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

Refactor parts of fast histogram utilities (#3564)

Browse Source 
* Refactor parts of fast histogram utilities

* Removed byte packing from column matrix
This commit is contained in:
Rory Mitchell
2018-08-09 17:59:57 +12:00
committed by GitHub
parent 3c72654e3b
commit bbb771f32e
8 changed files with 184 additions and 288 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
tests/cpp/data/test_metainfo.cc
View File

@@ -67,59 +67,4 @@ TEST(MetaInfo, SaveLoadBinary) {
}
TEST(MetaInfo, LoadQid) {
std::string tmp_file = TempFileName();
{
std::unique_ptr<dmlc::Stream> fs(
dmlc::Stream::Create(tmp_file.c_str(), "w"));
dmlc::ostream os(fs.get());
os << R"qid(3 qid:1 1:1 2:1 3:0 4:0.2 5:0
2 qid:1 1:0 2:0 3:1 4:0.1 5:1
1 qid:1 1:0 2:1 3:0 4:0.4 5:0
1 qid:1 1:0 2:0 3:1 4:0.3 5:0
1 qid:2 1:0 2:0 3:1 4:0.2 5:0
2 qid:2 1:1 2:0 3:1 4:0.4 5:0
1 qid:2 1:0 2:0 3:1 4:0.1 5:0
1 qid:2 1:0 2:0 3:1 4:0.2 5:0
2 qid:3 1:0 2:0 3:1 4:0.1 5:1
3 qid:3 1:1 2:1 3:0 4:0.3 5:0
4 qid:3 1:1 2:0 3:0 4:0.4 5:1
1 qid:3 1:0 2:1 3:1 4:0.5 5:0)qid";
os.set_stream(nullptr);
}
std::unique_ptr<xgboost::DMatrix> dmat(
xgboost::DMatrix::Load(tmp_file, true, false, "libsvm"));
std::remove(tmp_file.c_str());
const xgboost::MetaInfo& info = dmat->Info();
const std::vector<uint64_t> expected_qids{1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3};
const std::vector<xgboost::bst_uint> expected_group_ptr{0, 4, 8, 12};
CHECK(info.qids_ == expected_qids);
CHECK(info.group_ptr_ == expected_group_ptr);
CHECK_GE(info.kVersion, info.kVersionQidAdded);
const std::vector<size_t> expected_offset{
0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60
};
const std::vector<xgboost::Entry> expected_data{
{1, 1}, {2, 1}, {3, 0}, {4, 0.2}, {5, 0},
{1, 0}, {2, 0}, {3, 1}, {4, 0.1}, {5, 1},
{1, 0}, {2, 1}, {3, 0}, {4, 0.4}, {5, 0},
{1, 0}, {2, 0}, {3, 1}, {4, 0.3}, {5, 0},
{1, 0}, {2, 0}, {3, 1}, {4, 0.2}, {5, 0},
{1, 1}, {2, 0}, {3, 1}, {4, 0.4}, {5, 0},
{1, 0}, {2, 0}, {3, 1}, {4, 0.1}, {5, 0},
{1, 0}, {2, 0}, {3, 1}, {4, 0.2}, {5, 0},
{1, 0}, {2, 0}, {3, 1}, {4, 0.1}, {5, 1},
{1, 1}, {2, 1}, {3, 0}, {4, 0.3}, {5, 0},
{1, 1}, {2, 0}, {3, 0}, {4, 0.4}, {5, 1},
{1, 0}, {2, 1}, {3, 1}, {4, 0.5}, {5, 0}
};
dmlc::DataIter<xgboost::SparsePage>* iter = dmat->RowIterator();
iter->BeforeFirst();
CHECK(iter->Next());
const xgboost::SparsePage& batch = iter->Value();
CHECK_EQ(batch.base_rowid, 0);
CHECK(batch.offset == expected_offset);
CHECK(batch.data == expected_data);
CHECK(!iter->Next());
}