def test_get_average(self):
"""Test averaging bucket resampling."""
data = da.from_array(np.array([[2., 4.], [2., 2.]]))
# Without pre-calculated indices
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_average(data)
result = result.compute()
self.assertEqual(np.nanmax(result), 3.)
self.assertTrue(np.any(np.isnan(result)))
# Use a fill value other than np.nan
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_average(data, fill_value=-1)
result = result.compute()
self.assertEqual(np.max(result), 3.)
self.assertEqual(np.min(result), -1)
self.assertFalse(np.any(np.isnan(result)))
# Test masking all-NaN bins
data = da.from_array(np.array([[np.nan, np.nan], [np.nan, np.nan]]))
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_average(data, mask_all_nan=True)
self.assertTrue(np.all(np.isnan(result)))
# By default all-NaN bins have a value of 0.0
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_average(data)
self.assertEqual(np.nanmax(result), 0.0)
def test_get_bucket_indices(self):
"""Test calculation of array indices."""
# Ensure nothing is calculated
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
self.resampler._get_indices()
x_idxs, y_idxs = da.compute(self.resampler.x_idxs,
self.resampler.y_idxs)
np.testing.assert_equal(x_idxs, np.array([1710, 1710, 1707, 1705]))
np.testing.assert_equal(y_idxs, np.array([465, 465, 459, 455]))
# Additional small test case
adef = create_area_def(area_id='test',
projection={'proj': 'latlong'},
width=2,
height=2,
center=(0, 0),
resolution=10)
lons = da.from_array(np.array(
[-10.0, -9.9, -0.1, 0, 0.1, 9.9, 10.0, -10.1, 0]),
chunks=2)
lats = da.from_array(np.array(
[-10.0, -9.9, -0.1, 0, 0.1, 9.9, 10.0, 0, 10.1]),
chunks=2)
resampler = bucket.BucketResampler(source_lats=lats,
source_lons=lons,
target_area=adef)
resampler._get_indices()
np.testing.assert_equal(resampler.x_idxs,
np.array([-1, 0, 0, 1, 1, 1, -1, -1, -1]))
np.testing.assert_equal(resampler.y_idxs,
np.array([-1, 1, 1, 1, 0, 0, -1, -1, -1]))
def test_get_bucket_indices(self):
"""Test calculation of array indices."""
# Ensure nothing is calculated
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
self.resampler._get_indices()
x_idxs, y_idxs = da.compute(self.resampler.x_idxs,
self.resampler.y_idxs)
self.assertTrue(np.all(x_idxs == np.array([1709, 1709, 1706, 1705])))
self.assertTrue(np.all(y_idxs == np.array([465, 465, 458, 455])))
def test_get_count(self):
"""Test drop-in-a-bucket sum."""
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_count()
result = result.compute()
self.assertTrue(np.max(result) == 2)
self.assertEqual(np.sum(result == 1), 2)
self.assertEqual(np.sum(result == 2), 1)
self.assertTrue(self.resampler.counts is not None)
def test_get_sum(self):
"""Test drop-in-a-bucket sum."""
data = da.from_array(np.array([[2., 2.], [2., 2.]]),
chunks=self.chunks)
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_sum(data)
result = result.compute()
# One bin with two hits, so max value is 2.0
self.assertTrue(np.max(result) == 4.)
# Two bins with the same value
self.assertEqual(np.sum(result == 2.), 2)
# One bin with double the value
self.assertEqual(np.sum(result == 4.), 1)
self.assertEqual(result.shape, self.adef.shape)
# Test that also Xarray.DataArrays work
data = xr.DataArray(data)
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_sum(data)
# One bin with two hits, so max value is 2.0
self.assertTrue(np.max(result) == 4.)
# Two bins with the same value
self.assertEqual(np.sum(result == 2.), 2)
# One bin with double the value
self.assertEqual(np.sum(result == 4.), 1)
self.assertEqual(result.shape, self.adef.shape)
# Test masking all-NaN bins
data = da.from_array(np.array([[np.nan, np.nan], [np.nan, np.nan]]),
chunks=self.chunks)
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_sum(data, mask_all_nan=True)
self.assertTrue(np.all(np.isnan(result)))
# By default all-NaN bins have a value of 0.0
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_sum(data)
self.assertEqual(np.nanmax(result), 0.0)
def test_resample_bucket_fractions(self):
"""Test fraction calculations for categorical data."""
data = da.from_array(np.array([[2, 4], [2, 2]]))
categories = [1, 2, 3, 4]
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_fractions(data, categories=categories)
self.assertEqual(set(categories), set(result.keys()))
res = result[1].compute()
self.assertTrue(np.nanmax(res) == 0.)
res = result[2].compute()
self.assertTrue(np.nanmax(res) == 1.)
self.assertTrue(np.nanmin(res) == 0.5)
res = result[3].compute()
self.assertTrue(np.nanmax(res) == 0.)
res = result[4].compute()
self.assertTrue(np.nanmax(res) == 0.5)
self.assertTrue(np.nanmin(res) == 0.)
# There should be NaN values
self.assertTrue(np.any(np.isnan(res)))
# Use a fill value
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_fractions(data,
categories=categories,
fill_value=-1)
# There should not be any NaN values
for i in categories:
res = result[i].compute()
self.assertFalse(np.any(np.isnan(res)))
self.assertTrue(np.min(res) == -1)
# No categories given, need to compute the data once to get
# the categories
with dask.config.set(scheduler=CustomScheduler(max_computes=1)):
result = self.resampler.get_fractions(data, categories=None)
def _get_average_result(self, data, **kwargs):
"""Compute the bucket average with kwargs and check that no dask computation is performed."""
with dask.config.set(scheduler=CustomScheduler(max_computes=0)):
result = self.resampler.get_average(data, **kwargs)
return result.compute()
