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, 22 insertions, 0 deletions

diff --git a/sourcecodes/bnt-master/HMM/dhmm_logprob.m b/sourcecodes/bnt-master/HMM/dhmm_logprob.m
new file mode 100644
index 00000000..f8afe835
--- /dev/null
+++ b/sourcecodes/bnt-master/HMM/dhmm_logprob.m
@@ -0,0 +1,22 @@
+function [loglik, errors] = dhmm_logprob(data, prior, transmat, obsmat)
+% LOG_LIK_DHMM Compute the log-likelihood of a dataset using a discrete HMM
+% [loglik, errors] = log_lik_dhmm(data, prior, transmat, obsmat)
+%
+% data{m} or data(m,:) is the m'th sequence
+% errors  is a list of the cases which received a loglik of -infinity
+
+if ~iscell(data)
+  data = num2cell(data, 2);
+end
+ncases = length(data);
+
+loglik = 0;
+errors = [];
+for m=1:ncases
+  obslik = multinomial_prob(data{m}, obsmat);
+  [alpha, beta, gamma, ll] = fwdback(prior, transmat, obslik, 'fwd_only', 1);
+  if ll==-inf
+    errors = [errors m];
+  end
+  loglik = loglik + ll;
+end