bigPLSR (version 0.7.2)

pls_cross_validate: Cross-validate PLS models

Description

Cross-validate PLS models

Usage

pls_cross_validate(
  X,
  Y,
  ncomp,
  folds = 5L,
  type = c("kfold", "loo"),
  algorithm = c("simpls", "nipals", "kernelpls", "widekernelpls"),
  backend = "arma",
  metrics = c("rmse", "mae", "r2"),
  seed = NULL,
  parallel = c("none", "future"),
  future_seed = TRUE,
  ...
)

Value

A list containing per-fold metrics and their summary across folds.

Arguments

X

Predictor matrix as accepted by pls_fit()

Y

Response matrix or vector as accepted by pls_fit()

ncomp

Integer; components grid to evaluate.

folds

Number of folds (ignored when type = "loo").

type

Either "kfold" (default) or "loo".

algorithm

Backend algorithm: "simpls", "nipals", "kernelpls" or "widekernelpls".

backend

Backend passed to pls_fit().

metrics

Metrics to compute (subset of "rmse", "mae", "r2").

seed

Optional seed for reproducibility.

parallel

Logical or character; same semantics as in pls_bootstrap().

future_seed

Logical or integer; reproducible seeds for parallel evaluation.

...

Passed to pls_fit().

Examples

set.seed(123)
X <- matrix(rnorm(60), nrow = 20)
y <- X[, 1] - 0.5 * X[, 2] + rnorm(20, sd = 0.1)
pls_cross_validate(X, y, ncomp = 2, folds = 3)