet"))
bkg_trees_list[i].GetEntry(0)
if bkg_trees_list[i].GetEntries() == 0:
continue
factory.AddBackgroundTree(bkg_trees_list[i], 1)
signalWeight = 1 #0.0159/sigChain.GetEntries() #xs (pb)
# ====== register trees ====================================================
# 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");
#factory.SetBackgroundWeightExpression( "weight" )
factory.SetSignalWeightExpression(weightStrS)
factory.SetBackgroundWeightExpression(weightStrB)
# 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(cutStrS)
mycutBkg = TCut(cutStrB)
# 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:nTest_Signal=10:nTest_Background=100:SplitMode=Random:NormMode=NumEvents:!V" )
"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
# bdtSetting for "BDT"
bdtSetting = '!H:!V:NTrees=%s:MaxDepth=%s' % (nTrees, mDepth)
bdtSetting += ':MinNodeSize=2.5%:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20'
bdtSetting += ':IgnoreNegWeightsInTraining=True'
# bdtSetting for "BDTMitFisher"
bdtFSetting = '!H:!V:NTrees=%s' % nTrees
bdtFSetting += ':MinNodeSize=2.5%:UseFisherCuts:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20'
bdtFSetting += ':IgnoreNegWeightsInTraining=True'
# bdtSetting for "BDTG"
bdtGSetting = '!H:!V:NTrees=%s:MaxDepth=%s' % (nTrees, mDepth)
bdtGSetting += ':MinNodeSize=2.5%:BoostType=Grad:Shrinkage=0.10:UseBaggedBoost:BaggedSampleFraction=0.5:nCuts=20'
bdtGSetting += ':Pray' #Pray takes into account the effect of negative bins in BDTG
#bdtGSetting += ':IgnoreNegWeightsInTraining=True'
# bdtSetting for "BDTB"
bdtBSetting = '!H:!V:NTrees=%s' % nTrees
bdtBSetting += ':MinNodeSize=2.5%:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20'
bdtBSetting += ':IgnoreNegWeightsInTraining=True'
# bdtSetting for "BDTD"
bdtDSetting = '!H:!V:NTrees=%s' % nTrees
bdtDSetting += ':MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:SeparationType=GiniIndex:nCuts=20:VarTransform=Decorrelate'
bdtDSetting += ':IgnoreNegWeightsInTraining=True'
#Note also that explicitly setting *nEventsMin* so far OVERWRITES the option recomeded ^[[0m
#BOOKING AN ALGORITHM
if methods == "BDT": factory.BookMethod(TMVA.Types.kBDT, "BDT", bdtSetting)
if methods == "BDTG":
factory.BookMethod(TMVA.Types.kBDT, "BDTG", bdtGSetting)
if methods == "BDTMitFisher":
factory.BookMethod(TMVA.Types.kBDT, "BDTMitFisher", bdtFSetting)
if methods == "BDTB":
factory.BookMethod(TMVA.Types.kBDT, "BDTB", bdtBSetting)
if methods == "BDTD":
factory.BookMethod(TMVA.Types.kBDT, "BDTD", bdtDSetting)
# --------------------------------------------------------------------------------------------------
# ---- 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"
# save plots:
os.chdir('weights/' + Note)
#TMVA.mvaeffs( "../../"+outfname ) #Classifier Cut Efficiencies
gROOT.SetBatch(1)
TMVA.efficiencies(
"../../" + outfname
) #Classifier Background Rejection vs Signal Efficiency (ROC curve)
#TMVA.efficiencies( "weights/TMVA_BDTG_APR9_33vars_mDepth3_MLow.root", 3 ) #Classifier 1/(Backgr. Efficiency) vs Signal Efficiency (ROC curve)
TMVA.mvas("../../" + outfname,
0) #Classifier Output Distributions (test sample)
TMVA.correlations(
"../../" + outfname) #Input Variable Linear Correlation Coefficients
TMVA.variables("../../" + outfname) #Input variables (training sample)
#TMVA.mvas( "../../"+outfname ) #Classifier Output Distributions (test and training samples superimposed)
#gROOT.ProcessLine( ".x ../../mvas.C(\"%s\",3)" % ("../../"+outfname) ) #Classifier Output Distributions (test and training samples superimposed)
if not gROOT.IsBatch(): TMVA.TMVAGui("../../" + outfname)
# os.chdir('plots')
# try: os.system('convert CorrelationMatrixS.eps CorrelationMatrixS_'+Note+'.png')
# except: pass
# try: os.system('convert CorrelationMatrixB.eps CorrelationMatrixB_'+Note+'.png')
# except: pass
# #try: os.system('convert invBeffvsSeff.eps invBeffvsSeff_'+Note+'.png')
# #except: pass
# try: os.system('convert mva_'+Note.split('_')[0]+'.eps mva_'+Note+'.png')
# except: pass
# try: os.system('convert mvaeffs_'+Note.split('_')[0]+'.eps mvaeffs_'+Note+'.png')
# except: pass
# try: os.system('convert overtrain_'+Note.split('_')[0]+'.eps overtrain_'+Note+'.png')
# except: pass
# try: os.system('convert rejBvsS.eps rejBvsS_'+Note+'.png')
# except: pass
# try: os.system('convert variables_id_c1.eps variables_id_c1_'+Note+'.png')
# except: pass
# try: os.system('convert variables_id_c2.eps variables_id_c2_'+Note+'.png')
# except: pass
# try: os.system('convert variables_id_c3.eps variables_id_c3_'+Note+'.png')
# except: pass
# try: os.system('convert variables_id_c4.eps variables_id_c4_'+Note+'.png')
# except: pass
# try: os.system('convert variables_id_c5.eps variables_id_c5_'+Note+'.png')
# except: pass
# try: os.system('convert variables_id_c6.eps variables_id_c6_'+Note+'.png')
# except: pass
# os.system('rm *.eps')
print "DONE"
'BDTD': 0,
'BDTF': 0,
'MLP': 0,
'MLPBFGS': 0,
'MLPBNN': 0,
'CFMlpANN': 0,
'TMlpANN': 0
}
factory = t.Factory(
'vbf_bdt_combined_james_current', outputFile,
'!V:!Silent:Color:DrawProgressBar:Transformations=I;D;G,D:AnalysisType=Classification'
)
factory.Print()
t.gConfig().GetIONames().fWeightFileDir = outputWeightsDir
dataloader = t.DataLoader(".")
dataloader.AddVariable('dijetDEta', 'dijetDEta', 'dijetDEta', 'F')
dataloader.AddVariable('dijetDPhi', 'dijetDPhi', 'dijetDPhi', 'F')
dataloader.AddVariable('llgJJDPhi', 'llgJJDPhi', 'llgJJDPhi', 'F')
dataloader.AddVariable('jPhotonDRMin', 'jPhotonDRMin', 'jPhotonDRMin', 'F')
dataloader.AddVariable('ptt', 'ptt', 'ptt', 'F')
dataloader.AddVariable('jetOnePt', 'jetOnePt', 'jetOnePt', 'F')
dataloader.AddVariable('jetTwoPt', 'jetTwoPt', 'jetTwoPt', 'F')
dataloader.AddVariable('kin_bdt_james', 'kin_bdt_james', 'kin_bdt_james',
'F')
dataloader.AddVariable('vbfPtBalance', 'vbfPtBalance', 'vbfPtBalance', 'F')
dataloader.AddVariable('photonZepp', 'photonZepp', 'photonZepp', 'F')
# trees for training
loader.PrepareTrainingAndTestTree(
mycutSig, mycutBkg,
"nTrain_Signal=" + str(NSIG) +\
":nTrain_Background=" + str(NBKG) +\
":nTest_Signal=" + str(NSIG_TEST) +\
":nTest_Background=" + str(NBKG_TEST) +\
":SplitMode=Random:NormMode=NumEvents:!V"
)
factory = TMVA.Factory(
"Optimization",
'!V:!ROC:!Silent:Color:!DrawProgressBar:Transformations=I;:AnalysisType=Classification'
)
(TMVA.gConfig().GetIONames()).fWeightFileDir = '/weights'
kerasSetting = '!H:!V:VarTransform=G:FilenameModel=' + modelName +\
':SaveBestOnly=true' +\
':NumEpochs=' + str(epochs) +\
':BatchSize=' + str(batchSize) +\
':TriesEarlyStopping=' + str(patience)
factory.BookMethod(loader, TMVA.Types.kPyKeras, "PyKeras", kerasSetting)
factory.TrainAllMethods()
factory.TestAllMethods()
factory.EvaluateAllMethods()
ROC = factory.GetROCIntegral(dataset + "/optimize_" + outf_key, "PyKeras")
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_h2massweight1_prob", "MMC_h2massweight1_prob", "", 'F' ) ##ADDED
# 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()
def main(): # runs the program
checkRootVer() # check that ROOT version is correct
try: # retrieve command line options
shortopts = "d:o:v:w:y:h?" # possible command line options
longopts = [
"dataset=", "option=", "where=", "year=", "verbose", "help",
"usage"
]
opts, args = getopt.getopt(
sys.argv[1:], shortopts,
longopts) # associates command line inputs to variables
except getopt.GetoptError: # output error if command line argument invalid
print("ERROR: unknown options in argument %s" % sys.argv[1:])
usage()
sys.exit(1)
myArgs = np.array(
[ # Stores the command line arguments
['-d', '--dataset', 'dataset', 'dataset'],
['-w', '--where', 'where', 'lpc'], ['-y', '--year', 'year', 2017],
['-o', '--option', 'option', 0],
['-v', '--verbose', 'verbose', True]
],
dtype="object")
for opt, arg in opts:
if opt in myArgs[:, 0]:
index = np.where(
myArgs[:,
0] == opt)[0][0] # np.where returns a tuple of arrays
myArgs[index, 3] = str(
arg) # override the variables with the command line argument
elif opt in myArgs[:, 1]:
index = np.where(myArgs[:, 1] == opt)[0][0]
myArgs[index, 3] = arg
if opt in ("-?", "-h", "--help",
"--usage"): # provides command line help
usage()
sys.exit(0)
# Initialize some containers
bkg_list = []
bkg_trees_list = []
sig_list = []
sig_trees_list = []
# Initialize some variables after reading in arguments
option_index = np.where(myArgs[:, 2] == 'option')[0][0]
dataset_index = np.where(myArgs[:, 2] == 'dataset')[0][0]
verbose_index = np.where(myArgs[:, 2] == 'verbose')[0][0]
where_index = np.where(myArgs[:, 2] == 'where')[0][0]
year_index = np.where(myArgs[:, 2] == 'year')[0][0]
DATASETPATH = myArgs[dataset_index][3]
DATASET = DATASETPATH.split("/")[0]
OPTION = myArgs[option_index][3]
VERBOSE = myArgs[verbose_index][3]
WHERE = myArgs[where_index][3]
YEAR = myArgs[year_index][3]
if WHERE == "lpc":
if YEAR == 2017:
inputDir = varsList.inputDirLPC2017
elif YEAR == 2018:
inputDir = varsList.inputDirLPC2018
else:
if YEAR == 2017:
inputDir = varsList.inputDirBRUX2017
elif YEAR == 2018:
inputDir = varsList.inputDirBRUX2018
if OPTION == "0":
print("Using Option 0: default varList")
varList = varsList.varList["DNN"]
elif OPTION == "1":
print("Using Option 1: selected data from {}".format(DATASETPATH))
varsListHPO = open(DATASETPATH + "/varsListHPO.txt", "r").readlines()
varList = []
START = False
for line in varsListHPO:
if START == True:
varList.append(str(line.strip()))
if "Variable List:" in line:
START = True
numVars = len(varList)
outf_key = str("Keras_" + str(numVars) + "vars")
OUTF_NAME = DATASET + "/weights/TMVA_" + outf_key + ".root"
outputfile = TFile(OUTF_NAME, "RECREATE")
# initialize and set-up TMVA factory
factory = TMVA.Factory(
"Training", outputfile,
"!V:!ROC:Silent:Color:!DrawProgressBar:Transformations=I;:AnalysisType=Classification"
)
factory.SetVerbose(bool(myArgs[verbose_index, 3]))
(TMVA.gConfig().GetIONames()).fWeightFileDir = "weights/" + outf_key
# initialize and set-up TMVA loader
loader = TMVA.DataLoader(DATASET)
if OPTION == "0":
for var in varList:
if var[0] == "NJets_MultiLepCalc":
loader.AddVariable(var[0], var[1], var[2], 'I')
else:
loader.AddVariable(var[0], var[1], var[2], "F")
if OPTION == "1":
for var in varList:
if var == "NJets_MultiLepCalc":
loader.AddVariable(var, "", "", "I")
else:
loader.AddVariable(var, "", "", "F")
# add signal files
if YEAR == 2017:
for i in range(len(varsList.sig2017_2)):
sig_list.append(TFile.Open(inputDir + varsList.sig2017_2[i]))
sig_trees_list.append(sig_list[i].Get("ljmet"))
sig_trees_list[i].GetEntry(0)
loader.AddSignalTree(sig_trees_list[i])
elif YEAR == 2018:
for i in range(len(varsList.sig2018_2)):
sig_list.append(TFile.Open(inputDir + varsList.sig2018_2[i]))
sig_trees_list.append(sig_list[i].Get("ljmet"))
sig_trees_list[i].GetEntry(0)
loader.AddSignalTree(sig_trees_list[i])
# add background files
if YEAR == 2017:
for i in range(len(varsList.bkg2017_2)):
bkg_list.append(TFile.Open(inputDir + varsList.bkg2017_2[i]))
bkg_trees_list.append(bkg_list[i].Get("ljmet"))
bkg_trees_list[i].GetEntry(0)
if bkg_trees_list[i].GetEntries() == 0:
continue
loader.AddBackgroundTree(bkg_trees_list[i])
elif YEAR == 2018:
for i in range(len(varsList.bkg2018_2)):
bkg_list.append(TFile.Open(inputDir + varsList.bkg2018_2[i]))
bkg_trees_list.append(bkg_list[i].Get("ljmet"))
bkg_trees_list[i].GetEntry(0)
if bkg_trees_list[i].GetEntries() == 0:
continue
loader.AddBackgroundTree(bkg_trees_list[i])
loader.SetSignalWeightExpression(weightStrS)
loader.SetBackgroundWeightExpression(weightStrB)
mycutSig = TCut(cutStrS)
mycutBkg = TCut(cutStrB)
loader.PrepareTrainingAndTestTree(
mycutSig, mycutBkg,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V"
)
######################################################
######################################################
###### ######
###### K E R A S D N N ######
###### ######
######################################################
######################################################
HIDDEN = 0
NODES = 0
LRATE = 0.
PATTERN = ""
REGULATOR = ""
ACTIVATION = ""
BATCH_SIZE = 0
# modify this when implementing hyper parameter optimization:
model_name = 'TTTT_' + str(numVars) + 'vars_model.h5'
EPOCHS = 100
PATIENCE = 20
# edit these based on hyper parameter optimization results
if OPTION == "0":
HIDDEN = 3
NODES = 100
LRATE = 0.01
PATTERN = 'static'
REGULATOR = 'none'
ACTIVATION = 'relu'
BATCH_SIZE = 256
if OPTION == "1":
datasetDir = os.listdir(DATASETPATH)
for file in datasetDir:
if "params" in file: optFileName = file
optFile = open(DATASETPATH + "/" + optFileName, "r").readlines()
START = False
for line in optFile:
if START == True:
if "Hidden" in line: HIDDEN = int(line.split(":")[1].strip())
if "Initial" in line: NODES = int(line.split(":")[1].strip())
if "Batch" in line:
BATCH_SIZE = 2**int(line.split(":")[1].strip())
if "Learning" in line:
LRATE = float(line.split(":")[1].strip())
if "Pattern" in line: PATTERN = str(line.split(":")[1].strip())
if "Regulator" in line:
REGULATOR = str(line.split(":")[1].strip())
if "Activation" in line:
ACTIVATION = str(line.split(":")[1].strip())
if "Optimized Parameters:" in line: START = True
kerasSetting = '!H:!V:VarTransform=G:FilenameModel=' + model_name + \
':SaveBestOnly=true' + \
':NumEpochs=' + str(EPOCHS) + \
':BatchSize=' + str(BATCH_SIZE) + \
':TriesEarlyStopping=' + str(PATIENCE)
model = build_model(HIDDEN, NODES, LRATE, REGULATOR, PATTERN, ACTIVATION,
numVars)
model.save(model_name)
model.summary()
factory.BookMethod(loader, TMVA.Types.kPyKeras, 'PyKeras', kerasSetting)
factory.TrainAllMethods()
factory.TestAllMethods()
factory.EvaluateAllMethods()
outputfile.Close()
print("Finished training in " + str(
(time.time() - START_TIME) / 60.0) + " minutes.")
ROC = factory.GetROCIntegral(DATASET, 'PyKeras')
print('ROC value is: {}'.format(ROC))
if OPTION == "1":
varsListHPOtxt = open(DATASETPATH + "varsListHPO.txt", "a")
varsListHPOtxt.write("ROC Value: {}".format(ROC))
import sys
import os
from ROOT import TMVA, TFile, TCut
from config import cfg, variables_iso_only
from os.path import join
import uproot
import root_pandas
TMVA.Tools.Instance()
(TMVA.gConfig().GetVariablePlotting()).fNbinsXOfROCCurve = 400
out_dir_base = join(cfg["out_dir"], cfg['submit_version'])
max_n_per_class = 200000
for idname in cfg["trainings"]:
for training_bin in cfg["trainings"][idname]:
print("Process training pipeline for {0} {1}".format(idname, training_bin))
out_dir = join(out_dir_base, idname, training_bin, "legacy")
if not os.path.exists(out_dir):
os.makedirs(join(out_dir))
feature_cols = cfg["trainings"][idname][training_bin]["variables"]
outfileName = join(out_dir, "TMVA.root")
print("---> Working with OutfileName = " + outfileName);
def main():
try:
# retrive command line options
shortopts = "m:i:n:d:k:l:t:o:s:vh?"
longopts = [
"methods=", "inputfile=", "nTrees=", "maxDepth=", "mass=",
"varListKey=", "inputtrees=", "outputfile=", "seed=", "verbose",
"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)
infname = DEFAULT_INFNAME
treeNameSig = DEFAULT_TREESIG
treeNameBkg = DEFAULT_TREEBKG
outfname = DEFAULT_OUTFNAME
methods = DEFAULT_METHODS
nTrees = DEFAULT_NTREES
mDepth = DEFAULT_MDEPTH
varListKey = DEFAULT_VARLISTKEY
verbose = True
SeedN = DEFAULT_SEED
for o, a in opts:
if o in ("-?", "-h", "--help", "--usage"):
usage()
sys.exit(0)
elif o in ("-m", "--methods"):
methods = a
elif o in ("-d", "--maxDepth"):
mDepth = a
elif o in ("-l", "--varListKey"):
varListKey = a
elif o in ("-i", "--inputfile"):
infname = a
elif o in ("-n", "--nTrees"):
nTrees = a
elif o in ("-o", "--outputfile"):
outfname = 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 ("-s", "--seed"):
SeedN = long(a)
elif o in ("-v", "--verbose"):
verbose = True
varList = varsList.varList[varListKey]
nVars = str(len(varList)) + 'vars'
Note = methods + '_' + varListKey + '_' + nVars + '_mDepth' + mDepth
outfname = "dataset/weights/TMVA_" + Note + ".root"
# Import ROOT classes
from ROOT import gSystem, gROOT, gApplication, TFile, TTree, TCut, TRandom3
# check ROOT version, give alarm if 5.18
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)
# Import TMVA classes from ROOT
from ROOT import TMVA
fClassifier = TMVA.Factory(
"VariableImportance",
"!V:!ROC:!ModelPersistence:Silent:Color:!DrawProgressBar:AnalysisType=Classification"
)
str_xbitset = '{:053b}'.format(SeedN)
seeddl = TMVA.DataLoader(str_xbitset)
bdtSetting = '!H:!V:NTrees=%s:MaxDepth=%s' % (nTrees, mDepth)
bdtSetting += ':MinNodeSize=2.5%:BoostType=AdaBoost:AdaBoostBeta=0.5:UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20'
bdtSetting += ':IgnoreNegWeightsInTraining=True'
index = 52
for iVar in varList:
if (str_xbitset[index] == '1'):
seeddl.AddVariable(iVar[0], iVar[1], iVar[2], 'F')
print iVar[0]
index = index - 1
(TMVA.gConfig().GetIONames()).fWeightFileDir = "weights/" + Note
inputDir = varsList.inputDir
infname = "TTTT_TuneCP5_PSweights_13TeV-amcatnlo-pythia8_hadd.root"
iFileSig = TFile.Open(inputDir + infname)
sigChain = iFileSig.Get("ljmet")
seeddl.AddSignalTree(sigChain)
bkg_list = []
bkg_trees_list = []
bkgList = varsList.bkg
for i in range(len(bkgList)):
bkg_list.append(TFile.Open(inputDir + bkgList[i]))
bkg_trees_list.append(bkg_list[i].Get("ljmet"))
bkg_trees_list[i].GetEntry(0)
if bkg_trees_list[i].GetEntries() == 0:
continue
seeddl.AddBackgroundTree(bkg_trees_list[i], 1)
signalWeight = 1
seeddl.SetSignalWeightExpression(weightStrS)
seeddl.SetBackgroundWeightExpression(weightStrB)
mycutSig = TCut(cutStrS)
mycutBkg = TCut(cutStrB)
seeddl.PrepareTrainingAndTestTree(
mycutSig, mycutBkg,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V"
)
fClassifier.BookMethod(seeddl, TMVA.Types.kBDT, "BDT", bdtSetting)
fClassifier.TrainAllMethods()
fClassifier.TestAllMethods()
fClassifier.EvaluateAllMethods()
SROC = fClassifier.GetROCIntegral(str_xbitset, "BDT")
print "ROC-integral : ", str_xbitset, " ", SROC
print "SEED " + str_xbitset + " DONE"
fClassifier.DeleteAllMethods()
fClassifier.fMethodsMap.clear()
print "=================================================================="
print "=================================================================="
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()
## * Train a BDT with TMVA
##
## \macro_image
## \macro_output
## \macro_code
##
## \author Lailin XU
## Modified from [RegressionKeras.py](https://root.cern/doc/master/RegressionKeras_8py.html) and [TMVARegression.C](https://root.cern/doc/master/TMVARegression_8C.html)
from ROOT import TMVA, TFile, TTree, TCut
from subprocess import call
from os.path import isfile
# Setup TMVA
TMVA.Tools.Instance()
(TMVA.gConfig().GetVariablePlotting()).fMaxNumOfAllowedVariablesForScatterPlots = 5
outfileName = 'TMVA_tutorial_reg_1.root'
output = TFile.Open(outfileName, 'RECREATE')
factory = TMVA.Factory('TMVARegression', output, '!V:!Silent:Color:DrawProgressBar:Transformations=D,G:AnalysisType=Regression')
# Load data
trfile = "SM_ttbar.root"
if not isfile('tmva_reg_example.root'):
call(['curl', '-L', '-O', 'http://root.cern.ch/files/tmva_reg_example.root'])
data = TFile.Open(trfile)
if not data:
print("Error! file not opened", trfile)
trname = "tree"
tree = data.Get(trname)
test_size=0.2,
#train_size=10000,
#test_size=5000,
random_state=0)
# Training
if not args.quiet:
print 'start training ...'
if args.timeit:
start = timer()
output = TFile(args.outdir + 'tmva_output.root', 'recreate')
factory = TMVA.Factory(
'TMVA', output, 'AnalysisType=Classification:'
'!V:Silent:!DrawProgressBar')
dataloader = TMVA.DataLoader("")
TMVA.gConfig().GetIONames().fWeightFileDir = args.outdir + 'weights/'
for v in var:
vtype = 'I' if v in [
'nJet', 'tau0_decaymode', 'tau1_decaymode', 'ntags', 'ntags_loose'
] else 'F'
dataloader.AddVariable(v, vtype)
add_classification_events(dataloader, x_train, y_train, weights=w_train)
add_classification_events(dataloader,
x_test,
y_test,
weights=w_test,
test=True)
norm = 'None'
def main(): # runs the program
try: # retrieve command line options
shortopts = "o:w:y:v:s:h?" # possible command line options
longopts = [
"outputfile=", "where=", "year=", "verbose", "seed=", "help",
"usage"
]
opts, args = getopt.getopt(
sys.argv[1:], shortopts,
longopts) # associates command line inputs to variables
except getopt.GetoptError: # output error if command line argument invalid
print("ERROR: unknown options in argument %s" % sys.argv[1:])
usage()
sys.exit(1)
myArgs = np.array([ # Stores the command line arguments
['-o', '--outputfile', 'outfname', DEFAULT_OUTFNAME],
['-v', '--verbose', 'verbose', True],
['-w', '--where', 'where', "lpc"],
['-y', '--year', 'year', 2017],
['-s', '--seed', 'SeedN', DEFAULT_SEED],
])
for opt, arg in opts:
if opt in myArgs[:, 0]:
index = np.where(
myArgs[:,
0] == opt)[0][0] # np.where returns a tuple of arrays
myArgs[
index,
3] = arg # override the variables with the command line argument
elif opt in myArgs[:, 1]:
index = np.where(myArgs[:, 1] == opt)[0][0]
myArgs[index, 3] = arg
if opt in ("-?", "-h", "--help",
"--usage"): # provides command line help
usage()
sys.exit(0)
# Initialize some variables after reading in arguments
SeedN_index = np.where(myArgs[:, 2] == 'SeedN')[0][0]
outfname_index = np.where(myArgs[:, 2] == 'outfname')[0][0]
verbose_index = np.where(myArgs[:, 2] == 'verbose')[0][0]
where_index = np.where(myArgs[:, 2] == 'where')[0][0]
year_index = np.where(myArgs[:, 2] == 'year')[0][0]
seed = myArgs[SeedN_index, 3]
where = myArgs[where_index, 3]
year = int(myArgs[year_index, 3])
varList = varsList.varList["DNN"]
var_length = len(varList)
str_xbitset = '{:0{}b}'.format(long(myArgs[SeedN_index, 3]), var_length)
nVars = str_xbitset.count('1')
outf_key = "DNN_" + str(nVars) + "vars"
myArgs[outfname_index, 3] = "dataset/weights/TMVA_" + outf_key + ".root"
print("Seed: {}".format(str_xbitset))
outputfile = TFile(myArgs[outfname_index, 3], 'RECREATE')
checkRootVer() # check that ROOT version is correct
######################################################
######################################################
###### ######
###### T M V A ######
###### ######
######################################################
######################################################
# Declare some containers
sig_list = []
sig_trees_list = []
bkg_list = []
bkg_trees_list = []
hist_list = []
weightsList = []
if where == "brux":
if year == 2017:
inputDir = varsList.inputDirBRUX2017
elif year == 2018:
inputDir = varsList.inputDirBRUX2018
else:
inputDir = varsList.inputDirCondor
# Set up TMVA
ROOT.TMVA.Tools.Instance()
ROOT.TMVA.PyMethodBase.PyInitialize()
fClassifier = TMVA.Factory(
'VariableImportance',
'!V:!ROC:Silent:!Color:!DrawProgressBar:Transformations=I;:AnalysisType=Classification'
)
fClassifier.SetVerbose(bool(myArgs[verbose_index, 3]))
loader = TMVA.DataLoader("dataset/" + str_xbitset)
for indx, var in enumerate(varList):
if (str_xbitset[indx] == '1'):
if var[0] == "NJets_MultiLepCalc":
loader.AddVariable(var[0], var[1], var[2], "I")
else:
loader.AddVariable(var[0], var[1], var[2], "F")
# add signals to loader
if year == 2017:
for i in range(len(varsList.sig2017_0)):
sig_list.append(TFile.Open(inputDir + varsList.sig2017_0[i]))
sig_trees_list.append(sig_list[i].Get("ljmet"))
sig_trees_list[i].GetEntry(0)
loader.AddSignalTree(sig_trees_list[i])
elif year == 2018:
for i in range(len(varsList.sig2018_0)):
sig_list.append(TFile.Open(inputDir + varsList.sig2018_0[i]))
sig_trees_list.append(sig_list[i].Get("ljmet"))
sig_trees_list[i].GetEntry(0)
loader.AddSignalTree(sig_trees_list[i])
# add backgrounds to loader
if year == 2017:
for i in range(len(varsList.bkg2017_0)):
bkg_list.append(TFile.Open(inputDir + varsList.bkg2017_0[i]))
bkg_trees_list.append(bkg_list[i].Get("ljmet"))
bkg_trees_list[i].GetEntry(0)
if bkg_trees_list[i].GetEntries() == 0: continue
loader.AddBackgroundTree(bkg_trees_list[i])
elif year == 2018:
for i in range(len(varsList.bkg2018_0)):
bkg_list.append(TFile.Open(inputDir + varsList.bkg2018_0[i]))
bkg_trees_list.append(bkg_list[i].Get("ljmet"))
bkg_trees_list[i].GetEntry(0)
if bkg_trees_list[i].GetEntries() == 0: continue
loader.AddBackgroundTree(bkg_trees_list[i])
# set signal and background weights
loader.SetSignalWeightExpression(weightStrS)
loader.SetBackgroundWeightExpression(weightStrB)
# set cut thresholds for signal and background
mycutSig = TCut(cutStrS)
mycutBkg = TCut(cutStrB)
NSIG = 0
NSIG_TEST = 0
NBKG = 0
NBKG_TEST = 0
loader.PrepareTrainingAndTestTree(
mycutSig, mycutBkg,
"nTrain_Signal=" + str(NSIG) + \
":nTrain_Background=" + str(NBKG) + \
":nTest_Signal=" + str(NSIG_TEST) + \
":nTest_Background=" + str(NBKG_TEST) + \
":SplitMode=Random:NormMode=NumEvents:!V"
)
#####################################################
#####################################################
###### ######
###### K E R A S D N N ######
###### ######
#####################################################
#####################################################
model_name = "TTTT_TMVA_model.h5"
model = Sequential()
model.add(
Dense(100,
input_dim=nVars,
kernel_initializer="glorot_normal",
activation="relu"))
for i in range(2):
model.add(BatchNormalization())
model.add(
Dense(100, kernel_initializer="glorot_normal", activation="relu"))
model.add(Dense(2, activation="sigmoid"))
model.compile(loss="categorical_crossentropy",
optimizer=Adam(),
metrics=["accuracy"])
model.save(model_name)
model.summary()
######################################################
######################################################
###### ######
###### T M V A ######
###### ######
######################################################
######################################################
# Declare some containers
kerasSetting = "!H:!V:VarTransform=G:FilenameModel=" + model_name + \
":NumEpochs=15:BatchSize=512" # the trained model has to be specified in this string
# run the classifier
fClassifier.BookMethod(loader, TMVA.Types.kPyKeras, "PyKeras",
kerasSetting)
(TMVA.gConfig().GetIONames()
).fWeightFileDir = str_xbitset + "/weights/" + outf_key
#print("New weight file directory: {}".format((TMVA.gConfig().GetIONames()).fWeightFileDir))
fClassifier.TrainAllMethods()
fClassifier.TestAllMethods()
fClassifier.EvaluateAllMethods()
SROC = fClassifier.GetROCIntegral("dataset/" + str_xbitset, "PyKeras")
print("ROC-integral: {}".format(SROC))
fClassifier.DeleteAllMethods()
fClassifier.fMethodsMap.clear()
outputfile.Close()
##
## \macro_image
## \macro_output
## \macro_code
##
## \author Lailin XU
## Modified from [ClassificationKeras.py](https://root.cern/doc/master/ClassificationKeras_8py.html) and [TMVAClassification.C](https://root.cern/doc/master/TMVAClassification_8C.html)
from ROOT import TMVA, TFile, TTree, TCut
from subprocess import call
from os.path import isfile
# Setup TMVA
# =======================
TMVA.Tools.Instance()
(TMVA.gConfig().GetVariablePlotting()
).fMaxNumOfAllowedVariablesForScatterPlots = 5
outfileName = 'TMVA_tutorial_cla_1.root'
output = TFile.Open(outfileName, 'RECREATE')
# Create the factory object. Later you can choose the methods whose performance you'd like to investigate. The factory is
# the only TMVA object you have to interact with
#
# The first argument is the base of the name of all the weightfiles in the directory weight/
# The second argument is the output file for the training results
factory = TMVA.Factory(
"TMVAClassification", output,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;D;P;G,D:AnalysisType=Classification"
)
# Load data
def main():
try:
# retrive command line options
shortopts = "a:o:r:vh?"
longopts = ["analysis=","outputfile=", "regression=", "verbose", "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)
_outfname = OUTFNAME
_analysis = ANALYSIS
verbose = False
_regression = REGRESSION
for o, a in opts:
if o in ("-?", "-h", "--help", "--usage"):
usage()
sys.exit(0)
elif o in ("-o", "--outputfile"):
_outfname = a
elif o in ("-a", "--analysis"):
_analysis = a
elif o in ("-r", "--regression"):
_regression = True
elif o in ("-v", "--verbose"):
verbose = True
# Import ROOT classes
from ROOT import gSystem, gROOT, gApplication, TFile, TTree, TCut
# check ROOT version, give alarm if 5.18
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)
# 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
# gConfig().GetIONames()).fWeightFileDir = "myWeightDirectory"
TMVA.gConfig().GetIONames().fWeightFileDir = "weights_" + _analysis
# 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" )]
if _analysis == "Dijet":
if not _regression:
factory.AddVariable("H_mass := H.mass", 'F');
factory.AddVariable("H_pt :=H.pt", 'F');
factory.AddVariable("hJet_pt1 := hJet_pt[0]", 'F')
factory.AddVariable("hJet_pt2 := hJet_pt[1]", 'F')
else:
factory.AddVariable("HCorr_mass := newHiggsMass", 'F');
factory.AddVariable("HCorr_pt := newHiggsPt", 'F');
factory.AddVariable("hJ1Corr_pt := hJet_genPtReg0", 'F');
factory.AddVariable("hJ2Corr_pt := hJet_genPtReg1", 'F');
factory.AddVariable("V_pt :=V.pt", 'F');
factory.AddVariable("H_dR := H.dR", 'F');
factory.AddVariable("hJ12_MaxCsv := max(hJet_csv[0],hJet_csv[1])", 'F');
factory.AddVariable("hJ12_MinCsv := min(hJet_csv[0],hJet_csv[1])", 'F');
factory.AddVariable("HV_dPhi := HVdPhi", 'F');
factory.AddVariable("H_dEta := H.dEta", 'F');
factory.AddVariable("NAddJet:=Sum$(aJet_pt>20 && abs(aJet_eta)<4.5)", 'I' );
factory.AddVariable("dPull := deltaPullAngle", 'F');
# You can add so-called "Spectator variables", which are not used in the MVA training,
# but will appear in the final "TestTree" produced by TMVA. This TestTree will contain the
# input variables, the response values of all trained MVAs, and the spectator variables
#factory.AddSpectator("hJet_pt1 := hJet_pt[0]", 'F');
#factory.AddSpectator("hJet_pt2 := hJet_pt[1]", 'F');
elif _analysis == "Subjet":
if not _regression:
factory.AddVariable("H_mass := FatH.filteredmass", 'F');
factory.AddVariable("H_pt := FatH.filteredpt", 'F');
factory.AddVariable("SJ1_pt := fathFilterJets_pt[0]", 'F');
factory.AddVariable("SJ2_pt := fathFilterJets_pt[1]", 'F');
factory.AddVariable("SJ3_pt := Alt$(fathFilterJets_pt[2],0)", 'F');
else:
factory.AddVariable("HCorr_mass := newfatHiggsMass", 'F');
factory.AddVariable("HCorr_pt := newfatHiggsPt", 'F');
factory.AddVariable("SJ1Corr_pt := fathFilterJets_genPtReg0", 'F');
factory.AddVariable("SJ2Corr_pt := fathFilterJetsx_genPtReg1", 'F');
factory.AddVariable("SJ3_pt := Alt$(fathFilterJets_pt[2],0)", 'F'); #change later
factory.AddVariable("V_pt := V.pt", 'F');
factory.AddVariable("HV_dPhi := " +\
"FatH.filteredphi - V.phi > pi ? " +\
"abs(FatH.filteredphi - V.phi - 2*pi) : " +\
"FatH.filteredphi - V.phi < -pi ? " +\
"abs(FatH.filteredphi - V.phi + 2*pi) : " +\
"abs(FatH.filteredphi - V.phi)", 'F' )
factory.AddVariable("SJ1_csv := fathFilterJets_csv[0]", 'F');
factory.AddVariable("SJ2_csv := fathFilterJets_csv[1]", 'F');
factory.AddVariable("SJ3_csv := Alt$(fathFilterJets_csv[2],0)", 'F');
factory.AddVariable("SJ12_dEta := " +\
"nfathFilterJets < 2 ? 0 : " +\
"fabs(fathFilterJets_eta[0] - fathFilterJets_eta[1] )", 'F');
factory.AddVariable("SJ13_dEta := " +\
"nfathFilterJets < 3 ? 0 : " +\
"abs( fathFilterJets_eta[0] - Alt$(fathFilterJets_eta[2],0))", 'F');
factory.AddVariable("SJ12_dPhi := " +\
"nfathFilterJets < 2 ? 0 : " +\
"fathFilterJets_phi[0] - fathFilterJets_phi[1] > pi ? " +\
"abs( fathFilterJets_phi[0] - fathFilterJets_phi[1] - 2*pi) : " +\
"fathFilterJets_phi[0] - fathFilterJets_phi[1] < -pi ? " +\
"abs( fathFilterJets_phi[0] - fathFilterJets_phi[1] + 2*pi) : " +\
"abs( fathFilterJets_phi[0] - fathFilterJets_phi[1])", 'F');
factory.AddVariable("SJ13_dPhi := " +\
"nfathFilterJets < 3 ? 0 : " +\
"fathFilterJets_phi[0] - Alt$(fathFilterJets_phi[2],0) > pi ? " +\
"abs(fathFilterJets_phi[0] - " +\
"Alt$(fathFilterJets_phi[2],0) - 2*pi) : " +\
"fathFilterJets_phi[0] - Alt$(fathFilterJets_phi[2],0) < -pi ? " +\
"abs(fathFilterJets_phi[0] - " +\
"Alt$(fathFilterJets_phi[2],0) + 2*pi) : " +\
"abs(fathFilterJets_phi[0] - Alt$(fathFilterJets_phi[2],0))", 'F');
factory.AddVariable("SJ12_dR := " +\
"nfathFilterJets < 2 ? 0 : " +\
"deltaR(fathFilterJets_eta[0],fathFilterJets_phi[0],fathFilterJets_eta[1],fathFilterJets_phi[1])", 'F');
factory.AddVariable("SJ13_dR := nfathFilterJets < 3 ? 0 : " +\
"deltaR(fathFilterJets_eta[0],fathFilterJets_phi[0],Alt$(fathFilterJets_eta[2],0),Alt$(fathFilterJets_phi[2],0))", 'F');
factory.AddVariable("NAddJet:= " +\
"nfathFilterJets < 2 ? 0 : " +\
"Sum$(aJet_pt>20 && abs(aJet_eta)<4.5 && deltaR(fathFilterJets_eta[0],fathFilterJets_phi[0],aJet_eta,aJet_phi)>0.3 && deltaR(fathFilterJets_eta[1],fathFilterJets_phi[1],aJet_eta,aJet_phi)>0.3)+Sum$(hJet_pt>20 && abs(hJet_eta)<4.5 && deltaR(fathFilterJets_eta[0],fathFilterJets_phi[0],hJet_eta,hJet_phi)>0.3 && deltaR(fathFilterJets_eta[1],fathFilterJets_phi[1],hJet_eta,hJet_phi)>0.3)", 'I' );
else:
print "Problem specifying analysis. Please choose Dijet or Subjet."
sys.exit(1)
## Get the Signal and Background trees
for Sample in SAMPLES.keys():
SampleInfo=SAMPLES[Sample]
SampleType=SampleInfo[0] # signal or background
infile=os.path.join(INPUTDIR,SampleInfo[1])
xs=SampleInfo[2]
## get number of step 1 events
f=TFile.Open(infile)
h = f.Get("Count")
nEVT=int(h.GetBinContent(1))
wt =xs/(nEVT)
print Sample,": ",infile
print "XS:nEVT:wt: ", xs,nEVT,wt
theTree = f.Get( TREE )
if SampleType == "S":
factory.AddSignalTree ( theTree, wt )
elif SampleType == "B":
factory.AddBackgroundTree( theTree, wt )
else:
print "Trouble extracting SampleType for this sample"
sys.exit(1)
# table10 AN-2011/430
if _analysis == "Dijet":
cutString=\
"Vtype == 0" + " && " +\
"vLepton_pt[0]>20." + " && " +\
"H.HiggsFlag > 0" + " && " +\
"V.mass > 75.0" + " && " +\
"V.mass < 105.0" + " && " +\
"V.pt > 100.0" + " && " +\
"max(hJet_csv[0],hJet_csv[1]) > 0.244" + " && " +\
"min(hJet_csv[0],hJet_csv[1]) > 0.244" + " && "
if not _regression:
cutString += \
"hJet_pt[0] > 20.0" + " && " +\
"hJet_pt[1] > 20.0" + " && " +\
"H.mass > 80.0" + " && " +\
"H.mass < 150.0"
else:
cutString += \
"hJet_genPtReg0 > 20.0" + " && " +\
"hJet_genPtReg0 > 20.0" + " && " +\
"newHiggsMass > 80.0 && newHiggsMass < 150.0"
elif _analysis == "Subjet":
cutString=\
"Vtype == 0" + " && " +\
"vLepton_pt[0]>20." + " && " +\
"FatH.FatHiggsFlag > 0" + " && " +\
"V.mass > 75.0" + " && " +\
"V.mass < 105.0" + " && " +\
"V.pt > 100.0" + " && " +\
"nfathFilterJets >= 2" + " && " +\
"max(fathFilterJets_csv[0],fathFilterJets_csv[1]) > 0.244" + " && " +\
"min(fathFilterJets_csv[0],fathFilterJets_csv[1]) > 0.244" + " && "
if not _regression:
cutString += \
"fathFilterJets_pt[0] > 20.0" + " && " +\
"fathFilterJets_pt[1] > 20.0" + " && " +\
"FatH.filteredmass > 80.0" + " && " +\
"FatH.filteredmass < 150.0"
else:
cutString += \
"fathFilterJets_genPtReg0 > 20.0" + " && " +\
"fathFilterJets_genPtReg0 > 20.0" + " && " +\
"newfatHiggsMass > 80.0 && newfatHiggsMass < 150.0"
else:
print "Problem specifying analysis. Please choose Dijet or Subjet."
sys.exit(1)
print cutString
mycutSig = TCut( cutString )
mycutBkg = TCut( cutString )
# 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
prepareOptions="nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=None:!V"
#prepareOptions="SplitMode=Random:!V"
factory.PrepareTrainingAndTestTree( mycutSig, mycutBkg, prepareOptions)
bdtOptions = \
"!H" + ":" +\
"!V" + ":" +\
"NTrees=850" + ":" +\
"nEventsMin=150" + ":" +\
"MaxDepth=3" + ":" +\
"BoostType=AdaBoost" + ":" +\
"AdaBoostBeta=0.3" + ":" +\
"SeparationType=GiniIndex" + ":" +\
"nCuts=20" + ":" +\
"PruneMethod=NoPruning"
# "PruneMethod=CostComplexity"
#
print bdtOptions
factory.BookMethod( TMVA.Types.kBDT, "BDT", bdtOptions)
# 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"
def TMVAClassification(methods,
sigfname,
bkgfname,
optname,
channel,
trees,
verbose=False): #="DecayTree,DecayTree"
# Print methods
mlist = methods.replace(' ', ',').split(',')
print "=== TMVAClassification: use method(s)..."
for m in mlist:
if m.strip() != '':
print "=== - <%s>" % m.strip()
# Define trees
trees = trees.split(",")
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]
# Print output file and directory
outfname = "TMVA_%s_%s.root" % (channel, optname)
myWeightDirectory = "weights_%s_%s" % (channel, optname)
print "=== TMVAClassification: output will be written to:"
print "=== %s" % outfname
print "=== %s" % myWeightDirectory
# Import ROOT classes
from ROOT import gSystem, gROOT, gApplication, TFile, TTree, TCut
# check ROOT version, give alarm if 5.18
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( "./" )
#gROOT.Macro ( "./tmva/test/TMVAlogon.C" )
#gROOT.LoadMacro ( "./tmva/test/TMVAGui.C" ) ###Is this really necessary??
# Import TMVA classes from ROOT
from ROOT import TMVA
# Setup TMVA
TMVA.Tools.Instance()
# 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:AnalysisType=Classification"
)
# Set verbosity
factory.SetVerbose(verbose)
# Load data
dataloader = TMVA.DataLoader("dataset")
# 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 = myWeightDirectory
# 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" )]
print "*** Training on channel:"
print "*** %s" % channel
print "***"
'''
if channel == "1":
#dataloader.AddVariable( "pplus_ProbNNp", "Prob(p^{+})", "", 'F' );
#dataloader.AddVariable( "Kminus_ProbNNk", "Prob(K^{-})", "", 'F' );
dataloader.AddVariable( "pplus_PT", "P_{T}(p^{+})", "MeV", 'F' );
dataloader.AddVariable( "Kminus_PT", "P_{T}(K^{-})", "MeV", 'F' );
dataloader.AddVariable( "gamma_PT", "P_{T}(#gamma)", "MeV", 'F' );
dataloader.AddVariable( "Lambda_1520_0_PT", "P_{T}(#Lambda(1520))", "MeV", 'F' );
dataloader.AddVariable( "B_PT", "P_{T}(#Lambda_{b})", "MeV", 'F' );
dataloader.AddVariable( "beta:=(-gamma_P+Kminus_P+pplus_P)/(gamma_P+Kminus_P+pplus_P)","#beta", "MeV", 'F' );
dataloader.AddVariable( "MomCons1:=-B_P+gamma_P+Lambda_1520_0_P","P_{tot,1}", "MeV", 'F' );
dataloader.AddVariable( "MomCons2:=-Lambda_1520_0_P+Kminus_P+pplus_P","P_{tot,2}", "MeV", 'F' );
dataloader.AddVariable( "Sum_Kminus_p_eta:=atanh(pplus_PZ/pplus_P)+atanh(Kminus_PZ/Kminus_P)","#eta(K^{-})+#eta(p^{+})","MeV", 'F' );
dataloader.AddVariable( "Diff_Kminus_p_eta:=atanh(Kminus_PZ/Kminus_P)-atanh(pplus_PZ/pplus_P)","#eta(K^{-})-#eta(p^{+})","MeV", 'F' );
dataloader.AddVariable( "pplus_IPCHI2_OWNPV", "#chi^{2}_{IP}(p^{+})", "" , 'F' );
dataloader.AddVariable( "Kminus_IPCHI2_OWNPV", "#chi^{2}_{IP}(K^{-})", "" , 'F' );
dataloader.AddVariable( "B_IPCHI2_OWNPV", "#chi^{2}_{IP}(#Lambda_{b})", "" , 'F' );
#dataloader.AddVariable( "gamma_IPCHI2_OWNPV", "IP #chi^{2}(#gamma)", "" , 'F' );
#dataloader.AddVariable( "Lambda_1520_0_IP_OWNPV", "IP(#Lambda(1520))", "mm", 'F' );
#dataloader.AddVariable( "Lambda_1520_0_IPCHI2_OWNPV", "IP#chi^{2}(#Lambda(1520))", "", 'F' );
dataloader.AddVariable( "Lambda_1520_0_OWNPV_CHI2", "#chi^{2}_{vertex}(#Lambda(1520))", "" , 'F' );
dataloader.AddVariable( "B_OWNPV_CHI2", "#chi^{2}_{vertex}(#Lambda_{b})", "" , 'F' );
dataloader.AddVariable( "B_DIRA_OWNPV", "DIRA(#Lambda_{b})", "" , 'F' );
#dataloader.AddVariable( "Lambda_1520_0_FDCHI2_OWNPV", "FD #chi^{2}(#Lambda(1520))", "", 'F' );
dataloader.AddVariable( "B_FDCHI2_OWNPV", "#chi^{2}_{FD}(#Lambda_{b})", "", 'F' );
'''
if channel == "2":
dataloader.AddVariable("pplus_PT", "P_{T}(p^{+})", "MeV", 'F')
dataloader.AddVariable("Kminus_PT", "P_{T}(K^{-})", "MeV", 'F')
dataloader.AddVariable("gamma_PT", "P_{T}(#gamma)", "MeV", 'F')
dataloader.AddVariable("Lambda_1520_0_PT", "P_{T}(#Lambda*)", "MeV",
'F')
dataloader.AddVariable("B_PT", "P_{T}(#Lambda_{b})", "MeV", 'F')
dataloader.AddVariable(
"beta:=(-gamma_P+Kminus_P+pplus_P)/(gamma_P+Kminus_P+pplus_P)",
"#beta", "", 'F')
#ok
#dataloader.AddVariable( "MomCons1:=-B_P+gamma_P+Lambda_1520_0_P","P_{tot,1}", "MeV", 'F' );#BDT learned Mass check1
dataloader.AddVariable("MomCons2:=-Lambda_1520_0_P+Kminus_P+pplus_P",
"P_{tot,2}", "MeV", 'F')
#ok
#dataloader.AddVariable( "Sum_Kminus_p_eta:=atanh(pplus_PZ/pplus_P)+atanh(Kminus_PZ/Kminus_P)","#eta(K^{-})+#eta(p^{+})","", 'F' );#99correlationL_eta
dataloader.AddVariable(
"Diff_Kminus_p_eta:=atanh(Kminus_PZ/Kminus_P)-atanh(pplus_PZ/pplus_P)",
"#eta(K^{-})-#eta(p^{+})", "", 'F')
dataloader.AddVariable(
"Lambda_1520_0_eta:=atanh(Lambda_1520_0_PZ/Lambda_1520_0_P)",
"#eta(#Lambda*)", "", 'F')
dataloader.AddVariable("gamma_eta:=atanh(gamma_PZ/gamma_P)",
"#eta(#gamma)", "", 'F')
dataloader.AddVariable("pplus_IPCHI2_OWNPV", "#chi^{2}_{IP}(p^{+})",
"", 'F')
#dataloader.AddVariable( "Kminus_IPCHI2_OWNPV", "#chi^{2}_{IP}(K^{-})", "" , 'F' );
dataloader.AddVariable("B_IPCHI2_OWNPV", "#chi^{2}_{IP}(#Lambda_{b})",
"", 'F')
dataloader.AddVariable("Lambda_1520_0_IPCHI2_OWNPV",
"#chi^{2}_{IP}(#Lambda*)", "", 'F')
dataloader.AddVariable("Lambda_1520_0_OWNPV_CHI2",
"#chi^{2}_{vertex}(#Lambda*)", "", 'F')
dataloader.AddVariable("B_OWNPV_CHI2",
"#chi^{2}_{vertex}(#Lambda_{b})", "", 'F')
#dataloader.AddVariable( "B_BMassFit_chi2/B_BMassFit_nDOF", "#chi^{2}_{DTF}/n_{dof}", "" , 'F' );#BDT learned Mass check1
#dataloader.AddVariable( "B_PVFit_chi2/B_PVFit_nDOF", "#chi^{2}_{DTF}/n_{dof}", "" , 'F' );#put it out because array
#dataloader.AddVariable( "B_DIRA_OWNPV", "DIRA(#Lambda_{b})", "" , 'F' ); #not used by BDT
#dataloader.AddVariable( "Lambda_1520_0_DIRA_OWNPV", "DIRA(#Lambda*)", "" , 'F' ); #not used
#dataloader.AddVariable( "Lambda_1520_0_FDCHI2_OWNPV", "FD #chi^{2}(#Lambda*)", "", 'F' ); #not used
#dataloader.AddVariable( "B_FDCHI2_OWNPV", "#chi^{2}_{FD}(#Lambda_{b})", "", 'F' ); #not used
# Add Spectator Variables: not used for Training but written in final TestTree
#dataloader.AddSpectator( "B_M", "M(#Lambda_{b})", "MeV");
#dataloader.AddSpectator( "Lambda_1520_0_M", "M(#Lambda*)", "MeV");
# Read input data
if gSystem.AccessPathName(sigfname) != 0:
print "Can not find %s" % sigfname
if gSystem.AccessPathName(bkgfname) != 0:
print "Can not find %s" % bkgfname
inputSig = TFile.Open(sigfname)
inputBkg = TFile.Open(bkgfname)
# Get the signal and background trees for training
signal = inputSig.Get(treeNameSig)
background = inputBkg.Get(treeNameBkg)
# Global event weights (see below for setting event-wise weights)
signalWeight = 1.0
backgroundWeight = 1.0
# ====== register trees ====================================================
#
# the following method is the prefered one:
# you can add an arbitrary number of signal or background trees
dataloader.AddSignalTree(signal, signalWeight)
dataloader.AddBackgroundTree(background, backgroundWeight)
# To give different trees for training and testing, do as follows:
# dataloader.AddSignalTree( signalTrainingTree, signalTrainWeight, "Training" )
# dataloader.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 : dataloader.SetSignalWeightExpression ("weight1*weight2");
# for background: dataloader.SetBackgroundWeightExpression("weight1*weight2");
#dataloader.SetBackgroundWeightExpression( "weight" )
# 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(
""
) #"pplus_ProbNNp>0.2 && Kminus_ProbNNk>0.2 && B_PT>4000 && Lambda_1520_0_PT>1500 && gamma_PT>3000 && pplus_PT>1000 && B_FDCHI2_OWNPV>100 && pplus_IPCHI2_OWNPV>50 && Kminus_IPCHI2_OWNPV>40")# B_BKGCAT==0 directly applied in root sample
#print(sigfname + str( mycutSig ) + treeNameSig)
mycutBkg = TCut(
"B_M>6120"
) #"pplus_ProbNNp>0.2 && Kminus_ProbNNk>0.2 && B_PT>4000 && Lambda_1520_0_PT>1500 && gamma_PT>3000 && pplus_PT>1000 && B_FDCHI2_OWNPV>100 && pplus_IPCHI2_OWNPV>50 && Kminus_IPCHI2_OWNPV>40 && B_M>6120")#(B_M>6120 || B_M<5120)" )
#print(bkgfname + str( mycutBkg ) + treeNameBkg)
# 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
dataloader.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(
dataloader, TMVA.Types.kCuts, "Cuts",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart")
if "CutsD" in mlist:
factory.BookMethod(
dataloader, TMVA.Types.kCuts, "CutsD",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=Decorrelate"
)
if "CutsPCA" in mlist:
factory.BookMethod(
dataloader, TMVA.Types.kCuts, "CutsPCA",
"!H:!V:FitMethod=MC:EffSel:SampleSize=200000:VarProp=FSmart:VarTransform=PCA"
)
if "CutsGA" in mlist:
factory.BookMethod(
dataloader, TMVA.Types.kCuts, "CutsGA",
"H:!V:FitMethod=GA:CutRangeMin[0]=-10:CutRangeMax[0]=10:VarProp[1]=FMax:EffSel:Steps=30:Cycles=3:PopSize=400:SC_steps=10:SC_rate=5:SC_factor=0.95"
)
if "CutsSA" in mlist:
factory.BookMethod(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(dataloader, TMVA.Types.kHMatrix, "HMatrix", "!H:!V")
# Linear discriminant (same as Fisher discriminant)
if "LD" in mlist:
factory.BookMethod(
dataloader, 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(
dataloader, 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(dataloader, TMVA.Types.kFisher, "FisherG",
"H:!V:VarTransform=Gauss")
# Composite classifier: ensemble (tree) of boosted Fisher classifiers
if "BoostedFisher" in mlist:
factory.BookMethod(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader, 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(
dataloader,
TMVA.Types.kMLP,
"MLP",
#"!H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+3:TestRate=5:!UseRegulator" )#Try
"!H:!V:NeuronType=tanh:VarTransform=N:NCycles=600:HiddenLayers=N+5:TestRate=5:!UseRegulator"
) #Old
if "MLPBFGS" in mlist:
factory.BookMethod(
dataloader, 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(
dataloader, 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(dataloader, 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(
dataloader, 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(dataloader, TMVA.Types.kSVM, "SVM",
"Gamma=0.25:Tol=0.001:VarTransform=Norm")
# Boosted Decision Trees
if "BDTG" in mlist:
factory.BookMethod(
dataloader, TMVA.Types.kBDT, "BDTG",
"!H:!V:NTrees=600:BoostType=Grad:Shrinkage=0.1:UseBaggedGrad:GradBaggingFraction=0.73:SeparationType=GiniIndex:nCuts=15:MaxDepth=2"
) #Settings3
#"!H:!V:NTrees=300:BoostType=Grad:Shrinkage=0.11:UseBaggedGrad:GradBaggingFraction=0.73:SeparationType=GiniIndex:nCuts=17:MaxDepth=4" )#AnaNote
#"!H:!V:NTrees=1000:BoostType=Grad:Shrinkage=0.30:UseBaggedGrad:GradBaggingFraction=0.6:SeparationType=GiniIndex:nCuts=20:NNodesMax=5" )#Old
if "BDT" in mlist:
factory.BookMethod(
dataloader, TMVA.Types.kBDT, "BDT",
"!H:!V:NTrees=850:MinNodeSize=2.5%:MaxDepth=3:BoostType=AdaBoost:AdaBoostBeta=0.5:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning"
)
if "BDTB" in mlist:
factory.BookMethod(
dataloader, TMVA.Types.kBDT, "BDTB",
"!H:!V:NTrees=400:BoostType=Bagging:SeparationType=GiniIndex:nCuts=20:PruneMethod=NoPruning"
)
if "BDTD" in mlist:
factory.BookMethod(
dataloader, 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(
dataloader, 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
print("FLAG 0")
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 not gROOT.IsBatch(): TMVA.TMVAGui(outfname)
def main():
try:
# retrive command line options
shortopts = "m:i:n:d:k:l:t:o:vh?"
longopts = ["methods=", "inputfile=", "nTrees=", "maxDepth=", "mass=", "varListKey=", "inputtrees=", "outputfile=", "verbose", "help", "usage"]
opts, args = getopt.getopt( sys.argv[1:], shortopts, longopts )
except getopt.GetoptError:
print "ERROR: unknown options in argument %s" % sys.argv[1:]
usage()
sys.exit(1)
infname = DEFAULT_INFNAME
treeNameSig = DEFAULT_TREESIG
treeNameBkg = DEFAULT_TREEBKG
outfname = DEFAULT_OUTFNAME
methods = DEFAULT_METHODS
nTrees = DEFAULT_NTREES
mDepth = DEFAULT_MDEPTH
mass = DEFAULT_MASS
varListKey = DEFAULT_VARLISTKEY
verbose = True
for o, a in opts:
if o in ("-?", "-h", "--help", "--usage"):
usage()
sys.exit(0)
elif o in ("-m", "--methods"):
methods = a
elif o in ("-d", "--maxDepth"):
mDepth = a
elif o in ("-k", "--mass"):
mass = a
elif o in ("-l", "--varListKey"):
varListKey = a
elif o in ("-i", "--inputfile"):
infname = a
elif o in ("-n", "--nTrees"):
nTrees = a
elif o in ("-o", "--outputfile"):
outfname = 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
varList = varsList.varList[varListKey]
nVars = str(len(varList))+'vars'
Note=''+methods+'_'+varListKey+'_'+nVars+'_mDepth'+mDepth
outfname = "dataset/weights/TMVA_"+Note+".root"
# Print methods
mlist = methods.replace(' ',',').split(',')
print "=== TMVAClassification: use method(s)..."
for m in mlist:
if m.strip() != '':
print "=== - <%s>" % m.strip()
# Import ROOT classes
# check ROOT version, give alarm if 5.18
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)
# Output file
outputFile = TFile( outfname, 'RECREATE' )
factory = TMVA.Factory( "TMVAClassification", outputFile,
"!V:!Silent:Color:DrawProgressBar:Transformations=I;:AnalysisType=Classification" )
factory.SetVerbose( verbose )
(TMVA.gConfig().GetIONames()).fWeightFileDir = "weights/"+Note
dataloader = TMVA.DataLoader('dataset')
for iVar in varList:
if iVar[0]=='NJets_singleLepCalc': dataloader.AddVariable(iVar[0],iVar[1],iVar[2],'I')
else: dataloader.AddVariable(iVar[0],iVar[1],iVar[2],'F')
inputDir = varsList.inputDir
infname = "TTTT_TuneCP5_PSweights_13TeV-amcatnlo-pythia8_hadd.root"
iFileSig = TFile.Open(inputDir+infname)
sigChain = iFileSig.Get("ljmet")
dataloader.AddSignalTree(sigChain)
bkg_list = []
bkg_trees_list = []
hist_list = []
weightsList = []
for i in range(len(varsList.bkg)):
bkg_list.append(TFile.Open(inputDir+varsList.bkg[i]))
print inputDir+varsList.bkg[i]
bkg_trees_list.append(bkg_list[i].Get("ljmet"))
bkg_trees_list[i].GetEntry(0)
if bkg_trees_list[i].GetEntries() == 0:
continue
dataloader.AddBackgroundTree( bkg_trees_list[i], 1)
signalWeight = 1
dataloader.SetSignalWeightExpression( weightStrS )
dataloader.SetBackgroundWeightExpression( weightStrB )
mycutSig = TCut( cutStrS )
mycutBkg = TCut( cutStrB )
dataloader.PrepareTrainingAndTestTree( mycutSig, mycutBkg, "nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" )
kerasSetting = 'H:!V:VarTransform=G:FilenameModel=model.h5:NumEpochs=10:BatchSize=1028'
model = Sequential()
model.add(Dense(100, activation='relu', input_dim=53))
model.add((Dense(100, activation="relu")))
model.add((Dense(100, activation="relu")))
model.add((Dense(100, activation="relu")))
model.add((Dense(2, activation="sigmoid")))
# Set loss and optimizer
model.compile(loss='categorical_crossentropy', optimizer=Adam(), metrics=['accuracy',])
# Store model to file
model.save('model.h5')
model.summary()
if methods=="Keras": factory.BookMethod(dataloader, TMVA.Types.kPyKeras, "PyKeras",kerasSetting)
factory.TrainAllMethods()
factory.TestAllMethods()
factory.EvaluateAllMethods()
outputFile.Close()
# save plots:
print "DONE"
def TMVARegression():
try:
# retrieve command line options
shortopts = "a:o:vh?"
longopts = ["analysis=","outputfile=", "verbose", "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)
_outfname = OUTFNAME
_analysis = ANALYSIS
verbose = False
for o, a in opts:
if o in ("-?", "-h", "--help", "--usage"):
usage()
sys.exit(0)
elif o in ("-o", "--outputfile"):
_outfname = a
elif o in ("-a", "--analysis"):
_analysis = a
elif o in ("-v", "--verbose"):
verbose = True
# Import TMVA classes from ROOT
from ROOT import TMVA
# Output file
outputFile = TFile( _outfname, 'RECREATE' )
# // Create the factory object. Later you can choose the methods
# // whose performance you'd like to investigate. The factory will
# // then run the performance analysis for you.
# //
# // The first argument is the base of the name of all the
# // weightfiles in the directory weights_Reg/
# //
# // The second argument is the output file for the training results
# // All TMVA output can be suppressed by removing the "!" (not) in
# // front of the "Silent" argument in the option string
factory = TMVA.Factory ("TMVARegression", outputFile,
"!V:!Silent:Color:DrawProgressBar" )
# Set verbosity
factory.SetVerbose( verbose )
TMVA.gConfig().GetIONames().fWeightFileDir = "weights_Reg_8TeV" + "_" + _analysis
if _analysis == "Dijet":
factory.AddVariable("hJet_pt", "hJet_pt", "units", 'F')
factory.AddVariable("hJet_eta", "hJet_eta", "units", 'F')
factory.AddVariable("hJet_phi", "hJet_phi", "units", 'F')
factory.AddVariable("hJet_e", "hJet_e", "units", 'F')
factory.AddVariable("hJet_ptRaw*((hJet_ptRaw+resolutionBias(fabs(hJet_eta))*(hJet_ptRaw-hJet_genPt))/hJet_ptRaw)", "hJet_ptRaw*((hJet_ptRaw+resolutionBias(fabs(hJet_eta))*(hJet_ptRaw-hJet_genPt))/hJet_ptRaw)", "units", 'F')
factory.AddVariable("hJet_Mt:=evalMt(hJet_pt, hJet_eta, hJet_phi, hJet_e)","hJet_Mt", "units", 'F')
factory.AddVariable("hJet_Et:=evalEt(hJet_pt, hJet_eta, hJet_phi, hJet_e)","hJet_Et", "units", 'F')
factory.AddVariable("hJet_ptLeadTrack", "hJet_ptLeadTrack", "units", 'F')
factory.AddVariable("hJet_vtxPt", "hJet_vtxPt", "units", 'F')
factory.AddVariable("hJet_vtx3dL", "hJet_vtx3dL", "units", 'F')
factory.AddVariable("hJet_vtx3deL", "hJet_vtx3deL", "units", 'F')
factory.AddVariable("hJet_vtxMass", "hJet_vtxMass", "units", 'F')
factory.AddVariable("hJet_chf", "hJet_chf", "units", 'F')
factory.AddVariable("hJet_nch", "hJet_nch", "units", 'F')
factory.AddVariable("hJet_nconstituents", "hJet_nconstituents", "units", 'F')
factory.AddVariable("hJet_JECUnc", "hJet_JECUnc", "units", 'F')
factory.AddVariable("rho25", "rho25", "units", 'F')
factory.AddVariable("MET.et", "MET.et", "units", 'F')
factory.AddVariable("METdPhi:=METdeltaPhi(MET.phi, hJet_phi[0], hJet_phi[1])","METdPhi", "units",'F')
#Add the variable carrying the regression target
factory.AddTarget( "hJet_genPt" )
elif _analysis == "Subjet":
factory.AddVariable("fathFilterJets_pt", "fathFilterJets_pt", "units", 'F')
factory.AddVariable("fathFilterJets_eta", "fathFilterJets_eta", "units", 'F')
factory.AddVariable("fathFilterJets_phi", "fathFilterJets_phi", "units", 'F')
factory.AddVariable("fathFilterJets_e", "fathFilterJets_e", "units", 'F')
factory.AddVariable("fathFilterJets_ptRaw*((fathFilterJets_ptRaw+resolutionBias(fabs(fathFilterJets_eta))*(fathFilterJets_ptRaw-fathFilterJets_genPt))/fathFilterJets_ptRaw)", "fathFilterJets_ptRaw*((fathFilterJets_ptRaw+resolutionBias(fabs(fathFilterJets_eta))*(fathFilterJets_ptRaw-fathFilterJets_genPt))/fathFilterJets_ptRaw)", "units", 'F')
factory.AddVariable("fathFilterJets_Mt:=evalMt(fathFilterJets_pt, fathFilterJets_eta, fathFilterJets_phi, fathFilterJets_e)","fathFilterJets_Mt", "units", 'F')
factory.AddVariable("fathFilterJets_Et:=evalEt(fathFilterJets_pt, fathFilterJets_eta, fathFilterJets_phi, fathFilterJets_e)","fathFilterJets_Et", "units", 'F')
factory.AddVariable("fathFilterJets_ptLeadTrack", "fathFilterJets_ptLeadTrack", "units", 'F')
factory.AddVariable("fathFilterJets_vtxPt", "fathFilterJets_vtxPt", "units", 'F')
factory.AddVariable("fathFilterJets_vtx3dL", "fathFilterJets_vtx3dL", "units", 'F')
factory.AddVariable("fathFilterJets_vtx3deL", "fathFilterJets_vtx3deL", "units", 'F')
factory.AddVariable("fathFilterJets_vtxMass", "fathFilterJets_vtxMass", "units", 'F')
factory.AddVariable("fathFilterJets_chf", "fathFilterJets_chf", "units", 'F')
factory.AddVariable("rho25", "rho25", "units", 'F')
factory.AddVariable("MET.et", "MET.et", "units", 'F')
factory.AddVariable("METdPhi:=METdeltaPhi(MET.phi, fathFilterJets_phi[0], fathFilterJets_phi[1])","METdPhi", "units",'F')
factory.AddTarget("fathFilterJets_genPt")
else:
print "Problem specifying analysis. Please choose Dijet or Subjet."
sys.exit(1)
## Get the Signal trees
en7TeV = False
en8TeV = True
regWeight = 1.
chain = TChain("tree")
if en7TeV: #change the ntuple names later!!
chain.Add("Step2_output_May11/WH_125_ForRegression.root")
chain.Add("Step2_output_May11/WH_115_ForRegression.root")
chain.Add("Step2_output_May11/WH_120_ForRegression.root")
chain.Add("Step2_output_May11/WH_130_ForRegression.root")
chain.Add("Step2_output_May11/WH_135_ForRegression.root")
#if en8TeV and _analysis == "Dijet":
# chain.Add("dcache:/pnfs/cms/WAX/11/store/user/lpchbb/apana/Step1V33_Step2_V2/DiJetPt_ZH_ZToLL_HToBB_M-110_8TeV-powheg-herwigpp.root")
if en8TeV:
chain.Add("/uscmst1b_scratch/lpc1/lpctrig/apana/Higgs/Step2/NtupleV34/CMSSW_5_2_5/src/VHbbAnalysis/VHbbDataFormats/bin/Step2/ZH/ZH_110_summer12_33b.root")
chain.Add("/uscmst1b_scratch/lpc1/lpctrig/apana/Higgs/Step2/NtupleV34/CMSSW_5_2_5/src/VHbbAnalysis/VHbbDataFormats/bin/Step2/ZH/ZH_115_summer12_33b.root")
chain.Add("/uscmst1b_scratch/lpc1/lpctrig/apana/Higgs/Step2/NtupleV34/CMSSW_5_2_5/src/VHbbAnalysis/VHbbDataFormats/bin/Step2/ZH/ZH_120_summer12_33b.root")
chain.Add("/uscmst1b_scratch/lpc1/lpctrig/apana/Higgs/Step2/NtupleV34/CMSSW_5_2_5/src/VHbbAnalysis/VHbbDataFormats/bin/Step2/ZH/ZH_125_summer12_33b.root")
chain.Add("/uscmst1b_scratch/lpc1/lpctrig/apana/Higgs/Step2/NtupleV34/CMSSW_5_2_5/src/VHbbAnalysis/VHbbDataFormats/bin/Step2/ZH/ZH_130_summer12_33b.root")
chain.Add("/uscmst1b_scratch/lpc1/lpctrig/apana/Higgs/Step2/NtupleV34/CMSSW_5_2_5/src/VHbbAnalysis/VHbbDataFormats/bin/Step2/ZH/ZH_135_summer12_33b.root")
NEntries = chain.GetEntries()
print "Number of entries on Chain:",NEntries
regTree = chain
factory.AddRegressionTree( regTree, regWeight )
#This would set individual event weights (the variables defined in the
#expression need to exist in the original TTree)
#factory->SetWeightExpression( "var1", "Regression" )
if _analysis == "Dijet":
cutString=\
"(Vtype == 0 || Vtype == 1)" + " && " +\
"hJet_pt[0] > 20.0" + " && " +\
"hJet_pt[1] > 20.0" + " && " +\
"hJet_genPt[0] > 0.0" + " && " +\
"hJet_genPt[1] > 0.0" + " && " +\
"hJet_eta[0] < 2.4" + " && " +\
"hJet_eta[1] < 2.4" + " && " +\
"hJet_id[0] > 0.0" + " && " +\
"hJet_id[1] > 0.0" + " && " +\
"max(hJet_csv[0],hJet_csv[1]) > 0.0" + " && " +\
"min(hJet_csv[0],hJet_csv[1]) > 0.0" + " && " +\
"H.pt > 100"
elif _analysis == "Subjet":
cutString=\
"(Vtype == 0 || Vtype == 1)" + " && " +\
"fathFilterJets_pt[0] > 20.0" + " && " +\
"fathFilterJets_pt[1] > 20.0" + " && " +\
"fathFilterJets_genPt[0] > 0.0" + " && " +\
"fathFilterJets_genPt[1] > 0.0" + " && " +\
"fathFilterJets_eta[0] < 2.4" + " && " +\
"fathFilterJets_eta[1] < 2.4" + " && " +\
"max(fathFilterJets_csv[0],fathFilterJets_csv[1]) > 0.0" + " && " +\
"min(fathFilterJets_csv[0],fathFilterJets_csv[1]) > 0.0" + " && " +\
"FatH.filteredpt > 100"
else:
print "Problem specifying analysis. Please choose Dijet or Subjet."
sys.exit(1)
print cutString
mycut = TCut( cutString )
# tell the factory to use all remaining events in the trees after training for testing. The number is 25% of the events after cuts:
if en7TeV:
factory.PrepareTrainingAndTestTree( mycut, "nTrain_Regression=125000:nTest_Regression=125000:SplitMode=Random:NormMode=NumEvents:!V" )
if en8TeV:
factory.PrepareTrainingAndTestTree( mycut, "nTrain_Regression=111000:nTest_Regression=111000:SplitMode=Random:NormMode=NumEvents:!V" )
#If no numbers of events are given, half of the events in the tree are used
#for training, and the other half for testing:
#factory.PrepareTrainingAndTestTree( mycut, "SplitMode=random:!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
#Boosted Decision Trees
factory.BookMethod( TMVA.Types.kBDT, "BDT",
"!H:!V:NTrees=60:nEventsMin=5:BoostType=AdaBoostR2:SeparationType=RegressionVariance:nCuts=20:PruneMethod=CostComplexity:PruneStrength=30" )
# -------------------------------------------------------------------------------------------
#---- Now you can tell the factory to train, test, and evaluate the MVAs
# Train MVAs using the set of training events
factory.TrainAllMethods()
# ---- Evaluate all MVAs using the set of test events
factory.TestAllMethods()
# ----- Evaluate and compare performance of all configured MVAs
factory.EvaluateAllMethods()
# --------------------------------------------------------------
NEntries = regTree.GetEntries()
print "Number of entries on Tree: ",NEntries
# Save the output
outputFile.Close()
print "==> Wrote root file %s\n" % _outfname
print "==> TMVARegression is done!\n"
