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

Fix CPU bin compression with categorical data. (#8809)

Browse Source 
* Fix CPU bin compression with categorical data.

* The bug causes the maximum category to be lesser than 256 or the maximum number of bins when
the input data is dense.
This commit is contained in:
Jiaming Yuan
2023-02-16 04:20:34 +08:00
committed by GitHub
parent cce4af4acf
commit c0afdb6786
6 changed files with 49 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
tests/cpp/data/test_gradient_index.cc
View File

@@ -68,6 +68,30 @@ TEST(GradientIndex, FromCategoricalBasic) {
}
}
TEST(GradientIndex, FromCategoricalLarge) {
size_t constexpr kRows = 1000, kCats = 512, kCols = 1;
bst_bin_t max_bins = 8;
auto x = GenerateRandomCategoricalSingleColumn(kRows, kCats);
auto m = GetDMatrixFromData(x, kRows, 1);
Context ctx;
auto &h_ft = m->Info().feature_types.HostVector();
h_ft.resize(kCols, FeatureType::kCategorical);
BatchParam p{max_bins, 0.8};
{
GHistIndexMatrix gidx(m.get(), max_bins, p.sparse_thresh, false, AllThreadsForTest(), {});
ASSERT_TRUE(gidx.index.GetBinTypeSize() == common::kUint16BinsTypeSize);
}
{
for (auto const &page : m->GetBatches<GHistIndexMatrix>(p)) {
common::HistogramCuts cut = page.cut;
GHistIndexMatrix gidx{m->Info(), std::move(cut), max_bins};
ASSERT_EQ(gidx.MaxNumBinPerFeat(), kCats);
}
}
}
TEST(GradientIndex, PushBatch) {
size_t constexpr kRows = 64, kCols = 4;
bst_bin_t max_bins = 64;