def test_calc_perc(self, transpose):
ens = ensembles.create_ensemble(self.nc_datasets_simple)
if transpose:
ens = ens.transpose()
out1 = ensembles.ensemble_percentiles(ens, split=True)
np.testing.assert_array_equal(
np.percentile(ens["tg_mean"].isel(time=0, lon=5, lat=5), 10),
out1["tg_mean_p10"].isel(time=0, lon=5, lat=5),
)
np.testing.assert_array_equal(
np.percentile(ens["tg_mean"].isel(time=0, lon=5, lat=5), 50),
out1["tg_mean_p50"].isel(time=0, lon=5, lat=5),
)
np.testing.assert_array_equal(
np.percentile(ens["tg_mean"].isel(time=0, lon=5, lat=5), 90),
out1["tg_mean_p90"].isel(time=0, lon=5, lat=5),
)
assert np.all(out1["tg_mean_p90"] > out1["tg_mean_p50"])
assert np.all(out1["tg_mean_p50"] > out1["tg_mean_p10"])
out2 = ensembles.ensemble_percentiles(ens, values=(25, 75))
assert np.all(out2["tg_mean_p75"] > out2["tg_mean_p25"])
assert "Computation of the percentiles on" in out1.attrs[
"xclim_history"]
out3 = ensembles.ensemble_percentiles(ens, split=False)
xr.testing.assert_equal(out1["tg_mean_p10"],
out3.tg_mean.sel(percentiles=10, drop=True))
def test_calc_perc_dask(self, keep_chunk_size):
ens = ensembles.create_ensemble(self.nc_datasets_simple)
out2 = ensembles.ensemble_percentiles(ens.chunk({"time": 2}),
keep_chunk_size=keep_chunk_size,
split=False)
out1 = ensembles.ensemble_percentiles(ens.load(), split=False)
np.testing.assert_array_equal(out1["tg_mean"], out2["tg_mean"])
def test_calc_perc_dask(self, keep_chunk_size):
ens = ensembles.create_ensemble(self.nc_files_simple)
out2 = ensembles.ensemble_percentiles(
ens.chunk({"time": 2}), values=(10, 50, 90), keep_chunk_size=keep_chunk_size
)
out1 = ensembles.ensemble_percentiles(ens.load())
np.testing.assert_array_equal(out1["tg_mean_p10"], out2["tg_mean_p10"])
np.testing.assert_array_equal(out1["tg_mean_p50"], out2["tg_mean_p50"])
np.testing.assert_array_equal(out1["tg_mean_p90"], out2["tg_mean_p90"])
def test_calc_perc_blocks(self):
ens = ensembles.create_ensemble(self.nc_files_simple)
out1 = ensembles.ensemble_percentiles(ens)
out2 = ensembles.ensemble_percentiles(ens,
values=(10, 50, 90),
time_block=10)
np.testing.assert_array_equal(out1["tg_mean_p10"], out2["tg_mean_p10"])
np.testing.assert_array_equal(out1["tg_mean_p50"], out2["tg_mean_p50"])
np.testing.assert_array_equal(out1["tg_mean_p90"], out2["tg_mean_p90"])
def test_calc_perc(self):
ens = ensembles.create_ensemble(self.nc_files_simple)
out1 = ensembles.ensemble_percentiles(ens)
np.testing.assert_array_equal(
np.percentile(ens["tg_mean"][:, 0, 5, 5], 10),
out1["tg_mean_p10"][0, 5, 5])
np.testing.assert_array_equal(
np.percentile(ens["tg_mean"][:, 0, 5, 5], 50),
out1["tg_mean_p50"][0, 5, 5])
np.testing.assert_array_equal(
np.percentile(ens["tg_mean"][:, 0, 5, 5], 90),
out1["tg_mean_p90"][0, 5, 5])
assert np.all(out1["tg_mean_p90"] > out1["tg_mean_p50"])
assert np.all(out1["tg_mean_p50"] > out1["tg_mean_p10"])
out1 = ensembles.ensemble_percentiles(ens, values=(25, 75))
assert np.all(out1["tg_mean_p75"] > out1["tg_mean_p25"])
def make_ensemble(files: List[Path],
percentiles: List[int],
average_dims: Optional[Tuple[str]] = None) -> None:
ensemble = ensembles.create_ensemble(files)
# make sure we have data starting in 1950
ensemble = ensemble.sel(time=(ensemble.time.dt.year >= 1950))
# If data is in day of year, percentiles won't make sense.
# Convert to "days since" (base will be the time coordinate)
for v in ensemble.data_vars:
if ensemble[v].attrs.get('is_dayofyear', 0) == 1:
ensemble[v] = doy_to_days_since(ensemble[v])
if average_dims is not None:
ensemble = ensemble.mean(dim=average_dims)
ensemble_percentiles = ensembles.ensemble_percentiles(ensemble,
values=percentiles)
# Doy data converted previously is converted back.
for v in ensemble_percentiles.data_vars:
if ensemble_percentiles[v].attrs.get('units',
'').startswith('days after'):
ensemble_percentiles[v] = days_since_to_doy(
ensemble_percentiles[v])
# Depending on the datasets, I've found that writing the netcdf could hang
# if the dataset was not loaded explicitely previously... Not sure why.
# The datasets should be pretty small when computing the ensembles, so this is
# a best effort at working around what looks like a bug in either xclim or xarray.
# The xarray documentation mentions: 'this method can be necessary when working
# with many file objects on disk.'
ensemble_percentiles.load()
return ensemble_percentiles
def test_calc_perc(self, transpose):
ens = ensembles.create_ensemble(self.nc_files_simple)
if transpose:
ens = ens.transpose()
out1 = ensembles.ensemble_percentiles(ens)
np.testing.assert_array_equal(
np.percentile(ens["tg_mean"].isel(time=0, lon=5, lat=5), 10),
out1["tg_mean_p10"].isel(time=0, lon=5, lat=5),
)
np.testing.assert_array_equal(
np.percentile(ens["tg_mean"].isel(time=0, lon=5, lat=5), 50),
out1["tg_mean_p50"].isel(time=0, lon=5, lat=5),
)
np.testing.assert_array_equal(
np.percentile(ens["tg_mean"].isel(time=0, lon=5, lat=5), 90),
out1["tg_mean_p90"].isel(time=0, lon=5, lat=5),
)
assert np.all(out1["tg_mean_p90"] > out1["tg_mean_p50"])
assert np.all(out1["tg_mean_p50"] > out1["tg_mean_p10"])
out1 = ensembles.ensemble_percentiles(ens, values=(25, 75))
assert np.all(out1["tg_mean_p75"] > out1["tg_mean_p25"])
def test_calc_perc_nans(self):
ens = ensembles.create_ensemble(self.nc_datasets_simple).load()
ens.tg_mean[2, 0, 5, 5] = np.nan
ens.tg_mean[2, 7, 5, 5] = np.nan
out1 = ensembles.ensemble_percentiles(ens, split=True)
masked_arr = np.ma.fix_invalid(ens["tg_mean"][:, 0, 5, 5])
np.testing.assert_array_almost_equal(
mquantiles(masked_arr, 0.10, alphap=1, betap=1),
out1["tg_mean_p10"][0, 5, 5],
)
masked_arr = np.ma.fix_invalid(ens["tg_mean"][:, 7, 5, 5])
np.testing.assert_array_almost_equal(
mquantiles(masked_arr, 0.10, alphap=1, betap=1),
out1["tg_mean_p10"][7, 5, 5],
)
assert np.all(out1["tg_mean_p90"] > out1["tg_mean_p50"])
assert np.all(out1["tg_mean_p50"] > out1["tg_mean_p10"])
def test_calc_perc_nans(self):
ens = ensembles.create_ensemble(self.nc_files_simple).load()
ens.tg_mean[2, 0, 5, 5] = np.nan
ens.tg_mean[2, 7, 5, 5] = np.nan
out1 = ensembles.ensemble_percentiles(ens)
np.testing.assert_array_equal(
np.percentile(ens['tg_mean'][:, 0, 5, 5], 10), np.nan)
np.testing.assert_array_equal(
np.percentile(ens['tg_mean'][:, 7, 5, 5], 10), np.nan)
np.testing.assert_array_equal(
np.nanpercentile(ens['tg_mean'][:, 0, 5, 5], 10),
out1['tg_mean_p10'][0, 5, 5])
np.testing.assert_array_equal(
np.nanpercentile(ens['tg_mean'][:, 7, 5, 5], 10),
out1['tg_mean_p10'][7, 5, 5])
assert np.all(out1['tg_mean_p90'] > out1['tg_mean_p50'])
assert np.all(out1['tg_mean_p50'] > out1['tg_mean_p10'])
def test_calc_perc_nans(self):
ens = ensembles.create_ensemble(self.nc_datasets_simple).load()
ens.tg_mean[2, 0, 5, 5] = np.nan
ens.tg_mean[2, 7, 5, 5] = np.nan
out1 = ensembles.ensemble_percentiles(ens, split=True)
np.testing.assert_array_equal(
np.percentile(ens["tg_mean"][:, 0, 5, 5], 10), np.nan)
np.testing.assert_array_equal(
np.percentile(ens["tg_mean"][:, 7, 5, 5], 10), np.nan)
np.testing.assert_array_equal(
np.nanpercentile(ens["tg_mean"][:, 0, 5, 5], 10),
out1["tg_mean_p10"][0, 5, 5],
)
np.testing.assert_array_equal(
np.nanpercentile(ens["tg_mean"][:, 7, 5, 5], 10),
out1["tg_mean_p10"][7, 5, 5],
)
assert np.all(out1["tg_mean_p90"] > out1["tg_mean_p50"])
assert np.all(out1["tg_mean_p50"] > out1["tg_mean_p10"])
def exp_xcdef(ds, percentiles):
return xcens.ensemble_percentiles(ds, percentiles)
