合并多个工作表 | 易学教程

由于要连接四年的excel数据文件，为了节省时间，自己写了一段代码，虽然这只是我在工作中遇到的一个小的知识点，但是我希望把这记录下来，以免以后会有相同的处理，可以大大提升我们的工作效率。有需要的可以看一下

import xlrd
import pandas as pd
import time

filename = ['本地户存活周期研究(2015-08-01至2016-07-31)', '本地户存活周期研究(2016-08-01至2017-07-31)',
            '本地户存活周期研究(2017-08-01至2018-07-31)', '本地户存活周期研究(2018-08-01至2019-07-31)']
desktop_root_direct = "C:/Users/liuqiping/Desktop/"

def read_data():    # 读取Excel数据
    data_list = []
    for file in filename:
        workbook = xlrd.open_workbook(desktop_root_direct+file+".xlsx")
        worksheet = workbook.sheet_by_index(0)
        nrows = worksheet.nrows
        ncols = worksheet.ncols
        print(nrows, ncols)
        dicts = {}
        for colnum in range(0, ncols):
            coldata = worksheet.col_values(colnum)
            dicts[coldata[0]] = coldata[1:]
        data_list.append(dicts)
    return data_list

def merge_data(data_list):  # 利用pd.merge()函数合并filename文件数据
    left = pd.DataFrame(data_list[0])
    result = 0
    for i in range(1, len(data_list)):
        right = pd.DataFrame(data_list[i])
        result = pd.merge(left, right, how="outer",
                          on=["账户ID", "账户名称", "账户一级行业", "账户二级行业", "账户三级行业", "账号", "首次消费日", "注册日期", "分析行业"])
        left = result
    result_df = pd.DataFrame(result)
    result_df.to_excel(desktop_root_direct+"本地户存活周期研究_合并结果.xlsx", index=False)

if __name__ == '__main__':
    start = time.time()
    data_list = read_data()
    merge_data(data_list)
    end = time.time()
    print("程序运行时间："+str(end-start))

来源：CSDN

作者：liu_qiping

链接：https://blog.csdn.net/liu_qiping/article/details/103455583

标签