include parameters from reference dataset on subset (fixes #5402) (#5416

) * include parameters from reference dataset on copy * lint * set non-default parameters
microsoft · Aug 28, 2022 · 5079de4 · 5079de4
1 parent b6e2793
commit 5079de4
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 0 deletions.
diff --git a/src/io/dataset.cpp b/src/io/dataset.cpp
@@ -740,6 +740,11 @@ void Dataset::CopyFeatureMapperFrom(const Dataset* dataset) {
   group_feature_cnt_ = dataset->group_feature_cnt_;
   forced_bin_bounds_ = dataset->forced_bin_bounds_;
   feature_need_push_zeros_ = dataset->feature_need_push_zeros_;
+  max_bin_ = dataset->max_bin_;
+  min_data_in_bin_ = dataset->min_data_in_bin_;
+  bin_construct_sample_cnt_ = dataset->bin_construct_sample_cnt_;
+  use_missing_ = dataset->use_missing_;
+  zero_as_missing_ = dataset->zero_as_missing_;
 }
 
 void Dataset::CreateValid(const Dataset* dataset) {

diff --git a/tests/python_package_test/test_basic.py b/tests/python_package_test/test_basic.py
@@ -243,6 +243,14 @@ def test_chunked_dataset_linear():
     valid_data.construct()
 
 
+def test_save_dataset_subset_and_load_from_file(tmp_path):
+    data = np.random.rand(100, 2)
+    params = {'max_bin': 50, 'min_data_in_bin': 10}
+    ds = lgb.Dataset(data, params=params)
+    ds.subset([1, 2, 3, 5, 8]).save_binary(tmp_path / 'subset.bin')
+    lgb.Dataset(tmp_path / 'subset.bin', params=params).construct()
+
+
 def test_subset_group():
     rank_example_dir = Path(__file__).absolute().parents[2] / 'examples' / 'lambdarank'
     X_train, y_train = load_svmlight_file(str(rank_example_dir / 'rank.train'))