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

Jump to bottom

Updated to set data as Dask array back in Dataset if data is originally stored as Dask array #450

Merged
merged 1 commit into from
Apr 27, 2022
Merged

Updated to set data as Dask array back in Dataset if data is originally stored as Dask array #450

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
30 changes: 23 additions & 7 deletions act/qc/qcfilter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -942,9 +942,9 @@ def datafilter(
ds.qcfilter.datafilter(rm_assessments="Bad")
ds_2 = ds.mean()

print("All_data=", ds_1[var_name].values)
print("All_data =", ds_1[var_name].values)
All_data = 98.86098
print("Bad_Removed=", ds_2[var_name].values)
print("Bad_Removed =", ds_2[var_name].values)
Bad_Removed = 99.15148

"""
Expand All @@ -958,10 +958,18 @@ def datafilter(
qc_var_name = self.check_for_ancillary_qc(var_name, add_if_missing=False, cleanup=False)
if qc_var_name is None:
if verbose:
print(
f'No quality control variable for {var_name} found '
f'in call to .qcfilter.datafilter()'
)
if var_name in ['base_time', 'time_offset']:
continue

try:
if self._obj[var_name].attrs['standard_name'] == 'quality_flag':
continue
except KeyError:
pass

print(f'No quality control variable for {var_name} found '
f'in call to .qcfilter.datafilter()')

continue

data = self.get_masked_data(
Expand All @@ -971,8 +979,16 @@ def datafilter(
ma_fill_value=np_ma,
)

self._obj[var_name].values = data
# If data was orginally stored as Dask array return values to Dataset as Dask array
# else set as Numpy array.
try:
self._obj[var_name].data = dask.array.from_array(
data, chunks=self._obj[var_name].data.chunksize)

except AttributeError:
self._obj[var_name].values = data

# If requested delete quality control variable
if del_qc_var:
del self._obj[qc_var_name]
if verbose:
Expand Down
27 changes: 23 additions & 4 deletions act/tests/test_qc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -718,21 +718,40 @@ def test_qctests_dos():


def test_datafilter():
ds = read_netcdf(EXAMPLE_MET1)
ds = read_netcdf(EXAMPLE_MET1, drop_variables=['base_time', 'time_offset'])
ds.clean.cleanup()

data_var_names = list(ds.data_vars)
qc_var_names = [var_name for var_name in ds.data_vars if var_name.startswith('qc_')]
data_var_names = list(set(data_var_names) - set(qc_var_names))
data_var_names.sort()
qc_var_names.sort()

var_name = 'atmos_pressure'

ds_1 = ds.mean()

ds.qcfilter.add_less_test(var_name, 99, test_assessment='Bad')
ds.qcfilter.datafilter(rm_assessments='Bad')
ds_2 = ds.mean()

ds_filtered = copy.deepcopy(ds)
ds_filtered.qcfilter.datafilter(rm_assessments='Bad', del_qc_var=False)
ds_2 = ds_filtered.mean()
assert np.isclose(ds_1[var_name].values, 98.86, atol=0.01)
assert np.isclose(ds_2[var_name].values, 99.15, atol=0.01)
assert isinstance(ds_1[var_name].data, da.core.Array)

ds_filtered = copy.deepcopy(ds)
ds_filtered.qcfilter.datafilter(rm_assessments='Bad', variables=var_name)
ds_2 = ds_filtered.mean()
assert np.isclose(ds_2[var_name].values, 99.15, atol=0.01)
expected_var_names = sorted(list(set(data_var_names + qc_var_names) - set(['qc_' + var_name])))
assert sorted(list(ds_filtered.data_vars)) == expected_var_names

ds_filtered = copy.deepcopy(ds)
ds_filtered.qcfilter.datafilter(rm_assessments='Bad', del_qc_var=True)
assert sorted(list(ds_filtered.data_vars)) == data_var_names

ds.close()
del ds


def test_qc_remainder():
Expand Down