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

Extend array interface to handle ndarray. (#7434)

Browse Source 
* Extend array interface to handle ndarray.

The `ArrayInterface` class is extended to support multi-dim array inputs. Previously this
class handles only 2-dim (vector is also matrix).  This PR specifies the expected
dimension at compile-time and the array interface can perform various checks automatically
for input data. Also, adapters like CSR are more rigorous about their input.  Lastly, row
vector and column vector are handled without intervention from the caller.
This commit is contained in:
Jiaming Yuan
2021-11-16 09:52:15 +08:00
committed by GitHub
parent e27f543deb
commit 55ee272ea8
18 changed files with 654 additions and 456 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
src/data/data.cc
View File

@@ -1,5 +1,5 @@
/*!
* Copyright 2015-2020 by Contributors
* Copyright 2015-2021 by Contributors
* \file data.cc
*/
#include <dmlc/registry.h>
@@ -24,6 +24,7 @@
#include "../data/iterative_device_dmatrix.h"
#include "file_iterator.h"
#include "validation.h"
#include "./sparse_page_source.h"
#include "./sparse_page_dmatrix.h"
@@ -337,17 +338,6 @@ inline bool MetaTryLoadFloatInfo(const std::string& fname,
return true;
}
void ValidateQueryGroup(std::vector<bst_group_t> const &group_ptr_) {
bool valid_query_group = true;
for (size_t i = 1; i < group_ptr_.size(); ++i) {
valid_query_group = valid_query_group && group_ptr_[i] >= group_ptr_[i - 1];
if (!valid_query_group) {
break;
}
}
CHECK(valid_query_group) << "Invalid group structure.";
}
// macro to dispatch according to specified pointer types
#define DISPATCH_CONST_PTR(dtype, old_ptr, cast_ptr, proc) \
switch (dtype) { \
@@ -398,7 +388,7 @@ void MetaInfo::SetInfo(const char* key, const void* dptr, DataType dtype, size_t
for (size_t i = 1; i < group_ptr_.size(); ++i) {
group_ptr_[i] = group_ptr_[i - 1] + group_ptr_[i];
}
ValidateQueryGroup(group_ptr_);
data::ValidateQueryGroup(group_ptr_);
} else if (!std::strcmp(key, "qid")) {
std::vector<uint32_t> query_ids(num, 0);
DISPATCH_CONST_PTR(dtype, dptr, cast_dptr,
@@ -632,7 +622,7 @@ void MetaInfo::Validate(int32_t device) const {
}
#if !defined(XGBOOST_USE_CUDA)
void MetaInfo::SetInfo(const char * c_key, std::string const& interface_str) {
void MetaInfo::SetInfo(StringView key, std::string const& interface_str) {
common::AssertGPUSupport();
}
#endif // !defined(XGBOOST_USE_CUDA)