Description of slapplypca

Home > sltoolbox > subspace > slapplypca.m

slapplypca

PURPOSE

SLAPPLYPCA Applies PCA model to samples

SYNOPSIS

function Y = slapplypca(S, X)

DESCRIPTION

SLAPPLYPCA Applies PCA model to samples

 $ Syntax $
   Y = slapplypca(S, X)

 $ Arguments $
   - S:        the struct representing the PCA model 
   - X:        the sample matrix
   - Y:        the principal component vectors of the samples

 $ Description $
   - Y = slapplypca(S, X) applies the PCA model S to reduce the
     vector dimensions of samples X. It outputs the PCA features by Y.
     The formula for transform for each sample x in X is:
     y = S.P' * (x - S.vmean)

 $ History $
   - Created by Dahua Lin on May 1st, 2006
   - Modified by Dahua Lin, on Sep 10, 2006
       - change sladd to sladdvec

CROSS-REFERENCE INFORMATION

This function calls:

• sladdvec SLADDVEC adds a vector to columns or rows of a matrix
• raise_lackinput RAISE_LACKINPUT Raises an error indicating lack of input argument

This function is called by:

SOURCE CODE

0001 function Y = slapplypca(S, X)
0002 %SLAPPLYPCA Applies PCA model to samples
0003 %
0004 % $ Syntax $
0005 %   Y = slapplypca(S, X)
0006 %
0007 % $ Arguments $
0008 %   - S:        the struct representing the PCA model
0009 %   - X:        the sample matrix
0010 %   - Y:        the principal component vectors of the samples
0011 %
0012 % $ Description $
0013 %   - Y = slapplypca(S, X) applies the PCA model S to reduce the
0014 %     vector dimensions of samples X. It outputs the PCA features by Y.
0015 %     The formula for transform for each sample x in X is:
0016 %     y = S.P' * (x - S.vmean)
0017 %
0018 % $ History $
0019 %   - Created by Dahua Lin on May 1st, 2006
0020 %   - Modified by Dahua Lin, on Sep 10, 2006
0021 %       - change sladd to sladdvec
0022 %
0023 
0024 %% parse and verify input arguments
0025 if nargin < 2
0026     raise_lackinput('slapplypca', 2);
0027 end
0028 
0029 if ndims(X) ~= 2
0030     error('sltoolbox:invaliddims', ...
0031         'The sample matrix X should be a 2D matrix');
0032 end
0033 
0034 if size(X, 1) ~= S.sampledim
0035     error('sltoolbox:sizmismatch', ...
0036         'The sample dimension does not match that of PCA model');
0037 end
0038 
0039 %% compute
0040 Y = S.P' * sladdvec(X, -S.vmean, 1);

---

Generated on Wed 20-Sep-2006 12:43:11 by m2html © 2003