Fklearn

- **Enhancement**
- Allow users to set a gap between training and holdout in time splitters
- Raise Errors instead of use asserts
- **New**
- Support pipelines with duplicated learners
- Add stratified split method
- **Bug Fix**
- Fix space_time_split holdout
- Fix compatibility with newer shap version

- **Enhancement**
- Increasing isotonic calibration regression by adding upper and lower bounds.

- **Enhancement**
- Improve split evaluator to avoid unexpected errors
- **New**
- Now users can install only the set of requirements they need
- Add Target encoding learner
- Add PR AUC and rename AUC evaluator to ROC AUC
- **Bug Fix**
- Fix bug with space_time_split_dataset fn
- **Documentation**
- Update space time split DOCSTRING to match the actual behaviour
- Add more tutorials(Pydata)

- **Enhancement**
- Now learners that have a model exposes it in the logs as `object` key

- **Enhancement**
- Make `custom_transformer` a pure function
- Remove unused requirements
- **New**
- Now features created by one hot enconding can be used in the next steps of pipeline
- Shap multiclass support
- Custom model pipeline
- **Bug Fix**
- Fix the way one hot encoding handle nans
- **Documentation**
- Minor fix flake8 documentation to make it work in other shells
- Fix fbeta_score_evaluator docstring
- Fix typo on onehot_categorizer
- New tutorial from meetup presentation

- **Enhancement**
- Validator accepts predict_oof as argument
- **New**
- Add CatBoosting regressor
- Data corruption(Macacaos)
- **Documentation**
- Multiple fixes in the documentation
- Add Contribution guide