feat(pipelines): version 0

[heymarco]

This PR contains the first version of pipelines in Capymoa. Most importantly, it contains the classes Pipeline and Transformer.

• Transformers serve as elements in a pipeline and can be used to perform data preprocessing, such as normalization, feature transformation etc.
• Pipelines chain multiple trainsformers and a learner (classifier/regressor). Pipelines themselves serve as classifiers or regressors.

This version does not yet support changes in an instance's schema, e.g., due to feature selection. However, we will add this feature in the future.

[hmgomes]

Hi @heymarco, great work with the experimental version of the pipelines. I have expanded the jupyter notebook. We will continue working on this, but for now it is looking great, thanks again!