Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Support categorical data for dask functional interface and DQM. (#7043)

Browse Source 
* Support categorical data for dask functional interface and DQM.

* Implement categorical data support for GPU GK-merge.
* Add support for dask functional interface.
* Add support for DQM.

* Get newer cupy.
This commit is contained in:
Jiaming Yuan
2021-06-18 13:06:52 +08:00
committed by GitHub
parent 7dd29ffd47
commit 86715e4cd4
16 changed files with 364 additions and 167 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
tests/cpp/data/test_iterative_device_dmatrix.cu
View File

@@ -68,7 +68,16 @@ void TestEquivalent(float sparsity) {
auto const& buffer_from_iter = page_concatenated->gidx_buffer;
auto const& buffer_from_data = ellpack.Impl()->gidx_buffer;
ASSERT_NE(buffer_from_data.Size(), 0);
ASSERT_EQ(buffer_from_data.ConstHostVector(), buffer_from_data.ConstHostVector());
common::CompressedIterator<uint32_t> data_buf{
buffer_from_data.ConstHostPointer(), from_data.NumSymbols()};
common::CompressedIterator<uint32_t> data_iter{
buffer_from_iter.ConstHostPointer(), from_iter.NumSymbols()};
CHECK_EQ(from_data.NumSymbols(), from_iter.NumSymbols());
CHECK_EQ(from_data.n_rows * from_data.row_stride, from_data.n_rows * from_iter.row_stride);
for (size_t i = 0; i < from_data.n_rows * from_data.row_stride; ++i) {
CHECK_EQ(data_buf[i], data_iter[i]);
}
}
}

3
tests/cpp/predictor/test_predictor.cc
View File

@@ -225,6 +225,9 @@ void TestCategoricalPrediction(std::string name) {
row[split_ind] = split_cat;
auto m = GetDMatrixFromData(row, 1, kCols);
std::vector<FeatureType> types(10, FeatureType::kCategorical);
m->Info().feature_types.HostVector() = types;
predictor->InitOutPredictions(m->Info(), &out_predictions.predictions, model);
predictor->PredictBatch(m.get(), &out_predictions, model, 0);
ASSERT_EQ(out_predictions.predictions.Size(), 1ul);