| [1190] | 1 | from ..base.experiment_niching_abc import ExperimentNiching |
|---|
| 2 | from ..structures.individual import Individual |
|---|
| 3 | from ..structures.population import PopulationStructures |
|---|
| 4 | from ..utils import merge_two_parsers |
|---|
| 5 | from .experiment_frams import ExperimentFrams |
|---|
| 6 | |
|---|
| 7 | |
|---|
| 8 | class ExperimentFramsNiching(ExperimentFrams, ExperimentNiching): |
|---|
| [1308] | 9 | def __init__(self, frams_lib, optimization_criteria, hof_size, popsize, constraints, normalize, dissim, fit, genformat, archive_size, save_only_best, knn_niching, knn_nslc, crowding_dissim=None) -> None: |
|---|
| [1190] | 10 | ExperimentFrams.__init__(self, hof_size=hof_size, |
|---|
| 11 | popsize=popsize, |
|---|
| 12 | frams_lib=frams_lib, |
|---|
| 13 | constraints=constraints, |
|---|
| 14 | optimization_criteria=optimization_criteria, |
|---|
| 15 | genformat=genformat, |
|---|
| 16 | save_only_best=save_only_best |
|---|
| 17 | ) |
|---|
| 18 | ExperimentNiching.__init__(self, hof_size=hof_size, |
|---|
| 19 | popsize=popsize, |
|---|
| 20 | fit=fit, |
|---|
| 21 | normalize=normalize, |
|---|
| 22 | save_only_best=save_only_best, |
|---|
| [1270] | 23 | archive_size=archive_size, |
|---|
| 24 | knn_niching=knn_niching, |
|---|
| [1308] | 25 | knn_nslc=knn_nslc, |
|---|
| 26 | crowding_dissim=crowding_dissim |
|---|
| [1190] | 27 | ) |
|---|
| 28 | self.dissim = dissim |
|---|
| 29 | |
|---|
| 30 | |
|---|
| 31 | def initialize_evolution(self, genformat, initialgenotype): |
|---|
| 32 | self.current_generation = 0 |
|---|
| 33 | self.time_elapsed = 0 |
|---|
| 34 | self.stats = [] # stores the best individuals, one from each generation |
|---|
| 35 | initial_individual = Individual() |
|---|
| 36 | initial_individual.set_and_evaluate(self.frams_getsimplest( |
|---|
| 37 | '1' if genformat is None else genformat, initialgenotype), self.evaluate) |
|---|
| 38 | self.hof.add(initial_individual) |
|---|
| 39 | self.stats.append( |
|---|
| 40 | initial_individual.rawfitness if self.save_only_best else initial_individual) |
|---|
| 41 | self.population_structures = PopulationStructures( |
|---|
| 42 | initial_individual=initial_individual, archive_size=self.archive_size, popsize=self.popsize) |
|---|
| 43 | if self.fit == "nsga2": |
|---|
| 44 | self.do_nsga2_dissim(self.population_structures.population) |
|---|
| 45 | if self.fit == "nslc": |
|---|
| [1304] | 46 | self.do_nslc_dissim(self.population_structures, self.population_structures.population) |
|---|
| [1190] | 47 | |
|---|
| 48 | def dissimilarity(self, population): |
|---|
| 49 | return self.frams_lib.dissimilarity([i.genotype for i in population], self.dissim) |
|---|
| [1308] | 50 | |
|---|
| 51 | def crowding_distance_dissimilarity(self, population): |
|---|
| 52 | return self.frams_lib.dissimilarity([i.genotype for i in population], self.crowding_dissim) |
|---|
| [1190] | 53 | |
|---|
| 54 | |
|---|
| 55 | @staticmethod |
|---|
| 56 | def get_args_for_parser(): |
|---|
| 57 | p1 = ExperimentFrams.get_args_for_parser() |
|---|
| 58 | p2 = ExperimentNiching.get_args_for_parser() |
|---|
| 59 | return merge_two_parsers(p1, p2) |
|---|
| 60 | |
|---|
