CDpca: CDpca

In luisrei/new-cdpca: Clustering and Disjoint Principal Component Analysis

Description

CDpca performs a clustering and disjoint principal components analysis on the given numeric data matrix and returns a list of results.

Usage

CDpca(data, class, fixAtt, nnloads = 0, Q, P, tol, maxit, r)

Arguments

data	data frame (numeric).
class	vector (numeric) or 0, if classes of objects are unknown.
fixAtt	vector (numeric) or 0, for a selection of attributes.
nnloads	1 or 0, for nonnegative loadings.
Q	integer, number of clusters of variables.
P	integer, number of clusters of objects.
tol	real number, small positive tolerance.
maxit	integer, maximum of iterations.
r	number of runs of the cdpca algoritm for the final solution.

Value

iter: iterations used in the best loop for computing the best solution loop: best loop number timebestloop: computation time on the best loop timeallloops: computation time for all loops Y: the component score matrix Ybar: the object centroids matrix in the reduced space A: the component loading matrix U: the partition of objects V: the partition of variables Fobj: function to maximize bcdev: between cluster deviance bcdevTotal: between cluster deviance over the total variability tableclass: cdpca classification pseudocm: pseudo confusion matrix of the real and cdpca classifications Enorm: error norm for the obtained cdpca model

Examples

exampleCDpca = CDpca(data, class, fixAtt, nnloads, Q, P, tol, maxit, r)

luisrei/new-cdpca documentation built on May 17, 2019, 7:45 a.m.