Python Pandas - 创建一个函数来替换重复的 DataFrame

Question

我是 Python 新手，并且已成功构建了以下代码，该代码在四个单独的数据帧中生成所需的结果

import pandas as pd
x2019 = df.Date.between('2015-06-28','2015-07-04') #Transaction Dates we want to analyze
y2019 = df.First_Purchase_Date.between('2014-01-01','2015-07-04') #customer first purchase dates we want to include in the dataset

TABLE_2019_USA_XX = df.loc[x2019 & y2019 & (df['Region'] == 'USA')].groupby(df['FPYear'])[['New Customer', 'Existing Customer', 'revenue']].sum() #with date filters for table
TABLE_2019_USA_XX['TotalCusts'] = TABLE_2019_USA_XX['New Customer'] + TABLE_2019_USA_XX['Existing Customer']

TABLE_2019_CANADA_XX = df.loc[x2019 & y2019 & (df['Region'] == 'Canada')].groupby(df['FPYear'])[['New Customer', 'Existing Customer', 'revenue']].sum() #with date filters for table
TABLE_2019_CANADA_XX['TotalCusts'] = TABLE_2019_CANADA_XX['New Customer'] + TABLE_2019_CANADA_XX['Existing Customer']

x2018 = df.Date.between('2014-07-23','2014-07-28') #Transaction Dates we want to analyze
y2018 = df.First_Purchase_Date.between('2014-01-01','2014-07-30') #customer first purchase dates we want to include in the dataset

TABLE_2018_USA_XX = df.loc[x2018 & y2018 & (df['Region'] == 'USA')].groupby(df['FPYear'])[['New Customer', 'Existing Customer', 'revenue']].sum() #with date filters for table
TABLE_2018_USA_XX['TotalCusts'] = TABLE_2018_USA_XX['New Customer'] + TABLE_2018_USA_XX['Existing Customer']
TABLE_2018_CANADA_XX = df.loc[x2018 & y2018 & (df['Region'] == 'Canada')].groupby(df['FPYear'])[['New Customer', 'Existing Customer', 'revenue']].sum() #with date filters for table
TABLE_2018_CANADA_XX['TotalCusts'] = TABLE_2018_CANADA_XX['New Customer'] + TABLE_2018_CANADA_XX['Existing Customer']

print(TABLE_2018_USA_XX)
print(TABLE_2019_USA_XX)
print(TABLE_2018_CANADA_XX)
print(TABLE_2019_CANADA_XX)

输出

FPYear  New Customer    Existing Customer   revenue TotalCusts
2014    0                     23              134   23
2015    12                    32              432   44


FPYear  New Customer    Existing Customer   revenue TotalCusts
2014    432                   421            4315    853
2015    3415                  452            2341    3867

FPYear  New Customer    Existing Customer   revenue TotalCusts
2014    22                  432              4312    454
2015    33                  345              3415    378

FPYear  New Customer    Existing Customer   revenue TotalCusts
2014    5                   35               4312    40
2015    432                 32               6131    464

根据我所阅读的内容和构建此脚本时得到的反馈，我知道我应该能够使用函数构建上述内容，但我无法确切地弄清楚如何做到这一点。有人可以提供建议让我开始吗？我本质上是在尝试减少我的脚本并使其更加高效。

Answer 1

只需定义一个函数并向参数传递用作过滤器的日期和区域:

import pandas as pd
def process(df, start_dt, end_dt, purch_start, purch_end, region):
    mask_date = df['Date'].between(start_dt, end_dt)
    mask_purch_date = df['First_Purchase_Date'].between(purch_start, purch_end)
    mask_region = df['Region'] == region

    temp_df = df[mask_date & mask_purch_date & mask_region].groupby(df['FPYear'])[['New Customer', 'Existing Customer', 'revenue']].sum()

    temp_df['TotalCusts'] = temp_df['New Customer'] + temp_df['Existing Customer']

    return temp_df


TABLE_2019_USA_XX = process(df,'2015-06-28','2015-07-04', '2014-01-01','2015-07-04', 'USA')

TABLE_2019_CANADA_XX = process(df,'2015-06-28','2015-07-04', '2014-01-01','2015-07-04', 'Canada')

TABLE_2018_USA_XX = process(df,'2014-07-23','2014-07-28', '2014-01-01','2014-07-30', 'USA')

TABLE_2018_CANADA_XX = process(df,'2014-07-23','2014-07-28','2014-01-01','2014-07-30', 'Canada')