In [14]:

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

In [15]:

s = pd.Series([1,3,5,np.nan,6,8])

In [16]:

Out[16]:

0    1.0
1    3.0
2    5.0
3    NaN
4    6.0
5    8.0
dtype: float64

In [17]:

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

In [18]:

dates

Out[18]:

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 [19]:

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

In [20]:

df

Out[20]:

	A	B	C	D
2013-01-01	0.912308	1.042205	0.116620	-0.249330
2013-01-02	0.050897	-0.857851	1.892152	0.089577
2013-01-03	-0.276137	0.870425	-0.292043	1.759634
2013-01-04	0.810178	-0.394288	-0.298116	-0.504609
2013-01-05	1.347367	-0.987219	0.317209	-1.278711
2013-01-06	-0.888704	0.832839	0.526465	1.173505

In [21]:

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'})

In [22]:

df2

Out[22]:

	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 [23]:

df2.dtypes

Out[23]:

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

In [26]:

df.head()

Out[26]:

	A	B	C	D
2013-01-01	0.912308	1.042205	0.116620	-0.249330
2013-01-02	0.050897	-0.857851	1.892152	0.089577
2013-01-03	-0.276137	0.870425	-0.292043	1.759634
2013-01-04	0.810178	-0.394288	-0.298116	-0.504609
2013-01-05	1.347367	-0.987219	0.317209	-1.278711

In [27]:

df.tail()

Out[27]:

	A	B	C	D
2013-01-02	0.050897	-0.857851	1.892152	0.089577
2013-01-03	-0.276137	0.870425	-0.292043	1.759634
2013-01-04	0.810178	-0.394288	-0.298116	-0.504609
2013-01-05	1.347367	-0.987219	0.317209	-1.278711
2013-01-06	-0.888704	0.832839	0.526465	1.173505

In [28]:

df.index

Out[28]:

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 [29]:

df.columns

Out[29]:

Index(['A', 'B', 'C', 'D'], dtype='object')

In [30]:

df.values

Out[30]:

array([[ 0.91230835,  1.04220519,  0.11662036, -0.24932956],
       [ 0.05089737, -0.85785106,  1.89215172,  0.0895768 ],
       [-0.27613658,  0.87042539, -0.29204261,  1.75963441],
       [ 0.81017848, -0.3942882 , -0.29811603, -0.5046093 ],
       [ 1.34736699, -0.98721882,  0.31720941, -1.27871095],
       [-0.88870378,  0.83283915,  0.52646464,  1.17350527]])

In [31]:

df.describe()

Out[31]:

	A	B	C	D
count	6.000000	6.000000	6.000000	6.000000
mean	0.325985	0.084352	0.377048	0.165011
std	0.840849	0.933888	0.811517	1.119819
min	-0.888704	-0.987219	-0.298116	-1.278711
25%	-0.194378	-0.741960	-0.189877	-0.440789
50%	0.430538	0.219275	0.216915	-0.079876
75%	0.886776	0.861029	0.474151	0.902523
max	1.347367	1.042205	1.892152	1.759634

In [33]:

df.T

Out[33]:

	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	0.912308	0.050897	-0.276137	0.810178	1.347367	-0.888704
B	1.042205	-0.857851	0.870425	-0.394288	-0.987219	0.832839
C	0.116620	1.892152	-0.292043	-0.298116	0.317209	0.526465
D	-0.249330	0.089577	1.759634	-0.504609	-1.278711	1.173505

In [35]:

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

Out[35]:

	D	C	B	A
2013-01-01	-0.249330	0.116620	1.042205	0.912308
2013-01-02	0.089577	1.892152	-0.857851	0.050897
2013-01-03	1.759634	-0.292043	0.870425	-0.276137
2013-01-04	-0.504609	-0.298116	-0.394288	0.810178
2013-01-05	-1.278711	0.317209	-0.987219	1.347367
2013-01-06	1.173505	0.526465	0.832839	-0.888704

In [36]:

df.sort_values(by='B')

Out[36]:

	A	B	C	D
2013-01-05	1.347367	-0.987219	0.317209	-1.278711
2013-01-02	0.050897	-0.857851	1.892152	0.089577
2013-01-04	0.810178	-0.394288	-0.298116	-0.504609
2013-01-06	-0.888704	0.832839	0.526465	1.173505
2013-01-03	-0.276137	0.870425	-0.292043	1.759634
2013-01-01	0.912308	1.042205	0.116620	-0.249330

In [40]:

df['A']

Out[40]:

2013-01-01    0.912308
2013-01-02    0.050897
2013-01-03   -0.276137
2013-01-04    0.810178
2013-01-05    1.347367
2013-01-06   -0.888704
Freq: D, Name: A, dtype: float64

In [41]:

df[0:3]

Out[41]:

	A	B	C	D
2013-01-01	0.912308	1.042205	0.116620	-0.249330
2013-01-02	0.050897	-0.857851	1.892152	0.089577
2013-01-03	-0.276137	0.870425	-0.292043	1.759634

In [ ]:

df

Pay Notebook Creator: Stelios Phanartzis	0
Set Container: Numerical CPU with TINY Memory for 10 Minutes	0
Total	0

Give Me More Business for My Cart