From 47e49d04281da3f488bc0d954b366b272c08d316 Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Wed, 4 Dec 2024 12:55:18 -0800
Subject: [PATCH] Fix groupby(as_index=False).size not reseting index (#17499)

closes #17478

Also fixes a bug where the `Series.name` attribute wasn't preserved with `size`

Authors:
  - Matthew Roeschke (https://github.com/mroeschke)
  - GALI PREM SAGAR (https://github.com/galipremsagar)

Approvers:
  - Bradley Dice (https://github.com/bdice)
  - Matthew Murray (https://github.com/Matt711)
  - GALI PREM SAGAR (https://github.com/galipremsagar)

URL: https://github.com/rapidsai/cudf/pull/17499
---
 python/cudf/cudf/core/groupby/groupby.py |  7 +++++--
 python/cudf/cudf/tests/test_groupby.py   | 14 ++++++++++++++
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/python/cudf/cudf/core/groupby/groupby.py b/python/cudf/cudf/core/groupby/groupby.py
index 29ab3b60d9d..0f12f266a95 100644
--- a/python/cudf/cudf/core/groupby/groupby.py
+++ b/python/cudf/cudf/core/groupby/groupby.py
@@ -497,11 +497,14 @@ def size(self):
         col = cudf.core.column.column_empty(
             len(self.obj), "int8", masked=False
         )
-        return (
-            cudf.Series._from_column(col)
+        result = (
+            cudf.Series._from_column(col, name=getattr(self.obj, "name", None))
             .groupby(self.grouping, sort=self._sort, dropna=self._dropna)
             .agg("size")
         )
+        if not self._as_index:
+            result = result.rename("size").reset_index()
+        return result
 
     @_performance_tracking
     def cumcount(self, ascending: bool = True):
diff --git a/python/cudf/cudf/tests/test_groupby.py b/python/cudf/cudf/tests/test_groupby.py
index eae0fd23ef8..d8a2528230e 100644
--- a/python/cudf/cudf/tests/test_groupby.py
+++ b/python/cudf/cudf/tests/test_groupby.py
@@ -4074,3 +4074,17 @@ def test_get_group_list_like():
 
     with pytest.raises(KeyError):
         df.groupby(["a"]).get_group([1])
+
+
+def test_size_as_index_false():
+    df = pd.DataFrame({"a": [1, 2, 1], "b": [1, 2, 3]}, columns=["a", "b"])
+    expected = df.groupby("a", as_index=False).size()
+    result = cudf.from_pandas(df).groupby("a", as_index=False).size()
+    assert_eq(result, expected)
+
+
+def test_size_series_with_name():
+    ser = pd.Series(range(3), name="foo")
+    expected = ser.groupby(ser).size()
+    result = cudf.from_pandas(ser).groupby(ser).size()
+    assert_eq(result, expected)