from ttp_loader import ttp_loader
import PoblationalSearch.Operators.crossover as crossover
import PoblationalSearch.Operators.mutation as mutation
import PoblationalSearch.Operators.selection as selection
problem = ttp_loader('TTP/eil51_n50_uncorr_01.ttp')
tsp = {
'ind_size': problem.dimension,
'p_size': 64,
'generations': 0,
'agent': TSPCoAgent,
'selection_op': selection.matting_restriction(hamming_distance, 2),
'mutation_op': mutation.tsp_mutation(mutation.perm_mutation()),
'crossover_op': crossover.perm_crossover(problem.dimension),
'distance': hamming_distance,
'radious': 2
}
W = problem.capacity
item_w = [it[1] for it in problem.items]
kp = {
'ind_size': problem.n_items,
'p_size': 64,
'generations': 0,
'agent': KPCoAgent,
'selection_op': selection.matting_restriction(hamming_distance, 2),
'mutation_op': mutation.kp_mutation(W, item_w, mutation.bin_mutation()),
'crossover_op': crossover.kp_crossover(W, item_w, crossover.simple_crossover()),
'crossover_rate': 0.7,
'crossover_op': crossover.multipoint_crossover(2)
}
#rga = GeneticAlgorithm(**binary_GA).execute()
#print(rga.best_ind[-1])
permutation_GA = {
'function': dummy,
'ind_size': 10,
'p_size': p_size,
'generations': generations,
'agent': PermutationAgent,
'selection_op': selection.elitist_tournament(),
'mutation_op': mutation.flip_mutation(),
'crossover_rate': 0.7,
'crossover_op': crossover.perm_crossover(10)
}
#pga = GeneticAlgorithm(**permutation_GA).execute()
#print(pga.best_ind[-1])
evolution_strategy = {
'function': ackley,
'ind_size': 5,
'p_size': p_size,
'generations': generations,
'selection_op': selection.random_selection(),
'mutation_op': mutation.e_strategy_mutation(),
'recombination_op': crossover.real_crossover(5, 'exogenous'),
'marriage_size': 2,
'agent_args': {
'_min': -32.768,