利用python Pandas实现批量拆分Excel与合并Excel

work_dir="./course_datas/c15_excel_split_merge"
splits_dir=f"{work_dir}/splits"

import os
if not os.path.exists(splits_dir):
    os.mkdir(splits_dir)

import pandas as pd
No output

df_source = pd.read_excel(f"{work_dir}/crazyant_blog_articles_source.xlsx")
No output

df_source.head()

id	title	tags
0	2585	Tensorflow怎样接收变长列表特征	python,tensorflow,特征工程
1	2583	Pandas实现数据的合并concat	pandas,python,数据分析
2	2574	Pandas的Index索引有什么用途？	pandas,python,数据分析
3	2564	机器学习常用数据集大全	python,机器学习
4	2561	一个数据科学家的修炼路径	数据分析

df_source.index

RangeIndex(start=0, stop=258, step=1)

df_source.shape

total_row_count = df_source.shape[0]
total_row_count

# 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"]
No output

# 每个人的任务数目
split_size = total_row_count // len(user_names)
if total_row_count % len(user_names) != 0:
    split_size += 1

split_size

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存入列表
    df_subs.append((idx, user_name, df_sub))
No output

for idx, user_name, df_sub in df_subs:
    file_name = f"{splits_dir}/crazyant_blog_articles_{idx}_{user_name}.xlsx"
    df_sub.to_excel(file_name, index=False)
No output

import os
excel_names = []
for excel_name in os.listdir(splits_dir):
    excel_names.append(excel_name)
excel_names

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("crazyant_blog_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)

df_merged = pd.concat(df_list)
No output

df_merged.shape

df_merged.head()

df_merged["username"].value_counts()

df_merged.to_excel(f"{work_dir}/crazyant_blog_articles_merged.xlsx", index=False)