Multiclass Performance Evaluation Toolkit

Implementation of custom 'tidymodels' metrics for multi-class prediction models with a single negative class. Currently are implemented macro-average sensitivity and specificity as in Mortaz, Ebrahim (2020) "Imbalance accuracy metric for model selection in multi-class imbalance classification problems” and a generalized weighted Youden index as in Li, D.L., Shen F., Yin Y., Peng J.X and Chen P.Y. (2013) “Weighted Youden index and its two-independent-sample comparison based on weighted sensitivity and specificity” .

mupet

The goal of {mupet} is to provide a performance evaluation toolkit for multi-class prediction models in the form of metric functions compatible with the tidymodels framework, through the API designed in the {yardstick} package.

Installation

You can install the package directly from CRAN using:

pak::pak("mupet")

Or you can install the development version of mupet like so:

# pak::pak("remotes")
remotes::install_github("astamm/mupet")