Fklearn

- **Enhancement**
- Including Classification S-Learner and T-Learner models to the causal cate learning library.
- **Bug Fix**
- Fix validator behavior when receiving data containing gaps and a time based split function that
could generate empty
training and testing folds and then break.
The argument `drop_empty_folds` can be set to `True` to drop invalid folds from validation and
store them in the
log.
- **Documentation**
- Including Classification S-Learner and T-Learner documentation, also changing validator documentation to
reflect changes.

- **Enhancement**
- Add optional parameter `return_eval_logs_on_train` to the `validator` function,
enabling it to return the evaluation logs for all training folds instead of just
the first one
- **Bug Fix**
- Fix import in `pd_extractors.py` for Python 3.10 compatibility
- Set a minimal version of Python (3.6.2) for Fklearn
- **Documentation**
- Fixing some typos, broken links and general improvement on the documentation

- **Possible breaking changes**
- Allow greater versions of `catboost`, `lightgbm`, `xgboost`, `shap`, `swifter`
(mostly due to deprecation of support to Python 3.5 and older versions). Libraries depending on
`fklearn` can still restrict the versions of the aforementioned libraries, keeping the previous
behavior.

- **New**
- Add causal curves summary
- **Bug fix**
- Set correct learner name for learners with column_duplicatable decorator

- **New**
- Add common causal evaluation techniques
- Add methods to debias a dataframe with a treatment T and confounders X

- **Bug fix**
- Remove `cloudpickle` from requirements