10分钟 to pandas

import pandas as pd
import numpy as np
import matplotlib.pyplot as pltx

In [3]:

dates = pd.date_range('20130101', periods=6)
dates

Out[3]:

DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
               '2013-01-05', '2013-01-06'],
              dtype='datetime64[ns]', freq='D')

In [4]:

df = pd.DataFrame(np.random.randn(6,4), index=dates, columns=list('ABCD'))
df

Out[4]:

	A	B	C	D
2013-01-01	0.043660	0.914219	1.364281	0.960460
2013-01-02	0.245818	0.582317	0.456372	-0.734680
2013-01-03	-0.997398	-0.476202	0.967015	0.089730
2013-01-04	-1.132148	0.867161	0.458086	0.797743
2013-01-05	-1.226727	1.524988	-1.980305	0.694533
2013-01-06	1.695086	0.796078	-0.688947	-0.910752

In [5]:

df2 = pd.DataFrame({ 'A' : 1.,
              'B' : pd.Timestamp('20130102'),
              'C' : pd.Series(1,index=list(range(4)),dtype='float32'),
              'D' : np.array([3] * 4,dtype='int32'),
              'E' : pd.Categorical(["test","train","test","train"]),
              'F' : 'foo' })
df2

Out[5]:

	A	B	C	D	E	F
0	1.0	2013-01-02	1.0	3	test	foo
1	1.0	2013-01-02	1.0	3	train	foo
2	1.0	2013-01-02	1.0	3	test	foo
3	1.0	2013-01-02	1.0	3	train	foo

In [6]:

df2.dtypes

Out[6]:

A           float64
B    datetime64[ns]
C           float32
D             int32
E          category
F            object
dtype: object

In [11]:

df.describe()

Out[11]:

	A	B	C	D
count	6.000000	6.000000	6.000000	6.000000
mean	-0.228618	0.701427	0.096084	0.149506
std	1.131678	0.657413	1.229257	0.810483
min	-1.226727	-0.476202	-1.980305	-0.910752
25%	-1.098461	0.635757	-0.402617	-0.528577
50%	-0.476869	0.831620	0.457229	0.392131
75%	0.195279	0.902454	0.839783	0.771940
max	1.695086	1.524988	1.364281	0.960460

In [12]:

df.T

Out[12]:

	2013-01-01 00:00:00	2013-01-02 00:00:00	2013-01-03 00:00:00	2013-01-04 00:00:00	2013-01-05 00:00:00	2013-01-06 00:00:00
A	0.043660	0.245818	-0.997398	-1.132148	-1.226727	1.695086
B	0.914219	0.582317	-0.476202	0.867161	1.524988	0.796078
C	1.364281	0.456372	0.967015	0.458086	-1.980305	-0.688947
D	0.960460	-0.734680	0.089730	0.797743	0.694533	-0.910752

In [13]:

df.sort_index(axis=1, ascending=False)

Out[13]:

	D	C	B	A
2013-01-01	0.960460	1.364281	0.914219	0.043660
2013-01-02	-0.734680	0.456372	0.582317	0.245818
2013-01-03	0.089730	0.967015	-0.476202	-0.997398
2013-01-04	0.797743	0.458086	0.867161	-1.132148
2013-01-05	0.694533	-1.980305	1.524988	-1.226727
2013-01-06	-0.910752	-0.688947	0.796078	1.695086

In [14]:

df.sort_values(by='B')

Out[14]:

	A	B	C	D
2013-01-03	-0.997398	-0.476202	0.967015	0.089730
2013-01-02	0.245818	0.582317	0.456372	-0.734680
2013-01-06	1.695086	0.796078	-0.688947	-0.910752
2013-01-04	-1.132148	0.867161	0.458086	0.797743
2013-01-01	0.043660	0.914219	1.364281	0.960460
2013-01-05	-1.226727	1.524988	-1.980305	0.694533

In [15]:

df.apply(np.cumsum)

Out[15]:

	A	B	C	D
2013-01-01	0.043660	0.914219	1.364281	0.960460
2013-01-02	0.289478	1.496535	1.820653	0.225781
2013-01-03	-0.707920	1.020334	2.787668	0.315511
2013-01-04	-1.840068	1.887495	3.245754	1.113254
2013-01-05	-3.066794	3.412483	1.265449	1.807786
2013-01-06	-1.371708	4.208561	0.576502	0.897035

In [16]:

df.apply(lambda x: x.max() - x.min())

Out[16]:

A    2.921813
B    2.001190
C    3.344586
D    1.871212
dtype: float64

In [18]:

s = pd.Series(np.random.randint(0, 7, size=10))
s

Out[18]:

0    3
1    3
2    3
3    4
4    3
5    1
6    6
7    3
8    1
9    4
dtype: int32

In [19]:

s.value_counts()

Out[19]:

3    5
4    2
1    2
6    1
dtype: int64

In [20]:

s = pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'])
s.str.lower()

Out[20]:

0       a
1       b
2       c
3    aaba
4    baca
5     NaN
6    caba
7     dog
8