generate_params: Generate parameter values of a PO2PLS model
In selbouhaddani/PO2PLS: Probabilistic Two-Way Orthogonal Partial Least Squares

generate_params

R Documentation

Generate parameter values of a PO2PLS model

Generate parameter values of a PO2PLS model

generate_params(
  X,
  Y,
  r,
  rx,
  ry,
  alpha = 0.1,
  type = c("random", "o2m", "unit")
)

`X`	Numerical data matrix or positive integer. This parameter should either be a dataset `X` or the number of desired `X` variables.
`Y`	Numerical data matrix or positive integer. This parameter should either be a dataset `Y` or the number of desired `Y` variables.
`r`	Positive integer. Number of joint PLS components. Must be positive!
`rx`	Non-negative integer. Number of orthogonal components in `X`. Can be 0
`ry`	Non-negative integer. Number of orthogonal components in `Y`. Can be 0
`alpha`	Numeric vector. The length should be either one or three, with each entry between 0 and 1. It represents the proportion of noise relative to the variation of `X`, `Y`, and `U`, respectively. If only one number is given, it is used for all three parts.
`type`	Character. Should be one of "random", "o2m" or "unit". Specifies which kind of parameters should be generated. If "o2m" is chosen, `X` and `Y` should be data matrices.

A list of PO2PLS parameters are generated based on the value of type:

type="random": Variance parameters are randomly sampled from a uniform distribution on 1 and 3 (1 and 4 for B).
type="o2m": O2PLS is fitted to X and Y first using o2m from the OmicsPLS package, and the corresponding PO2PLS parameters are derived from the result.
type="unit": The diagonal of each covariance matrix is a decreasing sequence from the number of components to one.