BUG: Aggregation on index of empty dataframe still executes agg function

[gusostow]

Pandas version checks

• I have checked that this issue has not already been reported.

• I have confirmed this bug exists on the latest version of pandas.

• I have confirmed this bug exists on the main branch of pandas.

Reproducible Example

import pandas as pd

df = pd.DataFrame([], index=pd.Index([], name="a"), columns=["b"])
df.groupby("a").agg({"b": lambda x: x.iloc[0]})

IndexError                                Traceback (most recent call last)
Cell In [2], line 4
      1 import pandas as pd
      3 df = pd.DataFrame([], index=pd.Index([], name="a"), columns=["b"])
----> 4 df.groupby("a").agg({"b": lambda x: x.iloc[0]})

File PREFIX/lib/python3.10/site-packages/pandas/core/groupby/generic.py:869, in DataFrameGroupBy.aggregate(self, func, engine, engine_kwargs, *args, **kwargs)
    866 func = maybe_mangle_lambdas(func)
    868 op = GroupByApply(self, func, args, kwargs)
--> 869 result = op.agg()
    870 if not is_dict_like(func) and result is not None:
    871     return result

File PREFIX/lib/python3.10/site-packages/pandas/core/apply.py:168, in Apply.agg(self)
    165     return self.apply_str()
    167 if is_dict_like(arg):
--> 168     return self.agg_dict_like()
    169 elif is_list_like(arg):
    170     # we require a list, but not a 'str'
    171     return self.agg_list_like()

File PREFIX/lib/python3.10/site-packages/pandas/core/apply.py:481, in Apply.agg_dict_like(self)
    478     results = {key: colg.agg(how) for key, how in arg.items()}
    479 else:
    480     # key used for column selection and output
--> 481     results = {
    482         key: obj._gotitem(key, ndim=1).agg(how) for key, how in arg.items()
    483     }
    485 # set the final keys
    486 keys = list(arg.keys())

File PREFIX/lib/python3.10/site-packages/pandas/core/apply.py:482, in <dictcomp>(.0)
    478     results = {key: colg.agg(how) for key, how in arg.items()}
    479 else:
    480     # key used for column selection and output
    481     results = {
--> 482         key: obj._gotitem(key, ndim=1).agg(how) for key, how in arg.items()
    483     }
    485 # set the final keys
    486 keys = list(arg.keys())

File PREFIX/lib/python3.10/site-packages/pandas/core/groupby/generic.py:287, in SeriesGroupBy.aggregate(self, func, engine, engine_kwargs, *args, **kwargs)
    284     return self._python_agg_general(func, *args, **kwargs)
    286 try:
--> 287     return self._python_agg_general(func, *args, **kwargs)
    288 except KeyError:
    289     # TODO: KeyError is raised in _python_agg_general,
    290     #  see test_groupby.test_basic
    291     result = self._aggregate_named(func, *args, **kwargs)

File PREFIX/lib/python3.10/site-packages/pandas/core/groupby/groupby.py:1483, in GroupBy._python_agg_general(self, func, *args, **kwargs)
   1479 output: dict[base.OutputKey, ArrayLike] = {}
   1481 if self.ngroups == 0:
   1482     # agg_series below assumes ngroups > 0
-> 1483     return self._python_apply_general(f, self._selected_obj)
   1485 for idx, obj in enumerate(self._iterate_slices()):
   1486     name = obj.name

File PREFIX/lib/python3.10/site-packages/pandas/core/groupby/groupby.py:1464, in GroupBy._python_apply_general(self, f, data, not_indexed_same)
   1438 @final
   1439 def _python_apply_general(
   1440     self,
   (...)
   1443     not_indexed_same: bool | None = None,
   1444 ) -> DataFrame | Series:
   1445     """
   1446     Apply function f in python space
   1447
   (...)
   1462         data after applying f
   1463     """
-> 1464     values, mutated = self.grouper.apply(f, data, self.axis)
   1466     if not_indexed_same is None:
   1467         not_indexed_same = mutated or self.mutated

File PREFIX/lib/python3.10/site-packages/pandas/core/groupby/ops.py:776, in BaseGrouper.apply(self, f, data, axis)
    766 # getattr pattern for __name__ is needed for functools.partial objects
    767 if len(group_keys) == 0 and getattr(f, "__name__", None) not in [
    768     "idxmin",
    769     "idxmax",
   (...)
    774     #  so we will not have raised even if this is an invalid dtype.
    775     #  So do one dummy call here to raise appropriate TypeError.
--> 776     f(data.iloc[:0])
    778 return result_values, mutated

File PREFIX/lib/python3.10/site-packages/pandas/core/groupby/groupby.py:1476, in GroupBy._python_agg_general.<locals>.<lambda>(x)
   1473 @final
   1474 def _python_agg_general(self, func, *args, **kwargs):
   1475     func = com.is_builtin_func(func)
-> 1476     f = lambda x: func(x, *args, **kwargs)
   1478     # iterate through "columns" ex exclusions to populate output dict
   1479     output: dict[base.OutputKey, ArrayLike] = {}

Cell In [2], line 4, in <lambda>(x)
      1 import pandas as pd
      3 df = pd.DataFrame([], index=pd.Index([], name="a"), columns=["b"])
----> 4 df.groupby("a").agg({"b": lambda x: x.iloc[0]})

File PREFIX/lib/python3.10/site-packages/pandas/core/indexing.py:967, in _LocationIndexer.__getitem__(self, key)
    964 axis = self.axis or 0
    966 maybe_callable = com.apply_if_callable(key, self.obj)
--> 967 return self._getitem_axis(maybe_callable, axis=axis)

File PREFIX/lib/python3.10/site-packages/pandas/core/indexing.py:1523, in _iLocIndexer._getitem_axis(self, key, axis)
   1520     raise TypeError("Cannot index by location index with a non-integer key")
   1522 # validate the location
-> 1523 self._validate_integer(key, axis)
   1525 return self.obj._ixs(key, axis=axis)

File PREFIX/lib/python3.10/site-packages/pandas/core/indexing.py:1455, in _iLocIndexer._validate_integer(self, key, axis)
   1453 len_axis = len(self.obj._get_axis(axis))
   1454 if key >= len_axis or key < -len_axis:
-> 1455     raise IndexError("single positional indexer is out-of-bounds")

IndexError: single positional indexer is out-of-bounds

Issue Description

Aggregating on the index of an empty dataframe still executes the aggregation function once on an empty dataframe.

Expected Behavior

This is a regression. In pandas==1.3.5:

import pandas as pd

df = pd.DataFrame([], index=pd.Index([], name="a"), columns=["b"])
df.groupby("a").agg({"b": lambda x: x.iloc[0]})

print(df)

Empty DataFrame
Columns: [b]
Index: []

Installed Versions

INSTALLED VERSIONS

commit : ca60aab
python : 3.10.6.final.0
python-bits : 64
OS : Linux
OS-release : 4.18.0-348.20.1.el8_5.x86_64
Version : #1 SMP Tue Mar 8 12:56:54 EST 2022
machine : x86_64
processor : x86_64
byteorder : little
LC_ALL : en_US.UTF-8
LANG : en_US.UTF-8
LOCALE : en_US.UTF-8

pandas : 1.4.4
numpy : 1.23.3
pytz : 2022.2.1
dateutil : 2.8.2
setuptools : 65.3.0
pip : 22.2.2
Cython : None
pytest : None
hypothesis : None
sphinx : None
blosc : None
feather : None
xlsxwriter : None
lxml.etree : None
html5lib : None
pymysql : None
psycopg2 : None
jinja2 : None
IPython : 8.5.0
pandas_datareader: None
bs4 : None
bottleneck : None
brotli : None
fastparquet : None
fsspec : None
gcsfs : None
markupsafe : None
matplotlib : None
numba : None
numexpr : None
odfpy : None
openpyxl : None
pandas_gbq : None
pyarrow : None
pyreadstat : None
pyxlsb : None
s3fs : None
scipy : None
snappy : None
sqlalchemy : None
tables : None
tabulate : None
xarray : None
xlrd : None
xlwt : None
zstandard : None

[rhshadrach]

Thanks for the report! I believe this is a duplicate of #47985. If you think this is incorrect, comment here and can reopen.