Closed
Description
Creating a pandas DataFrame using ArrowDtype holding a pyarrow array with extension type fails using pandas 2.0.3:
In [1]: ext_arr = pa.array(pd.period_range("2012", periods=3))
In [2]: df = pa.table({'col': ext_arr}).to_pandas(types_mapper=pd.ArrowDtype)
---------------------------------------------------------------------------
NotImplementedError Traceback (most recent call last)
Cell In[2], line 1
----> 1 df = pa.table({'col': ext_arr}).to_pandas(types_mapper=pd.ArrowDtype)
...
File ~/miniconda3/envs/pandas20/lib/python3.11/site-packages/pandas/core/internals/api.py:73, in make_block(values, placement, klass, ndim, dtype)
70 placement = BlockPlacement(placement)
72 ndim = maybe_infer_ndim(values, placement, ndim)
---> 73 if is_datetime64tz_dtype(values.dtype) or is_period_dtype(values.dtype):
74 # GH#41168 ensure we can pass 1D dt64tz values
75 # More generally, any EA dtype that isn't is_1d_only_ea_dtype
76 values = extract_array(values, extract_numpy=True)
77 values = ensure_block_shape(values, ndim)
File ~/miniconda3/envs/pandas20/lib/python3.11/site-packages/pandas/core/dtypes/common.py:415, in is_period_dtype(arr_or_dtype)
387 """
388 Check whether an array-like or dtype is of the Period dtype.
389
(...)
411 True
412 """
413 if isinstance(arr_or_dtype, ExtensionDtype):
414 # GH#33400 fastpath for dtype object
--> 415 return arr_or_dtype.type is Period
417 if arr_or_dtype is None:
418 return False
File ~/miniconda3/envs/pandas20/lib/python3.11/site-packages/pandas/core/arrays/arrow/dtype.py:150, in ArrowDtype.type(self)
148 return type(pa_type)
149 else:
--> 150 raise NotImplementedError(pa_type)
NotImplementedError: extension<pandas.period<ArrowPeriodType>>
This works on the main branch, although there are still some other issues such as the repr not working, see #54062
Installed versions:
In [5]: pd.show_versions()
/home/joris/miniconda3/envs/pandas20/lib/python3.11/site-packages/_distutils_hack/__init__.py:33: UserWarning: Setuptools is replacing distutils.
warnings.warn("Setuptools is replacing distutils.")
INSTALLED VERSIONS
------------------
commit : 0f437949513225922d851e9581723d82120684a6
python : 3.11.3.final.0
python-bits : 64
OS : Linux
OS-release : 5.4.0-152-generic
Version : #169-Ubuntu SMP Tue Jun 6 22:23:09 UTC 2023
machine : x86_64
processor : x86_64
byteorder : little
LC_ALL : None
LANG : en_US.UTF-8
LOCALE : en_US.UTF-8
pandas : 2.0.3
numpy : 1.24.2
pytz : 2023.3
dateutil : 2.8.2
setuptools : 67.6.1
pip : 23.0.1
Cython : None
pytest : None
hypothesis : None
sphinx : None
blosc : None
feather : None
xlsxwriter : None
lxml.etree : None
html5lib : None
pymysql : None
psycopg2 : None
jinja2 : None
IPython : 8.12.0
pandas_datareader: None
bs4 : None
bottleneck : None
brotli : None
fastparquet : None
fsspec : None
gcsfs : None
matplotlib : None
numba : None
numexpr : None
odfpy : None
openpyxl : None
pandas_gbq : None
pyarrow : 11.0.0
pyreadstat : None
pyxlsb : None
s3fs : None
scipy : None
snappy : None
sqlalchemy : None
tables : None
tabulate : None
xarray : None
xlrd : None
zstandard : None
tzdata : 2023.3
qtpy : None
pyqt5 : None