NMFStrategyOctave-class: S4 Interface for Octave-Matlab NMF Algorithms

In renozao/NMF: Algorithms and Framework for Nonnegative Matrix Factorization (NMF)

Description

This class implements the virtual interface NMFStrategy for NMF algorithms that are implemented in Octave/Matlab, and provided as a set of .m files or as plain code.

Usage

## S4 method for signature 'NMFStrategyOctave,matrix,NMFfit'
run(object, y, x, ...)

## S4 method for signature 'NMFStrategyOctave'
algorithm(object, load = FALSE)

## S4 replacement method for signature 'NMFStrategyOctave,character'
algorithm(object) <- value

## S4 method for signature 'NMFStrategyOctave'
show(object)

Arguments

object	an object of class NMFStrategyOctave, which encapsulates the Octave NMF algorithm to run, access or modify.
y	the target data that we want to approximate, passed as a matrix(-like) object.
x	an NMFfit object used as a starting point/seed by the algorithm.
...	other arguments passed as parameters to the algorithm's Octave implementation.
load	logical that indicates if the algorithm should be loaded as an R function.
value	a single character string that speficies the name of a defined Octave function that implements the NMF algorithm.

Details

The run method for this class runs the algorithms via the RcppOctave package.

Slots

algorithm

character string that gives the name of the main Octave/Matlab function that implements the algorithm. The function must take at least two arguments: the target matrix and the initial NMF model, converted into an Octave list object, whose named element correspond to the slots of the R object's S4 class.

mcode

character vector that contains a set of path to .m files. These files are (re-)sourced every time the strategy is called, and must be present at runtime in the current directory or in a directory from Octave path.

Methods (by generic)

• run(object = NMFStrategyOctave,y = matrix,x = NMFfit): Runs the NMF algorithms implemented by the Octave/Matlab function associated with the strategy – and stored in slot 'algorithm' of object.

  This method is usually not called directly, but only via the function nmf, which takes care of many other details such as seeding the computation, handling RNG settings, or setting up parallel computations.

• algorithm(object = NMFStrategyOctave): Returns the name of the Octave/Matlab function that implements the NMF algorithm – as stored in slot algorithm.

• algorithm<-(object = NMFStrategyOctave,value = character): Sets the name of the Octave/Matlab function that implements the NMF algorithm. It is stored in slot algorithm.

renozao/NMF documentation built on June 14, 2020, 9:35 p.m.