GD.Biplot: Biplot for continuous data based on gradient descent methods
In villardon/MultBiplotR: Multivariate Analysis Using Biplots in R

Description Usage Arguments Details Value Author(s) Examples

Biplot for continuous data based on gradient descent methods.

GD.Biplot(X, dimension = 2, Scaling = 5, 
         lambda = 0.01, OptimMethod = "CG", 
         Orthogonalize = FALSE, Algorithm = "Alternated", 
         sup.rows = NULL, sup.cols = NULL,
         grouping = NULL, tolerance = 1e-04, 
         num_max_iters = 300, Initial = "random")

`X`	A data matrix with continuous variables.
`dimension`	Dimension of the final solution.
`Scaling`	Transformation of the raw data matrix before the calculation of the biplot.
`lambda`	Constant for the ridge Penalization
`OptimMethod`	Optimization method passed to the `optimr` function. By default is CG (Conjugate Gradient).
`Orthogonalize`	Should the solution be ortogonalized.
`Algorithm`	Algorithm to calculate the Biplot. (Alternated, Joint, Recursive)
`sup.rows`	Supplementary Rows. (not working now)
`sup.cols`	Supplementary Columns. (not working now)
`grouping`	Grouping factor for the within groups transformation.
`tolerance`	Tolerance for convergence
`num_max_iters`	Maximum number of iterations.
`Initial`	Initial Configuration

The function calculates a bilot using gradient descent methods. The function optimr is used to optimize the loss function. By default CG (Conjugate Gradient) method is used althoug other possibilities can be used.

An object of class "ContinuousBiplot" is returned.

Jose Luis Vicente Villardon

data("Protein")
X=Protein[,3:11]
gdbip=GD.Biplot(X, dimension=2, Algorithm="Joint", 
Orthogonalize=FALSE, lambda=0.3, Initial="random")
plot(gdbip)
summary(gdbip)