caretFitBglr: Fit with BGLR for caret

In timflutre/rutilstimflutre: Timothee Flutre's personal R code

Fit with BGLR for caret

Description

The argument named ETA is compulsory for BGLR::BGLR. Only its first component will be taken into account. The design matrix of its first component will be set to be x. The model of its first component is used in output files.

Usage

caretFitBglr(
  x,
  y,
  wts,
  param,
  lev,
  last,
  weights,
  classProbs,
  ETA,
  saveAt,
  nIter,
  burnIn,
  thin,
  keep.samples = FALSE,
  ...
)

Arguments

x	current predictors used to fit the model
y	current outcome used to fit the model
wts	optional instance weights
param	current tuning parameter values
lev	class levels of the outcome (or NULL in regression)
last	logical for whether the current fit is the final fit
weights	?
classProbs	logical for whether class probabilities should be computed
ETA	two-level list used to specify the regression function for BGLR::BGLR
saveAt	string that may include a path and a pre-fix that will be added to the name of the files that are saved as BGLR::BGLR runs
nIter	number of iterations
burnIn	number of burn-in
thin	thinning
keep.samples	logical for whether the samples will be returned (as a coda::mcmc.list)
...	arguments passed on to BGLR::BGLR

Value

output of BGLR::BGLR and, optionally, the samples

Author(s)

Timothee Flutre

timflutre/rutilstimflutre documentation built on Feb. 7, 2024, 8:17 a.m.