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

Use array interface for CSC matrix. (#8672)

Browse Source 
* Use array interface for CSC matrix.

Use array interface for CSC matrix and align the interface with CSR and dense.

- Fix nthread issue in the R package DMatrix.
- Unify the behavior of handling `missing` with other inputs.
- Unify the behavior of handling `missing` around R, Python, Java, and Scala DMatrix.
- Expose `num_non_missing` to the JVM interface.
- Deprecate old CSR and CSC constructors.
This commit is contained in:
Jiaming Yuan
2023-02-05 01:59:46 +08:00
committed by GitHub
parent 213b5602d9
commit c1786849e3
23 changed files with 673 additions and 380 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
src/data/data.cc
View File

@@ -945,31 +945,33 @@ DMatrix* DMatrix::Create(AdapterT* adapter, float missing, int nthread, const st
return new data::SimpleDMatrix(adapter, missing, nthread);
}
template DMatrix* DMatrix::Create<data::DenseAdapter>(
data::DenseAdapter* adapter, float missing, int nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::ArrayAdapter>(
data::ArrayAdapter* adapter, float missing, int nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::CSRAdapter>(
data::CSRAdapter* adapter, float missing, int nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::CSCAdapter>(
data::CSCAdapter* adapter, float missing, int nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::DataTableAdapter>(
data::DataTableAdapter* adapter, float missing, int nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::FileAdapter>(
data::FileAdapter* adapter, float missing, int nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::CSRArrayAdapter>(
data::CSRArrayAdapter* adapter, float missing, int nthread,
const std::string& cache_prefix);
template DMatrix *
DMatrix::Create(data::IteratorAdapter<DataIterHandle, XGBCallbackDataIterNext,
XGBoostBatchCSR> *adapter,
float missing, int nthread, const std::string &cache_prefix);
template DMatrix* DMatrix::Create<data::DenseAdapter>(data::DenseAdapter* adapter, float missing,
std::int32_t nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::ArrayAdapter>(data::ArrayAdapter* adapter, float missing,
std::int32_t nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::CSRAdapter>(data::CSRAdapter* adapter, float missing,
std::int32_t nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::CSCAdapter>(data::CSCAdapter* adapter, float missing,
std::int32_t nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::DataTableAdapter>(data::DataTableAdapter* adapter,
float missing, std::int32_t nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::FileAdapter>(data::FileAdapter* adapter, float missing,
std::int32_t nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::CSRArrayAdapter>(data::CSRArrayAdapter* adapter,
float missing, std::int32_t nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::CSCArrayAdapter>(data::CSCArrayAdapter* adapter,
float missing, std::int32_t nthread,
const std::string& cache_prefix);
template DMatrix* DMatrix::Create(
data::IteratorAdapter<DataIterHandle, XGBCallbackDataIterNext, XGBoostBatchCSR>* adapter,
float missing, int nthread, const std::string& cache_prefix);
template DMatrix* DMatrix::Create<data::RecordBatchesIterAdapter>(
data::RecordBatchesIterAdapter* adapter, float missing, int nthread, const std::string&);
@@ -1221,20 +1223,19 @@ void SparsePage::PushCSC(const SparsePage &batch) {
self_offset = std::move(offset);
}
template uint64_t
SparsePage::Push(const data::DenseAdapterBatch& batch, float missing, int nthread);
template uint64_t
SparsePage::Push(const data::ArrayAdapterBatch& batch, float missing, int nthread);
template uint64_t
SparsePage::Push(const data::CSRAdapterBatch& batch, float missing, int nthread);
template uint64_t
SparsePage::Push(const data::CSRArrayAdapterBatch& batch, float missing, int nthread);
template uint64_t
SparsePage::Push(const data::CSCAdapterBatch& batch, float missing, int nthread);
template uint64_t
SparsePage::Push(const data::DataTableAdapterBatch& batch, float missing, int nthread);
template uint64_t
SparsePage::Push(const data::FileAdapterBatch& batch, float missing, int nthread);
template uint64_t SparsePage::Push(const data::DenseAdapterBatch& batch, float missing,
int nthread);
template uint64_t SparsePage::Push(const data::ArrayAdapterBatch& batch, float missing,
int nthread);
template uint64_t SparsePage::Push(const data::CSRAdapterBatch& batch, float missing, int nthread);
template uint64_t SparsePage::Push(const data::CSRArrayAdapterBatch& batch, float missing,
int nthread);
template uint64_t SparsePage::Push(const data::CSCArrayAdapterBatch& batch, float missing,
int nthread);
template uint64_t SparsePage::Push(const data::CSCAdapterBatch& batch, float missing, int nthread);
template uint64_t SparsePage::Push(const data::DataTableAdapterBatch& batch, float missing,
int nthread);
template uint64_t SparsePage::Push(const data::FileAdapterBatch& batch, float missing, int nthread);
namespace data {