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

[breaking] Add prediction fucntion for DMatrix and use inplace predict for dask. (#6668)

Browse Source 
* Add a new API function for predicting on `DMatrix`.  This function aligns
with rest of the `XGBoosterPredictFrom*` functions on semantic of function
arguments.
* Purge `ntree_limit` from libxgboost, use iteration instead.
* [dask] Use `inplace_predict` by default for dask sklearn models.
* [dask] Run prediction shape inference on worker instead of client.

The breaking change is in the Python sklearn `apply` function, I made it to be
consistent with other prediction functions where `best_iteration` is used by
default.
This commit is contained in:
Jiaming Yuan
2021-02-08 18:26:32 +08:00
committed by GitHub
parent dbb5208a0a
commit 4656b09d5d
29 changed files with 1134 additions and 604 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/cpp/predictor/test_cpu_predictor.cc
View File

@@ -32,7 +32,7 @@ TEST(CpuPredictor, Basic) {
// Test predict batch
PredictionCacheEntry out_predictions;
cpu_predictor->PredictBatch(dmat.get(), &out_predictions, model, 0);
ASSERT_EQ(model.trees.size(), out_predictions.version);
std::vector<float>& out_predictions_h = out_predictions.predictions.HostVector();
for (size_t i = 0; i < out_predictions.predictions.Size(); i++) {
ASSERT_EQ(out_predictions_h[i], 1.5);
@@ -215,7 +215,7 @@ TEST(CpuPredictor, UpdatePredictionCache) {
PredictionCacheEntry out_predictions;
// perform fair prediction on the same input data, should be equal to cached result
gbm->PredictBatch(dmat.get(), &out_predictions, false, 0);
gbm->PredictBatch(dmat.get(), &out_predictions, false, 0, 0);
std::vector<float> &out_predictions_h = out_predictions.predictions.HostVector();
std::vector<float> &predtion_cache_from_train = predtion_cache.predictions.HostVector();

1
tests/cpp/predictor/test_gpu_predictor.cu
View File

@@ -45,7 +45,6 @@ TEST(GPUPredictor, Basic) {
PredictionCacheEntry cpu_out_predictions;
gpu_predictor->PredictBatch(dmat.get(), &gpu_out_predictions, model, 0);
ASSERT_EQ(model.trees.size(), gpu_out_predictions.version);
cpu_predictor->PredictBatch(dmat.get(), &cpu_out_predictions, model, 0);
std::vector<float>& gpu_out_predictions_h = gpu_out_predictions.predictions.HostVector();

12
tests/cpp/predictor/test_predictor.cc
View File

@@ -64,10 +64,10 @@ void TestTrainingPrediction(size_t rows, size_t bins,
}
HostDeviceVector<float> from_full;
learner->Predict(p_full, false, &from_full);
learner->Predict(p_full, false, &from_full, 0, 0);
HostDeviceVector<float> from_hist;
learner->Predict(p_hist, false, &from_hist);
learner->Predict(p_hist, false, &from_hist, 0, 0);
for (size_t i = 0; i < rows; ++i) {
EXPECT_NEAR(from_hist.ConstHostVector()[i],
@@ -157,20 +157,20 @@ void TestPredictionWithLesserFeatures(std::string predictor_name) {
learner->SaveConfig(&config);
ASSERT_EQ(get<String>(config["learner"]["gradient_booster"]["gbtree_train_param"]["predictor"]), predictor_name);
learner->Predict(m_test, false, &prediction);
learner->Predict(m_test, false, &prediction, 0, 0);
ASSERT_EQ(prediction.Size(), kRows);
auto m_invalid = RandomDataGenerator(kRows, kTrainCols + 1, 0.5).GenerateDMatrix(false);
ASSERT_THROW({learner->Predict(m_invalid, false, &prediction);}, dmlc::Error);
ASSERT_THROW({learner->Predict(m_invalid, false, &prediction, 0, 0);}, dmlc::Error);
#if defined(XGBOOST_USE_CUDA)
HostDeviceVector<float> from_cpu;
learner->SetParam("predictor", "cpu_predictor");
learner->Predict(m_test, false, &from_cpu);
learner->Predict(m_test, false, &from_cpu, 0, 0);
HostDeviceVector<float> from_cuda;
learner->SetParam("predictor", "gpu_predictor");
learner->Predict(m_test, false, &from_cuda);
learner->Predict(m_test, false, &from_cuda, 0, 0);
auto const& h_cpu = from_cpu.ConstHostVector();
auto const& h_gpu = from_cuda.ConstHostVector();