Changes - The `BaseTimeseriesRegressor` now requires a `to_dict` and `from_dict` to be implemented for a minimal version to be able to predict. - Now the `dump` method takes `model_file_extension` and `weight_file_extension` for deciding whether to load from pickle or json. - The `dump_parameters` function for `MLPTimeseriesRegressor` now supports being saved as ONNX. - The `dump_parameters` function for `ConstantTimeseriesRegressor` now supports being saved as json.
4.0.0
Changes - The `dump` and `load` functions are now inherited from the BaseTimeseriesRegressor. - Added abstract functions `dump_parameters` and `load_parameters` for dumping and loading model files. - Implemented `dump_parameters` and `load_parameters` for models. - Outliers in the `_interactive_quantile_plot` and `_static_quantile_plot` functions must now be within or *equal* to the quantile boundaries.
3.2.1
Changes - Added the option to forcefully overwrite the optimizer.
3.2.0
Changes - Removed support for Python 3.9 - Updated pandas, sqlalchemy, tensorflow, numpy, and scikit-learn. - Implemented necessary changes to keep behaviour unchanged.
3.1.11
Changes - Make `'ID'`and `'TYPE'` columns `pd.Categorical` instead of `str`, to reduce the memory spike when using `pd.pivot_table` in `sam_format_to_wide`. - Added parameter in `QuantileRegressor` to use HiGHS solver, as recommended in <https://docs.scipy.org/doc/scipy/reference/optimize.linprog-highs.html>. This will also keep the package compatible with future versions of SciPy.
3.1.10
Changes - Allow numpy versions up to 1.23.x. 1.24 is not yet supported by shap (and shap does not specify this constraint in its requirements). For future reference, note that numpy 1.24 is also not supported by h5py versions below 3.0.0 (again without specifying) as it uses the deprecated `np.typeDict`. h5py is a requirement of tensorflow. - Upgrade tensorflow - Limit scikit-learn version <2