mikropml: User-Friendly R Package for Robust Machine Learning Pipelines

mikropml implements supervised machine learning pipelines using regression, support vector machines, decision trees, random forest, or gradient-boosted trees. The main functions are preprocess_data() to process your data prior to running machine learning, and run_ml() to run machine learning.

Authors

• Begüm D. Topçuoğlu (ORCID)

• Zena Lapp (ORCID)

• Kelly L. Sovacool (ORCID)

• Evan Snitkin (ORCID)

• Jenna Wiens (ORCID)

• Patrick D. Schloss (ORCID)

See vignettes

• Introduction

• Preprocessing data

• Hyperparameter tuning

• Parallel processing

• The mikropml paper

See also

Useful links:

• https://www.schlosslab.org/mikropml/

• https://github.com/SchlossLab/mikropml

• Report bugs at https://github.com/SchlossLab/mikropml/issues

Author

Maintainer: Kelly Sovacool sovacool@umich.edu (ORCID)

Authors:

• Begüm Topçuoğlu topcuoglu.begum@gmail.com (ORCID)

• Zena Lapp zenalapp@umich.edu (ORCID)

• Evan Snitkin (ORCID)

• Jenna Wiens (ORCID)

• Patrick Schloss pschloss@umich.edu (ORCID)

Other contributors:

• Nick Lesniak nlesniak@umich.edu (ORCID) [contributor]

• Courtney Armour armourc@umich.edu (ORCID) [contributor]

• Sarah Lucas salucas@umich.edu (ORCID) [contributor]