Description
-
I have checked that this issue has not already been reported.
-
I have confirmed this bug exists on the latest version of pandas.
-
(optional) I have confirmed this bug exists on the master branch of pandas.
# Your code here
df=pd.DataFrame({'a':[1,2,3,3,2],'b':[0,1,1,0,0]})
df['b']=df['b'].astype(np.int8)
df.groupby('a')['b'].diff()
---------------------------------------------------------------------------
NotImplementedError Traceback (most recent call last)
<ipython-input-23-f6026edf0092> in <module>
1 df=pd.DataFrame({'a':[1,2,3,3,2],'b':[0,1,1,0,0]})
2 df['b']=df['b'].astype(np.int8)
----> 3 df.groupby('a')['b'].diff()
~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in wrapper(*args, **kwargs)
815 return self.apply(curried)
816
--> 817 return self._python_apply_general(curried, self._obj_with_exclusions)
818
819 wrapper.__name__ = name
~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _python_apply_general(self, f, data)
926 data after applying f
927 """
--> 928 keys, values, mutated = self.grouper.apply(f, data, self.axis)
929
930 return self._wrap_applied_output(
~\Anaconda3\lib\site-packages\pandas\core\groupby\ops.py in apply(self, f, data, axis)
235 # group might be modified
236 group_axes = group.axes
--> 237 res = f(group)
238 if not _is_indexed_like(res, group_axes, axis):
239 mutated = True
~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in curried(x)
804
805 def curried(x):
--> 806 return f(x, *args, **kwargs)
807
808 # preserve the name so we can detect it when calling plot methods,
~\Anaconda3\lib\site-packages\pandas\core\series.py in diff(self, periods)
2436 {examples}
2437 """
-> 2438 result = algorithms.diff(self.array, periods)
2439 return self._constructor(result, index=self.index).__finalize__(
2440 self, method="diff"
~\Anaconda3\lib\site-packages\pandas\core\algorithms.py in diff(arr, n, axis, stacklevel)
2000 # TODO: can diff_2d dtype specialization troubles be fixed by defining
2001 # out_arr inside diff_2d?
-> 2002 algos.diff_2d(arr, out_arr, n, axis, datetimelike=is_timedelta)
2003 else:
2004 # To keep mypy happy, _res_indexer is a list while res_indexer is
pandas\_libs\algos.pyx in pandas._libs.algos.diff_2d()
NotImplementedError: Problem description
I try to take the difference of dataframe on columns with dtype int8 and int16 but this yields an error. This was working in previous version of pandas, 1.1.5, but not in current version, 1.2.0.
Expected Output
0 NaN
1 NaN
2 NaN
3 -1.0
4 -1.0Output of pd.show_versions()
INSTALLED VERSIONS
commit : 3e89b4c
python : 3.8.6.final.0
python-bits : 64
OS : Windows
OS-release : 10
Version : 10.0.19041
machine : AMD64
processor : Intel64 Family 6 Model 142 Stepping 11, GenuineIntel
byteorder : little
LC_ALL : None
LANG : None
LOCALE : English_United States.1252
pandas : 1.2.0
numpy : 1.19.5
pytz : 2020.5
dateutil : 2.8.1
pip : 20.3.3
setuptools : 49.6.0.post20210108
Cython : 0.29.21
pytest : None
hypothesis : None
sphinx : None
blosc : None
feather : None
xlsxwriter : None
lxml.etree : 4.6.2
html5lib : 1.1
pymysql : None
psycopg2 : None
jinja2 : 2.11.2
IPython : 7.19.0
pandas_datareader: None
bs4 : 4.9.3
bottleneck : None
fsspec : 0.8.5
fastparquet : None
gcsfs : None
matplotlib : 3.3.3
numexpr : 2.7.1
odfpy : None
openpyxl : None
pandas_gbq : None
pyarrow : 2.0.0
pyxlsb : None
s3fs : None
scipy : 1.6.0
sqlalchemy : None
tables : 3.6.1
tabulate : 0.8.7
xarray : 0.16.2
xlrd : None
xlwt : None
numba : 0.52.0