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

Pass pointer to model parameters. (#5101)

Browse Source 
* Pass pointer to model parameters.

This PR de-duplicates most of the model parameters except the one in
`tree_model.h`.  One difficulty is `base_score` is a model property but can be
changed at runtime by objective function.  Hence when performing model IO, we
need to save the one provided by users, instead of the one transformed by
objective.  Here we created an immutable version of `LearnerModelParam` that
represents the value of model parameter after configuration.
This commit is contained in:
Jiaming Yuan
2019-12-10 12:11:22 +08:00
committed by GitHub
parent 979f74d51a
commit e089e16e3d
33 changed files with 623 additions and 404 deletions
Download Patch File Download Diff File Expand all files Collapse all files

78
tests/cpp/predictor/test_cpu_predictor.cc
View File

@@ -7,18 +7,23 @@
#include "../../../src/gbm/gbtree_model.h"
namespace xgboost {
TEST(cpu_predictor, Test) {
TEST(CpuPredictor, Basic) {
auto lparam = CreateEmptyGenericParam(GPUIDX);
auto cache = std::make_shared<std::unordered_map<DMatrix*, PredictionCacheEntry>>();
std::unique_ptr<Predictor> cpu_predictor =
std::unique_ptr<Predictor>(Predictor::Create("cpu_predictor", &lparam, cache));
gbm::GBTreeModel model = CreateTestModel();
int kRows = 5;
int kCols = 5;
int n_row = 5;
int n_col = 5;
LearnerModelParam param;
param.num_feature = kCols;
param.base_score = 0.0;
param.num_output_group = 1;
auto dmat = CreateDMatrix(n_row, n_col, 0);
gbm::GBTreeModel model = CreateTestModel(&param);
auto dmat = CreateDMatrix(kRows, kCols, 0);
// Test predict batch
HostDeviceVector<float> out_predictions;
@@ -46,19 +51,32 @@ TEST(cpu_predictor, Test) {
// Test predict contribution
std::vector<float> out_contribution;
cpu_predictor->PredictContribution((*dmat).get(), &out_contribution, model);
for (auto const& contri : out_contribution) {
ASSERT_EQ(contri, 1.5);
ASSERT_EQ(out_contribution.size(), kRows * (kCols + 1));
for (size_t i = 0; i < out_contribution.size(); ++i) {
auto const& contri = out_contribution[i];
// shift 1 for bias, as test tree is a decision dump, only global bias is filled with LeafValue().
if ((i+1) % (kCols+1) == 0) {
ASSERT_EQ(out_contribution.back(), 1.5f);
} else {
ASSERT_EQ(contri, 0);
}
}
// Test predict contribution (approximate method)
cpu_predictor->PredictContribution((*dmat).get(), &out_contribution, model, true);
for (auto const& contri : out_contribution) {
ASSERT_EQ(contri, 1.5);
cpu_predictor->PredictContribution((*dmat).get(), &out_contribution, model, 0, nullptr, true);
for (size_t i = 0; i < out_contribution.size(); ++i) {
auto const& contri = out_contribution[i];
// shift 1 for bias, as test tree is a decision dump, only global bias is filled with LeafValue().
if ((i+1) % (kCols+1) == 0) {
ASSERT_EQ(out_contribution.back(), 1.5f);
} else {
ASSERT_EQ(contri, 0);
}
}
delete dmat;
}
TEST(cpu_predictor, ExternalMemoryTest) {
TEST(CpuPredictor, ExternalMemory) {
dmlc::TemporaryDirectory tmpdir;
std::string filename = tmpdir.path + "/big.libsvm";
std::unique_ptr<DMatrix> dmat = CreateSparsePageDMatrix(12, 64, filename);
@@ -68,13 +86,18 @@ TEST(cpu_predictor, ExternalMemoryTest) {
std::unique_ptr<Predictor> cpu_predictor =
std::unique_ptr<Predictor>(Predictor::Create("cpu_predictor", &lparam, cache));
gbm::GBTreeModel model = CreateTestModel();
LearnerModelParam param;
param.base_score = 0;
param.num_feature = dmat->Info().num_col_;
param.num_output_group = 1;
gbm::GBTreeModel model = CreateTestModel(&param);
// Test predict batch
HostDeviceVector<float> out_predictions;
cpu_predictor->PredictBatch(dmat.get(), &out_predictions, model, 0);
std::vector<float> &out_predictions_h = out_predictions.HostVector();
EXPECT_EQ(out_predictions.Size(), dmat->Info().num_row_);
ASSERT_EQ(out_predictions.Size(), dmat->Info().num_row_);
for (const auto& v : out_predictions_h) {
ASSERT_EQ(v, 1.5);
}
@@ -82,7 +105,7 @@ TEST(cpu_predictor, ExternalMemoryTest) {
// Test predict leaf
std::vector<float> leaf_out_predictions;
cpu_predictor->PredictLeaf(dmat.get(), &leaf_out_predictions, model);
EXPECT_EQ(leaf_out_predictions.size(), dmat->Info().num_row_);
ASSERT_EQ(leaf_out_predictions.size(), dmat->Info().num_row_);
for (const auto& v : leaf_out_predictions) {
ASSERT_EQ(v, 0);
}
@@ -90,17 +113,30 @@ TEST(cpu_predictor, ExternalMemoryTest) {
// Test predict contribution
std::vector<float> out_contribution;
cpu_predictor->PredictContribution(dmat.get(), &out_contribution, model);
EXPECT_EQ(out_contribution.size(), dmat->Info().num_row_);
for (const auto& v : out_contribution) {
ASSERT_EQ(v, 1.5);
ASSERT_EQ(out_contribution.size(), dmat->Info().num_row_ * (dmat->Info().num_col_ + 1));
for (size_t i = 0; i < out_contribution.size(); ++i) {
auto const& contri = out_contribution[i];
// shift 1 for bias, as test tree is a decision dump, only global bias is filled with LeafValue().
if ((i + 1) % (dmat->Info().num_col_ + 1) == 0) {
ASSERT_EQ(out_contribution.back(), 1.5f);
} else {
ASSERT_EQ(contri, 0);
}
}
// Test predict contribution (approximate method)
std::vector<float> out_contribution_approximate;
cpu_predictor->PredictContribution(dmat.get(), &out_contribution_approximate, model, true);
EXPECT_EQ(out_contribution_approximate.size(), dmat->Info().num_row_);
for (const auto& v : out_contribution_approximate) {
ASSERT_EQ(v, 1.5);
cpu_predictor->PredictContribution(dmat.get(), &out_contribution_approximate, model, 0, nullptr, true);
ASSERT_EQ(out_contribution_approximate.size(),
dmat->Info().num_row_ * (dmat->Info().num_col_ + 1));
for (size_t i = 0; i < out_contribution.size(); ++i) {
auto const& contri = out_contribution[i];
// shift 1 for bias, as test tree is a decision dump, only global bias is filled with LeafValue().
if ((i + 1) % (dmat->Info().num_col_ + 1) == 0) {
ASSERT_EQ(out_contribution.back(), 1.5f);
} else {
ASSERT_EQ(contri, 0);
}
}
}
} // namespace xgboost