Add memetic algorithm prototype

src/genetic_algorithm.py

@@ -1,10 +1,11 @@
-from numpy import sum, append, intersect1d, array_equal
+from numpy import intersect1d, array_equal
 from numpy.random import randint, choice, shuffle
 from pandas import DataFrame
 from math import ceil
 from functools import partial
 from multiprocessing import Pool
 from copy import deepcopy
+from itertools import combinations
 
 
 def get_row_distance(source, destination, data):
@@ -35,22 +36,23 @@ def generate_individual(n, m, data):
 
 
 def evaluate_individual(individual, data):
-    fitness = []
-    genotype = individual.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}")
-        max_distance = element_df["distance"].astype(float).max()
-        fitness = append(arr=fitness, values=max_distance)
-        distances = distances.query(f"source != {item} and destination != {item}")
-    individual["fitness"] = sum(fitness)
+    fitness = 0
+    comb = combinations(individual.index, r=2)
+    for index in list(comb):
+        elements = individual.loc[index, :]
+        fitness += get_row_distance(
+            source=elements["point"].head(n=1).values[0],
+            destination=elements["point"].tail(n=1).values[0],
+            data=data,
+        )
+    individual["fitness"] = fitness
     return individual
 
 
 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(m - len(matching_genes))
+    cutoff = randint(m - len(matching_genes) + 1)
     first_parent_genes = first_parent.point.values[cutoff:]
     second_parent_genes = second_parent.point.values[:cutoff]
     return first_parent_genes, second_parent_genes
@@ -137,9 +139,8 @@ def group_parents(parents):
         first = parents[i]
         second = parents[i + 1]
         if array_equal(first.point.values, second.point.values):
-            tmp = second
-            second = parents[i - 2]
-            parents[i - 2] = tmp
+            random_index = randint(i + 1)
+            second, parents[random_index] = parents[random_index], second
         parent_pairs.append([first, second])
     return parent_pairs
 

src/main.py

@@ -1,9 +1,7 @@
 from preprocessing import parse_file
 from genetic_algorithm import genetic_algorithm
 from memetic_algorithm import memetic_algorithm
-from sys import argv
 from time import time
-from itertools import combinations
 from argparse import ArgumentParser
 
 
@@ -17,54 +15,24 @@ def execute_algorithm(args, n, m, data):
             crossover_mode=args.crossover,
             max_iterations=100,
         )
-    else:
-        return memetic_algorithm(
-            n,
-            m,
-            data,
-            hybridation=args.hybridation,
-            max_iterations=100,
-        )
-
-
-def get_row_distance(source, destination, data):
-    row = data.query(
-        """(source == @source and destination == @destination) or \
-        (source == @destination and destination == @source)"""
+    return memetic_algorithm(
+        n,
+        m,
+        data,
+        hybridation=args.hybridation,
+        max_iterations=100,
     )
-    return row["distance"].values[0]
 
 
-def get_fitness(solutions, data):
-    counter = 0
-    comb = combinations(solutions.index, r=2)
-    for index in list(comb):
-        elements = solutions.loc[index, :]
-        counter += get_row_distance(
-            source=elements["point"].head(n=1).values[0],
-            destination=elements["point"].tail(n=1).values[0],
-            data=data,
-        )
-    return counter
-
-
-def show_results(solutions, fitness, time_delta):
-    duplicates = solutions.duplicated().any()
-    print(solutions)
-    print(f"Total distance: {fitness}")
+def show_results(solution, time_delta):
+    duplicates = solution.duplicated().any()
+    print(solution)
+    print(f"Total distance: {solution.fitness.values[0]}")
     if not duplicates:
         print("No duplicates found")
     print(f"Execution time: {time_delta}")
 
 
-def usage(argv):
-    print(f"Usage: python {argv[0]} <file> <algorithm choice> <")
-    print("algorithm choices:")
-    print("genetic: genetic algorithm")
-    print("memetic: memetic algorithm")
-    exit(1)
-
-
 def parse_arguments():
     parser = ArgumentParser()
     parser.add_argument("file", help="dataset of choice")
@@ -83,8 +51,7 @@ def main():
     start_time = time()
     solutions = execute_algorithm(args, n, m, data)
     end_time = time()
-    fitness = get_fitness(solutions, data)
-    show_results(solutions, fitness, time_delta=end_time - start_time)
+    show_results(solutions, time_delta=end_time - start_time)
 
 
 if __name__ == "__main__":

src/memetic_algorithm.py

@@ -1,50 +1,22 @@
-from numpy.random import choice, seed
+from genetic_algorithm import *
+from local_search import local_search
 
 
-def get_first_random_solution(m, data):
-    seed(42)
-    random_indexes = choice(len(data.index), size=m, replace=False)
-    return data.loc[random_indexes]
+def run_local_search(n, m, data, individual):
+    pass
 
 
-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})"
-    )
-    return not duplicates.empty
-
-
-def replace_worst_element(previous, data):
-    solution = previous.copy()
-    worst_index = solution["distance"].astype(float).idxmin()
-    random_element = data.sample().squeeze()
-    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)
-    return solution
-
-
-def explore_neighbourhood(element, 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)
-        neighbourhood.append(neighbour)
-    return neighbour
-
-
-def memetic_algorithm(m, data):
-    first_solution = get_first_random_solution(m=m, data=data)
-    best_solution = explore_neighbourhood(
-        element=first_solution, data=data, max_iterations=100
-    )
-    return best_solution
+def memetic_algorithm(n, m, data, hybridation, max_iterations=100000):
+    population = [generate_individual(n, m, data) for _ in range(n)]
+    population = evaluate_population(population, data)
+    for i in range(max_iterations):
+        if i % 10 == 0:
+            best_index, _ = get_best_elements(population)
+            run_local_search(n, m, data, individual=population[best_index])
+        parents = select_parents(population, n, mode="stationary")
+        offspring = crossover(mode="uniform", parents=parents, m=m)
+        offspring = mutate(offspring, n, data)
+        population = replace_population(population, offspring, mode="stationary")
+        population = evaluate_population(population, data)
+    best_index, _ = get_best_elements(population)
+    return population[best_index]