Package: bigPLSR
Version: 0.7.2
Date: 2025-11-26
Depends: R (>= 4.0.0)
biocViews:
Imports: Rcpp, bigmemory
LinkingTo: Rcpp, RcppArmadillo, BH, bigmemory
Suggests: bench, dplyr, forcats, future, future.apply, ggplot2, knitr,
        pls, plsRglm, rmarkdown, RhpcBLASctl, svglite, testthat (>=
        3.0.0), tidyr, withr
VignetteBuilder: knitr
Title: Partial Least Squares Regression Models with Big Matrices
Authors@R: c(
  person(given = "Frederic", family= "Bertrand", role = c("cre", "aut"), 
  email = "frederic.bertrand@lecnam.net", comment = c(ORCID = "0000-0002-0837-8281")),
  person(given = "Myriam", family= "Maumy", role = c("aut"), 
  email = "myriam.maumy@ehesp.fr", comment = c(ORCID = "0000-0002-4615-1512")))
Author: Frederic Bertrand [cre, aut] (ORCID:
    <https://orcid.org/0000-0002-0837-8281>),
  Myriam Maumy [aut] (ORCID: <https://orcid.org/0000-0002-4615-1512>)
Maintainer: Frederic Bertrand <frederic.bertrand@lecnam.net>
Description: 
  Fast partial least squares (PLS) for dense and out-of-core data.
  Provides SIMPLS (straightforward implementation of a statistically inspired 
  modification of the PLS method) and NIPALS (non-linear iterative partial least-squares) solvers, 
  plus kernel-style PLS variants ('kernelpls' and 'widekernelpls') with parity to 'pls'. Optimized for
  'bigmemory'-backed matrices with streamed cross-products and chunked BLAS (Basic Linear Algebra Subprograms)
  (XtX/XtY and XXt/YX), optional file-backed score sinks, and deterministic
  testing helpers. Includes an auto-selection strategy that chooses between
  XtX SIMPLS, XXt (wide) SIMPLS, and NIPALS based on (n, p) and a configurable
  memory budget. About the package, Bertrand and Maumy (2023) <https://hal.science/hal-05352069>, 
  and  <https://hal.science/hal-05352061> highlighted fitting and cross-validating 
  PLS regression models to big data. For more details about some of the techniques 
  featured in the package, Dayal and MacGregor (1997) 
  <doi:10.1002/(SICI)1099-128X(199701)11:1%3C73::AID-CEM435%3E3.0.CO;2-%23>,
  Rosipal & Trejo (2001) <https://www.jmlr.org/papers/v2/rosipal01a.html>,
  Tenenhaus, Viennet, and Saporta (2007) <doi:10.1016/j.csda.2007.01.004>,
  Rosipal (2004) <doi:10.1007/978-3-540-45167-9_17>,
  Rosipal (2019) <https://ieeexplore.ieee.org/document/8616346>,
  Song, Wang, and Bai (2024) <doi:10.1016/j.chemolab.2024.105238>.
  Includes kernel logistic PLS with 'C++'-accelerated alternating iteratively 
  reweighted least squares (IRLS) updates, streamed reproducing kernel Hilbert space (RKHS) 
  solvers with reusable centering statistics, and bootstrap
  diagnostics with graphical summaries for coefficients, scores, and
  cross-validation workflows, alongside dedicated plotting utilities for
  individuals, variables, ellipses, and biplots.
  The streaming backend uses far less memory and keeps memory bounded across data sizes.
	For PLS1, streaming is often fast enough while preserving a small memory footprint; 
	for PLS2 it remains competitive with a bounded footprint.
	On small problems that fit comfortably in RAM (random-access memory), dense in-memory 
	solvers are slightly faster; the crossover occurs as n or p grow and the Gram/cross-product cost dominates.
License: GPL-3
Encoding: UTF-8
URL: https://fbertran.github.io/bigPLSR/,
        https://github.com/fbertran/bigPLSR
BugReports: https://github.com/fbertran/bigPLSR/issues
Classification/MSC: 62N01, 62N02, 62N03, 62N99
RoxygenNote: 7.3.3
LazyData: true
Config/testthat/edition: 3
SystemRequirements: C++17, Optional CBLAS (detected at compile time)
NeedsCompilation: yes
Packaged: 2025-11-26 01:52:43 UTC; bertran7
Repository: CRAN
Date/Publication: 2025-12-01 14:50:07 UTC
Built: R 4.4.3; x86_64-w64-mingw32; 2026-02-04 03:11:33 UTC; windows
Archs: x64
