遗传算法python实例

以下是一个遗传算法（Genetic Algorithm）的 Python 实例：

import random

# 目标函数：计算染色体适应度
def fitness(chromosome):
    return sum(chromosome)

# 交叉操作：单点交叉
def crossover(parent1, parent2):
    point = random.randint(1, len(parent1)-1)
    child1 = parent1[:point] + parent2[point:]
    child2 = parent2[:point] + parent1[point:]
    return child1, child2

# 变异操作：单点变异
def mutation(chromosome):
    point = random.randint(0, len(chromosome)-1)
    new_gene = random.randint(0, 9)
    chromosome[point] = new_gene
    return chromosome

# 初始化种群
def init_population(pop_size, chromosome_size):
    population = []
    for i in range(pop_size):
        chromosome = [random.randint(0, 9) for j in range(chromosome_size)]
        population.append(chromosome)
    return population

# 遗传算法主函数
def genetic_algorithm(pop_size, chromosome_size, generation):
    population = init_population(pop_size, chromosome_size)
    for i in range(generation):
        # 计算适应度
        fitness_list = [fitness(chromosome) for chromosome in population]
        # 选择操作：轮盘赌选择
        probability = [fitness / sum(fitness_list) for fitness in fitness_list]
        roulette_wheel = [sum(probability[:i+1]) for i in range(pop_size)]
        new_population = []
        for j in range(pop_size):
            r = random.uniform(0, 1)
            for k in range(pop_size):
                if r <= roulette_wheel[k]:
                    new_population.append(population[k])
                    break
        # 交叉操作
        for j in range(0, pop_size, 2):
            parent1, parent2 = new_population[j], new_population[j+1]
            child1, child2 = crossover(parent1, parent2)
            new_population[j], new_population[j+1] = child1, child2
        # 变异操作
        for j in range(pop_size):
            new_population[j] = mutation(new_population[j])
        population = new_population
    # 返回最佳个体
    fitness_list = [fitness(chromosome) for chromosome in population]
    best_chromosome = population[fitness_list.index(max(fitness_list))]
    return best_chromosome

# 测试
best_chromosome = genetic_algorithm(pop_size=100, chromosome_size=10, generation=50)
print(best_chromosome)

这个实例是一个求解最大值问题的遗传算法，目标函数为染色体内各基因的和。其中包括了初始化种群、计算适应度、选择操作、交叉操作、变异操作等基本步骤。