Bof

* The core is now the CountVectorizer class. Lighter and faster. Only features are kept inside.
* New process module inspired by fuzzywuzzy!

* Full refactoring to make the package fit/transform compliant.
* Add a fit_sampling method that allows to fit only a (random) subset of factors

* Docstrings added
* Common module (feat. save/load capabilities)
* Joint Complexity module

* First release on PyPI.
* Core FactorTree class added.