Impala Documentation

virtual void Impala::Core::Training::TrainDataSrc::FilterTrainFold	(	int	f,
		int	foldCount,
		int	repetition,
		bool	episodeConstrained
	)			`[inline, virtual]`

Definition at line 104 of file TrainDataSrc.h.

References Impala::Core::Table::TableTem< Col1T, Col2T, Col3T, Col4T, Col5T, Col6T, Col7T, Col8T, Col9T >::Append(), MakeFolds(), mSelection, and Impala::Core::Table::Table::Size().

Referenced by Impala::Core::Training::ClassifierEvaluator::Evaluate(), and Impala::Core::Training::Tester::FirstFoldInv().

00105     {
00106         std::vector<Table::QuidTable*> folds =
00107             MakeFolds(f, foldCount, repetition, episodeConstrained);
00108         mSelection = new Table::QuidTable(0);
00109         ILOG_DEBUG_NODE("selection size = "<<mSelection->Size()<<")");
00110         for(int i=0 ; i<folds.size() ; ++i)
00111         {
00112             if(f != i)
00113             {
00114                 mSelection->Append(folds[i]);
00115             }
00116             delete folds[i];
00117         }
00118     }

Here is the call graph for this function: