Hello,
It seems unittests are running against very new pandas version that wants
pyarrow (but it does not seems to be available in the archive).
Can you check while self.use_arrow evaluate to True ? That's mostly the root
cause of the failure.
I'll try to have a look when I'll be in front of my computer.
Regards, Adam.
On March 25, 2023 2:55:39 PM GMT+01:00, Andreas Tille <andr...@an3as.eu> wrote:
>Hi,
>
>as you can read in the bug log, there was an upload of a new version of
>tiledb a couple of hours before it has migrated to testing. Thus the
>package remains affected by a testing removal (together with its two
>reverse dependencies tiledb and genomicsdb). To follow the freeze
>policy I reverted the version bump and NMUed tiledb
>2.15.0really2.14.1-0.1 to experimental (since the maintainer did not
>responded).
>
>As we can see tiledb-py does not build against tiledb 2.15.0[1]
>
>I've now forced (Build-)Depends to
> tibtiledb-dev (>= 2.15.0really2.14.1~)
>but it seems Salsa CI autopkgtest does not respect the setting
>
>variables:
> # Build against tiledb in experimental
> RELEASE: 'experimental'
>
>and thus the autopkgtest log does not reproduce the error I've got
>in my local build:
>
>...
>
>=================================== FAILURES
>===================================
>_______________ TestNumpyToArray.test_from_numpy_empty_str[1-0]
>________________
>
>self = <tests.test_libtiledb.TestNumpyToArray object at 0x7fe177722710>
>empty_str = '', num_strs = 1
>
> @pytest.mark.parametrize("empty_str", ["", b""])
> @pytest.mark.parametrize("num_strs", [1, 1000])
> def test_from_numpy_empty_str(self, empty_str, num_strs):
> uri = self.path("test_from_numpy_empty_str")
> np_array = np.asarray([empty_str] * num_strs, dtype="O")
> tiledb.from_numpy(uri, np_array)
>....
> with tiledb.open(uri, "r") as A:
> assert_array_equal(A[:], np_array)
> if has_pandas():
>> assert_array_equal(A.query(use_arrow=True).df[:][""], np_array)
>
>tests/test_libtiledb.py:3356:
>_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
>_.
>/usr/lib/python3/dist-packages/tiledb/multirange_indexing.py:192: in
>__getitem__
> return self if self.return_incomplete else self._run_query()
>_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
>_.
>
>self = <tiledb.multirange_indexing.DataFrameIndexer object at 0x7fe1779ef150>
>
> def _run_query(self) -> Union[DataFrame, Table]:
> if self.pyquery is not None:
> self.pyquery.submit()
>....
> if self.pyquery is None:
> df = DataFrame(self._empty_results)
> elif self.use_arrow:
> with timing("buffer_conversion_time"):
>> table = self.pyquery._buffers_to_pa_table()
>E ModuleNotFoundError: No module named 'pyarrow'
>
>/usr/lib/python3/dist-packages/tiledb/multirange_indexing.py:329:
>ModuleNotFoundError
>_______________ TestNumpyToArray.test_from_numpy_empty_str[1-1]
>________________
>
>self = <tests.test_libtiledb.TestNumpyToArray object at 0x7fe177722490>
>empty_str = b'', num_strs = 1
>
> @pytest.mark.parametrize("empty_str", ["", b""])
> @pytest.mark.parametrize("num_strs", [1, 1000])
> def test_from_numpy_empty_str(self, empty_str, num_strs):
> uri = self.path("test_from_numpy_empty_str")
> np_array = np.asarray([empty_str] * num_strs, dtype="O")
> tiledb.from_numpy(uri, np_array)
>....
> with tiledb.open(uri, "r") as A:
> assert_array_equal(A[:], np_array)
> if has_pandas():
>> assert_array_equal(A.query(use_arrow=True).df[:][""], np_array)
>
>tests/test_libtiledb.py:3356:
>/usr/lib/python3/dist-packages/tiledb/multirange_indexing.py:192: in
>__getitem__
> return self if self.return_incomplete else self._run_query()
>_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
>_.
>
>self = <tiledb.multirange_indexing.DataFrameIndexer object at 0x7fe177a16ed0>
>
>variables:
> # Build against tiledb in experimental
> RELEASE: 'experimental'
> def _run_query(self) -> Union[DataFrame, Table]:
> if self.pyquery is not None:
> self.pyquery.submit()
>....
> if self.pyquery is None:
> df = DataFrame(self._empty_results)
> elif self.use_arrow:
> with timing("buffer_conversion_time"):
>> table = self.pyquery._buffers_to_pa_table()
>E ModuleNotFoundError: No module named 'pyarrow'
>
>/usr/lib/python3/dist-packages/tiledb/multirange_indexing.py:329:
>ModuleNotFoundError
>______________ TestNumpyToArray.test_from_numpy_empty_str[1000-0]
>______________
>
>self = <tests.test_libtiledb.TestNumpyToArray object at 0x7fe177722510>
>empty_str = '', num_strs = 1000
>
> @pytest.mark.parametrize("empty_str", ["", b""])
> @pytest.mark.parametrize("num_strs", [1, 1000])
> def test_from_numpy_empty_str(self, empty_str, num_strs):
> uri = self.path("test_from_numpy_empty_str")
> np_array = np.asarray([empty_str] * num
>
>=================================== FAILURES
>===================================
>_______________ TestNumpyToArray.test_from_numpy_empty_str[1-0]
>________________
>
>self = <tests.test_libtiledb.TestNumpyToArray object at 0x7fe177722710>
>empty_str = '', num_strs = 1
>
> @pytest.mark.parametrize("empty_str", ["", b""])
> @pytest.mark.parametrize("num_strs", [1, 1000])
> def test_from_numpy_empty_str(self, empty_str, num_strs):
> uri = self.path("test_from_numpy_empty_str")
> np_array = np.asarray([empty_str] * num_strs, dtype="O")
> tiledb.from_numpy(uri, np_array)
>....
> with tiledb.open(uri, "r") as A:
> assert_array_equal(A[:], np_array)
> if has_pandas():
>> assert_array_equal(A.query(use_arrow=True).df[:][""], np_array)
>
>tests/test_libtiledb.py:3356:
>...
>
>
>I admit I'm a bit astonished since when tiledb 2.14.1 was available
>in unstable the autopkgtest used to work. Any idea how to fix this
>issue would be welcome.
>
>Kind regards,
> Andreas
>
>[1] https://salsa.debian.org/python-team/packages/tiledb-py/-/pipelines/514328
>
>--
>http://fam-tille.de
