人工蜂群算法的python代码

以下是一个简单的人工蜂群算法的 Python 代码：

import random
import numpy as np

# 定义问题
def objective(x):
    return x**2 + 5*np.sin(x)

# 定义人工蜂群算法函数
def ABC(obj_func, lb, ub, dim, n_bees, max_it):
    best_sol = None
    best_obj = np.inf
    # 初始化蜜蜂群
    hive = []
    for i in range(n_bees):
        sol = {'position': np.random.uniform(lb, ub, dim)}
        sol['cost'] = obj_func(sol['position'])
        hive.append(sol)
        if sol['cost'] < best_obj:
            best_obj = sol['cost']
            best_sol = sol
    # 开始迭代
    for it in range(max_it):
        # 雇佣蜜蜂阶段
        for i in range(n_bees):
            # 随机选择其它蜜蜂
            k = random.randint(0, n_bees-1)
            while k == i:
                k = random.randint(0, n_bees-1)
            # 生成新解
            phi = np.random.uniform(-1, 1, dim)
            new_pos = hive[i]['position'] + phi * (hive[i]['position'] - hive[k]['position'])
            new_pos = np.clip(new_pos, lb, ub)
            new_cost = obj_func(new_pos)
            # 更新蜜蜂位置
            if new_cost < hive[i]['cost']:
                hive[i]['position'] = new_pos
                hive[i]['cost'] = new_cost
            # 更新最优解
            if hive[i]['cost'] < best_obj:
                best_obj = hive[i]['cost']
                best_sol = hive[i]
        # 侦查蜜蜂阶段
        for i in range(n_bees):
            # 随机生成新解
            new_pos = np.random.uniform(lb, ub, dim)
            new_cost = obj_func(new_pos)
            # 更新蜜蜂位置
            if new_cost < hive[i]['cost']:
                hive[i]['position'] = new_pos
                hive[i]['cost'] = new_cost
            # 更新最优解
            if hive[i]['cost'] < best_obj:
                best_obj = hive[i]['cost']
                best_sol = hive[i]
    return best_sol['position'], best_sol['cost']

# 测试算法
lb = -5
ub = 5
dim = 1
n_bees = 50
max_it = 100
best_pos, best_cost = ABC(objective, lb, ub, dim, n_bees, max_it)
print('最优解:', best_pos)
print('最优值:', best_cost)

注：以上代码仅为示例，实际使用时需要根据具体问题进行适当修改。