import pandas as pd
import numpy as np
from collections import defaultdict
import math
import random

classClassDivider:def__init__(self, data_path, class_count):"""        初始化分班器        :param data_path: 学生数据Excel路径        :param class_count: 需要划分的班级数量        """
        self.df = pd.read_excel(data_path)
        self.class_count = class_count
        self.classes ={i:[]for i inrange(1, class_count+1)}defintelligent_division(self, gender_balance=True, subject_weights=None, balance_subjects=None):"""        智能分班算法        :param gender_balance: 是否平衡性别比例        :param subject_weights: 学科权重字典 (e.g. {'数学':0.7, '语文':0.3})        :param balance_subjects: 需要平衡的学科列表        """# 预处理数据
        self._preprocess_data(subject_weights, balance_subjects)# 初始化班级容器
        class_stats ={
            cid:{'students':[],'gender_count':{'男':0,'女':0},'scores_sum':{subj:0for subj in self.subjects},'score_avg':{}}for cid in self.classes.keys()}# 按综合成绩排序
        sorted_students = self.df.sort_values('综合成绩', ascending=False).to_dict('records')# 蛇形分班算法（确保成绩均衡）for i, student inenumerate(sorted_students):
            class_id =(i % self.class_count)+1if i // self.class_count %2==1:# 反向填充
                class_id = self.class_count -(i % self.class_count)# 添加学生到班级
            class_stats[class_id]['students'].append(student['姓名'])
            class_stats[class_id]['gender_count'][student['性别']]+=1# 更新学科总分for subj in self.subjects:
                class_stats[class_id]['scores_sum'][subj]+= student[subj]# 平衡调整算法
        self._balance_adjustment(class_stats, sorted_students, gender_balance)# 计算班级统计数据
        self._calculate_class_stats(class_stats)# 保存结果
        self.class_stats = class_stats
    
    def_preprocess_data(self, weights, balance_subjects):"""数据预处理"""# 确定需要平衡的学科
        self.subjects = balance_subjects or[col for col in self.df.columns if col notin['姓名','性别']]# 计算综合成绩（加权）if weights:
            self.df['综合成绩']=0for subject, weight in weights.items():if subject in self.df.columns:
                    self.df['综合成绩']+= self.df[subject]* weight
        else:
            self.df['综合成绩']= self.df[self.subjects].mean(axis=1)def_balance_adjustment(self, class_stats, students, gender_balance):"""平衡调整算法"""
        MAX_ITERATIONS =1000for _ inrange(MAX_ITERATIONS):# 计算当前班级差异
            imbalances = self._calculate_imbalances(class_stats)# 检查是否达到平衡标准ifall(diff <1.0for diff in imbalances.values()):break# 寻找最不均衡的学科
            worst_subject =max(imbalances, key=imbalances.get)# 找出需要调整的学生for class_id in class_stats:for other_id in class_stats:if class_id == other_id:continue# 尝试交换学生
                    self._try_swap_students(class_id, other_id, 
                                            class_stats, students, 
                                            worst_subject, gender_balance)def_try_swap_students(self, c1, c2, stats, students, subject, gender_balance):"""尝试交换两个班级的学生"""# 获取班级学生名单
        c1_students = stats[c1]['students']
        c2_students = stats[c2]['students']# 找出可能交换的学生对for s1 in c1_students:for s2 in c2_students:# 获取学生完整数据
                stu1 =next((s for s in students if s['姓名']== s1),None)
                stu2 =next((s for s in students if s['姓名']== s2),None)ifnot stu1 ornot stu2:continue# 检查性别约束if gender_balance and stu1['性别']!= stu2['性别']:continue# 计算交换前后差异
                before_diff =abs(stats[c1]['scores_sum'][subject]- stats[c2]['scores_sum'][subject])# 模拟交换
                temp_sum_c1 = stats[c1]['scores_sum'][subject]- stu1[subject]+ stu2[subject]
                temp_sum_c2 = stats[c2]['scores_sum'][subject]- stu2[subject]+ stu1[subject]
                after_diff =abs(temp_sum_c1 - temp_sum_c2)# 如果交换后更平衡，则执行交换if after_diff < before_diff:# 执行交换
                    stats[c1]['students'].remove(s1)
                    stats[c2]['students'].remove(s2)
                    stats[c1]['students'].append(s2)
                    stats[c2]['students'].append(s1)# 更新分数总和
                    stats[c1]['scores_sum'][subject]= temp_sum_c1
                    stats[c2]['scores_sum'][subject]= temp_sum_c2
                    
                    # 更新性别统计if gender_balance:
                        stats[c1]['gender_count'][stu1['性别']]-=1
                        stats[c1]['gender_count'][stu2['性别']]+=1
                        stats[c2]['gender_count'][stu2['性别']]-=1
                        stats[c2]['gender_count'][stu1['性别']]+=1returnTruereturnFalsedef_calculate_imbalances(self, class_stats):"""计算班级间的不平衡度"""
        imbalances ={}for subject in self.subjects:
            subject_scores =[stats['scores_sum'][subject]/len(stats['students'])for stats in class_stats.values()]
            max_avg =max(subject_scores)
            min_avg =min(subject_scores)
            imbalances[subject]= max_avg - min_avg
        return imbalances
    
    def_calculate_class_stats(self, class_stats):"""计算班级统计数据"""for cid, stats in class_stats.items():
            student_count =len(stats['students'])
            stats['gender_ratio']={
                g: c/student_count for g, c in stats['gender_count'].items()}
            stats['score_avg']={
                subj: stats['scores_sum'][subj]/student_count 
                for subj in self.subjects
            }defexport_to_excel(self, output_path):"""导出分班结果到Excel"""with pd.ExcelWriter(output_path)as writer:# 创建班级明细表for cid, stats in self.class_stats.items():
                class_df = pd.DataFrame({'学号':range(1,len(stats['students'])+1),'姓名': stats['students'],'性别':[self.df[self.df['姓名']==name]['性别'].values[0]for name in stats['students']]})for subject in self.subjects:
                    class_df[subject]=[self.df[self.df['姓名']==name][subject].values[0]for name in stats['students']]
                class_df.to_excel(writer, sheet_name=f'班级{cid}', index=False)# 创建统计汇总表
            summary_data =[]for cid, stats in self.class_stats.items():
                row ={'班级': cid,'人数':len(stats['students'])}
                row.update(stats['gender_count'])for subject, avg in stats['score_avg'].items():
                    row[f'{subject}均分']=round(avg,2)
                summary_data.append(row)
            
            summary_df = pd.DataFrame(summary_data)
            summary_df.to_excel(writer, sheet_name='班级汇总', index=False)# 添加全局统计
            global_stats =[]for subject in self.subjects:
                row ={'学科': subject}
                class_avgs =[stats['score_avg'][subject]for stats in self.class_stats.values()]
                row['最高均分']=max(class_avgs)
                row['最低均分']=min(class_avgs)
                row['极差']= row['最高均分']- row['最低均分']
                global_stats.append(row)
            
            global_df = pd.DataFrame(global_stats)
            global_df.to_excel(writer, sheet_name='全局统计', index=False)# 使用示例if __name__ =="__main__":# 初始化分班器 (10个班级)
    divider = ClassDivider("students.xlsx", class_count=10)# 执行分班 (平衡性别，数学权重70%，语文30%，平衡所有学科)
    divider.intelligent_division(
        gender_balance=True,
        subject_weights={'数学':0.7,'语文':0.3},
        balance_subjects=['数学','语文','英语','物理'])# 导出结果
    divider.export_to_excel("分班结果.xlsx")