sammon

P = sammon(D, P, varargin)

SAMMON Computes Sammon's mapping of a data set.

 P = sammon(D, P, [value], [mode], [alpha], [Mdist])

  P = sammon(D,2);            % projection to 2-dim space
  P = sammon(sMap,3);         % projects the codebook vectors
  P = sammon(sMap,3,[],[],[],Md) % uses distance matrix Md
  som_grid(sMap,'Coord',P)    % visualization of map projection

  Input and output arguments ([]'s are optional):
   D        (matrix) size dlen x dim, data to be projected
            (struct) data or map struct            
   P        (scalar) output dimension
            (matrix) size dlen x odim, initial projection matrix
   [value]  (scalar) all different modes (the next argument) require 
                     a value, default = 100
   [mode]   (string) 'steps' or 'errlimit' or 'errchange' or 'seconds',
                     see below, default is 'steps'
   [alpha]  (scalar) iteration step size, default = 0.2
   [Dist]   (matrix) pairwise distance matrix, size dlen x dlen.
                     If the distances in the input space should
                     be calculated otherwise than as euclidian
                     distances, the distance from each vector
                     to each other vector can be given here,
                     size dlen x dlen. For example PDIST
                     function can be used to calculate the
                     distances: Dist = squareform(pdist(D,'mahal'));

   P        (matrix) size dlen x odim, the projections

 The output dimension must be 2 or higher but (naturally) lower 
 than data set dimension.

 The mode argument determines the end condition for iteration. If 
 the mode argument is used, also the value argument has to be 
 specified. Different mode possibilities are:
 'steps'      the iteration is terminated when it is run  
 'errlimit'   steps, the iteration is terminated when projection error 
              is lower than ,
 'errchange'  the iteration is terminated when change between 
              projection error on two successive iteration rounds
	       is less than  percent of total error, and
 'seconds'    the iteration is terminated after  seconds 
              of iteration.

 See also CCA, PCAPROJ, SOM_GRID.