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

Dmatrix refactor stage 1 (#3301)

Browse Source 
* Use sparse page as singular CSR matrix representation

* Simplify dmatrix methods

* Reduce statefullness of batch iterators

* BREAKING CHANGE: Remove prob_buffer_row parameter. Users are instead recommended to sample their dataset as a preprocessing step before using XGBoost.
This commit is contained in:
Rory Mitchell
2018-06-07 10:25:58 +12:00
committed by GitHub
parent 286dccb8e8
commit a96039141a
47 changed files with 650 additions and 1036 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/cpp/predictor/test_cpu_predictor.cc
View File

@@ -33,7 +33,7 @@ TEST(cpu_predictor, Test) {
// Test predict instance
auto batch = dmat->RowIterator()->Value();
for (int i = 0; i < batch.size; i++) {
for (int i = 0; i < batch.Size(); i++) {
std::vector<float> instance_out_predictions;
cpu_predictor->PredictInstance(batch[i], &instance_out_predictions, model);
ASSERT_EQ(instance_out_predictions[0], 1.5);

2
tests/cpp/predictor/test_gpu_predictor.cu
View File

@@ -46,7 +46,7 @@ TEST(gpu_predictor, Test) {
}
// Test predict instance
auto batch = dmat->RowIterator()->Value();
for (int i = 0; i < batch.size; i++) {
for (int i = 0; i < batch.Size(); i++) {
std::vector<float> gpu_instance_out_predictions;
std::vector<float> cpu_instance_out_predictions;
cpu_predictor->PredictInstance(batch[i], &cpu_instance_out_predictions,