def test_raise(self):
da = xr.open_dataset(self.nc_poslons).tas
with pytest.raises(ValueError):
subset.subset_bbox(da,
lon_bnds=self.lon,
lat_bnds=self.lat,
start_yr=2056,
end_yr=2055)
def test_simple(self):
da = xr.open_dataset(self.nc_file).tasmax
out = subset.subset_bbox(da, lon_bnds=self.lon, lat_bnds=self.lat)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat.values >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
da = xr.open_dataset(self.nc_poslons).tas
da = da.assign_coords(lon=(da.lon - 360))
yr_st = 2050
yr_ed = 2059
out = subset.subset_bbox(
da,
lon_bnds=self.lonGCM,
lat_bnds=self.latGCM,
start_date=str(yr_st),
end_date=str(yr_ed),
)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
assert np.all(out.lon >= np.min(self.lonGCM))
assert np.all(out.lon <= np.max(self.lonGCM))
assert np.all(out.lat >= np.min(self.latGCM))
assert np.all(out.lat <= np.max(self.latGCM))
np.testing.assert_array_equal(out.time.dt.year.max(), yr_ed)
np.testing.assert_array_equal(out.time.dt.year.min(), yr_st)
out = subset.subset_bbox(
da, lon_bnds=self.lon, lat_bnds=self.lat, start_date=str(yr_st)
)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
np.testing.assert_array_equal(out.time.dt.year.max(), da.time.dt.year.max())
np.testing.assert_array_equal(out.time.dt.year.min(), yr_st)
out = subset.subset_bbox(
da, lon_bnds=self.lon, lat_bnds=self.lat, end_date=str(yr_ed)
)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
np.testing.assert_array_equal(out.time.dt.year.max(), yr_ed)
np.testing.assert_array_equal(out.time.dt.year.min(), da.time.dt.year.min())
def test_simple(self):
da = xr.open_dataset(self.nc_file).tasmax
out = subset.subset_bbox(da, lon_bnds=self.lon, lat_bnds=self.lat)
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
da = xr.open_dataset(self.nc_poslons).tas
da["lon"] -= 360
yr_st = "2050"
yr_ed = "2059"
out = subset.subset_bbox(da,
lon_bnds=self.lon,
lat_bnds=self.lat,
start_date=yr_st,
end_date=yr_ed)
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
np.testing.assert_array_equal(out.time.dt.year.max(),
np.array(int(yr_ed)))
np.testing.assert_array_equal(out.time.dt.year.min(),
np.array(int(yr_st)))
with pytest.warns(Warning):
out = subset.subset_bbox(da,
lon_bnds=self.lon,
lat_bnds=self.lat,
start_date=yr_st)
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
np.testing.assert_array_equal(out.time.dt.year.max(),
da.time.dt.year.max())
np.testing.assert_array_equal(out.time.dt.year.min(),
np.array(int(yr_st)))
with pytest.warns(Warning):
out = subset.subset_bbox(da,
lon_bnds=self.lon,
lat_bnds=self.lat,
end_date=yr_ed)
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
np.testing.assert_array_equal(out.time.dt.year.max(),
np.array(int(yr_ed)))
np.testing.assert_array_equal(out.time.dt.year.min(),
da.time.dt.year.min())
def test_raise(self):
da = xr.open_dataset(self.nc_poslons).tas
with pytest.raises(ValueError):
subset.subset_bbox(da,
lon_bnds=self.lon,
lat_bnds=self.lat,
start_yr=2056,
end_yr=2055)
da = xr.open_dataset(self.nc_2dlonlat).tasmax.drop(["lon", "lat"])
with pytest.raises(Exception):
subset.subset_bbox(da, lon_bnds=self.lon, lat_bnds=self.lat)
def test_positive_lons(self):
da = xr.open_dataset(self.nc_poslons).tas
out = subset.subset_bbox(da, lon_bnds=self.lon, lat_bnds=self.lat)
assert np.all(out.lon >= np.min(np.asarray(self.lon) + 360))
assert np.all(out.lon <= np.max(np.asarray(self.lon) + 360))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
out = subset.subset_bbox(da,
lon_bnds=np.array(self.lon) + 360,
lat_bnds=self.lat)
assert np.all(out.lon >= np.min(np.asarray(self.lon) + 360))
def test_raise(self):
da = xr.open_dataset(self.nc_poslons).tas
with pytest.raises(ValueError):
subset.subset_bbox(
da,
lon_bnds=self.lonGCM,
lat_bnds=self.latGCM,
start_date="2056",
end_date="2055",
)
da = xr.open_dataset(self.nc_2dlonlat).tasmax.drop_vars(names=["lon", "lat"])
with pytest.raises(Exception):
subset.subset_bbox(da, lon_bnds=self.lon, lat_bnds=self.lat)
def test_simple(self):
da = xr.open_dataset(self.nc_file).tasmax
out = subset.subset_bbox(da, lon_bnds=self.lon, lat_bnds=self.lat)
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
da = xr.open_dataset(self.nc_poslons).tas
da["lon"] -= 360
yr_st = 2050
yr_ed = 2059
out = subset.subset_bbox(da,
lon_bnds=self.lon,
lat_bnds=self.lat,
start_yr=yr_st,
end_yr=yr_ed)
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
np.testing.assert_array_equal(out.time.dt.year.max(), yr_ed)
np.testing.assert_array_equal(out.time.dt.year.min(), yr_st)
out = subset.subset_bbox(da,
lon_bnds=self.lon,
lat_bnds=self.lat,
start_yr=yr_st)
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
np.testing.assert_array_equal(out.time.dt.year.max(),
da.time.dt.year.max())
np.testing.assert_array_equal(out.time.dt.year.min(), yr_st)
out = subset.subset_bbox(da,
lon_bnds=self.lon,
lat_bnds=self.lat,
end_yr=yr_ed)
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
np.testing.assert_array_equal(out.time.dt.year.max(), yr_ed)
np.testing.assert_array_equal(out.time.dt.year.min(),
da.time.dt.year.min())
def test_positive_lons(self):
da = xr.open_dataset(self.nc_poslons).tas
out = subset.subset_bbox(da, lon_bnds=self.lonGCM, lat_bnds=self.latGCM)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
assert np.all(out.lon >= np.min(np.asarray(self.lonGCM) + 360))
assert np.all(out.lon <= np.max(np.asarray(self.lonGCM) + 360))
assert np.all(out.lat >= np.min(self.latGCM))
assert np.all(out.lat <= np.max(self.latGCM))
out = subset.subset_bbox(
da, lon_bnds=np.array(self.lonGCM) + 360, lat_bnds=self.latGCM
)
assert np.all(out.lon >= np.min(np.asarray(self.lonGCM) + 360))
def test_single_bounds_rectilinear(self):
da = xr.open_dataset(self.nc_file).tasmax
out = subset.subset_bbox(da, lon_bnds=self.lon)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
np.testing.assert_array_equal(out.lat, da.lat)
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lon.values >= np.min(self.lon))
out = subset.subset_bbox(da, lat_bnds=self.lat)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
np.testing.assert_array_equal(out.lon, da.lon)
assert np.all(out.lat <= np.max(self.lat))
assert np.all(out.lat.values >= np.min(self.lat))
def test_single_bounds_curvilinear(self):
da = xr.open_dataset(self.nc_2dlonlat).tasmax
out = subset.subset_bbox(da, lon_bnds=self.lon)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
mask1 = ~(np.isnan(out.sel(time=out.time[0])))
assert np.all(out.lon.values[mask1.values] <= np.max(self.lon))
assert np.all(out.lon.values[mask1.values] >= np.min(self.lon))
out = subset.subset_bbox(da, lat_bnds=self.lat)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
mask1 = ~(np.isnan(out.sel(time=out.time[0])))
assert np.all(out.lat.values[mask1.values] <= np.max(self.lat))
assert np.all(out.lat.values[mask1.values] >= np.min(self.lat))
def test_irregular_dataset(self):
da = xr.open_dataset(self.nc_2dlonlat)
out = subset.subset_bbox(da, lon_bnds=[-150, 100], lat_bnds=[10, 60])
variables = list(da.data_vars)
variables.pop(variables.index("tasmax"))
# only tasmax should be subsetted/masked others should remain untouched
for v in variables:
assert out[v].dims == da[v].dims
np.testing.assert_array_equal(out[v], da[v])
# ensure results are equal to previous test on DataArray only
out1 = subset.subset_bbox(da.tasmax, lon_bnds=[-150, 100], lat_bnds=[10, 60])
np.testing.assert_array_equal(out1, out.tasmax)
# additional test if dimensions have no coordinates
da = da.drop_vars(["rlon", "rlat"])
subset.subset_bbox(da.tasmax, lon_bnds=[-150, 100], lat_bnds=[10, 60])
def test_badly_named_latlons(self):
da = xr.open_dataset(self.nc_file)
extended_latlons = {"lat": "latitude", "lon": "longitude"}
da_extended_names = da.rename(extended_latlons)
out = subset.subset_bbox(
da_extended_names, lon_bnds=self.lon, lat_bnds=self.lat
)
assert {"latitude", "longitude"}.issubset(out.dims)
long_for_some_reason = {"lon": "long"}
da_long = da.rename(long_for_some_reason)
out = subset.subset_bbox(da_long, lon_bnds=self.lon, lat_bnds=self.lat)
assert {"long"}.issubset(out.dims)
lons_lats = {"lon": "lons", "lat": "lats"}
da_lonslats = da.rename(lons_lats)
out = subset.subset_bbox(da_lonslats, lon_bnds=self.lon, lat_bnds=self.lat)
assert {"lons", "lats"}.issubset(out.dims)
def test_dataset(self):
da = xr.open_mfdataset(
[self.nc_file,
self.nc_file.replace("tasmax", "tasmin")])
out = subset.subset_bbox(da, lon_bnds=self.lon, lat_bnds=self.lat)
assert np.all(out.lon >= np.min(self.lon))
assert np.all(out.lon <= np.max(self.lon))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
np.testing.assert_array_equal(out.tasmin.shape, out.tasmax.shape)
def test_time(self):
da = xr.open_dataset(self.nc_poslons).tas
da["lon"] -= 360
out = subset.subset_bbox(
da,
lon_bnds=self.lonGCM,
lat_bnds=self.latGCM,
start_date="2050",
end_date="2059",
)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
assert np.all(out.lon >= np.min(self.lonGCM))
assert np.all(out.lon <= np.max(self.lonGCM))
assert np.all(out.lat >= np.min(self.latGCM))
assert np.all(out.lat <= np.max(self.latGCM))
np.testing.assert_array_equal(out.time.min().dt.year, 2050)
np.testing.assert_array_equal(out.time.min().dt.month, 1)
np.testing.assert_array_equal(out.time.min().dt.day, 1)
np.testing.assert_array_equal(out.time.max().dt.year, 2059)
np.testing.assert_array_equal(out.time.max().dt.month, 12)
np.testing.assert_array_equal(out.time.max().dt.day, 31)
out = subset.subset_bbox(
da,
lon_bnds=self.lonGCM,
lat_bnds=self.latGCM,
start_date="2050-02-05",
end_date="2059-07-15",
)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
assert np.all(out.lon >= np.min(self.lonGCM))
assert np.all(out.lon <= np.max(self.lonGCM))
assert np.all(out.lat >= np.min(self.latGCM))
assert np.all(out.lat <= np.max(self.latGCM))
np.testing.assert_array_equal(out.time.min().dt.year, 2050)
np.testing.assert_array_equal(out.time.min().dt.month, 2)
np.testing.assert_array_equal(out.time.min().dt.day, 5)
np.testing.assert_array_equal(out.time.max().dt.year, 2059)
np.testing.assert_array_equal(out.time.max().dt.month, 7)
np.testing.assert_array_equal(out.time.max().dt.day, 15)
def test_warnings(self):
da = xr.open_dataset(self.nc_poslons).tas
da = da.assign_coords(lon=(da.lon - 360))
with pytest.raises(TypeError):
subset.subset_bbox(
da, lon_bnds=self.lon, lat_bnds=self.lat, start_yr=2050, end_yr=2059
)
with pytest.warns(None) as record:
subset.subset_bbox(
da,
lon_bnds=self.lon,
lat_bnds=self.lat,
start_date="2050",
end_date="2055",
)
assert (
'"start_yr" and "end_yr" (type: int) are being deprecated. Temporal subsets will soon exclusively'
' support "start_date" and "end_date" (type: str) using formats of "%Y", "%Y-%m" or "%Y-%m-%d".'
not in [str(q.message) for q in record]
)
def test_warnings(self):
da = xr.open_dataset(self.nc_poslons).tas
da["lon"] -= 360
with pytest.warns(FutureWarning):
subset.subset_bbox(da,
lon_bnds=self.lon,
lat_bnds=self.lat,
start_yr=2050,
end_yr=2059)
with pytest.warns(None) as record:
subset.subset_bbox(
da,
lon_bnds=self.lon,
lat_bnds=self.lat,
start_date="2050",
end_date="2055",
)
assert (
'"start_yr" and "end_yr" (type: int) are being deprecated. Temporal subsets will soon exclusively'
' support "start_date" and "end_date" (type: str) using formats of "%Y", "%Y-%m" or "%Y-%m-%d".'
not in [q.message for q in record])
def test_irregular(self):
da = xr.open_dataset(self.nc_2dlonlat).tasmax
out = subset.subset_bbox(da, lon_bnds=self.lon, lat_bnds=self.lat)
# for irregular lat lon grids data matrix remains rectangular in native proj
# but with data outside bbox assigned nans. This means it can have lon and lats outside the bbox.
# Check only non-nans gridcells using mask
mask1 = ~np.isnan(out.sel(time=out.time[0]))
assert np.all(out.lon.values[mask1] >= np.min(self.lon))
assert np.all(out.lon.values[mask1] <= np.max(self.lon))
assert np.all(out.lat.values[mask1] >= np.min(self.lat))
assert np.all(out.lat.values[mask1] <= np.max(self.lat))
def _subset_function(dataset):
nonlocal count
count += 1
percentage = start_percentage + int((count - 1) / n_files * (end_percentage - start_percentage))
self.write_log(f"Processing file {count} of {n_files}", response, percentage)
dataset = dataset[variables] if variables else dataset
if lat1 is None and lon1 is None:
return subset_gridpoint(dataset, lon=lon0, lat=lat0, start_yr=y0, end_yr=y1)
else:
return subset_bbox(
dataset, lon_bnds=[lon0, lon1], lat_bnds=[lat0, lat1], start_yr=y0, end_yr=y1
)
def test_inverted_coords(self):
lon = np.linspace(-90, -60, 200)
lat = np.linspace(40, 80, 100)
da = xr.Dataset(
data_vars=None, coords={"lon": np.flip(lon), "lat": np.flip(lat)}
)
da["data"] = xr.DataArray(
np.random.rand(lon.size, lat.size), dims=["lon", "lat"]
)
out = subset.subset_bbox(da, lon_bnds=self.lon, lat_bnds=self.lat)
assert out.lon.values.size != 0
assert out.lat.values.size != 0
assert np.all(out.lon >= np.min(np.asarray(self.lon)))
assert np.all(out.lon <= np.max(np.asarray(self.lon)))
assert np.all(out.lat >= np.min(self.lat))
assert np.all(out.lat <= np.max(self.lat))
