Correct when df is empty and add test case

rapidsai · Apr 13, 2022 · cc5c79e · cc5c79e
1 parent 1509af5
commit cc5c79e
Show file tree

Hide file tree

Showing 2 changed files with 19 additions and 1 deletion.
diff --git a/python/cudf/cudf/core/dataframe.py b/python/cudf/cudf/core/dataframe.py
@@ -5135,7 +5135,7 @@ def _reduce(
             )
             source = self._get_columns_by_label(numeric_cols)
             if source.empty:
-                return source.astype("float64")
+                return Series(index=cudf.StringIndex([]))
 
         axis = source._get_axis_from_axis_arg(axis)
 

diff --git a/python/cudf/cudf/tests/test_dataframe.py b/python/cudf/cudf/tests/test_dataframe.py
@@ -9197,3 +9197,21 @@ def test_std_different_dtypes(data):
 
     with pytest.raises(TypeError):
         gdf.std()
+
+
+@pytest.mark.parametrize(
+    "data",
+    [
+        {
+            "id": ["a", "a", "a", "b", "b", "b", "c", "c", "c"],
+            "val1": ["v", "n", "k", "l", "m", "i", "y", "r", "w"],
+            "val2": ["d", "d", "d", "e", "e", "e", "f", "f", "f"],
+        }
+    ],
+)
+def test_empty_numeric_only(data):
+    gdf = cudf.DataFrame(data)
+    pdf = gdf.to_pandas()
+    expected = pdf.prod(numeric_only=True)
+    actual = gdf.prod(numeric_only=True)
+    assert_eq(expected, actual)