Python数据分析（2）Pandas（ipython版）

简介

  • Pandas是Python的一个数据分析包，该工具为解决数据分析任务而创建。
  • Pandas纳入大量库和标准数据模型，提供高效的操作数据集所需的工具。
  • Pandas提供大量能使我们快速便捷地处理数据的函数和方法。
  • Pandas是字典形式，基于NumPy创建，让NumPy为中心的应用变得更加简单。
  • 对于金融行业的用户，pandas提供了大量适用于金融数据的高性能时间序列功能和工具。
  • Excel 2007及其以后的版本的最大行数是1048576，最大列数是16384，超过这个规模的数据可使用Pandas

『ipynb文档传送门』

1
2
3
>>> import pandas as pd
>>> import numpy as np
>>> import matplotlib.pyplot as plt

Series

1
2
3
4
5
6
7
8
9
>>> s = pd.Series([1,3,5,np.nan,6,8])
>>> s
0    1.0
1    3.0
2    5.0
3    NaN
4    6.0
5    8.0
dtype: float64

DataFrame

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
>>> dates = pd.date_range('20170101', periods=6)
>>> dates
DatetimeIndex(['2017-01-01', '2017-01-02', '2017-01-03', '2017-01-04',
               '2017-01-05', '2017-01-06'],
              dtype='datetime64[ns]', freq='D')

>>> df = pd.DataFrame(np.random.randn(6,4), index=dates, columns=list('ABCD'))
>>> df
                   A         B         C         D
2017-01-01  2.005030  0.733879 -0.091630 -1.182515
2017-01-02 -0.816147  1.093998 -0.214505 -0.895524
2017-01-03  0.525449  0.592618 -0.843517  0.723407
2017-01-04  2.688099 -0.981475 -0.613816 -0.190706
2017-01-05 -1.129791 -0.653375  2.039835  1.488373
2017-01-06 -0.306414 -0.294490 -0.178337 -0.546832

>>> df.head(3)
                   A         B         C         D
2017-01-01  2.005030  0.733879 -0.091630 -1.182515
2017-01-02 -0.816147  1.093998 -0.214505 -0.895524
2017-01-03  0.525449  0.592618 -0.843517  0.723407

>>> df.tail(3)
                   A         B         C         D
2017-01-04  2.688099 -0.981475 -0.613816 -0.190706
2017-01-05 -1.129791 -0.653375  2.039835  1.488373
2017-01-06 -0.306414 -0.294490 -0.178337 -0.546832
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
>>> 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
     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

>>> df2.dtypes
A           float64
B    datetime64[ns]
C           float32
D             int32
E          category
F            object
dtype: object

>>> df2.columns #列的序号名字
Index(['A', 'B', 'C', 'D', 'E', 'F'], dtype='object')

>>> df2.index #行的序号
Int64Index([0, 1, 2, 3], dtype='int64')

>>> df2.values #把每个值进行打印出来
array([[1.0, Timestamp('2013-01-02 00:00:00'), 1.0, 3, 'test', 'foo'],
       [1.0, Timestamp('2013-01-02 00:00:00'), 1.0, 3, 'train', 'foo'],
       [1.0, Timestamp('2013-01-02 00:00:00'), 1.0, 3, 'test', 'foo'],
       [1.0, Timestamp('2013-01-02 00:00:00'), 1.0, 3, 'train', 'foo']],
      dtype=object)
      
>>> df2.describe() #数字总结
         A    C    D
count  4.0  4.0  4.0
mean   1.0  1.0  3.0
std    0.0  0.0  0.0
min    1.0  1.0  3.0
25%    1.0  1.0  3.0
50%    1.0  1.0  3.0
75%    1.0  1.0  3.0
max    1.0  1.0  3.0

>>> df2.T #翻转数据
                     0         ...                             3
A                    1         ...                             1
B  2013-01-02 00:00:00         ...           2013-01-02 00:00:00
C                    1         ...                             1
D                    3         ...                             3
E                 test         ...                         train
F                  foo         ...                           foo

[6 rows x 4 columns]

>>> df2.sort_index(axis=1, ascending=False) #axis等于1按列进行排序 如ABCDEFG 然后ascending倒叙进行显示
     F      E  D    C          B    A
0  foo   test  3  1.0 2013-01-02  1.0
1  foo  train  3  1.0 2013-01-02  1.0
2  foo   test  3  1.0 2013-01-02  1.0
3  foo  train  3  1.0 2013-01-02  1.0

>>> df2.sort_index(axis=0, ascending=False) #axis等于0按行进行排序 如0123 然后ascending倒叙进行显示
     A          B    C  D      E    F
3  1.0 2013-01-02  1.0  3  train  foo
2  1.0 2013-01-02  1.0  3   test  foo
1  1.0 2013-01-02  1.0  3  train  foo
0  1.0 2013-01-02  1.0  3   test  foo

>>> df2.sort_values(by='E') #按值进行排序
     A          B    C  D      E    F
0  1.0 2013-01-02  1.0  3   test  foo
2  1.0 2013-01-02  1.0  3   test  foo
1  1.0 2013-01-02  1.0  3  train  foo
3  1.0 2013-01-02  1.0  3  train  foo

选择

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
>>> df['A']
2017-01-01    2.005030
2017-01-02   -0.816147
2017-01-03    0.525449
2017-01-04    2.688099
2017-01-05   -1.129791
2017-01-06   -0.306414
Freq: D, Name: A, dtype: float64

>>> df[0:3] #切片选择
                   A         B         C         D
2017-01-01  2.005030  0.733879 -0.091630 -1.182515
2017-01-02 -0.816147  1.093998 -0.214505 -0.895524
2017-01-03  0.525449  0.592618 -0.843517  0.723407

>>> df['20170102':'20170104']
                   A         B         C         D
2017-01-02 -0.816147  1.093998 -0.214505 -0.895524
2017-01-03  0.525449  0.592618 -0.843517  0.723407
2017-01-04  2.688099 -0.981475 -0.613816 -0.190706

#loc方法为根据行标签label选择
>>> df.loc[dates[0]]
A    2.005030
B    0.733879
C   -0.091630
D   -1.182515
Name: 2017-01-01 00:00:00, dtype: float64

>>> df.loc[dates[0],'A']
2.0050298195407144

>>> df.loc[:,['A','B']]
                   A         B
2017-01-01  2.005030  0.733879
2017-01-02 -0.816147  1.093998
2017-01-03  0.525449  0.592618
2017-01-04  2.688099 -0.981475
2017-01-05 -1.129791 -0.653375
2017-01-06 -0.306414 -0.294490

>>> df.loc['20170102':'20170104',['A','B']]
                   A         B
2017-01-02 -0.816147  1.093998
2017-01-03  0.525449  0.592618
2017-01-04  2.688099 -0.981475


#iloc方法为根据position选择
>>> df.iloc[3]
A    2.688099
B   -0.981475
C   -0.613816
D   -0.190706
Name: 2017-01-04 00:00:00, dtype: float64

>>> df.iloc[3:5,0:2]
                   A         B
2017-01-04  2.688099 -0.981475
2017-01-05 -1.129791 -0.653375

>>> df.iloc[[1,2,4],[0,2]]
                   A         C
2017-01-02 -0.816147 -0.214505
2017-01-03  0.525449 -0.843517
2017-01-05 -1.129791  2.039835

>>> df.iloc[1,1]
1.0939979652715908

>>> df.iat[1,1]
1.0939979652715908

# 根据布尔表达式筛选
>>> df[df > 0]
                   A         B         C         D
2017-01-01  2.005030  0.733879       NaN       NaN
2017-01-02       NaN  1.093998       NaN       NaN
2017-01-03  0.525449  0.592618       NaN  0.723407
2017-01-04  2.688099       NaN       NaN       NaN
2017-01-05       NaN       NaN  2.039835  1.488373
2017-01-06       NaN       NaN       NaN       NaN

>>> df[df.A > 0]
                   A         B         C         D
2017-01-01  2.005030  0.733879 -0.091630 -1.182515
2017-01-03  0.525449  0.592618 -0.843517  0.723407
2017-01-04  2.688099 -0.981475 -0.613816 -0.190706

#使用isin
>>> df2[df2['E'].isin(['train'])]
     A          B    C  D      E    F
1  1.0 2013-01-02  1.0  3  train  foo
3  1.0 2013-01-02  1.0  3  train  foo

设置数据

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
>>> s1 = pd.Series([1,2,3,4,5,6], index=pd.date_range('20170102', periods=6))
>>> s1
2017-01-02    1
2017-01-03    2
2017-01-04    3
2017-01-05    4
2017-01-06    5
2017-01-07    6
Freq: D, dtype: int64

>>> df['F'] = s1
>>> df
                   A         B         C         D    F
2017-01-01  2.005030  0.733879 -0.091630 -1.182515  NaN
2017-01-02 -0.816147  1.093998 -0.214505 -0.895524  1.0
2017-01-03  0.525449  0.592618 -0.843517  0.723407  2.0
2017-01-04  2.688099 -0.981475 -0.613816 -0.190706  3.0
2017-01-05 -1.129791 -0.653375  2.039835  1.488373  4.0
2017-01-06 -0.306414 -0.294490 -0.178337 -0.546832  5.0

>>> df.at[dates[0],'A'] = 0
>>> df
                   A         B         C         D    F
2017-01-01  0.000000  0.733879 -0.091630 -1.182515  NaN
2017-01-02 -0.816147  1.093998 -0.214505 -0.895524  1.0
2017-01-03  0.525449  0.592618 -0.843517  0.723407  2.0
2017-01-04  2.688099 -0.981475 -0.613816 -0.190706  3.0
2017-01-05 -1.129791 -0.653375  2.039835  1.488373  4.0
2017-01-06 -0.306414 -0.294490 -0.178337 -0.546832  5.0

>>> df.iat[0,1] = 0
>>> df
                   A         B         C         D    F
2017-01-01  0.000000  0.000000 -0.091630 -1.182515  NaN
2017-01-02 -0.816147  1.093998 -0.214505 -0.895524  1.0
2017-01-03  0.525449  0.592618 -0.843517  0.723407  2.0
2017-01-04  2.688099 -0.981475 -0.613816 -0.190706  3.0
2017-01-05 -1.129791 -0.653375  2.039835  1.488373  4.0
2017-01-06 -0.306414 -0.294490 -0.178337 -0.546832  5.0

#使用numpy数组
>>> df.loc[:,'D'] = np.array([5] * len(df))
>>> df
                   A         B         C  D    F
2017-01-01  0.000000  0.000000 -0.091630  5  NaN
2017-01-02 -0.816147  1.093998 -0.214505  5  1.0
2017-01-03  0.525449  0.592618 -0.843517  5  2.0
2017-01-04  2.688099 -0.981475 -0.613816  5  3.0
2017-01-05 -1.129791 -0.653375  2.039835  5  4.0
2017-01-06 -0.306414 -0.294490 -0.178337  5  5.0

#where语句
>>> df[df > 0] = -df
>>> df
                   A         B         C  D    F
2017-01-01  0.000000  0.000000 -0.091630 -5  NaN
2017-01-02 -0.816147 -1.093998 -0.214505 -5 -1.0
2017-01-03 -0.525449 -0.592618 -0.843517 -5 -2.0
2017-01-04 -2.688099 -0.981475 -0.613816 -5 -3.0
2017-01-05 -1.129791 -0.653375 -2.039835 -5 -4.0
2017-01-06 -0.306414 -0.294490 -0.178337 -5 -5.0

处理丢失数据

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
>>> df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E'])
>>> df1.loc[dates[0]:dates[1],'E'] = 1
>>> df1
                   A         B         C  D    F    E
2017-01-01  0.000000  0.000000 -0.091630 -5  NaN  1.0
2017-01-02 -0.816147 -1.093998 -0.214505 -5 -1.0  1.0
2017-01-03 -0.525449 -0.592618 -0.843517 -5 -2.0  NaN
2017-01-04 -2.688099 -0.981475 -0.613816 -5 -3.0  NaN

>>> df1.dropna(how='any')
                   A         B         C  D    F    E
2017-01-02 -0.816147 -1.093998 -0.214505 -5 -1.0  1.0

>>> df1.fillna(value=5)
                   A         B         C  D    F    E
2017-01-01  0.000000  0.000000 -0.091630 -5  5.0  1.0
2017-01-02 -0.816147 -1.093998 -0.214505 -5 -1.0  1.0
2017-01-03 -0.525449 -0.592618 -0.843517 -5 -2.0  5.0
2017-01-04 -2.688099 -0.981475 -0.613816 -5 -3.0  5.0

>>> pd.isna(df1)
                A      B      C      D      F      E
2017-01-01  False  False  False  False   True  False
2017-01-02  False  False  False  False  False  False
2017-01-03  False  False  False  False  False   True
2017-01-04  False  False  False  False  False   True

运算

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
#统计
>>> df = pd.DataFrame(np.random.randint(10,size=(6,4)), index=dates, columns=list('ABCD'))
>>> df
            A  B  C  D
2017-01-01  0  2  3  6
2017-01-02  4  2  0  6
2017-01-03  4  7  4  2
2017-01-04  7  1  9  5
2017-01-05  4  7  5  7
2017-01-06  7  0  3  6

>>> df.mean()
A    4.333333
B    3.166667
C    4.000000
D    5.333333
dtype: float64

>>> df.mean(1)
2017-01-01    2.75
2017-01-02    3.00
2017-01-03    4.25
2017-01-04    5.50
2017-01-05    5.75
2017-01-06    4.00
Freq: D, dtype: float64

>>> s = pd.Series([1,3,5,np.nan,6,8], index=dates)
>>> s
2017-01-01    1.0
2017-01-02    3.0
2017-01-03    5.0
2017-01-04    NaN
2017-01-05    6.0
2017-01-06    8.0
Freq: D, dtype: float64

>>> s=s.shift(2)
>>> s
2017-01-01    NaN
2017-01-02    NaN
2017-01-03    1.0
2017-01-04    3.0
2017-01-05    5.0
2017-01-06    NaN
Freq: D, dtype: float64

>>> df.sub(s, axis='index')
              A    B    C    D
2017-01-01  NaN  NaN  NaN  NaN
2017-01-02  NaN  NaN  NaN  NaN
2017-01-03  3.0  6.0  3.0  1.0
2017-01-04  4.0 -2.0  6.0  2.0
2017-01-05 -1.0  2.0  0.0  2.0
2017-01-06  NaN  NaN  NaN  NaN

#apply函数
>>> df.apply(np.cumsum)
             A   B   C   D
2017-01-01   0   2   3   6
2017-01-02   4   4   3  12
2017-01-03   8  11   7  14
2017-01-04  15  12  16  19
2017-01-05  19  19  21  26
2017-01-06  26  19  24  32

>>> df.apply(lambda x: x.max() - x.min())
A    7
B    7
C    9
D    5
dtype: int64

#计数
>>> s = pd.Series(np.random.randint(0, 7, size=10))
>>> s
0    2
1    3
2    6
3    2
4    4
5    5
6    2
7    4
8    3
9    0
dtype: int64

>>> s.value_counts()
2    3
4    2
3    2
6    1
5    1
0    1
dtype: int64

#字符串方法
>>> s = pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'])
>>> s
0       A
1       B
2       C
3    Aaba
4    Baca
5     NaN
6    CABA
7     dog
8     cat
dtype: object

>>> s.str.lower()
0       a
1       b
2       c
3    aaba
4    baca
5     NaN
6    caba
7     dog
8     cat
dtype: object

合并

分为concat拼接、merge连接、append附加

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
#concat
>>> df = pd.DataFrame(np.random.randn(10, 4))
>>> df
          0         1         2         3
0 -0.151360  1.936300 -1.933860 -1.591089
1  0.543475 -1.078185  1.887563 -0.079848
2  0.096933  0.203424 -2.692479 -0.908979
3 -0.641344 -0.705723 -0.514991 -0.306118
4 -1.857033  2.996804  0.042935  0.086588
5  1.163863  0.573611 -1.792710  1.117765
6  0.016726 -0.264878  0.013678  0.142825
7  0.169513  0.549630 -2.428330  0.688122
8  0.589439  0.497580 -0.018289  0.111394
9 -1.306610 -0.506994 -1.254999  0.671447
>>> pieces = [df[:3], df[3:7], df[7:]]

>>> pieces[0]
          0         1         2         3
0 -0.151360  1.936300 -1.933860 -1.591089
1  0.543475 -1.078185  1.887563 -0.079848
2  0.096933  0.203424 -2.692479 -0.908979

>>> pieces[1]
          0         1         2         3
3 -0.641344 -0.705723 -0.514991 -0.306118
4 -1.857033  2.996804  0.042935  0.086588
5  1.163863  0.573611 -1.792710  1.117765
6  0.016726 -0.264878  0.013678  0.142825

>>> pieces[2]
          0         1         2         3
7  0.169513  0.549630 -2.428330  0.688122
8  0.589439  0.497580 -0.018289  0.111394
9 -1.306610 -0.506994 -1.254999  0.671447

>>> pd.concat(pieces)
          0         1         2         3
0 -0.151360  1.936300 -1.933860 -1.591089
1  0.543475 -1.078185  1.887563 -0.079848
2  0.096933  0.203424 -2.692479 -0.908979
3 -0.641344 -0.705723 -0.514991 -0.306118
4 -1.857033  2.996804  0.042935  0.086588
5  1.163863  0.573611 -1.792710  1.117765
6  0.016726 -0.264878  0.013678  0.142825
7  0.169513  0.549630 -2.428330  0.688122
8  0.589439  0.497580 -0.018289  0.111394
9 -1.306610 -0.506994 -1.254999  0.671447

#merge
>>> left = pd.DataFrame({'key': ['foo', 'foo'], 'lval': [1, 2]})
>>> right = pd.DataFrame({'key': ['foo', 'foo'], 'rval': [4, 5]})
>>> left
   key  lval
0  foo     1
1  foo     2
>>> right
   key  rval
0  foo     4
1  foo     5
>>> pd.merge(left, right, on='key')
   key  lval  rval
0  foo     1     4
1  foo     1     5
2  foo     2     4
3  foo     2     5

#df.append
>>> df = pd.DataFrame(np.random.randn(8, 4), columns=['A','B','C','D'])
>>> df
          A         B         C         D
0 -1.140957  0.520399  0.367026  0.379816
1 -0.320234 -2.002672 -1.573755 -0.917358
2 -1.535288 -1.427954 -1.411031 -1.550238
3 -1.273231 -1.818118  2.100161 -0.193851
4 -1.776232  0.330897 -0.000800  0.323965
5  0.390162 -2.498448  0.688449 -0.085605
6 -0.730385  0.776125 -0.535168  0.450266
7 -0.261463 -0.468258 -2.010936 -1.194405

>>> s = df.iloc[3]
>>> df.append(s, ignore_index=True)
          A         B         C         D
0 -1.140957  0.520399  0.367026  0.379816
1 -0.320234 -2.002672 -1.573755 -0.917358
2 -1.535288 -1.427954 -1.411031 -1.550238
3 -1.273231 -1.818118  2.100161 -0.193851
4 -1.776232  0.330897 -0.000800  0.323965
5  0.390162 -2.498448  0.688449 -0.085605
6 -0.730385  0.776125 -0.535168  0.450266
7 -0.261463 -0.468258 -2.010936 -1.194405
8 -1.273231 -1.818118  2.100161 -0.193851

分组

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
>>> 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)})
>>> df
     A      B         C         D
0  foo    one  0.768969  0.173497
1  bar    one  0.768786  2.306459
2  foo    two  0.731202 -0.503019
3  bar  three -0.513766 -2.045957
4  foo    two -0.399326  0.699242
5  bar    two -0.006959 -0.227020
6  foo    one  0.177778 -1.405640
7  foo  three -0.373651  0.298679

>>> df.groupby('A').sum()
            C         D
A                      
bar  0.248061  0.033482
foo  0.904972 -0.737242

>>> df.groupby(['A','B']).sum()
                  C         D
A   B                        
bar one    0.768786  2.306459
    three -0.513766 -2.045957
    two   -0.006959 -0.227020
foo one    0.946747 -1.232143
    three -0.373651  0.298679
    two    0.331876  0.196222

pivot table

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
>>> df = pd.DataFrame({'A' : ['one', 'one', 'two', 'three'] * 3,
                   'B' : ['A', 'B', 'C'] * 4,
                   'C' : ['foo', 'foo', 'foo', 'bar', 'bar', 'bar'] * 2,
                   'D' : np.random.randn(12),
                   'E' : np.random.randn(12)})
df
        A  B    C         D         E
0     one  A  foo -0.222380 -0.763609
1     one  B  foo  0.436697  1.399591
2     two  C  foo -1.888151 -1.888447
3   three  A  bar -1.476924  0.097636
4     one  B  bar  0.981243 -0.473387
5     one  C  bar  0.732474 -1.232232
6     two  A  foo  0.229707 -0.175676
7   three  B  foo  1.174989 -0.764255
8     one  C  foo  0.541069 -0.318213
9     one  A  bar -0.226409 -0.077711
10    two  B  bar  0.672698 -1.571569
11  three  C  bar  2.103090  0.368683

>>> pd.pivot_table(df, values='D', index=['A', 'B'], columns=['C'])
C             bar       foo
A     B                    
one   A -0.226409 -0.222380
      B  0.981243  0.436697
      C  0.732474  0.541069
three A -1.476924       NaN
      B       NaN  1.174989
      C  2.103090       NaN
two   A       NaN  0.229707
      B  0.672698       NaN
      C       NaN -1.888151

plotting

1
2
3
4
5
6
7
8
9
10
11
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

ts = pd.Series(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000))
ts = ts.cumsum()

plt.figure()
ts.plot()
plt.legend(loc='best')
plt.show()

导出和导入，支持csv、hdf5和excel

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
>>> df.to_csv('foo.csv')
>>> pd.read_csv('foo.csv')
    Unnamed: 0      A  B    C         D         E
0            0   herr  A  foo -0.222380 -0.763609
1            1    one  B  foo  0.436697  1.399591
2            2    two  C  foo -1.888151 -1.888447
3            3  three  A  bar -1.476924  0.097636
4            4    one  B  bar  0.981243 -0.473387

#excel导入导出，导出需要安装openpyxl库，导入需要安装xlrd库
>>> df.to_excel('foo.xlsx', sheet_name='Sheet1')
>>> pd.read_excel('foo.xlsx', 'Sheet1', index_col=None, na_values=['NA'])
        A  B    C         D         E
0    herr  A  foo -0.222380 -0.763609
1     one  B  foo  0.436697  1.399591
2     two  C  foo -1.888151 -1.888447
3   three  A  bar -1.476924  0.097636
4     one  B  bar  0.981243 -0.473387

读取MySQL

1
2
3
4
5
import pandas as pd
import MySQLdb
mysql_cn= MySQLdb.connect(host='localhost', port=3306,user='root', passwd='123', db='testdb')
df = pd.read_sql('select * from test;', con=mysql_cn)    
mysql_cn.close()

tag:

    缺失模块。
    1、请确保node版本大于6.2
    2、在博客根目录（注意不是yilia根目录）执行以下命令：
    npm i hexo-generator-json-content --save

    3、在根目录_config.yml里添加配置： 

      jsonContent:
    meta: false
    pages: false
    posts:
      title: true
      date: true
      path: true
      text: false
      raw: false
      content: false
      slug: false
      updated: false
      comments: false
      link: false
      permalink: false
      excerpt: false
      categories: false
      tags: true