用Python 写一个基于遗传算法的排班代码

遗传算法是一种仿生学算法，常被用于求解最优化问题。

下面是一个基于遗传算法的排班代码示例：

import random
import numpy as np

def create_schedule(n_employees, n_shifts):
    # 随机创建初始排班表
    schedule = np.random.randint(0, n_employees, (n_shifts,))
    return schedule

def evaluate_schedule(schedule, preferences):
    # 评估排班表的适应性
    fitness = 0
    for i, shift in enumerate(schedule):
        fitness += preferences[shift][i]
    return fitness

def mutate_schedule(schedule, n_employees):
    # 随机改变一个员工的排班
    i = random.randint(0, len(schedule) - 1)
    schedule[i] = random.randint(0, n_employees - 1)
    return schedule

def genetic_algorithm(preferences, n_employees, n_shifts, n_generations):
    # 遗传算法主体
    schedules = [create_schedule(n_employees, n_shifts) for i in range(100)]
    for i in range(n_generations):
        schedules = [mutate_schedule(s, n_employees) for s in schedules]
        schedules = [(s, evaluate_schedule(s, preferences)) for s in schedules]
        schedules.sort(key=lambda x: x[1], reverse=True)
        schedules = schedules[:50]
    return schedules[0][0]

# 示例：假设有10个员工，7天排班
preferences = [[random.randint(0, 100) for i in range(7)] for j in range(10)]
schedule = genetic_algorithm(preferences, 10, 7, 100)
print(schedule)

该代码的工作原理是：首先随机生成一组排班表，然后在这组排班表上进行多代的进化，每一代中对排班表进行随机变异，再评估每一种排班表的适应性，最终选出适应性最高的排