图片进化（待完成）

import random
from PIL import Image
from copy import deepcopy


img_chrome = Image.open('chrome.png')
h_chrome = img_chrome.size[1]
w_chrome = img_chrome.size[0]


img = Image.open('test1.png')
h = img.size[1]
w = img.size[0]


img_color = []
img_color_chrome = []


def info_pic():  # 获取图片信息

    for x in range(w):

        img_color_tmp = []  # 先获得每一列rgb信息
        for y in range(h):

            r, g, b = img.getpixel((x, y))[:3]
            # print(r,g,b)
            img_color_tmp.append([r, g, b])
        img_color.append(img_color_tmp)

    print(img_color)
    print(img.size)
    return img_color, img.size


def info_chrome():  # 获取图片信息

    for x in range(w_chrome):

        img_color_tmp = []  # 先获得每一列rgb信息
        for y in range(h_chrome):

            r, g, b = img_chrome.getpixel((x, y))[:3]
            # print(r,g,b)
            img_color_tmp.append([r, g, b])
        img_color_chrome.append(img_color_tmp)

    # print(img_color_chrome)
    print(img_chrome.size)
    return img_color_chrome, img_chrome.size


# info_chrome()
# print(img_color_chrome[10][10][0])

population = []


def initial_population(number=300):  # 编码

    for i in range(number):
        chromosome = []
        for x in range(w):
            row = []
            for y in range(h):
                r = random.randint(0, 255)
                g = random.randint(0, 255)
                b = random.randint(0, 255)
                row.append([r, g, b])
            chromosome.append(row)
        population.append(chromosome)
    print("随机基因初始化完成")
    return population

# initial_population()
# info_chrome()


def fitness(chromosome):  # 计算适应度函数
    print("开始处理基因")
    
    diff = 0
    # for index1, item1 in enumerate(population):

    for index2, item2 in enumerate(chromosome):  # chromosome , index2表示图片的第几列

            for index3, item3 in enumerate(item2):  # row，index3表示某一列的第几行

                for index4, item4 in enumerate(item3):  # 像素值，index4表示rgb的位置
                    

                    diff += abs(img_color_chrome[index2][index3][index4]-item4)
    print(diff)
    return diff

def population_fitness(population):
    for index1, item1 in enumerate(population):
        fitness(item1)


# fitness(population[1])

class ga(object):
    def __init__(self,population):
        pass

    def evolution(self, retain_rate=0.3, random_select_rate=0.5, mutation_rate=0.01):
        """
        对当前种群依次进行选择、交叉并生成新一代种群，然后对新一代种群进行变异
        """
        parents = self.selection(retain_rate, random_select_rate)
        self.crossover(parents)
        self.mutation(mutation_rate)

    def selection(self, retain_rate, random_select_rate):
        graded = [(fitness(chromosome), chromosome) for chromosome in population]
        sort = [x[1] for x in sorted(graded)]  # 正向排序
        retain_length = int(len(sort) * retain_rate)
        # 选出适应性强的个体，精英选择
        parents = sort[:retain_length]
        for chromosome in sort[retain_length:]:
            if random.random() < random_select_rate:
                parents.append(chromosome)
        return parents

    def crossover(self, parents,population):  # 交叉
        children = []
        # 需要繁殖的子代数量
        target_number = len(population) - len(parents)
        # 开始繁殖
        while len(children) < target_number:
            father = random.randint(0, len(parents) - 1)  # 选择交叉父代
            mother = random.randint(0, len(parents) - 1)  # 选择交叉母代
            if father != mother:
                # 随机选取交叉点
                cross_point_x = random.randint(0, w)
                cross_point_y = random.randint(0, h)

                new_gene = deepcopy(population[father][0][:cross_point_x])
                new_gene = [new_gene, 0]
                new_gene[0][cross_point_x:] = deepcopy(population[mother][0][cross_point_x:])
                new_gene[0][cross_point_x][:cross_point_y] = deepcopy(population[father][0][cross_point_x][:cross_point_y])
            children.append(new_gene)
                # 经过繁殖后，孩子和父母的数量与原始种群数量相等，在这里可以更新种群。
        population = parents + children

    def variation(genes, size):
        rate = 0.5
        print("开始变异")
        for i, gene in enumerate(genes):
            for x, row in enumerate(gene[0]):
                for y, col in enumerate(row):
                    if random.randint(1, 100) / 100 <= rate:
                        # 图片由 r g b 三种颜色混合而成 变异就是改变他们的值
                        # a b c 分别对应 r_ g_ b_ 改变的值 可自行修改
                        # r g b 的最大值为255
                        # ------------------------------请修改这里-------------------------------------#
                        a = [-1, 1][random.randint(0, 1)] * random.randint(3, 10)
                        b = [-1, 1][random.randint(0, 1)] * random.randint(3, 10)
                        c = [-1, 1][random.randint(0, 1)] * random.randint(3, 10)
                        # ------------------------------请修改这里-------------------------------------#
                        genes[i][0][x][y][0] += a
                        genes[i][0][x][y][0] += b
                        genes[i][0][x][y][0] += c
                        genes[i][0][x][y][3] += a + b + c
        print("变异结束")

    def result(self):
        '''
        获得近优值
        '''
        graded = [(self.fitness_function(chromosome), chromosome) for chromosome in self.population]
        graded = [x[1] for x in sorted(graded, reverse=True)]
        # print('近优的x值为：', self.decode(graded[0]),
        #       '近优的y值为：', self.fitness_function(graded[0]))
        # 将每一步迭代的结果存储到列表中
        y_label.append(self.fitness_function(graded[0]))
        return self.decode(graded[0])

    def iteration(self, iter_number):
        for i in range(iter_number):
            self.evolution()
            self.result()
            x_label.append(i)