pandas的基本用法(二)——选择数据

| |
pandas的基本用法(二)——选择数据

文章作者：Tyan
博客：noahsnail.com  |  CSDN  |  简书

本文主要是关于pandas的一些基本用法。

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
#!/usr/bin/env python
# _*_ coding: utf-8 _*_

import pandas as pd
import numpy as np


# Test 1
# 定义数据
dates = pd.date_range('20170101', periods = 6)
print dates

df = pd.DataFrame(np.arange(24).reshape((6, 4)), index = dates, columns = ['A', 'B', 'C', 'D'])
print df


# Test 1 result
DatetimeIndex(['2017-01-01', '2017-01-02', '2017-01-03', '2017-01-04',
               '2017-01-05', '2017-01-06'],
              dtype='datetime64[ns]', freq='D')

             A   B   C   D
2017-01-01   0   1   2   3
2017-01-02   4   5   6   7
2017-01-03   8   9  10  11
2017-01-04  12  13  14  15
2017-01-05  16  17  18  19
2017-01-06  20  21  22  23

# Test 2
# 选择第一列数据
print df['A']
print df.A

# 选择前三行数据
print df[0:3]
print df['20170101':'20170103']

# 根据标签选择
print df.loc['20170101']

# 选择所有行, 特定列
print df.loc[:, ['A', 'B']]

# 选择特定行, 特定列
print df.loc['20170102', ['A', 'B']]

# Test 2 result
2017-01-01     0
2017-01-02     4
2017-01-03     8
2017-01-04    12
2017-01-05    16
2017-01-06    20
Freq: D, Name: A, dtype: int64
2017-01-01     0
2017-01-02     4
2017-01-03     8
2017-01-04    12
2017-01-05    16
2017-01-06    20
Freq: D, Name: A, dtype: int64

            A  B   C   D
2017-01-01  0  1   2   3
2017-01-02  4  5   6   7
2017-01-03  8  9  10  11
            A  B   C   D
2017-01-01  0  1   2   3
2017-01-02  4  5   6   7
2017-01-03  8  9  10  11

A    0
B    1
C    2
D    3
Name: 2017-01-01 00:00:00, dtype: int64

             A   B
2017-01-01   0   1
2017-01-02   4   5
2017-01-03   8   9
2017-01-04  12  13
2017-01-05  16  17
2017-01-06  20  21

A    4
B    5
Name: 2017-01-02 00:00:00, dtype: int64

# Test 3
# 根据行列来选择
print df.iloc[3:5, 1:3]

# 不连续的选择
print df.iloc[[1, 3, 5], 2:4]

# 混合选择
print df.ix[[1, 3, 5], ['A', 'B']]

# 对比选择
print df[df.A > 4]

# Test 3 result
             B   C
2017-01-04  13  14
2017-01-05  17  18

             C   D
2017-01-02   6   7
2017-01-04  14  15
2017-01-06  22  23

             A   B
2017-01-02   4   5
2017-01-04  12  13
2017-01-06  20  21

             A   B   C   D
2017-01-03   8   9  10  11
2017-01-04  12  13  14  15
2017-01-05  16  17  18  19
2017-01-06  20  21  22  23

参考资料

  1. https://www.youtube.com/user/MorvanZhou
如果有收获，可以请我喝杯咖啡！