matthiasm@8: function bnet = learn_params(bnet, data)
matthiasm@8: % LEARN_PARAMS Find the maximum likelihood params for a fully observed model
matthiasm@8: % bnet = learn_params(bnet, data)
matthiasm@8: %
matthiasm@8: % data(i,m) is the value of node i in case m (can be a cell array)
matthiasm@8: %
matthiasm@8: % We set bnet.CPD{i} to its ML/MAP estimate.
matthiasm@8: %
matthiasm@8: % Currently we assume no param tying
matthiasm@8: 
matthiasm@8: % AND THAT EACH DATA POINT IS A SCALAR - no longer assumed
matthiasm@8: 
matthiasm@8: %if iscell(data)
matthiasm@8: %  data=cell2num(data);
matthiasm@8: %end
matthiasm@8: [n ncases] = size(data);
matthiasm@8: for j=1:n
matthiasm@8:   e = bnet.equiv_class(j);
matthiasm@8:   assert(e==j);
matthiasm@8:   if adjustable_CPD(bnet.CPD{e})
matthiasm@8:     fam = family(bnet.dag,j);
matthiasm@8:     %bnet.CPD{j} = learn_params(bnet.CPD{j}, data(fam,:));
matthiasm@8:     bnet.CPD{j} = learn_params(bnet.CPD{j}, fam, data, bnet.node_sizes, bnet.cnodes);
matthiasm@8:   end
matthiasm@8: end
matthiasm@8: