Suppr超能文献

mikropml:用于监督式机器学习管道的用户友好型R包。

mikropml: User-Friendly R Package for Supervised Machine Learning Pipelines.

作者信息

Topçuoğlu Begüm D, Lapp Zena, Sovacool Kelly L, Snitkin Evan, Wiens Jenna, Schloss Patrick D

机构信息

Department of Microbiology & Immunology, University of Michigan.

Exploratory Science Center, Merck & Co., Inc., Cambridge, Massachusetts, USA.

出版信息

J Open Source Softw. 2021;6(61). doi: 10.21105/joss.03073. Epub 2021 May 14.

Abstract

Machine learning (ML) for classification and prediction based on a set of features is used to make decisions in healthcare, economics, criminal justice and more. However, implementing an ML pipeline including preprocessing, model selection, and evaluation can be time-consuming, confusing, and difficult. Here, we present mikropml (prononced "meek-ROPE em el"), an easy-to-use R package that implements ML pipelines using regression, support vector machines, decision trees, random forest, or gradient-boosted trees. The package is available on GitHub, CRAN, and conda.

摘要

基于一组特征进行分类和预测的机器学习(ML)被用于医疗保健、经济学、刑事司法等领域来做出决策。然而,实施一个包括预处理、模型选择和评估的ML流程可能既耗时、令人困惑又困难。在此,我们展示了mikropml(发音为“meek-ROPE em el”),这是一个易于使用的R包,它使用回归、支持向量机、决策树、随机森林或梯度提升树来实现ML流程。该包可在GitHub、CRAN和conda上获取。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a256/8372219/b961c3345ba2/nihms-1706874-f0002.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验