Add a Binarizer class

[d-lazenby]

A clear and concise description of what the problem is. I needed to binarize some features in a pipeline but saw that this wasn't currently implemented in the package; I instead used the sklearn Binarizer and ColumnTransformer classes. This wasn't ideal as I had to keep track of the new indexes at subsequent steps of the pipeline - one of the nice things about feature engine is that you don't have to worry about that.

Describe the solution you'd like An implementation of a Binarizer class that bypasses the need for the corresponding sklearn class and that you can use directly within the Pipeline class instead of using ColumnTransformer.

Describe alternatives you've considered I wrote a class that inherits from the BaseDiscretizer which works as described above.

Would it be OK for me to work on this and open a PR?