In [1]:

import pandas as pd
import numpy as np
df=pd.DataFrame({'A':['foo','bar','foo','bar',
                     'foo','bar','foo','foo'],
                 'B':['one','one','two','three',
                     'two','two','one','three'],
                 'C':np.random.randn(8),
                 'D':np.random.randn(8)})#randn=>具有标准正态分布
df

Out[1]:

	A	B	C	D
0	foo	one	1.126165	-0.676814
1	bar	one	-1.429697	-0.464149
2	foo	two	-0.383661	-0.309679
3	bar	three	0.945099	1.375307
4	foo	two	-0.296882	-0.630503
5	bar	two	2.526570	-1.142886
6	foo	one	-0.848323	-0.310705
7	foo	three	-1.683177	-1.371868

In [2]:

grouped=df.groupby('A')
grouped

Out[2]:

<pandas.core.groupby.generic.DataFrameGroupBy object at 0x00000000052092B0>

In [3]:

grouped.count()#统计次数

Out[3]:

	B	C	D
A
bar	3	3	3
foo	5	5	5

In [4]:

grouped=df.groupby(['A','B'])#索引多项
grouped.count()

Out[4]:

		C	D
A	B
bar	one	1	1
	three	1	1
	two	1	1
foo	one	2	2
	three	1	1
	two	2	2

In [5]:

def get_letter_type(letter):
    if letter.lower() in 'aeiou':
        return 'a'
    else:
        return 'b'
grouped=df.groupby(get_letter_type,axis=1)
grouped.count().iloc[0]

Out[5]:

a    1
b    3
Name: 0, dtype: int64

In [6]:

s=pd.Series([1,2,3,1,2,3],[8,7,6,8,7,6])
s

Out[6]:

8    1
7    2
6    3
8    1
7    2
6    3
dtype: int64

1.指定多个索引的多个操作

In [7]:

grouped=s.groupby(level=0)#默认从0开始
grouped.first()#索引的第一部分，自动去除重复部分；也可以指定last()

Out[7]:

6    3
7    2
8    1
dtype: int64

In [8]:

grouped.sum()

Out[8]:

6    6
7    4
8    2
dtype: int64

In [9]:

grouped=s.groupby(level=0,sort=False)
grouped.first()

Out[9]:

8    1
7    2
6    3
dtype: int64

2.单独索引某一列的某一个元素:多重索引

In [10]:

df2=pd.DataFrame({'X':['A','B','A','B'],'Y':[1,2,3,4]})
df2

Out[10]:

	X	Y
0	A	1
1	B	2
2	A	3
3	B	4

2-1 多重所以方法一

In [11]:

df2.groupby(['X']).get_group('A')#关注具体的某一个键值

Out[11]:

	X	Y
0	A	1
2	A	3

2-2 多重所以方法二

In [12]:

arrays=[['foo','bar','foo','bar', 'foo','bar','foo','foo'],
         ['one','one','two','three','two','two','one','three']]
index=pd.MultiIndex.from_arrays(arrays,names=['first','second'])#添加索引名字
s=pd.Series(np.random.randn(8),index=index)#对索引键来添加值
s

Out[12]:

first  second
foo    one      -0.518263
bar    one       0.583992
foo    two       1.338273
bar    three    -0.671916
foo    two       0.633448
bar    two       0.144302
foo    one       0.828419
       three    -0.834918
dtype: float64

In [13]:

grouped=s.groupby(level=0)#索引第一列
grouped.sum()

Out[13]:

first
bar    0.056377
foo    1.446958
dtype: float64

In [14]:

grouped=s.groupby(level='second')#索引第二列，也可以指定名字
grouped.sum()

Out[14]:

second
one      0.894148
three   -1.506835
two      2.116022
dtype: float64

3 aggregate:以A B为键求和

In [15]:

grouped=df.groupby(['A','B'])
grouped.aggregate(np.sum)

Out[15]:

		C	D
A	B
bar	one	-1.429697	-0.464149
	three	0.945099	1.375307
	two	2.526570	-1.142886
foo	one	0.277842	-0.987519
	three	-1.683177	-1.371868
	two	-0.680543	-0.940182

In [16]:

grouped=df.groupby(['A','B'],as_index=False)#as_index=False ：不去除重复的行，是一行行索引
grouped.aggregate(np.sum)

Out[16]:

	A	B	C	D
0	bar	one	-1.429697	-0.464149
1	bar	three	0.945099	1.375307
2	bar	two	2.526570	-1.142886
3	foo	one	0.277842	-0.987519
4	foo	three	-1.683177	-1.371868
5	foo	two	-0.680543	-0.940182

In [17]:

grouped=df.groupby(['A','B']).sum().reset_index()#重新构建索引
grouped

Out[17]:

	A	B	C	D
0	bar	one	-1.429697	-0.464149
1	bar	three	0.945099	1.375307
2	bar	two	2.526570	-1.142886
3	foo	one	0.277842	-0.987519
4	foo	three	-1.683177	-1.371868
5	foo	two	-0.680543	-0.940182

In [18]:

grouped=df.groupby(['A','B'])
grouped.size()#统计出现次数

Out[18]:

A    B    
bar  one      1
     three    1
     two      1
foo  one      2
     three    1
     two      2
dtype: int64

7.得出统计特性值

In [19]:

grouped.describe().head()

Out[19]:

		C								D
		count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max
A	B
bar	one	1.0	-1.429697	NaN	-1.429697	-1.429697	-1.429697	-1.429697	-1.429697	1.0	-0.464149	NaN	-0.464149	-0.464149	-0.464149	-0.464149	-0.464149
	three	1.0	0.945099	NaN	0.945099	0.945099	0.945099	0.945099	0.945099	1.0	1.375307	NaN	1.375307	1.375307	1.375307	1.375307	1.375307
	two	1.0	2.526570	NaN	2.526570	2.526570	2.526570	2.526570	2.526570	1.0	-1.142886	NaN	-1.142886	-1.142886	-1.142886	-1.142886	-1.142886
foo	one	2.0	0.138921	1.396174	-0.848323	-0.354701	0.138921	0.632543	1.126165	2.0	-0.493760	0.258878	-0.676814	-0.585287	-0.493760	-0.402232	-0.310705
foo	three	1.0	-1.683177	NaN	-1.683177	-1.683177	-1.683177	-1.683177	-1.683177	1.0	-1.371868	NaN	-1.371868	-1.371868	-1.371868	-1.371868	-1.371868

得出指定的统计指标 agg操作

In [20]:

grouped=df.groupby('A')
grouped['C'].agg([np.sum,np.mean,np.std])

Out[20]:

	sum	mean	std
A
bar	2.041972	0.680657	1.991346
foo	-2.085878	-0.417176	1.023003

In [21]:

grouped['C'].agg({'sum1':np.sum,'mean1':np.mean,'std1':np.std})#改名字

3-11 group操作拓展

参与评论

评论留言

还没有评论留言，赶紧来抢楼吧~~

给这篇文章打个标签吧~