Multiple aggregations with DatetimeIndexResamplerGroupby raises

[TomAugspurger]

On master, doing a groupby().resample.agg with multiple aggfuncs fails.

In [13]: df = pd.DataFrame({"A": pd.to_datetime(['2015', '2017']), "B": [1, 1]})

In [14]: df
Out[14]:
           A  B
0 2015-01-01  1
1 2017-01-01  1

In [15]: df.set_index("A").groupby([0, 0]).resample("AS")
Out[15]: DatetimeIndexResamplerGroupby [freq=<YearBegin: month=1>, axis=0, closed=left, label=left, convention=e, base=0]

In [16]: df.set_index("A").groupby([0, 0]).resample("AS").agg(['sum', 'count'])
---------------------------------------------------------------------------
Exception                                 Traceback (most recent call last)
<ipython-input-16-5f1c18a8d4ac> in <module>()
----> 1 df.set_index("A").groupby([0, 0]).resample("AS").agg(['sum', 'count'])

~/Envs/pandas-dev/lib/python3.6/site-packages/pandas/pandas/core/resample.py in aggregate(self, arg, *args, **kwargs)
    339
    340         self._set_binner()
--> 341         result, how = self._aggregate(arg, *args, **kwargs)
    342         if result is None:
    343             result = self._groupby_and_aggregate(arg,

~/Envs/pandas-dev/lib/python3.6/site-packages/pandas/pandas/core/base.py in _aggregate(self, arg, *args, **kwargs)
    538             return self._aggregate_multiple_funcs(arg,
    539                                                   _level=_level,
--> 540                                                   _axis=_axis), None
    541         else:
    542             result = None

~/Envs/pandas-dev/lib/python3.6/site-packages/pandas/pandas/core/base.py in _aggregate_multiple_funcs(self, arg, _level, _axis)
    583                 try:
    584                     colg = self._gotitem(col, ndim=1, subset=obj[col])
--> 585                     results.append(colg.aggregate(arg))
    586                     keys.append(col)
    587                 except (TypeError, DataError):

~/Envs/pandas-dev/lib/python3.6/site-packages/pandas/pandas/core/resample.py in aggregate(self, arg, *args, **kwargs)
    339
    340         self._set_binner()
--> 341         result, how = self._aggregate(arg, *args, **kwargs)
    342         if result is None:
    343             result = self._groupby_and_aggregate(arg,

~/Envs/pandas-dev/lib/python3.6/site-packages/pandas/pandas/core/base.py in _aggregate(self, arg, *args, **kwargs)
    538             return self._aggregate_multiple_funcs(arg,
    539                                                   _level=_level,
--> 540                                                   _axis=_axis), None
    541         else:
    542             result = None

~/Envs/pandas-dev/lib/python3.6/site-packages/pandas/pandas/core/base.py in _aggregate_multiple_funcs(self, arg, _level, _axis)
    582             for col in obj:
    583                 try:
--> 584                     colg = self._gotitem(col, ndim=1, subset=obj[col])
    585                     results.append(colg.aggregate(arg))
    586                     keys.append(col)

~/Envs/pandas-dev/lib/python3.6/site-packages/pandas/pandas/core/base.py in _gotitem(self, key, ndim, subset)
    675                        for attr in self._attributes])
    676         self = self.__class__(subset,
--> 677                               groupby=self._groupby[key],
    678                               parent=self,
    679                               **kwargs)

~/Envs/pandas-dev/lib/python3.6/site-packages/pandas/pandas/core/base.py in __getitem__(self, key)
    241         if self._selection is not None:
    242             raise Exception('Column(s) {selection} already selected'
--> 243                             .format(selection=self._selection))
    244
    245         if isinstance(key, (list, tuple, ABCSeries, ABCIndexClass,

Exception: Column(s) B already selected

A single aggfunc is OK.

[jreback]

this is the same as #15072, but slightly different end effects.

[TomAugspurger]

Whoops, yep. I'll add this example to that issue.

[SeedyL]

Reference to this issue was added to #15702 as noted above - i.e. "this is the same as #15072, but slightly different end effects".
#15702 was fixed in #21323 but this issue still seems to exist. I'm using 0.23.4 and still have this problem.

df.groupby('City').resample('D').agg('mean') # works fine

df.groupby('City').resample('D').agg(['mean', 'count']) # doesn't
...
Exception: Column(s) City already selected

Any chance someone can have a look at this?

[jreback]

this is in not yet released 0.24.0

[SeedyL]

Thanks. I got my dates and major releases confused.

[TrentonBush]

When I run the same code as the OP I get a RecursionError. I'm on pandas 1.4.2, python 3.9

In [40]: pd.__version__
Out[40]: '1.4.2'

In [41]: df = pd.DataFrame({"A": pd.to_datetime(['2015', '2017']), "B": [1, 1]})

In [42]: df
Out[42]:
           A  B
0 2015-01-01  1
1 2017-01-01  1

In [43]: df.set_index("A").groupby([0, 0]).resample("AS")
Out[43]: <pandas.core.resample.DatetimeIndexResamplerGroupby object at 0x7feef4038640>

In [44]: df.set_index("A").groupby([0, 0]).resample("AS").agg(['sum', 'count'])
---------------------------------------------------------------------------
RecursionError                            Traceback (most recent call last)
Input In [44], in <cell line: 1>()
----> 1 df.set_index("A").groupby([0, 0]).resample("AS").agg(['sum', 'count'])

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/resample.py:347, in Resampler.aggregate(self, func, *args, **kwargs)
    338 @doc(
    339     _shared_docs["aggregate"],
    340     see_also=_agg_see_also_doc,
   (...)
    344 )
    345 def aggregate(self, func=None, *args, **kwargs):
--> 347     result = ResamplerWindowApply(self, func, args=args, kwargs=kwargs).agg()
    348     if result is None:
    349         how = func

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/apply.py:171, in Apply.agg(self)
    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()
    173 if callable(arg):
    174     f = com.get_cython_func(arg)

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/apply.py:375, in Apply.agg_list_like(self)
    368 try:
    369     # Capture and suppress any warnings emitted by us in the call
    370     # to agg below, but pass through any warnings that were
    371     # generated otherwise.
    372     # This is necessary because of https://bugs.python.org/issue29672
    373     # See GH #43741 for more details
    374     with warnings.catch_warnings(record=True) as record:
--> 375         new_res = colg.aggregate(arg)
    376     if len(record) > 0:
    377         match = re.compile(depr_nuisance_columns_msg.format(".*"))

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/resample.py:347, in Resampler.aggregate(self, func, *args, **kwargs)
    338 @doc(
    339     _shared_docs["aggregate"],
    340     see_also=_agg_see_also_doc,
   (...)
    344 )
    345 def aggregate(self, func=None, *args, **kwargs):
--> 347     result = ResamplerWindowApply(self, func, args=args, kwargs=kwargs).agg()
    348     if result is None:
    349         how = func

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/apply.py:171, in Apply.agg(self)
    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()
    173 if callable(arg):
    174     f = com.get_cython_func(arg)

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/apply.py:375, in Apply.agg_list_like(self)
    368 try:
    369     # Capture and suppress any warnings emitted by us in the call
    370     # to agg below, but pass through any warnings that were
    371     # generated otherwise.
    372     # This is necessary because of https://bugs.python.org/issue29672
    373     # See GH #43741 for more details
    374     with warnings.catch_warnings(record=True) as record:
--> 375         new_res = colg.aggregate(arg)
    376     if len(record) > 0:
    377         match = re.compile(depr_nuisance_columns_msg.format(".*"))

    [... skipping similar frames: Apply.agg at line 171 (985 times), Resampler.aggregate at line 347 (985 times), Apply.agg_list_like at line 375 (984 times)]

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/apply.py:375, in Apply.agg_list_like(self)
    368 try:
    369     # Capture and suppress any warnings emitted by us in the call
    370     # to agg below, but pass through any warnings that were
    371     # generated otherwise.
    372     # This is necessary because of https://bugs.python.org/issue29672
    373     # See GH #43741 for more details
    374     with warnings.catch_warnings(record=True) as record:
--> 375         new_res = colg.aggregate(arg)
    376     if len(record) > 0:
    377         match = re.compile(depr_nuisance_columns_msg.format(".*"))

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/resample.py:347, in Resampler.aggregate(self, func, *args, **kwargs)
    338 @doc(
    339     _shared_docs["aggregate"],
    340     see_also=_agg_see_also_doc,
   (...)
    344 )
    345 def aggregate(self, func=None, *args, **kwargs):
--> 347     result = ResamplerWindowApply(self, func, args=args, kwargs=kwargs).agg()
    348     if result is None:
    349         how = func

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/apply.py:171, in Apply.agg(self)
    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()
    173 if callable(arg):
    174     f = com.get_cython_func(arg)

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/apply.py:367, in Apply.agg_list_like(self)
    365 indices = []
    366 for index, col in enumerate(selected_obj):
--> 367     colg = obj._gotitem(col, ndim=1, subset=selected_obj.iloc[:, index])
    368     try:
    369         # Capture and suppress any warnings emitted by us in the call
    370         # to agg below, but pass through any warnings that were
    371         # generated otherwise.
    372         # This is necessary because of https://bugs.python.org/issue29672
    373         # See GH #43741 for more details
    374         with warnings.catch_warnings(record=True) as record:

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/indexing.py:961, in _LocationIndexer.__getitem__(self, key)
    959     if self._is_scalar_access(key):
    960         return self.obj._get_value(*key, takeable=self._takeable)
--> 961     return self._getitem_tuple(key)
    962 else:
    963     # we by definition only have the 0th axis
    964     axis = self.axis or 0

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/indexing.py:1458, in _iLocIndexer._getitem_tuple(self, tup)
   1456 def _getitem_tuple(self, tup: tuple):
-> 1458     tup = self._validate_tuple_indexer(tup)
   1459     with suppress(IndexingError):
   1460         return self._getitem_lowerdim(tup)

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/indexing.py:769, in _LocationIndexer._validate_tuple_indexer(self, key)
    767 for i, k in enumerate(key):
    768     try:
--> 769         self._validate_key(k, i)
    770     except ValueError as err:
    771         raise ValueError(
    772             "Location based indexing can only have "
    773             f"[{self._valid_types}] types"
    774         ) from err

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/indexing.py:1344, in _iLocIndexer._validate_key(self, key, axis)
   1343 def _validate_key(self, key, axis: int):
-> 1344     if com.is_bool_indexer(key):
   1345         if hasattr(key, "index") and isinstance(key.index, Index):
   1346             if key.index.inferred_type == "integer":

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/common.py:133, in is_bool_indexer(key)
    105 def is_bool_indexer(key: Any) -> bool:
    106     """
    107     Check whether `key` is a valid boolean indexer.
    108 
   (...)
    131         and convert to an ndarray.
    132     """
--> 133     if isinstance(key, (ABCSeries, np.ndarray, ABCIndex)) or (
    134         is_array_like(key) and is_extension_array_dtype(key.dtype)
    135     ):
    136         if key.dtype == np.object_:
    137             key = np.asarray(key)

File ~/miniconda3/envs/gsod/lib/python3.9/site-packages/pandas/core/dtypes/generic.py:45, in create_pandas_abc_type.<locals>._check(cls, inst)
     43 @classmethod  # type: ignore[misc]
     44 def _check(cls, inst) -> bool:
---> 45     return getattr(inst, attr, "_typ") in comp

RecursionError: maximum recursion depth exceeded while calling a Python object

[alexlokhov]

Same here, getting a recursion error.