目录
#-*- coding:utf-8 -*-
import pandas as pd
import numpy as np
df=pd.DataFrame({
'key1':['a','a','b','b','a'],'key2':['one','two','one','two','one'],
'data1':np.random.randn(5),'data2':np.random.randn(5)})
for name,group in df.groupby('key1'):
print(name) # 'key1'列去重后的结果,去重后为['a', 'b']
print(group)
#结果:
a
##########################################################
data1 data2 key1 key2
0 -1.389589 0.605121 a one
1 0.057731 1.387236 a two
4 0.973961 -1.540356 a one
##########################################################
b
data1 data2 key1 key2
2 -0.476933 -0.110656 b one