/*
  Peter L's Wine example

  * [+,-,*,/,if_less_equal,pow2,pow3,sqrt,log,exp] num_gens=1800 stop_criteria=generations
  gen = 293  (time: 13.719s)
  results_best = [[167.743504502318928,if_less_equal(pris,log(prisvarde * 47),-3 * 29,log(prisvarde * pow3(pris)))]]


  gen = 1766  (time: 76.484s)
  results_best = [[127.769664904533983,log(pow2(pris)) + prisvarde / 29 * 47]]



  Cf pererl_vin.conf

*/
import util.
data(p4,Data,Vars,Unknown,Ops,Constants,MaxSize,Params) :-
  Data =  [ [[A,B],X] : [A,B,X] in chunks_of([
% pris prisvarde betyg
82,4.6,15.5,
82,4.6,15.5,
60,4.4,13.5,
68,4.4,14.5,
72,4.4,14.5,
92,4.4,16,
69,4.2,14,
86,4.2,15.5,
89,4.2,15.5,
75,4,14.5,
99,4,15.5,
56,3.8,12.5,
76,3.8,14,
90,3.8,15,
90,3.8,15,
92,3.8,15,
208,3.8,17.5,
51,3.6,11.5,
64,3.6,13,
79,3.6,14,
86,3.6,15,
89,3.6,15,
111,3.4,15.5,
65,3.4,13,
68,3.4,13,
76,3.4,13.5,
79,3.4,14,
109,3.2,15,
56,3,11.5,
62,3,12,
67,3,12.5,
79,3,13.5,
87,3,14,
89,3,14,
94,3,14.5,
26,2.8,12,
70,2.6,12.5,
82,2.6,13,
59,2.4,11,
105,2.2,13.5,
87,1,8.5,
110,4.4,16.5,
84,4.4,15.5,
71,4,14,
116,4,16,
79,3.8,14.5,
90,3.8,15,
142,3.8,16.5,
77,4.4,15,
99,4.4,16,
99,4.4,16,
168,4.4,17.5,
88,4.2,15,
107,4.2,16,
103,4.2,16,
69,2.8,12.5,
419,4,18.5,
318,3.6,17.5,
59,2.6,11.5,
219,4.6,18.5,
337,4,18.5,
261,3.2,17,
329,3.4,18,
109,4.2,16,
395,4.6,19.5,
199,2.2,15.5,
359,2.4,17,
159,3,16,
119,1,10,
239,2,15.5,
99,2.4,13.5,
285,2.6,17,
89,1.8,12,
432,3,17.5,
67,3,12.5,
79,1.6,11.5,
165,3,16,
82,3.6,14.5,
54,4,12,
89,2.8,14,
58,4,13,
87,2.4,13,
70,3.8,14,
102,3.8,15.5,
110,4.6,16.5,
109,4.4,16,
1400,4.2,20,
990,4,19.5,
295,4.2,18,
195,4.2,17.5,
174,4.4,17.5,
249,4.2,18,
196,4.6,13,
179,1.2,13.5,
85,1.2,11.5,
159,1.6,14,
59,2.2,10.5,
73,3.4,13.5,
58,3.4,12,
383,2.4,17,
199,2.6,16,
106,4.4,16.5,
72,4.4,14.5,
87,4.4,15.5,
111,4.8,17,
77,4.6,15.5,
96,2,13,
229,3.2,17,
119,3.6,16,
175,1.4,14,
261,1.8,15,
289,4,18,
99,4,15.5,
61,4,13,
98,4,15,
469,3.8,18.5,
399,3.2,18,
241,3.6,17.5,
82,1.2,11,
159,1.4,13,
54,1.4,9.5,
119,2,14,
79,2,12,
99,2.2,13.5,
174,2.2,15,
299,2.6,17,
79,3.2,13.5,
598,3.8,18.8,
2750,4,19.8,
49,4,12,
59,4,13,
148,3,15.5,
63,3.8,13,
99,4,15.5,
47,3.8,11.5,
199,3.6,17,
125,4.2,16.5,
89,2,12.5,
139,3.4,16,
79,4,14.5,
90,3.2,14.5,
52,1.4,8.5,
395,1.8,16.5,
339,2,16,
69,3.8,13.5,
329,1.6,15.5,
405,3.6,18.5,
339,4.6,18.5,
82,4.2,14.5,
249,4,17,
49,2.8,10.5,
59,2.8,11.5,
1190,2.2,18,
295,2,15.5,
159,3.6,16.5,
48,1.2,8.5,
53,3.4,11.5,
77,4.6,15,
79,4.6,15.5,
67,5,15,
71,1.8,11,
159,2.2,15,
64,1,9.5,
96,1.4,12.5,
82,1.2,11  
  ],3)],
  Unknown = [82,4.6],  % Should be 15.5
  Vars = ['pris','prisvarde'],
  Ops = [+,-,*,/,if_less_equal,pow2,pow3,pow4,sqrt,log,exp],
  Constants = [random(-100,100) : _ in 1..10],
  MaxSize = 11,
  Params = new_map([% approx=1,
                    init_size=100,
                    show_best=1,
                    crossover_rate=0.5,
                    mutation_rate=0.5,
                    num_gens=1800,
                    show_only_improvements=true,
                    stop_criteria=generations,
                    % debug=true,
                    remove_dups=true
                   ]).