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

Use adapters for SparsePageDMatrix (#5092)

Browse Source
This commit is contained in:
Rory Mitchell
2019-12-11 15:59:23 +13:00
committed by GitHub
parent e089e16e3d
commit c7cc657a4d
12 changed files with 437 additions and 253 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
tests/cpp/data/test_adapter.cc
View File

@@ -1,8 +1,6 @@
// Copyright (c) 2019 by Contributors
#include <gtest/gtest.h>
#include <xgboost/c_api.h>
#include <xgboost/data.h>
#include <xgboost/version_config.h>
#include "../../../src/data/adapter.h"
#include "../../../src/data/simple_dmatrix.h"
#include "../../../src/common/timer.h"
@@ -29,71 +27,6 @@ TEST(c_api, CSRAdapter) {
EXPECT_EQ(line2 .GetElement(0).value, 5);
EXPECT_EQ(line2 .GetElement(0).row_idx, 2);
EXPECT_EQ(line2 .GetElement(0).column_idx, 1);
data::SimpleDMatrix dmat(&adapter, std::nan(""), -1);
EXPECT_EQ(dmat.Info().num_col_, 2);
EXPECT_EQ(dmat.Info().num_row_, 3);
EXPECT_EQ(dmat.Info().num_nonzero_, 5);
for (auto &batch : dmat.GetBatches<SparsePage>()) {
for (auto i = 0ull; i < batch.Size(); i++) {
auto inst = batch[i];
for(auto j = 0ull; j < inst.size(); j++)
{
EXPECT_EQ(inst[j].fvalue, data[row_ptr[i] + j]);
EXPECT_EQ(inst[j].index, feature_idx[row_ptr[i] + j]);
}
}
}
}
TEST(c_api, DenseAdapter) {
int m = 3;
int n = 2;
std::vector<float> data = {1, 2, 3, 4, 5, 6};
data::DenseAdapter adapter(data.data(), m, m*n, n);
data::SimpleDMatrix dmat(&adapter, std::numeric_limits<float>::quiet_NaN(), -1);
EXPECT_EQ(dmat.Info().num_col_, 2);
EXPECT_EQ(dmat.Info().num_row_, 3);
EXPECT_EQ(dmat.Info().num_nonzero_, 6);
for (auto &batch : dmat.GetBatches<SparsePage>()) {
for (auto i = 0ull; i < batch.Size(); i++) {
auto inst = batch[i];
for(auto j = 0ull; j < inst.size(); j++)
{
EXPECT_EQ(inst[j].fvalue, data[i*n+j]);
EXPECT_EQ(inst[j].index, j);
}
}
}
}
TEST(c_api, CSCAdapter) {
std::vector<float> data = {1, 3, 2, 4, 5};
std::vector<unsigned> row_idx = {0, 1, 0, 1, 2};
std::vector<size_t> col_ptr = {0, 2, 5};
data::CSCAdapter adapter(col_ptr.data(), row_idx.data(), data.data(), 2, 3);
data::SimpleDMatrix dmat(&adapter, std::numeric_limits<float>::quiet_NaN(), -1);
EXPECT_EQ(dmat.Info().num_col_, 2);
EXPECT_EQ(dmat.Info().num_row_, 3);
EXPECT_EQ(dmat.Info().num_nonzero_, 5);
auto &batch = *dmat.GetBatches<SparsePage>().begin();
auto inst = batch[0];
EXPECT_EQ(inst[0].fvalue, 1);
EXPECT_EQ(inst[0].index, 0);
EXPECT_EQ(inst[1].fvalue, 2);
EXPECT_EQ(inst[1].index, 1);
inst = batch[1];
EXPECT_EQ(inst[0].fvalue, 3);
EXPECT_EQ(inst[0].index, 0);
EXPECT_EQ(inst[1].fvalue, 4);
EXPECT_EQ(inst[1].index, 1);
inst = batch[2];
EXPECT_EQ(inst[0].fvalue, 5);
EXPECT_EQ(inst[0].index, 1);
}
TEST(c_api, CSCAdapterColsMoreThanRows) {
@@ -128,10 +61,3 @@ TEST(c_api, CSCAdapterColsMoreThanRows) {
EXPECT_EQ(inst[3].fvalue, 8);
EXPECT_EQ(inst[3].index, 3);
}
TEST(c_api, FileAdapter) {
std::string filename = "test.libsvm";
CreateBigTestData(filename, 10);
std::unique_ptr<dmlc::Parser<uint32_t>> parser(dmlc::Parser<uint32_t>::Create(filename.c_str(), 0, 1,"auto"));
data::FileAdapter adapter(parser.get());
}