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, 17 insertions, 0 deletions

diff --git a/sourcecodes/bnt-master/KPMtools/compute_counts.m b/sourcecodes/bnt-master/KPMtools/compute_counts.m
new file mode 100644
index 00000000..d710bfcb
--- /dev/null
+++ b/sourcecodes/bnt-master/KPMtools/compute_counts.m
@@ -0,0 +1,17 @@
+function count = compute_counts(data, sz)
+% COMPUTE_COUNTS Count the number of times each combination of discrete assignments occurs
+% count = compute_counts(data, sz)
+%
+% data(i,t) is the value of variable i in case t
+% sz(i) : values for variable i are assumed to be in [1:sz(i)]
+%
+% Example: to compute a transition matrix for an HMM from a sequence of labeled states:
+% transmat = mk_stochastic(compute_counts([seq(1:end-1); seq(2:end)], [nstates nstates]));
+
+assert(length(sz) == size(data, 1));
+P = prod(sz);
+indices = subv2ind(sz, data'); % each row of data' is a case 
+%count = histc(indices, 1:P);
+count = hist(indices, 1:P);
+count = myreshape(count, sz);
+