def test_prefix_attrs():
source = {"units": "mm/s", "name": "pr"}
dest = fmt.prefix_attrs(source, ["units"], "original_")
assert "original_units" in dest
out = fmt.unprefix_attrs(dest, ["units"], "original_")
assert out == source
# Check that the "naked" units will be overwritten.
dest["units"] = ""
out = fmt.unprefix_attrs(dest, ["units"], "original_")
assert out == source
def parametric_quantile(p: xr.DataArray, q: Union[int, Sequence]) -> xr.DataArray:
"""Return the value corresponding to the given distribution parameters and quantile.
Parameters
----------
p : xr.DataArray
Distribution parameters returned by the `fit` function.
The array should have dimension `dparams` storing the distribution parameters,
and attribute `scipy_dist`, storing the name of the distribution.
q : Union[float, Sequence]
Quantile to compute, which must be between `0` and `1`, inclusive.
Returns
-------
xarray.DataArray
An array of parametric quantiles estimated from the distribution parameters.
Notes
-----
When all quantiles are above 0.5, the `isf` method is used instead of `ppf` because accuracy is sometimes better.
"""
q = np.atleast_1d(q)
# Get the distribution
dist = p.attrs["scipy_dist"]
dc = get_dist(dist)
# Create a lambda function to facilitate passing arguments to dask. There is probably a better way to do this.
if np.all(q > 0.5):
def func(x):
return dc.isf(1 - q, *x)
else:
def func(x):
return dc.ppf(q, *x)
duck = dask.array if isinstance(p.data, dask.array.Array) else np
data = duck.apply_along_axis(func, p.get_axis_num("dparams"), p)
# Create coordinate for the return periods
coords = dict(p.coords.items())
coords.pop("dparams")
coords["quantile"] = q
# Create dimensions
dims = [d if d != "dparams" else "quantile" for d in p.dims]
out = xr.DataArray(data=data, coords=coords, dims=dims)
out.attrs = unprefix_attrs(p.attrs, ["units", "standard_name"], "original_")
attrs = dict(
long_name=f"{dist} quantiles",
description=f"Quantiles estimated by the {dist} distribution",
cell_methods=merge_attributes("dparams: ppf", out, new_line=" "),
xclim_history=update_history(
"Compute parametric quantiles from distribution parameters",
new_name="parametric_quantile",
parameters=p,
),
)
out.attrs.update(attrs)
return out
def parametric_cdf(p: xr.DataArray, v: Union[float, Sequence]) -> xr.DataArray:
"""Return the cumulative distribution function corresponding to the given distribution parameters and value.
Parameters
----------
p : xr.DataArray
Distribution parameters returned by the `fit` function.
The array should have dimension `dparams` storing the distribution parameters,
and attribute `scipy_dist`, storing the name of the distribution.
v : Union[float, Sequence]
Value to compute the CDF.
Returns
-------
xarray.DataArray
An array of parametric CDF values estimated from the distribution parameters.
Notes
-----
"""
v = np.atleast_1d(v)
# Get the distribution
dist = p.attrs["scipy_dist"]
dc = get_dist(dist)
# Create a lambda function to facilitate passing arguments to dask. There is probably a better way to do this.
def func(x):
return dc.cdf(v, *x)
data = xr.apply_ufunc(
func,
p,
input_core_dims=[["dparams"]],
output_core_dims=[["cdf"]],
vectorize=True,
dask="parallelized",
output_dtypes=[float],
keep_attrs=True,
dask_gufunc_kwargs={"output_sizes": {
"cdf": len(v)
}},
)
# Assign quantile coordinates and transpose to preserve original dimension order
dims = [d if d != "dparams" else "cdf" for d in p.dims]
out = data.assign_coords(cdf=v).transpose(*dims)
out.attrs = unprefix_attrs(p.attrs, ["units", "standard_name"],
"original_")
attrs = dict(
long_name=f"{dist} cdf",
description=f"CDF estimated by the {dist} distribution",
cell_methods="dparams: cdf",
history=update_history(
"Compute parametric cdf from distribution parameters",
new_name="parametric_cdf",
parameters=p,
),
)
out.attrs.update(attrs)
return out
def parametric_quantile(p: xr.DataArray, q: Union[int,
Sequence]) -> xr.DataArray:
"""Return the value corresponding to the given distribution parameters and quantile.
Parameters
----------
p : xr.DataArray
Distribution parameters returned by the `fit` function.
The array should have dimension `dparams` storing the distribution parameters,
and attribute `scipy_dist`, storing the name of the distribution.
q : Union[float, Sequence]
Quantile to compute, which must be between `0` and `1`, inclusive.
Returns
-------
xarray.DataArray
An array of parametric quantiles estimated from the distribution parameters.
Notes
-----
When all quantiles are above 0.5, the `isf` method is used instead of `ppf` because accuracy is sometimes better.
"""
q = np.atleast_1d(q)
# Get the distribution
dist = p.attrs["scipy_dist"]
dc = get_dist(dist)
# Create a lambda function to facilitate passing arguments to dask. There is probably a better way to do this.
if np.all(q > 0.5):
def func(x):
return dc.isf(1 - q, *x)
else:
def func(x):
return dc.ppf(q, *x)
data = xr.apply_ufunc(
func,
p,
input_core_dims=[["dparams"]],
output_core_dims=[["quantile"]],
vectorize=True,
dask="parallelized",
output_dtypes=[float],
keep_attrs=True,
dask_gufunc_kwargs={"output_sizes": {
"quantile": len(q)
}},
)
# Assign quantile coordinates and transpose to preserve original dimension order
dims = [d if d != "dparams" else "quantile" for d in p.dims]
out = data.assign_coords(quantile=q).transpose(*dims)
out.attrs = unprefix_attrs(p.attrs, ["units", "standard_name"],
"original_")
attrs = dict(
long_name=f"{dist} quantiles",
description=f"Quantiles estimated by the {dist} distribution",
cell_methods="dparams: ppf",
history=update_history(
"Compute parametric quantiles from distribution parameters",
new_name="parametric_quantile",
parameters=p,
),
)
out.attrs.update(attrs)
return out