Mercurial > hg > camir-aes2014

annotate toolboxes/FullBNT-1.0.7/KPMtools/mk_stochastic.m @ 0:e9a9cd732c1e tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
first hg version after svn
author wolffd
date Tue, 10 Feb 2015 15:05:51 +0000
parents
children
rev   line source
wolffd@0 1 function [T,Z] = mk_stochastic(T)
wolffd@0 2 % MK_STOCHASTIC Ensure the argument is a stochastic matrix, i.e., the sum over the last dimension is 1.
wolffd@0 3 % [T,Z] = mk_stochastic(T)
wolffd@0 4 %
wolffd@0 5 % If T is a vector, it will sum to 1.
wolffd@0 6 % If T is a matrix, each row will sum to 1.
wolffd@0 7 % If T is a 3D array, then sum_k T(i,j,k) = 1 for all i,j.
wolffd@0 8
wolffd@0 9 % Set zeros to 1 before dividing
wolffd@0 10 % This is valid since S(j) = 0 iff T(i,j) = 0 for all j
wolffd@0 11
wolffd@0 12 if (ndims(T)==2) & (size(T,1)==1 | size(T,2)==1) % isvector
wolffd@0 13 [T,Z] = normalise(T);
wolffd@0 14 elseif ndims(T)==2 % matrix
wolffd@0 15 Z = sum(T,2);
wolffd@0 16 S = Z + (Z==0);
wolffd@0 17 norm = repmat(S, 1, size(T,2));
wolffd@0 18 T = T ./ norm;
wolffd@0 19 else % multi-dimensional array
wolffd@0 20 ns = size(T);
wolffd@0 21 T = reshape(T, prod(ns(1:end-1)), ns(end));
wolffd@0 22 Z = sum(T,2);
wolffd@0 23 S = Z + (Z==0);
wolffd@0 24 norm = repmat(S, 1, ns(end));
wolffd@0 25 T = T ./ norm;
wolffd@0 26 T = reshape(T, ns);
wolffd@0 27 end