pandas_2

import pandas as pd
import numpy as np
import pandas as pd
import numpy as np
s
s = pd.Series(np.random.rand(5),index=list('abcde'))
s
a    0.272040
b    0.867085
c    0.850881
d    0.467187
e    0.115594
dtype: float64
s.index
s.index
Index(['a', 'b', 'c', 'd', 'e'], dtype='object')
ha
s.index.name = 'alpha'
s
s
alpha
a    0.272040
b    0.867085
c    0.850881
d    0.467187
e    0.115594
dtype: float64
n
df = pd.DataFrame(np.random.randn(4,3),columns=['one','two','three'])
df
one	two	three
0	-1.756171	1.211440	0.721272
1	-0.240596	0.885698	0.430981
2	-1.337347	-0.296998	-0.012915
3	-1.688144	0.821678	0.419868
df.index
df.index
RangeIndex(start=0, stop=4, step=1)
df.columns
df.columns
Index(['one', 'two', 'three'], dtype='object')
o
df.index.name='row'
s
df.columns.name='col'
df
col	one	two	three
row			
0	-1.756171	1.211440	0.721272
1	-0.240596	0.885698	0.430981
2	-1.337347	-0.296998	-0.012915
3	-1.688144	0.821678	0.419868
)
s = pd.Series(np.arange(6),index = list('abcbda'))
s
s
a    0
b    1
c    2
b    3
d    4
a    5
dtype: int32
a
s['a']
a    0
a    5
dtype: int32
s.index.is_unique
False
s.index.unique()
Index(['a', 'b', 'c', 'd'], dtype='object')
s.unique()
array([0, 1, 2, 3, 4, 5], dtype=int64)
求和
s.groupby(s.index).sum()#分组求和
a    5
b    4
c    2
d    4
dtype: int32
分组计算
df = pd.DataFrame({'key1':['a','a','b','b','a'],
                  'key2':['one','two','one','two','one'],
                  'data1':np.random.randint(1,10,5),
                          'data2':np.random.randint(1,10,5)})
f
df
key1	key2	data1	data2
0	a	one	9	1
1	a	two	3	9
2	b	one	5	8
3	b	two	1	1
4	a	one	5	8
df['data1'].groupby(df['key1']).mean()
key1
a    5.666667
b    3.000000
Name: data1, dtype: float64
oup
for name,group in df.groupby('key1'):
    print(name)
    print(group)
a
  key1 key2  data1  data2
0    a  one      9      1
1    a  two      3      9
4    a  one      5      8
b
  key1 key2  data1  data2
2    b  one      5      8
3    b  two      1      1
list(df.groupby('key1')
dict(list(df.groupby('key1')))
{'a':   key1 key2  data1  data2
 0    a  one      9      1
 1    a  two      3      9
 4    a  one      5      8, 'b':   key1 key2  data1  data2
 2    b  one      5      8
 3    b  two      1      1}
)
list(df.groupby('key1'))
[('a',   key1 key2  data1  data2
  0    a  one      9      1
  1    a  two      3      9
  4    a  one      5      8), ('b',   key1 key2  data1  data2
  2    b  one      5      8
  3    b  two      1      1)]
聚合函数
grouped.agg(['std','mean','sum',('range',oeak_range)])
d = {'data1':'mean',
    'data2':'sum'}
grouped.agg(d)#对不同的数据采用不同的聚合函数
时间序列
from datetime import timedelta
from datetime import datetime
from datetime import timedelta
now = datetime.now()
now
datetime.datetime(2020, 8, 21, 17, 43, 51, 104762)
now.year,now.month,now.day
now.year,now.month,now.day
(2020, 8, 21)
-now
date1 = datetime(2020,10,16)-now
date1
date1
datetime.timedelta(days=55, seconds=22568, microseconds=895238)
date1
str(date1)
'55 days, 6:16:08.895238'
now.strftime('%Y/%m/%d %H:%M:%S')
now.strftime('%Y/%m/%d %H:%M:%S')
'2020/08/21 17:43:51'
pd.period_range('2016-01','2016-12',freq='M')
pd.period_range('2016-01','2016-12',freq='M')
PeriodIndex(['2016-01', '2016-02', '2016-03', '2016-04', '2016-05', '2016-06',
             '2016-07', '2016-08', '2016-09', '2016-10', '2016-11', '2016-12'],
            dtype='period[M]', freq='M')
Q
pd.period_range('2016Q1',periods=10,freq='Q')
PeriodIndex(['2016Q1', '2016Q2', '2016Q3', '2016Q4', '2017Q1', '2017Q2',
             '2017Q3', '2017Q4', '2018Q1', '2018Q2'],
            dtype='period[Q-DEC]', freq='Q-DEC')

import datetime as datetime
import numpy as np
import pandas as pd
import numpy as np
ts
ts = pd.Series(np.random.randint(0,50,60),index = pd.date_range('2016-04-25 09:30',periods=60,freq = 'T'))
ts
2016-04-25 09:30:00    45
2016-04-25 09:31:00    37
2016-04-25 09:32:00    39
2016-04-25 09:33:00    47
2016-04-25 09:34:00     1
2016-04-25 09:35:00    46
2016-04-25 09:36:00    31
2016-04-25 09:37:00     8
2016-04-25 09:38:00     2
2016-04-25 09:39:00    40
2016-04-25 09:40:00    43
2016-04-25 09:41:00    19
2016-04-25 09:42:00     0
2016-04-25 09:43:00    17
2016-04-25 09:44:00     7
2016-04-25 09:45:00    45
2016-04-25 09:46:00     3
2016-04-25 09:47:00    23
2016-04-25 09:48:00    35
2016-04-25 09:49:00    38
2016-04-25 09:50:00    18
2016-04-25 09:51:00     2
2016-04-25 09:52:00    42
2016-04-25 09:53:00    39
2016-04-25 09:54:00     1
2016-04-25 09:55:00    26
2016-04-25 09:56:00     8
2016-04-25 09:57:00    35
2016-04-25 09:58:00    34
2016-04-25 09:59:00    18
2016-04-25 10:00:00    37
2016-04-25 10:01:00    28
2016-04-25 10:02:00    45
2016-04-25 10:03:00    20
2016-04-25 10:04:00    46
2016-04-25 10:05:00    30
2016-04-25 10:06:00    14
2016-04-25 10:07:00    23
2016-04-25 10:08:00    12
2016-04-25 10:09:00     7
2016-04-25 10:10:00    29
2016-04-25 10:11:00     0
2016-04-25 10:12:00     1
2016-04-25 10:13:00    15
2016-04-25 10:14:00    20
2016-04-25 10:15:00    20
2016-04-25 10:16:00     6
2016-04-25 10:17:00    30
2016-04-25 10:18:00    48
2016-04-25 10:19:00    28
2016-04-25 10:20:00    45
2016-04-25 10:21:00    15
2016-04-25 10:22:00    24
2016-04-25 10:23:00    14
2016-04-25 10:24:00    45
2016-04-25 10:25:00     3
2016-04-25 10:26:00    38
2016-04-25 10:27:00    46
2016-04-25 10:28:00    29
2016-04-25 10:29:00    44
Freq: T, dtype: int32
ts.resample('5min').sum()#重采样
2016-04-25 09:30:00    169
2016-04-25 09:35:00    127
2016-04-25 09:40:00     86
2016-04-25 09:45:00    144
2016-04-25 09:50:00    102
2016-04-25 09:55:00    121
2016-04-25 10:00:00    176
2016-04-25 10:05:00     86
2016-04-25 10:10:00     65
2016-04-25 10:15:00    132
2016-04-25 10:20:00    143
2016-04-25 10:25:00    160
Freq: 5T, dtype: int32
数据可视化
nline
%matplotlib inline
ts = pd.Series(np.random.randn(1000),index = pd.date_range('2000/1/1',periods=1000))
ts = ts.cumsum()
ts.describe()
count    1000.000000
mean        7.292909
std         9.028347
min       -15.164886
25%         1.531374
50%         9.228288
75%        14.624091
max        23.938509
dtype: float64
',
ts.plot(title = 'cumsum',style= 'r-',figsize =(10,6))
<matplotlib.axes._subplots.AxesSubplot at 0x21647116e10>

​