普通高中選課數(shù)據(jù)分析和可視化（4）

# 讀文件source_df = pd.read_csv("xk73.csv",sep=',',header='infer',encoding='utf-8')schools = source_df['學(xué)校代碼'].unique() #生成學(xué)校代碼名稱列表
for sch in schools: #遍歷每一所學(xué)校，生成7選3原始報(bào)名數(shù)據(jù)到excel文件    sch_df = source_df[source_df['學(xué)校代碼']==sch]    writer = pd.ExcelWriter(f'各校原始報(bào)名文件\{sch}.xlsx')    sch_df.to_excel(writer,sheet_name='7選3原始數(shù)據(jù)',startcol=0,index=False)    writer.save()    writer.close()

    # 合成學(xué)生選課組合信息    courses = []      for r in sch_df.index:         km = ""        for c in sch_df.columns:            if sch_df.at[r,c] == 1:                km += kms_dic[c]        courses.append(km)    zuhe_df = sch_df.loc[:, ['學(xué)生編號(hào)','學(xué)校代碼','姓名']] #篩選某些行和列    zuhe_df.insert(3, '選課組合', courses) #插入選課組合列    zuhe_df = zuhe_df.sort_values(['選課組合'],ascending=False)        #生成7選3固定班級(jí)名單    kmzh_3_nums = zuhe_df['選課組合'].value_counts()    base = 40  #固定班人數(shù)下限    in_list = [c for c in kmzh_3_nums.index if kmzh_3_nums[c]>=base]    stu_1 = zuhe_df.loc[zuhe_df['選課組合'].isin(in_list)]  #也可以去掉.loc    stu_2 = zuhe_df.loc[~zuhe_df['選課組合'].isin(in_list)] #不在，前面加一個(gè)~

#生成7選2固定班級(jí)名單    kmzh_2_df = pd.DataFrame(columns=stu_2.columns)    kmzh_2_df["組合2"] = ""    base = 40 #固定班人數(shù)下限    for k in kmzh_2:        tmp = stu_2.loc[(stu_2["選課組合"].str.contains(k[0])) & (stu_2["選課組合"].str.contains(k[1]))]        tmp.insert(4, "組合2", [k] * len(tmp))         kmzh_2_df = kmzh_2_df.append(tmp)    kmzh_2_nums = kmzh_2_df['組合2'].value_counts()    in_list = [c for c in kmzh_2_nums.index if kmzh_2_nums[c]>=base]    stu_3 = kmzh_2_df.loc[kmzh_2_df['組合2'].isin(in_list)]  #也可以去掉.loc    stu_4 = kmzh_2_df.loc[~kmzh_2_df['組合2'].isin(in_list)] #不在，前面加一個(gè)~