function[res_ordering] = ViewDenDroStruct(run_structures,viewparams)
ViewDenDroStruct: Shows the dendrograms of the edges according to
their co-occurrence in the structures learned by
the EDAs. Allows to detect complex hierarchical
relationships between the variables of the problem
INPUT
run_structures: Contain the data structures with all the structures
learned by the probability models in every run and generation (see
program ReadStructures.m for details.
viewparams{1} = fs; % fs: Font size for the images
viewparams{2} : Matrices with edges that will be shown. One row for each
edge. If viewparams{2}== [], the algorithm finds a subset of edges
according viewparams{3}
viewparams{3} = const_edg : Minimal number of times that an edge has to appear in (all) the structures learned
to be selected for visualization. Since the clarity of the parallel coordinate
visualization depend on the number of variables, this is an important parameter.
viewparams{4} = min_edg : Minimal number of edges in the substructures selected (min_edg>0)
viewparams{5} = distance. Distance used to cluster edges from their
appearance in the structures (distances used by matlab command pdist (ex. 'correlation', 'euclidean',etc.) can
be used (see help pdist).
OUTPUT:
res_ordering{1} = T;
res_ordering{2} = PERM; % Ordering of the variables in the dendrogram
res_ordering{3} = List of the originals edges in the order they are shown
in the dendrogram
Last version 8/26/2008. Roberto Santana (roberto.santana@ehu.es)0001 function[res_ordering] = ViewDenDroStruct(run_structures,viewparams) 0002 % function[res_ordering] = ViewDenDroStruct(run_structures,viewparams) 0003 % ViewDenDroStruct: Shows the dendrograms of the edges according to 0004 % their co-occurrence in the structures learned by 0005 % the EDAs. Allows to detect complex hierarchical 0006 % relationships between the variables of the problem 0007 % 0008 % INPUT 0009 % run_structures: Contain the data structures with all the structures 0010 % learned by the probability models in every run and generation (see 0011 % program ReadStructures.m for details. 0012 % viewparams{1} = fs; % fs: Font size for the images 0013 % viewparams{2} : Matrices with edges that will be shown. One row for each 0014 % edge. If viewparams{2}== [], the algorithm finds a subset of edges 0015 % according viewparams{3} 0016 % viewparams{3} = const_edg : Minimal number of times that an edge has to appear in (all) the structures learned 0017 % to be selected for visualization. Since the clarity of the parallel coordinate 0018 % visualization depend on the number of variables, this is an important parameter. 0019 % viewparams{4} = min_edg : Minimal number of edges in the substructures selected (min_edg>0) 0020 % viewparams{5} = distance. Distance used to cluster edges from their 0021 % appearance in the structures (distances used by matlab command pdist (ex. 'correlation', 'euclidean',etc.) can 0022 % be used (see help pdist). 0023 % OUTPUT: 0024 % res_ordering{1} = T; 0025 % res_ordering{2} = PERM; % Ordering of the variables in the dendrogram 0026 % res_ordering{3} = List of the originals edges in the order they are shown 0027 % in the dendrogram 0028 % 0029 % Last version 8/26/2008. Roberto Santana (roberto.santana@ehu.es) 0030 0031 0032 indexmatrix = run_structures{1}; 0033 fs = viewparams{1}; 0034 substruct = viewparams{2}; 0035 const_edg = viewparams{3}; 0036 min_edg = viewparams{4}; 0037 distance = viewparams{5}; 0038 0039 results = []; 0040 0041 0042 if isempty(substruct) 0043 [RepEdges] = SelectEdgesToShow(run_structures,const_edg); % Edges are selected according to const_edg value 0044 if(isempty(RepEdges)) 0045 disp('No edges were selected. Reduce the number of times required to an edge to appear.') %No edges were found 0046 return 0047 end 0048 for i=1:size(RepEdges,2) 0049 [row,col] = find(indexmatrix==RepEdges(i)); 0050 dlabels{i} = [int2str(row(1)),'-',int2str(col(1))]; 0051 end 0052 else 0053 for i=1:size(substruct,1) 0054 RepEdges(1,i) = indexmatrix(substruct(i,1),substruct(i,2)); % Indices of the edges in indexmatrix 0055 dlabels{i} = [int2str(substruct(i,1)),'-',int2str(substruct(i,2))]; 0056 end 0057 end 0058 0059 0060 [AllRepVectors] = ExtractSubstructures(run_structures,RepEdges,min_edg); % The substructures to be shown are extracted 0061 0062 nedges = size(RepEdges,2) 0063 0064 0065 y = pdist(AllRepVectors', distance); 0066 z = linkage(y,'single') 0067 0068 figure % Dendrogram figure 0069 axes('Fontsize',fs); 0070 [H,T,PERM] = dendrogram(z,nedges,'orientation','left','labels',dlabels); 0071 0072 0073 res_ordering{1} = T; 0074 res_ordering{2} = PERM; % Ordering of the variables in the dendrogram 0075 0076 for i=1:nedges 0077 [row,col] = find(indexmatrix==RepEdges(PERM(i))); 0078 res_ordering{3}(i,:) = [row(1),col(1)]; 0079 end 0080 0081 return 0082 0083 0084 0085 0086 0087 0088 0089 0090 0091