Bug#1094417: pandas: test_frame_setitem_dask_array_into_new_col fails

Rebecca N. Palmer rebecca_palmer at zoho.com
Mon Jan 27 23:22:35 GMT 2025


Package: python3-pandas,python3-dask
Version: 2.2.3+dfsg-6,2024.12.1+dfsg-1

The pandas test test_frame_setitem_dask_array_into_new_col is failing in 
Salsa; it looks like assigning a dask array to a DataFrame used to make 
a copy and now does not.

I'm not sure yet whether this is an actual problem - I'm mostly opening 
this bug so I don't forget about it.

__________________ test_frame_setitem_dask_array_into_new_col 
__________________

     @pytest.mark.xfail(
         condition=not IS64,
         reason="dask has different nativesize-int vs int64 type rules",
         strict=False,
     )
     def test_frame_setitem_dask_array_into_new_col():
         # GH#47128

         # dask sets "compute.use_numexpr" to False, so catch the 
current value
         # and ensure to reset it afterwards to avoid impacting other tests
         olduse = pd.get_option("compute.use_numexpr")

         try:
             da = td.versioned_importorskip("dask.array")

             dda = da.array([1, 2])
             df = DataFrame({"a": ["a", "b"]})
             df["b"] = dda
             df["c"] = dda
             df.loc[[False, True], "b"] = 100
             result = df.loc[[1], :]
             expected = DataFrame({"a": ["b"], "b": [100], "c": [2]}, 
index=[1])
 >           tm.assert_frame_equal(result, expected)

pandas/tests/test_downstream.py:259:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
_ _ _ _

left = array([100]), right = array([2]), err_msg = None

     def _raise(left, right, err_msg) -> NoReturn:
         if err_msg is None:
             if left.shape != right.shape:
                 raise_assert_detail(
                     obj, f"{obj} shapes are different", left.shape, 
right.shape
                 )

             diff = 0
             for left_arr, right_arr in zip(left, right):
                 # count up differences
                 if not array_equivalent(left_arr, right_arr, 
strict_nan=strict_nan):
                     diff += 1

             diff = diff * 100.0 / left.size
             msg = f"{obj} values are different ({np.round(diff, 5)} %)"
 >           raise_assert_detail(obj, msg, left, right, 
index_values=index_values)
E           AssertionError: DataFrame.iloc[:, 2] (column name="c") are 
different
E
E           DataFrame.iloc[:, 2] (column name="c") values are different 
(100.0 %)
E           [index]: [1]
E           [left]:  [100]
E           [right]: [2]

pandas/_testing/asserters.py:684: AssertionError



More information about the debian-science-maintainers mailing list