Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support P2P rechunking datetime arrays #8875

Merged
merged 1 commit into from
Sep 17, 2024
Merged

Support P2P rechunking datetime arrays #8875

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions distributed/shuffle/_core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -526,6 +526,12 @@ def handle_unpack_errors(id: ShuffleId) -> Iterator[None]:
raise RuntimeError(f"P2P shuffling {id} failed during unpack phase") from e


def _handle_datetime(buf: Any) -> Any:
if hasattr(buf, "dtype") and buf.dtype.kind in "Mm":
return buf.view("u8")
return buf


def _mean_shard_size(shards: Iterable) -> int:
"""Return estimated mean size in bytes of each shard"""
size = 0
Expand All @@ -534,6 +540,7 @@ def _mean_shard_size(shards: Iterable) -> int:
if not isinstance(shard, int):
# This also asserts that shard is a Buffer and that we didn't forget
# a container or metadata type above
shard = _handle_datetime(shard)
size += memoryview(shard).nbytes
count += 1
if count == 10:
Expand Down
12 changes: 12 additions & 0 deletions distributed/shuffle/tests/test_rechunk.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1524,3 +1524,15 @@ def transition(self, key, start, finish, *args, stimulus_id, **kwargs):
min_count = min(counts.values())
max_count = max(counts.values())
assert min_count >= max_count, counts


@pytest.mark.parametrize("method", ["tasks", "p2p"])
@gen_cluster(client=True)
async def test_rechunk_datetime(c, s, *ws, method):
pd = pytest.importorskip("pandas")

x = pd.date_range("2005-01-01", "2005-01-10").to_numpy(dtype="datetime64[ns]")
dx = da.from_array(x, chunks=10)
result = dx.rechunk(2, method=method)
result = await c.compute(result)
np.testing.assert_array_equal(x, result)
Loading