Extract meaningful interactions from machine learning models to obtain machine-learning performance with statistical model interpretability.

Code accompanying the manuscript: "Don't Dismiss Logistic Regression: The Case for Sensible Extraction of Interactions in the Era of Machine Learning"
BMC Medical Research Methodology: https://bmcmedresmethodol.biomedcentral.com/articles/10.1186/s12874-020-01046-3

Please see our wiki for more information on setting up and running this package: https://github.com/jlevy44/InteractionTransformer/wiki

QUICKSTART DEMOS can be found here:

Python: https://github.com/jlevy44/InteractionTransformer/blob/master/demos/InteractionTransformerPythonDemo.ipynb

R: https://github.com/jlevy44/InteractionTransformer/blob/master/demos/InteractionTransformerRDemo.Rmd

Python: We recommend installing using anaconda (https://www.anaconda.com/distribution/). First, install anaconda. Then, run:

conda create -n interaction_transform_environ python=3.7
conda activate interaction_transform_environ

Finally:

pip install interactiontransformer

R
First, install the python pip package. Then:

devtools::install_github("jlevy44/interactiontransformer")

Or:

library(devtools)
install_github("jlevy44/interactiontransformer")

git clone https://github.com/jlevy44/InteractionTransformer
cd InteractionTransformer
pip install . # make sure conda is running

👤 Joshua Levy

• Github: @jlevy44