BaseSetitemTests.test_setitem_integer_array fails with ValueError
xhochy opened this issue · comments
Failure is without fletcher in the stacktrace, so I'm a bit confused:
tests/test_pandas_extension.py::TestBaseSetitemTests::test_setitem_integer_array[True-fletcher_type7-chunked-list] FAILED
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> traceback >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
self = 0 ['B' 'C']
1 ['A']
2 [None]
3 ['A' 'A']
4 []
dtype: fletcher_chunked[list<item: string>], key = [0, 1, 2], value = ['B', 'C']
def __setitem__(self, key, value):
key = com.apply_if_callable(key, self)
cacher_needs_updating = self._check_is_chained_assignment_possible()
try:
> self._set_with_engine(key, value)
../pandas/pandas/core/series.py:982:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = 0 ['B' 'C']
1 ['A']
2 [None]
3 ['A' 'A']
4 []
dtype: fletcher_chunked[list<item: string>], key = [0, 1, 2], value = ['B', 'C']
def _set_with_engine(self, key, value):
# fails with AttributeError for IntervalIndex
> loc = self.index._engine.get_loc(key)
../pandas/pandas/core/series.py:1015:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
> ???
pandas/_libs/index.pyx:61:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
> ???
E TypeError: '[0, 1, 2]' is an invalid key
pandas/_libs/index.pyx:66: TypeError
During handling of the above exception, another exception occurred:
self = <test_pandas_extension.TestBaseSetitemTests object at 0x12679e450>, data = <FletcherChunkedArray>
[['B', 'C'], ['A'], [None], ['A', 'A'], [], ['B', 'C'],
['A'], [None..., ['B', 'C'],
['A'], [None], ['A', 'A'], []]
Length: 100, dtype: fletcher_chunked[list<item: string>], idx = [0, 1, 2], box_in_series = True
@pytest.mark.parametrize(
"idx",
[[0, 1, 2], pd.array([0, 1, 2], dtype="Int64"), np.array([0, 1, 2])],
ids=["list", "integer-array", "numpy-array"],
)
def test_setitem_integer_array(self, data, idx, box_in_series):
arr = data[:5].copy()
expected = data.take([0, 0, 0, 3, 4])
if box_in_series:
arr = pd.Series(arr)
expected = pd.Series(expected)
> arr[idx] = arr[0]
../pandas/pandas/tests/extension/base/setitem.py:153:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
../pandas/pandas/core/series.py:1008: in __setitem__
self._set_with(key, value)
../pandas/pandas/core/series.py:1051: in _set_with
self._set_labels(key, value)
../pandas/pandas/core/series.py:1065: in _set_labels
self._set_values(indexer, value)
../pandas/pandas/core/series.py:1070: in _set_values
self._data = self._data.setitem(indexer=key, value=value)
../pandas/pandas/core/internals/managers.py:544: in setitem
return self.apply("setitem", **kwargs)
../pandas/pandas/core/internals/managers.py:424: in apply
applied = getattr(b, f)(**kwargs)
../pandas/pandas/core/internals/blocks.py:1816: in setitem
check_setitem_lengths(indexer, value, self.values)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
indexer = array([0, 1, 2]), value = ['B', 'C'], values = <FletcherChunkedArray>
[['B', 'C'], ['A'], [None], ['A', 'A'], []]
Length: 5, dtype: fletcher_chunked[list<item: string>]
def check_setitem_lengths(indexer, value, values) -> None:
"""
Validate that value and indexer are the same length.
An special-case is allowed for when the indexer is a boolean array
and the number of true values equals the length of ``value``. In
this case, no exception is raised.
Parameters
----------
indexer : sequence
Key for the setitem.
value : array-like
Value for the setitem.
values : array-like
Values being set into.
Returns
-------
None
Raises
------
ValueError
When the indexer is an ndarray or list and the lengths don't match.
"""
# boolean with truth values == len of the value is ok too
if isinstance(indexer, (np.ndarray, list)):
if is_list_like(value) and len(indexer) != len(value):
if not (
isinstance(indexer, np.ndarray)
and indexer.dtype == np.bool_
and len(indexer[indexer]) == len(value)
):
raise ValueError(
> "cannot set using a list-like indexer "
"with a different length than the value"
)
E ValueError: cannot set using a list-like indexer with a different length than the value
../pandas/pandas/core/indexers.py:115: ValueError
Note that this test seems to exist only in pandas master currently.
Could be related to the dtype, seeing the same problem with test_setitem_slice and fletcher_chunked[list<item: string>].
This project has been archived as development has ceased around 2021.
With the support of Apache Arrow-backed extension arrays in pandas, the major goal of this project has been fulfilled.