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

6 files changed, 123 insertions, 0 deletions

diff --git a/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/CVS/Entries b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/CVS/Entries
new file mode 100644
index 00000000..c9482cbd
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/CVS/Entries
@@ -0,0 +1,4 @@
+/enter_evidence.m/1.1.1.1/Wed May 29 15:59:56 2002//
+/likelihood_weighting_inf_engine.m/1.1.1.1/Wed May 29 15:59:56 2002//
+/marginal_nodes.m/1.1.1.1/Wed May 29 15:59:56 2002//
+D
diff --git a/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/CVS/Repository b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/CVS/Repository
new file mode 100644
index 00000000..e39429d7
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/CVS/Repository
@@ -0,0 +1 @@
+FullBNT/BNT/inference/static/@likelihood_weighting_inf_engine
diff --git a/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/CVS/Root b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/CVS/Root
new file mode 100644
index 00000000..f3bd14a6
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/CVS/Root
@@ -0,0 +1 @@
+:ext:nsaunier@bnt.cvs.sourceforge.net:/cvsroot/bnt
diff --git a/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/enter_evidence.m b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/enter_evidence.m
new file mode 100644
index 00000000..62e252aa
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/enter_evidence.m
@@ -0,0 +1,39 @@
+function [engine, ll] = enter_evidence(engine, evidence, nsamples)
+% ENTER_EVIDENCE Add the specified evidence to the network (likelihood_weighting)
+% [engine, ll] = enter_evidence(engine, evidence, nsamples)
+% evidence{i} = [] if if X(i) is hidden, and otherwise contains its observed value (scalar or column vector)
+%
+% If nsamples is not specified, the value specified when the engine was created will be used.
+% ll (log-likelihood) is set to [].
+
+ll = [];
+if nargin < 3, nsamples = engine.nsamples; end
+
+bnet = bnet_from_engine(engine);
+N = length(bnet.dag);
+samples = cell(nsamples, N);
+weights = zeros(1, nsamples);
+
+ns = bnet.node_sizes;
+original_evidence = evidence;
+observed = ~isemptycell(original_evidence);
+for s=1:nsamples
+  evidence = original_evidence(:); % must be a column vector
+  w = 1;
+  for i=1:N
+    ps = parents(bnet.dag, i);
+    e = bnet.equiv_class(i);
+    if observed(i)
+      p = exp(log_prob_node(bnet.CPD{e}, evidence(i), evidence(ps)));
+      w = w * p;
+    else
+      x = sample_node(bnet.CPD{e}, evidence(ps));
+      evidence{i} = x;
+    end
+  end
+  samples(s,:) = evidence;
+  weights(s) = w;
+end                 
+
+engine.samples = samples;
+engine.weights = weights;
diff --git a/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/likelihood_weighting_inf_engine.m b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/likelihood_weighting_inf_engine.m
new file mode 100644
index 00000000..eb1794fa
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/likelihood_weighting_inf_engine.m
@@ -0,0 +1,25 @@
+function engine = likelihood_weighting_inf_engine(bnet, varargin)
+% LIKELIHOOD_WEIGHTING_INF_ENGINE 
+% engine = likelihood_weighting_inf_engine(bnet, ...)
+%
+% Optional arguments [defaults]
+% nsamples - [500]
+
+nsamples = 500;
+
+if nargin >= 2
+  args = varargin;
+  nargs = length(args);
+  for i=1:2:nargs
+    switch args{i},
+     case 'nsamples', nsamples= args{i+1};
+     otherwise,
+      error(['invalid argument name ' args{i}]);
+    end
+  end
+end   
+
+engine.nsamples = nsamples;
+engine.samples = [];
+engine.weights = [];
+engine = class(engine, 'likelihood_weighting_inf_engine', inf_engine(bnet));
diff --git a/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/marginal_nodes.m b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/marginal_nodes.m
new file mode 100644
index 00000000..d00ee606
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/inference/static/@likelihood_weighting_inf_engine/marginal_nodes.m
@@ -0,0 +1,53 @@
+function marginal = marginal_nodes(engine, nodes)
+% MARGINAL_NODES Compute the marginal on the specified query nodes (likelihood_weighting)
+% marginal = marginal_nodes(engine, nodes)
+
+bnet = bnet_from_engine(engine);
+ddom = myintersect(nodes, bnet.dnodes);
+cdom = myintersect(nodes, bnet.cnodes);
+nsamples = size(engine.samples, 1);
+ns = bnet.node_sizes;
+
+%w = normalise(engine.weights);
+w = engine.weights;
+if mysubset(nodes, ddom)
+  T = 0*myones(ns(nodes));
+  P = prod(ns(nodes));
+  indices = ind2subv(ns(nodes), 1:P);
+  samples = reshape(cat(1, engine.samples{:,nodes}), nsamples, length(nodes));
+  for j = 1:P
+    rows = find_rows(samples, indices(j,:));
+    T(j) = sum(w(rows));
+  end
+  T = normalise(T);
+  marginal.T = T;
+elseif subset(nodes, cdom)
+  samples = reshape(cat(1, engine.samples{:,nodes}), nsamples*sum(ns(nodes)), length(nodes));
+  [marginal.mu, marginal.Sigma] =  wstats(samples', normalise(w));
+else
+  error('can''t handle mixed marginals yet');
+end
+
+marginal.domain = nodes;
+
+%%%%%%%%%
+
+function rows = find_rows(M, v)
+% FINDROWS Find rows which are equal to a specified vector
+% rows = findrows(M, v)
+% Each row of M is a sample
+
+temp = abs(M - repmat(v, size(M, 1), 1));
+rows = find(sum(temp,2) == 0);      
+
+%%%%%%%%
+
+function [mu, Sigma] = wstats(X, w)
+
+% Computes the weighted mean and weighted covariance matrix for a given
+% set of observations X(:,i), and a set of normalised weights w(i).
+% Each column of X is a sample.
+
+d = X - repmat(X * w', 1, size(X, 2));
+mu = sum(X .* repmat(w, size(X, 1), 1), 2);
+Sigma = d * diag(w) * d';