Closed
Description
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 master branch of pandas.
Reproducible Example
In [20]: df = pd.DataFrame({'group': pd.Series(dtype='object'), 'str': pd.Series(dtype='object')})
In [21]: df.groupby('group').any()
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-21-d0b9fa3e2ddd> in <module>
----> 1 df.groupby('group').any()
~/.pyenv/versions/3.8.6/envs/beam/lib/python3.8/site-packages/pandas/core/groupby/groupby.py in any(self, skipna)
1804 is True within its respective group, False otherwise.
1805 """
-> 1806 return self._bool_agg("any", skipna)
1807
1808 @final
~/.pyenv/versions/3.8.6/envs/beam/lib/python3.8/site-packages/pandas/core/groupby/groupby.py in _bool_agg(self, val_test, skipna)
1774 return result.astype(inference, copy=False)
1775
-> 1776 return self._get_cythonized_result(
1777 libgroupby.group_any_all,
1778 numeric_only=False,
~/.pyenv/versions/3.8.6/envs/beam/lib/python3.8/site-packages/pandas/core/groupby/groupby.py in _get_cythonized_result(self, base_func, cython_dtype, numeric_only, needs_counts, needs_nullable, needs_mask, pre_processing, post_proce
ssing, **kwargs)
3383 mgr = mgr.get_numeric_data()
3384
-> 3385 res_mgr = mgr.grouped_reduce(blk_func, ignore_failures=True)
3386
3387 if not is_ser and len(res_mgr.items) != len(mgr.items):
~/.pyenv/versions/3.8.6/envs/beam/lib/python3.8/site-packages/pandas/core/internals/managers.py in grouped_reduce(self, func, ignore_failures)
1338 for sb in blk._split():
1339 try:
-> 1340 applied = sb.apply(func)
1341 except (TypeError, NotImplementedError):
1342 if not ignore_failures:
~/.pyenv/versions/3.8.6/envs/beam/lib/python3.8/site-packages/pandas/core/internals/blocks.py in apply(self, func, **kwargs)
388 one
389 """
--> 390 result = func(self.values, **kwargs)
391
392 return self._split_op_result(result)
~/.pyenv/versions/3.8.6/envs/beam/lib/python3.8/site-packages/pandas/core/groupby/groupby.py in blk_func(values)
3342 vals = values
3343 if pre_processing:
-> 3344 vals, inferences = pre_processing(vals)
3345
3346 vals = vals.astype(cython_dtype, copy=False)
~/.pyenv/versions/3.8.6/envs/beam/lib/python3.8/site-packages/pandas/core/groupby/groupby.py in objs_to_bool(vals)
1752 if skipna:
1753 func = np.vectorize(lambda x: bool(x) if not isna(x) else True)
-> 1754 vals = func(vals)
1755 else:
1756 vals = vals.astype(bool, copy=False)
~/.pyenv/versions/3.8.6/envs/beam/lib/python3.8/site-packages/numpy/lib/function_base.py in __call__(self, *args, **kwargs)
2106 vargs.extend([kwargs[_n] for _n in names])
2107
-> 2108 return self._vectorize_call(func=func, args=vargs)
2109
2110 def _get_ufunc_and_otypes(self, func, args):
~/.pyenv/versions/3.8.6/envs/beam/lib/python3.8/site-packages/numpy/lib/function_base.py in _vectorize_call(self, func, args)
2184 res = func()
2185 else:
-> 2186 ufunc, otypes = self._get_ufunc_and_otypes(func=func, args=args)
2187
2188 # Convert args to object arrays first
~/.pyenv/versions/3.8.6/envs/beam/lib/python3.8/site-packages/numpy/lib/function_base.py in _get_ufunc_and_otypes(self, func, args)
2140 args = [asarray(arg) for arg in args]
2141 if builtins.any(arg.size == 0 for arg in args):
-> 2142 raise ValueError('cannot call `vectorize` on size 0 inputs '
2143 'unless `otypes` is set')
2144
ValueError: cannot call `vectorize` on size 0 inputs unless `otypes` is setIssue Description
Some grouped aggregations raise a ValueError (from numpy vectorization code) when operating on an empty DataFrame with an object dtype column. I've only observed this in any and all (perhaps because other aggregations drop the object column by default).
I've only observed this behavior in 1.4.0rc1. I've verified this code works fine in previous pandas versions, but I haven't tested with master.
Expected Behavior
Pandas should produce an empty result, as in previous versions.
Installed Versions
1.4.0rc1