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, 27 insertions, 0 deletions

diff --git a/sourcecodes/bnt-master/graph/mk_rnd_dag.m b/sourcecodes/bnt-master/graph/mk_rnd_dag.m
new file mode 100644
index 00000000..4bf59c34
--- /dev/null
+++ b/sourcecodes/bnt-master/graph/mk_rnd_dag.m
@@ -0,0 +1,27 @@
+function [dag, order] = mk_rnd_dag(N, max_fan_in)
+% MY_MK_RND_DAG  Create a random directed acyclic graph
+%
+% [dag, order] = my_mk_rnd_dag(N, max_fan_in)
+%  max_fan_in defaults to N.
+%  order is the random topological order that was chosen
+
+% Modified by Sonia Leach 2/25/02
+
+if nargin < 2, max_fan_in = N; end
+
+order = randperm(N);
+dag = zeros(N,N);
+for i=2:N
+  j = order(i);
+  %k = sample_discrete(normalise(ones(1, min(i-1, max_fan_in))));
+  k = sample_discrete(normalise(ones(1, min(i-1, max_fan_in)+1))) - 1; % min = 0 (bug fix due to
+                                                                       % Pedrito, 7/28/04)
+  SS = order(1:i-1);          % get Set of possible parentS
+  p  = randperm(length(SS));  % permute order of set
+  dag(SS(p(1:k)),j) = 1;      % take first k in permuted order
+
+  % Kevin had:
+  %SS = subsets(order(1:i-1), k, k);
+  %p = sample_discrete(normalise(ones(1, length(SS))));
+  %dag(SS{p}, j) = 1;
+end