Support categorical data in ellpack. (#6140)

This commit is contained in:
Jiaming Yuan
2020-09-24 19:28:57 +08:00
committed by GitHub
parent 78d72ef936
commit 14afdb4d92
9 changed files with 189 additions and 43 deletions

View File

@@ -17,6 +17,7 @@
#include "helpers.h"
#include "xgboost/c_api.h"
#include "../../src/data/adapter.h"
#include "../../src/data/simple_dmatrix.h"
#include "../../src/gbm/gbtree_model.h"
#include "xgboost/predictor.h"
@@ -350,6 +351,13 @@ RandomDataGenerator::GenerateDMatrix(bool with_label, bool float_label,
return out;
}
std::shared_ptr<DMatrix>
GetDMatrixFromData(const std::vector<float> &x, int num_rows, int num_columns){
data::DenseAdapter adapter(x.data(), num_rows, num_columns);
return std::shared_ptr<DMatrix>(new data::SimpleDMatrix(
&adapter, std::numeric_limits<float>::quiet_NaN(), 1));
}
std::unique_ptr<DMatrix> CreateSparsePageDMatrix(
size_t n_entries, size_t page_size, std::string tmp_file) {
// Create sufficiently large data to make two row pages
@@ -539,5 +547,4 @@ RMMAllocatorPtr SetUpRMMResourceForCppTests(int argc, char** argv) {
return RMMAllocatorPtr(nullptr, DeleteRMMResource);
}
#endif // !defined(XGBOOST_USE_RMM) || XGBOOST_USE_RMM != 1
} // namespace xgboost