/usr/include/root/TMVA/DataSetFactory.h is in libroot-tmva-dev 5.34.30-0ubuntu8.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 | // @(#)root/tmva $Id$
// Author: Andreas Hoecker, Peter Speckmayer, Joerg Stelzer, Eckhard von Toerne, Helge Voss
/**********************************************************************************
* Project: TMVA - a Root-integrated toolkit for multivariate data analysis *
* Package: TMVA *
* Class : DataSetFactory *
* Web : http://tmva.sourceforge.net *
* *
* Description: *
* Contains all the data information *
* *
* Authors (alphabetical): *
* Andreas Hoecker <Andreas.Hocker@cern.ch> - CERN, Switzerland *
* Joerg Stelzer <Joerg.Stelzer@cern.ch> - CERN, Switzerland *
* Peter Speckmayer <Peter.Speckmayer@cern.ch> - CERN, Switzerland *
* Eckhard von Toerne <evt@physik.uni-bonn.de> - U. of Bonn, Germany *
* Helge Voss <Helge.Voss@cern.ch> - MPI-K Heidelberg, Germany *
* *
* Copyright (c) 2006: *
* CERN, Switzerland *
* MPI-K Heidelberg, Germany *
* *
* Redistribution and use in source and binary forms, with or without *
* modification, are permitted according to the terms listed in LICENSE *
* (http://tmva.sourceforge.net/LICENSE) *
**********************************************************************************/
#ifndef ROOT_TMVA_DataSetFactory
#define ROOT_TMVA_DataSetFactory
//////////////////////////////////////////////////////////////////////////
// //
// DataSetFactory //
// //
// Class that contains all the data information //
// //
//////////////////////////////////////////////////////////////////////////
#include <vector>
#include <stdlib.h>
#ifndef ROOT_TString
#include "TString.h"
#endif
#ifndef ROOT_TTree
#include "TTree.h"
#endif
#ifndef ROOT_TCut
#include "TCut.h"
#endif
#ifndef ROOT_TTreeFormula
#include "TTreeFormula.h"
#endif
#ifndef ROOT_TMatrixDfwd
#include "TMatrixDfwd.h"
#endif
#ifndef ROOT_TPrincipal
#include "TPrincipal.h"
#endif
#ifndef ROOT_TRandom3
#include "TRandom3.h"
#endif
#ifndef ROOT_TMVA_Types
#include "TMVA/Types.h"
#endif
#ifndef ROOT_TMVA_VariableInfo
#include "TMVA/VariableInfo.h"
#endif
#ifndef ROOT_TMVA_Event
#include "TMVA/Event.h"
#endif
namespace TMVA {
class DataSet;
class DataSetInfo;
class DataInputHandler;
class TreeInfo;
class MsgLogger;
// =============== maybe move these elswhere (e.g. into the tools )
// =============== functors =======================
class RandomGenerator {
public:
RandomGenerator( UInt_t seed ){
fRandom.SetSeed( seed );
}
UInt_t operator() ( UInt_t n ) {
return fRandom.Integer(n);
}
private:
TRandom3 fRandom; // random generator
};
// delete-functor (to be used in e.g. for_each algorithm)
template<class T>
struct DeleteFunctor_t
{
DeleteFunctor_t& operator()(const T* p) {
delete p;
return *this;
}
};
template<class T>
DeleteFunctor_t<const T> DeleteFunctor()
{
return DeleteFunctor_t<const T>();
}
template< typename T >
class Increment {
T value;
public:
Increment( T start ) : value( start ){ }
T operator()() {
return value++;
}
};
template <typename F>
class null_t
{
private:
// returns argF
public:
typedef F argument_type;
F operator()(const F& argF) const
{
return argF;
}
};
template <typename F>
inline null_t<F> null() {
return null_t<F>();
}
template <typename F, typename G, typename H>
class compose_binary_t : public std::binary_function<typename G::argument_type,
typename H::argument_type,
typename F::result_type>
{
private:
const F& f; // f(g(argG),h(argH))
const G& g;
const H& h;
public:
compose_binary_t(const F& _f, const G& _g, const H& _h) : f(_f), g(_g), h(_h)
{
}
typename F::result_type operator()(const typename G::argument_type& argG,
const typename H::argument_type& argH) const
{
return f(g(argG),h(argH));
}
};
template <typename F, typename G, typename H>
inline compose_binary_t<F,G,H> compose_binary(const F& _f, const G& _g, const H& _h) {
return compose_binary_t<F,G,H>(_f,_g,_h);
}
template <typename F, typename G>
class compose_unary_t : public std::unary_function<typename G::argument_type,
typename F::result_type>
{
private:
const F& f; // f(g(argG))
const G& g;
public:
compose_unary_t(const F& _f, const G& _g) : f(_f), g(_g)
{
}
typename F::result_type operator()(const typename G::argument_type& argG) const
{
return f(g(argG));
}
};
template <typename F, typename G>
inline compose_unary_t<F,G> compose_unary(const F& _f, const G& _g) {
return compose_unary_t<F,G>(_f,_g);
}
// =============== functors =======================
// =========================================================
class DataSetFactory {
typedef std::vector<Event* > EventVector;
typedef std::vector< EventVector > EventVectorOfClasses;
typedef std::map<Types::ETreeType, EventVectorOfClasses > EventVectorOfClassesOfTreeType;
typedef std::map<Types::ETreeType, EventVector > EventVectorOfTreeType;
typedef std::vector< Double_t > ValuePerClass;
typedef std::map<Types::ETreeType, ValuePerClass > ValuePerClassOfTreeType;
class EventStats {
public:
Int_t nTrainingEventsRequested;
Int_t nTestingEventsRequested;
Int_t nInitialEvents;
Int_t nEvBeforeCut;
Int_t nEvAfterCut;
Float_t nWeEvBeforeCut;
Float_t nWeEvAfterCut;
Double_t nNegWeights;
Float_t* varAvLength;
EventStats():
nTrainingEventsRequested(0),
nTestingEventsRequested(0),
nInitialEvents(0),
nEvBeforeCut(0),
nEvAfterCut(0),
nWeEvBeforeCut(0),
nWeEvAfterCut(0),
nNegWeights(0),
varAvLength(0)
{}
~EventStats() { delete[] varAvLength; }
Float_t cutScaling() const { return Float_t(nEvAfterCut)/nEvBeforeCut; }
};
typedef std::vector< int > NumberPerClass;
typedef std::vector< EventStats > EvtStatsPerClass;
public:
// singleton class
static DataSetFactory& Instance() { if (!fgInstance) fgInstance = new DataSetFactory(); return *fgInstance; }
static void destroyInstance() { if (fgInstance) { delete fgInstance; fgInstance=0; } }
DataSet* CreateDataSet( DataSetInfo &, DataInputHandler& );
protected:
~DataSetFactory();
DataSetFactory();
static DataSetFactory *fgInstance;
DataSet* BuildInitialDataSet( DataSetInfo&, TMVA::DataInputHandler& );
DataSet* BuildDynamicDataSet( DataSetInfo& );
// ---------- new versions
void BuildEventVector ( DataSetInfo& dsi,
DataInputHandler& dataInput,
EventVectorOfClassesOfTreeType& eventsmap,
EvtStatsPerClass& eventCounts);
DataSet* MixEvents ( DataSetInfo& dsi,
EventVectorOfClassesOfTreeType& eventsmap,
EvtStatsPerClass& eventCounts,
const TString& splitMode,
const TString& mixMode,
const TString& normMode,
UInt_t splitSeed);
void RenormEvents ( DataSetInfo& dsi,
EventVectorOfClassesOfTreeType& eventsmap,
const EvtStatsPerClass& eventCounts,
const TString& normMode );
void InitOptions ( DataSetInfo& dsi,
EvtStatsPerClass& eventsmap,
TString& normMode, UInt_t& splitSeed,
TString& splitMode, TString& mixMode );
// ------------------------
// auxiliary functions to compute correlations
TMatrixD* CalcCorrelationMatrix( DataSet*, const UInt_t classNumber );
TMatrixD* CalcCovarianceMatrix ( DataSet*, const UInt_t classNumber );
void CalcMinMax ( DataSet*, DataSetInfo& dsi );
// resets branch addresses to current event
void ResetBranchAndEventAddresses( TTree* );
void ResetCurrentTree() { fCurrentTree = 0; }
void ChangeToNewTree( TreeInfo&, const DataSetInfo & );
Bool_t CheckTTreeFormula( TTreeFormula* ttf, const TString& expression, Bool_t& hasDollar );
// verbosity
Bool_t Verbose() { return fVerbose; }
// data members
// verbosity
Bool_t fVerbose; //! Verbosity
TString fVerboseLevel; //! VerboseLevel
Bool_t fScaleWithPreselEff; //! how to deal with requested #events in connection with preselection cuts
// the event
mutable TTree* fCurrentTree; //! the tree, events are currently read from
mutable UInt_t fCurrentEvtIdx; //! the current event (to avoid reading of the same event)
// the formulas for reading the original tree
std::vector<TTreeFormula*> fInputFormulas; //! input variables
std::vector<TTreeFormula*> fTargetFormulas; //! targets
std::vector<TTreeFormula*> fCutFormulas; //! cuts
std::vector<TTreeFormula*> fWeightFormula; //! weights
std::vector<TTreeFormula*> fSpectatorFormulas; //! spectators
mutable MsgLogger* fLogger; //! message logger
MsgLogger& Log() const { return *fLogger; }
};
}
#endif
|