User-Friendly R Package for Supervised Machine Learning Pipelines
Overview
An interface to build machine learning models for classification and regression problems. 'mikropml' implements the ML pipeline described by Topçuoğlu et al. (2020) doi:10.1128/mBio.00434-20 with reasonable default options for data preprocessing, hyperparameter tuning, cross-validation, testing, model evaluation, and interpretation steps. See the website https://www.schlosslab.org/mikropml/ for more information, documentation, and examples.
- Allow
training_fracequal to 1... really this time! (#360, @pschloss) - Note: the maximum
xgboostversion supported is1.7(see #362). - A container is now available in ghcr (#364, #366, @kelly-sovacool).
- see <https://github.com/SchlossLab/mikropml/pkgs/container/mikropml>.
From NEWS.md in the release
Install
Health
ERRORpackage dependenciesr-oldrel-macos-arm64, r-oldrel-macos-x86_64
Package required but not available: ‘TreeSummarizedExperiment’ See section ‘The DESCRIPTION file’ in the ‘Writing R Extensions’ manual.
- ERROR11 OK, 2 ERRORNow
- ERROR8 OK, 3 NOTE, 3 ERROR2026-03-10
Documentation
- Help pages
- 103 (58 internal)includes a package overview page
- Examples that run
- 26%20 run in a plain check · 56 never run
- Exported functions with examples
- 94%
- Documented parameters
- 100%
- Return-value docs
- 94%
- Help pages citing references
- 0%
Downloads
Repository
- PRs merged (all time)
- 98%
- Median days to close, 50 most recently updated closed issues
- 26
- Median days to close, 50 most recently updated closed PRs
- 2
Stars over time
Forks over time
Releases over time
Issues over time
PRs over time
Commits over time
18 development-tooling and community-health practices detected across 8 families in the upstream repository
Checks run against github.com/schlosslab/mikropml on 2026-10-11.
The R CMD check workflow runs on Linux, macOS and Windows
GitHub Pages site last deployed 2026-08-29 · The repository has a site deploy workflow
pkgdown site last built 2026-08-28
Show all practicesHide 4 practices
Dependencies
Installing mikropml adds 75 packages (43 with compiled code, 61 MB of source tarballs). Heaviest: stringi 11 MB, ggplot2 6.0 MB, data.table 5.7 MB. 4 more not on CRAN are not measured.
Code & Tests
Datasets
People & History
Pick two releases to compare their code metrics.
- 1.7.1Latest
- RR 4.6.0 released · 2026-04-24
- 1.7.02025-10-29 · diff ↗
- 1.6.22025-08-22 · diff ↗
- RR 4.5.0 released · 2025-04-11
- RR 4.4.0 released · 2024-04-24
- 1.6.12023-08-21 · diff ↗
- RR 4.3.0 released · 2023-04-21
- 1.6.0
- 1.5.02023-01-16 · diff ↗ ·
added 6 exports
calc_baseline_precision, calc_mean_prc, calc_mean_roc, calc_model_sensspec, plot_mean_prc, plot_mean_roc - 1.4.02022-10-16 · diff ↗
- 1.3.0
- RR 4.2.0 released · 2022-04-22
- 1.2.22022-02-03 · diff ↗
- 1.2.12022-01-30 · diff ↗
- 1.2.02021-11-11 · diff ↗
Show 7 earlier eventsHide 7 earlier events
Package metadata
- First published
- 2020-11-23
- Total releases
- 16 / 6 yrs
- License
- MIT + file LICENSE OSI
- Minimum R
- ≥ 4.1.0
- Bundled data
- 1.2 MB / 14 files
- Download size
- 2.1 MB
Cite
Cite this package
Run in R for the authors' entry:
citation("mikropml")The package provides a citation file, so citation() returns the authors' own entry.
It points to 10.21105/joss.03073.
The repository also keeps a CITATION.cff.
Cite the R Observatory
For a number measured here: a download total, a coverage figure, an archival date.
From data release v2026-10-17, which the citation names so these numbers can be found later. More on citing and the projects behind them.