Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 9422c1a

Browse files
Fix bug when save_best_solution=True
The bug is fixed by creating a copy of the best solution. This is by replacing the next line: ```python best_solution = self.population[best_match_idx, :] ``` By this line: ```python best_solution = self.population[best_match_idx, :].copy() ```
1 parent c7dd751 commit 9422c1a

File tree

1 file changed

+14
-13
lines changed

1 file changed

+14
-13
lines changed

‎pygad.py

Lines changed: 14 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -661,9 +661,9 @@ def initialize_population(self, low, high):
661661
self.gene_space[gene_idx] = numpy.asarray(numpy.random.uniform(low=low,
662662
high=high,
663663
size=1), dtype=self.gene_type)[0]
664-
self.population[sol_idx, gene_idx] = self.gene_space[gene_idx]
664+
self.population[sol_idx, gene_idx] = self.gene_space[gene_idx].copy()
665665
elif type(self.gene_space[gene_idx]) in [int, float, numpy.int, numpy.int8, numpy.int16, numpy.int32, numpy.int64, numpy.uint, numpy.uint8, numpy.uint16, numpy.uint32, numpy.uint64, numpy.float, numpy.float16, numpy.float32, numpy.float64]:
666-
self.population[sol_idx, gene_idx] = self.gene_space[gene_idx]
666+
self.population[sol_idx, gene_idx] = self.gene_space[gene_idx].copy()
667667
else:
668668
# Replace all the None values with random values using the init_range_low, init_range_high, and gene_type attributes.
669669
for idx, curr_gene_space in enumerate(self.gene_space):
@@ -727,6 +727,7 @@ def run(self):
727727
# Appending the best solution to the best_solutions list.
728728
if self.save_best_solutions:
729729
self.best_solutions.append(best_solution)
730+
print("AAAAAAAAA ", self.best_solutions)
730731

731732
# Selecting the best parents in the population for mating.
732733
parents = self.select_parents(fitness, num_parents=self.num_parents_mating)
@@ -809,7 +810,7 @@ def steady_state_selection(self, fitness, num_parents):
809810
# Selecting the best individuals in the current generation as parents for producing the offspring of the next generation.
810811
parents = numpy.empty((num_parents, self.population.shape[1]))
811812
for parent_num in range(num_parents):
812-
parents[parent_num, :] = self.population[fitness_sorted[parent_num], :]
813+
parents[parent_num, :] = self.population[fitness_sorted[parent_num], :].copy()
813814
return parents
814815

815816
def rank_selection(self, fitness, num_parents):
@@ -827,7 +828,7 @@ def rank_selection(self, fitness, num_parents):
827828
# Selecting the best individuals in the current generation as parents for producing the offspring of the next generation.
828829
parents = numpy.empty((num_parents, self.population.shape[1]))
829830
for parent_num in range(num_parents):
830-
parents[parent_num, :] = self.population[fitness_sorted[parent_num], :]
831+
parents[parent_num, :] = self.population[fitness_sorted[parent_num], :].copy()
831832
return parents
832833

833834
def random_selection(self, fitness, num_parents):
@@ -845,7 +846,7 @@ def random_selection(self, fitness, num_parents):
845846
rand_indices = numpy.random.randint(low=0.0, high=fitness.shape[0], size=num_parents)
846847

847848
for parent_num in range(num_parents):
848-
parents[parent_num, :] = self.population[rand_indices[parent_num], :]
849+
parents[parent_num, :] = self.population[rand_indices[parent_num], :].copy()
849850
return parents
850851

851852
def tournament_selection(self, fitness, num_parents):
@@ -863,7 +864,7 @@ def tournament_selection(self, fitness, num_parents):
863864
rand_indices = numpy.random.randint(low=0.0, high=len(fitness), size=self.K_tournament)
864865
K_fitnesses = fitness[rand_indices]
865866
selected_parent_idx = numpy.where(K_fitnesses == numpy.max(K_fitnesses))[0][0]
866-
parents[parent_num, :] = self.population[rand_indices[selected_parent_idx], :]
867+
parents[parent_num, :] = self.population[rand_indices[selected_parent_idx], :].copy()
867868
return parents
868869

869870
def roulette_wheel_selection(self, fitness, num_parents):
@@ -897,7 +898,7 @@ def roulette_wheel_selection(self, fitness, num_parents):
897898
rand_prob = numpy.random.rand()
898899
for idx in range(probs.shape[0]):
899900
if (rand_prob >= probs_start[idx] and rand_prob < probs_end[idx]):
900-
parents[parent_num, :] = self.population[idx, :]
901+
parents[parent_num, :] = self.population[idx, :].copy()
901902
break
902903
return parents
903904

@@ -935,7 +936,7 @@ def stochastic_universal_selection(self, fitness, num_parents):
935936
rand_pointer = first_pointer + parent_num*pointers_distance
936937
for idx in range(probs.shape[0]):
937938
if (rand_pointer >= probs_start[idx] and rand_pointer < probs_end[idx]):
938-
parents[parent_num, :] = self.population[idx, :]
939+
parents[parent_num, :] = self.population[idx, :].copy()
939940
break
940941
return parents
941942

@@ -1161,7 +1162,7 @@ def mutation_by_space(self, offspring):
11611162

11621163
if self.gene_space_nested:
11631164
# Returning the current gene space from the 'gene_space' attribute.
1164-
curr_gene_space = self.gene_space[gene_idx]
1165+
curr_gene_space = self.gene_space[gene_idx].copy()
11651166

11661167
# If the gene space has only a single value, use it as the new gene value.
11671168
if type(curr_gene_space) in [int, float, numpy.int, numpy.int8, numpy.int16, numpy.int32, numpy.int64, numpy.uint, numpy.uint8, numpy.uint16, numpy.uint32, numpy.uint64, numpy.float, numpy.float16, numpy.float32, numpy.float64]:
@@ -1203,7 +1204,7 @@ def mutation_probs_by_space(self, offspring):
12031204
if probs[gene_idx] <= self.mutation_probability:
12041205
if self.gene_space_nested:
12051206
# Returning the current gene space from the 'gene_space' attribute.
1206-
curr_gene_space = self.gene_space[gene_idx]
1207+
curr_gene_space = self.gene_space[gene_idx].copy()
12071208

12081209
# If the gene space has only a single value, use it as the new gene value.
12091210
if type(curr_gene_space) in [int, float, numpy.int, numpy.int8, numpy.int16, numpy.int32, numpy.int64, numpy.uint, numpy.uint8, numpy.uint16, numpy.uint32, numpy.uint64, numpy.float, numpy.float16, numpy.float32, numpy.float64]:
@@ -1422,7 +1423,7 @@ def adaptive_mutation_by_space(self, offspring):
14221423

14231424
if self.gene_space_nested:
14241425
# Returning the current gene space from the 'gene_space' attribute.
1425-
curr_gene_space = self.gene_space[gene_idx]
1426+
curr_gene_space = self.gene_space[gene_idx].copy()
14261427

14271428
# If the gene space has only a single value, use it as the new gene value.
14281429
if type(curr_gene_space) in [int, float, numpy.int, numpy.int8, numpy.int16, numpy.int32, numpy.int64, numpy.uint, numpy.uint8, numpy.uint16, numpy.uint32, numpy.uint64, numpy.float, numpy.float16, numpy.float32, numpy.float64]:
@@ -1510,7 +1511,7 @@ def adaptive_mutation_probs_by_space(self, offspring):
15101511
if probs[gene_idx] <= adaptive_mutation_probability:
15111512
if self.gene_space_nested:
15121513
# Returning the current gene space from the 'gene_space' attribute.
1513-
curr_gene_space = self.gene_space[gene_idx]
1514+
curr_gene_space = self.gene_space[gene_idx].copy()
15141515

15151516
# If the gene space has only a single value, use it as the new gene value.
15161517
if type(curr_gene_space) in [int, float, numpy.int, numpy.int8, numpy.int16, numpy.int32, numpy.int64, numpy.uint, numpy.uint8, numpy.uint16, numpy.uint32, numpy.uint64, numpy.float, numpy.float16, numpy.float32, numpy.float64]:
@@ -1597,7 +1598,7 @@ def best_solution(self, pop_fitness=None):
15971598
# Then return the index of that solution corresponding to the best fitness.
15981599
best_match_idx = numpy.where(pop_fitness == numpy.max(pop_fitness))[0][0]
15991600

1600-
best_solution = self.population[best_match_idx, :]
1601+
best_solution = self.population[best_match_idx, :].copy()
16011602
best_solution_fitness = pop_fitness[best_match_idx]
16021603

16031604
return best_solution, best_solution_fitness, best_match_idx

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /