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
2 changed files with 26 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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