empLPP: Empirical Locality Preserving Projection

In abnormally-distributed/cvreg: Cross Validation and Robust Estimation Utilities

Description

This function implements a variant of the locality preserving projection method. Ordinary locality preserving projections require user-defined parameters to construct a graph for characterizing the local structure of the data. Here an empirical (data dependent) approach is used to construct the graph. The only tuning parameter that requires input by the user is the kernel precision parameter tau.

Usage

empLPP(x, ncomp = min(nrow(x) - 1, ncol(x)), h = 1, scale = T)

Arguments

x	a data frame or matrix of numeric covariates
ncomp	number of desired components
h	kernel smoothing parameter. defaults to 1.
scale	should the variables be scaled prior to analysis? Defaults to TRUE.

Value

a 'PrincipalComp' object.

References

Yang, B. and Chen, S. (2010). Sample-dependent graph construction with application to dimensionality reduction. Neurocomputing, 74(1-3), pp. 301–314.

abnormally-distributed/cvreg documentation built on May 3, 2020, 3:45 p.m.