A reticulate-powered interface to the Python InterpretML framework for fitting explainable boosting machines (EBMs). EBMs are a modern type of generalized additive model that use tree-based, cyclic gradient boosting with automatic interaction detection. They are often as accurate as state-of-the-art blackbox models while remaining completely interpretable.

Installation

You can install the ebm package from either CRAN (stable) or GitHub (development):

# Install the latest stable version from CRAN:
install.packages("ebm")
# Install the latest development version from GitHub:
if (!requireNamespace("remotes")) {
  install.packages("remotes")
}
remotes::install_github("bgreenwell/ebm")

Usage

For a thorough overview of using the ebm package, see this article.