makes a historgram of the values found in the second column of data (the column with the 'class id') considering the filter.
Definition at line 52 of file MakeRandomTree.h. References Impala::Core::Histogram::Histogram1dTem< ElemT >::AddWeight(), Impala::Core::Table::TableTem< Col1T, Col2T, Col3T, Col4T, Col5T, Col6T, Col7T, Col8T, Col9T >::Get2(), Impala::Core::Table::TableTem< Col1T, Col2T, Col3T, Col4T, Col5T, Col6T, Col7T, Col8T, Col9T >::GetInfo(), and Impala::Core::Table::Table::Size(). Referenced by Gain(), and Impala::Core::Feature::TestMakeRandomTree::testMakeHistogram(). 00053 { 00054 int outLyers; 00055 Histogram::Histogram1dTem<int>* hist = 00056 new Histogram::Histogram1dTem<int>(-0.5, nrClasses+0.5, nrClasses, 00057 &outLyers); 00058 String a=data->GetInfo(); 00059 for(int y=0 ; y<data->Size() ; ++y) 00060 if(filter[y]) 00061 hist->AddWeight(data->Get2(y), 1.); 00062 return hist; 00063 }
Here is the call graph for this function:
|