added README, added ability to specify output folder, and use 10 folds default, and calculate the fold size instead of the inverse

2 files changed, 163 insertions, 0 deletions

diff --git a/fly-tools/cci-calculator/LeastSquareSolution.m b/fly-tools/cci-calculator/LeastSquareSolution.m
new file mode 100644
index 0000000..275f822
--- /dev/null
+++ b/fly-tools/cci-calculator/LeastSquareSolution.m
@@ -0,0 +1,133 @@
+function [x, e] = LeastSquareSolution(fileNameA, fileNameB, output)
+    inputData = load(fileNameA);
+    A = inputData;
+    inputData = load(fileNameB);
+    b = inputData;
+    % singular value decomposition
+    CI = [];
+    
+    %testing one sample at a time, using all remaining samples as training data
+
+   total_folds = 10;
+   fold_size = length(b)/total_folds;
+
+   total_folds = floor(total_folds)
+   remainder_of_total_folds = length(b) - total_folds*fold_size
+   elements_per_fold = fold_size;
+   
+   solution=[];
+   
+   for i=0:(total_folds-1)
+       
+        % debug
+        file_id_number = num2str((i+1),'%2d');
+        
+        debug_file = strcat(output, '/');
+        debug_file = strcat(debug_file, 'Fold_');
+        debug_file = strcat(debug_file, file_id_number); 
+        debug_file = strcat(debug_file, '.txt');
+        
+    
+       
+
+       
+        if (i == (total_folds-1))
+            elements_per_fold = fold_size + remainder_of_total_folds
+        end
+        %select one sample at a time for testing using the rest for training
+
+        %if the value is set to 1, that is the sample that will be used for
+
+        %training/testing
+
+        train = ones(length(b),1); %create a column vector of ones
+
+        for k=(i*fold_size+1):((i*fold_size) + elements_per_fold)
+            train(k) = 0;   %set the i-th sample to be the test sample, all others are used for training
+        end
+
+        train = ismember(train, 1); %converts to logical the train set
+
+        test = ismember(train, 0);  %converts to logical the test set
+
+        A_ = A(train,:); % A_ will contain all the data except the test data. This is the train data.
+        b_ = b(train); % b_ will contain all status except the test status
+        [m n] = size(A_);
+    
+        % do the SVD on the test A data
+        [U,S,V] = svd(A_);
+        
+        % this value should be equal to A_
+        U*S*V';
+        
+
+        % compute the c from the training b data
+        c = U'*b_;
+        
+        % compute y on from the singular values
+        y=[];
+        for j=1:n
+            yj = c(j)/S(j,j);
+            y = [y; yj];
+        end
+ 
+        % compute the unknown x values we are trying to find the least
+        % square approximation of
+        x = V*y;
+        
+        % the error estimate on the training data
+        e = A_*x - b_;
+
+        % add the solution to the solution vector
+        solution = [solution; x']
+
+        % compute the ci value of the test data
+        test_data = A(test,:); % this extract just a row vector
+        size(test_data)
+        
+        ci = test_data*x;      % compute the ci value for this test sample
+        
+        %saving the calculated cis
+        CI = [CI; ci];         % store the ci values
+       
+    
+        %fid_debug = fopen(debug_file,'w');
+        %fprintf(fid_debug, '%s\n','Train data');
+        %fprintf(fid_debug, '%8.6f\t%8.6f\t%8.6f\t%8.6f\t%8.6f\t%8.6f\t%8.6f\t%8.6f', A_);
+%         fprintf(fid_debug, '%s\n','Test data');
+%         fprintf(fid_debug, '%8.6f\t%8.6f\t%8.6f\t%8.6f\t%8.6f\t%8.6f\t%8.6f\t%8.6f', test_data);
+        
+        fid_debug = fopen(debug_file,'w');
+%         fprintf(fid_debug, '%s\n\n','Test data');
+        
+        
+        fprintf(fid_debug, '%s\n\n','new CI');
+        fprintf(fid_debug, '%8.6f\n', ci);
+        
+        fprintf(fid_debug, '%s\n\n','actual CI');
+        actual_ci = b(test,:);
+        fprintf(fid_debug, '%8.6f\n', actual_ci);
+        fprintf(fid_debug, '%s\n\n','error');
+        fprintf(fid_debug, '%8.6f\n', (ci-actual_ci));
+%         fprintf(fid_debug, '%s\n\n','Train data');
+        
+        
+        fclose(fid_debug);
+
+        dlmwrite(debug_file, A_, 'delimiter', '\t', '-append');
+        
+        dlmwrite(debug_file, test_data, 'delimiter', '\t', '-append');
+
+   
+   end
+   
+   % write out the ci values
+   fid_ci = fopen('newCIs.txt','w');
+   fprintf(fid_ci, '%8.6f\n', CI);
+   fclose(fid_ci);
+   
+   %fid_solution_vectors = fopen('Solution_vectors.txt', 'w');
+   dlmwrite('Solution_vectors.txt', solution, 'delimiter', '\t');
+   %fclose(fid_solution_vectors);
+   
+        
diff --git a/fly-tools/cci-calculator/README.markdown b/fly-tools/cci-calculator/README.markdown
new file mode 100644
index 0000000..065563c
--- /dev/null
+++ b/fly-tools/cci-calculator/README.markdown
@@ -0,0 +1,30 @@
+== This is the least square solution CCI calulator ==
+
+You'll need to run this in matlab, and have prepared your CSV's in advance. You
+should have two CSV's. One csv should be all of your concatenated feature
+vectors. One feature per column,  columns, and as many rows as you have
+specimen. The second CSV should include the actual CI data recorded and
+calculated by the biologists.
+
+In matlab the command may look like this: (note you need to be in the directory
+to call this)
+
+    [x, e] = LeastSquareSolution('../input/ALL_FVs.csv','ALL_CIs.csv',
+../output/);
+
+Alternatively you can run it without first invoking the compiler by running
+this:
+
+    matlab -r "LeastSquareSolution  ALL_FV.csv ALL_CIs.csv ../output"
+
+
+The ouput will an output specified, and will be in text files that are named
+like this: Fold_1.txt Fold_2.txt etc. You will find it somewhat annoying to have
+to concatenate all that data manually so here is a nice one-liner that allows
+you to concatenate all of your data. For the number of specimen in each fold,
+you need to setup your variables accordingly.
+
+If we have 21 specimen per fold, use number of folds + 2 for the head argument,
+and the number of folds for the tail. This will give you proper results!
+
+    for i in Fold_*.txt; do head $i -n 23 |  tail -n 21 >> output.txt; echo $i; done;