familiar: End-to-End Automated Machine Learning and Model Evaluation

Single unified interface for end-to-end modelling of regression, categorical and time-to-event (survival) outcomes. Models created using familiar are self-containing, and their use does not require additional information such as baseline survival, feature clustering, or feature transformation and normalisation parameters. Model performance, calibration, risk group stratification, (permutation) variable importance, individual conditional expectation, partial dependence, and more, are assessed automatically as part of the evaluation process and exported in tabular format and plotted, and may also be computed manually using export and plot functions. Where possible, metrics and values obtained during the evaluation process come with confidence intervals.

Version: 1.4.0
Depends: R (≥ 4.0.0)
Imports: data.table, methods, rlang (≥ 0.3.4), rstream, survival
Suggests: BART, callr (≥ 3.4.3), cluster, CORElearn, coro, dynamicTreeCut, e1071 (≥ 1.7.5), Ecdat, fastcluster, fastglm, ggplot2 (≥ 3.0.0), glmnet, gtable, harmonicmeanp, isotree (≥ 0.3.0), knitr, labeling, laGP, MASS, maxstat, mboost (≥ 2.9.0), microbenchmark, nnet, partykit, praznik, proxy, qvalue, randomForestSRC, ranger, rmarkdown, scales, testthat (≥ 3.0.0), xml2, VGAM, xgboost
Published: 2022-11-23
Author: Alex Zwanenburg ORCID iD [aut, cre], Steffen Löck [aut], Stefan Leger [ctb], Iram Shahzadi [ctb], Asier Rabasco Meneghetti [ctb], Sebastian Starke [ctb], Technische Universität Dresden [cph], German Cancer Research Center (DKFZ) [cph]
Maintainer: Alex Zwanenburg <alexander.zwanenburg at nct-dresden.de>
BugReports: https://github.com/alexzwanenburg/familiar/issues
License: EUPL
URL: https://github.com/alexzwanenburg/familiar
NeedsCompilation: no
Citation: familiar citation info
Materials: NEWS
CRAN checks: familiar results

Documentation:

Reference manual: familiar.pdf
Vignettes: Evaluation and explanation
Feature selection methods
Introducing familiar
Learning algorithms and hyperparameter optimisation
Performance metrics
Using familiar prospectively

Downloads:

Package source: familiar_1.4.0.tar.gz
Windows binaries: r-devel: familiar_1.4.0.zip, r-release: familiar_1.4.0.zip, r-oldrel: familiar_1.4.0.zip
macOS binaries: r-release (arm64): familiar_1.4.0.tgz, r-oldrel (arm64): familiar_1.4.0.tgz, r-release (x86_64): familiar_1.4.0.tgz, r-oldrel (x86_64): familiar_1.4.0.tgz
Old sources: familiar archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=familiar to link to this page.