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

Handle missing values in dataframe with category dtype. (#7331)

Browse Source 
* Replace -1 in pandas initializer.
* Unify `IsValid` functor.
* Mimic pandas data handling in cuDF glue code.
* Check invalid categories.
* Fix DDM sketching.
This commit is contained in:
Jiaming Yuan
2021-10-28 03:33:54 +08:00
committed by GitHub
parent 2eee87423c
commit ac9bfaa4f2
13 changed files with 301 additions and 103 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/data/data.cc
View File

@@ -999,18 +999,19 @@ uint64_t SparsePage::Push(const AdapterBatchT& batch, float missing, int nthread
// Second pass over batch, placing elements in correct position
auto is_valid = data::IsValidFunctor{missing};
#pragma omp parallel num_threads(nthread)
{
exec.Run([&]() {
int tid = omp_get_thread_num();
size_t begin = tid*thread_size;
size_t end = tid != (nthread-1) ? (tid+1)*thread_size : batch_size;
size_t begin = tid * thread_size;
size_t end = tid != (nthread - 1) ? (tid + 1) * thread_size : batch_size;
for (size_t i = begin; i < end; ++i) {
auto line = batch.GetLine(i);
for (auto j = 0ull; j < line.Size(); j++) {
auto element = line.GetElement(j);
const size_t key = (element.row_idx - base_rowid);
if (!common::CheckNAN(element.value) && element.value != missing) {
if (is_valid(element)) {
builder.Push(key, Entry(element.column_idx, element.value), tid);
}
}