Groupby sum for all-nan object array should be nan instead of None

Author: snitish

pandas/_libs/groupby.pyx

@@ -727,7 +727,7 @@ def group_sum(
     nobs = np.zeros((<object>out).shape, dtype=np.int64)
     if sum_t is object:
         # For object dtype, fill value should not be 0 (#60229)
-        sumx = np.empty((<object>out).shape, dtype=object)
+        sumx = np.full((<object>out).shape, NAN, dtype=object)
     else:
         # the below is equivalent to `np.zeros_like(out)` but faster
         sumx = np.zeros((<object>out).shape, dtype=(<object>out).base.dtype)
@@ -764,7 +764,10 @@ def group_sum(
                     if uses_mask:
                         isna_result = result_mask[lab, j]
                     else:
-                        isna_result = _treat_as_na(sumx[lab, j], is_datetimelike)
+                        isna_result = (
+                            _treat_as_na(sumx[lab, j], is_datetimelike) and
+                            nobs[lab, j] > 0
+                        )
 
                     if isna_result:
                         # If sum is already NA, don't add to it. This is important for
@@ -799,6 +802,7 @@ def group_sum(
                             compensation[lab, j] = 0
                         sumx[lab, j] = t
                 elif not skipna:
+                    nobs[lab, j] += 1
                     if uses_mask:
                         result_mask[lab, j] = True
                     else:

pandas/tests/groupby/test_categorical.py

@@ -358,7 +358,7 @@ def test_observed(request, using_infer_string, observed):
         expected = cartesian_product_for_groupers(
             expected, [cat1, cat2], list("AB"), fill_value=0
         )
-        expected.loc[expected.C == 0, "C"] = None
+        expected.loc[expected.C == 0, "C"] = np.nan
 
     tm.assert_frame_equal(result, expected)
 

pandas/tests/groupby/test_reductions.py

@@ -514,6 +514,21 @@ def test_sum_skipna_object(skipna):
     tm.assert_series_equal(result, expected)
 
 
+def test_sum_allnan_object(skipna):
+    # GH#60229
+    df = DataFrame(
+        {
+            "val": [np.nan] * 10,
+            "cat": ["A", "B"] * 5,
+        }
+    ).astype({"val": object})
+    expected = Series(
+        [np.nan, np.nan], index=pd.Index(["A", "B"], name="cat"), name="val"
+    ).astype(object)
+    result = df.groupby("cat")["val"].sum(skipna=skipna)
+    tm.assert_series_equal(result, expected)
+
+
 @pytest.mark.parametrize(
     "func, values, dtype, result_dtype",
     [

pandas/tests/groupby/test_timegrouper.py

@@ -113,7 +113,7 @@ def test_groupby_with_timegrouper(self):
                 unit=df.index.unit,
             )
             expected = DataFrame(
-                {"Buyer": None, "Quantity": 0},
+                {"Buyer": np.nan, "Quantity": 0},
                 index=exp_dti,
             )
             # Cast to object to avoid implicit cast when setting entry to "CarlCarlCarl"