pandas-09 pd.groupby()的用法
在pandas中的groupby和在sql语句中的groupby有异曲同工之妙，不过也难怪，毕竟关系数据库中的存放数据的结构也是一张大表罢了，与dataframe的形式相似。
import numpy as np
import pandas as pd
from pandas import Series, DataFrame
df = pd.read_csv('./city_weather.csv')
print(df)
'''
date city temperature wind
0 03/01/2016 BJ 8 5
1 17/01/2016 BJ 12 2
2 31/01/2016 BJ 19 2
3 14/02/2016 BJ -3 3
4 28/02/2016 BJ 19 2
5 13/03/2016 BJ 5 3
6 27/03/2016 SH -4 4
7 10/04/2016 SH 19 3
8 24/04/2016 SH 20 3
9 08/05/2016 SH 17 3
10 22/05/2016 SH 4 2
11 05/06/2016 SH -10 4
12 19/06/2016 SH 0 5
13 03/07/2016 SH -9 5
14 17/07/2016 GZ 10 2
15 31/07/2016 GZ -1 5
16 14/08/2016 GZ 1 5
17 28/08/2016 GZ 25 4
18 11/09/2016 SZ 20 1
19 25/09/2016 SZ -10 4
'''
g = df.groupby(df['city'])
# <pandas.core.groupby.groupby.DataFrameGroupBy object at 0x7f10450e12e8>
print(g.groups)
# {'BJ': Int64Index([0, 1, 2, 3, 4, 5], dtype='int64'),
# 'GZ': Int64Index([14, 15, 16, 17], dtype='int64'),
# 'SZ': Int64Index([18, 19], dtype='int64'),
# 'SH': Int64Index([6, 7, 8, 9, 10, 11, 12, 13], dtype='int64')}
print(g.size()) # g.size() 可以统计每个组 成员的 数量
'''
city
BJ 6
GZ 4
SH 8
SZ 2
dtype: int64
'''
print(g.get_group('BJ')) # 得到 某个 分组
'''
date city temperature wind
0 03/01/2016 BJ 8 5
1 17/01/2016 BJ 12 2
2 31/01/2016 BJ 19 2
3 14/02/2016 BJ -3 3
4 28/02/2016 BJ 19 2
5 13/03/2016 BJ 5 3
'''
df_bj = g.get_group('BJ')
print(df_bj.mean()) # 对这个 分组 求平均
'''
temperature 10.000000
wind 2.833333
dtype: float64
'''
# 直接使用 g 对象，求平均值
print(g.mean()) # 对 每一个 分组， 都计算分组
'''
temperature wind
city
BJ 10.000 2.833333
GZ 8.750 4.000000
SH 4.625 3.625000
SZ 5.000 2.500000
'''
print(g.max())
'''
date temperature wind
city
BJ 31/01/2016 19 5
GZ 31/07/2016 25 5
SH 27/03/2016 20 5
SZ 25/09/2016 20 4
'''
print(g.min())
'''
date temperature wind
city
BJ 03/01/2016 -3 2
GZ 14/08/2016 -1 2
SH 03/07/2016 -10 2
SZ 11/09/2016 -10 1
'''
# g 对象还可以使用 for 进行循环遍历
for name, group in g:
print(name)
print(group)
# g 可以转化为 list类型， dict类型
print(list(g)) # 元组第一个元素是 分组的label，第二个是dataframe
'''
[('BJ', date city temperature wind
0 03/01/2016 BJ 8 5
1 17/01/2016 BJ 12 2
2 31/01/2016 BJ 19 2
3 14/02/2016 BJ -3 3
4 28/02/2016 BJ 19 2
5 13/03/2016 BJ 5 3),
('GZ', date city temperature wind
14 17/07/2016 GZ 10 2
15 31/07/2016 GZ -1 5
16 14/08/2016 GZ 1 5
17 28/08/2016 GZ 25 4),
('SH', date city temperature wind
6 27/03/2016 SH -4 4
7 10/04/2016 SH 19 3
8 24/04/2016 SH 20 3
9 08/05/2016 SH 17 3
10 22/05/2016 SH 4 2
11 05/06/2016 SH -10 4
12 19/06/2016 SH 0 5
13 03/07/2016 SH -9 5),
('SZ', date city temperature wind
18 11/09/2016 SZ 20 1
19 25/09/2016 SZ -10 4)]
'''
print(dict(list(g))) # 返回键值对，值的类型是 dataframe
'''
{'SH': date city temperature wind
6 27/03/2016 SH -4 4
7 10/04/2016 SH 19 3
8 24/04/2016 SH 20 3
9 08/05/2016 SH 17 3
10 22/05/2016 SH 4 2
11 05/06/2016 SH -10 4
12 19/06/2016 SH 0 5
13 03/07/2016 SH -9 5,
'SZ': date city temperature wind
18 11/09/2016 SZ 20 1
19 25/09/2016 SZ -10 4,
'GZ': date city temperature wind
14 17/07/2016 GZ 10 2
15 31/07/2016 GZ -1 5
16 14/08/2016 GZ 1 5
17 28/08/2016 GZ 25 4,
'BJ': date city temperature wind
0 03/01/2016 BJ 8 5
1 17/01/2016 BJ 12 2
2 31/01/2016 BJ 19 2
3 14/02/2016 BJ -3 3
4 28/02/2016 BJ 19 2
5 13/03/2016 BJ 5 3}
'''