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

Implement sketching with adapter. (#8019)

Browse Source
This commit is contained in:
Jiaming Yuan
2022-06-23 00:03:02 +08:00
committed by GitHub
parent 142a208a90
commit f0c1b842bf
6 changed files with 197 additions and 165 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
src/common/hist_util.cc
View File

@@ -33,6 +33,40 @@ HistogramCuts::HistogramCuts() {
cut_ptrs_.HostVector().emplace_back(0);
}
HistogramCuts SketchOnDMatrix(DMatrix *m, int32_t max_bins, int32_t n_threads, bool use_sorted,
Span<float> const hessian) {
HistogramCuts out;
auto const& info = m->Info();
std::vector<bst_row_t> reduced(info.num_col_, 0);
for (auto const &page : m->GetBatches<SparsePage>()) {
auto const &entries_per_column =
CalcColumnSize(data::SparsePageAdapterBatch{page.GetView()}, info.num_col_, n_threads,
[](auto) { return true; });
CHECK_EQ(entries_per_column.size(), info.num_col_);
for (size_t i = 0; i < entries_per_column.size(); ++i) {
reduced[i] += entries_per_column[i];
}
}
if (!use_sorted) {
HostSketchContainer container(max_bins, m->Info(), reduced, HostSketchContainer::UseGroup(info),
n_threads);
for (auto const& page : m->GetBatches<SparsePage>()) {
container.PushRowPage(page, info, hessian);
}
container.MakeCuts(&out);
} else {
SortedSketchContainer container{max_bins, m->Info(), reduced,
HostSketchContainer::UseGroup(info), n_threads};
for (auto const& page : m->GetBatches<SortedCSCPage>()) {
container.PushColPage(page, info, hessian);
}
container.MakeCuts(&out);
}
return out;
}
/*!
* \brief fill a histogram by zeros in range [begin, end)
*/