docs/Summary.org

@@ -1,143 +0,0 @@
-#+TITLE: Práctica 2
-#+SUBTITLE: Metaheurísticas
-#+AUTHOR: Amin Kasrou Aouam
-#+DATE: 2021-06-22
-#+PANDOC_OPTIONS: template:~/.pandoc/templates/eisvogel.latex
-#+PANDOC_OPTIONS: listings:t
-#+PANDOC_OPTIONS: toc:t
-#+PANDOC_METADATA: lang=es
-#+PANDOC_METADATA: titlepage:t
-#+PANDOC_METADATA: listings-no-page-break:t
-#+PANDOC_METADATA: toc-own-page:t
-#+PANDOC_METADATA: table-use-row-colors:t
-#+PANDOC_METADATA: colorlinks:t
-#+PANDOC_METADATA: logo:/home/coolneng/Photos/Logos/UGR.png
-#+LaTeX_HEADER: \usepackage[ruled, lined, linesnumbered, commentsnumbered, longend]{algorithm2e}
-* Práctica 2
-
-** Introducción
-
-En esta práctica, usaremos distintos algoritmos de búsqueda, basados en poblaciones, para resolver el problema de la máxima diversidad (MDP). Implementaremos:
-
-- Algoritmo genético
-- Algoritmo memético
-
-** Algoritmos
-
-*** Genético
-
-Los algoritmos genéticos se inspiran en la evolución natural y la genética. Generan un conjunto de soluciones inicial (i.e. población), seleccionan un subconjunto de individuos sobre los cuales se opera, hacen operaciones de recombinación y mutación, y finalmente reemplazan la población anterior por una nueva.
-
-El procedimiento general del algoritmo queda ilustrado a continuación:
-
-\begin{algorithm}
-    \KwIn{A list $[a_i]$, $i=1, 2, \cdots, n$, that contains the population of individuals}
-    \KwOut{Processed list}
-
-    $P(t) \leftarrow initializePopulation()$
-    $P(t) \leftarrow evaluatePopulation()$
-
-    \While{$\neg stop  condition $}{
-        $t = t + 1$
-
-        $parents \leftarrow selectParents(P(t-1))$
-
-        $offspring \leftarrow recombine(parents)$
-
-        $offspring \leftarrow mutate(offspring)$
-
-        $P(t) \leftarrow replacePopulation(P(t-1), offspring)$
-
-        $P(t) \leftarrow evaluatePopulation()$
-    }
-    \KwRet{$P(t)$}
-\end{algorithm}
-
-Procedemos a la implementación de 4 variantes distintas, según 2 criterios:
-
-**** Criterio de reemplazamiento
-- *Generacional*: la nueva población reemplaza totalmente a la población anterior
-- *Estacionario*: los dos mejores hijos reemplazan los dos peores individuos en la población anterior
-**** Operador de cruce
-- *Uniforme*: mantiene las posiciones comunes de ambos padres, las demás se eligen de forma aleatoria de cada padre (requiere reparador)
-- *Posición*: mantiene las posiciones comunes de ambos padres, elige el resto de elementos de cada padre y los baraja. Genera 2 hijos.
-
-*** Memético
-
-Los algoritmos meméticos surgen de la hibridación de un algoritmo genético, con un algoritmo de búsqueda local. El resultado es un algoritmo que posee un buen equilibrio entre exploración y explotación.
-
-El procedimiento general del algoritmo queda ilustrado a continuación:
-
-\begin{algorithm}
-    \KwIn{A list $[a_i]$, $i=1, 2, \cdots, n$, that contains the population of individuals}
-    \KwOut{Processed list}
-
-    $P(t) \leftarrow initializePopulation()$
-    $P(t) \leftarrow evaluatePopulation()$
-
-    \While{$\neg stop  condition $}{
-        \If{$certain  iteration$}{
-            $P(t) <- localSearch(P(t-1))$
-        }
-        $t = t + 1$
-
-        $parents \leftarrow selectParents(P(t-1))$
-
-        $offspring \leftarrow recombine(parents)$
-
-        $offspring \leftarrow mutate(offspring)$
-
-        $P(t) \leftarrow replacePopulation(P(t-1), offspring)$
-
-        $P(t) \leftarrow evaluatePopulation()$
-    }
-    \KwRet{$P(t)$}
-\end{algorithm}
-
-Procedemos a la implementación de 3 variantes distintas:
-- Búsqueda local sobre todos los cromosomas
-- Búsqueda local sobre un subconjunto aleatorio de cromosomas
-- Búsqueda local sobre un el subconjunto de los mejores cromosomas
-
-** Implementación
-
-La práctica ha sido implementada en /Python/, usando las siguientes bibliotecas:
-
-- NumPy
-- Pandas
-
-*** Instalación
-
-Para ejecutar el programa es preciso instalar Python, junto con las bibliotecas *Pandas* y *NumPy*.
-
-Se proporciona el archivo shell.nix para facilitar la instalación de las dependencias, con el gestor de paquetes [[https://nixos.org/][Nix]]. Tras instalar la herramienta Nix, únicamente habría que ejecutar el siguiente comando en la raíz del proyecto:
-
-#+begin_src shell
-nix-shell
-#+end_src
-
-** Ejecución
-
-La ejecución del programa se realiza mediante el siguiente comando:
-
-#+begin_src shell
-python src/main.py <dataset> <algoritmo> <parámetros>
-#+end_src
-
-Los parámetros posibles son:
-
-| dataset                              | algoritmo | parámetros                             |
-| Cualquier archivo de la carpeta data | genetic   | uniform/position generation/stationary |
-|                                      | memetic   | all/random/best                        |
-
-También se proporciona un script que ejecuta 1 iteración de cada algoritmo, sobre cada uno de los /datasets/, y guarda los resultados en una hoja de cálculo. Se puede ejecutar mediante el siguiente comando:
-
-#+begin_src shell
-python src/execution.py
-#+end_src
-
-*Nota*: se precisa instalar la biblioteca [[https://xlsxwriter.readthedocs.io/][XlsxWriter]] para la exportación de los resultados a un archivo Excel.
-
-* Análisis de los resultados
-
-Desafortunadamente, debido a un tiempo de ejecución excesivamente alto (incluso tras ajustar los metaparámetros) no podemos proporcionar resultados de la ejecución de los algoritmos.

src/execution.py

@@ -14,67 +14,70 @@ def file_list(path):
 
 
 def create_dataframes():
-    return [DataFrame() for _ in range(7)]
+    greedy = DataFrame()
+    local = DataFrame()
+    return greedy, local
 
 
 def process_output(results):
     distances = []
     time = []
-    for line in results:
-        if line.startswith(bytes("Total distance:", encoding="utf-8")):
-            line_elements = line.split(sep=bytes(":", encoding="utf-8"))
-            distances.append(float(line_elements[1]))
-        if line.startswith(bytes("Execution time:", encoding="utf-8")):
-            line_elements = line.split(sep=bytes(":", encoding="utf-8"))
-            time.append(float(line_elements[1]))
+    for element in results:
+        for line in element:
+            if line.startswith(bytes("Total distance:", encoding="utf-8")):
+                line_elements = line.split(sep=bytes(":", encoding="utf-8"))
+                distances.append(float(line_elements[1]))
+            if line.startswith(bytes("Execution time:", encoding="utf-8")):
+                line_elements = line.split(sep=bytes(":", encoding="utf-8"))
+                time.append(float(line_elements[1]))
     return distances, time
 
 
-def populate_dataframe(df, output_cmd, dataset):
-    distances, time = process_output(output_cmd)
-    data_dict = {
+def populate_dataframes(greedy, local, greedy_list, local_list, dataset):
+    greedy_distances, greedy_time = process_output(greedy_list)
+    local_distances, local_time = process_output(local_list)
+    greedy_dict = {
         "dataset": dataset.removeprefix("data/"),
-        "media distancia": mean(distances),
-        "desviacion distancia": std(distances),
-        "media tiempo": mean(time),
-        "desviacion tiempo": std(time),
+        "media distancia": mean(greedy_distances),
+        "desviacion distancia": std(greedy_distances),
+        "media tiempo": mean(greedy_time),
+        "desviacion tiempo": std(greedy_time),
     }
-    df = df.append(data_dict, ignore_index=True)
-    return df
+    local_dict = {
+        "dataset": dataset.removeprefix("data/"),
+        "media distancia": mean(local_distances),
+        "desviacion distancia": std(local_distances),
+        "media tiempo": mean(local_time),
+        "desviacion tiempo": std(local_time),
+    }
+    greedy = greedy.append(greedy_dict, ignore_index=True)
+    local = local.append(local_dict, ignore_index=True)
+    return greedy, local
 
 
-def script_execution(filenames, df_list):
+def script_execution(filenames, greedy, local, iterations=3):
     script = "src/main.py"
-    parameters = [
-        ["genetic", "uniform", "generational"],
-        ["genetic", "position", "generational"],
-        ["genetic", "uniform", "stationary"],
-        ["genetic", "position", "stationary"],
-        ["memetic", "all"],
-        ["memetic", "random"],
-        ["memetic", "best"],
-    ]
     for dataset in filenames:
         print(f"Running on dataset {dataset}")
-        for index, params in zip(range(4), parameters):
-            print(f"Running {params} algorithm")
-            output_cmd = run(
-                [executable, script, dataset, *params], capture_output=True
+        greedy_list = []
+        local_list = []
+        for _ in range(iterations):
+            greedy_cmd = run(
+                [executable, script, dataset, "greedy"], capture_output=True
             ).stdout.splitlines()
-            df_list[index] = populate_dataframe(df_list[index], output_cmd, dataset)
-    return df_list
+            local_cmd = run(
+                [executable, script, dataset, "local"], capture_output=True
+            ).stdout.splitlines()
+            greedy_list.append(greedy_cmd)
+            local_list.append(local_cmd)
+        greedy, local = populate_dataframes(
+            greedy, local, greedy_list, local_list, dataset
+        )
+    return greedy, local
 
 
-def export_results(df_list):
-    dataframes = {
-        "Generational uniform genetic": df_list[0],
-        "Generational position genetic": df_list[1],
-        "Stationary uniform genetic": df_list[2],
-        "Stationary position genetic": df_list[3],
-        "All genes memetic": df_list[4],
-        "Random genes memetic": df_list[5],
-        "Best genes memetic": df_list[6],
-    }
+def export_results(greedy, local):
+    dataframes = {"Greedy": greedy, "Local search": local}
     writer = ExcelWriter(path="docs/algorithm-results.xlsx", engine="xlsxwriter")
     for name, df in dataframes.items():
         df.to_excel(writer, sheet_name=name, index=False)
@@ -88,9 +91,9 @@ def export_results(df_list):
 
 def main():
     datasets = file_list(path="data/*.txt")
-    df_list = create_dataframes()
-    populated_df_list = script_execution(datasets, df_list)
-    export_results(populated_df_list)
+    greedy, local = create_dataframes()
+    populated_greedy, populated_local = script_execution(datasets, greedy, local)
+    export_results(populated_greedy, populated_local)
 
 
 if __name__ == "__main__":

src/genetic_algorithm.py

@@ -1,11 +1,6 @@
-from numpy import intersect1d, array_equal
+from numpy import sum, append, arange, delete, where
 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):
@@ -16,288 +11,148 @@ def get_row_distance(source, destination, data):
     return row["distance"].values[0]
 
 
-def compute_distance(element, individual, data):
+def compute_distance(element, solution, data):
     accumulator = 0
-    distinct_elements = individual.query(f"point != {element}")
+    distinct_elements = solution.query(f"point != {element}")
     for _, item in distinct_elements.iterrows():
         accumulator += get_row_distance(
-            source=element, destination=item.point, data=data
+            source=element,
+            destination=item.point,
+            data=data,
         )
     return accumulator
 
 
-def generate_individual(n, m, data):
-    individual = DataFrame(columns=["point", "distance", "fitness"])
-    individual["point"] = choice(n, size=m, replace=False)
-    individual["distance"] = individual["point"].apply(
-        func=compute_distance, individual=individual, data=data
+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 individual
+    return solution
 
 
-def evaluate_individual(individual, data):
-    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 evaluate_element(element, data):
+    fitness = []
+    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}")
+        max_distance = element_df["distance"].astype(float).max()
+        fitness = append(arr=fitness, values=max_distance)
+        distances = distances.query(f"source != {item} and destination != {item}")
+    return sum(fitness)
 
 
 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) + 1)
-    first_parent_genes = first_parent.point.values[cutoff:]
-    second_parent_genes = second_parent.point.values[:cutoff]
+    cutoff = randint(m)
+    distinct_indexes = delete(arange(m), matching_genes)
+    first_parent_genes = parents[0].point.iloc[distinct_indexes[cutoff:]]
+    second_parent_genes = parents[1].point.iloc[distinct_indexes[:cutoff]]
     return first_parent_genes, second_parent_genes
 
 
-def select_shuffled_genes(matching_genes, parents):
-    first_parent = parents[0].query("point not in @matching_genes")
-    second_parent = parents[1].query("point not in @matching_genes")
-    first_genes = first_parent.point.values
-    second_genes = second_parent.point.values
-    shuffle(first_genes)
-    shuffle(second_genes)
-    return first_genes, second_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 get_best_point(parents, offspring):
-    while True:
-        random_parent = deepcopy(select_random_parent(parents))
-        best_index = random_parent["distance"].idxmax()
-        best_point = random_parent["point"].iloc[best_index]
-        random_parent.drop(index=best_index, inplace=True)
-        if best_point not in offspring.point.values:
-            return best_point
+def select_random_genes(matching_genes, parents, m):
+    random_parent = parents[randint(len(parents))]
+    distinct_indexes = delete(arange(m), matching_genes)
+    genes = random_parent.point.iloc[distinct_indexes].values
+    shuffle(genes)
+    return genes
 
 
 def repair_offspring(offspring, parents, m):
     while len(offspring) != m:
         if len(offspring) > m:
-            best_index = offspring["distance"].idxmax()
+            best_index = offspring["distance"].astype(float).idxmax()
             offspring.drop(index=best_index, inplace=True)
         elif len(offspring) < m:
-            best_point = get_best_point(parents, offspring)
+            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, "fitness": 0}, ignore_index=True
+                {"point": best_point, "distance": 0}, ignore_index=True
             )
+            random_parent.drop(index=best_index, inplace=True)
     return offspring
 
 
 def get_matching_genes(parents):
-    first_parent = parents[0].point.values
-    second_parent = parents[1].point.values
-    return intersect1d(first_parent, second_parent)
+    first_parent = parents[0].point
+    second_parent = parents[1].point
+    return where(first_parent == second_parent)
 
 
 def populate_offspring(values):
-    offspring = DataFrame(columns=["point", "distance", "fitness"])
+    offspring = DataFrame(columns=["point", "distance"])
     for element in values:
-        aux = DataFrame(columns=["point", "distance", "fitness"])
+        aux = DataFrame(columns=["point", "distance"])
         aux["point"] = element
         offspring = offspring.append(aux)
     offspring["distance"] = 0
-    offspring["fitness"] = 0
+    offspring = offspring[1:]
     return offspring
 
 
 def uniform_crossover(parents, m):
-    matching_genes = get_matching_genes(parents)
+    matching_indexes = get_matching_genes(parents)
+    matching_genes = parents[0].point.iloc[matching_indexes]
     first_genes, second_genes = select_distinct_genes(matching_genes, parents, m)
     offspring = populate_offspring(values=[matching_genes, first_genes, second_genes])
     viable_offspring = repair_offspring(offspring, parents, m)
     return viable_offspring
 
 
-def position_crossover(parents):
+def position_crossover(parents, m):
     matching_genes = get_matching_genes(parents)
-    first_genes, second_genes = select_shuffled_genes(matching_genes, parents)
-    first_offspring = populate_offspring(values=[matching_genes, first_genes])
-    second_offspring = populate_offspring(values=[matching_genes, second_genes])
-    return first_offspring, second_offspring
-
-
-def group_parents(parents):
-    parent_pairs = []
-    for i in range(0, len(parents), 2):
-        first = parents[i]
-        second = parents[i + 1]
-        if array_equal(first.point.values, second.point.values):
-            random_index = randint(i + 1)
-            second, parents[random_index] = parents[random_index], second
-        parent_pairs.append([first, second])
-    return parent_pairs
-
-
-def crossover(mode, parents, m, probability=0.7):
-    parent_groups = group_parents(parents)
-    offspring = []
-    if mode == "uniform":
-        expected_crossovers = int(len(parents) * probability)
-        cutoff = expected_crossovers // 2
-        for element in parent_groups[:cutoff]:
-            offspring.append(uniform_crossover(element, m))
-            offspring.append(uniform_crossover(element, m))
-        for element in parent_groups[cutoff:]:
-            offspring.append(element[0])
-            offspring.append(element[1])
-    else:
-        for element in parent_groups:
-            first_offspring, second_offspring = position_crossover(element)
-            offspring.append(first_offspring)
-            offspring.append(second_offspring)
+    shuffled_genes = select_random_genes(matching_genes, parents, m)
+    offspring = populate_offspring(values=[matching_genes, shuffled_genes])
     return offspring
 
 
-def element_in_dataframe(individual, element):
-    duplicates = individual.query(f"point == {element}")
+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"point == {element}")
     return not duplicates.empty
 
 
-def select_new_gene(individual, n):
-    while True:
-        new_gene = randint(n)
-        if not element_in_dataframe(individual=individual, element=new_gene):
-            return new_gene
+def replace_worst_element(previous, n, data):
+    solution = previous.copy()
+    worst_index = solution["distance"].astype(float).idxmin()
+    random_element = randint(n)
+    while element_in_dataframe(solution=solution, element=random_element):
+        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 mutate(offspring, n, data, probability=0.001):
-    expected_mutations = len(offspring) * n * probability
-    individuals = []
-    genes = []
-    for _ in range(ceil(expected_mutations)):
-        individuals.append(randint(len(offspring)))
-        current_individual = individuals[-1]
-        genes.append(offspring[current_individual].sample().index)
-    for ind, gen in zip(individuals, genes):
-        individual = offspring[ind]
-        individual["point"].iloc[gen] = select_new_gene(individual, n)
-        individual["distance"].iloc[gen] = compute_distance(
-            element=individual["point"].iloc[gen].values[0],
-            individual=individual,
-            data=data,
-        )
-    return offspring
+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 get_individual_index(element, population):
-    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(best_element, population)
-    return best_element, population_index
-
-
-def check_element_population(element, population):
-    for item in population:
-        if array_equal(element.point.values, item.point.values):
-            return True
-    return False
-
-
-def generational_replacement(prev_population, current_population):
-    new_population = current_population
-    best_previous_individual = max(prev_population, key=lambda x: x.fitness.values[0])
-    if check_element_population(best_previous_individual, new_population):
-        worst_element = min(new_population, key=lambda x: x.fitness.values[0])
-        worst_index = get_individual_index(worst_element, new_population)
-        new_population[worst_index] = best_previous_individual
-    return new_population
-
-
-def get_best_elements(population):
-    select_population = deepcopy(population)
-    first_element = max(select_population, key=lambda x: x.fitness.values[0])
-    first_index = get_individual_index(first_element, select_population)
-    select_population.pop(first_index)
-    second_element = max(select_population, key=lambda x: x.fitness.values[0])
-    second_index = get_individual_index(second_element, select_population)
-    return first_index, second_index
-
-
-def get_worst_elements(population):
-    select_population = deepcopy(population)
-    first_element = min(select_population, key=lambda x: x.fitness.values[0])
-    first_index = get_individual_index(first_element, select_population)
-    select_population.pop(first_index)
-    second_element = min(select_population, key=lambda x: x.fitness.values[0])
-    second_index = get_individual_index(second_element, select_population)
-    return first_index, second_index
-
-
-def stationary_replacement(prev_population, current_population):
-    new_population = prev_population
-    first_worst, second_worst = get_worst_elements(prev_population)
-    first_best, second_best = get_best_elements(current_population)
-    worst_indexes = [first_worst, second_worst]
-    best_indexes = [first_best, second_best]
-    for worst, best in zip(worst_indexes, best_indexes):
-        if (
-            current_population[best].fitness.values[0]
-            > prev_population[worst].fitness.values[0]
-        ):
-            new_population[worst] = current_population[best]
-    return new_population
-
-
-def replace_population(prev_population, current_population, mode):
-    if mode == "generational":
-        return generational_replacement(prev_population, current_population)
-    return stationary_replacement(prev_population, current_population)
-
-
-def evaluate_population(population, data, cores=4):
-    fitness_func = partial(evaluate_individual, data=data)
-    with Pool(cores) as pool:
-        evaluated_population = pool.map(fitness_func, population)
-    return evaluated_population
-
-
-def select_parents(population, n, mode):
-    select_population = deepcopy(population)
-    parents = []
-    if mode == "generational":
-        for _ in range(n):
-            element, index = tournament_selection(population=select_population)
-            parents.append(element)
-            select_population.pop(index)
-    else:
-        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, select_mode, crossover_mode, max_iterations=100000):
-    population = [generate_individual(n, m, data) for _ in range(n)]
-    population = evaluate_population(population, data)
+def explore_neighbourhood(element, n, data, max_iterations=100000):
+    neighbourhood = []
+    neighbourhood.append(element)
     for _ in range(max_iterations):
-        parents = select_parents(population, n, select_mode)
-        offspring = crossover(crossover_mode, parents, m)
-        offspring = mutate(offspring, n, data)
-        population = replace_population(population, offspring, select_mode)
-        population = evaluate_population(population, data)
-    best_index, _ = get_best_elements(population)
-    return population[best_index]
+        previous_solution = neighbourhood[-1]
+        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, m, data)
+    best_solution = explore_neighbourhood(
+        element=first_solution, n=n, data=data, max_iterations=100
+    )
+    return best_solution

src/local_search.py

@@ -1,64 +0,0 @@
-from numpy.random import choice, seed, randint
-from pandas import DataFrame
-
-
-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 element_in_dataframe(solution, element):
-    duplicates = solution.query(f"point == {element}")
-    return not duplicates.empty
-
-
-def replace_worst_element(previous, n, data):
-    solution = previous.copy()
-    worst_index = solution["distance"].astype(float).idxmin()
-    random_element = randint(n)
-    while element_in_dataframe(solution=solution, element=random_element):
-        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 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, n=n, data=data)
-        neighbourhood.append(neighbour)
-    return neighbour
-
-
-def local_search(first_solution, n, data):
-    best_solution = explore_neighbourhood(
-        element=first_solution, n=n, data=data, max_iterations=5
-    )
-    return best_solution

src/main.py

@@ -1,57 +1,68 @@
 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 argparse import ArgumentParser
+from itertools import combinations
 
 
-def execute_algorithm(args, n, m, data):
-    if args.algorithm == "genetic":
-        return genetic_algorithm(
-            n,
-            m,
-            data,
-            select_mode=args.selection,
-            crossover_mode=args.crossover,
-            max_iterations=100,
-        )
-    return memetic_algorithm(
-        n,
-        m,
-        data,
-        hybridation=args.hybridation,
-        max_iterations=100,
+def execute_algorithm(choice, n, m, data):
+    if choice == "genetic":
+        return genetic_algorithm(n, m, data)
+    elif choice == "memetic":
+        return memetic_algorithm(m, data)
+    else:
+        print("The valid algorithm choices are 'genetic' and 'memetic'")
+        exit(1)
+
+
+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 show_results(solution, time_delta):
-    duplicates = solution.duplicated().any()
-    print(solution)
-    print(f"Total distance: {solution.fitness.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}")
     if not duplicates:
         print("No duplicates found")
     print(f"Execution time: {time_delta}")
 
 
-def parse_arguments():
-    parser = ArgumentParser()
-    parser.add_argument("file", help="dataset of choice")
-    subparsers = parser.add_subparsers(dest="algorithm")
-    parser_genetic = subparsers.add_parser("genetic")
-    parser_memetic = subparsers.add_parser("memetic")
-    parser_genetic.add_argument("crossover", choices=["uniform", "position"])
-    parser_genetic.add_argument("selection", choices=["generational", "stationary"])
-    parser_memetic.add_argument("hybridation", choices=["all", "random", "best"])
-    return parser.parse_args()
+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 main():
-    args = parse_arguments()
-    n, m, data = parse_file(args.file)
+    if len(argv) != 3:
+        usage(argv)
+    n, m, data = parse_file(argv[1])
     start_time = time()
-    solutions = execute_algorithm(args, n, m, data)
+    solutions = execute_algorithm(choice=argv[2], n=n, m=m, data=data)
     end_time = time()
-    show_results(solutions, time_delta=end_time - start_time)
+    fitness = get_fitness(solutions, data)
+    show_results(solutions, fitness, time_delta=end_time - start_time)
 
 
 if __name__ == "__main__":

src/memetic_algorithm.py

@@ -1,59 +1,50 @@
-from genetic_algorithm import *
-from local_search import local_search
-from copy import deepcopy
+from numpy.random import choice, seed
 
 
-def get_best_indices(n, population):
-    select_population = deepcopy(population)
-    best_elements = []
-    for _ in range(n):
-        best_index, _ = get_best_elements(select_population)
-        best_elements.append(best_index)
-        select_population.pop(best_index)
-    return best_elements
+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 replace_elements(current_population, new_population, indices):
-    for item in indices:
-        current_population[item] = new_population[item]
-    return current_population
+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 run_local_search(n, data, population, mode, probability=0.1):
+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 = []
-    if mode == "all":
-        for individual in population:
-            neighbourhood.append(local_search(individual, n, data))
-        new_population = neighbourhood
-    elif mode == "random":
-        expected_individuals = len(population) * probability
-        indices = []
-        for _ in range(expected_individuals):
-            random_index = randint(len(population))
-            random_individual = population[random_index]
-            neighbourhood.append(local_search(random_individual, n, data))
-            indices.append(random_index)
-        new_population = replace_elements(population, neighbourhood, indices)
-    else:
-        expected_individuals = len(population) * probability
-        best_indices = get_best_indices(n=expected_individuals, population=population)
-        for element in best_indices:
-            neighbourhood.append(local_search(population[element], n, data))
-        new_population = replace_elements(population, neighbourhood, best_indices)
-    return new_population
+    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(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:
-            population = run_local_search(n, data, population, mode=hybridation)
-            i += 5
-        parents = select_parents(population, n, mode="stationary")
-        offspring = crossover(mode="position", 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]
+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