Fix parent selection

src/genetic_algorithm.py

@@ -51,7 +51,7 @@ def evaluate_individual(individual, data):
 def select_distinct_genes(matching_genes, parents, m):
     first_parent = parents[0].query("point not in @matching_genes")
     second_parent = parents[1].query("point not in @matching_genes")
-    cutoff = randint(len(first_parent.point.values))
+    cutoff = randint(m - len(matching_genes))
     first_parent_genes = first_parent.point.values[cutoff:]
     second_parent_genes = second_parent.point.values[:cutoff]
     return first_parent_genes, second_parent_genes
@@ -65,18 +65,28 @@ def select_random_genes(matching_genes, parents, m):
     return genes
 
 
+def select_random_parent(parents):
+    random_index = randint(len(parents))
+    random_parent = parents[random_index]
+    if random_parent.point.empty:
+        opposite_index = 1 - random_index
+        random_parent = parents[opposite_index]
+    return random_parent
+
+
 def repair_offspring(offspring, parents, m):
     while len(offspring) != m:
         if len(offspring) > m:
             best_index = offspring["distance"].idxmax()
             offspring.drop(index=best_index, inplace=True)
         elif len(offspring) < m:
-            random_parent = parents[randint(len(parents))]
+            # NOTE Refactor into its own function
             while True:
+                random_parent = select_random_parent(parents)
                 best_index = random_parent["distance"].idxmax()
                 best_point = random_parent["point"].loc[best_index]
                 random_parent.drop(index=best_index, inplace=True)
-                if not any(offspring["point"].isin([best_point])):
+                if best_point not in offspring.point.values:
                     break
             offspring = offspring.append(
                 {"point": best_point, "distance": 0, "fitness": 0}, ignore_index=True
@@ -119,7 +129,7 @@ def position_crossover(parents, m):
 
 
 def crossover(mode, parents, m):
-    split_parents = [parents[i : i + 2] for i in range(0, len(parents), 2)]
+    split_parents = zip(*[iter(parents)] * 2)
     if mode == "uniform":
         crossover_func = partial(uniform_crossover, m=m)
     else:
@@ -140,25 +150,36 @@ def select_new_gene(individual, n):
             return new_gene
 
 
-def mutate(population, n, probability=0.001):
-    expected_mutations = len(population) * n * probability
+def mutate(offspring, data, probability=0.001):
+    expected_mutations = len(offspring) * n * probability
     individuals = []
     genes = []
     for _ in range(ceil(expected_mutations)):
-        individuals.append(randint(n))
+        individuals.append(randint(len(offspring)))
         current_individual = individuals[-1]
-        genes.append(population[current_individual].sample().index)
+        genes.append(offspring[current_individual].sample().index)
     for ind, gen in zip(individuals, genes):
-        individual = population[ind]
+        individual = offspring[ind]
         individual["point"].iloc[gen] = select_new_gene(individual, n)
-        individual["distance"].iloc[gen] = 0
-    return population
+        individual["distance"].iloc[gen] = compute_distance(
+            element=individual["point"].iloc[gen].values[0],
+            individual=individual,
+            data=data,
+        )
+    return offspring
 
 
-def tournament_selection(m, population):
-    individuals = [population[randint(m)] for _ in range(2)]
-    best_index = population.index(max(population, key=lambda x: all(x.fitness)))
-    return individuals[best_index]
+def get_individual_index(population, element):
+    for index in range(len(population)):
+        if population[index].fitness.values[0] == element.fitness.values[0]:
+            return index
+
+
+def tournament_selection(population):
+    individuals = [population[randint(len(population))] for _ in range(2)]
+    best_element = max(individuals, key=lambda x: x.fitness.values[0])
+    population_index = get_individual_index(population, best_element)
+    return best_element, population_index
 
 
 def generational_replacement(previous_population, current_population):
@@ -209,20 +230,41 @@ def evaluate_population(population, data, cores=4):
     return evaluated_population
 
 
-def select_new_population(population, n, m, mode):
+def select_parents(population, n, mode):
+    select_population = population
+    parents = []
     if mode == "generational":
-        parents = [tournament_selection(m, population) for _ in range(n)]
+        for _ in range(n):
+            element, index = tournament_selection(population=select_population)
+            parents.append(element)
+            select_population.pop(index)
     else:
-        parents = [tournament_selection(m, population) for _ in range(2)]
+        for _ in range(2):
+            element, index = tournament_selection(population=select_population)
+            parents.append(element)
+            select_population.pop(index)
     return parents
 
 
-def genetic_algorithm(n, m, data, mode, max_iterations=100000):
+def genetic_algorithm(n, m, data, select_mode, crossover_mode, max_iterations=100000):
     population = [generate_individual(n, m, data) for _ in range(n)]
     population = evaluate_population(population, data)
     for _ in range(max_iterations):
-        parents = select_new_population(population, n, m, mode)
+        parents = select_parents(population, n, select_mode)
+        offspring = crossover(crossover_mode, parents, m)
+        offspring = mutate(offspring, data)
+        population = replace_population(population, offspring, select_mode)
+        population = evaluate_population(population, data)
+    best_solution, _ = get_best_elements(population)
+    return best_solution
 
 
 n, m, data = parse_file("data/GKD-c_11_n500_m50.txt")
-genetic_algorithm(n=10, m=5, data=data, mode="generational", max_iterations=1)
+genetic_algorithm(
+    n=10,
+    m=4,
+    data=data,
+    select_mode="generational",
+    crossover_mode="uniform",
+    max_iterations=1,
+)