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

Remove unnecessary DMatrix methods (#5324)

Browse Source
This commit is contained in:
Rory Mitchell
2020-02-25 12:40:39 +13:00
committed by GitHub
parent 655cf17b60
commit b0ed3f0a66
10 changed files with 43 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/cpp/data/test_simple_dmatrix.cc
View File

@@ -51,9 +51,6 @@ TEST(SimpleDMatrix, ColAccessWithoutBatches) {
CreateSimpleTestData(tmp_file);
xgboost::DMatrix *dmat = xgboost::DMatrix::Load(tmp_file, true, false);
// Sorted column access
EXPECT_EQ(dmat->GetColDensity(0), 1);
EXPECT_EQ(dmat->GetColDensity(1), 0.5);
ASSERT_TRUE(dmat->SingleColBlock());
// Loop over the batches and assert the data is as expected

3
tests/cpp/data/test_sparse_page_dmatrix.cc
View File

@@ -47,9 +47,6 @@ TEST(SparsePageDMatrix, ColAccess) {
xgboost::DMatrix *dmat =
xgboost::DMatrix::Load(tmp_file + "#" + tmp_file + ".cache", true, false);
EXPECT_EQ(dmat->GetColDensity(0), 1);
EXPECT_EQ(dmat->GetColDensity(1), 0.5);
// Loop over the batches and assert the data is as expected
for (auto const &col_batch : dmat->GetBatches<xgboost::SortedCSCPage>()) {
EXPECT_EQ(col_batch.Size(), dmat->Info().num_col_);

5
tests/cpp/test_learner.cc
View File

@@ -96,8 +96,9 @@ TEST(Learner, SLOW_CheckMultiBatch) {
// Create sufficiently large data to make two row pages
dmlc::TemporaryDirectory tempdir;
const std::string tmp_file = tempdir.path + "/big.libsvm";
CreateBigTestData(tmp_file, 5000000);
std::shared_ptr<DMatrix> dmat(xgboost::DMatrix::Load( tmp_file + "#" + tmp_file + ".cache", true, false));
CreateBigTestData(tmp_file, 50000);
std::shared_ptr<DMatrix> dmat(xgboost::DMatrix::Load(
tmp_file + "#" + tmp_file + ".cache", true, false, "auto", 100));
EXPECT_TRUE(FileExists(tmp_file + ".cache.row.page"));
EXPECT_FALSE(dmat->SingleColBlock());
size_t num_row = dmat->Info().num_row_;