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

[R] Add missing DMatrix functions (#9929)

Browse Source 
* `XGDMatrixGetQuantileCut`
* `XGDMatrixNumNonMissing`
* `XGDMatrixGetDataAsCSR`

---------

Co-authored-by: Jiaming Yuan <jm.yuan@outlook.com>
This commit is contained in:
david-cortes
2024-01-03 10:29:21 +01:00
committed by GitHub
parent 49247458f9
commit 3c004a4145
14 changed files with 438 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
R-package/src/Makevars.in
View File

@@ -63,6 +63,7 @@ OBJECTS= \
$(PKGROOT)/src/gbm/gblinear.o \
$(PKGROOT)/src/gbm/gblinear_model.o \
$(PKGROOT)/src/data/adapter.o \
$(PKGROOT)/src/data/array_interface.o \
$(PKGROOT)/src/data/simple_dmatrix.o \
$(PKGROOT)/src/data/data.o \
$(PKGROOT)/src/data/sparse_page_raw_format.o \

1
R-package/src/Makevars.win
View File

@@ -63,6 +63,7 @@ OBJECTS= \
$(PKGROOT)/src/gbm/gblinear.o \
$(PKGROOT)/src/gbm/gblinear_model.o \
$(PKGROOT)/src/data/adapter.o \
$(PKGROOT)/src/data/array_interface.o \
$(PKGROOT)/src/data/simple_dmatrix.o \
$(PKGROOT)/src/data/data.o \
$(PKGROOT)/src/data/sparse_page_raw_format.o \

6
R-package/src/init.c
View File

@@ -45,6 +45,9 @@ extern SEXP XGDMatrixCreateFromDF_R(SEXP, SEXP, SEXP);
extern SEXP XGDMatrixGetStrFeatureInfo_R(SEXP, SEXP);
extern SEXP XGDMatrixNumCol_R(SEXP);
extern SEXP XGDMatrixNumRow_R(SEXP);
extern SEXP XGDMatrixGetQuantileCut_R(SEXP);
extern SEXP XGDMatrixNumNonMissing_R(SEXP);
extern SEXP XGDMatrixGetDataAsCSR_R(SEXP);
extern SEXP XGDMatrixSaveBinary_R(SEXP, SEXP, SEXP);
extern SEXP XGDMatrixSetInfo_R(SEXP, SEXP, SEXP);
extern SEXP XGDMatrixSetStrFeatureInfo_R(SEXP, SEXP, SEXP);
@@ -84,6 +87,9 @@ static const R_CallMethodDef CallEntries[] = {
{"XGDMatrixGetStrFeatureInfo_R", (DL_FUNC) &XGDMatrixGetStrFeatureInfo_R, 2},
{"XGDMatrixNumCol_R", (DL_FUNC) &XGDMatrixNumCol_R, 1},
{"XGDMatrixNumRow_R", (DL_FUNC) &XGDMatrixNumRow_R, 1},
{"XGDMatrixGetQuantileCut_R", (DL_FUNC) &XGDMatrixGetQuantileCut_R, 1},
{"XGDMatrixNumNonMissing_R", (DL_FUNC) &XGDMatrixNumNonMissing_R, 1},
{"XGDMatrixGetDataAsCSR_R", (DL_FUNC) &XGDMatrixGetDataAsCSR_R, 1},
{"XGDMatrixSaveBinary_R", (DL_FUNC) &XGDMatrixSaveBinary_R, 3},
{"XGDMatrixSetInfo_R", (DL_FUNC) &XGDMatrixSetInfo_R, 3},
{"XGDMatrixSetStrFeatureInfo_R", (DL_FUNC) &XGDMatrixSetStrFeatureInfo_R, 3},

130
R-package/src/xgboost_R.cc
View File

@@ -1,5 +1,5 @@
/**
* Copyright 2014-2023 by XGBoost Contributors
* Copyright 2014-2024, XGBoost Contributors
*/
#include <dmlc/common.h>
#include <dmlc/omp.h>
@@ -9,9 +9,11 @@
#include <xgboost/logging.h>
#include <algorithm>
#include <cmath>
#include <cstdint>
#include <cstdio>
#include <cstring>
#include <limits>
#include <sstream>
#include <string>
#include <utility>
@@ -20,14 +22,14 @@
#include "../../src/c_api/c_api_error.h"
#include "../../src/c_api/c_api_utils.h" // MakeSparseFromPtr
#include "../../src/common/threading_utils.h"
#include "../../src/data/array_interface.h" // for ArrayInterface
#include "./xgboost_R.h" // Must follow other includes.
namespace {
struct ErrorWithUnwind : public std::exception {};
void ThrowExceptionFromRError(void *unused, Rboolean jump) {
void ThrowExceptionFromRError(void *, Rboolean jump) {
if (jump) {
throw ErrorWithUnwind();
}
@@ -49,6 +51,30 @@ SEXP SafeMkChar(const char *c_str, SEXP continuation_token) {
continuation_token);
}
SEXP WrappedAllocReal(void *void_ptr) {
size_t *size = static_cast<size_t*>(void_ptr);
return Rf_allocVector(REALSXP, *size);
}
SEXP SafeAllocReal(size_t size, SEXP continuation_token) {
return R_UnwindProtect(
WrappedAllocReal, static_cast<void*>(&size),
ThrowExceptionFromRError, nullptr,
continuation_token);
}
SEXP WrappedAllocInteger(void *void_ptr) {
size_t *size = static_cast<size_t*>(void_ptr);
return Rf_allocVector(INTSXP, *size);
}
SEXP SafeAllocInteger(size_t size, SEXP continuation_token) {
return R_UnwindProtect(
WrappedAllocInteger, static_cast<void*>(&size),
ThrowExceptionFromRError, nullptr,
continuation_token);
}
[[nodiscard]] std::string MakeArrayInterfaceFromRMat(SEXP R_mat) {
SEXP mat_dims = Rf_getAttrib(R_mat, R_DimSymbol);
if (Rf_xlength(mat_dims) > 2) {
@@ -136,6 +162,37 @@ SEXP SafeMkChar(const char *c_str, SEXP continuation_token) {
jconfig["nthread"] = Rf_asInteger(n_threads);
return Json::Dump(jconfig);
}
// Allocate a R vector and copy an array interface encoded object to it.
[[nodiscard]] SEXP CopyArrayToR(const char *array_str, SEXP ctoken) {
xgboost::ArrayInterface<1> array{xgboost::StringView{array_str}};
// R supports only int and double.
bool is_int =
xgboost::DispatchDType(array.type, [](auto t) { return std::is_integral_v<decltype(t)>; });
bool is_float = xgboost::DispatchDType(
array.type, [](auto v) { return std::is_floating_point_v<decltype(v)>; });
CHECK(is_int || is_float) << "Internal error: Invalid DType.";
CHECK(array.is_contiguous) << "Internal error: Return by XGBoost should be contiguous";
// Allocate memory in R
SEXP out =
Rf_protect(is_int ? SafeAllocInteger(array.n, ctoken) : SafeAllocReal(array.n, ctoken));
xgboost::DispatchDType(array.type, [&](auto t) {
using T = decltype(t);
auto in_ptr = static_cast<T const *>(array.data);
if (is_int) {
auto out_ptr = INTEGER(out);
std::copy_n(in_ptr, array.n, out_ptr);
} else {
auto out_ptr = REAL(out);
std::copy_n(in_ptr, array.n, out_ptr);
}
});
Rf_unprotect(1);
return out;
}
} // namespace
struct RRNGStateController {
@@ -540,6 +597,73 @@ XGB_DLL SEXP XGDMatrixNumCol_R(SEXP handle) {
return ScalarInteger(static_cast<int>(ncol));
}
XGB_DLL SEXP XGDMatrixGetQuantileCut_R(SEXP handle) {
const char *out_names[] = {"indptr", "data", ""};
SEXP continuation_token = Rf_protect(R_MakeUnwindCont());
SEXP out = Rf_protect(Rf_mkNamed(VECSXP, out_names));
R_API_BEGIN();
const char *out_indptr;
const char *out_data;
CHECK_CALL(XGDMatrixGetQuantileCut(R_ExternalPtrAddr(handle), "{}", &out_indptr, &out_data));
try {
SET_VECTOR_ELT(out, 0, CopyArrayToR(out_indptr, continuation_token));
SET_VECTOR_ELT(out, 1, CopyArrayToR(out_data, continuation_token));
} catch (ErrorWithUnwind &e) {
R_ContinueUnwind(continuation_token);
}
R_API_END();
Rf_unprotect(2);
return out;
}
XGB_DLL SEXP XGDMatrixNumNonMissing_R(SEXP handle) {
SEXP out = Rf_protect(Rf_allocVector(REALSXP, 1));
R_API_BEGIN();
bst_ulong out_;
CHECK_CALL(XGDMatrixNumNonMissing(R_ExternalPtrAddr(handle), &out_));
REAL(out)[0] = static_cast<double>(out_);
R_API_END();
Rf_unprotect(1);
return out;
}
XGB_DLL SEXP XGDMatrixGetDataAsCSR_R(SEXP handle) {
const char *out_names[] = {"indptr", "indices", "data", "ncols", ""};
SEXP out = Rf_protect(Rf_mkNamed(VECSXP, out_names));
R_API_BEGIN();
bst_ulong nrows, ncols, nnz;
CHECK_CALL(XGDMatrixNumRow(R_ExternalPtrAddr(handle), &nrows));
CHECK_CALL(XGDMatrixNumCol(R_ExternalPtrAddr(handle), &ncols));
CHECK_CALL(XGDMatrixNumNonMissing(R_ExternalPtrAddr(handle), &nnz));
if (std::max(nrows, ncols) > std::numeric_limits<int>::max()) {
Rf_error("%s", "Error: resulting DMatrix data does not fit into R 'dgRMatrix'.");
}
SET_VECTOR_ELT(out, 0, Rf_allocVector(INTSXP, nrows + 1));
SET_VECTOR_ELT(out, 1, Rf_allocVector(INTSXP, nnz));
SET_VECTOR_ELT(out, 2, Rf_allocVector(REALSXP, nnz));
SET_VECTOR_ELT(out, 3, Rf_ScalarInteger(ncols));
std::unique_ptr<bst_ulong[]> indptr(new bst_ulong[nrows + 1]);
std::unique_ptr<unsigned[]> indices(new unsigned[nnz]);
std::unique_ptr<float[]> data(new float[nnz]);
CHECK_CALL(XGDMatrixGetDataAsCSR(R_ExternalPtrAddr(handle),
"{}",
indptr.get(),
indices.get(),
data.get()));
std::copy(indptr.get(), indptr.get() + nrows + 1, INTEGER(VECTOR_ELT(out, 0)));
std::copy(indices.get(), indices.get() + nnz, INTEGER(VECTOR_ELT(out, 1)));
std::copy(data.get(), data.get() + nnz, REAL(VECTOR_ELT(out, 2)));
R_API_END();
Rf_unprotect(1);
return out;
}
// functions related to booster
void _BoosterFinalizer(SEXP ext) {
if (R_ExternalPtrAddr(ext) == NULL) return;

25
R-package/src/xgboost_R.h
View File

@@ -143,6 +143,31 @@ XGB_DLL SEXP XGDMatrixNumRow_R(SEXP handle);
*/
XGB_DLL SEXP XGDMatrixNumCol_R(SEXP handle);
/*!
* \brief return the quantile cuts used for the histogram method
* \param handle an instance of data matrix
* \return A list with entries 'indptr' and 'data'
*/
XGB_DLL SEXP XGDMatrixGetQuantileCut_R(SEXP handle);
/*!
* \brief get the number of non-missing entries in a dmatrix
* \param handle an instance of data matrix
* \return the number of non-missing entries
*/
XGB_DLL SEXP XGDMatrixNumNonMissing_R(SEXP handle);
/*!
* \brief get the data in a dmatrix in CSR format
* \param handle an instance of data matrix
* \return R list with the following entries in this order:
* - 'indptr
* - 'indices
* - 'data'
* - 'ncol'
*/
XGB_DLL SEXP XGDMatrixGetDataAsCSR_R(SEXP handle);
/*!
* \brief create xgboost learner
* \param dmats a list of dmatrix handles that will be cached