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

Use Predictor for dart. (#6693)

Browse Source 
* Use normal predictor for dart booster.
* Implement `inplace_predict` for dart.
* Enable `dart` for dask interface now that it's thread-safe.
* categorical data should be working out of box for dart now.

The implementation is not very efficient as it has to pull back the data and
apply weight for each tree, but still a significant improvement over previous
implementation as now we no longer binary search for each sample.

* Fix output prediction shape on dataframe.
This commit is contained in:
Jiaming Yuan
2021-02-09 23:30:19 +08:00
committed by GitHub
parent dbf7e9d3cb
commit e8c5c53e2f
13 changed files with 246 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -31,6 +31,7 @@ TEST(CpuPredictor, Basic) {
// Test predict batch
PredictionCacheEntry out_predictions;
cpu_predictor->InitOutPredictions(dmat->Info(), &out_predictions.predictions, model);
cpu_predictor->PredictBatch(dmat.get(), &out_predictions, model, 0);
std::vector<float>& out_predictions_h = out_predictions.predictions.HostVector();
@@ -107,6 +108,7 @@ TEST(CpuPredictor, ExternalMemory) {
// Test predict batch
PredictionCacheEntry out_predictions;
cpu_predictor->InitOutPredictions(dmat->Info(), &out_predictions.predictions, model);
cpu_predictor->PredictBatch(dmat.get(), &out_predictions, model, 0);
std::vector<float> &out_predictions_h = out_predictions.predictions.HostVector();
ASSERT_EQ(out_predictions.predictions.Size(), dmat->Info().num_row_);

3
tests/cpp/predictor/test_gpu_predictor.cu
View File

@@ -44,7 +44,9 @@ TEST(GPUPredictor, Basic) {
PredictionCacheEntry gpu_out_predictions;
PredictionCacheEntry cpu_out_predictions;
gpu_predictor->InitOutPredictions(dmat->Info(), &gpu_out_predictions.predictions, model);
gpu_predictor->PredictBatch(dmat.get(), &gpu_out_predictions, model, 0);
cpu_predictor->InitOutPredictions(dmat->Info(), &cpu_out_predictions.predictions, model);
cpu_predictor->PredictBatch(dmat.get(), &cpu_out_predictions, model, 0);
std::vector<float>& gpu_out_predictions_h = gpu_out_predictions.predictions.HostVector();
@@ -111,6 +113,7 @@ TEST(GPUPredictor, ExternalMemoryTest) {
for (const auto& dmat: dmats) {
dmat->Info().base_margin_.Resize(dmat->Info().num_row_ * n_classes, 0.5);
PredictionCacheEntry out_predictions;
gpu_predictor->InitOutPredictions(dmat->Info(), &out_predictions.predictions, model);
gpu_predictor->PredictBatch(dmat.get(), &out_predictions, model, 0);
EXPECT_EQ(out_predictions.predictions.Size(), dmat->Info().num_row_ * n_classes);
const std::vector<float> &host_vector = out_predictions.predictions.ConstHostVector();

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

@@ -218,6 +218,7 @@ void TestCategoricalPrediction(std::string name) {
row[split_ind] = split_cat;
auto m = GetDMatrixFromData(row, 1, kCols);
predictor->InitOutPredictions(m->Info(), &out_predictions.predictions, model);
predictor->PredictBatch(m.get(), &out_predictions, model, 0);
ASSERT_EQ(out_predictions.predictions.Size(), 1ul);
ASSERT_EQ(out_predictions.predictions.HostVector()[0],
@@ -226,6 +227,7 @@ void TestCategoricalPrediction(std::string name) {
row[split_ind] = split_cat + 1;
m = GetDMatrixFromData(row, 1, kCols);
out_predictions.version = 0;
predictor->InitOutPredictions(m->Info(), &out_predictions.predictions, model);
predictor->PredictBatch(m.get(), &out_predictions, model, 0);
ASSERT_EQ(out_predictions.predictions.HostVector()[0],
left_weight + param.base_score);

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

@@ -29,9 +29,11 @@ void TestPredictionFromGradientIndex(std::string name, size_t rows, size_t cols,
auto p_precise = RandomDataGenerator(rows, cols, 0).GenerateDMatrix();
PredictionCacheEntry approx_out_predictions;
predictor->InitOutPredictions(p_hist->Info(), &approx_out_predictions.predictions, model);
predictor->PredictBatch(p_hist.get(), &approx_out_predictions, model, 0);
PredictionCacheEntry precise_out_predictions;
predictor->InitOutPredictions(p_precise->Info(), &precise_out_predictions.predictions, model);
predictor->PredictBatch(p_precise.get(), &precise_out_predictions, model, 0);
for (size_t i = 0; i < rows; ++i) {
@@ -46,6 +48,7 @@ void TestPredictionFromGradientIndex(std::string name, size_t rows, size_t cols,
// matrix is used for training.
auto p_dmat = RandomDataGenerator(rows, cols, 0).GenerateDMatrix();
PredictionCacheEntry precise_out_predictions;
predictor->InitOutPredictions(p_dmat->Info(), &precise_out_predictions.predictions, model);
predictor->PredictBatch(p_dmat.get(), &precise_out_predictions, model, 0);
ASSERT_FALSE(p_dmat->PageExists<Page>());
}