Implement uniform crossover operator

src/genetic_algorithm.py

@@ -1,23 +1,40 @@
-from numpy import put, sum, append, where, zeros
-from numpy.random import choice, seed
+from numpy import sum, append, arange, delete, where
+from numpy.random import randint, choice
+from pandas import DataFrame
 
 
-def generate_first_solution(n, m):
-    seed(42)
-    solution = zeros(shape=n, dtype=bool)
-    random_indices = choice(n, size=m, replace=False)
-    put(solution, ind=random_indices, v=True)
+def get_row_distance(source, destination, data):
+    row = data.query(
+        """(source == @source and destination == @destination) or \
+        (source == @destination and destination == @source)"""
+    )
+    return row["distance"].values[0]
+
+
+def compute_distance(element, solution, data):
+    accumulator = 0
+    distinct_elements = solution.query(f"point != {element}")
+    for _, item in distinct_elements.iterrows():
+        accumulator += get_row_distance(
+            source=element,
+            destination=item.point,
+            data=data,
+        )
+    return accumulator
+
+
+def generate_first_solution(n, m, data):
+    solution = DataFrame(columns=["point", "distance"])
+    solution["point"] = choice(n, size=m, replace=False)
+    solution["distance"] = solution["point"].apply(
+        func=compute_distance, solution=solution, data=data
+    )
     return solution
 
 
-def get_genotype(element):
-    genotype = where(element == True)
-    return genotype[0]
-
-
 def evaluate_element(element, data):
     fitness = []
-    genotype = get_genotype(element)
+    genotype = element.point.values
     distances = data.query(f"source in @genotype and destination in @genotype")
     for item in genotype[:-1]:
         element_df = distances.query(f"source == {item} or destination == {item}")
@@ -27,44 +44,95 @@ def evaluate_element(element, data):
     return sum(fitness)
 
 
+def select_random_genes(matching_genes, parents, m):
+    cutoff = randint(m)
+    distinct_genes = delete(arange(m), matching_genes)
+    first_parent_genes = parents[0].point.iloc[distinct_genes[cutoff:]]
+    second_parent_genes = parents[1].point.iloc[distinct_genes[:cutoff]]
+    return first_parent_genes, second_parent_genes
+
+
+def repair_offspring(offspring, parents, m):
+    while len(offspring) != m:
+        if len(offspring) > m:
+            best_index = offspring["distance"].astype(float).idxmax()
+            offspring.drop(index=best_index, inplace=True)
+        elif len(offspring) < m:
+            random_parent = parents[randint(len(parents))]
+            best_index = random_parent["distance"].astype(float).idxmax()
+            best_point = random_parent["point"].loc[best_index]
+            offspring = offspring.append(
+                {"point": best_point, "distance": 0}, ignore_index=True
+            )
+    return offspring
+
+
+def get_matching_genes(parents):
+    first_parent = parents[0].point
+    second_parent = parents[1].point
+    return where(first_parent == second_parent)
+
+
+def uniform_crossover(parents, m):
+    offspring = DataFrame(columns=["point", "distance"])
+    matching_genes = get_matching_genes(parents)
+    offspring["point"] = parents[0].point.iloc[matching_genes]
+    first_genes, second_genes = select_random_genes(matching_genes, parents, m)
+    offspring["point"] = offspring["point"].append(first_genes)
+    offspring["point"] = offspring["point"].append(second_genes)
+    offspring["distance"] = 0
+    viable_offspring = repair_offspring(offspring, parents, m)
+    return viable_offspring
+
+
+def position_crossover(parents, n):
+    genotypes = [parents[0].point.values, parents[1].point.values]
+
+
+def crossover(mode, parents, m):
+    if mode == "uniform":
+        return uniform_crossover(parents, m)
+    return position_crossover(parents, m)
+
+
 def element_in_dataframe(solution, element):
-    duplicates = solution.query(
-        f"(source == {element.source} and destination == {element.destination}) or (source == {element.destination} and destination == {element.source})"
-    )
+    duplicates = solution.query(f"point == {element}")
     return not duplicates.empty
 
 
-def replace_worst_element(previous, data):
+def replace_worst_element(previous, n, data):
     solution = previous.copy()
     worst_index = solution["distance"].astype(float).idxmin()
-    random_element = data.sample().squeeze()
+    random_element = randint(n)
     while element_in_dataframe(solution=solution, element=random_element):
-        random_element = data.sample().squeeze()
-    solution.loc[worst_index] = random_element
-    return solution, worst_index
-
-
-def get_random_solution(previous, data):
-    solution, worst_index = replace_worst_element(previous, data)
-    previous_worst_distance = previous["distance"].loc[worst_index]
-    while solution.distance.loc[worst_index] <= previous_worst_distance:
-        solution, _ = replace_worst_element(previous=solution, data=data)
+        random_element = randint(n)
+    solution["point"].loc[worst_index] = random_element
+    solution["distance"].loc[worst_index] = compute_distance(
+        element=solution["point"].loc[worst_index], solution=solution, data=data
+    )
     return solution
 
 
-def explore_neighbourhood(element, data, max_iterations=100000):
+def get_random_solution(previous, n, data):
+    solution = replace_worst_element(previous, n, data)
+    while solution["distance"].sum() <= previous["distance"].sum():
+        solution = replace_worst_element(previous=solution, n=n, data=data)
+    return solution
+
+
+def explore_neighbourhood(element, n, data, max_iterations=100000):
     neighbourhood = []
     neighbourhood.append(element)
     for _ in range(max_iterations):
         previous_solution = neighbourhood[-1]
-        neighbour = get_random_solution(previous=previous_solution, data=data)
+        neighbour = get_random_solution(previous=previous_solution, n=n, data=data)
         neighbourhood.append(neighbour)
     return neighbour
 
 
 def genetic_algorithm(n, m, data):
-    first_solution = generate_first_solution(n=n, m=m)
+    first_solution = generate_first_solution(n, m, data)
     best_solution = explore_neighbourhood(
-        element=first_solution, data=data, max_iterations=100
+        element=first_solution, n=n, data=data, max_iterations=100
     )
     return best_solution