|
12 | 12 | desired_output=44# Function output. |
13 | 13 |
|
14 | 14 | deffitness_func(solution,solution_idx): |
15 | | -# Calculating the fitness value of each solution in the current population. |
16 | | -# The fitness function calulates the sum of products between each input and its corresponding weight. |
17 | 15 | output=numpy.sum(solution*function_inputs) |
18 | | -# The value 0.000001 is used to avoid the Inf value when the denominator numpy.abs(output - desired_output) is 0.0. |
19 | 16 | fitness=1.0/ (numpy.abs(output-desired_output)+0.000001) |
20 | 17 | returnfitness |
21 | 18 |
|
22 | | -fitness_function=fitness_func |
23 | | - |
24 | 19 | num_generations=100# Number of generations. |
25 | 20 | num_parents_mating=10# Number of solutions to be selected as parents in the mating pool. |
26 | 21 |
|
27 | | -# To prepare the initial population, there are 2 ways: |
28 | | -# 1) Prepare it yourself and pass it to the initial_population parameter. This way is useful when the user wants to start the genetic algorithm with a custom initial population. |
29 | | -# 2) Assign valid integer values to the sol_per_pop and num_genes parameters. If the initial_population parameter exists, then the sol_per_pop and num_genes parameters are useless. |
30 | 22 | sol_per_pop=20# Number of solutions in the population. |
31 | 23 | num_genes=len(function_inputs) |
32 | 24 |
|
33 | | -parent_selection_type="sss"# Type of parent selection. |
34 | | -keep_parents=-1# Number of parents to keep in the next population. -1 means keep all parents and 0 means keep nothing. |
35 | | - |
36 | | -crossover_type="single_point"# Type of the crossover operator. |
37 | | - |
38 | | -# Parameters of the mutation operation. |
39 | | -mutation_type="random"# Type of the mutation operator. |
40 | | -mutation_percent_genes=10# Percentage of genes to mutate. This parameter has no action if the parameter mutation_num_genes exists or when mutation_type is None. |
41 | | - |
42 | 25 | last_fitness=0 |
43 | | -defcallback_generation(ga_instance): |
| 26 | +defon_generation(ga_instance): |
44 | 27 | globallast_fitness |
45 | 28 | print("Generation = {generation}".format(generation=ga_instance.generations_completed)) |
46 | 29 | print("Fitness = {fitness}".format(fitness=ga_instance.best_solution(pop_fitness=ga_instance.last_generation_fitness)[1])) |
47 | 30 | print("Change = {change}".format(change=ga_instance.best_solution(pop_fitness=ga_instance.last_generation_fitness)[1]-last_fitness)) |
48 | 31 | last_fitness=ga_instance.best_solution(pop_fitness=ga_instance.last_generation_fitness)[1] |
49 | 32 |
|
50 | | -# Creating an instance of the GA class inside the ga module. Some parameters are initialized within the constructor. |
51 | 33 | ga_instance=pygad.GA(num_generations=num_generations, |
52 | 34 | num_parents_mating=num_parents_mating, |
53 | | -fitness_func=fitness_function, |
54 | 35 | sol_per_pop=sol_per_pop, |
55 | 36 | num_genes=num_genes, |
56 | | -parent_selection_type=parent_selection_type, |
57 | | -keep_parents=keep_parents, |
58 | | -crossover_type=crossover_type, |
59 | | -mutation_type=mutation_type, |
60 | | -mutation_percent_genes=mutation_percent_genes, |
61 | | -on_generation=callback_generation) |
| 37 | +fitness_func=fitness_func, |
| 38 | +on_generation=on_generation) |
62 | 39 |
|
63 | 40 | # Running the GA to optimize the parameters of the function. |
64 | 41 | ga_instance.run() |
65 | 42 |
|
66 | | -# After the generations complete, some plots are showed that summarize the how the outputs/fitenss values evolve over generations. |
67 | 43 | ga_instance.plot_result() |
68 | 44 |
|
69 | 45 | # Returning the details of the best solution. |
70 | | -solution,solution_fitness,solution_idx=ga_instance.best_solution() |
| 46 | +solution,solution_fitness,solution_idx=ga_instance.best_solution(ga_instance.last_generation_fitness) |
71 | 47 | print("Parameters of the best solution : {solution}".format(solution=solution)) |
72 | 48 | print("Fitness value of the best solution = {solution_fitness}".format(solution_fitness=solution_fitness)) |
73 | 49 | print("Index of the best solution : {solution_idx}".format(solution_idx=solution_idx)) |
|