Logo ROOT  

Reference Guide
 
Loading...
Searching...
No Matches
TMVAClassificationCategory.C File Reference
Tutorials » Machine Learning tutorials

Detailed Description

View in nbviewer Open in SWAN
This macro provides examples for the training and testing of the TMVA classifiers in categorisation mode.

  • Project : TMVA - a Root-integrated toolkit for multivariate data analysis
  • Package : TMVA
  • Root Macro: TMVAClassificationCategory

As input data is used a toy-MC sample consisting of four Gaussian-distributed and linearly correlated input variables with category (eta) dependent properties.

For this example, only Fisher and Likelihood are used. Run via: 

root -l TMVAClassificationCategory.C

The output file "TMVACC.root" can be analysed with the use of dedicated macros (simply say: root -l <macro.C>), which can be conveniently invoked through a GUI that will appear at the end of the run of this macro.

#include <cstdlib>
#include <iostream>
#include <map>
#include <string>
#include "TChain.h"
#include "TFile.h"
#include "TTree.h"
#include "TString.h"
#include "TObjString.h"
#include "TSystem.h"
#include "TROOT.h"
#include "TMVA/MethodCategory.h"
#include "TMVA/Factory.h"
#include "TMVA/DataLoader.h"
#include "TMVA/Tools.h"
#include "TMVA/TMVAGui.h"
// two types of category methods are implemented
Bool_t UseOffsetMethod = kTRUE;
void TMVAClassificationCategory()
{
//---------------------------------------------------------------
// Example for usage of different event categories with classifiers
std::cout << std::endl << "==> Start TMVAClassificationCategory" << std::endl;
// This loads the library
TMVA::Tools::Instance();
bool batchMode = false;
// Create a new root output file.
TString outfileName( "TMVACC.root" );
TFile* outputFile = TFile::Open( outfileName, "RECREATE" );
// Create the factory object (see TMVAClassification.C for more information)
std::string factoryOptions( "!V:!Silent:Transformations=I;D;P;G,D" );
if (batchMode) factoryOptions += ":!Color:!DrawProgressBar";
TMVA::Factory *factory = new TMVA::Factory( "TMVAClassificationCategory", outputFile, factoryOptions );
// Create DataLoader
TMVA::DataLoader *dataloader=new TMVA::DataLoader("dataset");
// Define the input variables used for the MVA training
dataloader->AddVariable( "var1", 'F' );
dataloader->AddVariable( "var2", 'F' );
dataloader->AddVariable( "var3", 'F' );
dataloader->AddVariable( "var4", '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
dataloader->AddSpectator( "eta" );
// Load the signal and background event samples from ROOT trees
TFile *input(0);
TString fname = gSystem->GetDirName(__FILE__) + "/data/";
if (gSystem->AccessPathName( fname + "toy_sigbkg_categ_offset.root")) {
// if directory data not found try using tutorials dir
fname = gROOT->GetTutorialDir() + "/machine_learning/data/";
}
if (UseOffsetMethod) fname += "toy_sigbkg_categ_offset.root";
else fname += "toy_sigbkg_categ_varoff.root";
if (!gSystem->AccessPathName( fname )) {
// first we try to find tmva_example.root in the local directory
std::cout << "--- TMVAClassificationCategory: Accessing " << fname << std::endl;
input = TFile::Open( fname );
}
if (!input) {
std::cout << "ERROR: could not open data file: " << fname << std::endl;
exit(1);
}
TTree *signalTree = (TTree*)input->Get("TreeS");
TTree *background = (TTree*)input->Get("TreeB");
// Global event weights per tree (see below for setting event-wise weights)
Double_t signalWeight = 1.0;
Double_t backgroundWeight = 1.0;
// You can add an arbitrary number of signal or background trees
dataloader->AddSignalTree ( signalTree, signalWeight );
dataloader->AddBackgroundTree( background, backgroundWeight );
// Apply additional cuts on the signal and background samples (can be different)
TCut mycuts = ""; // for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
TCut mycutb = ""; // for example: TCut mycutb = "abs(var1)<0.5";
// Tell the factory how to use the training and testing events
dataloader->PrepareTrainingAndTestTree( mycuts, mycutb,
"nTrain_Signal=0:nTrain_Background=0:SplitMode=Random:NormMode=NumEvents:!V" );
// Book MVA methods
// Fisher discriminant
factory->BookMethod( dataloader, TMVA::Types::kFisher, "Fisher", "!H:!V:Fisher" );
// Likelihood
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" );
// Categorised classifier
TMVA::MethodCategory* mcat = 0;
// The variable sets
TString theCat1Vars = "var1:var2:var3:var4";
TString theCat2Vars = (UseOffsetMethod ? "var1:var2:var3:var4" : "var1:var2:var3");
// Fisher with categories
TMVA::MethodBase* fiCat = factory->BookMethod( dataloader, TMVA::Types::kCategory, "FisherCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(fiCat);
mcat->AddMethod( "abs(eta)<=1.3", theCat1Vars, TMVA::Types::kFisher, "Category_Fisher_1","!H:!V:Fisher" );
mcat->AddMethod( "abs(eta)>1.3", theCat2Vars, TMVA::Types::kFisher, "Category_Fisher_2","!H:!V:Fisher" );
// Likelihood with categories
TMVA::MethodBase* liCat = factory->BookMethod( dataloader, TMVA::Types::kCategory, "LikelihoodCat","" );
mcat = dynamic_cast<TMVA::MethodCategory*>(liCat);
mcat->AddMethod( "abs(eta)<=1.3",theCat1Vars, TMVA::Types::kLikelihood,
"Category_Likelihood_1","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
mcat->AddMethod( "abs(eta)>1.3", theCat2Vars, TMVA::Types::kLikelihood,
"Category_Likelihood_2","!H:!V:TransformOutput:PDFInterpol=Spline2:NSmoothSig[0]=20:NSmoothBkg[0]=20:NSmoothBkg[1]=10:NSmooth=1:NAvEvtPerBin=50" );
// 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();
// --------------------------------------------------------------
// Save the output
outputFile->Close();
std::cout << "==> Wrote root file: " << outputFile->GetName() << std::endl;
std::cout << "==> TMVAClassificationCategory is done!" << std::endl;
// Clean up
delete factory;
delete dataloader;
// Launch the GUI for the root macros
if (!gROOT->IsBatch()) TMVA::TMVAGui( outfileName );
}
int main( int argc, char** argv )
{
TMVAClassificationCategory();
return 0;
}
main
int main()
Definition Prototype.cxx:12
Bool_t
bool Bool_t
Definition RtypesCore.h:63
Double_t
double Double_t
Definition RtypesCore.h:59
kTRUE
constexpr Bool_t kTRUE
Definition RtypesCore.h:93
TRangeDynCast
ROOT::Detail::TRangeCast< T, true > TRangeDynCast
TRangeDynCast is an adapter class that allows the typed iteration through a TCollection.
Definition TCollection.h:358
input
Option_t Option_t TPoint TPoint const char GetTextMagnitude GetFillStyle GetLineColor GetLineWidth GetMarkerStyle GetTextAlign GetTextColor GetTextSize void input
Definition TGWin32VirtualXProxy.cxx:142
gROOT
#define gROOT
Definition TROOT.h:414
gSystem
R__EXTERN TSystem * gSystem
Definition TSystem.h:572
TCut
A specialized string object used for TTree selections.
Definition TCut.h:25
TFile
A ROOT file is an on-disk file, usually with extension .root, that stores objects in a file-system-li...
Definition TFile.h:131
TFile::Open
static TFile * Open(const char *name, Option_t *option="", const char *ftitle="", Int_t compress=ROOT::RCompressionSetting::EDefaults::kUseCompiledDefault, Int_t netopt=0)
Create / open a file.
Definition TFile.cxx:4131
TMVA::Factory
This is the main MVA steering class.
Definition Factory.h:80
TMVA::Factory::TrainAllMethods
void TrainAllMethods()
Iterates through all booked methods and calls training.
Definition Factory.cxx:1114
TMVA::Factory::BookMethod
MethodBase * BookMethod(DataLoader *loader, TString theMethodName, TString methodTitle, TString theOption="")
Book a classifier or regression method.
Definition Factory.cxx:352
TMVA::Factory::TestAllMethods
void TestAllMethods()
Evaluates all booked methods on the testing data and adds the output to the Results in the corresponi...
Definition Factory.cxx:1271
TMVA::Factory::EvaluateAllMethods
void EvaluateAllMethods(void)
Iterates over all MVAs that have been booked, and calls their evaluation methods.
Definition Factory.cxx:1376
TMVA::MethodBase
Virtual base Class for all MVA method.
Definition MethodBase.h:111
TMVA::MethodCategory
Class for categorizing the phase space.
Definition MethodCategory.h:58
TMVA::Tools::Instance
static Tools & Instance()
Definition Tools.cxx:71
TMVA::Types::kFisher
@ kFisher
Definition Types.h:82
TMVA::Types::kCategory
@ kCategory
Definition Types.h:97
TMVA::Types::kLikelihood
@ kLikelihood
Definition Types.h:79
TString
Basic string class.
Definition TString.h:139
TSystem::AccessPathName
virtual Bool_t AccessPathName(const char *path, EAccessMode mode=kFileExists)
Returns FALSE if one can access a file using the specified access mode.
Definition TSystem.cxx:1308
TSystem::GetDirName
virtual TString GetDirName(const char *pathname)
Return the directory name in pathname.
Definition TSystem.cxx:1044
TTree
A TTree represents a columnar dataset.
Definition TTree.h:84
TMVA::TMVAGui
void TMVAGui(const char *fName="TMVA.root", TString dataset="")
==> Start TMVAClassificationCategory
--- TMVAClassificationCategory: Accessing /github/home/ROOT-CI/src/tutorials/machine_learning/data/toy_sigbkg_categ_offset.root
<HEADER> DataSetInfo : [dataset] : Added class "Signal"
: Add Tree TreeS of type Signal with 10000 events
<HEADER> DataSetInfo : [dataset] : Added class "Background"
: Add Tree TreeB of type Background with 10000 events
<HEADER> Factory : Booking method: Fisher
:
<HEADER> Factory : Booking method: Likelihood
:
<HEADER> Factory : Booking method: FisherCat
:
: Adding sub-classifier: Fisher::Category_Fisher_1
<HEADER> DataSetInfo : [Category_Fisher_1_dsi] : Added class "Signal"
<HEADER> DataSetInfo : [Category_Fisher_1_dsi] : Added class "Background"
: Adding sub-classifier: Fisher::Category_Fisher_2
<HEADER> DataSetInfo : [Category_Fisher_2_dsi] : Added class "Signal"
<HEADER> DataSetInfo : [Category_Fisher_2_dsi] : Added class "Background"
<HEADER> Factory : Booking method: LikelihoodCat
:
: Adding sub-classifier: Likelihood::Category_Likelihood_1
<HEADER> DataSetInfo : [Category_Likelihood_1_dsi] : Added class "Signal"
<HEADER> DataSetInfo : [Category_Likelihood_1_dsi] : Added class "Background"
: Adding sub-classifier: Likelihood::Category_Likelihood_2
<HEADER> DataSetInfo : [Category_Likelihood_2_dsi] : Added class "Signal"
<HEADER> DataSetInfo : [Category_Likelihood_2_dsi] : Added class "Background"
<HEADER> Factory : Train all methods
: Rebuilding Dataset dataset
: Building event vectors for type 2 Signal
: Dataset[dataset] : create input formulas for tree TreeS
: Building event vectors for type 2 Background
: Dataset[dataset] : create input formulas for tree TreeB
<HEADER> DataSetFactory : [dataset] : Number of events in input trees
:
:
: Number of training and testing events
: ---------------------------------------------------------------------------
: Signal -- training events : 5000
: Signal -- testing events : 5000
: Signal -- training and testing events: 10000
: Background -- training events : 5000
: Background -- testing events : 5000
: Background -- training and testing events: 10000
:
<HEADER> DataSetInfo : Correlation matrix (Signal):
: ----------------------------------------
: var1 var2 var3 var4
: var1: +1.000 +0.383 +0.379 +0.387
: var2: +0.383 +1.000 +0.395 +0.402
: var3: +0.379 +0.395 +1.000 +0.388
: var4: +0.387 +0.402 +0.388 +1.000
: ----------------------------------------
<HEADER> DataSetInfo : Correlation matrix (Background):
: ----------------------------------------
: var1 var2 var3 var4
: var1: +1.000 +0.362 +0.373 +0.393
: var2: +0.362 +1.000 +0.376 +0.377
: var3: +0.373 +0.376 +1.000 +0.374
: var4: +0.393 +0.377 +0.374 +1.000
: ----------------------------------------
<HEADER> DataSetFactory : [dataset] :
:
<HEADER> Factory : Train method: Fisher for Classification
:
<HEADER> Fisher : Results for Fisher coefficients:
: -----------------------
: Variable: Coefficient:
: -----------------------
: var1: -0.056
: var2: -0.015
: var3: +0.098
: var4: +0.215
: (offset): -0.022
: -----------------------
: Elapsed time for training with 10000 events: 0.00193 sec
<HEADER> Fisher : [dataset] : Evaluation of Fisher on training sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.000748 sec
: Creating xml weight file: dataset/weights/TMVAClassificationCategory_Fisher.weights.xml
: Creating standalone class: dataset/weights/TMVAClassificationCategory_Fisher.class.C
<HEADER> Factory : Training finished
:
<HEADER> Factory : Train method: Likelihood for Classification
:
: Filling reference histograms
: Building PDF out of reference histograms
: Elapsed time for training with 10000 events: 0.0386 sec
<HEADER> Likelihood : [dataset] : Evaluation of Likelihood on training sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.00614 sec
: Creating xml weight file: dataset/weights/TMVAClassificationCategory_Likelihood.weights.xml
: Creating standalone class: dataset/weights/TMVAClassificationCategory_Likelihood.class.C
: TMVACC.root:/dataset/Method_Likelihood/Likelihood
<HEADER> Factory : Training finished
:
<HEADER> Factory : Train method: FisherCat for Classification
:
: Train all sub-classifiers for Classification ...
: Rebuilding Dataset Category_Fisher_1_dsi
: Building event vectors for type 2 Signal
: Dataset[Category_Fisher_1_dsi] : create input formulas for tree TreeS
: Building event vectors for type 2 Background
: Dataset[Category_Fisher_1_dsi] : create input formulas for tree TreeB
<HEADER> DataSetFactory : [Category_Fisher_1_dsi] : Number of events in input trees
: Dataset[Category_Fisher_1_dsi] : Signal requirement: "abs(eta)<=1.3"
: Dataset[Category_Fisher_1_dsi] : Signal -- number of events passed: 5123 / sum of weights: 5123
: Dataset[Category_Fisher_1_dsi] : Signal -- efficiency : 0.5123
: Dataset[Category_Fisher_1_dsi] : Background requirement: "abs(eta)<=1.3"
: Dataset[Category_Fisher_1_dsi] : Background -- number of events passed: 5134 / sum of weights: 5134
: Dataset[Category_Fisher_1_dsi] : Background -- efficiency : 0.5134
: Dataset[Category_Fisher_1_dsi] : you have opted for scaling the number of requested training/testing events
: to be scaled by the preselection efficiency
: ( 0 * 0.5123 preselection efficiency)
: Dataset[Category_Fisher_1_dsi] : you have opted for scaling the number of requested training/testing events
: to be scaled by the preselection efficiency
: ( 0 * 0.5134 preselection efficiency)
: Number of training and testing events
: ---------------------------------------------------------------------------
: Signal -- training events : 2561
: Signal -- testing events : 2561
: Signal -- training and testing events: 5122
: Dataset[Category_Fisher_1_dsi] : Signal -- due to the preselection a scaling factor has been applied to the numbers of requested events: 0.5123
: Background -- training events : 2567
: Background -- testing events : 2567
: Background -- training and testing events: 5134
: Dataset[Category_Fisher_1_dsi] : Background -- due to the preselection a scaling factor has been applied to the numbers of requested events: 0.5134
:
<HEADER> DataSetInfo : Correlation matrix (Signal):
: ----------------------------------------
: var1 var2 var3 var4
: var1: +1.000 -0.006 +0.008 -0.021
: var2: -0.006 +1.000 +0.002 +0.011
: var3: +0.008 +0.002 +1.000 -0.003
: var4: -0.021 +0.011 -0.003 +1.000
: ----------------------------------------
<HEADER> DataSetInfo : Correlation matrix (Background):
: ----------------------------------------
: var1 var2 var3 var4
: var1: +1.000 -0.022 -0.027 +0.012
: var2: -0.022 +1.000 -0.013 -0.009
: var3: -0.027 -0.013 +1.000 -0.019
: var4: +0.012 -0.009 -0.019 +1.000
: ----------------------------------------
<HEADER> DataSetFactory : [Category_Fisher_1_dsi] :
:
: Train method: Category_Fisher_1 for Classification
<HEADER> Category_Fisher_1 : Results for Fisher coefficients:
: -----------------------
: Variable: Coefficient:
: -----------------------
: var1: +0.106
: var2: +0.152
: var3: +0.254
: var4: +0.379
: (offset): +0.663
: -----------------------
: Elapsed time for training with 5128 events: 0.00126 sec
<HEADER> Category_Fisher_1 : [Category_Fisher_1_dsi] : Evaluation of Category_Fisher_1 on training sample (5128 events)
: Elapsed time for evaluation of 5128 events: 0.000583 sec
: Training finished
: Rebuilding Dataset Category_Fisher_2_dsi
: Building event vectors for type 2 Signal
: Dataset[Category_Fisher_2_dsi] : create input formulas for tree TreeS
: Building event vectors for type 2 Background
: Dataset[Category_Fisher_2_dsi] : create input formulas for tree TreeB
<HEADER> DataSetFactory : [Category_Fisher_2_dsi] : Number of events in input trees
: Dataset[Category_Fisher_2_dsi] : Signal requirement: "abs(eta)>1.3"
: Dataset[Category_Fisher_2_dsi] : Signal -- number of events passed: 4877 / sum of weights: 4877
: Dataset[Category_Fisher_2_dsi] : Signal -- efficiency : 0.4877
: Dataset[Category_Fisher_2_dsi] : Background requirement: "abs(eta)>1.3"
: Dataset[Category_Fisher_2_dsi] : Background -- number of events passed: 4866 / sum of weights: 4866
: Dataset[Category_Fisher_2_dsi] : Background -- efficiency : 0.4866
: Dataset[Category_Fisher_2_dsi] : you have opted for scaling the number of requested training/testing events
: to be scaled by the preselection efficiency
: ( 0 * 0.4877 preselection efficiency)
: Dataset[Category_Fisher_2_dsi] : you have opted for scaling the number of requested training/testing events
: to be scaled by the preselection efficiency
: ( 0 * 0.4866 preselection efficiency)
: Number of training and testing events
: ---------------------------------------------------------------------------
: Signal -- training events : 2438
: Signal -- testing events : 2438
: Signal -- training and testing events: 4876
: Dataset[Category_Fisher_2_dsi] : Signal -- due to the preselection a scaling factor has been applied to the numbers of requested events: 0.4877
: Background -- training events : 2433
: Background -- testing events : 2433
: Background -- training and testing events: 4866
: Dataset[Category_Fisher_2_dsi] : Background -- due to the preselection a scaling factor has been applied to the numbers of requested events: 0.4866
:
<HEADER> DataSetInfo : Correlation matrix (Signal):
: ----------------------------------------
: var1 var2 var3 var4
: var1: +1.000 +0.006 -0.029 -0.001
: var2: +0.006 +1.000 +0.015 -0.002
: var3: -0.029 +0.015 +1.000 -0.006
: var4: -0.001 -0.002 -0.006 +1.000
: ----------------------------------------
<HEADER> DataSetInfo : Correlation matrix (Background):
: ----------------------------------------
: var1 var2 var3 var4
: var1: +1.000 -0.005 +0.005 +0.012
: var2: -0.005 +1.000 +0.018 +0.029
: var3: +0.005 +0.018 +1.000 -0.001
: var4: +0.012 +0.029 -0.001 +1.000
: ----------------------------------------
<HEADER> DataSetFactory : [Category_Fisher_2_dsi] :
:
: Train method: Category_Fisher_2 for Classification
<HEADER> Category_Fisher_2 : Results for Fisher coefficients:
: -----------------------
: Variable: Coefficient:
: -----------------------
: var1: +0.096
: var2: +0.138
: var3: +0.244
: var4: +0.368
: (offset): -0.722
: -----------------------
: Elapsed time for training with 4871 events: 0.00119 sec
<HEADER> Category_Fisher_2 : [Category_Fisher_2_dsi] : Evaluation of Category_Fisher_2 on training sample (4871 events)
: Elapsed time for evaluation of 4871 events: 0.000562 sec
: Training finished
: Begin ranking of input variables...
<HEADER> Category_Fisher_1 : Ranking result (top variable is best ranked)
: -------------------------------
: Rank : Variable : Discr. power
: -------------------------------
: 1 : var4 : 2.215e-01
: 2 : var3 : 1.132e-01
: 3 : var2 : 4.361e-02
: 4 : var1 : 1.980e-02
: -------------------------------
<HEADER> Category_Fisher_2 : Ranking result (top variable is best ranked)
: -------------------------------
: Rank : Variable : Discr. power
: -------------------------------
: 1 : var4 : 2.181e-01
: 2 : var3 : 1.067e-01
: 3 : var2 : 4.196e-02
: 4 : var1 : 1.785e-02
: -------------------------------
: Elapsed time for training with 10000 events: 0.0303 sec
<HEADER> Category_Fisher_1 : [Category_Fisher_1_dsi] : Evaluation of Category_Fisher_1 on training sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.00221 sec
<HEADER> Category_Fisher_2 : [Category_Fisher_2_dsi] : Evaluation of Category_Fisher_2 on training sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.00125 sec
: Creating xml weight file: dataset/weights/TMVAClassificationCategory_FisherCat.weights.xml
<HEADER> Factory : Training finished
:
<HEADER> Factory : Train method: LikelihoodCat for Classification
:
: Train all sub-classifiers for Classification ...
: Rebuilding Dataset Category_Likelihood_1_dsi
: Building event vectors for type 2 Signal
: Dataset[Category_Likelihood_1_dsi] : create input formulas for tree TreeS
: Building event vectors for type 2 Background
: Dataset[Category_Likelihood_1_dsi] : create input formulas for tree TreeB
<HEADER> DataSetFactory : [Category_Likelihood_1_dsi] : Number of events in input trees
: Dataset[Category_Likelihood_1_dsi] : Signal requirement: "abs(eta)<=1.3"
: Dataset[Category_Likelihood_1_dsi] : Signal -- number of events passed: 5123 / sum of weights: 5123
: Dataset[Category_Likelihood_1_dsi] : Signal -- efficiency : 0.5123
: Dataset[Category_Likelihood_1_dsi] : Background requirement: "abs(eta)<=1.3"
: Dataset[Category_Likelihood_1_dsi] : Background -- number of events passed: 5134 / sum of weights: 5134
: Dataset[Category_Likelihood_1_dsi] : Background -- efficiency : 0.5134
: Dataset[Category_Likelihood_1_dsi] : you have opted for scaling the number of requested training/testing events
: to be scaled by the preselection efficiency
: ( 0 * 0.5123 preselection efficiency)
: Dataset[Category_Likelihood_1_dsi] : you have opted for scaling the number of requested training/testing events
: to be scaled by the preselection efficiency
: ( 0 * 0.5134 preselection efficiency)
: Number of training and testing events
: ---------------------------------------------------------------------------
: Signal -- training events : 2561
: Signal -- testing events : 2561
: Signal -- training and testing events: 5122
: Dataset[Category_Likelihood_1_dsi] : Signal -- due to the preselection a scaling factor has been applied to the numbers of requested events: 0.5123
: Background -- training events : 2567
: Background -- testing events : 2567
: Background -- training and testing events: 5134
: Dataset[Category_Likelihood_1_dsi] : Background -- due to the preselection a scaling factor has been applied to the numbers of requested events: 0.5134
:
<HEADER> DataSetInfo : Correlation matrix (Signal):
: ----------------------------------------
: var1 var2 var3 var4
: var1: +1.000 -0.006 +0.008 -0.021
: var2: -0.006 +1.000 +0.002 +0.011
: var3: +0.008 +0.002 +1.000 -0.003
: var4: -0.021 +0.011 -0.003 +1.000
: ----------------------------------------
<HEADER> DataSetInfo : Correlation matrix (Background):
: ----------------------------------------
: var1 var2 var3 var4
: var1: +1.000 -0.022 -0.027 +0.012
: var2: -0.022 +1.000 -0.013 -0.009
: var3: -0.027 -0.013 +1.000 -0.019
: var4: +0.012 -0.009 -0.019 +1.000
: ----------------------------------------
<HEADER> DataSetFactory : [Category_Likelihood_1_dsi] :
:
: Train method: Category_Likelihood_1 for Classification
: Filling reference histograms
: Building PDF out of reference histograms
: Elapsed time for training with 5128 events: 0.024 sec
<HEADER> Category_Likelihood_1 : [Category_Likelihood_1_dsi] : Evaluation of Category_Likelihood_1 on training sample (5128 events)
: Elapsed time for evaluation of 5128 events: 0.00405 sec
: TMVACC.root:/dataset/Method_Category/LikelihoodCat/Method_Likelihood/Category_Likelihood_1
: Training finished
: Rebuilding Dataset Category_Likelihood_2_dsi
: Building event vectors for type 2 Signal
: Dataset[Category_Likelihood_2_dsi] : create input formulas for tree TreeS
: Building event vectors for type 2 Background
: Dataset[Category_Likelihood_2_dsi] : create input formulas for tree TreeB
<HEADER> DataSetFactory : [Category_Likelihood_2_dsi] : Number of events in input trees
: Dataset[Category_Likelihood_2_dsi] : Signal requirement: "abs(eta)>1.3"
: Dataset[Category_Likelihood_2_dsi] : Signal -- number of events passed: 4877 / sum of weights: 4877
: Dataset[Category_Likelihood_2_dsi] : Signal -- efficiency : 0.4877
: Dataset[Category_Likelihood_2_dsi] : Background requirement: "abs(eta)>1.3"
: Dataset[Category_Likelihood_2_dsi] : Background -- number of events passed: 4866 / sum of weights: 4866
: Dataset[Category_Likelihood_2_dsi] : Background -- efficiency : 0.4866
: Dataset[Category_Likelihood_2_dsi] : you have opted for scaling the number of requested training/testing events
: to be scaled by the preselection efficiency
: ( 0 * 0.4877 preselection efficiency)
: Dataset[Category_Likelihood_2_dsi] : you have opted for scaling the number of requested training/testing events
: to be scaled by the preselection efficiency
: ( 0 * 0.4866 preselection efficiency)
: Number of training and testing events
: ---------------------------------------------------------------------------
: Signal -- training events : 2438
: Signal -- testing events : 2438
: Signal -- training and testing events: 4876
: Dataset[Category_Likelihood_2_dsi] : Signal -- due to the preselection a scaling factor has been applied to the numbers of requested events: 0.4877
: Background -- training events : 2433
: Background -- testing events : 2433
: Background -- training and testing events: 4866
: Dataset[Category_Likelihood_2_dsi] : Background -- due to the preselection a scaling factor has been applied to the numbers of requested events: 0.4866
:
<HEADER> DataSetInfo : Correlation matrix (Signal):
: ----------------------------------------
: var1 var2 var3 var4
: var1: +1.000 +0.006 -0.029 -0.001
: var2: +0.006 +1.000 +0.015 -0.002
: var3: -0.029 +0.015 +1.000 -0.006
: var4: -0.001 -0.002 -0.006 +1.000
: ----------------------------------------
<HEADER> DataSetInfo : Correlation matrix (Background):
: ----------------------------------------
: var1 var2 var3 var4
: var1: +1.000 -0.005 +0.005 +0.012
: var2: -0.005 +1.000 +0.018 +0.029
: var3: +0.005 +0.018 +1.000 -0.001
: var4: +0.012 +0.029 -0.001 +1.000
: ----------------------------------------
<HEADER> DataSetFactory : [Category_Likelihood_2_dsi] :
:
: Train method: Category_Likelihood_2 for Classification
: Filling reference histograms
: Building PDF out of reference histograms
: Elapsed time for training with 4871 events: 0.0229 sec
<HEADER> Category_Likelihood_2 : [Category_Likelihood_2_dsi] : Evaluation of Category_Likelihood_2 on training sample (4871 events)
: Elapsed time for evaluation of 4871 events: 0.00389 sec
: TMVACC.root:/dataset/Method_Category/LikelihoodCat/Method_Likelihood/Category_Likelihood_2
: Training finished
: Begin ranking of input variables...
<HEADER> Category_Likelihood_1 : Ranking result (top variable is best ranked)
: -----------------------------------
: Rank : Variable : Delta Separation
: -----------------------------------
: 1 : var4 : 1.328e-01
: 2 : var3 : 4.844e-02
: 3 : var1 : 1.142e-02
: 4 : var2 : -4.784e-03
: -----------------------------------
<HEADER> Category_Likelihood_2 : Ranking result (top variable is best ranked)
: -----------------------------------
: Rank : Variable : Delta Separation
: -----------------------------------
: 1 : var4 : 1.499e-01
: 2 : var3 : 7.807e-02
: 3 : var1 : 3.084e-02
: 4 : var2 : 2.260e-02
: -----------------------------------
: Elapsed time for training with 10000 events: 0.198 sec
<HEADER> Category_Likelihood_1 : [Category_Likelihood_1_dsi] : Evaluation of Category_Likelihood_1 on training sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.00792 sec
<HEADER> Category_Likelihood_2 : [Category_Likelihood_2_dsi] : Evaluation of Category_Likelihood_2 on training sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.00741 sec
: Creating xml weight file: dataset/weights/TMVAClassificationCategory_LikelihoodCat.weights.xml
<HEADER> Factory : Training finished
:
: Ranking input variables (method specific)...
<HEADER> Fisher : Ranking result (top variable is best ranked)
: -------------------------------
: Rank : Variable : Discr. power
: -------------------------------
: 1 : var4 : 1.447e-01
: 2 : var3 : 7.194e-02
: 3 : var2 : 2.379e-02
: 4 : var1 : 1.174e-02
: -------------------------------
<HEADER> Likelihood : Ranking result (top variable is best ranked)
: -----------------------------------
: Rank : Variable : Delta Separation
: -----------------------------------
: 1 : var4 : 9.878e-02
: 2 : var3 : 5.677e-02
: 3 : var2 : 3.557e-02
: 4 : var1 : 1.915e-02
: -----------------------------------
: No variable ranking supplied by classifier: FisherCat
: No variable ranking supplied by classifier: LikelihoodCat
<HEADER> Factory : === Destroy and recreate all methods via weight files for testing ===
:
: Reading weight file: dataset/weights/TMVAClassificationCategory_Fisher.weights.xml
: Reading weight file: dataset/weights/TMVAClassificationCategory_Likelihood.weights.xml
: Reading weight file: dataset/weights/TMVAClassificationCategory_FisherCat.weights.xml
: Recreating sub-classifiers from XML-file
<HEADER> DataSetInfo : [Category_Fisher_1_dsi] : Added class "Signal"
<HEADER> DataSetInfo : [Category_Fisher_1_dsi] : Added class "Background"
<HEADER> DataSetInfo : [Category_Fisher_2_dsi] : Added class "Signal"
<HEADER> DataSetInfo : [Category_Fisher_2_dsi] : Added class "Background"
: Reading weight file: dataset/weights/TMVAClassificationCategory_LikelihoodCat.weights.xml
: Recreating sub-classifiers from XML-file
<HEADER> DataSetInfo : [Category_Likelihood_1_dsi] : Added class "Signal"
<HEADER> DataSetInfo : [Category_Likelihood_1_dsi] : Added class "Background"
<HEADER> DataSetInfo : [Category_Likelihood_2_dsi] : Added class "Signal"
<HEADER> DataSetInfo : [Category_Likelihood_2_dsi] : Added class "Background"
<HEADER> Factory : Test all methods
<HEADER> Factory : Test method: Fisher for Classification performance
:
<HEADER> Fisher : [dataset] : Evaluation of Fisher on testing sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.00235 sec
<HEADER> Factory : Test method: Likelihood for Classification performance
:
<HEADER> Likelihood : [dataset] : Evaluation of Likelihood on testing sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.00739 sec
<HEADER> Factory : Test method: FisherCat for Classification performance
:
<HEADER> Category_Fisher_1 : [Category_Fisher_1_dsi] : Evaluation of Category_Fisher_1 on testing sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.00127 sec
<HEADER> Category_Fisher_2 : [Category_Fisher_2_dsi] : Evaluation of Category_Fisher_2 on testing sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.000944 sec
<HEADER> Factory : Test method: LikelihoodCat for Classification performance
:
<HEADER> Category_Likelihood_1 : [Category_Likelihood_1_dsi] : Evaluation of Category_Likelihood_1 on testing sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.00677 sec
<HEADER> Category_Likelihood_2 : [Category_Likelihood_2_dsi] : Evaluation of Category_Likelihood_2 on testing sample (10000 events)
: Elapsed time for evaluation of 10000 events: 0.00689 sec
<HEADER> Factory : Evaluate all methods
<HEADER> Factory : Evaluate classifier: Fisher
:
<HEADER> Fisher : [dataset] : Loop over test events and fill histograms with classifier response...
:
<HEADER> TFHandler_Fisher : Variable Mean RMS [ Min Max ]
: -----------------------------------------------------------
: var1: 0.010009 1.2852 [ -5.3119 4.5609 ]
: var2: 0.0034020 1.3067 [ -4.1946 4.6723 ]
: var3: -0.0054637 1.3764 [ -4.5297 4.8202 ]
: var4: 0.13424 1.4680 [ -5.1002 4.9850 ]
: -----------------------------------------------------------
<HEADER> Factory : Evaluate classifier: Likelihood
:
<HEADER> Likelihood : [dataset] : Loop over test events and fill histograms with classifier response...
:
<HEADER> TFHandler_Likelihood : Variable Mean RMS [ Min Max ]
: -----------------------------------------------------------
: var1: 0.010009 1.2852 [ -5.3119 4.5609 ]
: var2: 0.0034020 1.3067 [ -4.1946 4.6723 ]
: var3: -0.0054637 1.3764 [ -4.5297 4.8202 ]
: var4: 0.13424 1.4680 [ -5.1002 4.9850 ]
: -----------------------------------------------------------
<HEADER> Factory : Evaluate classifier: FisherCat
:
<HEADER> FisherCat : [dataset] : Loop over test events and fill histograms with classifier response...
:
<HEADER> TFHandler_FisherCat : Variable Mean RMS [ Min Max ]
: -----------------------------------------------------------
: var1: 0.010009 1.2852 [ -5.3119 4.5609 ]
: var2: 0.0034020 1.3067 [ -4.1946 4.6723 ]
: var3: -0.0054637 1.3764 [ -4.5297 4.8202 ]
: var4: 0.13424 1.4680 [ -5.1002 4.9850 ]
: -----------------------------------------------------------
<HEADER> Factory : Evaluate classifier: LikelihoodCat
:
<HEADER> LikelihoodCat : [dataset] : Loop over test events and fill histograms with classifier response...
:
<HEADER> TFHandler_LikelihoodCat : Variable Mean RMS [ Min Max ]
: -----------------------------------------------------------
: var1: 0.010009 1.2852 [ -5.3119 4.5609 ]
: var2: 0.0034020 1.3067 [ -4.1946 4.6723 ]
: var3: -0.0054637 1.3764 [ -4.5297 4.8202 ]
: var4: 0.13424 1.4680 [ -5.1002 4.9850 ]
: -----------------------------------------------------------
:
: Evaluation results ranked by best signal efficiency and purity (area)
: -------------------------------------------------------------------------------------------------------------------
: DataSet MVA
: Name: Method: ROC-integ
: dataset FisherCat : 0.913
: dataset LikelihoodCat : 0.912
: dataset Fisher : 0.807
: dataset Likelihood : 0.769
: -------------------------------------------------------------------------------------------------------------------
:
: Testing efficiency compared to training efficiency (overtraining check)
: -------------------------------------------------------------------------------------------------------------------
: DataSet MVA Signal efficiency: from test sample (from training sample)
: Name: Method: @B=0.01 @B=0.10 @B=0.30
: -------------------------------------------------------------------------------------------------------------------
: dataset FisherCat : 0.342 (0.362) 0.752 (0.744) 0.916 (0.921)
: dataset LikelihoodCat : 0.345 (0.350) 0.750 (0.744) 0.915 (0.920)
: dataset Fisher : 0.185 (0.178) 0.475 (0.487) 0.746 (0.748)
: dataset Likelihood : 0.212 (0.226) 0.454 (0.455) 0.602 (0.620)
: -------------------------------------------------------------------------------------------------------------------
:
<HEADER> Dataset:dataset : Created tree 'TestTree' with 10000 events
:
<HEADER> Dataset:dataset : Created tree 'TrainTree' with 10000 events
:
<HEADER> Factory : Thank you for using TMVA!
: For citation information, please visit: http://tmva.sf.net/citeTMVA.html
==> Wrote root file: TMVACC.root
==> TMVAClassificationCategory is done!
Author
Andreas Hoecker

Definition in file TMVAClassificationCategory.C.