BNW using Octave instead of Matlab.

This version of BNW should perform the same as the original version. The only difference is that it uses Octave instead of Matlab when running BayesNet Toolbox during parameter learning.

I am calling this BNW_1.02. It can be accessed at:
compbio.uthsc.edu/BNW_1.02

1 files changed, 25 insertions, 0 deletions

diff --git a/sourcecodes/bnt-master/BNT/learning/mk_tetrad_data_file.m b/sourcecodes/bnt-master/BNT/learning/mk_tetrad_data_file.m
new file mode 100644
index 00000000..9c556556
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/learning/mk_tetrad_data_file.m
@@ -0,0 +1,25 @@
+function mk_tetrad_data_file(filename, samples, sig)
+% MK_TETRAD_DATA_FILE Make a file containing raw discrete data for input to TETRAD
+% mk_tetrad_data_file(filename, samples, sig)
+%
+% samples(i,j) is the value for case i, variable j
+% The resulting file can be used for the 'build' part of Tetrad.
+% For details on tetrad, see hss.cmu.edu/html/departments/philosophy/TETRAD/tetrad.html
+
+[nsamples N] = size(samples);
+
+fid = fopen(filename, 'w');
+fprintf(fid, '/Raw\n');
+fprintf(fid, '%d\n', nsamples);
+for i=1:N
+  fprintf(fid, 'x%d ', i);
+end
+fprintf(fid, '\n');
+for i=1:nsamples
+  fprintf(fid, '%d ', samples(i,:)-1); % tetrad counts from 0
+  fprintf(fid, '\n');
+end
+%fprintf(fid, '/Knowledge\n');
+%fprintf(fid, 'Significance %4.2f\n', sig);
+fclose(fid);
+