Logo ROOT  
Reference Guide
TMVA::GiniIndex Class Reference

Implementation of the GiniIndex as separation criterion.

Large Gini Indices (maximum 0.5) mean , that the sample is well mixed (same amount of signal and bkg) bkg.

Small Indices mean, well separated.

General definition:

\[ Gini(Sample M) = 1 - (\frac{c(1)}{N})^2 - (\frac{c(2)}{N})^2 .... - (\frac{c(k)}{N})^2 \]


\( M \) is a sample of whatever \( N \) elements (events) that belong to \( K \) different classes.

\( c(k) \) is the number of elements that belong to class \( k \) for just Signal and Background classes this boils down to:

\[ Gini(Sample) = \frac{2sb}{(s+b)^2} \]

Definition at line 95 of file GiniIndex.h.

Public Member Functions

 GiniIndex ()
 GiniIndex (const GiniIndex &g)
virtual ~GiniIndex ()
virtual Double_t GetSeparationIndex (const Double_t s, const Double_t b)
 what we use here is 2*Gini. More...
- Public Member Functions inherited from TMVA::SeparationBase
 SeparationBase ()
 Constructor. More...
 SeparationBase (const SeparationBase &s)
 Copy constructor. More...
virtual ~SeparationBase ()
const TStringGetName ()
virtual Double_t GetSeparationGain (const Double_t nSelS, const Double_t nSelB, const Double_t nTotS, const Double_t nTotB)
 Separation Gain: the measure of how the quality of separation of the sample increases by splitting the sample e.g. More...

Additional Inherited Members

- Protected Attributes inherited from TMVA::SeparationBase
TString fName
Double_t fPrecisionCut

#include <TMVA/GiniIndex.h>

Inheritance diagram for TMVA::GiniIndex:

Constructor & Destructor Documentation

◆ GiniIndex() [1/2]

TMVA::GiniIndex::GiniIndex ( )

Definition at line 132 of file GiniIndex.h.

◆ GiniIndex() [2/2]

TMVA::GiniIndex::GiniIndex ( const GiniIndex g)

Definition at line 135 of file GiniIndex.h.

◆ ~GiniIndex()

virtual TMVA::GiniIndex::~GiniIndex ( )

Definition at line 138 of file GiniIndex.h.

Member Function Documentation

◆ GetSeparationIndex()

Double_t TMVA::GiniIndex::GetSeparationIndex ( const Double_t  s,
const Double_t  b 

what we use here is 2*Gini.

. as for the later use the factor 2 is irrelevant and hence I'd like to save this calculation

Implements TMVA::SeparationBase.

Definition at line 76 of file GiniIndex.cxx.

Libraries for TMVA::GiniIndex:

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