dimRed (version 0.2.6)

dimRedMethod-class: Class "dimRedMethod"

Description

A virtual class "dimRedMethod" to serve as a template to implement methods for dimensionality reduction.

Slots

fun

A function that does the embedding.

stdpars

A list with the default parameters for the fun slot.

requires

A vector with all packages R packages that need to be installed to run the method. In some occasions a method may work without one of the packages. Does not include Python dependencies such as Tensorflow. Used to auto skip tests

Details

Implementations of dimensionality reductions should inherit from this class.

The fun slot should be a function that takes three arguments

data

An object of class dimRedData.

pars

A list with the standard parameters.

keep.org.data

Logical. If the original data should be kept in the output.

and returns an object of class dimRedResult.

The stdpars slot should take a list that contains standard parameters for the implemented methods.

This way the method can be called by embed(data, "method-name", ...), where ... can be used to to change single parameters.

See Also

Other dimensionality reduction methods: AutoEncoder-class, DRR-class, DiffusionMaps-class, DrL-class, FastICA-class, FruchtermanReingold-class, HLLE-class, Isomap-class, KamadaKawai-class, MDS-class, NNMF-class, PCA-class, PCA_L1-class, UMAP-class, dimRedMethodList(), kPCA-class, nMDS-class, tSNE-class