[REVIEW] Concatenate an empty and non-empty series

CHANGELOG.md

@@ -72,6 +72,7 @@
 - PR #6199 Fix index preservation for dask_cudf parquet
 - PR #6207 Remove shared libs from Java sources jar
 - PR #6212 Update codeowners file
+- PR #6157 Fix issue related to `Series.concat` to concat a non-empty and empty series.
 - PR #6226 Add in some JNI checks for null handles
 
 

python/cudf/cudf/core/reshape.py

@@ -241,7 +241,7 @@ def concat(objs, axis=0, ignore_index=False, sort=None):
 
         df.columns = result_columns.unique()
         if ignore_index:
-            df.index = None
+            df.index = cudf.RangeIndex(len(objs[0]))
             return df
         elif not match_index:
             return df.sort_index()
@@ -282,9 +282,15 @@ def concat(objs, axis=0, ignore_index=False, sort=None):
                 objs, axis=axis, ignore_index=ignore_index, sort=sort
             )
     elif typ is cudf.Series:
-        return cudf.Series._concat(
-            objs, axis=axis, index=None if ignore_index else True
-        )
+        objs = [obj for obj in objs if len(obj)]
+        if len(objs) == 0:
+            return cudf.Series()
+        elif len(objs) == 1 and not ignore_index:
+            return objs[0]
+        else:
+            return cudf.Series._concat(
+                objs, axis=axis, index=None if ignore_index else True
+            )
     elif typ is cudf.MultiIndex:
         return cudf.MultiIndex._concat(objs)
     elif issubclass(typ, cudf.Index):

python/cudf/cudf/tests/test_concat.py

@@ -527,6 +527,39 @@ def test_concat_empty_dataframes(df, other, ignore_index):
         )
 
 
+@pytest.mark.parametrize("ignore_index", [True, False])
+@pytest.mark.parametrize("axis", [0, "index"])
+@pytest.mark.parametrize(
+    "data",
+    [
+        (["a", "b", "c"], ["a", "b", "c"]),
+        (["a", "b", "c"], ["XX", "YY", "ZZ"]),
+    ],
+)
+def test_concat_empty_and_nonempty_series(ignore_index, data, axis):
+    s1 = gd.Series()
+    s2 = gd.Series(data[0])
+    ps1 = s1.to_pandas()
+    ps2 = s2.to_pandas()
+    got = gd.concat([s1, s2], axis=axis, ignore_index=ignore_index)
+    expect = pd.concat([ps1, ps2], axis=axis, ignore_index=ignore_index)
+
+    assert_eq(got, expect)
+
+
+@pytest.mark.parametrize("ignore_index", [True, False])
+@pytest.mark.parametrize("axis", [0, "index"])
+def test_concat_two_empty_series(ignore_index, axis):
+    s1 = gd.Series()
+    s2 = gd.Series()
+    ps1 = s1.to_pandas()
+    ps2 = s2.to_pandas()
+    got = gd.concat([s1, s2], axis=axis, ignore_index=ignore_index)
+    expect = pd.concat([ps1, ps2], axis=axis, ignore_index=ignore_index)
+
+    assert_eq(got, expect)
+
+
 @pytest.mark.parametrize(
     "df1,df2",
     [