我就废话不多说了,大家还是直接看代码吧!
# -*- encoding=utf-8 -*-
import pandas as pd
data=['abc','abc','abc','asc','ase','ase','ase']
num=[1,2,2,1,2,1,2]
df1=pd.DataFrame({'name':data,'num':num})
print(df1)
df1['mmm']=df1['num']
df2=df1.groupby(['name', 'num'], as_index=False).count()
print(df2)
df2.sort_values(['name', 'num'], ascending=[1, 1], inplace=True)
print(df2)
df2['sum']=df2.groupby(['name'])['mmm'].cumsum()
print(df2)
kk=df2.groupby(['name'],as_index=False)['num'].sum()
print(kk)
df3 = pd.merge(df2, kk, on='name', how='left',)
print(df3)
df3['ratio']=df3['sum']/df3['num_y']
df3.columns = ['name', 'num', 'mmm', 'sum','numsum','ratio']
print(df3)
df4&#