basemodels

Baseline Models for Classification and Regression

Ying-Ju Chen, Fadel M. Megahed, L. Allison Jones-Farmer, Steven E. Rigdon

Last update: 9 August 2023

Copyright license: MIT license, File License

Software version identifier: 1.0.0, 1.1.0

Providing equivalent functions for the dummy classifier and regressor used in 'Python' 'scikit-learn' library. Our goal is to allow R users to easily identify baseline performance for their classification and regression problems. Our baseline models use no predictors, and are useful in cases of class imbalance, multiclass classification, and when users want to quickly identify how much improvement their statistical and machine learning models are over several baseline models. We use a "better" default (proportional guessing) for the dummy classifier than the 'Python' implementation ("prior", which is the most frequent class in the training set). The functions in the package can be used on their own, or introduce methods named 'dummy_regressor' or 'dummy_classifier' that can be used within the caret package pipeline.

This page was built for software: basemodels