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

Fix feature weights with multiple column sampling. (#8100)

Browse Source
This commit is contained in:
Jiaming Yuan 2022-07-22 20:23:05 +08:00 committed by GitHub
parent 4a4e5c7c18
commit 7785d65c8a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 26 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
src/common/random.cc
View File

@ -7,8 +7,7 @@
namespace xgboost {
namespace common {
std::shared_ptr<HostDeviceVector<bst_feature_t>> ColumnSampler::ColSample(
std::shared_ptr<HostDeviceVector<bst_feature_t>> p_features,
float colsample) {
std::shared_ptr<HostDeviceVector<bst_feature_t>> p_features, float colsample) {
if (colsample == 1.0f) {
return p_features;
}
@ -20,19 +19,21 @@ std::shared_ptr<HostDeviceVector<bst_feature_t>> ColumnSampler::ColSample(
auto &new_features = *p_new_features;
if (feature_weights_.size() != 0) {
new_features.HostVector() = WeightedSamplingWithoutReplacement(
p_features->HostVector(), feature_weights_, n);
auto const &h_features = p_features->HostVector();
std::vector<float> weights(h_features.size());
for (size_t i = 0; i < h_features.size(); ++i) {
weights[i] = feature_weights_[h_features[i]];
}
new_features.HostVector() =
WeightedSamplingWithoutReplacement(p_features->HostVector(), weights, n);
} else {
new_features.Resize(features.size());
std::copy(features.begin(), features.end(),
new_features.HostVector().begin());
std::shuffle(new_features.HostVector().begin(),
new_features.HostVector().end(), rng_);
std::copy(features.begin(), features.end(), new_features.HostVector().begin());
std::shuffle(new_features.HostVector().begin(), new_features.HostVector().end(), rng_);
new_features.Resize(n);
}
std::sort(new_features.HostVector().begin(), new_features.HostVector().end());
return p_new_features;
}
} // namespace common
} // namespace xgboost

16
tests/cpp/common/test_random.cc
View File

@ -126,5 +126,21 @@ TEST(ColumnSampler, WeightedSampling) {
EXPECT_NEAR(freq[i], feature_weights[i], 1e-2);
}
}
TEST(ColumnSampler, WeightedMultiSampling) {
size_t constexpr kCols = 32;
std::vector<float> feature_weights(kCols, 0);
for (size_t i = 0; i < feature_weights.size(); ++i) {
feature_weights[i] = i;
}
ColumnSampler cs{0};
float bytree{0.5}, bylevel{0.5}, bynode{0.5};
cs.Init(feature_weights.size(), feature_weights, bytree, bylevel, bynode);
auto feature_set = cs.GetFeatureSet(0);
size_t n_sampled = kCols * bytree * bylevel * bynode;
ASSERT_EQ(feature_set->Size(), n_sampled);
feature_set = cs.GetFeatureSet(1);
ASSERT_EQ(feature_set->Size(), n_sampled);
}
} // namespace common
} // namespace xgboost