BUG: Fix calling groupBy(...).apply(func) on an empty dataframe invokes func (pandas-dev#48579)

Author: ntachukwu

doc/source/whatsnew/v1.5.1.rst

@@ -77,6 +77,7 @@ Fixed regressions
 - Fixed performance regression in :func:`factorize` when ``na_sentinel`` is not ``None`` and ``sort=False`` (:issue:`48620`)
 - Fixed regression causing an ``AttributeError`` during warning emitted if the provided table name in :meth:`DataFrame.to_sql` and the table name actually used in the database do not match (:issue:`48733`)
 - Fixed :meth:`.DataFrameGroupBy.size` not returning a Series when ``axis=1`` (:issue:`48738`)
+- Fixed Regression in :meth:`DataFrameGroupBy.apply` when user defined function is called on an empty dataframe (:issue:`47985`)
 
 .. ---------------------------------------------------------------------------
 

pandas/core/groupby/ops.py

@@ -787,15 +787,14 @@ 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 len(group_keys) == 0 and getattr(f, "__name__", None) in [
+ "mad",
+ "skew",
+ "sum",
+ "prod",
  ]:
- # If group_keys is empty, then no function calls have been made,
+ #  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])

pandas/tests/groupby/test_apply.py

@@ -1331,3 +1331,28 @@ def test_result_name_when_one_group(name):
  expected = Series([1, 2], name=name)
 
  tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+ "method, op",
+ [
+ ("apply", lambda gb: gb.values[-1]),
+ ("apply", lambda gb: gb["b"].iloc[0]),
+ ("agg", "mad"),
+ ("agg", "skew"),
+ ("agg", "prod"),
+ ("agg", "sum"),
+ ],
+)
+def test_empty_df(method, op):
+ # GH 47985
+ empty_df = DataFrame({"a": [], "b": []})
+ gb = empty_df.groupby("a", group_keys=True)
+ group = getattr(gb, "b")
+
+ result = getattr(group, method)(op)
+ expected = Series(
+ [], name="b", dtype="float64", index=Index([], dtype="float64", name="a")
+ )
+
+ tm.assert_series_equal(result, expected)