python 遗传算法示例

Python 是一门非常流行的编程语言，在遗传算法方面也有很多优秀的库和示例。遗传算法是一种基于生物进化理论的优化算法，可以用于解决许多优化问题，如函数优化、组合优化、路径规划等。

下面是一个 Python 实现的简单遗传算法示例：

import random

# 目标函数
def fitness(x):
    return x * x

# 初始化种群
def init_population(pop_size, gene_length):
    population = []
    for i in range(pop_size):
        gene = []
        for j in range(gene_length):
            gene.append(random.randint(0, 1))
        population.append(gene)
    return population

# 计算适应度
def calc_fitness(population):
    fitness_values = []
    for gene in population:
        x = int(''.join(map(str, gene)), 2)
        fitness_values.append(fitness(x))
    return fitness_values

# 选择
def selection(population, fitness_values):
    total_fitness = sum(fitness_values)
    p = [f / total_fitness for f in fitness_values]
    p_sum = [sum(p[:i+1]) for i in range(len(p))]
    selected_population = []
    for i in range(len(population)):
        r = random.random()
        for j in range(len(p_sum)):
            if r <= p_sum[j]:
                selected_population.append(population[j])
                break
    return selected_population

# 交叉
def crossover(parent1, parent2):
    pos = random.randint(0, len(parent1) - 1)
    child1 = parent1[:pos] + parent2[pos:]
    child2 = parent2[:pos] + parent1[pos:]
    return child1, child2

# 变异
def mutation(gene, mutation_rate):
    for i in range(len(gene)):
        if random.random() < mutation_rate:
            gene[i] = 1 - gene[i]
    return gene

# 遗传算法主程序
def genetic_algorithm(pop_size, gene_length, num_generation, crossover_rate, mutation_rate):
    population = init_population(pop_size, gene_length)
    for i in range(num_generation):
        fitness_values = calc_fitness(population)
        selected_population = selection(population, fitness_values)
        next_population = []
        for j in range(int(len(selected_population) / 2)):
            parent1 = selected_population[j * 2]
            parent2 = selected_population[j * 2 + 1]
            if random.random() < crossover_rate:
                child1, child2 = crossover(parent1, parent2)
            else:
                child1, child2 = parent1, parent2
            child1 = mutation(child1, mutation_rate)
            child2 = mutation(child2, mutation_rate)
            next_population.append(child1)
            next_population.append(child2)
        population = next_population
    fitness_values = calc_fitness(population)
    best_gene = population[fitness_values.index(max(fitness_values))]
    x = int(''.join(map(str, best_gene)), 2)
    print("最优解：x =", x, "f(x) =", fitness(x))

# 示例运行
genetic_algorithm(pop_size=50, gene_length=6, num_generation=100, crossover_rate=0.8, mutation_rate=0.01)

这个示例是一个简单的二进制遗传算法，目标函数为 f(x) = x²，求在 x∈[0, 63] 范围内的最大值。代码中包括了初始化种群、计算适应度、选择、交叉和变异等基本操作。