/* 

  Reasoning in Belief Networks in Picat v3.

  This is a port of the belief networks program from
  I. Bratko, "Prolog Programming for Artificial Intelligence", 4th edn.,
  Pearson Education / Addison-Wesley 2012
  Page 378ff (Figure 16.4 and 16.5)
       


  This Picat model was created by Hakan Kjellerstrand, hakank@gmail.com
  See also my Picat page: http://www.hakank.org/picat/

*/

import belief_network_v3.

main => go.


go ?=>
  L = [
     [burglary,[call]],
     [burglary,[call,lightning]],
     [burglary,[call,not lightning]],
     [burglary,[burglary,lightning]]
  ],
  foreach(T in L)
    println(T),
    prob(T[1],T[2],P), % page 380
    println(p=P),
    nl
  end,
  nl. 

go => true.


% Example

% Figure 16.5  A specification of the belief network of Fig. 15.10 as 
% expected by the program of Fig. 15.11.


% Belief network "sensor"

parent( burglary, sensor).    % Burglary tends to trigger sensor
parent( lightning, sensor).   % Strong lightning may trigger sensor
parent( sensor, alarm).
parent( sensor, call).

p( burglary, 0.001).
p( lightning, 0.02).
p( sensor, [ burglary, lightning], 0.9).
p( sensor, [ burglary, not lightning], 0.9).
p( sensor, [ not burglary, lightning], 0.1).
p( sensor, [ not burglary, not lightning], 0.001).
p( alarm, [ sensor], 0.95).
p( alarm, [ not sensor], 0.001).
p( call, [ sensor], 0.9).
p( call, [ not sensor], 0.0).