BUG: Getting got an unexpected keyword argument 'engine_kwargs' when doing groupby in 12.1.0 · Issue #55006 · pandas-dev/pandas (original) (raw)

import sys

import pandas as pd

df = pd.concat( [ pd.Series([], dtype="datetime64[ns]", name="key_1"), pd.Series([], dtype=float, name="value_1"), pd.Series([], dtype=float, name="value_2"), pd.Series([], dtype=float, name="value_2"), ], axis=1, )

df.to_markdown(sys.stdout)

df.groupby(["key_1"]).aggregate({"value_1": "sum"})

I'm doing a groupby followed by aggregate, with a dictionary argument. My DataFrame has got duplicated column names, but none of the operations I'm using refer to the duplicate columns.

File "JetBrains/PyCharm2023.1/scratches/scratch_223.py", line 18, in <module>
    df.groupby(["key_1"]).aggregate({"value_1": "sum"})
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/groupby/generic.py", line 1442, in aggregate
    result = op.agg()
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/apply.py", line 175, in agg
    return self.agg_dict_like()
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/apply.py", line 406, in agg_dict_like
    return self.agg_or_apply_dict_like(op_name="agg")
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/apply.py", line 1390, in agg_or_apply_dict_like
    result_index, result_data = self.compute_dict_like(
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/apply.py", line 463, in compute_dict_like
    key_data = [
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/apply.py", line 464, in <listcomp>
    getattr(selected_obj._ixs(indice, axis=1), op_name)(how, **kwargs)
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/series.py", line 4606, in aggregate
    result = op.agg()
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/apply.py", line 1204, in agg
    result = super().agg()
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/apply.py", line 172, in agg
    return self.apply_str()
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/apply.py", line 580, in apply_str
    return self._apply_str(obj, func, *self.args, **self.kwargs)
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/apply.py", line 663, in _apply_str
    return f(*args, **kwargs)
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/series.py", line 6205, in sum
    return NDFrame.sum(self, axis, skipna, numeric_only, min_count, **kwargs)
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/generic.py", line 12055, in sum
    return self._min_count_stat_function(
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/core/generic.py", line 12020, in _min_count_stat_function
    nv.validate_func(name, (), kwargs)
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/compat/numpy/function.py", line 416, in validate_func
    return validation_func(args, kwargs)
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/compat/numpy/function.py", line 88, in __call__
    validate_args_and_kwargs(
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/util/_validators.py", line 223, in validate_args_and_kwargs
    validate_kwargs(fname, kwargs, compat_args)
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/util/_validators.py", line 164, in validate_kwargs
    _check_for_invalid_keys(fname, kwargs, compat_args)
  File "base_error_forward_featurevenv/lib/python3.10/site-packages/pandas/util/_validators.py", line 138, in _check_for_invalid_keys
    raise TypeError(f"{fname}() got an unexpected keyword argument '{bad_arg}'")
TypeError: sum() got an unexpected keyword argument 'engine_kwargs'

This should not throw an exception.

commit : ba1cccd
python : 3.10.11.final.0
python-bits : 64
OS : Darwin
OS-release : 22.6.0
Version : Darwin Kernel Version 22.6.0: Wed Jul 5 22:22:05 PDT 2023; root:xnu-8796.141.3~6/RELEASE_ARM64_T6000
machine : x86_64
processor : i386
byteorder : little
LC_ALL : None
LANG : None
LOCALE : None.UTF-8

pandas : 2.1.0
numpy : 1.25.1
pytz : 2023.3
dateutil : 2.8.2
setuptools : 68.1.0
pip : 23.2.1
Cython : None
pytest : 7.4.0
hypothesis : None
sphinx : None
blosc : None
feather : None
xlsxwriter : None
lxml.etree : 4.9.3
html5lib : None
pymysql : None
psycopg2 : 2.9.5
jinja2 : 3.1.2
IPython : 8.14.0
pandas_datareader : 0.10.0
bs4 : 4.12.2
bottleneck : None
dataframe-api-compat: None
fastparquet : None
fsspec : 2023.6.0
gcsfs : None
matplotlib : 3.6.0
numba : None
numexpr : 2.8.4
odfpy : None
openpyxl : None
pandas_gbq : None
pyarrow : 12.0.0
pyreadstat : None
pyxlsb : None
s3fs : 2023.6.0
scipy : 1.10.1
sqlalchemy : 2.0.9
tables : None
tabulate : 0.9.0
xarray : 2023.7.0
xlrd : None
zstandard : None
tzdata : 2023.3
qtpy : 2.2.0
pyqt5 : None