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

Fix dask statistics #922

Merged
merged 1 commit into from
Oct 18, 2024
Merged

Fix dask statistics #922

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
9 changes: 5 additions & 4 deletions spectral_cube/dask_spectral_cube.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -781,11 +781,12 @@ def compute_stats(chunk, *args):

count_values, min_values, max_values, sum_values, ssum_values = results.reshape((-1, 5)).T

# all-NAN chunks are possible, so we need to use nan<stat> here
stats = {'npts': count_values.sum(),
'min': min_values.min() * self._unit,
'max': max_values.max() * self._unit,
'sum': sum_values.sum() * self._unit,
'sumsq': ssum_values.sum() * self._unit ** 2}
'min': np.nanmin(min_values) * self._unit,
'max': np.nanmax(max_values) * self._unit,
'sum': np.nansum(sum_values) * self._unit,
'sumsq': np.nansum(ssum_values) * self._unit ** 2}

stats['mean'] = stats['sum'] / stats['npts']

Expand Down
11 changes: 11 additions & 0 deletions spectral_cube/tests/test_dask.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,17 @@ def test_statistics(data_adv):
assert_quantity_allclose(stats['rms'], 0.5759458158839716 * u.K)


def test_statistics_withnans(data_adv):
cube = DaskSpectralCube.read(data_adv).rechunk(chunks=(1, 2, 3))
# shape is 2, 3, 4
cube._data[:,:,:2] = np.nan
# ensure some chunks are all nan
cube.rechunk((1,2,2))
stats = cube.statistics()
for key in ('min', 'max', 'sum'):
assert stats[key] == getattr(cube, key)()


@pytest.mark.skipif(not CASA_INSTALLED, reason='Requires CASA to be installed')
def test_statistics_consistency_casa(data_adv, tmp_path):

Expand Down
Loading