一、遗传算法流程图
交叉过程即存在于上图的”交叉“(crossover)步骤中。
二、单点交叉
随机地选择1个交叉位点进行交叉,如下图所示:
用random库实现随机性:
import random
# 简单的单点交叉方式
def sing_muta(list1, list2):
# 假设len(list1) == len(list2)
# 随机选择交叉点
cross_pt = random.randint(0, len(list1) - 2)
list1_cut = list1[cross_pt + 1: len(list1)]
list2_cut = list2[cross_pt + 1: len(list2)]
new_list1 = list1[0: cross_pt + 1]
new_list1.append(list2_cut)
new_list2 = list2[0: cross_pt + 1]
new_list2.append(list1_cut)
return new_list1, new_list2
list1 = [1, 2, 3, 4, 5, 6, 7, 8]
list2 = [10, 20, 30, 40, 50, 60, 70, 80]
for i in range(5):
print(sing_muta(list1, list2))
程序输出(5次交换结果):
三、两点交叉
随机地选择一个交叉起点和一个交叉终点,交换父代两个基因的中间部分,如下图所示:
Python代码:
import random
# 简单的两点交叉方式
def doub_muta(list1, list2):
# 假设len(list1) == len(list2)
# 随机选择起点和终点
new_list1 = list1
new_list2 = list2
cross_begin = random.randint(0, len(list1) - 1)
cross_end = random.randint(0, len(list1) - 1)
if cross_begin == cross_end:
cross_end += 1 # 至少产生1个位点的交换
elif cross_begin > cross_end:
cross_begin, cross_end = cross_end, cross_begin # 结束位点不能在开始位点之前
print(cross_begin, cross_end) # 检查位点
# 切出片段
list1_cut = new_list1[cross_begin: cross_end]
list2_cut = new_list2[cross_begin: cross_end]
new_list1[cross_begin: cross_end] = list2_cut
new_list2[cross_begin: cross_end] = list1_cut
return new_list1, new_list2
for i in range(5):
list1 = [1, 2, 3, 4, 5, 6, 7, 8]
list2 = [10, 20, 30, 40, 50, 60, 70, 80]
print(doub_muta(list1, list2))
程序输出(5次交换结果):