Fix flaky test_flaky_connect_recover_with_retry
(#8556)
#2189
116 fail, 110 skipped, 3 822 pass in 10h 8m 57s
27 files 27 suites 10h 8m 57s ⏱️
4 048 tests 3 822 ✅ 110 💤 116 ❌
50 810 runs 47 367 ✅ 2 301 💤 1 142 ❌
Results for commit b1597b6.
Annotations
Check warning on line 0 in distributed.dashboard.tests.test_scheduler_bokeh
github-actions / Unit Test Results
All 10 runs failed: test_shuffling (distributed.dashboard.tests.test_scheduler_bokeh)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
UserWarning: dask_expr does not support the DataFrameIOFunction protocol for column projection. To enable column projection, please ensure that the signature of `func` includes a `columns=` keyword argument instead.
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:34381', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:43517', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:43929', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
@gen_cluster(client=True, scheduler_kwargs={"dashboard": True})
async def test_shuffling(c, s, a, b):
pytest.importorskip("pyarrow")
dd = pytest.importorskip("dask.dataframe")
ss = Shuffling(s)
> df = dask.datasets.timeseries(
start="2000-01-01",
end="2000-02-01",
dtypes={"x": float, "y": float},
freq="10 s",
)
distributed/dashboard/tests/test_scheduler_bokeh.py:1342:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
../../../miniconda3/envs/dask-distributed/lib/python3.9/site-packages/dask/datasets.py:63: in timeseries
return make_timeseries(
../../../miniconda3/envs/dask-distributed/lib/python3.9/site-packages/dask/dataframe/io/demo.py:434: in make_timeseries
return from_map(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
func = <dask.dataframe.io.demo.MakeDataframePart object at 0x7f5ccc0eb1f0>
args = None
meta = x y
timestamp
2000-01-01 0.249765 -0.919819
divisions = [Timestamp('2000-01-01 00:00:00'), Timestamp('2000-01-02 00:00:00'), Timestamp('2000-01-03 00:00:00'), Timestamp('2000-01-04 00:00:00'), Timestamp('2000-01-05 00:00:00'), Timestamp('2000-01-06 00:00:00'), ...]
label = 'make-timeseries', enforce_metadata = False
iterables = [[([Timestamp('2000-01-01 00:00:00'), Timestamp('2000-01-02 00:00:00')], 1828363483), ([Timestamp('2000-01-02 00:00:00...1-06 00:00:00')], 559906344), ([Timestamp('2000-01-06 00:00:00'), Timestamp('2000-01-07 00:00:00')], 1366879366), ...]]
kwargs = {}
DataFrameIOFunction = <class 'dask.dataframe.io.utils.DataFrameIOFunction'>
FromMap = <class 'dask_expr.io.io.FromMap'>
FromMapProjectable = <class 'dask_expr.io.io.FromMapProjectable'>
lengths = {31}, i = 0
def from_map(
func,
*iterables,
args=None,
meta=no_default,
divisions=None,
label=None,
enforce_metadata=False,
**kwargs,
):
"""Create a dask-expr collection from a custom function map
NOTE: The underlying ``Expr`` object produced by this API
will support column projection (via ``simplify``) if
the ``func`` argument has "columns" in its signature.
"""
from dask.dataframe.io.utils import DataFrameIOFunction
from dask_expr.io import FromMap, FromMapProjectable
if "token" in kwargs:
# This option doesn't really make sense in dask-expr
raise NotImplementedError("dask_expr does not support a token argument.")
lengths = set()
iterables = list(iterables)
for i, iterable in enumerate(iterables):
if not isinstance(iterable, Iterable):
raise ValueError(
f"All elements of `iterables` must be Iterable, got {type(iterable)}"
)
try:
lengths.add(len(iterable))
except (AttributeError, TypeError):
iterables[i] = list(iterable)
lengths.add(len(iterables[i]))
if len(lengths) == 0:
raise ValueError("`from_map` requires at least one Iterable input")
elif len(lengths) > 1:
raise ValueError("All `iterables` must have the same length")
if lengths == {0}:
raise ValueError("All `iterables` must have a non-zero length")
# Check if `func` supports column projection
allow_projection = False
columns_arg_required = False
if param := inspect.signature(func).parameters.get("columns", None):
allow_projection = True
columns_arg_required = param.default is param.empty
if meta is no_default and columns_arg_required:
raise TypeError(
"Argument `func` of `from_map` has a required `columns` "
" parameter and not `meta` provided."
"Either provide `meta` yourself or make `columns` an optional argument."
)
elif isinstance(func, DataFrameIOFunction):
> warnings.warn(
"dask_expr does not support the DataFrameIOFunction "
"protocol for column projection. To enable column "
"projection, please ensure that the signature of `func` "
"includes a `columns=` keyword argument instead."
)
E UserWarning: dask_expr does not support the DataFrameIOFunction protocol for column projection. To enable column projection, please ensure that the signature of `func` includes a `columns=` keyword argument instead.
../../../miniconda3/envs/dask-distributed/lib/python3.9/site-packages/dask_expr/_collection.py:4999: UserWarning
Check warning on line 0 in distributed.protocol.tests.test_highlevelgraph
github-actions / Unit Test Results
10 out of 11 runs failed: test_dataframe_annotations (distributed.protocol.tests.test_highlevelgraph)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 3s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 1s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 1s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 1s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 1s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 1s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 2s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 2s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 2s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 2s]
Raw output
AssertionError: assert 0 == 5
+ where 0 = <distributed.protocol.tests.test_highlevelgraph.ExampleAnnotationPlugin object at 0x7f5c9f0c41c0>.retry_matches
+ and 5 = <dask_expr.expr.Series: expr=Shuffle(416dd28)['a'] + Shuffle(416dd28)['b']>.npartitions
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:38949', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:44805', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:45247', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
@gen_cluster(client=True)
async def test_dataframe_annotations(c, s, a, b):
retries = 5
plugin = ExampleAnnotationPlugin(retries=retries)
s.add_plugin(plugin)
assert plugin in s.plugins.values()
df = dd.from_pandas(
pd.DataFrame(
{"a": np.arange(10, dtype=int), "b": np.arange(10, 0, -1, dtype=float)}
),
npartitions=5,
)
df = df.shuffle("a", max_branch=2)
acol = df["a"]
bcol = df["b"]
with dask.annotate(retries=retries):
df = acol + bcol
with dask.config.set(optimization__fuse__active=False):
rdf = await c.compute(df)
assert rdf.dtypes == np.float64
assert (rdf == 10.0).all()
# There is an annotation match per partition (i.e. task)
> assert plugin.retry_matches == df.npartitions
E AssertionError: assert 0 == 5
E + where 0 = <distributed.protocol.tests.test_highlevelgraph.ExampleAnnotationPlugin object at 0x7f5c9f0c41c0>.retry_matches
E + and 5 = <dask_expr.expr.Series: expr=Shuffle(416dd28)['a'] + Shuffle(416dd28)['b']>.npartitions
distributed/protocol/tests/test_highlevelgraph.py:186: AssertionError
Check warning on line 0 in distributed.shuffle.tests.test_graph
github-actions / Unit Test Results
10 out of 11 runs failed: test_basic (distributed.shuffle.tests.test_graph)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 6s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 1s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 2s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 3s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 2s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 2s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 3s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 3s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 5s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 3s]
Raw output
UserWarning: dask_expr does not support the DataFrameIOFunction protocol for column projection. To enable column projection, please ensure that the signature of `func` includes a `columns=` keyword argument instead.
client = <Client: 'tcp://127.0.0.1:36857' processes=2 threads=2, memory=31.21 GiB>
def test_basic(client):
> df = dd.demo.make_timeseries(freq="15D", partition_freq="30D")
distributed/shuffle/tests/test_graph.py:20:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
../../../miniconda3/envs/dask-distributed/lib/python3.9/site-packages/dask/dataframe/io/demo.py:434: in make_timeseries
return from_map(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
func = <dask.dataframe.io.demo.MakeDataframePart object at 0x7f5c9d6e0ac0>
args = None
meta = name id x y
timestamp
2000-01-01 Norbert 1016 0.731171 0.590149
divisions = [Timestamp('2000-01-01 00:00:00'), Timestamp('2000-01-31 00:00:00'), Timestamp('2000-03-01 00:00:00'), Timestamp('2000-03-31 00:00:00'), Timestamp('2000-04-30 00:00:00'), Timestamp('2000-05-30 00:00:00'), ...]
label = 'make-timeseries', enforce_metadata = False
iterables = [[([Timestamp('2000-01-01 00:00:00'), Timestamp('2000-01-31 00:00:00')], 720267087), ([Timestamp('2000-01-31 00:00:00'...5-30 00:00:00')], 827030214), ([Timestamp('2000-05-30 00:00:00'), Timestamp('2000-06-29 00:00:00')], 1648004478), ...]]
kwargs = {}
DataFrameIOFunction = <class 'dask.dataframe.io.utils.DataFrameIOFunction'>
FromMap = <class 'dask_expr.io.io.FromMap'>
FromMapProjectable = <class 'dask_expr.io.io.FromMapProjectable'>
lengths = {12}, i = 0
def from_map(
func,
*iterables,
args=None,
meta=no_default,
divisions=None,
label=None,
enforce_metadata=False,
**kwargs,
):
"""Create a dask-expr collection from a custom function map
NOTE: The underlying ``Expr`` object produced by this API
will support column projection (via ``simplify``) if
the ``func`` argument has "columns" in its signature.
"""
from dask.dataframe.io.utils import DataFrameIOFunction
from dask_expr.io import FromMap, FromMapProjectable
if "token" in kwargs:
# This option doesn't really make sense in dask-expr
raise NotImplementedError("dask_expr does not support a token argument.")
lengths = set()
iterables = list(iterables)
for i, iterable in enumerate(iterables):
if not isinstance(iterable, Iterable):
raise ValueError(
f"All elements of `iterables` must be Iterable, got {type(iterable)}"
)
try:
lengths.add(len(iterable))
except (AttributeError, TypeError):
iterables[i] = list(iterable)
lengths.add(len(iterables[i]))
if len(lengths) == 0:
raise ValueError("`from_map` requires at least one Iterable input")
elif len(lengths) > 1:
raise ValueError("All `iterables` must have the same length")
if lengths == {0}:
raise ValueError("All `iterables` must have a non-zero length")
# Check if `func` supports column projection
allow_projection = False
columns_arg_required = False
if param := inspect.signature(func).parameters.get("columns", None):
allow_projection = True
columns_arg_required = param.default is param.empty
if meta is no_default and columns_arg_required:
raise TypeError(
"Argument `func` of `from_map` has a required `columns` "
" parameter and not `meta` provided."
"Either provide `meta` yourself or make `columns` an optional argument."
)
elif isinstance(func, DataFrameIOFunction):
> warnings.warn(
"dask_expr does not support the DataFrameIOFunction "
"protocol for column projection. To enable column "
"projection, please ensure that the signature of `func` "
"includes a `columns=` keyword argument instead."
)
E UserWarning: dask_expr does not support the DataFrameIOFunction protocol for column projection. To enable column projection, please ensure that the signature of `func` includes a `columns=` keyword argument instead.
../../../miniconda3/envs/dask-distributed/lib/python3.9/site-packages/dask_expr/_collection.py:4999: UserWarning
Check warning on line 0 in distributed.shuffle.tests.test_graph
github-actions / Unit Test Results
10 out of 11 runs failed: test_raise_on_complex_numbers[csingle] (distributed.shuffle.tests.test_graph)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
Failed: DID NOT RAISE <class 'TypeError'>
dtype = 'csingle'
@pytest.mark.parametrize("dtype", ["csingle", "cdouble", "clongdouble"])
def test_raise_on_complex_numbers(dtype):
df = dd.from_pandas(
pd.DataFrame({"x": pd.array(range(10), dtype=dtype)}), npartitions=5
)
with pytest.raises(
TypeError, match=f"p2p does not support data of type '{df.x.dtype}'"
), dask.config.set({"dataframe.shuffle.method": "p2p"}):
> df.shuffle("x")
E Failed: DID NOT RAISE <class 'TypeError'>
distributed/shuffle/tests/test_graph.py:43: Failed
Check warning on line 0 in distributed.shuffle.tests.test_graph
github-actions / Unit Test Results
10 out of 11 runs failed: test_raise_on_complex_numbers[cdouble] (distributed.shuffle.tests.test_graph)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
Failed: DID NOT RAISE <class 'TypeError'>
dtype = 'cdouble'
@pytest.mark.parametrize("dtype", ["csingle", "cdouble", "clongdouble"])
def test_raise_on_complex_numbers(dtype):
df = dd.from_pandas(
pd.DataFrame({"x": pd.array(range(10), dtype=dtype)}), npartitions=5
)
with pytest.raises(
TypeError, match=f"p2p does not support data of type '{df.x.dtype}'"
), dask.config.set({"dataframe.shuffle.method": "p2p"}):
> df.shuffle("x")
E Failed: DID NOT RAISE <class 'TypeError'>
distributed/shuffle/tests/test_graph.py:43: Failed
Check warning on line 0 in distributed.shuffle.tests.test_graph
github-actions / Unit Test Results
10 out of 11 runs failed: test_raise_on_complex_numbers[clongdouble] (distributed.shuffle.tests.test_graph)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
Failed: DID NOT RAISE <class 'TypeError'>
dtype = 'clongdouble'
@pytest.mark.parametrize("dtype", ["csingle", "cdouble", "clongdouble"])
def test_raise_on_complex_numbers(dtype):
df = dd.from_pandas(
pd.DataFrame({"x": pd.array(range(10), dtype=dtype)}), npartitions=5
)
with pytest.raises(
TypeError, match=f"p2p does not support data of type '{df.x.dtype}'"
), dask.config.set({"dataframe.shuffle.method": "p2p"}):
> df.shuffle("x")
E Failed: DID NOT RAISE <class 'TypeError'>
distributed/shuffle/tests/test_graph.py:43: Failed
Check warning on line 0 in distributed.shuffle.tests.test_graph
github-actions / Unit Test Results
10 out of 11 runs failed: test_raise_on_sparse_data (distributed.shuffle.tests.test_graph)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
Failed: DID NOT RAISE <class 'TypeError'>
def test_raise_on_sparse_data():
df = dd.from_pandas(
pd.DataFrame({"x": pd.array(range(10), dtype="Sparse[float64]")}), npartitions=5
)
with pytest.raises(
TypeError, match="p2p does not support sparse data"
), dask.config.set({"dataframe.shuffle.method": "p2p"}):
> df.shuffle("x")
E Failed: DID NOT RAISE <class 'TypeError'>
distributed/shuffle/tests/test_graph.py:71: Failed
Check warning on line 0 in distributed.shuffle.tests.test_graph
github-actions / Unit Test Results
10 out of 11 runs failed: test_raise_on_non_string_column_name (distributed.shuffle.tests.test_graph)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
Failed: DID NOT RAISE <class 'TypeError'>
def test_raise_on_non_string_column_name():
df = dd.from_pandas(pd.DataFrame({"a": range(10), 1: range(10)}), npartitions=5)
with pytest.raises(
TypeError, match="p2p requires all column names to be str"
), dask.config.set({"dataframe.shuffle.method": "p2p"}):
> df.shuffle("a")
E Failed: DID NOT RAISE <class 'TypeError'>
distributed/shuffle/tests/test_graph.py:79: Failed
Check warning on line 0 in distributed.shuffle.tests.test_graph
github-actions / Unit Test Results
10 out of 11 runs failed: test_basic_state (distributed.shuffle.tests.test_graph)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
UserWarning: dask_expr does not support the DataFrameIOFunction protocol for column projection. To enable column projection, please ensure that the signature of `func` includes a `columns=` keyword argument instead.
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:45997', workers: 0, cores: 0, tasks: 0>
workers = (<Worker 'tcp://127.0.0.1:36755', name: 0, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>, <W... 0>, <Worker 'tcp://127.0.0.1:42615', name: 3, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>)
@gen_cluster([("", 2)] * 4, client=True)
async def test_basic_state(c, s, *workers):
> df = dd.demo.make_timeseries(freq="15D", partition_freq="30D")
distributed/shuffle/tests/test_graph.py:90:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
../../../miniconda3/envs/dask-distributed/lib/python3.9/site-packages/dask/dataframe/io/demo.py:434: in make_timeseries
return from_map(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
func = <dask.dataframe.io.demo.MakeDataframePart object at 0x7f5c9df95130>
args = None
meta = name id x y
timestamp
2000-01-01 Tim 983 -0.170822 0.418217
divisions = [Timestamp('2000-01-01 00:00:00'), Timestamp('2000-01-31 00:00:00'), Timestamp('2000-03-01 00:00:00'), Timestamp('2000-03-31 00:00:00'), Timestamp('2000-04-30 00:00:00'), Timestamp('2000-05-30 00:00:00'), ...]
label = 'make-timeseries', enforce_metadata = False
iterables = [[([Timestamp('2000-01-01 00:00:00'), Timestamp('2000-01-31 00:00:00')], 1185735830), ([Timestamp('2000-01-31 00:00:00...5-30 00:00:00')], 1323701270), ([Timestamp('2000-05-30 00:00:00'), Timestamp('2000-06-29 00:00:00')], 456587806), ...]]
kwargs = {}
DataFrameIOFunction = <class 'dask.dataframe.io.utils.DataFrameIOFunction'>
FromMap = <class 'dask_expr.io.io.FromMap'>
FromMapProjectable = <class 'dask_expr.io.io.FromMapProjectable'>
lengths = {12}, i = 0
def from_map(
func,
*iterables,
args=None,
meta=no_default,
divisions=None,
label=None,
enforce_metadata=False,
**kwargs,
):
"""Create a dask-expr collection from a custom function map
NOTE: The underlying ``Expr`` object produced by this API
will support column projection (via ``simplify``) if
the ``func`` argument has "columns" in its signature.
"""
from dask.dataframe.io.utils import DataFrameIOFunction
from dask_expr.io import FromMap, FromMapProjectable
if "token" in kwargs:
# This option doesn't really make sense in dask-expr
raise NotImplementedError("dask_expr does not support a token argument.")
lengths = set()
iterables = list(iterables)
for i, iterable in enumerate(iterables):
if not isinstance(iterable, Iterable):
raise ValueError(
f"All elements of `iterables` must be Iterable, got {type(iterable)}"
)
try:
lengths.add(len(iterable))
except (AttributeError, TypeError):
iterables[i] = list(iterable)
lengths.add(len(iterables[i]))
if len(lengths) == 0:
raise ValueError("`from_map` requires at least one Iterable input")
elif len(lengths) > 1:
raise ValueError("All `iterables` must have the same length")
if lengths == {0}:
raise ValueError("All `iterables` must have a non-zero length")
# Check if `func` supports column projection
allow_projection = False
columns_arg_required = False
if param := inspect.signature(func).parameters.get("columns", None):
allow_projection = True
columns_arg_required = param.default is param.empty
if meta is no_default and columns_arg_required:
raise TypeError(
"Argument `func` of `from_map` has a required `columns` "
" parameter and not `meta` provided."
"Either provide `meta` yourself or make `columns` an optional argument."
)
elif isinstance(func, DataFrameIOFunction):
> warnings.warn(
"dask_expr does not support the DataFrameIOFunction "
"protocol for column projection. To enable column "
"projection, please ensure that the signature of `func` "
"includes a `columns=` keyword argument instead."
)
E UserWarning: dask_expr does not support the DataFrameIOFunction protocol for column projection. To enable column projection, please ensure that the signature of `func` includes a `columns=` keyword argument instead.
../../../miniconda3/envs/dask-distributed/lib/python3.9/site-packages/dask_expr/_collection.py:4999: UserWarning
Check warning on line 0 in distributed.shuffle.tests.test_graph
github-actions / Unit Test Results
10 out of 11 runs failed: test_multiple_linear (distributed.shuffle.tests.test_graph)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 5s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 1s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 1s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 3s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 2s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 2s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 3s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 3s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 5s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 3s]
Raw output
UserWarning: dask_expr does not support the DataFrameIOFunction protocol for column projection. To enable column projection, please ensure that the signature of `func` includes a `columns=` keyword argument instead.
client = <Client: 'tcp://127.0.0.1:38997' processes=2 threads=2, memory=31.21 GiB>
def test_multiple_linear(client):
> df = dd.demo.make_timeseries(freq="15D", partition_freq="30D")
distributed/shuffle/tests/test_graph.py:114:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
../../../miniconda3/envs/dask-distributed/lib/python3.9/site-packages/dask/dataframe/io/demo.py:434: in make_timeseries
return from_map(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
func = <dask.dataframe.io.demo.MakeDataframePart object at 0x7f5c9f9c2700>
args = None
meta = name id x y
timestamp
2000-01-01 Charlie 988 0.213058 -0.761275
divisions = [Timestamp('2000-01-01 00:00:00'), Timestamp('2000-01-31 00:00:00'), Timestamp('2000-03-01 00:00:00'), Timestamp('2000-03-31 00:00:00'), Timestamp('2000-04-30 00:00:00'), Timestamp('2000-05-30 00:00:00'), ...]
label = 'make-timeseries', enforce_metadata = False
iterables = [[([Timestamp('2000-01-01 00:00:00'), Timestamp('2000-01-31 00:00:00')], 1124569897), ([Timestamp('2000-01-31 00:00:00...5-30 00:00:00')], 1971128239), ([Timestamp('2000-05-30 00:00:00'), Timestamp('2000-06-29 00:00:00')], 174883427), ...]]
kwargs = {}
DataFrameIOFunction = <class 'dask.dataframe.io.utils.DataFrameIOFunction'>
FromMap = <class 'dask_expr.io.io.FromMap'>
FromMapProjectable = <class 'dask_expr.io.io.FromMapProjectable'>
lengths = {12}, i = 0
def from_map(
func,
*iterables,
args=None,
meta=no_default,
divisions=None,
label=None,
enforce_metadata=False,
**kwargs,
):
"""Create a dask-expr collection from a custom function map
NOTE: The underlying ``Expr`` object produced by this API
will support column projection (via ``simplify``) if
the ``func`` argument has "columns" in its signature.
"""
from dask.dataframe.io.utils import DataFrameIOFunction
from dask_expr.io import FromMap, FromMapProjectable
if "token" in kwargs:
# This option doesn't really make sense in dask-expr
raise NotImplementedError("dask_expr does not support a token argument.")
lengths = set()
iterables = list(iterables)
for i, iterable in enumerate(iterables):
if not isinstance(iterable, Iterable):
raise ValueError(
f"All elements of `iterables` must be Iterable, got {type(iterable)}"
)
try:
lengths.add(len(iterable))
except (AttributeError, TypeError):
iterables[i] = list(iterable)
lengths.add(len(iterables[i]))
if len(lengths) == 0:
raise ValueError("`from_map` requires at least one Iterable input")
elif len(lengths) > 1:
raise ValueError("All `iterables` must have the same length")
if lengths == {0}:
raise ValueError("All `iterables` must have a non-zero length")
# Check if `func` supports column projection
allow_projection = False
columns_arg_required = False
if param := inspect.signature(func).parameters.get("columns", None):
allow_projection = True
columns_arg_required = param.default is param.empty
if meta is no_default and columns_arg_required:
raise TypeError(
"Argument `func` of `from_map` has a required `columns` "
" parameter and not `meta` provided."
"Either provide `meta` yourself or make `columns` an optional argument."
)
elif isinstance(func, DataFrameIOFunction):
> warnings.warn(
"dask_expr does not support the DataFrameIOFunction "
"protocol for column projection. To enable column "
"projection, please ensure that the signature of `func` "
"includes a `columns=` keyword argument instead."
)
E UserWarning: dask_expr does not support the DataFrameIOFunction protocol for column projection. To enable column projection, please ensure that the signature of `func` includes a `columns=` keyword argument instead.
../../../miniconda3/envs/dask-distributed/lib/python3.9/site-packages/dask_expr/_collection.py:4999: UserWarning
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[idx-inner] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:38493', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:42937', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:34017', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = 'idx', how = 'inner'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[idx-left] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:34469', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:40547', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:34333', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = 'idx', how = 'left'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[idx-right] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:35841', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:45441', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:40239', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = 'idx', how = 'right'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[idx-outer] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:38929', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:35857', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:46239', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = 'idx', how = 'outer'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[on1-inner] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:33715', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:43907', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:37979', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = ['idx'], how = 'inner'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[on1-left] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:41225', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:40497', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:41293', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = ['idx'], how = 'left'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[on1-right] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:38441', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:33473', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:41751', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = ['idx'], how = 'right'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[on1-outer] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:35629', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:41603', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:45729', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = ['idx'], how = 'outer'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[on2-inner] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:44619', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:37617', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:40373', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = ['idx', 'k'], how = 'inner'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[on2-left] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:33221', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:44507', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:43007', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = ['idx', 'k'], how = 'left'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[on2-right] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:35909', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:34027', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:46455', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = ['idx', 'k'], how = 'right'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[on2-outer] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:39581', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:44197', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:33515', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = ['idx', 'k'], how = 'outer'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[on3-inner] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:46221', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:40317', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:36801', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = ['k', 'idx'], how = 'inner'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[on3-left] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:45737', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:46741', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:42193', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = ['k', 'idx'], how = 'left'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError
Check warning on line 0 in distributed.shuffle.tests.test_merge_column_and_index
github-actions / Unit Test Results
10 out of 11 runs failed: test_merge_unknown_to_unknown[on3-right] (distributed.shuffle.tests.test_merge_column_and_index)
artifacts/macos-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-no_queue-notci1/pytest.xml [took 0s]
artifacts/ubuntu-latest-3.9-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.10-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.11-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.12-queue-notci1/pytest.xml [took 0s]
artifacts/windows-latest-3.9-queue-notci1/pytest.xml [took 0s]
Raw output
AttributeError: 'dict' object has no attribute 'layers'
c = <Client: No scheduler connected>
s = <Scheduler 'tcp://127.0.0.1:46091', workers: 0, cores: 0, tasks: 0>
a = <Worker 'tcp://127.0.0.1:39643', name: 0, status: closed, stored: 0, running: 0/1, ready: 0, comm: 0, waiting: 0>
b = <Worker 'tcp://127.0.0.1:38845', name: 1, status: closed, stored: 0, running: 0/2, ready: 0, comm: 0, waiting: 0>
df_left = k v1
idx
0 0 0
0 1 1
0 2 2
1 0 3
1 1 4
1 2 5
1 3 6
2 0 7
2 1 ... 0 37
9 1 38
9 2 39
9 3 40
9 4 41
9 5 42
9 6 43
10 0 44
10 1 45
10 2 46
10 3 47
df_right = k v1
idx
0 0 0
0 1 1
0 2 2
0 3 3
1 0 4
1 1 5
2 0 6
2 1 7
2 2 ... 1 42
9 2 43
9 3 44
10 0 45
10 1 46
10 2 47
10 3 48
10 4 49
10 5 50
10 6 51
10 7 52
ddf_left_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
ddf_right_unknown = <dask_expr.expr.DataFrame: expr=ClearDivisions(frame=df)>
on = ['k', 'idx'], how = 'right'
@gen_cluster(client=True)
async def test_merge_unknown_to_unknown(
c,
s,
a,
b,
df_left,
df_right,
ddf_left_unknown,
ddf_right_unknown,
on,
how,
):
# Compute expected
expected = df_left.merge(df_right, on=on, how=how)
# Merge unknown to unknown
with dask.config.set({"dataframe.shuffle.method": "p2p"}):
result_graph = ddf_left_unknown.merge(ddf_right_unknown, on=on, how=how)
if not any(
isinstance(layer, (HashJoinP2PLayer, P2PShuffleLayer))
> for layer in result_graph.dask.layers.values()
):
E AttributeError: 'dict' object has no attribute 'layers'
distributed/shuffle/tests/test_merge_column_and_index.py:183: AttributeError