skduplo 0.1.1

Sci-kit learn tools for machine learning pipelines

scikit-duplo

Very simple reusable blocks for scikit-learn pipelines (inspired by scikit-lego)

Installation

Installation from the source tree:

python setup.py install

Or via pip from PyPI:

pip install scikit-duplo

Contents

The sci-kit duplo package contains multiple classes that you can use in a sci-kit learn compatible pipeline. There are ensemble learning classes within the meta subdirectory. These classes expect you to pass in multiple other Sci-kit learn compatible machine learning classes. It will use these to build an ensemble of models to predict the target variable.

There are feature engineering classes inside the preprocessing subdirectory. These are ColumnTransformer compatible classes that expect to receive a dataframe and set of column names that it will transform for the downstream pipeline processes.