贝叶斯网络的K2结构学习

贝叶斯网络的K2结构学习 clear N = 4; dag = zeros(N,N); %C = 1; S = 2; R = 3; W = 4; % topological order C = 4; S = 2; R = 3; W = 1; % arbitrary order dag(C,[R S]) = 1; dag(R,W) = 1; dag(S,W)=1; false = 1; true = 2; ns = 2*ones(1,N); % binary nodes bnet = mk_bnet(dag, ns); bnet.CPD{C} = tabular_CPD(bnet, C, 'CPT', [0.5 0.5]); bnet.CPD{R} = tabular_CPD(bnet, R, 'CPT', [0.8 0.2 0.2 0.8]); bnet.CPD{S} = tabular_CPD(bnet, S, 'CPT', [0.5 0.9 0.5 0.1]); bnet.CPD{W} = tabular_CPD(bnet, W, 'CPT', [1 0.1 0.1 0.01 0 0.9 0.9 0.99]); [n ncases] = size(data); % set default params type = cell(1,n); params = cell(1,n); for i=1:n type{i} = 'tabular'; %params{i} = { 'prior', 1 }; params{i} = { 'prior_type', 'dirichlet', 'dirichlet_weight', 1 }; end scoring_fn = 'bayesian'; discrete = 1:n; clamped = zeros(n, ncases); max_fan_in = n; verbose = 0; dag = zeros(n,n); for i=1:n ps = []; j = order(i); u = find(clamped(j,:)==0); score = score_family(j, ps, type{j}, scoring_fn, ns, discrete, data(:,u), params{j}); if verbose, fprintf('\nnode %d, empty score %6.4f\n', j, score), end done = 0; while ~done & (length(ps) score score = best_pscore; ps = [ps best_p]; if verbose, fprintf('* adding %d to %d, score %6.4f\n', best_p, j, best_pscore),end else done = 1; end end if ~isempty(ps) % need this check for matlab 5.2 dag(ps, j) = 1; end end