GH-16161 - add comparison to the test & dont write NA (#16195)

h2oai · May 11, 2024 · a4b9436 · a4b9436
1 parent 5ffa80c
commit a4b9436
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/h2o-parsers/h2o-parquet-parser/src/main/java/water/parser/parquet/FrameParquetExporter.java b/h2o-parsers/h2o-parquet-parser/src/main/java/water/parser/parquet/FrameParquetExporter.java
@@ -112,11 +112,9 @@ public void map(Chunk[] cs) {
                                 group = group.append(currColName, cs[j].at8(i));
                                 break;
                             case (T_STR):
-                                if (cs[j].isNA(i)) {
-                                    group = group.append(currColName, "");
-                                } else {
+                                if (!cs[j].isNA(i)) {
                                     group = group.append(currColName, cs[j].atStr(new BufferedString(), i).toString());
-                                } 
+                                }
                                 break;
                             case (T_CAT):
                                 if (cs[j].isNA(i)) {

diff --git a/h2o-py/tests/testdir_misc/pyunit_export_parquet_npe.py b/h2o-py/tests/testdir_misc/pyunit_export_parquet_npe.py
@@ -10,6 +10,8 @@ def test_export_file_npe_gh_16161():
     with tempfile.TemporaryDirectory() as dir:
         df = h2o.create_frame(rows=100, cols=10, string_fraction=0.1, seed=5, seed_for_column_types=25)
         h2o.export_file(df, path=dir, format="parquet", write_checksum=False)
+        df2 = h2o.import_file(dir)
+        assert pyunit_utils.compare_frames(df, df2, tol_numeric=1e-10, numElements=0)
 
 
 if __name__ == "__main__":