EIC code displayed by LXR |
|
|
|
|||
File indexing completed on 2025-01-18 10:11:04
0001 // @(#)root/tmva $Id$ 0002 // Author: Andreas Hoecker, Joerg Stelzer, Helge Voss, Kai Voss 0003 0004 /********************************************************************************** 0005 * Project: TMVA - a Root-integrated toolkit for multivariate data analysis * 0006 * Package: TMVA * 0007 * Class : RegressionVariance * 0008 * * 0009 * * 0010 * Description: Calculate the separation criteria used in regression * 0011 * * 0012 * There are two things: the Separation Index, and the Separation Gain * 0013 * Separation Index: * 0014 * Measure of the "Variance" of a sample. * 0015 * * 0016 * Separation Gain: * 0017 * the measure of how the quality of separation of the sample increases * 0018 * by splitting the sample e.g. into a "left-node" and a "right-node" * 0019 * (N * Index_parent) - (N_left * Index_left) - (N_right * Index_right) * 0020 * this is then the quality criteria which is optimized for when trying * 0021 * to increase the information in the system (making the best selection * 0022 * * 0023 * * 0024 * Authors (alphabetical): * 0025 * Helge Voss <Helge.Voss@cern.ch> - MPI-K Heidelberg, Germany * 0026 * * 0027 * Copyright (c) 2005: * 0028 * CERN, Switzerland * 0029 * U. of Victoria, Canada * 0030 * Heidelberg U., Germany * 0031 * * 0032 * Redistribution and use in source and binary forms, with or without * 0033 * modification, are permitted according to the terms listed in LICENSE * 0034 * (see tmva/doc/LICENSE) * 0035 **********************************************************************************/ 0036 0037 #ifndef ROOT_TMVA_RegressionVariance 0038 #define ROOT_TMVA_RegressionVariance 0039 0040 ////////////////////////////////////////////////////////////////////////// 0041 // // 0042 // RegressionVariance // 0043 // // 0044 // Calculate the "SeparationGain" for Regression analysis // 0045 // separation criteria used in various training algorithms // 0046 // // 0047 // There are two things: the Separation Index, and the Separation Gain // 0048 // Separation Index: // 0049 // Measure of the "Variance" of a sample. // 0050 // // 0051 // Separation Gain: // 0052 // the measure of how the quality of separation of the sample increases // 0053 // by splitting the sample e.g. into a "left-node" and a "right-node" // 0054 // (N * Index_parent) - (N_left * Index_left) - (N_right * Index_right) // 0055 // this is then the quality criteria which is optimized for when trying // 0056 // to increase the information in the system (making the best selection // 0057 // // 0058 ////////////////////////////////////////////////////////////////////////// 0059 0060 #include "Rtypes.h" 0061 0062 #include "TString.h" 0063 0064 namespace TMVA { 0065 0066 class RegressionVariance { 0067 0068 public: 0069 0070 //default constructor 0071 RegressionVariance(){fName = "Variance for Regression";} 0072 0073 //copy constructor 0074 RegressionVariance( const RegressionVariance& s ): fName ( s.fName ) {} 0075 0076 // destructor 0077 virtual ~RegressionVariance(){} 0078 0079 // Return the gain in separation of the original sample is split in two sub-samples 0080 // (N * Index_parent) - (N_left * Index_left) - (N_right * Index_right) 0081 Double_t GetSeparationGain( const Double_t nLeft, const Double_t targetLeft, const Double_t target2Left, 0082 const Double_t nTot, const Double_t targetTot, const Double_t target2Tot ); 0083 0084 // Return the separation index (a measure for "purity" of the sample") 0085 virtual Double_t GetSeparationIndex( const Double_t n, const Double_t target, const Double_t target2 ); 0086 0087 // Return the name of the concrete Index implementation 0088 TString GetName() { return fName; } 0089 0090 protected: 0091 0092 TString fName; ///< name of the concrete Separation Index implementation 0093 0094 ClassDef(RegressionVariance,0); // Interface to different separation criteria used in training algorithms 0095 }; 0096 0097 0098 } // namespace TMVA 0099 0100 #endif
| [ Source navigation ] | [ Diff markup ] | [ Identifier search ] | [ general search ] |
|
This page was automatically generated by the 2.3.7 LXR engine. The LXR team |
|