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

Categorical data support in CPU sketching. (#7221)

Browse Source
This commit is contained in:
Jiaming Yuan
2021-09-17 04:37:09 +08:00
committed by GitHub
parent 9f63d6fead
commit 31c1e13f90
7 changed files with 129 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
tests/cpp/common/test_hist_util.cu
View File

@@ -1,3 +1,6 @@
/*!
* Copyright 2019-2021 by XGBoost Contributors
*/
#include <dmlc/filesystem.h>
#include <gtest/gtest.h>
@@ -126,43 +129,15 @@ TEST(HistUtil, DeviceSketchCategoricalAsNumeric) {
}
}
void TestCategoricalSketch(size_t n, size_t num_categories, int32_t num_bins, bool weighted) {
auto x = GenerateRandomCategoricalSingleColumn(n, num_categories);
auto dmat = GetDMatrixFromData(x, n, 1);
dmat->Info().feature_types.HostVector().push_back(FeatureType::kCategorical);
if (weighted) {
std::vector<float> weights(n, 0);
SimpleLCG lcg;
SimpleRealUniformDistribution<float> dist(0, 1);
for (auto& v : weights) {
v = dist(&lcg);
}
dmat->Info().weights_.HostVector() = weights;
}
ASSERT_EQ(dmat->Info().feature_types.Size(), 1);
auto cuts = DeviceSketch(0, dmat.get(), num_bins);
std::sort(x.begin(), x.end());
auto n_uniques = std::unique(x.begin(), x.end()) - x.begin();
ASSERT_NE(n_uniques, x.size());
ASSERT_EQ(cuts.TotalBins(), n_uniques);
ASSERT_EQ(n_uniques, num_categories);
auto& values = cuts.cut_values_.HostVector();
ASSERT_TRUE(std::is_sorted(values.cbegin(), values.cend()));
auto is_unique = (std::unique(values.begin(), values.end()) - values.begin()) == n_uniques;
ASSERT_TRUE(is_unique);
x.resize(n_uniques);
for (size_t i = 0; i < n_uniques; ++i) {
ASSERT_EQ(x[i], values[i]);
}
}
TEST(HistUtil, DeviceSketchCategoricalFeatures) {
TestCategoricalSketch(1000, 256, 32, false);
TestCategoricalSketch(1000, 256, 32, true);
TestCategoricalSketch(1000, 256, 32, false,
[](DMatrix *p_fmat, int32_t num_bins) {
return DeviceSketch(0, p_fmat, num_bins);
});
TestCategoricalSketch(1000, 256, 32, true,
[](DMatrix *p_fmat, int32_t num_bins) {
return DeviceSketch(0, p_fmat, num_bins);
});
}
void TestMixedSketch() {