Logo ROOT  
Reference Guide
 
Loading...
Searching...
No Matches
TMVA::RuleFitParams Class Reference

A class doing the actual fitting of a linear model using rules as base functions.

Definition at line 49 of file RuleFitParams.h.

Public Member Functions

 RuleFitParams ()
 constructor
 
virtual ~RuleFitParams ()
 destructor
 
Int_t FindGDTau ()
 This finds the cutoff parameter tau by scanning several different paths.
 
UInt_t GetPathIdx1 () const
 
UInt_t GetPathIdx2 () const
 
UInt_t GetPerfIdx1 () const
 
UInt_t GetPerfIdx2 () const
 
void Init ()
 Initializes all parameters using the RuleEnsemble and the training tree.
 
void InitGD ()
 Initialize GD path search.
 
Double_t LossFunction (const Event &e) const
 Implementation of squared-error ramp loss function (eq 39,40 in ref 1) This is used for binary Classifications where y = {+1,-1} for (sig,bkg)
 
Double_t LossFunction (UInt_t evtidx) const
 Implementation of squared-error ramp loss function (eq 39,40 in ref 1) This is used for binary Classifications where y = {+1,-1} for (sig,bkg)
 
Double_t LossFunction (UInt_t evtidx, UInt_t itau) const
 Implementation of squared-error ramp loss function (eq 39,40 in ref 1) This is used for binary Classifications where y = {+1,-1} for (sig,bkg)
 
void MakeGDPath ()
 The following finds the gradient directed path in parameter space.
 
Double_t Penalty () const
 This is the "lasso" penalty To be used for regression.
 
Double_t Risk (UInt_t ind1, UInt_t ind2, Double_t neff) const
 risk assessment
 
Double_t Risk (UInt_t ind1, UInt_t ind2, Double_t neff, UInt_t itau) const
 risk assessment for tau model <itau>
 
Double_t RiskPath () const
 
Double_t RiskPerf () const
 
Double_t RiskPerf (UInt_t itau) const
 
UInt_t RiskPerfTst ()
 Estimates the error rate with the current set of parameters.
 
void SetGDErrScale (Double_t s)
 
void SetGDNPathSteps (Int_t np)
 
void SetGDPathStep (Double_t s)
 
void SetGDTau (Double_t t)
 
void SetGDTauPrec (Double_t p)
 
void SetGDTauRange (Double_t t0, Double_t t1)
 
void SetGDTauScan (UInt_t n)
 
void SetMsgType (EMsgType t)
 
void SetRuleFit (RuleFit *rf)
 
Int_t Type (const Event *e) const
 

Protected Types

typedef std::vector< constTMVA::Event * >::const_iterator EventItr
 

Protected Member Functions

Double_t CalcAverageResponse ()
 calculate the average response - TODO : rewrite bad dependancy on EvaluateAverage() !
 
Double_t CalcAverageResponseOLD ()
 
Double_t CalcAverageTruth ()
 calculate the average truth
 
void CalcFStar ()
 Estimates F* (optimum scoring function) for all events for the given sets.
 
void CalcGDNTau ()
 
void CalcTstAverageResponse ()
 calc average response for all test paths - TODO: see comment under CalcAverageResponse() note that 0 offset is used
 
Double_t ErrorRateBin ()
 Estimates the error rate with the current set of parameters It uses a binary estimate of (y-F*(x)) (y-F*(x)) = (Num of events where sign(F)!=sign(y))/Neve y = {+1 if event is signal, -1 otherwise} — NOT USED —.
 
Double_t ErrorRateReg ()
 Estimates the error rate with the current set of parameters This code is pretty messy at the moment.
 
Double_t ErrorRateRoc ()
 Estimates the error rate with the current set of parameters.
 
Double_t ErrorRateRocRaw (std::vector< Double_t > &sFsig, std::vector< Double_t > &sFbkg)
 Estimates the error rate with the current set of parameters.
 
void ErrorRateRocTst ()
 Estimates the error rate with the current set of parameters.
 
void EvaluateAverage (UInt_t ind1, UInt_t ind2, std::vector< Double_t > &avsel, std::vector< Double_t > &avrul)
 evaluate the average of each variable and f(x) in the given range
 
void EvaluateAveragePath ()
 
void EvaluateAveragePerf ()
 
void FillCoefficients ()
 helper function to store the rule coefficients in local arrays
 
void InitNtuple ()
 initializes the ntuple
 
void MakeGradientVector ()
 make gradient vector
 
void MakeTstGradientVector ()
 make test gradient vector for all tau same algorithm as MakeGradientVector()
 
Double_t Optimism ()
 implementation of eq.
 
void UpdateCoefficients ()
 Establish maximum gradient for rules, linear terms and the offset.
 
void UpdateTstCoefficients ()
 Establish maximum gradient for rules, linear terms and the offset for all taus TODO: do not need index range!
 

Protected Attributes

std::vector< Double_tfAverageRulePath
 average of each rule, same range
 
std::vector< Double_tfAverageRulePerf
 average of each rule, same range
 
std::vector< Double_tfAverageSelectorPath
 average of each variable over the range fPathIdx1,2
 
std::vector< Double_tfAverageSelectorPerf
 average of each variable over the range fPerfIdx1,2
 
Double_t fAverageTruth
 average truth, ie sum(y)/N, y=+-1
 
Double_t fbkgave
 Average of F(bkg)
 
Double_t fbkgrms
 Rms of F(bkg)
 
std::vector< Double_tfFstar
 vector of F*() - filled in CalcFStar()
 
Double_t fFstarMedian
 median value of F*() using
 
std::vector< std::vector< Double_t > > fGDCoefLinTst
 linear coeffs - one per tau
 
std::vector< std::vector< Double_t > > fGDCoefTst
 rule coeffs - one per tau
 
Double_t fGDErrScale
 stop scan at error = scale*errmin
 
std::vector< Double_tfGDErrTst
 error rates per tau
 
std::vector< Char_tfGDErrTstOK
 error rate is sufficiently low <— stores boolean
 
Int_t fGDNPathSteps
 number of path steps
 
UInt_t fGDNTau
 number of tau-paths - calculated in SetGDTauPrec
 
UInt_t fGDNTauTstOK
 number of tau in the test-phase that are ok
 
TTreefGDNtuple
 Gradient path ntuple, contains params for each step along the path.
 
std::vector< Double_tfGDOfsTst
 offset per tau
 
Double_t fGDPathStep
 step size along path (delta nu in eq 22, ref 1)
 
Double_t fGDTau
 selected threshold parameter (tau in eq 26, ref 1)
 
Double_t fGDTauMax
 max threshold parameter (tau in eq 26, ref 1)
 
Double_t fGDTauMin
 min threshold parameter (tau in eq 26, ref 1)
 
Double_t fGDTauPrec
 precision in tau
 
UInt_t fGDTauScan
 number scan for tau-paths
 
std::vector< Double_tfGDTauVec
 the tau's
 
std::vector< Double_tfGradVec
 gradient vector - dimension = number of rules in ensemble
 
std::vector< Double_tfGradVecLin
 gradient vector - dimension = number of variables
 
std::vector< std::vector< Double_t > > fGradVecLinTst
 gradient vector, linear terms - one per tau
 
std::vector< std::vector< Double_t > > fGradVecTst
 gradient vector - one per tau
 
Double_t fNEveEffPath
 sum of weights for Path events
 
Double_t fNEveEffPerf
 idem for Perf events
 
UInt_t fNLinear
 number of linear terms
 
UInt_t fNRules
 number of rules
 
Double_tfNTCoeff
 GD path: rule coefficients.
 
Double_t fNTCoefRad
 GD path: 'radius' of all rulecoeffs.
 
Double_t fNTErrorRate
 GD path: error rate (or performance)
 
Double_tfNTLinCoeff
 GD path: linear coefficients.
 
Double_t fNTNuval
 GD path: value of nu.
 
Double_t fNTOffset
 GD path: model offset.
 
Double_t fNTRisk
 GD path: risk.
 
UInt_t fPathIdx1
 first event index for path search
 
UInt_t fPathIdx2
 last event index for path search
 
UInt_t fPerfIdx1
 first event index for performance evaluation
 
UInt_t fPerfIdx2
 last event index for performance evaluation
 
RuleEnsemblefRuleEnsemble
 rule ensemble
 
RuleFitfRuleFit
 rule fit
 
Double_t fsigave
 Sigma of current signal score function F(sig)
 
Double_t fsigrms
 Rms of F(sig)
 

Private Member Functions

MsgLoggerLog () const
 

Private Attributes

MsgLoggerfLogger
 ! message logger
 

#include <TMVA/RuleFitParams.h>

Member Typedef Documentation

◆ EventItr

typedef std::vector<constTMVA::Event*>::const_iterator TMVA::RuleFitParams::EventItr
protected

Definition at line 130 of file RuleFitParams.h.

Constructor & Destructor Documentation

◆ RuleFitParams()

TMVA::RuleFitParams::RuleFitParams ( )

constructor

Definition at line 64 of file RuleFitParams.cxx.

◆ ~RuleFitParams()

TMVA::RuleFitParams::~RuleFitParams ( )
virtual

destructor

Definition at line 104 of file RuleFitParams.cxx.

Member Function Documentation

◆ CalcAverageResponse()

Double_t TMVA::RuleFitParams::CalcAverageResponse ( )
protected

calculate the average response - TODO : rewrite bad dependancy on EvaluateAverage() !

note that 0 offset is used

Definition at line 1512 of file RuleFitParams.cxx.

◆ CalcAverageResponseOLD()

Double_t TMVA::RuleFitParams::CalcAverageResponseOLD ( )
protected

◆ CalcAverageTruth()

Double_t TMVA::RuleFitParams::CalcAverageTruth ( )
protected

calculate the average truth

Definition at line 1527 of file RuleFitParams.cxx.

◆ CalcFStar()

void TMVA::RuleFitParams::CalcFStar ( )
protected

Estimates F* (optimum scoring function) for all events for the given sets.

The result is used in ErrorRateReg(). — NOT USED —

Definition at line 885 of file RuleFitParams.cxx.

◆ CalcGDNTau()

void TMVA::RuleFitParams::CalcGDNTau ( )
inlineprotected

Definition at line 136 of file RuleFitParams.h.

◆ CalcTstAverageResponse()

void TMVA::RuleFitParams::CalcTstAverageResponse ( )
protected

calc average response for all test paths - TODO: see comment under CalcAverageResponse() note that 0 offset is used

Definition at line 1491 of file RuleFitParams.cxx.

◆ ErrorRateBin()

Double_t TMVA::RuleFitParams::ErrorRateBin ( )
protected

Estimates the error rate with the current set of parameters It uses a binary estimate of (y-F*(x)) (y-F*(x)) = (Num of events where sign(F)!=sign(y))/Neve y = {+1 if event is signal, -1 otherwise} — NOT USED —.

Definition at line 1008 of file RuleFitParams.cxx.

◆ ErrorRateReg()

Double_t TMVA::RuleFitParams::ErrorRateReg ( )
protected

Estimates the error rate with the current set of parameters This code is pretty messy at the moment.

Cleanup is needed. – NOT USED —

Definition at line 964 of file RuleFitParams.cxx.

◆ ErrorRateRoc()

Double_t TMVA::RuleFitParams::ErrorRateRoc ( )
protected

Estimates the error rate with the current set of parameters.

It calculates the area under the bkg rejection vs signal efficiency curve. The value returned is 1-area. This works but is less efficient than calculating the Risk using RiskPerf().

Definition at line 1107 of file RuleFitParams.cxx.

◆ ErrorRateRocRaw()

Double_t TMVA::RuleFitParams::ErrorRateRocRaw ( std::vector< Double_t > &  sFsig,
std::vector< Double_t > &  sFbkg 
)
protected

Estimates the error rate with the current set of parameters.

It calculates the area under the bkg rejection vs signal efficiency curve. The value returned is 1-area.

Definition at line 1042 of file RuleFitParams.cxx.

◆ ErrorRateRocTst()

void TMVA::RuleFitParams::ErrorRateRocTst ( )
protected

Estimates the error rate with the current set of parameters.

It calculates the area under the bkg rejection vs signal efficiency curve. The value returned is 1-area.

See comment under ErrorRateRoc().

Definition at line 1155 of file RuleFitParams.cxx.

◆ EvaluateAverage()

void TMVA::RuleFitParams::EvaluateAverage ( UInt_t  ind1,
UInt_t  ind2,
std::vector< Double_t > &  avsel,
std::vector< Double_t > &  avrul 
)
protected

evaluate the average of each variable and f(x) in the given range

Definition at line 208 of file RuleFitParams.cxx.

◆ EvaluateAveragePath()

void TMVA::RuleFitParams::EvaluateAveragePath ( )
inlineprotected

Definition at line 177 of file RuleFitParams.h.

◆ EvaluateAveragePerf()

void TMVA::RuleFitParams::EvaluateAveragePerf ( )
inlineprotected

Definition at line 180 of file RuleFitParams.h.

◆ FillCoefficients()

void TMVA::RuleFitParams::FillCoefficients ( )
protected

helper function to store the rule coefficients in local arrays

Definition at line 868 of file RuleFitParams.cxx.

◆ FindGDTau()

Int_t TMVA::RuleFitParams::FindGDTau ( )

This finds the cutoff parameter tau by scanning several different paths.

Definition at line 449 of file RuleFitParams.cxx.

◆ GetPathIdx1()

UInt_t TMVA::RuleFitParams::GetPathIdx1 ( ) const
inline

Definition at line 91 of file RuleFitParams.h.

◆ GetPathIdx2()

UInt_t TMVA::RuleFitParams::GetPathIdx2 ( ) const
inline

Definition at line 92 of file RuleFitParams.h.

◆ GetPerfIdx1()

UInt_t TMVA::RuleFitParams::GetPerfIdx1 ( ) const
inline

Definition at line 93 of file RuleFitParams.h.

◆ GetPerfIdx2()

UInt_t TMVA::RuleFitParams::GetPerfIdx2 ( ) const
inline

Definition at line 94 of file RuleFitParams.h.

◆ Init()

void TMVA::RuleFitParams::Init ( )

Initializes all parameters using the RuleEnsemble and the training tree.

Definition at line 114 of file RuleFitParams.cxx.

◆ InitGD()

void TMVA::RuleFitParams::InitGD ( )

Initialize GD path search.

Definition at line 373 of file RuleFitParams.cxx.

◆ InitNtuple()

void TMVA::RuleFitParams::InitNtuple ( )
protected

initializes the ntuple

Definition at line 185 of file RuleFitParams.cxx.

◆ Log()

MsgLogger & TMVA::RuleFitParams::Log ( ) const
inlineprivate

Definition at line 254 of file RuleFitParams.h.

◆ LossFunction() [1/3]

Double_t TMVA::RuleFitParams::LossFunction ( const Event e) const

Implementation of squared-error ramp loss function (eq 39,40 in ref 1) This is used for binary Classifications where y = {+1,-1} for (sig,bkg)

Definition at line 278 of file RuleFitParams.cxx.

◆ LossFunction() [2/3]

Double_t TMVA::RuleFitParams::LossFunction ( UInt_t  evtidx) const

Implementation of squared-error ramp loss function (eq 39,40 in ref 1) This is used for binary Classifications where y = {+1,-1} for (sig,bkg)

Definition at line 290 of file RuleFitParams.cxx.

◆ LossFunction() [3/3]

Double_t TMVA::RuleFitParams::LossFunction ( UInt_t  evtidx,
UInt_t  itau 
) const

Implementation of squared-error ramp loss function (eq 39,40 in ref 1) This is used for binary Classifications where y = {+1,-1} for (sig,bkg)

Definition at line 302 of file RuleFitParams.cxx.

◆ MakeGDPath()

void TMVA::RuleFitParams::MakeGDPath ( )

The following finds the gradient directed path in parameter space.

More work is needed... FT, 24/9/2006

The algorithm is currently as follows (if not otherwise stated, the sample used below is [fPathIdx1,fPathIdx2]):

  1. Set offset to -average(y(true)) and all coefs=0 => average of F(x)==0
  2. FindGDTau() : start scanning using several paths defined by different tau choose the tau yielding the best path
  3. start the scanning the chosen path
  4. check error rate at a given frequency data used for check: [fPerfIdx1,fPerfIdx2]
  5. stop when either of the following conditions are fullfilled:
    1. loop index==fGDNPathSteps
    2. error > fGDErrScale*errmin
    3. only in DEBUG mode: risk is not monotonously decreasing

The algorithm will warn if:

  1. the error rate was still decreasing when loop finished -> increase fGDNPathSteps!
  2. minimum was found at an early stage -> decrease fGDPathStep
  3. DEBUG: risk > previous risk -> entered chaotic region (regularization is too small)

Definition at line 538 of file RuleFitParams.cxx.

◆ MakeGradientVector()

void TMVA::RuleFitParams::MakeGradientVector ( )
protected

make gradient vector

Definition at line 1375 of file RuleFitParams.cxx.

◆ MakeTstGradientVector()

void TMVA::RuleFitParams::MakeTstGradientVector ( )
protected

make test gradient vector for all tau same algorithm as MakeGradientVector()

Definition at line 1259 of file RuleFitParams.cxx.

◆ Optimism()

Double_t TMVA::RuleFitParams::Optimism ( )
protected

implementation of eq.

7.17 in Hastie,Tibshirani & Friedman book this is the covariance between the estimated response yhat and the true value y. NOT REALLY SURE IF THIS IS CORRECT! — THIS IS NOT USED —

Definition at line 925 of file RuleFitParams.cxx.

◆ Penalty()

Double_t TMVA::RuleFitParams::Penalty ( ) const

This is the "lasso" penalty To be used for regression.

— NOT USED —

Definition at line 356 of file RuleFitParams.cxx.

◆ Risk() [1/2]

Double_t TMVA::RuleFitParams::Risk ( UInt_t  ind1,
UInt_t  ind2,
Double_t  neff 
) const

risk assessment

Definition at line 314 of file RuleFitParams.cxx.

◆ Risk() [2/2]

Double_t TMVA::RuleFitParams::Risk ( UInt_t  ind1,
UInt_t  ind2,
Double_t  neff,
UInt_t  itau 
) const

risk assessment for tau model <itau>

Definition at line 334 of file RuleFitParams.cxx.

◆ RiskPath()

Double_t TMVA::RuleFitParams::RiskPath ( ) const
inline

Definition at line 108 of file RuleFitParams.h.

◆ RiskPerf() [1/2]

Double_t TMVA::RuleFitParams::RiskPerf ( ) const
inline

Definition at line 109 of file RuleFitParams.h.

◆ RiskPerf() [2/2]

Double_t TMVA::RuleFitParams::RiskPerf ( UInt_t  itau) const
inline

Definition at line 110 of file RuleFitParams.h.

◆ RiskPerfTst()

UInt_t TMVA::RuleFitParams::RiskPerfTst ( )

Estimates the error rate with the current set of parameters.

using the <Perf> subsample. Return the tau index giving the lowest error

Definition at line 1201 of file RuleFitParams.cxx.

◆ SetGDErrScale()

void TMVA::RuleFitParams::SetGDErrScale ( Double_t  s)
inline

Definition at line 85 of file RuleFitParams.h.

◆ SetGDNPathSteps()

void TMVA::RuleFitParams::SetGDNPathSteps ( Int_t  np)
inline

Definition at line 65 of file RuleFitParams.h.

◆ SetGDPathStep()

void TMVA::RuleFitParams::SetGDPathStep ( Double_t  s)
inline

Definition at line 68 of file RuleFitParams.h.

◆ SetGDTau()

void TMVA::RuleFitParams::SetGDTau ( Double_t  t)
inline

Definition at line 82 of file RuleFitParams.h.

◆ SetGDTauPrec()

void TMVA::RuleFitParams::SetGDTauPrec ( Double_t  p)
inline

Definition at line 86 of file RuleFitParams.h.

◆ SetGDTauRange()

void TMVA::RuleFitParams::SetGDTauRange ( Double_t  t0,
Double_t  t1 
)
inline

Definition at line 71 of file RuleFitParams.h.

◆ SetGDTauScan()

void TMVA::RuleFitParams::SetGDTauScan ( UInt_t  n)
inline

Definition at line 79 of file RuleFitParams.h.

◆ SetMsgType()

void TMVA::RuleFitParams::SetMsgType ( EMsgType  t)

Definition at line 1556 of file RuleFitParams.cxx.

◆ SetRuleFit()

void TMVA::RuleFitParams::SetRuleFit ( RuleFit rf)
inline

Definition at line 62 of file RuleFitParams.h.

◆ Type()

Int_t TMVA::RuleFitParams::Type ( const Event e) const

Definition at line 1550 of file RuleFitParams.cxx.

◆ UpdateCoefficients()

void TMVA::RuleFitParams::UpdateCoefficients ( )
protected

Establish maximum gradient for rules, linear terms and the offset.

Definition at line 1441 of file RuleFitParams.cxx.

◆ UpdateTstCoefficients()

void TMVA::RuleFitParams::UpdateTstCoefficients ( )
protected

Establish maximum gradient for rules, linear terms and the offset for all taus TODO: do not need index range!

Definition at line 1327 of file RuleFitParams.cxx.

Member Data Documentation

◆ fAverageRulePath

std::vector<Double_t> TMVA::RuleFitParams::fAverageRulePath
protected

average of each rule, same range

Definition at line 205 of file RuleFitParams.h.

◆ fAverageRulePerf

std::vector<Double_t> TMVA::RuleFitParams::fAverageRulePerf
protected

average of each rule, same range

Definition at line 207 of file RuleFitParams.h.

◆ fAverageSelectorPath

std::vector<Double_t> TMVA::RuleFitParams::fAverageSelectorPath
protected

average of each variable over the range fPathIdx1,2

Definition at line 204 of file RuleFitParams.h.

◆ fAverageSelectorPerf

std::vector<Double_t> TMVA::RuleFitParams::fAverageSelectorPerf
protected

average of each variable over the range fPerfIdx1,2

Definition at line 206 of file RuleFitParams.h.

◆ fAverageTruth

Double_t TMVA::RuleFitParams::fAverageTruth
protected

average truth, ie sum(y)/N, y=+-1

Definition at line 232 of file RuleFitParams.h.

◆ fbkgave

Double_t TMVA::RuleFitParams::fbkgave
protected

Average of F(bkg)

Definition at line 248 of file RuleFitParams.h.

◆ fbkgrms

Double_t TMVA::RuleFitParams::fbkgrms
protected

Rms of F(bkg)

Definition at line 249 of file RuleFitParams.h.

◆ fFstar

std::vector<Double_t> TMVA::RuleFitParams::fFstar
protected

vector of F*() - filled in CalcFStar()

Definition at line 234 of file RuleFitParams.h.

◆ fFstarMedian

Double_t TMVA::RuleFitParams::fFstarMedian
protected

median value of F*() using

Definition at line 235 of file RuleFitParams.h.

◆ fGDCoefLinTst

std::vector< std::vector<Double_t> > TMVA::RuleFitParams::fGDCoefLinTst
protected

linear coeffs - one per tau

Definition at line 218 of file RuleFitParams.h.

◆ fGDCoefTst

std::vector< std::vector<Double_t> > TMVA::RuleFitParams::fGDCoefTst
protected

rule coeffs - one per tau

Definition at line 217 of file RuleFitParams.h.

◆ fGDErrScale

Double_t TMVA::RuleFitParams::fGDErrScale
protected

stop scan at error = scale*errmin

Definition at line 230 of file RuleFitParams.h.

◆ fGDErrTst

std::vector<Double_t> TMVA::RuleFitParams::fGDErrTst
protected

error rates per tau

Definition at line 215 of file RuleFitParams.h.

◆ fGDErrTstOK

std::vector<Char_t> TMVA::RuleFitParams::fGDErrTstOK
protected

error rate is sufficiently low <— stores boolean

Definition at line 216 of file RuleFitParams.h.

◆ fGDNPathSteps

Int_t TMVA::RuleFitParams::fGDNPathSteps
protected

number of path steps

Definition at line 229 of file RuleFitParams.h.

◆ fGDNTau

UInt_t TMVA::RuleFitParams::fGDNTau
protected

number of tau-paths - calculated in SetGDTauPrec

Definition at line 222 of file RuleFitParams.h.

◆ fGDNTauTstOK

UInt_t TMVA::RuleFitParams::fGDNTauTstOK
protected

number of tau in the test-phase that are ok

Definition at line 221 of file RuleFitParams.h.

◆ fGDNtuple

TTree* TMVA::RuleFitParams::fGDNtuple
protected

Gradient path ntuple, contains params for each step along the path.

Definition at line 237 of file RuleFitParams.h.

◆ fGDOfsTst

std::vector<Double_t> TMVA::RuleFitParams::fGDOfsTst
protected

offset per tau

Definition at line 219 of file RuleFitParams.h.

◆ fGDPathStep

Double_t TMVA::RuleFitParams::fGDPathStep
protected

step size along path (delta nu in eq 22, ref 1)

Definition at line 228 of file RuleFitParams.h.

◆ fGDTau

Double_t TMVA::RuleFitParams::fGDTau
protected

selected threshold parameter (tau in eq 26, ref 1)

Definition at line 227 of file RuleFitParams.h.

◆ fGDTauMax

Double_t TMVA::RuleFitParams::fGDTauMax
protected

max threshold parameter (tau in eq 26, ref 1)

Definition at line 226 of file RuleFitParams.h.

◆ fGDTauMin

Double_t TMVA::RuleFitParams::fGDTauMin
protected

min threshold parameter (tau in eq 26, ref 1)

Definition at line 225 of file RuleFitParams.h.

◆ fGDTauPrec

Double_t TMVA::RuleFitParams::fGDTauPrec
protected

precision in tau

Definition at line 223 of file RuleFitParams.h.

◆ fGDTauScan

UInt_t TMVA::RuleFitParams::fGDTauScan
protected

number scan for tau-paths

Definition at line 224 of file RuleFitParams.h.

◆ fGDTauVec

std::vector< Double_t > TMVA::RuleFitParams::fGDTauVec
protected

the tau's

Definition at line 220 of file RuleFitParams.h.

◆ fGradVec

std::vector<Double_t> TMVA::RuleFitParams::fGradVec
protected

gradient vector - dimension = number of rules in ensemble

Definition at line 209 of file RuleFitParams.h.

◆ fGradVecLin

std::vector<Double_t> TMVA::RuleFitParams::fGradVecLin
protected

gradient vector - dimension = number of variables

Definition at line 210 of file RuleFitParams.h.

◆ fGradVecLinTst

std::vector< std::vector<Double_t> > TMVA::RuleFitParams::fGradVecLinTst
protected

gradient vector, linear terms - one per tau

Definition at line 213 of file RuleFitParams.h.

◆ fGradVecTst

std::vector< std::vector<Double_t> > TMVA::RuleFitParams::fGradVecTst
protected

gradient vector - one per tau

Definition at line 212 of file RuleFitParams.h.

◆ fLogger

MsgLogger* TMVA::RuleFitParams::fLogger
mutableprivate

! message logger

Definition at line 253 of file RuleFitParams.h.

◆ fNEveEffPath

Double_t TMVA::RuleFitParams::fNEveEffPath
protected

sum of weights for Path events

Definition at line 201 of file RuleFitParams.h.

◆ fNEveEffPerf

Double_t TMVA::RuleFitParams::fNEveEffPerf
protected

idem for Perf events

Definition at line 202 of file RuleFitParams.h.

◆ fNLinear

UInt_t TMVA::RuleFitParams::fNLinear
protected

number of linear terms

Definition at line 192 of file RuleFitParams.h.

◆ fNRules

UInt_t TMVA::RuleFitParams::fNRules
protected

number of rules

Definition at line 191 of file RuleFitParams.h.

◆ fNTCoeff

Double_t* TMVA::RuleFitParams::fNTCoeff
protected

GD path: rule coefficients.

Definition at line 243 of file RuleFitParams.h.

◆ fNTCoefRad

Double_t TMVA::RuleFitParams::fNTCoefRad
protected

GD path: 'radius' of all rulecoeffs.

Definition at line 241 of file RuleFitParams.h.

◆ fNTErrorRate

Double_t TMVA::RuleFitParams::fNTErrorRate
protected

GD path: error rate (or performance)

Definition at line 239 of file RuleFitParams.h.

◆ fNTLinCoeff

Double_t* TMVA::RuleFitParams::fNTLinCoeff
protected

GD path: linear coefficients.

Definition at line 244 of file RuleFitParams.h.

◆ fNTNuval

Double_t TMVA::RuleFitParams::fNTNuval
protected

GD path: value of nu.

Definition at line 240 of file RuleFitParams.h.

◆ fNTOffset

Double_t TMVA::RuleFitParams::fNTOffset
protected

GD path: model offset.

Definition at line 242 of file RuleFitParams.h.

◆ fNTRisk

Double_t TMVA::RuleFitParams::fNTRisk
protected

GD path: risk.

Definition at line 238 of file RuleFitParams.h.

◆ fPathIdx1

UInt_t TMVA::RuleFitParams::fPathIdx1
protected

first event index for path search

Definition at line 197 of file RuleFitParams.h.

◆ fPathIdx2

UInt_t TMVA::RuleFitParams::fPathIdx2
protected

last event index for path search

Definition at line 198 of file RuleFitParams.h.

◆ fPerfIdx1

UInt_t TMVA::RuleFitParams::fPerfIdx1
protected

first event index for performance evaluation

Definition at line 199 of file RuleFitParams.h.

◆ fPerfIdx2

UInt_t TMVA::RuleFitParams::fPerfIdx2
protected

last event index for performance evaluation

Definition at line 200 of file RuleFitParams.h.

◆ fRuleEnsemble

RuleEnsemble* TMVA::RuleFitParams::fRuleEnsemble
protected

rule ensemble

Definition at line 189 of file RuleFitParams.h.

◆ fRuleFit

RuleFit* TMVA::RuleFitParams::fRuleFit
protected

rule fit

Definition at line 188 of file RuleFitParams.h.

◆ fsigave

Double_t TMVA::RuleFitParams::fsigave
protected

Sigma of current signal score function F(sig)

Definition at line 246 of file RuleFitParams.h.

◆ fsigrms

Double_t TMVA::RuleFitParams::fsigrms
protected

Rms of F(sig)

Definition at line 247 of file RuleFitParams.h.

Libraries for TMVA::RuleFitParams:

The documentation for this class was generated from the following files: