Merge pull request #1 from ziejd2/octave_php_separate

Octave php separate

13 files changed, 431 insertions, 0 deletions

diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/BIC_score_CPD.m b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/BIC_score_CPD.m
new file mode 100644
index 00000000..ab4ef6cf
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/BIC_score_CPD.m
@@ -0,0 +1,17 @@
+function score = BIC_score_CPD(CPD, fam, data, ns, cnodes)
+% BIC_score_CPD Compute the BIC score of a tabular CPD
+% score = BIC_score_CPD(CPD, fam, data, ns, cnodes)
+
+if iscell(data)
+  local_data = cell2num(data(fam,:));
+else
+  local_data = data(fam, :);
+end
+counts = compute_counts(local_data, CPD.sizes);
+CPT = mk_stochastic(counts); % MLE
+tiny = exp(-700); 
+CPT = CPT + (CPT==0)*tiny;  % replace 0s by tiny
+LL = sum(log(CPT(:)) .* counts(:));
+N = size(data, 2);
+score = LL - 0.5*CPD.nparams*log(N);
+
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/CVS/Entries b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/CVS/Entries
new file mode 100644
index 00000000..cbddfaa9
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/CVS/Entries
@@ -0,0 +1,11 @@
+/BIC_score_CPD.m/1.1.1.1/Wed May 29 15:59:54 2002//
+/bayesian_score_CPD.m/1.1.1.1/Wed May 29 15:59:54 2002//
+/log_marg_prob_node_case.m/1.1.1.1/Wed May 29 15:59:54 2002//
+/mult_CPD_and_pi_msgs.m/1.1.1.1/Wed May 29 15:59:54 2002//
+/prob_CPT.m/1.1.1.1/Wed May 29 15:59:54 2002//
+/prob_node.m/1.1.1.1/Wed May 29 15:59:54 2002//
+/sample_node.m/1.1.1.1/Wed May 29 15:59:54 2002//
+/sample_node_single_case.m/1.1.1.1/Wed May 29 15:59:54 2002//
+/tabular_CPD.m/1.1.1.1/Wed May 29 15:59:54 2002//
+/update_params.m/1.1.1.1/Wed May 29 15:59:54 2002//
+D
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/CVS/Repository b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/CVS/Repository
new file mode 100644
index 00000000..b43e738b
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/CVS/Repository
@@ -0,0 +1 @@
+FullBNT/BNT/CPDs/@tabular_CPD/Old
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/CVS/Root b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/CVS/Root
new file mode 100644
index 00000000..f3bd14a6
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/CVS/Root
@@ -0,0 +1 @@
+:ext:nsaunier@bnt.cvs.sourceforge.net:/cvsroot/bnt
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/bayesian_score_CPD.m b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/bayesian_score_CPD.m
new file mode 100644
index 00000000..083a00d7
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/bayesian_score_CPD.m
@@ -0,0 +1,13 @@
+function score = bayesian_score_CPD(CPD, local_ev)
+% bayesian_score_CPD Compute the Bayesian score of a tabular CPD using uniform Dirichlet prior
+% score = bayesian_score_CPD(CPD, local_ev)
+%
+% The Bayesian score is the log marginal likelihood
+
+if iscell(local_ev)
+ data = num2cell(local_ev);
+else
+ data =	local_ev;
+end
+
+score = dirichlet_score_family(compute_counts(data, CPD.sizes));
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/log_marg_prob_node_case.m b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/log_marg_prob_node_case.m
new file mode 100644
index 00000000..2a177fe6
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/log_marg_prob_node_case.m
@@ -0,0 +1,22 @@
+function L = log_marg_prob_node_case(CPD, y, x)
+% LOG_MARG_PROB_NODE_CASE Compute prod_m log P(x(i,m)| x(pi_i,m)) for node i (tabular)
+% L = log_marg_prob_node_case(CPD, self_ev, parent_ev)
+% 
+% This is a slightly optimised version of log_marg_prob_node.
+% We assume we have exactly 1 case, i.e., y is a scalar and x is a vector (not a cell array).
+
+sz = CPD.sizes;
+nparents = length(sz)-1;
+
+% We assume the CPTs are already set to the mean of the posterior (due to update_params)
+
+switch nparents
+ case 0, p = CPD.CPT(y);
+ case 1, p = CPD.CPT(x(1), y);
+ case 2, p = CPD.CPT(x(1), x(2), y);
+ case 3, p = CPD.CPT(x(1), x(2), x(3), y);
+ otherwise,
+  ind = subv2ind(sz, [x y]);
+  p = CPD.CPT(ind);
+end
+L = log(p);
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/mult_CPD_and_pi_msgs.m b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/mult_CPD_and_pi_msgs.m
new file mode 100644
index 00000000..b67ed2e6
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/mult_CPD_and_pi_msgs.m
@@ -0,0 +1,17 @@
+function T = mult_CPD_and_pi_msgs(CPD, n, ps, msgs, except)
+% MULT_CPD_AND_PI_MSGS Multiply the CPD and all the pi messages from parents, perhaps excepting one
+% T = mult_CPD_and_pi_msgs(CPD, n, ps, msgs, except)
+
+if nargin < 5, except = -1; end
+
+dom = [ps n];
+%ns = sparse(1, max(dom));
+ns = zeros(1, max(dom));
+ns(dom) = mysize(CPD.CPT);
+T = dpot(dom, ns(dom), CPD.CPT);
+for i=1:length(ps)
+  p = ps(i);
+  if p ~= except
+    T = multiply_by_pot(T, dpot(p, ns(p), msgs{n}.pi_from_parent{i}.T)); 
+  end
+end         
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/prob_CPT.m b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/prob_CPT.m
new file mode 100644
index 00000000..6685de30
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/prob_CPT.m
@@ -0,0 +1,16 @@
+function p = prob_CPT(CPD, x)
+% PROB_CPT Lookup the prob. of a family value in a tabular CPD
+% p = prob_CPT(CPD, x)
+%
+% This is a version of prob_CPD optimized for tables.
+
+switch length(x)
+ case 1, p = CPD.CPT(x);
+ case 2, p = CPD.CPT(x(1), x(2));
+ case 3, p = CPD.CPT(x(1), x(2), x(3));
+ case 4, p = CPD.CPT(x(1), x(2), x(3), x(4));
+ otherwise,
+  ind = subv2ind(mysize(CPD.CPT), x);
+  p = CPD.CPT(ind);
+end
+
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/prob_node.m b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/prob_node.m
new file mode 100644
index 00000000..2764e6c1
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/prob_node.m
@@ -0,0 +1,40 @@
+function p = prob_node(CPD, self_ev, pev)
+% PROB_NODE Compute P(y|pa(y), theta) (tabular)
+% p = prob_node(CPD, self_ev, pev)
+%
+% self_ev{m} is the evidence on this node in case m
+% pev{i,m} is the evidence on the i'th parent in case m
+% If there is a single case, self_ev can be a scalar instead of a cell array
+
+ncases = size(pev, 2);
+
+%assert(~any(isemptycell(pev))); % slow
+%assert(~any(isemptycell(self_ev))); % slow
+
+CPT = CPD_to_CPT(CPD);  
+sz = mysize(CPT);
+nparents = length(sz)-1;
+assert(nparents == size(pev, 1));
+
+if ncases==1 
+  x = cat(1, pev{:});
+  if iscell(y)
+    y = self_ev{1};
+  else
+    y = self_ev;
+  end
+  switch nparents
+   case 0, p = CPT(y);
+   case 1, p = CPT(x(1), y);
+   case 2, p = CPT(x(1), x(2), y);
+   case 3, p = CPT(x(1), x(2), x(3), y);
+   otherwise,
+    ind = subv2ind(CPD.sizes, [x y]);
+    p = CPT(ind);
+  end
+else
+  x = num2cell(pev)'; % each row is a case
+  y = cat(1, self_ev{:})';
+  ind = subv2ind(CPD.sizes, [x y]);
+  p = CPT(ind);
+end     
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/sample_node.m b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/sample_node.m
new file mode 100644
index 00000000..3fd92d79
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/sample_node.m
@@ -0,0 +1,53 @@
+function y = sample_node(CPD, pev, nsamples)
+% SAMPLE_NODE Draw a random sample from P(Xi | x(pi_i), theta_i)  (tabular)
+% Y = SAMPLE_NODE(CPD, PEV, NSAMPLES)
+%
+% pev(i,m) is the value of the i'th parent in sample m (if there are any parents).
+% y(m) is the m'th sampled value (a row vector).
+% (If pev is a cell array, so is y.)
+% nsamples defaults to 1.
+
+if nargin < 3, nsamples = 1; end
+
+%if nargin < 4, usecell = 0; end
+if iscell(pev), usecell = 1; else usecell = 0; end
+
+if nsamples == 1, pev = pev(:); end
+
+sz = CPD.sizes; 
+nparents = length(sz)-1;
+if nparents==0
+  y = sample_discrete(CPD.CPT, 1, nsamples);
+  if usecell
+    y = num2cell(y);
+  end
+  return;
+end
+
+sz = CPD.sizes; 
+[nparents nsamples] = size(pev);
+
+if usecell
+  pvals = cell2num(pev)'; % each row is a case
+else
+  pvals = pev';
+end
+
+psz = sz(1:end-1);
+ssz = sz(end);
+ndx = subv2ind(psz, pvals);
+T = reshape(CPD.CPT, [prod(psz) ssz]);
+T2 = T(ndx,:); % each row is a distribution selected by the parents
+C = cumsum(T2, 2); % sum across columns
+R = rand(nsamples, 1);
+y = ones(nsamples, 1);
+for i=1:ssz-1
+  y = y + (R > C(:,i));
+end
+y = y(:)';
+if usecell
+  y = num2cell(y);
+end
+
+
+
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/sample_node_single_case.m b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/sample_node_single_case.m
new file mode 100644
index 00000000..3e1dcf34
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/sample_node_single_case.m
@@ -0,0 +1,39 @@
+function y = sample_node(CPD, pev)
+% SAMPLE_NODE Draw a random sample from P(Xi | x(pi_i), theta_i)  (tabular)
+% y = sample_node(CPD, pev)
+%
+% pev{i} is the value of the i'th parent (if any)
+
+%assert(~any(isemptycell(pev)));
+
+%CPT = CPD_to_CPT(CPD);
+%sz = mysize(CPT);
+sz = CPD.sizes; 
+nparents = length(sz)-1;
+if nparents > 0
+  pvals = cat(1, pev{:});
+end
+switch nparents
+ case 0, T = CPD.CPT;
+ case 1, T = CPD.CPT(pvals(1), :);
+ case 2, T = CPD.CPT(pvals(1), pvals(2), :);
+ case 3, T = CPD.CPT(pvals(1), pvals(2), pvals(3), :);
+ case 4, T = CPD.CPT(pvals(1), pvals(2), pvals(3), pvals(4), :);
+ otherwise,
+  psz = sz(1:end-1);
+  ssz = sz(end);
+  i = subv2ind(psz, pvals(:)');
+  T = reshape(CPD.CPT, [prod(psz) ssz]);
+  T = T(i,:);
+end
+
+if sz(end)==2
+  r = rand(1,1);
+  if r > T(1)
+    y = 2;
+  else
+    y = 1;
+  end
+else
+  y = sample_discrete(T);
+end
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/tabular_CPD.m b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/tabular_CPD.m
new file mode 100644
index 00000000..2227e051
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/tabular_CPD.m
@@ -0,0 +1,186 @@
+function CPD = tabular_CPD(bnet, self, varargin)
+% TABULAR_CPD Make a multinomial conditional prob. distrib. (CPT)
+%
+% CPD = tabular_CPD(bnet, node) creates a random CPT.
+%
+% The following arguments can be specified [default in brackets]
+%
+% CPT - specifies the params ['rnd']
+%   - T means use table T; it will be reshaped to the size of node's family.
+%   - 'rnd' creates rnd params (drawn from uniform)
+%   - 'unif' creates a uniform distribution
+%   - 'leftright' only transitions from i to i/i+1 are allowed, for each non-self parent context.
+%       The non-self parents are all parents except oldself.
+% selfprob - The prob of transition from i to i if CPT = 'leftright' [0.1]
+% old_self - id of the node corresponding to self in the previous slice [self-ss]
+% adjustable - 0 means don't adjust the parameters during learning [1]
+% prior_type - defines type of prior ['none']
+%  - 'none' means do ML estimation
+%  - 'dirichlet' means add pseudo-counts to every cell
+%  - 'entropic' means use a prior P(theta) propto exp(-H(theta)) (see Brand)
+% dirichlet_weight - equivalent sample size (ess) of the dirichlet prior [1]
+% dirichlet_type - defines the type of Dirichlet prior ['BDeu']
+%  - 'unif' means put dirichlet_weight in every cell
+%  - 'BDeu' means we put 'dirichlet_weight/(r q)' in every cell
+%    where r = self_sz and q = prod(parent_sz) (see Heckerman)
+% trim - 1 means trim redundant params (rows in CPT) when using entropic prior [0]
+%
+% e.g., tabular_CPD(bnet, i, 'CPT', T)
+% e.g., tabular_CPD(bnet, i, 'CPT', 'unif', 'dirichlet_weight', 2, 'dirichlet_type', 'unif')
+%
+% REFERENCES
+% M. Brand - "Structure learning in conditional probability models via an entropic  prior
+%   and parameter extinction", Neural Computation 11 (1999): 1155--1182
+% M. Brand - "Pattern discovery via entropy minimization" [covers annealing]
+%   AI & Statistics 1999. Equation numbers refer to this paper, which is available from
+%   www.merl.com/reports/docs/TR98-21.pdf
+% D. Heckerman, D. Geiger and M. Chickering, 
+%   "Learning Bayesian networks: the combination of knowledge and statistical data",
+%   Microsoft Research Tech Report, 1994
+
+
+if nargin==0
+  % This occurs if we are trying to load an object from a file.
+  CPD = init_fields;
+  CPD = class(CPD, 'tabular_CPD', discrete_CPD(0, []));
+  return;
+elseif isa(bnet, 'tabular_CPD')
+  % This might occur if we are copying an object.
+  CPD = bnet;
+  return;
+end
+CPD = init_fields;
+
+ns = bnet.node_sizes;
+ps = parents(bnet.dag, self);
+fam_sz = ns([ps self]);
+CPD.sizes = fam_sz;
+CPD.leftright = 0;
+
+% set defaults
+CPD.CPT = mk_stochastic(myrand(fam_sz));
+CPD.adjustable = 1;
+CPD.prior_type = 'none';
+dirichlet_type = 'BDeu';
+dirichlet_weight = 1;
+CPD.trim = 0;
+selfprob = 0.1;
+
+% extract optional args
+args = varargin;
+% check for old syntax CPD(bnet, i, CPT) as opposed to CPD(bnet, i, 'CPT', CPT)
+if ~isempty(args) && ~ischar(args{1})
+  CPD.CPT = myreshape(args{1}, fam_sz);
+  args = [];
+end
+
+% if old_self is specified, read in the value before CPT is created
+old_self = []; 
+for i=1:2:length(args)
+  switch args{i},
+   case 'old_self', old_self = args{i+1};
+  end
+end
+
+for i=1:2:length(args)
+  switch args{i},
+   case 'CPT',
+    T = args{i+1};
+    if ischar(T)
+      switch T
+       case 'unif', CPD.CPT = mk_stochastic(myones(fam_sz));
+       case 'rnd',  CPD.CPT = mk_stochastic(myrand(fam_sz));
+       case 'leftright', 
+	% we just initialise the CPT to leftright - this structure will
+	% be maintained by EM, assuming we don't use a prior...
+	CPD.leftright = 1;
+	if isempty(old_self) % we assume the network is a DBN
+	  ss = bnet.nnodes_per_slice;
+	  old_self = self-ss;
+	end
+	other_ps = mysetdiff(ps, old_self);
+	Qps = prod(ns(other_ps));
+	Q = ns(self);
+	p = selfprob;
+	LR = mk_leftright_transmat(Q, p);
+	transprob = repmat(reshape(LR, [1 Q Q]), [Qps 1 1]); % transprob(k,i,j)
+	transprob = permute(transprob, [2 1 3]); % now transprob(i,k,j)
+	CPD.CPT = myreshape(transprob, fam_sz);
+       otherwise,   error(['invalid CPT ' T]);       
+      end
+    else
+      CPD.CPT = myreshape(T, fam_sz);
+    end
+    
+   case 'prior_type', CPD.prior_type = args{i+1};
+   case 'dirichlet_type', dirichlet_type = args{i+1};
+   case 'dirichlet_weight', dirichlet_weight = args{i+1};
+   case 'adjustable', CPD.adjustable = args{i+1};
+   case 'clamped', CPD.adjustable = ~args{i+1};
+   case 'trim', CPD.trim = args{i+1};
+   case 'old_self', noop = 1; % already read in
+   otherwise, error(['invalid argument name: ' args{i}]);       
+  end
+end
+
+switch CPD.prior_type
+ case 'dirichlet',
+  switch dirichlet_type
+   case 'unif', CPD.dirichlet = dirichlet_weight * myones(fam_sz);
+   case 'BDeu',  CPD.dirichlet = dirichlet_weight * mk_stochastic(myones(fam_sz));
+   otherwise, error(['invalid dirichlet_type ' dirichlet_type])
+  end
+ case {'entropic', 'none'}
+  CPD.dirichlet = [];
+ otherwise, error(['invalid prior_type ' prior_type])
+end
+
+  
+
+% fields to do with learning
+if ~CPD.adjustable
+  CPD.counts = [];
+  CPD.nparams = 0;
+  CPD.nsamples = [];
+else
+  CPD.counts = zeros(size(CPD.CPT));
+  psz = fam_sz(1:end-1);
+  ss = fam_sz(end);
+  if CPD.leftright
+    % For each of the Qps contexts, we specify Q elements on the diagoanl
+    CPD.nparams = Qps * Q;
+  else
+    % sum-to-1 constraint reduces the effective arity of the node by 1
+    CPD.nparams = prod([psz ss-1]);
+  end
+  CPD.nsamples = 0;
+end
+
+fam_sz = CPD.sizes;
+psz = prod(fam_sz(1:end-1));
+ssz = fam_sz(end);
+CPD.trimmed_trans = zeros(psz, ssz); % must declare before reading
+
+CPD = class(CPD, 'tabular_CPD', discrete_CPD(~CPD.adjustable, fam_sz));
+
+
+%%%%%%%%%%%
+
+function CPD = init_fields()
+% This ensures we define the fields in the same order 
+% no matter whether we load an object from a file,
+% or create it from scratch. (Matlab requires this.)
+
+CPD.CPT = [];
+CPD.sizes = [];
+CPD.prior_type = [];
+CPD.dirichlet = [];
+CPD.adjustable = [];
+CPD.counts = [];
+CPD.nparams = [];
+CPD.nsamples = [];
+CPD.trim = [];
+CPD.trimmed_trans = [];
+CPD.leftright = [];
+
+
diff --git a/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/update_params.m b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/update_params.m
new file mode 100644
index 00000000..5a1e93a8
--- /dev/null
+++ b/sourcecodes/bnt-master/BNT/CPDs/@tabular_CPD/Old/update_params.m
@@ -0,0 +1,15 @@
+function CPD = update_params(CPD, ev, counts)
+% UPDATE_PARAMS Update the Dirichlet pseudo counts and compute the new MAP param estimates (tabular)
+%
+% CPD = update_params(CPD, ev) uses the evidence on the family from a single case.
+%
+% CPD = update_params(CPD, [], counts) does a batch update using the specified suff. stats.
+
+if nargin < 3
+  n = length(ev);
+  data = cat(1, ev{:}); % convert to a vector of scalars
+  counts = compute_counts(data(:)', 1:n, mysize(CPD.CPT));
+end
+  
+CPD.prior = CPD.prior + counts;
+CPD.CPT = mk_stochastic(CPD.prior);