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

Dmatrix refactor stage 2 (#3395)

Browse Source 
* DMatrix refactor 2

* Remove buffered rowset usage where possible

* Transition to c++11 style iterators for row access

* Transition column iterators to C++ 11
This commit is contained in:
Rory Mitchell
2018-10-01 01:29:03 +13:00
committed by GitHub
parent b50bc2c1d4
commit 70d208d68c
36 changed files with 459 additions and 846 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
tests/cpp/data/test_simple_dmatrix.cc
View File

@@ -23,20 +23,18 @@ TEST(SimpleDMatrix, RowAccess) {
xgboost::DMatrix * dmat = xgboost::DMatrix::Load(tmp_file, false, false);
std::remove(tmp_file.c_str());
auto row_iter = dmat->RowIterator();
// Loop over the batches and count the records
long row_count = 0;
row_iter->BeforeFirst();
while (row_iter->Next()) row_count += row_iter->Value().Size();
for (auto &batch : dmat->GetRowBatches()) {
row_count += batch.Size();
}
EXPECT_EQ(row_count, dmat->Info().num_row_);
// Test the data read into the first row
row_iter->BeforeFirst();
row_iter->Next();
auto first_row = row_iter->Value()[0];
auto &batch = *dmat->GetRowBatches().begin();
auto first_row = batch[0];
ASSERT_EQ(first_row.size(), 3);
EXPECT_EQ(first_row[2].index, 2);
EXPECT_EQ(first_row[2].fvalue, 20);
row_iter = nullptr;
delete dmat;
}
@@ -46,40 +44,18 @@ TEST(SimpleDMatrix, ColAccessWithoutBatches) {
xgboost::DMatrix * dmat = xgboost::DMatrix::Load(tmp_file, true, false);
std::remove(tmp_file.c_str());
// Unsorted column access
const std::vector<bool> enable(dmat->Info().num_col_, true);
EXPECT_EQ(dmat->HaveColAccess(false), false);
dmat->InitColAccess(dmat->Info().num_row_, false);
dmat->InitColAccess(0, false); // Calling it again should not change it
ASSERT_EQ(dmat->HaveColAccess(false), true);
// Sorted column access
EXPECT_EQ(dmat->HaveColAccess(true), false);
dmat->InitColAccess(dmat->Info().num_row_, true);
dmat->InitColAccess(0, true); // Calling it again should not change it
ASSERT_EQ(dmat->HaveColAccess(true), true);
EXPECT_EQ(dmat->GetColSize(0), 2);
EXPECT_EQ(dmat->GetColSize(1), 1);
EXPECT_EQ(dmat->GetColDensity(0), 1);
EXPECT_EQ(dmat->GetColDensity(1), 0.5);
ASSERT_TRUE(dmat->SingleColBlock());
auto* col_iter = dmat->ColIterator();
// Loop over the batches and assert the data is as expected
long num_col_batch = 0;
col_iter->BeforeFirst();
while (col_iter->Next()) {
for (const auto &batch : dmat->GetSortedColumnBatches()) {
num_col_batch += 1;
EXPECT_EQ(col_iter->Value().Size(), dmat->Info().num_col_)
<< "Expected batch size = number of cells as #batches is 1.";
for (int i = 0; i < static_cast<int>(col_iter->Value().Size()); ++i) {
EXPECT_EQ(col_iter->Value()[i].size(), dmat->GetColSize(i))
<< "Expected length of each colbatch = colsize as #batches is 1.";
}
EXPECT_EQ(batch.Size(), dmat->Info().num_col_)
<< "Expected batch size = number of cells as #batches is 1.";
}
EXPECT_EQ(num_col_batch, 1) << "Expected number of batches to be 1";
col_iter = nullptr;
delete dmat;
}