BUG: Can't cast pyarrow floats to ints

[mattharrison]

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 main branch of pandas.

Reproducible Example

This fails with pyarrow types but works with legacy types:

>>> pd.Series([2.3, 2.5], dtype='float64[pyarrow]').astype('int64[pyarrow]')
---------------------------------------------------------------------------
ArrowInvalid                              Traceback (most recent call last)
Cell In[100], line 1
----> 1 pd.Series([2.3, 2.5], dtype='float64[pyarrow]').astype('int64[pyarrow]')

File ~/.envs/pd22rc/lib/python3.11/site-packages/pandas/core/generic.py:6637, in NDFrame.astype(self, dtype, copy, errors)
   6631     results = [
   6632         ser.astype(dtype, copy=copy, errors=errors) for _, ser in self.items()
   6633     ]
   6635 else:
   6636     # else, only a single dtype is given
-> 6637     new_data = self._mgr.astype(dtype=dtype, copy=copy, errors=errors)
   6638     res = self._constructor_from_mgr(new_data, axes=new_data.axes)
   6639     return res.__finalize__(self, method="astype")

File ~/.envs/pd22rc/lib/python3.11/site-packages/pandas/core/internals/managers.py:431, in BaseBlockManager.astype(self, dtype, copy, errors)
    428 elif using_copy_on_write():
    429     copy = False
--> 431 return self.apply(
    432     "astype",
    433     dtype=dtype,
    434     copy=copy,
    435     errors=errors,
    436     using_cow=using_copy_on_write(),
    437 )

File ~/.envs/pd22rc/lib/python3.11/site-packages/pandas/core/internals/managers.py:364, in BaseBlockManager.apply(self, f, align_keys, **kwargs)
    362         applied = b.apply(f, **kwargs)
    363     else:
--> 364         applied = getattr(b, f)(**kwargs)
    365     result_blocks = extend_blocks(applied, result_blocks)
    367 out = type(self).from_blocks(result_blocks, self.axes)

File ~/.envs/pd22rc/lib/python3.11/site-packages/pandas/core/internals/blocks.py:754, in Block.astype(self, dtype, copy, errors, using_cow, squeeze)
    751         raise ValueError("Can not squeeze with more than one column.")
    752     values = values[0, :]  # type: ignore[call-overload]
--> 754 new_values = astype_array_safe(values, dtype, copy=copy, errors=errors)
    756 new_values = maybe_coerce_values(new_values)
    758 refs = None

File ~/.envs/pd22rc/lib/python3.11/site-packages/pandas/core/dtypes/astype.py:237, in astype_array_safe(values, dtype, copy, errors)
    234     dtype = dtype.numpy_dtype
    236 try:
--> 237     new_values = astype_array(values, dtype, copy=copy)
    238 except (ValueError, TypeError):
    239     # e.g. _astype_nansafe can fail on object-dtype of strings
    240     #  trying to convert to float
    241     if errors == "ignore":

File ~/.envs/pd22rc/lib/python3.11/site-packages/pandas/core/dtypes/astype.py:179, in astype_array(values, dtype, copy)
    175     return values
    177 if not isinstance(values, np.ndarray):
    178     # i.e. ExtensionArray
--> 179     values = values.astype(dtype, copy=copy)
    181 else:
    182     values = _astype_nansafe(values, dtype, copy=copy)

File ~/.envs/pd22rc/lib/python3.11/site-packages/pandas/core/arrays/base.py:709, in ExtensionArray.astype(self, dtype, copy)
    707 if isinstance(dtype, ExtensionDtype):
    708     cls = dtype.construct_array_type()
--> 709     return cls._from_sequence(self, dtype=dtype, copy=copy)
    711 elif lib.is_np_dtype(dtype, "M"):
    712     from pandas.core.arrays import DatetimeArray

File ~/.envs/pd22rc/lib/python3.11/site-packages/pandas/core/arrays/arrow/array.py:281, in ArrowExtensionArray._from_sequence(cls, scalars, dtype, copy)
    277 """
    278 Construct a new ExtensionArray from a sequence of scalars.
    279 """
    280 pa_type = to_pyarrow_type(dtype)
--> 281 pa_array = cls._box_pa_array(scalars, pa_type=pa_type, copy=copy)
    282 arr = cls(pa_array)
    283 return arr

File ~/.envs/pd22rc/lib/python3.11/site-packages/pandas/core/arrays/arrow/array.py:497, in ArrowExtensionArray._box_pa_array(cls, value, pa_type, copy)
    495 else:
    496     try:
--> 497         pa_array = pa_array.cast(pa_type)
    498     except (
    499         pa.ArrowInvalid,
    500         pa.ArrowTypeError,
    501         pa.ArrowNotImplementedError,
    502     ):
    503         if pa.types.is_string(pa_array.type) or pa.types.is_large_string(
    504             pa_array.type
    505         ):
    506             # TODO: Move logic in _from_sequence_of_strings into
    507             # _box_pa_array

File ~/.envs/pd22rc/lib/python3.11/site-packages/pyarrow/table.pxi:565, in pyarrow.lib.ChunkedArray.cast()

File ~/.envs/pd22rc/lib/python3.11/site-packages/pyarrow/compute.py:404, in cast(arr, target_type, safe, options, memory_pool)
    402     else:
    403         options = CastOptions.safe(target_type)
--> 404 return call_function("cast", [arr], options, memory_pool)

File ~/.envs/pd22rc/lib/python3.11/site-packages/pyarrow/_compute.pyx:590, in pyarrow._compute.call_function()

File ~/.envs/pd22rc/lib/python3.11/site-packages/pyarrow/_compute.pyx:385, in pyarrow._compute.Function.call()

File ~/.envs/pd22rc/lib/python3.11/site-packages/pyarrow/error.pxi:154, in pyarrow.lib.pyarrow_internal_check_status()

File ~/.envs/pd22rc/lib/python3.11/site-packages/pyarrow/error.pxi:91, in pyarrow.lib.check_status()

ArrowInvalid: Float value 2.3 was truncated converting to int64

Issue Description

Converting pyarrow floats to integers requires passing through legacy types

Expected Behavior

I would expect the same behavior with legacy pandas types

Installed Versions

---

commit : d4c8d82
python : 3.11.6.final.0
python-bits : 64
OS : Darwin
OS-release : 23.2.0
Version : Darwin Kernel Version 23.2.0: Wed Nov 15 21:53:18 PST 2023; root:xnu-10002.61.3~2/RELEASE_ARM64_T6000
machine : arm64
processor : arm
byteorder : little
LC_ALL : en_US.UTF-8
LANG : None
LOCALE : en_US.UTF-8

pandas : 2.2.0rc0
numpy : 1.26.2
pytz : 2023.3.post1
dateutil : 2.8.2
setuptools : 68.2.2
pip : 23.3.1
Cython : 3.0.7
pytest : None
hypothesis : None
sphinx : None
blosc : None
feather : None
xlsxwriter : None
lxml.etree : 4.9.4
html5lib : None
pymysql : None
psycopg2 : None
jinja2 : 3.1.2
IPython : 8.19.0
pandas_datareader : None
adbc-driver-postgresql: None
adbc-driver-sqlite : None
bs4 : 4.12.2
bottleneck : None
dataframe-api-compat : None
fastparquet : None
fsspec : None
gcsfs : None
matplotlib : 3.8.2
numba : 0.58.1
numexpr : None
odfpy : None
openpyxl : 3.1.2
pandas_gbq : None
pyarrow : 14.0.2
pyreadstat : None
python-calamine : None
pyxlsb : None
s3fs : None
scipy : 1.11.4
sqlalchemy : None
tables : None
tabulate : None
xarray : None
xlrd : None
zstandard : None
tzdata : 2023.3
qtpy : None
pyqt5 : None

[lithomas1]

Hm, I think Arrow casts are safe by default.

Maybe this can be solved by adding a safe keyword to astype.

I'll also add that there's an existing issue for turning on "safe" casting by default - even for numpy,
#45588.