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

[Breaking] Accept multi-dim meta info. (#7405)

Browse Source 
This PR changes base_margin into a 3-dim array, with one of them being reserved for multi-target classification. Also, a breaking change is made for binary serialization due to extra dimension along with a fix for saving the feature weights. Lastly, it unifies the prediction initialization between CPU and GPU. After this PR, the meta info setter in Python will be based on array interface.
This commit is contained in:
Jiaming Yuan
2021-11-18 23:02:54 +08:00
committed by GitHub
parent 9fb4338964
commit d33854af1b
25 changed files with 545 additions and 256 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
tests/cpp/data/test_metainfo.cu
View File

@@ -3,10 +3,13 @@
#include <gtest/gtest.h>
#include <xgboost/data.h>
#include <xgboost/json.h>
#include <xgboost/generic_parameters.h>
#include <thrust/device_vector.h>
#include "test_array_interface.h"
#include "../../../src/common/device_helpers.cuh"
#include "test_metainfo.h"
namespace xgboost {
template <typename T>
@@ -23,7 +26,7 @@ std::string PrepareData(std::string typestr, thrust::device_vector<T>* out, cons
std::vector<Json> j_shape {Json(Integer(static_cast<Integer::Int>(kRows)))};
column["shape"] = Array(j_shape);
column["strides"] = Array(std::vector<Json>{Json(Integer(static_cast<Integer::Int>(sizeof(T))))});
column["version"] = Integer(static_cast<Integer::Int>(1));
column["version"] = 3;
column["typestr"] = String(typestr);
auto p_d_data = d_data.data().get();
@@ -31,6 +34,7 @@ std::string PrepareData(std::string typestr, thrust::device_vector<T>* out, cons
Json(Integer(reinterpret_cast<Integer::Int>(p_d_data))),
Json(Boolean(false))};
column["data"] = j_data;
column["stream"] = nullptr;
Json array(std::vector<Json>{column});
std::string str;
@@ -49,6 +53,7 @@ TEST(MetaInfo, FromInterface) {
info.SetInfo("label", str.c_str());
auto const& h_label = info.labels_.HostVector();
ASSERT_EQ(h_label.size(), d_data.size());
for (size_t i = 0; i < d_data.size(); ++i) {
ASSERT_EQ(h_label[i], d_data[i]);
}
@@ -60,9 +65,10 @@ TEST(MetaInfo, FromInterface) {
}
info.SetInfo("base_margin", str.c_str());
auto const& h_base_margin = info.base_margin_.HostVector();
auto const h_base_margin = info.base_margin_.View(GenericParameter::kCpuId);
ASSERT_EQ(h_base_margin.Size(), d_data.size());
for (size_t i = 0; i < d_data.size(); ++i) {
ASSERT_EQ(h_base_margin[i], d_data[i]);
ASSERT_EQ(h_base_margin(i), d_data[i]);
}
thrust::device_vector<int> d_group_data;
@@ -76,6 +82,10 @@ TEST(MetaInfo, FromInterface) {
EXPECT_EQ(info.group_ptr_, expected_group_ptr);
}
TEST(MetaInfo, GPUStridedData) {
TestMetaInfoStridedData(0);
}
TEST(MetaInfo, Group) {
cudaSetDevice(0);
MetaInfo info;