diff core/magnatagatune/sim_from_comparison_UNfair_components.m @ 0:e9a9cd732c1e tip

first hg version after svn

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/core/magnatagatune/sim_from_comparison_UNfair_components.m	Tue Feb 10 15:05:51 2015 +0000
@@ -0,0 +1,91 @@
+function [partBinTrn, partBinTst, partBinNoTrn] = sim_from_comparison_UNfair_components(comparison, comparison_ids, k, trainpart, filename)
+%
+% FOR ISMIR 2012 
+%
+% creates a cross-validation partitioning of the 
+% similarity data in "multiG", NOT PRESERVING the 
+% connected components in it during partitioning
+
+% ---
+% get the similarity multigraph and remove cycles
+% ---
+cprint(2, 'creating graph')
+% Gm = ClipSimGraphMulti(comparison, comparison_ids);
+% Gm.remove_cycles_length2; 
+cprint(2, 'loading Multigraph for Similarity Constraints')
+load('comp_SimGraphMulti.mat', 'G');
+
+
+% get similarity data
+[weights, a, b, c] = G.similarities();
+
+% ---
+% We randomise the constraint succession 
+% ---
+datPermu = randperm(numel(a));
+a = a(datPermu);
+b = b(datPermu);
+c = c(datPermu);
+weights = weights(datPermu);
+
+% ---
+% NOTE: we try the easy route: partition the graphs
+% and look at which constraints  balance we end up with
+% ---
+P = cvpartition(numel(a), 'k', k);
+
+% ---
+% here we export  similarity test sets
+% ---
+cprint(2, 'export test similarity')
+partBinTst = {};
+for i = 1:P.NumTestSets  % test runs
+
+    partBinTst{i} = [a(P.test(i))' b(P.test(i))' c(P.test(i))' weights(P.test(i))];
+end
+
+
+% ---
+% Note: This uses a "truly" increasing training set
+% to do the partial training partition
+% ---
+cprint(2, 'export train similarity')
+for m = 1:numel(trainpart)
+
+    % save test indices
+    Ptrain(m) = cvpartition_trunctrain_incsubsets(P, trainpart(m));
+end
+
+% ---
+% here we export similarity training sets
+% ---
+partBinTrn = {};
+for i = 1:P.NumTestSets % train runs
+
+    for m = 1:numel(trainpart) % increasing training sets
+
+        % get training indices
+        idxB = Ptrain(m).training(i);
+        
+        % save into cell
+        partBinTrn{i,m} = [a(idxB)' b(idxB)' c(idxB)' weights(idxB)];
+    end   
+end
+
+partBinNoTrn = {};
+for i = 1:P.NumTestSets % train runs
+
+    for m = 1:numel(trainpart) % increasing training sets
+
+        % get training indices
+        idxB = ~Ptrain(m).training(i) & ~Ptrain(m).test(i);
+        
+        % save into cell
+        partBinNoTrn{i,m} = [a(idxB)' b(idxB)' c(idxB)' weights(idxB)];
+    end   
+end
+
+if nargin == 5
+    save(filename, 'partBinTrn', 'partBinTst', 'partBinNoTrn')
+end
+end
\ No newline at end of file