Description
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
In [1]: import pandas as pd
In [2]: df = pd.DataFrame({"a": [1, 2], "c": [0, 2], "d": ["c", "a"]})
In [3]: df.iloc[:, df['c']] # works fine
Out[3]:
a d
0 1 c
1 2 a
In [4]: df = pd.DataFrame({"a": [1, 2], "c": [0, 2], "d": ["c", "a"]}).convert_dtypes(dtype_backend='pyarrow')
In [5]: df.iloc[:, df['c']] # now, it raises
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
Cell In[5], line 1
----> 1 df.iloc[:, df['c']]
File ~/pandas-dev/pandas/core/indexing.py:1189, in _LocationIndexer.__getitem__(self, key)
1187 if self._is_scalar_access(key):
1188 return self.obj._get_value(*key, takeable=self._takeable)
-> 1189 return self._getitem_tuple(key)
1190 else:
1191 # we by definition only have the 0th axis
1192 axis = self.axis or 0
File ~/pandas-dev/pandas/core/indexing.py:1692, in _iLocIndexer._getitem_tuple(self, tup)
1691 def _getitem_tuple(self, tup: tuple):
-> 1692 tup = self._validate_tuple_indexer(tup)
1693 with suppress(IndexingError):
1694 return self._getitem_lowerdim(tup)
File ~/pandas-dev/pandas/core/indexing.py:975, in _LocationIndexer._validate_tuple_indexer(self, key)
973 for i, k in enumerate(key):
974 try:
--> 975 self._validate_key(k, i)
976 except ValueError as err:
977 raise ValueError(
978 f"Location based indexing can only have [{self._valid_types}] types"
979 ) from err
File ~/pandas-dev/pandas/core/indexing.py:1613, in _iLocIndexer._validate_key(self, key, axis)
1610 raise IndexError(f".iloc requires numeric indexers, got {arr}")
1612 # check that the key does not exceed the maximum size of the index
-> 1613 if len(arr) and (arr.max() >= len_axis or arr.min() < -len_axis):
1614 raise IndexError("positional indexers are out-of-bounds")
1615 else:
AttributeError: 'ArrowExtensionArray' object has no attribute 'max'Issue Description
df.iloc[:, df['c']] works for regular pandas dataframes but raises for pyarrow-backed ones
spotted in narwhals
Expected Behavior
a d
0 1 c
1 2 a
Installed Versions
INSTALLED VERSIONS
commit : 57fd502
python : 3.10.12
python-bits : 64
OS : Linux
OS-release : 5.15.167.4-microsoft-standard-WSL2
Version : #1 SMP Tue Nov 5 00:21:55 UTC 2024
machine : x86_64
processor : x86_64
byteorder : little
LC_ALL : None
LANG : C.UTF-8
LOCALE : en_US.UTF-8
pandas : 3.0.0.dev0+1979.g57fd50221e
numpy : 1.26.4
dateutil : 2.9.0.post0
pip : 25.0.1
Cython : 3.0.12
sphinx : 8.1.3
IPython : 8.33.0
adbc-driver-postgresql: None
adbc-driver-sqlite : None
bs4 : 4.13.3
blosc : None
bottleneck : 1.4.2
fastparquet : 2024.11.0
fsspec : 2025.2.0
html5lib : 1.1
hypothesis : 6.127.5
gcsfs : 2025.2.0
jinja2 : 3.1.5
lxml.etree : 5.3.1
matplotlib : 3.10.1
numba : 0.61.0
numexpr : 2.10.2
odfpy : None
openpyxl : 3.1.5
psycopg2 : 2.9.10
pymysql : 1.4.6
pyarrow : 19.0.1
pyreadstat : 1.2.8
pytest : 8.3.5
python-calamine : None
pytz : 2025.1
pyxlsb : 1.0.10
s3fs : 2025.2.0
scipy : 1.15.2
sqlalchemy : 2.0.38
tables : 3.10.1
tabulate : 0.9.0
xarray : 2024.9.0
xlrd : 2.0.1
xlsxwriter : 3.2.2
zstandard : 0.23.0
tzdata : 2025.1
qtpy : None
pyqt5 : None