双倍体遗传算法代码实例

双倍体遗传算法是一种基于自然选择、交叉和变异等生物进化原理的优化搜索算法。它通常用于解决复杂的全局优化问题，比如函数优化、机器学习模型参数调整等。这里是一个简单的Python代码示例，使用DEAP库（Distributed Evolutionary Algorithms in Python）实现：

from deap import base, creator, tools

# 定义染色体类型
creator.create("FitnessMax", base.Fitness, weights=(1.0,))
creator.create("Individual", list, fitness=creator.FitnessMax)

def mate(ind1, ind2):
    return [ind1[i] + ind2[i] for i in range(len(ind1))]

def mutate(individual):
    individual[random.randint(0, len(individual) - 1)] += random.randint(-1, 1)
    return individual

toolbox = base.Toolbox()
toolbox.register("individual", creator.Individual, range(10))  # 假设我们有一个10维的搜索空间
toolbox.register("population", tools.initRepeat, list, toolbox.individual)
toolbox.register("mate", mate)
toolbox.register("mutate", mutate)
toolbox.register("select", tools.selTournament, tournsize=3)
toolbox.register("evaluate", evaluate_function)  # 自定义的目标函数

def evolve(population,ngen=50, cxpb=0.5, mutpb=0.2):
    pop = toolbox.population(n=population)
    hof = tools.HallOfFame(1)
    
    for g in range(ngen):
        offspring = [toolbox.clone(ind) for ind in pop]
        
        # 遗传操作
        for _ in range(int(len(offspring)/2)):
            if random.random() < cxpb:
                offspring[random.randint(0, len(offspring)-1)], offspring[random.randint(0, len(offspring)-1)] = toolbox.mate(offspring[random.randint(0, len(offspring)-1)], offspring[random.randint(0, len(offspring)-1)])
            offspring[random.randint(0, len(offspring)-1)].fitness.values = toolbox.evaluate(offspring[random.randint(0, len(offspring)-1)])

        # 变异操作
        for ind in offspring:
            if random.random() < mutpb:
                toolbox.mutate(ind)
                ind.fitness.values = toolbox.evaluate(ind)

        # 更新种群并保存最佳解
        population[:] = toolbox.select(offspring, k=len(pop))
        hof.update(pop)

    return pop, hof

best_solution, best_fitness = evolve(100)
print(f"Best solution found: {best_solution}, Fitness: {best_fitness[0].fitness}")