df = pd.DataFrame(data={'books':['bk1','bk1','bk1','bk2','bk2','bk3'], 'price': [12,12,12,15,15,17]})
df.groupby('books', as_index=True).sum()
df.groupby('books', as_index=False).sum()
import numpy as np
import pandas as pd
df = pd.DataFrame(data={'books': ['bk1', 'bk1', 'bk1', 'bk2', 'bk2', 'bk3'], 'price': [12, 16, 12, 15, 15, 17]})
print(df.head())
c = df.groupby(by=['books'], as_index=False).agg({'price': sum})
# <class 'pandas.core.frame.DataFrame'>
# print(type(c))
print(c)
d = df.groupby(by=['books'], as_index=False).price.mean()
print(d)
groupby分组之后,后面可以跟agg()聚合函数,也可以直接通过“.”的方式获取列属性后,再通过mean()、min()、max()、describe()等方式
f = df.groupby(by=['books'], as_index=True).price.agg(['min', 'max', 'mean'])
print(f)