fix to maintain consistency for apply UDF on empty inputs

Author: ntachukwu

pandas/core/groupby/ops.py

@@ -844,18 +844,22 @@ def apply(
  if not mutated and not _is_indexed_like(res, group_axes, axis):
  mutated = True
  result_values.append(res)
-
  # getattr pattern for __name__ is needed for functools.partial objects
  if len(group_keys) == 0 and getattr(f, "__name__", None) not in [
  "idxmin",
  "idxmax",
  "nanargmin",
  "nanargmax",
  ]:
- # If group_keys is empty, then no function calls have been made,
- # so we will not have raised even if this is an invalid dtype.
- # So do one dummy call here to raise appropriate TypeError.
- f(data.iloc[:0])
+ try:
+ # If group_keys is empty, then no function calls have been made,
+ # so we will not have raised even if this is an invalid dtype.
+ # So do one dummy call here to raise appropriate TypeError.
+ f(data.iloc[:0])
+ except IndexError:
+ # If IndexError is raised,
+ # maintain consistency for all operations on empty groups
+ pass
 
  return result_values, mutated
 

pandas/tests/groupby/test_apply.py

@@ -1331,3 +1331,11 @@ def test_result_name_when_one_group(name):
  expected = Series([1, 2], name=name)
 
  tm.assert_series_equal(result, expected)
+
+
+def test_empty_df():
+ empty_df = pd.DataFrame({"a": [], "b": []})
+ result = empty_df.groupby("a").b.apply(lambda x: x.values[-1])
+ expected = empty_df.groupby("a").b.take([0])
+
+ tm.assert_series_equal(result, expected)