Python Pivot table透视表使用方法解析

#%%

import pandas as pd

df01 = pd.DataFrame(
  {
    "年份":[2019,2019,2019,2020,2020,2020],
    "平台":["京东","淘宝","拼多多","京东","淘宝","拼多多"],
    "销量":[100,200,300,400,500,600]
  }
)

df01

#%%

pd.pivot(df01,
     index = "年份",
     columns = "平台",
     values = "销量")

#%%

df02 = pd.DataFrame(
  {
    "年份":[2019,2019,2019,2019,2020,2020,2020,2020],
    "平台":["京东","淘宝","淘宝","拼多多","京东","淘宝","拼多多","拼多多"],
    "销量":[100,200,300,400,500,600,700,800]
  }
)
df02
#%%
#pivot_table用的很多.因为可以对重复的元素进行聚合操作.而pivot函数只能对不重复的行进行运算

pd.pivot_table(df02,
        index="年份",
        columns="平台",
        values="销量",
        aggfunc=sum #聚合函数来对销量进行运算.可以指定最大，最小,平均值等函数.默认为mean平均值
)
#%%

#%%
df = pd.read_excel("./datas/result_datas.xlsx",
         ).convert_dtypes()  #读取数据并自动转化type
df.dtypes
#%%
df.head(3)
#%%

#按照自定义指定index,columns,values值
result = pd.pivot_table(df,
        index = ["姓名","服务卡卡号","明细","规格"],
        values = ["理赔金额（元）","数量"],
        aggfunc=sum
        )
result = result.sort_values("服务卡卡号") #按照指定values值排序
result

#%%

#输出到文件
result.to_excel("./datas/output_datas.xlsx")
print("Done!!!")