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, 35 insertions, 0 deletions

diff --git a/sourcecodes/bnt-master/SLP/misc/histc_ic.m b/sourcecodes/bnt-master/SLP/misc/histc_ic.m
new file mode 100644
index 00000000..3e4a5af5
--- /dev/null
+++ b/sourcecodes/bnt-master/SLP/misc/histc_ic.m
@@ -0,0 +1,35 @@
+function [n,xechan] = histc_ic(x,edges)
+%HISTC_IC  Histogram count 
+%
+%   [N XECHAN] = HISTC_IC(X,EDGES), for vector X, counts the number of values
+%   in X that fall between the elements in the EDGES vector 
+%   (EDGES = cell array returned by HIST_IC function)
+%
+%   N is cell array containing these counts.
+%    (or a vector if X is a column vector)
+%
+%   XECHAN = discretized version of X
+%
+%   Example :
+%	X=randn(100,5);
+%	Xapp=X(1:50,:);
+%	Xtest=X(51:100,:);
+%
+%       % bins are computed with Xapp data
+%	[n1,bornes,nbbornes,xechan]=hist_ic(Xapp);
+%       % histogram is computed on Xtest data, with previously obtained bins
+%	[n2,xtechan]=histc_ic(Xtest,bornes);
+%
+%   05-06-2001 by Ph. Leray - philippe.leray@univ-nantes.fr
+%
+
+[nb_l,nb_c]=size(x);
+% Outputs declaration
+xechan=zeros(nb_l,nb_c);
+if nb_c==1, edges={edges}; end
+% edges=mat2cell(edges); modified by francois.olivier.c.h@gmail.com
+for j=1:nb_c,
+  [n{j} xechan(:,j)]=histc(x(:,j),[-inf edges{j} inf]);
+  n{j}=n{j}(1:end-1);
+end
+if nb_c==1, n=n{1}; end