Package: DynForest 1.2.1

DynForest: Random Forest with Multivariate Longitudinal Predictors

Based on random forest principle, 'DynForest' is able to include multiple longitudinal predictors to provide individual predictions. Longitudinal predictors are modeled through the random forest. The methodology is fully described for a survival outcome in: Devaux, Helmer, Genuer & Proust-Lima (2023) <doi:10.1177/09622802231206477>.

Authors:Anthony Devaux [aut, cre], Robin Genuer [aut], Cécile Proust-Lima [aut], Louis Capitaine [aut]

DynForest_1.2.1.tar.gz
DynForest_1.2.1.zip(r-4.7)DynForest_1.2.1.zip(r-4.6)DynForest_1.2.1.zip(r-4.5)
DynForest_1.2.1.tgz(r-4.6-any)DynForest_1.2.1.tgz(r-4.5-any)
DynForest_1.2.1.tar.gz(r-4.7-any)DynForest_1.2.1.tar.gz(r-4.6-any)
DynForest_1.2.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
DynForest/json (API)

# Install 'DynForest' in R:
install.packages('DynForest', repos = c('https://anthonydevaux.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/anthonydevaux/dynforest/issues

Datasets:

On CRAN:

Conda:

5.65 score 18 stars 10 scripts 556 downloads 7 exports 140 dependencies

Last updated from:46cb72d6f1. Checks:9 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-x86_64OK214
source / vignettesOK261
linux-release-x86_64OK184
macos-release-arm64OK209
macos-oldrel-arm64OK176
windows-develOK128
windows-releaseOK135
windows-oldrelOK138
wasm-releaseOK191

Exports:compute_gvimpcompute_ooberrorcompute_vardepthcompute_vimpdynforestget_treeget_treenodes

Dependencies:askpassbackportsbase64encbitbit64bootbslibcachemcellrangercheckmateclassclicliprclustercmprskcodetoolscolorspacecpp11crayoncurldata.tableDescToolsdiagramdigestdoParalleldoRNGe1071evaluateExactexpmfarverfastmapfontawesomeforcatsforeachforeignFormulafsfuturefuture.applyggplot2gldglmnetglobalsgluegridExtragtablehavenhighrHmischmshtmlTablehtmltoolshtmlwidgetshttrisobanditeratorsjquerylibjsonliteKernSmoothknitrlabelinglatticelavalcmmlifecyclelistenvlmommagrittrmarqLevAlgMASSMatrixMatrixModelsmemoisemetsmimemultcompmvtnormnlmennetnumDerivopensslparallellypbapplypecpillarpkgconfigplotrixpolsplineprettyunitsprodlimprogressprogressrproxyPublishquantregR6rangerrappdirsRColorBrewerRcppRcppArmadilloRcppEigenreadrreadxlrematchriskRegressionrlangrmarkdownrmsrngtoolsrootSolverpartrstudioapiS7sandwichsassscalesshapespacefillrSparseMSQUAREMstringistringrsurvivalsysTH.datatibbletidyselecttimeregtinytextzdbutf8vctrsviridisLitevroomwithrxfunyamlzoo

How to use DynForest with survival outcome?
Illustrative dataset: pbc2 dataset | Data management | Specification of the models for the time-dependent predictors | Random forest building | Out-Of-Bag error | Individual prediction of the outcome | Predictiveness of the variables | Variable importance | Minimal depth | Guidelines to tune the hyperparameters | References
Rendered fromsurvival.Rmdusingknitr::rmarkdown

Last update: 2024-10-25
Started: 2024-10-23

Introduction to DynForest methodology
The tree building | Individual prediction of the outcome | Out-Of-Bag individual prediction | Individual dynamic prediction from a landmark time | Out-Of-Bag prediction error | Explore the most predictive variables | Variable importance | Minimal depth | References
Rendered fromintroduction.Rmdusingknitr::rmarkdown

Last update: 2024-10-23
Started: 2024-10-23

How to use DynForest with categorical outcome?
Illustrative dataset: pbc2 dataset | Data management | The random forest building | Out-Of-Bag error | Prediction of the outcome | Predictiveness variables | Variable importance | Minimal depth | References
Rendered fromclassification.Rmdusingknitr::rmarkdown

Last update: 2024-10-23
Started: 2024-10-23

How to use DynForest with continuous outcome?
Illustrative dataset: data_simu1 and data_simu2 datasets | Data management | The random forest building | Out-Of-Bag error | Prediction of the outcome | Predictiveness of the variables
Rendered fromregression.Rmdusingknitr::rmarkdown

Last update: 2024-10-23
Started: 2024-10-23

Overview of DynForest package
dynforest() function | Arguments | Values | Additional information about the dependencies | predict() function | References
Rendered fromoverview.Rmdusingknitr::rmarkdown

Last update: 2024-10-23
Started: 2024-10-23

Readme and manuals

Help Manual

Help pageTopics
Compute the grouped importance of variables (gVIMP) statisticcompute_gvimp
Compute the Out-Of-Bag error (OOB error)compute_ooberror
Extract characteristics from the trees building processcompute_vardepth
Compute the importance of variables (VIMP) statisticcompute_vimp
data_simu1 datasetdata_simu1
data_simu2 datasetdata_simu2
Random forest with multivariate longitudinal endogenous covariatesdynforest
Extract some information about the split for a tree by userget_tree
Extract nodes identifiers for a given treeget_treenodes
pbc2 datasetpbc2
Plot function in dynforestplot.dynforest plot.dynforestgvimp plot.dynforestpred plot.dynforestvardepth plot.dynforestvimp
Prediction using dynamic random forestspredict.dynforest
Print functionprint.dynforest print.dynforestgvimp print.dynforestoob print.dynforestpred print.dynforestvardepth print.dynforestvimp
Display the summary of dynforestsummary.dynforest summary.dynforestoob