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

Support categorical data for hist. (#7695)

Browse Source 
* Extract partitioner from hist.
* Implement categorical data support by passing the gradient index directly into the partitioner.
* Organize/update document.
* Remove code for negative hessian.
This commit is contained in:
Jiaming Yuan
2022-02-25 03:47:14 +08:00
committed by GitHub
parent f60d95b0ba
commit 83a66b4994
15 changed files with 402 additions and 498 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
include/xgboost/tree_model.h
View File

@@ -604,6 +604,16 @@ class RegTree : public Model {
*/
std::vector<FeatureType> const &GetSplitTypes() const { return split_types_; }
common::Span<uint32_t const> GetSplitCategories() const { return split_categories_; }
/*!
* \brief Get the bit storage for categories
*/
common::Span<uint32_t const> NodeCats(bst_node_t nidx) const {
auto node_ptr = GetCategoriesMatrix().node_ptr;
auto categories = GetCategoriesMatrix().categories;
auto segment = node_ptr[nidx];
auto node_cats = categories.subspan(segment.beg, segment.size);
return node_cats;
}
auto const& GetSplitCategoriesPtr() const { return split_categories_segments_; }
// The fields of split_categories_segments_[i] are set such that