Daniel@0: function [PCcoeff, PCvec] = pca(data, N)
Daniel@0: %PCA	Principal Components Analysis
Daniel@0: %
Daniel@0: %	Description
Daniel@0: %	 PCCOEFF = PCA(DATA) computes the eigenvalues of the covariance
Daniel@0: %	matrix of the dataset DATA and returns them as PCCOEFF.  These
Daniel@0: %	coefficients give the variance of DATA along the corresponding
Daniel@0: %	principal components.
Daniel@0: %
Daniel@0: %	PCCOEFF = PCA(DATA, N) returns the largest N eigenvalues.
Daniel@0: %
Daniel@0: %	[PCCOEFF, PCVEC] = PCA(DATA) returns the principal components as well
Daniel@0: %	as the coefficients.  This is considerably more computationally
Daniel@0: %	demanding than just computing the eigenvalues.
Daniel@0: %
Daniel@0: %	See also
Daniel@0: %	EIGDEC, GTMINIT, PPCA
Daniel@0: %
Daniel@0: 
Daniel@0: %	Copyright (c) Ian T Nabney (1996-2001)
Daniel@0: 
Daniel@0: if nargin == 1
Daniel@0:    N = size(data, 2);
Daniel@0: end
Daniel@0: 
Daniel@0: if nargout == 1
Daniel@0:    evals_only = logical(1);
Daniel@0: else
Daniel@0:    evals_only = logical(0);
Daniel@0: end
Daniel@0: 
Daniel@0: if N ~= round(N) | N < 1 | N > size(data, 2)
Daniel@0:    error('Number of PCs must be integer, >0, < dim');
Daniel@0: end
Daniel@0: 
Daniel@0: % Find the sorted eigenvalues of the data covariance matrix
Daniel@0: if evals_only
Daniel@0:    PCcoeff = eigdec(cov(data), N);
Daniel@0: else
Daniel@0:   [PCcoeff, PCvec] = eigdec(cov(data), N);
Daniel@0: end
Daniel@0: