nlargest of multiindex grouper throw type error: nlargest() got an unexpected keyword argument 'axis'

[lf-shaw]

Code Sample

import numpy as np
import pandas as pd

dts = pd.date_range('20180101', periods=10)
iterables = [dts, ['one', 'two']]
idx = pd.MultiIndex.from_product(iterables, names=['first', 'second'])
s = pd.Series(np.random.randn(20), index=idx)
s.groupby('first').nlargest(1)

Problem description

After upgrade to Anaconda 5.2.0, the sample code raises the following exception

TypeError                                 Traceback (most recent call last)
~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, func, *args, **kwargs)
    917             try:
--> 918                 result = self._python_apply_general(f)
    919             except Exception:

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _python_apply_general(self, f)
    935         keys, values, mutated = self.grouper.apply(f, self._selected_obj,
--> 936                                                    self.axis)
    937 

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, f, data, axis)
   2272             group_axes = _get_axes(group)
-> 2273             res = f(group)
   2274             if not _is_indexed_like(res, group_axes):

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in curried_with_axis(x)
    819             def curried_with_axis(x):
--> 820                 return f(x, *args, **kwargs_with_axis)
    821 

TypeError: nlargest() got an unexpected keyword argument 'axis'

During handling of the above exception, another exception occurred:

TypeError                                 Traceback (most recent call last)
~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in wrapper(*args, **kwargs)
    834             try:
--> 835                 return self.apply(curried_with_axis)
    836             except Exception:

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, func, *args, **kwargs)
   3468     def apply(self, func, *args, **kwargs):
-> 3469         return super(SeriesGroupBy, self).apply(func, *args, **kwargs)
   3470 

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, func, *args, **kwargs)
    929                 with _group_selection_context(self):
--> 930                     return self._python_apply_general(f)
    931 

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _python_apply_general(self, f)
    935         keys, values, mutated = self.grouper.apply(f, self._selected_obj,
--> 936                                                    self.axis)
    937 

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, f, data, axis)
   2272             group_axes = _get_axes(group)
-> 2273             res = f(group)
   2274             if not _is_indexed_like(res, group_axes):

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in curried_with_axis(x)
    819             def curried_with_axis(x):
--> 820                 return f(x, *args, **kwargs_with_axis)
    821 

TypeError: nlargest() got an unexpected keyword argument 'axis'

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, func, *args, **kwargs)
    917             try:
--> 918                 result = self._python_apply_general(f)
    919             except Exception:

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _python_apply_general(self, f)
    940             values,
--> 941             not_indexed_same=mutated or self.mutated)
    942 

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _wrap_applied_output(self, keys, values, not_indexed_same)
   3611             return self._concat_objects(keys, values,
-> 3612                                         not_indexed_same=not_indexed_same)
   3613         elif isinstance(values[0], DataFrame):

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _concat_objects(self, keys, values, not_indexed_same)
   1135                                 levels=group_levels, names=group_names,
-> 1136                                 sort=False)
   1137             else:

~\Programs\Anaconda3\lib\site-packages\pandas\core\reshape\concat.py in concat(objs, axis, join, join_axes, ignore_index, keys, levels, names, verify_integrity, sort, copy)
    224                        verify_integrity=verify_integrity,
--> 225                        copy=copy, sort=sort)
    226     return op.get_result()

~\Programs\Anaconda3\lib\site-packages\pandas\core\reshape\concat.py in __init__(self, objs, axis, join, join_axes, keys, levels, names, ignore_index, verify_integrity, copy, sort)
    377 
--> 378         self.new_axes = self._get_new_axes()
    379 

~\Programs\Anaconda3\lib\site-packages\pandas\core\reshape\concat.py in _get_new_axes(self)
    457 
--> 458         new_axes[self.axis] = self._get_concat_axis()
    459         return new_axes

~\Programs\Anaconda3\lib\site-packages\pandas\core\reshape\concat.py in _get_concat_axis(self)
    513             concat_axis = _make_concat_multiindex(indexes, self.keys,
--> 514                                                   self.levels, self.names)
    515 

~\Programs\Anaconda3\lib\site-packages\pandas\core\reshape\concat.py in _make_concat_multiindex(indexes, keys, levels, names)
    594         return MultiIndex(levels=levels, labels=label_list, names=names,
--> 595                           verify_integrity=False)
    596 

~\Programs\Anaconda3\lib\site-packages\pandas\core\indexes\multi.py in __new__(cls, levels, labels, sortorder, names, dtype, copy, name, verify_integrity, _set_identity)
    231             # handles name validation
--> 232             result._set_names(names)
    233 

~\Programs\Anaconda3\lib\site-packages\pandas\core\indexes\multi.py in _set_names(self, names, level, validate)
    694                         'level {}, is already used for level '
--> 695                         '{}.'.format(name, l, used[name]))
    696 

ValueError: Duplicated level name: "first", assigned to level 1, is already used for level 0.

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in wrapper(*args, **kwargs)
    837                 try:
--> 838                     return self.apply(curried)
    839                 except Exception:

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, func, *args, **kwargs)
   3468     def apply(self, func, *args, **kwargs):
-> 3469         return super(SeriesGroupBy, self).apply(func, *args, **kwargs)
   3470 

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, func, *args, **kwargs)
    929                 with _group_selection_context(self):
--> 930                     return self._python_apply_general(f)
    931 

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _python_apply_general(self, f)
    940             values,
--> 941             not_indexed_same=mutated or self.mutated)
    942 

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _wrap_applied_output(self, keys, values, not_indexed_same)
   3611             return self._concat_objects(keys, values,
-> 3612                                         not_indexed_same=not_indexed_same)
   3613         elif isinstance(values[0], DataFrame):

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _concat_objects(self, keys, values, not_indexed_same)
   1135                                 levels=group_levels, names=group_names,
-> 1136                                 sort=False)
   1137             else:

~\Programs\Anaconda3\lib\site-packages\pandas\core\reshape\concat.py in concat(objs, axis, join, join_axes, ignore_index, keys, levels, names, verify_integrity, sort, copy)
    224                        verify_integrity=verify_integrity,
--> 225                        copy=copy, sort=sort)
    226     return op.get_result()

~\Programs\Anaconda3\lib\site-packages\pandas\core\reshape\concat.py in __init__(self, objs, axis, join, join_axes, keys, levels, names, ignore_index, verify_integrity, copy, sort)
    377 
--> 378         self.new_axes = self._get_new_axes()
    379 

~\Programs\Anaconda3\lib\site-packages\pandas\core\reshape\concat.py in _get_new_axes(self)
    457 
--> 458         new_axes[self.axis] = self._get_concat_axis()
    459         return new_axes

~\Programs\Anaconda3\lib\site-packages\pandas\core\reshape\concat.py in _get_concat_axis(self)
    513             concat_axis = _make_concat_multiindex(indexes, self.keys,
--> 514                                                   self.levels, self.names)
    515 

~\Programs\Anaconda3\lib\site-packages\pandas\core\reshape\concat.py in _make_concat_multiindex(indexes, keys, levels, names)
    594         return MultiIndex(levels=levels, labels=label_list, names=names,
--> 595                           verify_integrity=False)
    596 

~\Programs\Anaconda3\lib\site-packages\pandas\core\indexes\multi.py in __new__(cls, levels, labels, sortorder, names, dtype, copy, name, verify_integrity, _set_identity)
    231             # handles name validation
--> 232             result._set_names(names)
    233 

~\Programs\Anaconda3\lib\site-packages\pandas\core\indexes\multi.py in _set_names(self, names, level, validate)
    694                         'level {}, is already used for level '
--> 695                         '{}.'.format(name, l, used[name]))
    696 

ValueError: Duplicated level name: "first", assigned to level 1, is already used for level 0.

During handling of the above exception, another exception occurred:

AttributeError                            Traceback (most recent call last)
~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in wrapper(*args, **kwargs)
    847                     try:
--> 848                         return self._aggregate_item_by_item(name,
    849                                                             *args, **kwargs)

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in __getattr__(self, attr)
    764         raise AttributeError("%r object has no attribute %r" %
--> 765                              (type(self).__name__, attr))
    766 

AttributeError: 'SeriesGroupBy' object has no attribute '_aggregate_item_by_item'

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
<ipython-input-2-2e8f88f2b9dc> in <module>()
      6 idx = pd.MultiIndex.from_product(iterables, names=['first', 'second'])
      7 s = pd.Series(np.random.randn(20), index=idx)
----> 8 s.groupby('first').nlargest(1)

~\Programs\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in wrapper(*args, **kwargs)
    849                                                             *args, **kwargs)
    850                     except (AttributeError):
--> 851                         raise ValueError
    852 
    853         return wrapper

ValueError: 

Expected Output

sample output from pandas 0.22.0 (Anaconda 5.1.0)

first       first       second
2018-01-01  2018-01-01  two       0.488124
2018-01-02  2018-01-02  one       0.884829
2018-01-03  2018-01-03  one       0.476739
2018-01-04  2018-01-04  two      -0.375585
2018-01-05  2018-01-05  two       0.317667
2018-01-06  2018-01-06  two      -1.067373
2018-01-07  2018-01-07  two       1.135441
2018-01-08  2018-01-08  two       0.808737
2018-01-09  2018-01-09  one       1.440924
2018-01-10  2018-01-10  one      -0.204873
dtype: float64

Output of pd.show_versions()

INSTALLED VERSIONS

commit: None
python: 3.6.5.final.0
python-bits: 64
OS: Windows
OS-release: 10
machine: AMD64
processor: Intel64 Family 6 Model 78 Stepping 3, GenuineIntel
byteorder: little
LC_ALL: None
LANG: zh_CN.UTF-8
LOCALE: None.None

pandas: 0.23.0
pytest: 3.5.1
pip: 10.0.1
setuptools: 39.1.0
Cython: 0.28.2
numpy: 1.14.3
scipy: 1.1.0
pyarrow: None
xarray: None
IPython: 6.4.0
sphinx: 1.7.4
patsy: 0.5.0
dateutil: 2.7.3
pytz: 2018.4
blosc: None
bottleneck: 1.2.1
tables: 3.4.3
numexpr: 2.6.5
feather: None
matplotlib: 2.2.2
openpyxl: 2.5.3
xlrd: 1.1.0
xlwt: 1.3.0
xlsxwriter: 1.0.4
lxml: 4.2.1
bs4: 4.6.0
html5lib: 1.0.1
sqlalchemy: 1.2.7
pymysql: 0.8.1
psycopg2: None
jinja2: 2.10
s3fs: None
fastparquet: None
pandas_gbq: None
pandas_datareader: None

[gfyoung]

cc @jreback

[jbachlombardo]

Have received identical as well -- worked using pandas 0.22 but with update am having this issue.

[gfyoung]

Given this report of a regression from 0.22.0 to 0.23.0, marking for 0.23.2.

cc @jreback @jorisvandenbossche

[mroeschke]

Looks to work on master. Could use a test.

In [203]: dts = pd.date_range('20180101', periods=10)
     ...: iterables = [dts, ['one', 'two']]
     ...: idx = pd.MultiIndex.from_product(iterables, names=['first', 'second'])
     ...: s = pd.Series(np.random.randn(20), index=idx)
     ...: s.groupby('first').nlargest(1)
Out[203]:
first       first       second
2018-01-01  2018-01-01  one      -0.176182
2018-01-02  2018-01-02  two      -0.196403
2018-01-03  2018-01-03  two       1.908156
2018-01-04  2018-01-04  one      -0.685376
2018-01-05  2018-01-05  two       0.635422
2018-01-06  2018-01-06  one       1.137039
2018-01-07  2018-01-07  one       0.209114
2018-01-08  2018-01-08  one       0.067952
2018-01-09  2018-01-09  one      -1.112250
2018-01-10  2018-01-10  one       0.002893
dtype: float64

In [204]: pd.__version__
Out[204]: '0.26.0.dev0+682.g08ab156eb'