* Rewrite import_from_sklearn_pipeline, reducing copying and calls to set_params * update black version used for formatting code to 2023 standard * Improvements to monoidal TargetEnoder implementation * minor improvement to task graph code
0.7.4
* Add support for scikit-learn 1.2.0 * Add a monoidal version of TargetEncoder * Simplify import_from_sklearn_pipeline and improve how it works with higher order operators * Fix spark schema inspection so it uses only metadata * Refactor schemas in autoai_libs
0.7.3
1. Test-suite improvements such as adding sphinx build 2. Documentation improvements: fixed all sphinx warnings 3. New operators: TargetEncoder and fairSMOTE 4. Bug fixes and support of new schema features such as "transient":"alwaysPrint" to always print a hyperparameter value in pretty_print even if it has default value.
0.7.2
CI and RASL fixes.
0.7.1
- fixes to autogen schemas - fix to autoai_libs DateTransformer
0.7.0
* Improves support for partial_fit * Improves the pretty printer * Improves support for typed users * Adds lale.lib.sklearn.perceptron (wrapping sklearn.linear_model.Perceptron) * RASL (experimental): - Removes support for Spark Dataframes that don't have an index - Moves HashingEncoder to category_encoders and improved documentation