Aaron Spring

I can find https://climetlab.readthedocs.io/en/latest/examples/11-weatherbench.html

Seems so climetlab/datasets/weather_bench.py

please add these tests to `asv` and for small 1D, and larger 3D arrays and for chunked and not chunked. otherwise the timings are less robust. would it be possible...

are you sure that the second run isnt faster than the first because some parts of the data are already in memory? can reverse ordering. `asv` runs multiple times to...

We don’t use factorize anyways.

I would implement this with `xskillscore.set_options(xr_apply_ufunc_dask="parallelized")` as default. and then users could switch to `"allowed"` themselves. or we implement `"default"` where the metrics take `"allowed"` if it doesnt fail else...

a bit closer. works but ugly API ```python import xarray as xr import xskillscore as xs from functools import partial ds = xr.tutorial.open_dataset('air_temperature') ds['air2'] = ds['air'] * 2 @xr.register_dataset_accessor("XS") class...

Doppyo also has the brier score decomposition. See my PR soon.

I think linking this paper is actually misleading as @kpegion pointed out in climpred. This formula of Brier Score is only for 2 category forecasts, see https://en.wikipedia.org/wiki/Brier_score

We could add a keyword for which formula to use...