Logo ROOT   6.18/05
Reference Guide
MethodBase.h
Go to the documentation of this file.
1// @(#)root/tmva $Id$
2// Author: Andreas Hoecker, Peter Speckmayer, Joerg Stelzer, Helge Voss, Kai Voss, Eckhard von Toerne, Jan Therhaag
3
4/**********************************************************************************
5 * Project: TMVA - a Root-integrated toolkit for multivariate data analysis *
6 * Package: TMVA *
7 * Class : MethodBase *
8 * Web : http://tmva.sourceforge.net *
9 * *
10 * Description: *
11 * Virtual base class for all MVA method *
12 * *
13 * Authors (alphabetical): *
14 * Andreas Hoecker <Andreas.Hocker@cern.ch> - CERN, Switzerland *
15 * Peter Speckmayer <peter.speckmayer@cern.ch> - CERN, Switzerland *
16 * Joerg Stelzer <Joerg.Stelzer@cern.ch> - CERN, Switzerland *
17 * Jan Therhaag <Jan.Therhaag@cern.ch> - U of Bonn, Germany *
18 * Eckhard v. Toerne <evt@uni-bonn.de> - U of Bonn, Germany *
19 * Helge Voss <Helge.Voss@cern.ch> - MPI-K Heidelberg, Germany *
20 * Kai Voss <Kai.Voss@cern.ch> - U. of Victoria, Canada *
21 * *
22 * Copyright (c) 2005-2011: *
23 * CERN, Switzerland *
24 * U. of Victoria, Canada *
25 * MPI-K Heidelberg, Germany *
26 * U. of Bonn, Germany *
27 * *
28 * Redistribution and use in source and binary forms, with or without *
29 * modification, are permitted according to the terms listed in LICENSE *
30 * (http://tmva.sourceforge.net/LICENSE) *
31 **********************************************************************************/
32
33#ifndef ROOT_TMVA_MethodBase
34#define ROOT_TMVA_MethodBase
35
36//////////////////////////////////////////////////////////////////////////
37// //
38// MethodBase //
39// //
40// Virtual base class for all TMVA method //
41// //
42//////////////////////////////////////////////////////////////////////////
43
44#include <iosfwd>
45#include <vector>
46#include <map>
47#include "assert.h"
48
49#include "TString.h"
50
51#include "TMVA/IMethod.h"
52#include "TMVA/Configurable.h"
53#include "TMVA/Types.h"
54#include "TMVA/DataSet.h"
55#include "TMVA/Event.h"
57#include <TMVA/Results.h>
58
59#include <TFile.h>
60
61class TGraph;
62class TTree;
63class TDirectory;
64class TSpline;
65class TH1F;
66class TH1D;
67class TMultiGraph;
68
69/*! \class TMVA::IPythonInteractive
70\ingroup TMVA
71
72This class is needed by JsMVA, and it's a helper class for tracking errors during
73the training in Jupyter notebook. It’s only initialized in Jupyter notebook context.
74In initialization we specify some title, and a TGraph will be created for every title.
75We can add new data points easily to all TGraphs. These graphs are added to a
76TMultiGraph, and during an interactive training we get this TMultiGraph object
77and plot it with JsROOT.
78*/
79
80namespace TMVA {
81
82 class Ranking;
83 class PDF;
84 class TSpline1;
85 class MethodCuts;
86 class MethodBoost;
87 class DataSetInfo;
88 namespace Experimental {
89 class Classification;
90 }
91
93 public:
96 void Init(std::vector<TString>& graphTitles);
97 void ClearGraphs();
98 void AddPoint(Double_t x, Double_t y1, Double_t y2);
99 void AddPoint(std::vector<Double_t>& dat);
100 inline TMultiGraph* Get() {return fMultiGraph;}
101 inline bool NotInitialized(){ return fNumGraphs==0;};
102 private:
104 std::vector<TGraph*> fGraphs;
107 };
108
109 class MethodBase : virtual public IMethod, public Configurable {
110
111 friend class CrossValidation;
112 friend class Factory;
113 friend class RootFinder;
114 friend class MethodBoost;
117
118 public:
119
121
122 // default constructor
123 MethodBase( const TString& jobName,
124 Types::EMVA methodType,
125 const TString& methodTitle,
126 DataSetInfo& dsi,
127 const TString& theOption = "" );
128
129 // constructor used for Testing + Application of the MVA, only (no training),
130 // using given weight file
131 MethodBase( Types::EMVA methodType,
132 DataSetInfo& dsi,
133 const TString& weightFile );
134
135 // default destructor
136 virtual ~MethodBase();
137
138 // declaration, processing and checking of configuration options
139 void SetupMethod();
140 void ProcessSetup();
141 virtual void CheckSetup(); // may be overwritten by derived classes
142
143 // ---------- main training and testing methods ------------------------------
144
145 // prepare tree branch with the method's discriminating variable
147
148 // performs classifier training
149 // calls methods Train() implemented by derived classes
150 void TrainMethod();
151
152 // optimize tuning parameters
153 virtual std::map<TString,Double_t> OptimizeTuningParameters(TString fomType="ROCIntegral", TString fitType="FitGA");
154 virtual void SetTuneParameters(std::map<TString,Double_t> tuneParameters);
155
156 virtual void Train() = 0;
157
158 // store and retrieve time used for training
159 void SetTrainTime( Double_t trainTime ) { fTrainTime = trainTime; }
160 Double_t GetTrainTime() const { return fTrainTime; }
161
162 // store and retrieve time used for testing
163 void SetTestTime ( Double_t testTime ) { fTestTime = testTime; }
164 Double_t GetTestTime () const { return fTestTime; }
165
166 // performs classifier testing
167 virtual void TestClassification();
168 virtual Double_t GetKSTrainingVsTest(Char_t SorB, TString opt="X");
169
170 // performs multiclass classifier testing
171 virtual void TestMulticlass();
172
173 // performs regression testing
174 virtual void TestRegression( Double_t& bias, Double_t& biasT,
175 Double_t& dev, Double_t& devT,
176 Double_t& rms, Double_t& rmsT,
177 Double_t& mInf, Double_t& mInfT, // mutual information
178 Double_t& corr,
180
181 // options treatment
182 virtual void Init() = 0;
183 virtual void DeclareOptions() = 0;
184 virtual void ProcessOptions() = 0;
185 virtual void DeclareCompatibilityOptions(); // declaration of past options
186
187 // reset the Method --> As if it was not yet trained, just instantiated
188 // virtual void Reset() = 0;
189 //for the moment, I provide a dummy (that would not work) default, just to make
190 // compilation/running w/o parameter optimisation still possible
191 virtual void Reset(){return;}
192
193 // classifier response:
194 // some methods may return a per-event error estimate
195 // error calculation is skipped if err==0
196 virtual Double_t GetMvaValue( Double_t* errLower = 0, Double_t* errUpper = 0) = 0;
197
198 // signal/background classification response
199 Double_t GetMvaValue( const TMVA::Event* const ev, Double_t* err = 0, Double_t* errUpper = 0 );
200
201 protected:
202 // helper function to set errors to -1
203 void NoErrorCalc(Double_t* const err, Double_t* const errUpper);
204
205 // signal/background classification response for all current set of data
206 virtual std::vector<Double_t> GetMvaValues(Long64_t firstEvt = 0, Long64_t lastEvt = -1, Bool_t logProgress = false);
207
208
209 public:
210 // regression response
211 const std::vector<Float_t>& GetRegressionValues(const TMVA::Event* const ev){
212 fTmpEvent = ev;
213 const std::vector<Float_t>* ptr = &GetRegressionValues();
214 fTmpEvent = 0;
215 return (*ptr);
216 }
217
218 virtual const std::vector<Float_t>& GetRegressionValues() {
219 std::vector<Float_t>* ptr = new std::vector<Float_t>(0);
220 return (*ptr);
221 }
222
223 // multiclass classification response
224 virtual const std::vector<Float_t>& GetMulticlassValues() {
225 std::vector<Float_t>* ptr = new std::vector<Float_t>(0);
226 return (*ptr);
227 }
228
229 // probability of classifier response (mvaval) to be signal (requires "CreateMvaPdf" option set)
230 virtual Double_t GetProba( const Event *ev); // the simple one, automatically calculates the mvaVal and uses the SAME sig/bkg ratio as given in the training sample (typically 50/50 .. (NormMode=EqualNumEvents) but can be different)
231 virtual Double_t GetProba( Double_t mvaVal, Double_t ap_sig );
232
233 // Rarity of classifier response (signal or background (default) is uniform in [0,1])
234 virtual Double_t GetRarity( Double_t mvaVal, Types::ESBType reftype = Types::kBackground ) const;
235
236 // create ranking
237 virtual const Ranking* CreateRanking() = 0;
238
239 // make ROOT-independent C++ class
240 virtual void MakeClass( const TString& classFileName = TString("") ) const;
241
242 // print help message
243 void PrintHelpMessage() const;
244
245 //
246 // streamer methods for training information (creates "weight" files) --------
247 //
248 public:
249 void WriteStateToFile () const;
250 void ReadStateFromFile ();
251
252 protected:
253 // the actual "weights"
254 virtual void AddWeightsXMLTo ( void* parent ) const = 0;
255 virtual void ReadWeightsFromXML ( void* wghtnode ) = 0;
256 virtual void ReadWeightsFromStream( std::istream& ) = 0; // backward compatibility
257 virtual void ReadWeightsFromStream( TFile& ) {} // backward compatibility
258
259 private:
260 friend class MethodCategory;
262 void WriteStateToXML ( void* parent ) const;
263 void ReadStateFromXML ( void* parent );
264 void WriteStateToStream ( std::ostream& tf ) const; // needed for MakeClass
265 void WriteVarsToStream ( std::ostream& tf, const TString& prefix = "" ) const; // needed for MakeClass
266
267
268 public: // these two need to be public, they are used to read in-memory weight-files
269 void ReadStateFromStream ( std::istream& tf ); // backward compatibility
270 void ReadStateFromStream ( TFile& rf ); // backward compatibility
271 void ReadStateFromXMLString( const char* xmlstr ); // for reading from memory
272
273 private:
274 // the variable information
275 void AddVarsXMLTo ( void* parent ) const;
276 void AddSpectatorsXMLTo ( void* parent ) const;
277 void AddTargetsXMLTo ( void* parent ) const;
278 void AddClassesXMLTo ( void* parent ) const;
279 void ReadVariablesFromXML ( void* varnode );
280 void ReadSpectatorsFromXML( void* specnode);
281 void ReadTargetsFromXML ( void* tarnode );
282 void ReadClassesFromXML ( void* clsnode );
283 void ReadVarsFromStream ( std::istream& istr ); // backward compatibility
284
285 public:
286 // ---------------------------------------------------------------------------
287
288 // write evaluation histograms into target file
289 virtual void WriteEvaluationHistosToFile(Types::ETreeType treetype);
290
291 // write classifier-specific monitoring information to target file
292 virtual void WriteMonitoringHistosToFile() const;
293
294 // ---------- public evaluation methods --------------------------------------
295
296 // individual initialization for testing of each method
297 // overload this one for individual initialisation of the testing,
298 // it is then called automatically within the global "TestInit"
299
300 // variables (and private member functions) for the Evaluation:
301 // get the efficiency. It fills a histogram for efficiency/vs/bkg
302 // and returns the one value fo the efficiency demanded for
303 // in the TString argument. (Watch the string format)
304 virtual Double_t GetEfficiency( const TString&, Types::ETreeType, Double_t& err );
305 virtual Double_t GetTrainingEfficiency(const TString& );
306 virtual std::vector<Float_t> GetMulticlassEfficiency( std::vector<std::vector<Float_t> >& purity );
307 virtual std::vector<Float_t> GetMulticlassTrainingEfficiency(std::vector<std::vector<Float_t> >& purity );
309 virtual Double_t GetSignificance() const;
310 virtual Double_t GetROCIntegral(TH1D *histS, TH1D *histB) const;
311 virtual Double_t GetROCIntegral(PDF *pdfS=0, PDF *pdfB=0) const;
312 virtual Double_t GetMaximumSignificance( Double_t SignalEvents, Double_t BackgroundEvents,
313 Double_t& optimal_significance_value ) const;
314 virtual Double_t GetSeparation( TH1*, TH1* ) const;
315 virtual Double_t GetSeparation( PDF* pdfS = 0, PDF* pdfB = 0 ) const;
316
317 virtual void GetRegressionDeviation(UInt_t tgtNum, Types::ETreeType type, Double_t& stddev,Double_t& stddev90Percent ) const;
318 // ---------- public accessors -----------------------------------------------
319
320 // classifier naming (a lot of names ... aren't they ;-)
321 const TString& GetJobName () const { return fJobName; }
322 const TString& GetMethodName () const { return fMethodName; }
325 const char* GetName () const { return fMethodName.Data(); }
326 const TString& GetTestvarName () const { return fTestvar; }
327 const TString GetProbaName () const { return fTestvar + "_Proba"; }
329
330 // build classifier name in Test tree
331 // MVA prefix (e.g., "TMVA_")
332 void SetTestvarName ( const TString & v="" ) { fTestvar = (v=="") ? ("MVA_" + GetMethodName()) : v; }
333
334 // number of input variable used by classifier
335 UInt_t GetNvar() const { return DataInfo().GetNVariables(); }
337 UInt_t GetNTargets() const { return DataInfo().GetNTargets(); };
338
339 // internal names and expressions of input variables
340 const TString& GetInputVar ( Int_t i ) const { return DataInfo().GetVariableInfo(i).GetInternalName(); }
341 const TString& GetInputLabel( Int_t i ) const { return DataInfo().GetVariableInfo(i).GetLabel(); }
342 const char * GetInputTitle( Int_t i ) const { return DataInfo().GetVariableInfo(i).GetTitle(); }
343
344 // normalisation and limit accessors
345 Double_t GetMean( Int_t ivar ) const { return GetTransformationHandler().GetMean(ivar); }
346 Double_t GetRMS ( Int_t ivar ) const { return GetTransformationHandler().GetRMS(ivar); }
347 Double_t GetXmin( Int_t ivar ) const { return GetTransformationHandler().GetMin(ivar); }
348 Double_t GetXmax( Int_t ivar ) const { return GetTransformationHandler().GetMax(ivar); }
349
350 // sets the minimum requirement on the MVA output to declare an event signal-like
353
354 // sets the minimum requirement on the MVA output to declare an event signal-like
357
358 // pointers to ROOT directories
359 TDirectory* BaseDir() const;
360 TDirectory* MethodBaseDir() const;
361 TFile* GetFile() const {return fFile;}
362
363 void SetMethodDir ( TDirectory* methodDir ) { fBaseDir = fMethodBaseDir = methodDir; }
364 void SetBaseDir( TDirectory* methodDir ){ fBaseDir = methodDir; }
365 void SetMethodBaseDir( TDirectory* methodDir ){ fMethodBaseDir = methodDir; }
367
368 //Silent file
369 void SetSilentFile(Bool_t status){fSilentFile=status;}
371
372 //Model Persistence
373 void SetModelPersistence(Bool_t status){fModelPersistence=status;}//added support to create/remove dir here if exits or not
375
376 // the TMVA version can be obtained and checked using
377 // if (GetTrainingTMVAVersionCode()>TMVA_VERSION(3,7,2)) {...}
378 // or
379 // if (GetTrainingROOTVersionCode()>ROOT_VERSION(5,15,5)) {...}
384
386 {
387 if(fTransformationPointer && takeReroutedIfAvailable) return *fTransformationPointer; else return fTransformation;
388 }
389 const TransformationHandler& GetTransformationHandler(Bool_t takeReroutedIfAvailable=true) const
390 {
391 if(fTransformationPointer && takeReroutedIfAvailable) return *fTransformationPointer; else return fTransformation;
392 }
393
394 void RerouteTransformationHandler (TransformationHandler* fTargetTransformation) { fTransformationPointer=fTargetTransformation; }
395
396 // ---------- event accessors ------------------------------------------------
397
398 // returns reference to data set
399 // NOTE: this DataSet is the "original" dataset, i.e. the one seen by ALL Classifiers WITHOUT transformation
400 DataSet* Data() const { return DataInfo().GetDataSet(); }
401 DataSetInfo& DataInfo() const { return fDataSetInfo; }
402
403 mutable const Event* fTmpEvent; //! temporary event when testing on a different DataSet than the own one
404
405 // event reference and update
406 // NOTE: these Event accessors make sure that you get the events transformed according to the
407 // particular classifiers transformation chosen
408 UInt_t GetNEvents () const { return Data()->GetNEvents(); }
409 const Event* GetEvent () const;
410 const Event* GetEvent ( const TMVA::Event* ev ) const;
411 const Event* GetEvent ( Long64_t ievt ) const;
412 const Event* GetEvent ( Long64_t ievt , Types::ETreeType type ) const;
413 const Event* GetTrainingEvent( Long64_t ievt ) const;
414 const Event* GetTestingEvent ( Long64_t ievt ) const;
415 const std::vector<TMVA::Event*>& GetEventCollection( Types::ETreeType type );
416
417 // ---------- public auxiliary methods ---------------------------------------
418
419 // this method is used to decide whether an event is signal- or background-like
420 // the reference cut "xC" is taken to be where
421 // Int_[-oo,xC] { PDF_S(x) dx } = Int_[xC,+oo] { PDF_B(x) dx }
422 virtual Bool_t IsSignalLike();
423 virtual Bool_t IsSignalLike(Double_t mvaVal);
424
425
426 Bool_t HasMVAPdfs() const { return fHasMVAPdfs; }
431
432 // setter method for suppressing writing to XML and writing of standalone classes
433 void DisableWriting(Bool_t setter){ fModelPersistence = setter?kFALSE:kTRUE; }//DEPRECATED
434
435 protected:
436 // helper variables for JsMVA
438 bool fExitFromTraining = false;
440
441 public:
442
443 // initializing IPythonInteractive class (for JsMVA only)
445 if (fInteractive) delete fInteractive;
447 }
448
449 // get training errors (for JsMVA only)
451
452 // stop's the training process (for JsMVA only)
453 inline void ExitFromTraining(){
454 fExitFromTraining = true;
455 }
456
457 // check's if the training ended (for JsMVA only)
458 inline bool TrainingEnded(){
460 delete fInteractive;
461 fInteractive = nullptr;
462 }
463 return fExitFromTraining;
464 }
465
466 // get fIPyMaxIter
467 inline UInt_t GetMaxIter(){ return fIPyMaxIter; }
468
469 // get fIPyCurrentIter
471
472 protected:
473
474 // ---------- protected accessors -------------------------------------------
475
476 //TDirectory* LocalTDir() const { return Data().LocalRootDir(); }
477
478 // weight file name and directory (given by global config variable)
480
481 const TString& GetWeightFileDir() const { return fFileDir; }
482 void SetWeightFileDir( TString fileDir );
483
484 // are input variables normalised ?
485 Bool_t IsNormalised() const { return fNormalise; }
486 void SetNormalised( Bool_t norm ) { fNormalise = norm; }
487
488 // set number of input variables (only used by MethodCuts, could perhaps be removed)
489 // void SetNvar( Int_t n ) { fNvar = n; }
490
491 // verbose and help flags
492 Bool_t Verbose() const { return fVerbose; }
493 Bool_t Help () const { return fHelp; }
494
495 // ---------- protected event and tree accessors -----------------------------
496
497 // names of input variables (if the original names are expressions, they are
498 // transformed into regexps)
499 const TString& GetInternalVarName( Int_t ivar ) const { return (*fInputVars)[ivar]; }
500 const TString& GetOriginalVarName( Int_t ivar ) const { return DataInfo().GetVariableInfo(ivar).GetExpression(); }
501
502 Bool_t HasTrainingTree() const { return Data()->GetNTrainingEvents() != 0; }
503
504 // ---------- protected auxiliary methods ------------------------------------
505
506 protected:
507
508 // make ROOT-independent C++ class for classifier response (classifier-specific implementation)
509 virtual void MakeClassSpecific( std::ostream&, const TString& = "" ) const {}
510
511 // header and auxiliary classes
512 virtual void MakeClassSpecificHeader( std::ostream&, const TString& = "" ) const {}
513
514 // static pointer to this object - required for ROOT finder (to be solved differently)(solved by Omar)
515 //static MethodBase* GetThisBase();
516
517 // some basic statistical analysis
518 void Statistics( Types::ETreeType treeType, const TString& theVarName,
521
522 // if TRUE, write weights only to text files
523 Bool_t TxtWeightsOnly() const { return kTRUE; }
524
525 protected:
526
527 // access to event information that needs method-specific information
528
530
531 private:
532
533 // ---------- private definitions --------------------------------------------
534 // Initialisation
535 void InitBase();
536 void DeclareBaseOptions();
537 void ProcessBaseOptions();
538
539 // used in efficiency computation
542
543 // ---------- private accessors ---------------------------------------------
544
545 // reset required for RootFinder
547
548 // ---------- private auxiliary methods --------------------------------------
549
550 // PDFs for classifier response (required to compute signal probability and Rarity)
551 void CreateMVAPdfs();
552
553 // for root finder
554 //virtual method to find ROOT
555 virtual Double_t GetValueForRoot ( Double_t ); // implementation
556
557 // used for file parsing
558 Bool_t GetLine( std::istream& fin, char * buf );
559
560 // fill test tree with classification or regression results
565
566 private:
567
568 void AddInfoItem( void* gi, const TString& name,
569 const TString& value) const;
570
571 // ========== class members ==================================================
572
573 protected:
574
575 // direct accessors
576 Ranking* fRanking; // pointer to ranking object (created by derived classifiers)
577 std::vector<TString>* fInputVars; // vector of input variables used in MVA
578
579 // histogram binning
580 Int_t fNbins; // number of bins in input variable histograms
581 Int_t fNbinsMVAoutput; // number of bins in MVA output histograms
582 Int_t fNbinsH; // number of bins in evaluation histograms
583
584 Types::EAnalysisType fAnalysisType; // method-mode : true --> regression, false --> classification
585
586 std::vector<Float_t>* fRegressionReturnVal; // holds the return-values for the regression
587 std::vector<Float_t>* fMulticlassReturnVal; // holds the return-values for the multiclass classification
588
589 private:
590
591 // MethodCuts redefines some of the evaluation variables and histograms -> must access private members
592 friend class MethodCuts;
593
594
595 // data sets
596 DataSetInfo& fDataSetInfo; //! the data set information (sometimes needed)
597
598 Double_t fSignalReferenceCut; // minimum requirement on the MVA output to declare an event signal-like
599 Double_t fSignalReferenceCutOrientation; // minimum requirement on the MVA output to declare an event signal-like
600 Types::ESBType fVariableTransformType; // this is the event type (sig or bgd) assumed for variable transform
601
602 // naming and versioning
603 TString fJobName; // name of job -> user defined, appears in weight files
604 TString fMethodName; // name of the method (set in derived class)
605 Types::EMVA fMethodType; // type of method (set in derived class)
606 TString fTestvar; // variable used in evaluation, etc (mostly the MVA)
607 UInt_t fTMVATrainingVersion; // TMVA version used for training
608 UInt_t fROOTTrainingVersion; // ROOT version used for training
609 Bool_t fConstructedFromWeightFile; // is it obtained from weight file?
610
611 // Directory structure: dataloader/fMethodBaseDir/fBaseDir
612 // where the first directory name is defined by the method type
613 // and the second is user supplied (the title given in Factory::BookMethod())
614 TDirectory* fBaseDir; // base directory for the instance, needed to know where to jump back from localDir
615 mutable TDirectory* fMethodBaseDir; // base directory for the method
616 //this will be the next way to save results
618
619 //SilentFile
621 //Model Persistence
623
624 TString fParentDir; // method parent name, like booster name
625
626 TString fFileDir; // unix sub-directory for weight files (default: DataLoader's Name + "weights")
627 TString fWeightFile; // weight file name
628
629 private:
630
631 TH1* fEffS; // efficiency histogram for rootfinder
632
633 PDF* fDefaultPDF; // default PDF definitions
634 PDF* fMVAPdfS; // signal MVA PDF
635 PDF* fMVAPdfB; // background MVA PDF
636
637 // TH1D* fmvaS; // PDFs of MVA distribution (signal)
638 // TH1D* fmvaB; // PDFs of MVA distribution (background)
639 PDF* fSplS; // PDFs of MVA distribution (signal)
640 PDF* fSplB; // PDFs of MVA distribution (background)
641 TSpline* fSpleffBvsS; // splines for signal eff. versus background eff.
642
643 PDF* fSplTrainS; // PDFs of training MVA distribution (signal)
644 PDF* fSplTrainB; // PDFs of training MVA distribution (background)
645 TSpline* fSplTrainEffBvsS; // splines for training signal eff. versus background eff.
646
647 private:
648
649 // basic statistics quantities of MVA
650 Double_t fMeanS; // mean (signal)
651 Double_t fMeanB; // mean (background)
652 Double_t fRmsS; // RMS (signal)
653 Double_t fRmsB; // RMS (background)
654 Double_t fXmin; // minimum (signal and background)
655 Double_t fXmax; // maximum (signal and background)
656
657 // variable preprocessing
658 TString fVarTransformString; // labels variable transform method
659
660 TransformationHandler* fTransformationPointer; // pointer to the rest of transformations
661 TransformationHandler fTransformation; // the list of transformations
662
663
664 // help and verbosity
665 Bool_t fVerbose; // verbose flag
666 TString fVerbosityLevelString; // verbosity level (user input string)
667 EMsgType fVerbosityLevel; // verbosity level
668 Bool_t fHelp; // help flag
669 Bool_t fHasMVAPdfs; // MVA Pdfs are created for this classifier
670
671 Bool_t fIgnoreNegWeightsInTraining;// If true, events with negative weights are not used in training
672
673 protected:
674
676
677 // for signal/background
678 UInt_t fSignalClass; // index of the Signal-class
679 UInt_t fBackgroundClass; // index of the Background-class
680
681 private:
682
683 // timing variables
684 Double_t fTrainTime; // for timing measurements
685 Double_t fTestTime; // for timing measurements
686
687 // orientation of cut: depends on signal and background mean values
688 ECutOrientation fCutOrientation; // +1 if Sig>Bkg, -1 otherwise
689
690 // for root finder
691 TSpline1* fSplRefS; // helper splines for RootFinder (signal)
692 TSpline1* fSplRefB; // helper splines for RootFinder (background)
693
694 TSpline1* fSplTrainRefS; // helper splines for RootFinder (signal)
695 TSpline1* fSplTrainRefB; // helper splines for RootFinder (background)
696
697 mutable std::vector<const std::vector<TMVA::Event*>*> fEventCollections; // if the method needs the complete event-collection, the transformed event coll. ist stored here.
698
699 public:
700 Bool_t fSetupCompleted; // is method setup
701
702 private:
703
704 // This is a workaround for OSx where static thread_local data members are
705 // not supported. The C++ solution would indeed be the following:
706// static MethodBase*& GetThisBaseThreadLocal() {TTHREAD_TLS(MethodBase*) fgThisBase(nullptr); return fgThisBase; };
707
708 // ===== depreciated options, kept for backward compatibility =====
709 private:
710
711 Bool_t fNormalise; // normalise input variables
712 Bool_t fUseDecorr; // synonymous for decorrelation
713 TString fVariableTransformTypeString; // labels variable transform type
714 Bool_t fTxtWeightsOnly; // if TRUE, write weights only to text files
715 Int_t fNbinsMVAPdf; // number of bins used in histogram that creates PDF
716 Int_t fNsmoothMVAPdf; // number of times a histogram is smoothed before creating the PDF
717
718 protected:
720 ClassDef(MethodBase,0); // Virtual base class for all TMVA method
721
722 };
723} // namespace TMVA
724
725
726
727
728
729
730
731// ========== INLINE FUNCTIONS =========================================================
732
733
734//_______________________________________________________________________
735inline const TMVA::Event* TMVA::MethodBase::GetEvent( const TMVA::Event* ev ) const
736{
738}
739
741{
742 if(fTmpEvent)
743 return GetTransformationHandler().Transform(fTmpEvent);
744 else
745 return GetTransformationHandler().Transform(Data()->GetEvent());
746}
747
749{
750 assert(fTmpEvent==0);
751 return GetTransformationHandler().Transform(Data()->GetEvent(ievt));
752}
753
755{
756 assert(fTmpEvent==0);
757 return GetTransformationHandler().Transform(Data()->GetEvent(ievt, type));
758}
759
761{
762 assert(fTmpEvent==0);
763 return GetEvent(ievt, Types::kTraining);
764}
765
767{
768 assert(fTmpEvent==0);
769 return GetEvent(ievt, Types::kTesting);
770}
771
772#endif
SVector< double, 2 > v
Definition: Dict.h:5
int Int_t
Definition: RtypesCore.h:41
char Char_t
Definition: RtypesCore.h:29
unsigned int UInt_t
Definition: RtypesCore.h:42
const Bool_t kFALSE
Definition: RtypesCore.h:88
bool Bool_t
Definition: RtypesCore.h:59
double Double_t
Definition: RtypesCore.h:55
long long Long64_t
Definition: RtypesCore.h:69
const Bool_t kTRUE
Definition: RtypesCore.h:87
#define ClassDef(name, id)
Definition: Rtypes.h:326
char name[80]
Definition: TGX11.cxx:109
int type
Definition: TGX11.cxx:120
Describe directory structure in memory.
Definition: TDirectory.h:34
A ROOT file is a suite of consecutive data records (TKey instances) with a well defined format.
Definition: TFile.h:48
A Graph is a graphics object made of two arrays X and Y with npoints each.
Definition: TGraph.h:41
1-D histogram with a double per channel (see TH1 documentation)}
Definition: TH1.h:614
1-D histogram with a float per channel (see TH1 documentation)}
Definition: TH1.h:571
The TH1 histogram class.
Definition: TH1.h:56
Class to perform two class classification.
Class to perform cross validation, splitting the dataloader into folds.
Class that contains all the data information.
Definition: DataSetInfo.h:60
UInt_t GetNVariables() const
Definition: DataSetInfo.h:110
UInt_t GetNTargets() const
Definition: DataSetInfo.h:111
DataSet * GetDataSet() const
returns data set
VariableInfo & GetVariableInfo(Int_t i)
Definition: DataSetInfo.h:96
Class that contains all the data information.
Definition: DataSet.h:69
Long64_t GetNEvents(Types::ETreeType type=Types::kMaxTreeType) const
Definition: DataSet.h:217
Long64_t GetNTrainingEvents() const
Definition: DataSet.h:79
This is the main MVA steering class.
Definition: Factory.h:81
Interface for all concrete MVA method implementations.
Definition: IMethod.h:54
This class is needed by JsMVA, and it's a helper class for tracking errors during the training in Jup...
Definition: MethodBase.h:92
void Init(std::vector< TString > &graphTitles)
This function gets some title and it creates a TGraph for every title.
Definition: MethodBase.cxx:174
IPythonInteractive()
standard constructor
Definition: MethodBase.cxx:151
TMultiGraph * fMultiGraph
Definition: MethodBase.h:101
std::vector< TGraph * > fGraphs
Definition: MethodBase.h:104
~IPythonInteractive()
standard destructor
Definition: MethodBase.cxx:159
TMultiGraph * Get()
Definition: MethodBase.h:100
void ClearGraphs()
This function sets the point number to 0 for all graphs.
Definition: MethodBase.cxx:198
void AddPoint(Double_t x, Double_t y1, Double_t y2)
This function is used only in 2 TGraph case, and it will add new data points to graphs.
Definition: MethodBase.cxx:212
Virtual base Class for all MVA method.
Definition: MethodBase.h:109
TransformationHandler * fTransformationPointer
Definition: MethodBase.h:660
virtual void MakeClassSpecificHeader(std::ostream &, const TString &="") const
Definition: MethodBase.h:512
TString fVerbosityLevelString
Definition: MethodBase.h:666
TDirectory * MethodBaseDir() const
returns the ROOT directory where all instances of the corresponding MVA method are stored
virtual const std::vector< Float_t > & GetRegressionValues()
Definition: MethodBase.h:218
const std::vector< Float_t > & GetRegressionValues(const TMVA::Event *const ev)
Definition: MethodBase.h:211
virtual void Train()=0
virtual Double_t GetKSTrainingVsTest(Char_t SorB, TString opt="X")
MethodBase(const TString &jobName, Types::EMVA methodType, const TString &methodTitle, DataSetInfo &dsi, const TString &theOption="")
standard constructor
Definition: MethodBase.cxx:242
TString fMethodName
Definition: MethodBase.h:604
TFile * GetFile() const
Definition: MethodBase.h:361
virtual Double_t GetSeparation(TH1 *, TH1 *) const
compute "separation" defined as
TString fFileDir
Definition: MethodBase.h:626
Bool_t HasTrainingTree() const
Definition: MethodBase.h:502
virtual void DeclareOptions()=0
void SetSilentFile(Bool_t status)
Definition: MethodBase.h:369
void ReadClassesFromXML(void *clsnode)
read number of classes from XML
TMultiGraph * GetInteractiveTrainingError()
Definition: MethodBase.h:450
void SetWeightFileDir(TString fileDir)
set directory of weight file
void WriteStateToXML(void *parent) const
general method used in writing the header of the weight files where the used variables,...
Bool_t fSilentFile
Definition: MethodBase.h:620
void DeclareBaseOptions()
define the options (their key words) that can be set in the option string here the options valid for ...
Definition: MethodBase.cxx:514
UInt_t GetMaxIter()
Definition: MethodBase.h:467
Double_t fRmsB
Definition: MethodBase.h:653
Double_t GetXmin(Int_t ivar) const
Definition: MethodBase.h:347
Bool_t Verbose() const
Definition: MethodBase.h:492
virtual void TestRegression(Double_t &bias, Double_t &biasT, Double_t &dev, Double_t &devT, Double_t &rms, Double_t &rmsT, Double_t &mInf, Double_t &mInfT, Double_t &corr, Types::ETreeType type)
calculate <sum-of-deviation-squared> of regression output versus "true" value from test sample
Definition: MethodBase.cxx:982
Double_t GetMean(Int_t ivar) const
Definition: MethodBase.h:345
virtual void DeclareCompatibilityOptions()
options that are used ONLY for the READER to ensure backward compatibility they are hence without any...
Definition: MethodBase.cxx:601
TString GetMethodTypeName() const
Definition: MethodBase.h:323
Bool_t DoMulticlass() const
Definition: MethodBase.h:430
virtual Double_t GetSignificance() const
compute significance of mean difference
void DisableWriting(Bool_t setter)
Definition: MethodBase.h:433
Bool_t fTxtWeightsOnly
Definition: MethodBase.h:714
virtual void ReadWeightsFromXML(void *wghtnode)=0
virtual Double_t GetProba(const Event *ev)
const char * GetName() const
Definition: MethodBase.h:325
TString fParentDir
Definition: MethodBase.h:624
virtual const std::vector< Float_t > & GetMulticlassValues()
Definition: MethodBase.h:224
TSpline * fSplTrainEffBvsS
Definition: MethodBase.h:645
Types::EAnalysisType GetAnalysisType() const
Definition: MethodBase.h:428
virtual TMatrixD GetMulticlassConfusionMatrix(Double_t effB, Types::ETreeType type)
Construct a confusion matrix for a multiclass classifier.
UInt_t GetTrainingTMVAVersionCode() const
Definition: MethodBase.h:380
UInt_t fTMVATrainingVersion
Definition: MethodBase.h:607
Double_t fXmax
Definition: MethodBase.h:655
Double_t fMeanS
Definition: MethodBase.h:650
Types::ESBType fVariableTransformType
Definition: MethodBase.h:600
const TString & GetInputVar(Int_t i) const
Definition: MethodBase.h:340
void PrintHelpMessage() const
prints out method-specific help method
void SetMethodDir(TDirectory *methodDir)
Definition: MethodBase.h:363
const TString & GetJobName() const
Definition: MethodBase.h:321
Bool_t IgnoreEventsWithNegWeightsInTraining() const
Definition: MethodBase.h:675
Double_t fTrainTime
Definition: MethodBase.h:684
virtual void WriteEvaluationHistosToFile(Types::ETreeType treetype)
writes all MVA evaluation histograms to file
virtual void TestMulticlass()
test multiclass classification
Bool_t fModelPersistence
Definition: MethodBase.h:622
const TString & GetTestvarName() const
Definition: MethodBase.h:326
const std::vector< TMVA::Event * > & GetEventCollection(Types::ETreeType type)
returns the event collection (i.e.
void SetupMethod()
setup of methods
Definition: MethodBase.cxx:411
TDirectory * BaseDir() const
returns the ROOT directory where info/histograms etc of the corresponding MVA method instance are sto...
const Event * GetTestingEvent(Long64_t ievt) const
Definition: MethodBase.h:766
virtual std::vector< Float_t > GetMulticlassEfficiency(std::vector< std::vector< Float_t > > &purity)
UInt_t GetNTargets() const
Definition: MethodBase.h:337
EMsgType fVerbosityLevel
Definition: MethodBase.h:667
const TString GetProbaName() const
Definition: MethodBase.h:327
UInt_t fIPyMaxIter
Definition: MethodBase.h:439
TransformationHandler fTransformation
Definition: MethodBase.h:661
virtual void ReadWeightsFromStream(std::istream &)=0
void AddInfoItem(void *gi, const TString &name, const TString &value) const
xml writing
TDirectory * fMethodBaseDir
Definition: MethodBase.h:615
virtual void AddClassifierOutputProb(Types::ETreeType type)
prepare tree branch with the method's discriminating variable
Definition: MethodBase.cxx:941
virtual void MakeClassSpecific(std::ostream &, const TString &="") const
Definition: MethodBase.h:509
Double_t fSignalReferenceCutOrientation
Definition: MethodBase.h:599
virtual Double_t GetEfficiency(const TString &, Types::ETreeType, Double_t &err)
fill background efficiency (resp.
Int_t fNbinsMVAoutput
Definition: MethodBase.h:581
TString GetTrainingTMVAVersionString() const
calculates the TMVA version string from the training version code on the fly
TSpline * fSpleffBvsS
Definition: MethodBase.h:641
TString fVariableTransformTypeString
Definition: MethodBase.h:713
TSpline1 * fSplTrainRefB
Definition: MethodBase.h:695
const TString & GetWeightFileDir() const
Definition: MethodBase.h:481
virtual void SetAnalysisType(Types::EAnalysisType type)
Definition: MethodBase.h:427
UInt_t GetCurrentIter()
Definition: MethodBase.h:470
TString fTestvar
Definition: MethodBase.h:606
const TString & GetMethodName() const
Definition: MethodBase.h:322
Bool_t TxtWeightsOnly() const
Definition: MethodBase.h:523
void Statistics(Types::ETreeType treeType, const TString &theVarName, Double_t &, Double_t &, Double_t &, Double_t &, Double_t &, Double_t &)
calculates rms,mean, xmin, xmax of the event variable this can be either done for the variables as th...
virtual void ReadWeightsFromStream(TFile &)
Definition: MethodBase.h:257
void ExitFromTraining()
Definition: MethodBase.h:453
UInt_t GetNEvents() const
temporary event when testing on a different DataSet than the own one
Definition: MethodBase.h:408
Bool_t DoRegression() const
Definition: MethodBase.h:429
std::vector< Float_t > * fRegressionReturnVal
Definition: MethodBase.h:586
std::vector< Float_t > * fMulticlassReturnVal
Definition: MethodBase.h:587
Double_t fRmsS
Definition: MethodBase.h:652
Bool_t GetLine(std::istream &fin, char *buf)
reads one line from the input stream checks for certain keywords and interprets the line if keywords ...
const Event * GetEvent() const
Definition: MethodBase.h:740
TString fVarTransformString
Definition: MethodBase.h:658
void ProcessSetup()
process all options the "CheckForUnusedOptions" is done in an independent call, since it may be overr...
Definition: MethodBase.cxx:428
virtual void ProcessOptions()=0
virtual std::vector< Double_t > GetMvaValues(Long64_t firstEvt=0, Long64_t lastEvt=-1, Bool_t logProgress=false)
get all the MVA values for the events of the current Data type
Definition: MethodBase.cxx:899
virtual Bool_t IsSignalLike()
uses a pre-set cut on the MVA output (SetSignalReferenceCut and SetSignalReferenceCutOrientation) for...
Definition: MethodBase.cxx:859
void RerouteTransformationHandler(TransformationHandler *fTargetTransformation)
Definition: MethodBase.h:394
virtual ~MethodBase()
destructor
Definition: MethodBase.cxx:369
Bool_t HasMVAPdfs() const
Definition: MethodBase.h:426
UInt_t fBackgroundClass
Definition: MethodBase.h:679
Double_t fTestTime
Definition: MethodBase.h:685
virtual Double_t GetMaximumSignificance(Double_t SignalEvents, Double_t BackgroundEvents, Double_t &optimal_significance_value) const
plot significance, , curve for given number of signal and background events; returns cut for maximum ...
virtual Double_t GetTrainingEfficiency(const TString &)
void SetWeightFileName(TString)
set the weight file name (depreciated)
DataSetInfo & DataInfo() const
Definition: MethodBase.h:401
virtual void MakeClass(const TString &classFileName=TString("")) const
create reader class for method (classification only at present)
TString GetWeightFileName() const
retrieve weight file name
void SetTestTime(Double_t testTime)
Definition: MethodBase.h:163
Types::EMVA fMethodType
Definition: MethodBase.h:605
virtual void TestClassification()
initialization
void AddOutput(Types::ETreeType type, Types::EAnalysisType analysisType)
virtual void WriteMonitoringHistosToFile() const
write special monitoring histograms to file dummy implementation here --------------—
UInt_t GetNVariables() const
Definition: MethodBase.h:336
Types::EAnalysisType fAnalysisType
Definition: MethodBase.h:584
virtual void AddRegressionOutput(Types::ETreeType type)
prepare tree branch with the method's discriminating variable
Definition: MethodBase.cxx:749
void InitBase()
default initialization called by all constructors
Definition: MethodBase.cxx:446
std::vector< const std::vector< TMVA::Event * > * > fEventCollections
Definition: MethodBase.h:697
Bool_t IsSilentFile()
Definition: MethodBase.h:370
bool TrainingEnded()
Definition: MethodBase.h:458
virtual void GetRegressionDeviation(UInt_t tgtNum, Types::ETreeType type, Double_t &stddev, Double_t &stddev90Percent) const
Definition: MethodBase.cxx:729
void InitIPythonInteractive()
Definition: MethodBase.h:444
void ReadStateFromXMLString(const char *xmlstr)
for reading from memory
Bool_t fSetupCompleted
Definition: MethodBase.h:700
void CreateMVAPdfs()
Create PDFs of the MVA output variables.
TString GetTrainingROOTVersionString() const
calculates the ROOT version string from the training version code on the fly
virtual Double_t GetValueForRoot(Double_t)
returns efficiency as function of cut
UInt_t GetTrainingROOTVersionCode() const
Definition: MethodBase.h:381
void ReadStateFromFile()
Function to write options and weights to file.
void WriteVarsToStream(std::ostream &tf, const TString &prefix="") const
write the list of variables (name, min, max) for a given data transformation method to the stream
void ReadVarsFromStream(std::istream &istr)
Read the variables (name, min, max) for a given data transformation method from the stream.
virtual void AddWeightsXMLTo(void *parent) const =0
virtual void Init()=0
void ReadSpectatorsFromXML(void *specnode)
read spectator info from XML
const Event * fTmpEvent
Definition: MethodBase.h:403
virtual Double_t GetMvaValue(Double_t *errLower=0, Double_t *errUpper=0)=0
bool fExitFromTraining
Definition: MethodBase.h:438
void SetNormalised(Bool_t norm)
Definition: MethodBase.h:486
void SetTestvarName(const TString &v="")
Definition: MethodBase.h:332
void ReadVariablesFromXML(void *varnode)
read variable info from XML
Bool_t fConstructedFromWeightFile
Definition: MethodBase.h:609
UInt_t GetNvar() const
Definition: MethodBase.h:335
virtual std::map< TString, Double_t > OptimizeTuningParameters(TString fomType="ROCIntegral", TString fitType="FitGA")
call the Optimizer with the set of parameters and ranges that are meant to be tuned.
Definition: MethodBase.cxx:628
void SetTrainTime(Double_t trainTime)
Definition: MethodBase.h:159
Double_t GetXmax(Int_t ivar) const
Definition: MethodBase.h:348
virtual std::vector< Float_t > GetMulticlassTrainingEfficiency(std::vector< std::vector< Float_t > > &purity)
DataSetInfo & fDataSetInfo
Definition: MethodBase.h:596
Bool_t fHasMVAPdfs
Definition: MethodBase.h:669
void WriteStateToStream(std::ostream &tf) const
general method used in writing the header of the weight files where the used variables,...
virtual Double_t GetRarity(Double_t mvaVal, Types::ESBType reftype=Types::kBackground) const
compute rarity:
virtual void SetTuneParameters(std::map< TString, Double_t > tuneParameters)
set the tuning parameters according to the argument This is just a dummy .
Definition: MethodBase.cxx:649
Double_t GetTrainTime() const
Definition: MethodBase.h:160
void SetBaseDir(TDirectory *methodDir)
Definition: MethodBase.h:364
void ReadStateFromStream(std::istream &tf)
read the header from the weight files of the different MVA methods
void AddVarsXMLTo(void *parent) const
write variable info to XML
Bool_t Help() const
Definition: MethodBase.h:493
TSpline1 * fSplRefB
Definition: MethodBase.h:692
TString fJobName
Definition: MethodBase.h:603
UInt_t fIPyCurrentIter
Definition: MethodBase.h:439
TransformationHandler & GetTransformationHandler(Bool_t takeReroutedIfAvailable=true)
Definition: MethodBase.h:385
Types::EMVA GetMethodType() const
Definition: MethodBase.h:324
void AddTargetsXMLTo(void *parent) const
write target info to XML
Results * fResults
Definition: MethodBase.h:719
Double_t fXmin
Definition: MethodBase.h:654
void ReadTargetsFromXML(void *tarnode)
read target info from XML
void SetFile(TFile *file)
Definition: MethodBase.h:366
void ProcessBaseOptions()
the option string is decoded, for available options see "DeclareOptions"
Definition: MethodBase.cxx:545
virtual void Reset()
Definition: MethodBase.h:191
UInt_t fROOTTrainingVersion
Definition: MethodBase.h:608
void ReadStateFromXML(void *parent)
Double_t GetSignalReferenceCutOrientation() const
Definition: MethodBase.h:352
void SetSignalReferenceCut(Double_t cut)
Definition: MethodBase.h:355
Bool_t IsModelPersistence()
Definition: MethodBase.h:374
std::vector< TString > * fInputVars
Definition: MethodBase.h:577
void NoErrorCalc(Double_t *const err, Double_t *const errUpper)
Definition: MethodBase.cxx:841
Double_t fSignalReferenceCut
the data set information (sometimes needed)
Definition: MethodBase.h:598
Double_t GetTestTime() const
Definition: MethodBase.h:164
UInt_t fSignalClass
Definition: MethodBase.h:678
Double_t fMeanB
Definition: MethodBase.h:651
const TransformationHandler & GetTransformationHandler(Bool_t takeReroutedIfAvailable=true) const
Definition: MethodBase.h:389
Int_t fNsmoothMVAPdf
Definition: MethodBase.h:716
void SetSignalReferenceCutOrientation(Double_t cutOrientation)
Definition: MethodBase.h:356
TDirectory * fBaseDir
Definition: MethodBase.h:614
Bool_t fIgnoreNegWeightsInTraining
Definition: MethodBase.h:671
void WriteStateToFile() const
write options and weights to file note that each one text file for the main configuration information...
void AddClassesXMLTo(void *parent) const
write class info to XML
const TString & GetInputLabel(Int_t i) const
Definition: MethodBase.h:341
ECutOrientation GetCutOrientation() const
Definition: MethodBase.h:541
Ranking * fRanking
Definition: MethodBase.h:576
void SetMethodBaseDir(TDirectory *methodDir)
Definition: MethodBase.h:365
virtual void AddClassifierOutput(Types::ETreeType type)
prepare tree branch with the method's discriminating variable
Definition: MethodBase.cxx:873
DataSet * Data() const
Definition: MethodBase.h:400
void AddSpectatorsXMLTo(void *parent) const
write spectator info to XML
void SetModelPersistence(Bool_t status)
Definition: MethodBase.h:373
TString fWeightFile
Definition: MethodBase.h:627
Bool_t IsNormalised() const
Definition: MethodBase.h:485
const TString & GetInternalVarName(Int_t ivar) const
Definition: MethodBase.h:499
const Event * GetTrainingEvent(Long64_t ievt) const
Definition: MethodBase.h:760
Double_t GetSignalReferenceCut() const
Definition: MethodBase.h:351
TSpline1 * fSplTrainRefS
Definition: MethodBase.h:694
TSpline1 * fSplRefS
Definition: MethodBase.h:691
virtual Double_t GetROCIntegral(TH1D *histS, TH1D *histB) const
calculate the area (integral) under the ROC curve as a overall quality measure of the classification
ECutOrientation fCutOrientation
Definition: MethodBase.h:688
virtual const Ranking * CreateRanking()=0
Double_t GetRMS(Int_t ivar) const
Definition: MethodBase.h:346
IPythonInteractive * fInteractive
Definition: MethodBase.h:437
const char * GetInputTitle(Int_t i) const
Definition: MethodBase.h:342
const TString & GetOriginalVarName(Int_t ivar) const
Definition: MethodBase.h:500
virtual void AddMulticlassOutput(Types::ETreeType type)
prepare tree branch with the method's discriminating variable
Definition: MethodBase.cxx:799
Bool_t IsConstructedFromWeightFile() const
Definition: MethodBase.h:529
virtual void CheckSetup()
check may be overridden by derived class (sometimes, eg, fitters are used which can only be implement...
Definition: MethodBase.cxx:438
Class for boosting a TMVA method.
Definition: MethodBoost.h:58
Class for categorizing the phase space.
Virtual base class for combining several TMVA method.
Multivariate optimisation of signal efficiency for given background efficiency, applying rectangular ...
Definition: MethodCuts.h:61
PDF wrapper for histograms; uses user-defined spline interpolation.
Definition: PDF.h:63
Ranking for variables in method (implementation)
Definition: Ranking.h:48
Class that is the base-class for a vector of result.
Definition: Results.h:57
Root finding using Brents algorithm (translated from CERNLIB function RZERO)
Definition: RootFinder.h:48
Linear interpolation of TGraph.
Definition: TSpline1.h:43
Class that contains all the data information.
const Event * Transform(const Event *) const
the transformation
Double_t GetRMS(Int_t ivar, Int_t cls=-1) const
Double_t GetMean(Int_t ivar, Int_t cls=-1) const
Double_t GetMin(Int_t ivar, Int_t cls=-1) const
Double_t GetMax(Int_t ivar, Int_t cls=-1) const
TString GetMethodName(Types::EMVA method) const
Definition: Types.cxx:136
static Types & Instance()
the the single instance of "Types" if existing already, or create it (Singleton)
Definition: Types.cxx:70
@ kBackground
Definition: Types.h:137
EAnalysisType
Definition: Types.h:127
@ kMulticlass
Definition: Types.h:130
@ kRegression
Definition: Types.h:129
@ kTraining
Definition: Types.h:144
@ kTesting
Definition: Types.h:145
const TString & GetLabel() const
Definition: VariableInfo.h:59
const TString & GetExpression() const
Definition: VariableInfo.h:57
const TString & GetInternalName() const
Definition: VariableInfo.h:58
A TMultiGraph is a collection of TGraph (or derived) objects.
Definition: TMultiGraph.h:35
virtual const char * GetTitle() const
Returns title of object.
Definition: TNamed.h:48
Base class for spline implementation containing the Draw/Paint methods.
Definition: TSpline.h:22
Basic string class.
Definition: TString.h:131
const char * Data() const
Definition: TString.h:364
A TTree represents a columnar dataset.
Definition: TTree.h:71
Double_t x[n]
Definition: legend1.C:17
create variable transformations
Definition: file.py:1