1.2.0

Release Notes (What's New)

Version 1.2.0 (September 13, 2024)

For a list of all changes in this release, see the full changelog. Below are the changes we think users may wish to be aware of.

Features

• Added three new metrics:
  • Percent bias (PBIAS): scores.continuous.pbias. See PR #639 and PR #655.
  • Threshold weighted continuous ranked probability score (twCRPS) for ensembles: scores.probability.tw_crps_for_ensemble. See PR #644.
  • Tail threshold weighted continuous ranked probability score (twCRPS) for ensembles: scores.probability.tail_tw_crps_for_ensemble. See PR #644.
• The FIxed Risk Multicategorical (FIRM) score (scores.categorical.firm) can now take a sequence of mulitdimensional arrays (xr.DataArray) of thresholds. This allows the FIRM score to be used with categorical thresholds that vary across the domain. See PR #661.

Documentation

• Added information about percent bias to the "Additive Bias and Multiplicative Bias" tutorial. See PR #639 and PR #656.
• Updated documentation to say there are now over 60 metrics, statistical techniques and data processing tools contained in scores. See PR #659.
• In the "Contributing Guide", updated instructions for installing a conda-based virtual environment. See PR #654.

Internal Changes

• Modified automated tests to work with NumPy 2.1. Incorporated a union type of array and generic in assert statements for Dask operations. See PR #643.

Contributors to this Release

Durga Shrestha* (@durgals), Maree Carroll (@mareecarroll), Nicholas Loveday (@nicholasloveday), Tennessee Leeuwenburg (@tennlee), Stephanie Chong (@Steph-Chong) and Robert J. Taggart (@rob-taggart).

* indicates that this release contains their first contribution to scores.