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

merge latest changes

Browse Source
This commit is contained in:
amdsc21
2023-03-10 22:10:20 +01:00
parent 5e8b1842b9 2aa838c75e
commit f0b8c02f15
57 changed files with 1435 additions and 592 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/buildkite/build-cuda-with-rmm.sh
View File

@@ -20,7 +20,7 @@ command_wrapper="tests/ci_build/ci_build.sh rmm docker --build-arg "`
echo "--- Build libxgboost from the source"
$command_wrapper tests/ci_build/build_via_cmake.sh --conda-env=gpu_test -DUSE_CUDA=ON \
-DUSE_NCCL=ON -DPLUGIN_RMM=ON -DBUILD_WITH_CUDA_CUB=ON ${arch_flag}
-DUSE_NCCL=ON -DPLUGIN_RMM=ON ${arch_flag}
echo "-- Stash C++ test executable (testxgboost)"
buildkite-agent artifact upload build/testxgboost

57
tests/cpp/common/test_ranking_utils.cc
View File

@@ -1,38 +1,69 @@
/**
* Copyright 2023 by XGBoost Contributors
*/
#include <gtest/gtest.h>
#include <gtest/gtest.h> // for Test, AssertionResult, Message, TestPartR...
#include <gtest/gtest.h> // for ASSERT_NEAR, ASSERT_T...
#include <xgboost/base.h> // for Args
#include <xgboost/context.h> // for Context
#include <xgboost/string_view.h> // for StringView
#include <cstdint> // std::uint32_t
#include <cstdint> // for uint32_t
#include <utility> // for pair
#include "../../../src/common/ranking_utils.h"
#include "../../../src/common/ranking_utils.h" // for LambdaRankParam, ParseMetricName, MakeMet...
namespace xgboost {
namespace ltr {
TEST(RankingUtils, MakeMetricName) {
namespace xgboost::ltr {
TEST(RankingUtils, LambdaRankParam) {
// make sure no memory is shared in dmlc parameter.
LambdaRankParam p0;
p0.UpdateAllowUnknown(Args{{"lambdarank_num_pair_per_sample", "3"}});
ASSERT_EQ(p0.NumPair(), 3);
LambdaRankParam p1;
p1.UpdateAllowUnknown(Args{{"lambdarank_num_pair_per_sample", "8"}});
ASSERT_EQ(p0.NumPair(), 3);
ASSERT_EQ(p1.NumPair(), 8);
p0.UpdateAllowUnknown(Args{{"lambdarank_num_pair_per_sample", "17"}});
ASSERT_EQ(p0.NumPair(), 17);
ASSERT_EQ(p1.NumPair(), 8);
}
TEST(RankingUtils, ParseMetricName) {
std::uint32_t topn{32};
bool minus{false};
auto name = MakeMetricName("ndcg", "3-", &topn, &minus);
auto name = ParseMetricName("ndcg", "3-", &topn, &minus);
ASSERT_EQ(name, "ndcg@3-");
ASSERT_EQ(topn, 3);
ASSERT_TRUE(minus);
name = MakeMetricName("ndcg", "6", &topn, &minus);
name = ParseMetricName("ndcg", "6", &topn, &minus);
ASSERT_EQ(topn, 6);
ASSERT_TRUE(minus); // unchanged
minus = false;
name = MakeMetricName("ndcg", "-", &topn, &minus);
name = ParseMetricName("ndcg", "-", &topn, &minus);
ASSERT_EQ(topn, 6); // unchanged
ASSERT_TRUE(minus);
name = MakeMetricName("ndcg", nullptr, &topn, &minus);
name = ParseMetricName("ndcg", nullptr, &topn, &minus);
ASSERT_EQ(topn, 6); // unchanged
ASSERT_TRUE(minus); // unchanged
name = MakeMetricName("ndcg", StringView{}, &topn, &minus);
name = ParseMetricName("ndcg", StringView{}, &topn, &minus);
ASSERT_EQ(topn, 6); // unchanged
ASSERT_TRUE(minus); // unchanged
}
} // namespace ltr
} // namespace xgboost
TEST(RankingUtils, MakeMetricName) {
auto name = MakeMetricName("map", LambdaRankParam::NotSet(), true);
ASSERT_EQ(name, "map-");
name = MakeMetricName("map", LambdaRankParam::NotSet(), false);
ASSERT_EQ(name, "map");
name = MakeMetricName("map", 2, true);
ASSERT_EQ(name, "map@2-");
name = MakeMetricName("map", 2, false);
ASSERT_EQ(name, "map@2");
}
} // namespace xgboost::ltr

3
tests/cpp/helpers.h
View File

@@ -24,6 +24,7 @@
#include "../../src/data/array_interface.h"
#include "../../src/gbm/gbtree_model.h"
#include "filesystem.h" // dmlc::TemporaryDirectory
#include "xgboost/linalg.h"
#if defined(__CUDACC__)
#define DeclareUnifiedTest(name) GPU ## name
@@ -461,7 +462,7 @@ inline LearnerModelParam MakeMP(bst_feature_t n_features, float base_score, uint
int32_t device = Context::kCpuId) {
size_t shape[1]{1};
LearnerModelParam mparam(n_features, linalg::Tensor<float, 1>{{base_score}, shape, device},
n_groups);
n_groups, 1, MultiStrategy::kComposite);
return mparam;
}

42
tests/cpp/test_multi_target.cc
View File

@@ -2,24 +2,26 @@
* Copyright 2023 by XGBoost Contributors
*/
#include <gtest/gtest.h>
#include <xgboost/base.h> // bst_target_t
#include <xgboost/data.h> // DMatrix
#include <xgboost/json.h> // Json,Object,Number,get
#include <xgboost/learner.h> // Learner
#include <xgboost/base.h> // for Args, bst_target_t
#include <xgboost/data.h> // for DMatrix, MetaInfo
#include <xgboost/json.h> // for Json, get, Object, String
#include <xgboost/learner.h> // for Learner
#include <cstddef> // size_t
#include <memory> // shared_ptr,unique_ptr
#include <numeric>
#include <string> // stod
#include <vector>
#include <algorithm> // for copy
#include <cstddef> // for size_t
#include <memory> // for shared_ptr, allocator, __shared_ptr_access
#include <numeric> // for accumulate
#include <string> // for stod, string
#include <vector> // for vector
#include "../../src/common/linalg_op.h" // cbegin,cend
#include "../../src/common/stats.h" // Median
#include "helpers.h" // RandomDataGenerator
#include "xgboost/linalg.h"
#include "../../src/common/linalg_op.h" // for begin, cbegin, cend
#include "../../src/common/stats.h" // for Median
#include "../../src/common/transform_iterator.h" // for IndexTransformIter
#include "helpers.h" // for RandomDataGenerator
#include "xgboost/host_device_vector.h" // for HostDeviceVector
#include "xgboost/linalg.h" // for Tensor, All, TensorView, Vector
namespace xgboost {
class TestL1MultiTarget : public ::testing::Test {
std::shared_ptr<DMatrix> Xy_;
std::shared_ptr<DMatrix> Xyw_;
@@ -117,4 +119,16 @@ TEST_F(TestL1MultiTarget, Approx) { this->RunTest("approx"); }
#if defined(XGBOOST_USE_CUDA)
TEST_F(TestL1MultiTarget, GpuHist) { this->RunTest("gpu_hist"); }
#endif // defined(XGBOOST_USE_CUDA)
TEST(MultiStrategy, Configure) {
auto p_fmat = RandomDataGenerator{12ul, 3ul, 0.0}.GenerateDMatrix();
p_fmat->Info().labels.Reshape(p_fmat->Info().num_row_, 2);
std::unique_ptr<Learner> learner{Learner::Create({p_fmat})};
learner->SetParams(Args{{"multi_strategy", "monolithic"}, {"num_target", "2"}});
learner->Configure();
ASSERT_EQ(learner->Groups(), 2);
learner->SetParams(Args{{"multi_strategy", "monolithic"}, {"num_target", "0"}});
ASSERT_THROW({ learner->Configure(); }, dmlc::Error);
}
} // namespace xgboost

11
tests/cpp/tree/test_gpu_hist.cu
View File

@@ -170,8 +170,8 @@ void TestHistogramIndexImpl() {
// Build 2 matrices and build a histogram maker with that
Context ctx(CreateEmptyGenericParam(0));
tree::GPUHistMaker hist_maker{&ctx, ObjInfo{ObjInfo::kRegression}},
hist_maker_ext{&ctx, ObjInfo{ObjInfo::kRegression}};
ObjInfo task{ObjInfo::kRegression};
tree::GPUHistMaker hist_maker{&ctx, &task}, hist_maker_ext{&ctx, &task};
std::unique_ptr<DMatrix> hist_maker_dmat(
CreateSparsePageDMatrixWithRC(kNRows, kNCols, 0, true));
@@ -240,7 +240,8 @@ void UpdateTree(HostDeviceVector<GradientPair>* gpair, DMatrix* dmat,
param.UpdateAllowUnknown(args);
Context ctx(CreateEmptyGenericParam(0));
tree::GPUHistMaker hist_maker{&ctx,ObjInfo{ObjInfo::kRegression}};
ObjInfo task{ObjInfo::kRegression};
tree::GPUHistMaker hist_maker{&ctx, &task};
std::vector<HostDeviceVector<bst_node_t>> position(1);
hist_maker.Update(&param, gpair, dmat, common::Span<HostDeviceVector<bst_node_t>>{position},
@@ -385,8 +386,8 @@ TEST(GpuHist, ExternalMemoryWithSampling) {
TEST(GpuHist, ConfigIO) {
Context ctx(CreateEmptyGenericParam(0));
std::unique_ptr<TreeUpdater> updater{
TreeUpdater::Create("grow_gpu_hist", &ctx, ObjInfo{ObjInfo::kRegression})};
ObjInfo task{ObjInfo::kRegression};
std::unique_ptr<TreeUpdater> updater{TreeUpdater::Create("grow_gpu_hist", &ctx, &task)};
updater->Configure(Args{});
Json j_updater { Object() };

15
tests/cpp/tree/test_histmaker.cc
View File

@@ -37,13 +37,13 @@ TEST(GrowHistMaker, InteractionConstraint)
auto p_gradients = GenerateGradients(kRows);
Context ctx;
ObjInfo task{ObjInfo::kRegression};
{
// With constraints
RegTree tree;
tree.param.num_feature = kCols;
std::unique_ptr<TreeUpdater> updater{
TreeUpdater::Create("grow_histmaker", &ctx, ObjInfo{ObjInfo::kRegression})};
std::unique_ptr<TreeUpdater> updater{TreeUpdater::Create("grow_histmaker", &ctx, &task)};
TrainParam param;
param.UpdateAllowUnknown(
Args{{"interaction_constraints", "[[0, 1]]"}, {"num_feature", std::to_string(kCols)}});
@@ -61,8 +61,7 @@ TEST(GrowHistMaker, InteractionConstraint)
RegTree tree;
tree.param.num_feature = kCols;
std::unique_ptr<TreeUpdater> updater{
TreeUpdater::Create("grow_histmaker", &ctx, ObjInfo{ObjInfo::kRegression})};
std::unique_ptr<TreeUpdater> updater{TreeUpdater::Create("grow_histmaker", &ctx, &task)};
std::vector<HostDeviceVector<bst_node_t>> position(1);
TrainParam param;
param.Init(Args{});
@@ -81,8 +80,8 @@ void TestColumnSplit(int32_t rows, int32_t cols, RegTree const& expected_tree) {
auto p_dmat = GenerateDMatrix(rows, cols);
auto p_gradients = GenerateGradients(rows);
Context ctx;
std::unique_ptr<TreeUpdater> updater{
TreeUpdater::Create("grow_histmaker", &ctx, ObjInfo{ObjInfo::kRegression})};
ObjInfo task{ObjInfo::kRegression};
std::unique_ptr<TreeUpdater> updater{TreeUpdater::Create("grow_histmaker", &ctx, &task)};
std::vector<HostDeviceVector<bst_node_t>> position(1);
std::unique_ptr<DMatrix> sliced{
@@ -110,12 +109,12 @@ TEST(GrowHistMaker, ColumnSplit) {
RegTree expected_tree;
expected_tree.param.num_feature = kCols;
ObjInfo task{ObjInfo::kRegression};
{
auto p_dmat = GenerateDMatrix(kRows, kCols);
auto p_gradients = GenerateGradients(kRows);
Context ctx;
std::unique_ptr<TreeUpdater> updater{
TreeUpdater::Create("grow_histmaker", &ctx, ObjInfo{ObjInfo::kRegression})};
std::unique_ptr<TreeUpdater> updater{TreeUpdater::Create("grow_histmaker", &ctx, &task)};
std::vector<HostDeviceVector<bst_node_t>> position(1);
TrainParam param;
param.Init(Args{});

48
tests/cpp/tree/test_multi_target_tree_model.cc Normal file
View File

@@ -0,0 +1,48 @@
/**
* Copyright 2023 by XGBoost Contributors
*/
#include <gtest/gtest.h>
#include <xgboost/context.h> // for Context
#include <xgboost/multi_target_tree_model.h>
#include <xgboost/tree_model.h> // for RegTree
namespace xgboost {
TEST(MultiTargetTree, JsonIO) {
bst_target_t n_targets{3};
bst_feature_t n_features{4};
RegTree tree{n_targets, n_features};
ASSERT_TRUE(tree.IsMultiTarget());
linalg::Vector<float> base_weight{{1.0f, 2.0f, 3.0f}, {3ul}, Context::kCpuId};
linalg::Vector<float> left_weight{{2.0f, 3.0f, 4.0f}, {3ul}, Context::kCpuId};
linalg::Vector<float> right_weight{{3.0f, 4.0f, 5.0f}, {3ul}, Context::kCpuId};
tree.ExpandNode(RegTree::kRoot, /*split_idx=*/1, 0.5f, true, base_weight.HostView(),
left_weight.HostView(), right_weight.HostView());
ASSERT_EQ(tree.param.num_nodes, 3);
ASSERT_EQ(tree.param.size_leaf_vector, 3);
ASSERT_EQ(tree.GetMultiTargetTree()->Size(), 3);
ASSERT_EQ(tree.Size(), 3);
Json jtree{Object{}};
tree.SaveModel(&jtree);
auto check_jtree = [](Json jtree, RegTree const& tree) {
ASSERT_EQ(get<String const>(jtree["tree_param"]["num_nodes"]),
std::to_string(tree.param.num_nodes));
ASSERT_EQ(get<F32Array const>(jtree["base_weights"]).size(),
tree.param.num_nodes * tree.param.size_leaf_vector);
ASSERT_EQ(get<I32Array const>(jtree["parents"]).size(), tree.param.num_nodes);
ASSERT_EQ(get<I32Array const>(jtree["left_children"]).size(), tree.param.num_nodes);
ASSERT_EQ(get<I32Array const>(jtree["right_children"]).size(), tree.param.num_nodes);
};
check_jtree(jtree, tree);
RegTree loaded;
loaded.LoadModel(jtree);
ASSERT_TRUE(loaded.IsMultiTarget());
ASSERT_EQ(loaded.param.num_nodes, 3);
Json jtree1{Object{}};
loaded.SaveModel(&jtree1);
check_jtree(jtree1, tree);
}
} // namespace xgboost

13
tests/cpp/tree/test_node_partition.cc
View File

@@ -2,22 +2,25 @@
* Copyright 2023 by XGBoost contributors
*/
#include <gtest/gtest.h>
#include <xgboost/task.h>
#include <xgboost/tree_updater.h>
#include <xgboost/context.h> // for Context
#include <xgboost/task.h> // for ObjInfo
#include <xgboost/tree_updater.h> // for TreeUpdater
#include <memory> // for unique_ptr
namespace xgboost {
TEST(Updater, HasNodePosition) {
Context ctx;
ObjInfo task{ObjInfo::kRegression, true, true};
std::unique_ptr<TreeUpdater> up{TreeUpdater::Create("grow_histmaker", &ctx, task)};
std::unique_ptr<TreeUpdater> up{TreeUpdater::Create("grow_histmaker", &ctx, &task)};
ASSERT_TRUE(up->HasNodePosition());
up.reset(TreeUpdater::Create("grow_quantile_histmaker", &ctx, task));
up.reset(TreeUpdater::Create("grow_quantile_histmaker", &ctx, &task));
ASSERT_TRUE(up->HasNodePosition());
#if defined(XGBOOST_USE_CUDA)
ctx.gpu_id = 0;
up.reset(TreeUpdater::Create("grow_gpu_hist", &ctx, task));
up.reset(TreeUpdater::Create("grow_gpu_hist", &ctx, &task));
ASSERT_TRUE(up->HasNodePosition());
#endif // defined(XGBOOST_USE_CUDA)
}

5
tests/cpp/tree/test_prediction_cache.cc
View File

@@ -9,6 +9,7 @@
#include "../../../src/tree/param.h" // for TrainParam
#include "../helpers.h"
#include "xgboost/task.h" // for ObjInfo
namespace xgboost {
@@ -71,8 +72,8 @@ class TestPredictionCache : public ::testing::Test {
ctx.gpu_id = Context::kCpuId;
}
std::unique_ptr<TreeUpdater> updater{
TreeUpdater::Create(updater_name, &ctx, ObjInfo{ObjInfo::kRegression})};
ObjInfo task{ObjInfo::kRegression};
std::unique_ptr<TreeUpdater> updater{TreeUpdater::Create(updater_name, &ctx, &task)};
RegTree tree;
std::vector<RegTree *> trees{&tree};
auto gpair = GenerateRandomGradients(n_samples_);

4
tests/cpp/tree/test_prune.cc
View File

@@ -39,8 +39,8 @@ TEST(Updater, Prune) {
TrainParam param;
param.UpdateAllowUnknown(cfg);
std::unique_ptr<TreeUpdater> pruner(
TreeUpdater::Create("prune", &ctx, ObjInfo{ObjInfo::kRegression}));
ObjInfo task{ObjInfo::kRegression};
std::unique_ptr<TreeUpdater> pruner(TreeUpdater::Create("prune", &ctx, &task));
// loss_chg < min_split_loss;
std::vector<HostDeviceVector<bst_node_t>> position(trees.size());

16
tests/cpp/tree/test_refresh.cc
View File

@@ -1,8 +1,9 @@
/**
* Copyright 2018-2013 by XGBoost Contributors
* Copyright 2018-2023 by XGBoost Contributors
*/
#include <gtest/gtest.h>
#include <xgboost/host_device_vector.h>
#include <xgboost/task.h> // for ObjInfo
#include <xgboost/tree_updater.h>
#include <memory>
@@ -12,9 +13,7 @@
#include "../../../src/tree/param.h" // for TrainParam
#include "../helpers.h"
namespace xgboost {
namespace tree {
namespace xgboost::tree {
TEST(Updater, Refresh) {
bst_row_t constexpr kRows = 8;
bst_feature_t constexpr kCols = 16;
@@ -33,8 +32,9 @@ TEST(Updater, Refresh) {
auto ctx = CreateEmptyGenericParam(GPUIDX);
tree.param.UpdateAllowUnknown(cfg);
std::vector<RegTree*> trees{&tree};
std::unique_ptr<TreeUpdater> refresher(
TreeUpdater::Create("refresh", &ctx, ObjInfo{ObjInfo::kRegression}));
ObjInfo task{ObjInfo::kRegression};
std::unique_ptr<TreeUpdater> refresher(TreeUpdater::Create("refresh", &ctx, &task));
tree.ExpandNode(0, 2, 0.2f, false, 0.0, 0.2f, 0.8f, 0.0f, 0.0f,
/*left_sum=*/0.0f, /*right_sum=*/0.0f);
@@ -57,6 +57,4 @@ TEST(Updater, Refresh) {
ASSERT_NEAR(0, tree.Stat(1).loss_chg, kEps);
ASSERT_NEAR(0, tree.Stat(2).loss_chg, kEps);
}
} // namespace tree
} // namespace xgboost
} // namespace xgboost::tree

2
tests/cpp/tree/test_tree_model.cc
View File

@@ -477,7 +477,7 @@ TEST(Tree, JsonIO) {
auto tparam = j_tree["tree_param"];
ASSERT_EQ(get<String>(tparam["num_feature"]), "0");
ASSERT_EQ(get<String>(tparam["num_nodes"]), "3");
ASSERT_EQ(get<String>(tparam["size_leaf_vector"]), "0");
ASSERT_EQ(get<String>(tparam["size_leaf_vector"]), "1");
ASSERT_EQ(get<I32Array const>(j_tree["left_children"]).size(), 3ul);
ASSERT_EQ(get<I32Array const>(j_tree["right_children"]).size(), 3ul);

20
tests/cpp/tree/test_tree_stat.cc
View File

@@ -2,9 +2,13 @@
* Copyright 2020-2023 by XGBoost Contributors
*/
#include <gtest/gtest.h>
#include <xgboost/context.h> // for Context
#include <xgboost/task.h> // for ObjInfo
#include <xgboost/tree_model.h>
#include <xgboost/tree_updater.h>
#include <memory> // for unique_ptr
#include "../../../src/tree/param.h" // for TrainParam
#include "../helpers.h"
@@ -26,12 +30,12 @@ class UpdaterTreeStatTest : public ::testing::Test {
void RunTest(std::string updater) {
tree::TrainParam param;
ObjInfo task{ObjInfo::kRegression};
param.Init(Args{});
Context ctx(updater == "grow_gpu_hist" ? CreateEmptyGenericParam(0)
: CreateEmptyGenericParam(Context::kCpuId));
auto up = std::unique_ptr<TreeUpdater>{
TreeUpdater::Create(updater, &ctx, ObjInfo{ObjInfo::kRegression})};
auto up = std::unique_ptr<TreeUpdater>{TreeUpdater::Create(updater, &ctx, &task)};
up->Configure(Args{});
RegTree tree;
tree.param.num_feature = kCols;
@@ -74,18 +78,18 @@ class UpdaterEtaTest : public ::testing::Test {
}
void RunTest(std::string updater) {
ObjInfo task{ObjInfo::kClassification};
Context ctx(updater == "grow_gpu_hist" ? CreateEmptyGenericParam(0)
: CreateEmptyGenericParam(Context::kCpuId));
float eta = 0.4;
auto up_0 = std::unique_ptr<TreeUpdater>{
TreeUpdater::Create(updater, &ctx, ObjInfo{ObjInfo::kClassification})};
auto up_0 = std::unique_ptr<TreeUpdater>{TreeUpdater::Create(updater, &ctx, &task)};
up_0->Configure(Args{});
tree::TrainParam param0;
param0.Init(Args{{"eta", std::to_string(eta)}});
auto up_1 = std::unique_ptr<TreeUpdater>{
TreeUpdater::Create(updater, &ctx, ObjInfo{ObjInfo::kClassification})};
auto up_1 = std::unique_ptr<TreeUpdater>{TreeUpdater::Create(updater, &ctx, &task)};
up_1->Configure(Args{{"eta", "1.0"}});
tree::TrainParam param1;
param1.Init(Args{{"eta", "1.0"}});
@@ -153,11 +157,11 @@ class TestMinSplitLoss : public ::testing::Test {
{"gamma", std::to_string(gamma)}};
tree::TrainParam param;
param.UpdateAllowUnknown(args);
ObjInfo task{ObjInfo::kRegression};
Context ctx(updater == "grow_gpu_hist" ? CreateEmptyGenericParam(0)
: CreateEmptyGenericParam(Context::kCpuId));
auto up = std::unique_ptr<TreeUpdater>{
TreeUpdater::Create(updater, &ctx, ObjInfo{ObjInfo::kRegression})};
auto up = std::unique_ptr<TreeUpdater>{TreeUpdater::Create(updater, &ctx, &task)};
up->Configure({});
RegTree tree;