Pandas数据分析之批量拆分/合并Excel

work_dir="./datas"
splits_dir=f"{work_dir}/splits"
import os
if not os.path.exists(splits_dir):
    os.mkdir(splits_dir)

#0.读取源Excel到Pandas
import pandas as pd
df_source=pd.read_excel(f"{work_dir}/1.xlsx")
df_source.head()

df_source.index

df_source.shape

total_row_count=df_source.shape[0]
total_row_count

#1.计算拆分后的每个excel的行数
#这个大excel，会拆分给这几个人
user_names=['xiao_shuai',"xiao_wang","xiao_ming","xiao_lei","xiao_bo","xiao_hong"]
#每个人的人数数目
split_size=total_row_count//len(user_names)
if total_row_count%len(user_names)!=0:
    split_size+=1
split_size

#拆分成多个dataframe
df_subs=[]
for idx,user_name in enumerate(user_names):
    #iloc的开始索引
    begin=idx*split_size
    #iloc的结束索引
    end=begin+split_size
    #实现df按照iloc拆分
    df_sub=df_source.iloc[begin:end]
    #将每个子df存入到列表
    df_subs.append((idx,user_name,df_sub))

#3. 将每个dataframe存入到excel
for idx,user_name,df_sub in df_subs:
    file_name=f"{splits_dir}/articles_{idx}_{user_name}.xlsx"
    df_sub.to_excel(file_name,index=False)

#1.遍历文件夹，得到要合并的Excel名称列表
import os
excel_names=[]
for excel_name in os.listdir(splits_dir):
    excel_names.append(excel_name)
excel_names

#2分别读取到dataframe
df_list=[]
for excel_name in excel_names:
    #读取每个excel到df
    excel_path=f"{splits_dir}/{excel_name}"
    df_split=pd.read_excel(excel_path)
    #得到username
    username=excel_name.replace("articles_","").replace(".xlsx","")[2:]
    print(excel_name,username)
    #给每个df添加1列，即用户名字
    df_split["username"]=username
    df_list.append(df_split)

#3.使用pd.concat进行合并
df_merged=pd.concat(df_list)

df_merged.shape

df_merged.head()

df_merged["username"].value_counts()
#4.将合并后的dataframe输出到excel
df_merged.to_excel(f"{work_dir}/result_merged.xlsx",index=False)