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

initial merge

Browse Source
This commit is contained in:
amdsc21
2023-03-25 04:31:55 +01:00
parent d97be6f396 cff50fe3ef
commit 7fbc561e17
146 changed files with 6730 additions and 4082 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
tests/cpp/data/test_data.cc
View File

@@ -112,31 +112,12 @@ TEST(SparsePage, SortIndices) {
}
TEST(DMatrix, Uri) {
size_t constexpr kRows {16};
size_t constexpr kCols {8};
std::vector<float> data (kRows * kCols);
for (size_t i = 0; i < kRows * kCols; ++i) {
data[i] = i;
}
auto constexpr kRows {16};
auto constexpr kCols {8};
dmlc::TemporaryDirectory tmpdir;
std::string path = tmpdir.path + "/small.csv";
std::ofstream fout(path);
size_t i = 0;
for (size_t r = 0; r < kRows; ++r) {
for (size_t c = 0; c < kCols; ++c) {
fout << data[i];
i++;
if (c != kCols - 1) {
fout << ",";
}
}
fout << "\n";
}
fout.flush();
fout.close();
auto const path = tmpdir.path + "/small.csv";
CreateTestCSV(path, kRows, kCols);
std::unique_ptr<DMatrix> dmat;
// FIXME(trivialfis): Enable the following test by restricting csv parser in dmlc-core.

13
tests/cpp/data/test_file_iterator.cc
View File

@@ -1,8 +1,9 @@
/*!
* Copyright 2021 XGBoost contributors
/**
* Copyright 2021-2023 XGBoost contributors
*/
#include <gtest/gtest.h>
#include <any> // for any_cast
#include <memory>
#include "../../../src/data/adapter.h"
@@ -11,15 +12,14 @@
#include "../filesystem.h" // dmlc::TemporaryDirectory
#include "../helpers.h"
namespace xgboost {
namespace data {
namespace xgboost::data {
TEST(FileIterator, Basic) {
auto check_n_features = [](FileIterator *iter) {
size_t n_features = 0;
iter->Reset();
while (iter->Next()) {
auto proxy = MakeProxy(iter->Proxy());
auto csr = dmlc::get<std::shared_ptr<CSRArrayAdapter>>(proxy->Adapter());
auto csr = std::any_cast<std::shared_ptr<CSRArrayAdapter>>(proxy->Adapter());
n_features = std::max(n_features, csr->NumColumns());
}
ASSERT_EQ(n_features, 5);
@@ -42,5 +42,4 @@ TEST(FileIterator, Basic) {
check_n_features(&iter);
}
}
} // namespace data
} // namespace xgboost
} // namespace xgboost::data

40
tests/cpp/data/test_proxy_dmatrix.cu
View File

@@ -1,23 +1,24 @@
/**
* Copyright 2020-2023 XGBoost contributors
*/
#include <gtest/gtest.h>
#include <xgboost/host_device_vector.h>
#include <any> // for any_cast
#include <memory>
#include "../helpers.h"
#include "../../../src/data/device_adapter.cuh"
#include "../../../src/data/proxy_dmatrix.h"
#include "../helpers.h"
namespace xgboost {
namespace data {
namespace xgboost::data {
TEST(ProxyDMatrix, DeviceData) {
constexpr size_t kRows{100}, kCols{100};
HostDeviceVector<float> storage;
auto data = RandomDataGenerator(kRows, kCols, 0.5)
.Device(0)
.GenerateArrayInterface(&storage);
auto data = RandomDataGenerator(kRows, kCols, 0.5).Device(0).GenerateArrayInterface(&storage);
std::vector<HostDeviceVector<float>> label_storage(1);
auto labels = RandomDataGenerator(kRows, 1, 0)
.Device(0)
.GenerateColumnarArrayInterface(&label_storage);
auto labels =
RandomDataGenerator(kRows, 1, 0).Device(0).GenerateColumnarArrayInterface(&label_storage);
DMatrixProxy proxy;
proxy.SetCUDAArray(data.c_str());
@@ -25,23 +26,16 @@ TEST(ProxyDMatrix, DeviceData) {
ASSERT_EQ(proxy.Adapter().type(), typeid(std::shared_ptr<CupyAdapter>));
ASSERT_EQ(proxy.Info().labels.Size(), kRows);
ASSERT_EQ(dmlc::get<std::shared_ptr<CupyAdapter>>(proxy.Adapter())->NumRows(),
kRows);
ASSERT_EQ(
dmlc::get<std::shared_ptr<CupyAdapter>>(proxy.Adapter())->NumColumns(),
kCols);
ASSERT_EQ(std::any_cast<std::shared_ptr<CupyAdapter>>(proxy.Adapter())->NumRows(), kRows);
ASSERT_EQ(std::any_cast<std::shared_ptr<CupyAdapter>>(proxy.Adapter())->NumColumns(), kCols);
std::vector<HostDeviceVector<float>> columnar_storage(kCols);
data = RandomDataGenerator(kRows, kCols, 0)
.Device(0)
.GenerateColumnarArrayInterface(&columnar_storage);
.Device(0)
.GenerateColumnarArrayInterface(&columnar_storage);
proxy.SetCUDAArray(data.c_str());
ASSERT_EQ(proxy.Adapter().type(), typeid(std::shared_ptr<CudfAdapter>));
ASSERT_EQ(dmlc::get<std::shared_ptr<CudfAdapter>>(proxy.Adapter())->NumRows(),
kRows);
ASSERT_EQ(
dmlc::get<std::shared_ptr<CudfAdapter>>(proxy.Adapter())->NumColumns(),
kCols);
ASSERT_EQ(std::any_cast<std::shared_ptr<CudfAdapter>>(proxy.Adapter())->NumRows(), kRows);
ASSERT_EQ(std::any_cast<std::shared_ptr<CudfAdapter>>(proxy.Adapter())->NumColumns(), kCols);
}
} // namespace data
} // namespace xgboost
} // namespace xgboost::data