by: Oege Dijk
Defines a bunch of transformer classes based on the scikit learn transformer class.
These transformers can then be pieced together using sklearn-pandas to create a transformer pipeline.
A collection of sklearn compatible transformer classes. Sklearn's standard transformers have some annoying lacunes (especially when fitting on new data with labels missing in training data for example), so these transformers fix that. Also some other more adventurous transformer classes. Shows how to quickly make transformer pipelines for e.g. making dataframe ready for neural net with embeddings.
Python