小学6个年级每个年级1个班有11个老师不同年级有不同科目和指定科目的课时量不同教师有指定课时量一周上5天课每天7节课语数英只排每天前3节里体育不排每天前3节里遗传算法排输出每天每节课课程表到Excel Python代码

以下是一个使用遗传算法生成每天每节课课程表并输出到Excel的Python代码示例：

import random
import numpy as np
import pandas as pd

# 定义问题参数
num_grades = 6  # 年级数量
num_teachers = 11  # 老师数量
num_days = 5  # 每周上课天数
num_periods = 7  # 每天上课节数
num_courses = 5  # 科目数量（不包括语数英和体育）

# 定义每个年级的科目和指定科目的课时量
grade_subjects = {
    1: {'语文': 5, '数学': 4, '英语': 3, '科学': 2, '社会': 2},
    2: {'语文': 5, '数学': 4, '英语': 3, '科学': 2, '社会': 2},
    3: {'语文': 5, '数学': 4, '英语': 3, '科学': 2, '社会': 2},
    4: {'语文': 5, '数学': 4, '英语': 3, '科学': 2, '社会': 2},
    5: {'语文': 5, '数学': 4, '英语': 3, '科学': 2, '社会': 2},
    6: {'语文': 5, '数学': 4, '英语': 3, '科学': 2, '社会': 2}
}

# 定义每个老师的指定课时量
teacher_courses = {
    1: {'语文': 4, '数学': 3, '英语': 3, '科学': 2, '社会': 2},
    2: {'语文': 4, '数学': 3, '英语': 3, '科学': 2, '社会': 2},
    3: {'语文': 4, '数学': 3, '英语': 3, '科学': 2, '社会': 2},
    4: {'语文': 4, '数学': 3, '英语': 3, '科学': 2, '社会': 2},
    5: {'语文': 4, '数学': 3, '英语': 3, '科学': 2, '社会': 2},
    6: {'语文': 4, '数学': 3, '英语': 3, '科学': 2, '社会': 2},
    7: {'语文': 4, '数学': 3, '英语': 3, '科学': 2, '社会': 2},
    8: {'语文': 4, '数学': 3, '英语': 3, '科学': 2, '社会': 2},
    9: {'语文': 4, '数学': 3, '英语': 3, '科学': 2, '社会': 2},
    10: {'语文': 4, '数学': 3, '英语': 3, '科学': 2, '社会': 2},
    11: {'语文': 4, '数学': 3, '英语': 3, '科学': 2, '社会': 2}
}

# 定义遗传算法参数
population_size = 100  # 种群大小
mutation_rate = 0.01  # 变异率
num_generations = 100  # 迭代次数

# 生成初始种群
def generate_population():
    population = []
    for _ in range(population_size):
        chromosome = []
        for _ in range(num_days * num_periods):
            gene = random.randint(0, num_courses + 1)  # 0表示休息，1-5表示科目
            chromosome.append(gene)
        population.append(chromosome)
    return population

# 计算适应度
def calculate_fitness(chromosome):
    conflicts = 0
    schedule = np.array(chromosome).reshape(num_days, num_periods)
    
    # 检查每天每节课的冲突
    for day in range(num_days):
        for period in range(num_periods):
            course = schedule[day][period]
            
            # 检查是否在前3节课里排了语数英
            if period < 3 and (course == 1 or course == 2 or course == 3):
                conflicts += 1
            
            # 检查是否在前3节课里排了体育
            if period < 3 and course == num_courses + 1:
                conflicts += 1
    
    # 检查每个年级各科目的课时量是否满足要求
    for grade in range(1, num_grades + 1):
        grade_schedule = schedule[:, grade-1]
        grade_subject_hours = sum([grade_subjects[grade][subject] for subject in grade_subjects[grade]])
        for subject in grade_subjects[grade]:
            subject_hours = sum(grade_schedule == subject)
            if subject_hours != grade_subjects[grade][subject]:
                conflicts += abs(subject_hours - grade_subjects[grade][subject])
    
    # 检查每个老师的指定课时量是否满足要求
    for teacher in range(1, num_teachers + 1):
        teacher_schedule = schedule[:, teacher-1]
        for subject in teacher_courses[teacher]:
            subject_hours = sum(teacher_schedule == subject)
            if subject_hours != teacher_courses[teacher][subject]:
                conflicts += abs(subject_hours - teacher_courses[teacher][subject])
    
    fitness = 1 / (conflicts + 1)
    return fitness

# 选择操作
def selection(population, fitness_scores):
    selected_indices = np.random.choice(range(population_size), size=population_size, p=fitness_scores/sum(fitness_scores))
    selected_population = [population[i] for i in selected_indices]
    return selected_population

# 交叉操作
def crossover(parent1, parent2):
    crossover_point = random.randint(1, num_days * num_periods - 1)
    child1 = parent1[:crossover_point] + parent2[crossover_point:]
    child2 = parent2[:crossover_point] + parent1[crossover_point:]
    return child1, child2

# 变异操作
def mutate(chromosome):
    for i in range(num_days * num_periods):
        if random.random() < mutation_rate:
            chromosome[i] = random.randint(0, num_courses + 1)
    return chromosome

# 创建课程表
def create_schedule():
    population = generate_population()
    
    for generation in range(num_generations):
        fitness_scores = [calculate_fitness(chromosome) for chromosome in population]
        selected_population = selection(population, fitness_scores)
        
        next_population = []
        while len(next_population) < population_size:
            parent1, parent2 = random.choices(selected_population, k=2)
            child1, child2 = crossover(parent1, parent2)
            next_population.extend([mutate(child1), mutate(child2)])
        
        population = next_population
    
    best_chromosome = max(population, key=calculate_fitness)
    best_schedule = np.array(best_chromosome).reshape(num_days, num_periods)
    
    return best_schedule

# 输出课程表到Excel
def output_schedule(schedule):
    days = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday']
    periods = [f'Period {i+1}' for i in range(num_periods)]
    
    df = pd.DataFrame(schedule, index=days, columns=periods)
    writer = pd.ExcelWriter('schedule.xlsx')
    df.to_excel(writer, sheet_name='Schedule')
    writer.save()

# 主函数
def main():
    schedule = create_schedule()
    output_schedule(schedule)

if __name__ == '__main__':
    main()

请注意，这只是一个示例代码，可能需要根据实际需求进行进一步修改和完善