v0.9.0#

  • Added Credit Loan Decisions example notebook.

  • Bugfix for selection_rate() to handle TypeError when input is scalar.

  • Added support for pickling classes in fairlearn.reductions.

  • Bugfix for sklearn.preprocessing.OneHotEncoder in fairlearn.adversarial to ensure compatibility with scikit-learn 1.2.

  • Set default value of parser of sklearn.datasets.fetch_openml in fairlearn.datasets to liac-arff to match behavior before scikit-learn 1.2.

  • Replaced calculations in fairlearn.reductions by matrix multiplication which can lead to substantial speed-ups for ExponentiatedGradient for simple estimators like logistic regression.

  • Added as_frame (with default True) argument to fetch_diabetes_hospital().

  • Changed as_frame default to True for all remaining datasets.

  • Changed MetricFrame so that all results (including aggregations) are computed in the constructor and then cached.

  • Bugfix for fairlearn.adversarial that changes the loss function NLLLoss to CrossEntropyLoss.

  • Various documentation tweaks and enhancements, including restructuring of the user guide and breaking out information in the API reference to separate pages.

  • Removed customplots extra. To use our plotting capabilities, please install matplotlib if it is not already part of your environment.