pandas使用

Posted on

……

pandas有两种特殊的数据结构：Series和DataFrame。
参考官方10 Minutes to pandas
import pandas as pd

对象创建

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
# Series
>>> 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

>>> s = pd.Series([1,'a','bbb'], index=['x','y','z'])
>>> s
x      1
y      a
z    bbb
dtype: object

>>> sd = {'python':8000, 'c++':8100, 'c#':4000}
>>> s = Series(sd)
>>> s
python   8000
c++      8001
c#       4000


# DataFrame
>>> dates = pd.date_range('20130101', periods=6)  # 日期序列索引
>>> dates
DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
               '2013-01-05', '2013-01-06'],
              dtype='datetime64[ns]', freq='D')
>>> df = pd.DataFrame(np.random.randn(6,4), index=dates, columns=list('ABCD'))
>>> df
                   A         B         C         D
2013-01-01  0.469112 -0.282863 -1.509059 -1.135632
2013-01-02  1.212112 -0.173215  0.119209 -1.044236
2013-01-03 -0.861849 -2.104569 -0.494929  1.071804
2013-01-04  0.721555 -0.706771 -1.039575  0.271860
2013-01-05 -0.424972  0.567020  0.276232 -1.087401
2013-01-06 -0.673690  0.113648 -1.478427  0.524988

>>> 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

查看数据

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
# 查看前几行、后几行
>>> df.head(2)
                   A         B         C         D
2013-01-01  0.469112 -0.282863 -1.509059 -1.135632
2013-01-02  1.212112 -0.173215  0.119209 -1.044236
>>> df.tail(3)
                   A         B         C         D
2013-01-04  0.721555 -0.706771 -1.039575  0.271860
2013-01-05 -0.424972  0.567020  0.276232 -1.087401
2013-01-06 -0.673690  0.113648 -1.478427  0.524988

# 查看index、columns、values、详细信息
>>> df.index
DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
               '2013-01-05', '2013-01-06'],
              dtype='datetime64[ns]', freq='D')
>>> df.columns
Index(['A', 'B', 'C', 'D'], dtype='object')
>>> df.values
array([[ 0.4691, -0.2829, -1.5091, -1.1356],
       [ 1.2121, -0.1732,  0.1192, -1.0442],
       [-0.8618, -2.1046, -0.4949,  1.0718],
       [ 0.7216, -0.7068, -1.0396,  0.2719],
       [-0.425 ,  0.567 ,  0.2762, -1.0874],
       [-0.6737,  0.1136, -1.4784,  0.525 ]])
	   
>>> df.describe()
              A         B         C         D
count  6.000000  6.000000  6.000000  6.000000
mean   0.073711 -0.431125 -0.687758 -0.233103
std    0.843157  0.922818  0.779887  0.973118
min   -0.861849 -2.104569 -1.509059 -1.135632
25%   -0.611510 -0.600794 -1.368714 -1.076610
50%    0.022070 -0.228039 -0.767252 -0.386188
75%    0.658444  0.041933 -0.034326  0.461706
max    1.212112  0.567020  0.276232  1.071804

# 操作：转置、排序
>>> df.T
   2013-01-01  2013-01-02  2013-01-03  2013-01-04  2013-01-05  2013-01-06
A    0.469112    1.212112   -0.861849    0.721555   -0.424972   -0.673690
B   -0.282863   -0.173215   -2.104569   -0.706771    0.567020    0.113648
C   -1.509059    0.119209   -0.494929   -1.039575    0.276232   -1.478427
D   -1.135632   -1.044236    1.071804    0.271860   -1.087401    0.524988
>>> df.sort_index(axis=1, ascending=False)
                   D         C         B         A
2013-01-01 -1.135632 -1.509059 -0.282863  0.469112
2013-01-02 -1.044236  0.119209 -0.173215  1.212112
2013-01-03  1.071804 -0.494929 -2.104569 -0.861849
2013-01-04  0.271860 -1.039575 -0.706771  0.721555
2013-01-05 -1.087401  0.276232  0.567020 -0.424972
2013-01-06  0.524988 -1.478427  0.113648 -0.673690
>>> df.sort_values(by='B')
                   A         B         C         D
2013-01-03 -0.861849 -2.104569 -0.494929  1.071804
2013-01-04  0.721555 -0.706771 -1.039575  0.271860
2013-01-01  0.469112 -0.282863 -1.509059 -1.135632
2013-01-02  1.212112 -0.173215  0.119209 -1.044236
2013-01-06 -0.673690  0.113648 -1.478427  0.524988
2013-01-05 -0.424972  0.567020  0.276232 -1.087401

选择数据

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
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
# 选择单个column
>>> df['A']   # 等价于df.A
2013-01-01    0.469112
2013-01-02    1.212112
2013-01-03   -0.861849
2013-01-04    0.721555
2013-01-05   -0.424972
2013-01-06   -0.673690
Freq: D, Name: A, dtype: float64
# 选择行，切片的方式
>>> df[0:3]
                   A         B         C         D
2013-01-01  0.469112 -0.282863 -1.509059 -1.135632
2013-01-02  1.212112 -0.173215  0.119209 -1.044236
2013-01-03 -0.861849 -2.104569 -0.494929  1.071804
>>> df['20130102':'20130104']  # 注意，头尾均包含
                   A         B         C         D
2013-01-02  1.212112 -0.173215  0.119209 -1.044236
2013-01-03 -0.861849 -2.104569 -0.494929  1.071804
2013-01-04  0.721555 -0.706771 -1.039575  0.271860


# 根据label
>>> df.loc['2013-01-01']
A    0.469112
B   -0.282863
C   -1.509059
D   -1.135632
Name: 2013-01-01 00:00:00, dtype: float64
>>> df.loc[:,['A','B']]
                   A         B
2013-01-01  0.469112 -0.282863
2013-01-02  1.212112 -0.173215
2013-01-03 -0.861849 -2.104569
2013-01-04  0.721555 -0.706771
2013-01-05 -0.424972  0.567020
2013-01-06 -0.673690  0.113648
>>> df.loc['20130102':'20130104',['A','B']]
                   A         B
2013-01-02  1.212112 -0.173215
2013-01-03 -0.861849 -2.104569
2013-01-04  0.721555 -0.706771
>>> df.loc['2013-01-01','A']  # 等价于df.at['2013-01-01','A']
0.46911229990718628


# 根据位置
>>> df.iloc[3]
A    0.721555
B   -0.706771
C   -1.039575
D    0.271860
Name: 2013-01-04 00:00:00, dtype: float64
>>> df.iloc[3:5,0:2]
                   A         B
2013-01-04  0.721555 -0.706771
2013-01-05 -0.424972  0.567020
>>> df.iloc[[1,2,4],[0,2]]
                   A         C
2013-01-02  1.212112  0.119209
2013-01-03 -0.861849 -0.494929
2013-01-05 -0.424972  0.276232
>>>df.iloc[1,1]  # 等价于df.iat[1,1]
-0.17321464905330858


# boolean进行选择
>>> df[df.A > 0]
                   A         B         C         D
2013-01-01  0.469112 -0.282863 -1.509059 -1.135632
2013-01-02  1.212112 -0.173215  0.119209 -1.044236
2013-01-04  0.721555 -0.706771 -1.039575  0.271860
>>> df[df > 0]
                   A         B         C         D
2013-01-01  0.469112       NaN       NaN       NaN
2013-01-02  1.212112       NaN  0.119209       NaN
2013-01-03       NaN       NaN       NaN  1.071804
2013-01-04  0.721555       NaN       NaN  0.271860
2013-01-05       NaN  0.567020  0.276232       NaN
2013-01-06       NaN  0.113648       NaN  0.524988

>>> df2 = df.copy()
>>> df2['E'] = ['one', 'one','two','three','four','three']
>>> df2
                   A         B         C         D      E
2013-01-01  0.469112 -0.282863 -1.509059 -1.135632    one
2013-01-02  1.212112 -0.173215  0.119209 -1.044236    one
2013-01-03 -0.861849 -2.104569 -0.494929  1.071804    two
2013-01-04  0.721555 -0.706771 -1.039575  0.271860  three
2013-01-05 -0.424972  0.567020  0.276232 -1.087401   four
2013-01-06 -0.673690  0.113648 -1.478427  0.524988  three
>>> df2[df2['E'].isin(['two','four'])]
                   A         B         C         D     E
2013-01-03 -0.861849 -2.104569 -0.494929  1.071804   two
2013-01-05 -0.424972  0.567020  0.276232 -1.087401  four

设置新的值

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
>>> s1 = pd.Series([1,2,3,4,5,6], index=pd.date_range('20130102', periods=6))
>>> s1
2013-01-02    1
2013-01-03    2
2013-01-04    3
2013-01-05    4
2013-01-06    5
2013-01-07    6
Freq: D, dtype: int64
>>> df['F'] = s1
>>> df.at[dates[0],'A'] = 0
>>> df.iat[0,1] = 0
>>> df.loc[:,'D'] = np.array([5] * len(df))

>>> df2 = df.copy()
>>>> df2[df2 > 0] = -df2

缺失值NaN

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
>>> df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E']) #将df的一部分copy给df1，df不变
>>> df1.loc[dates[0]:dates[1],'E'] = 1
>>> df1
                   A         B         C  D    F    E
2013-01-01  0.000000  0.000000 -1.509059  5  NaN  1.0
2013-01-02  1.212112 -0.173215  0.119209  5  1.0  1.0
2013-01-03 -0.861849 -2.104569 -0.494929  5  2.0  NaN
2013-01-04  0.721555 -0.706771 -1.039575  5  3.0  NaN

>>> df1.dropna(how='any') # 丢弃包含NaN的行
                   A         B         C  D    F    E
2013-01-02  1.212112 -0.173215  0.119209  5  1.0  1.0
>>> df1.fillna(value=5) # 填充缺失值
                   A         B         C  D    F    E
2013-01-01  0.000000  0.000000 -1.509059  5  5.0  1.0
2013-01-02  1.212112 -0.173215  0.119209  5  1.0  1.0
2013-01-03 -0.861849 -2.104569 -0.494929  5  2.0  5.0
2013-01-04  0.721555 -0.706771 -1.039575  5  3.0  5.0
>>> pd.isna(df1)  # 判断是否是NaN
                A      B      C      D      F      E
2013-01-01  False  False  False  False   True  False
2013-01-02  False  False  False  False  False  False
2013-01-03  False  False  False  False  False   True
2013-01-04  False  False  False  False  False   True

操作

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
>>> df.mean() # 求每一列的平均值
A   -0.004474
B   -0.383981
C   -0.687758
D    5.000000
F    3.000000
dtype: float64
>>> df.mean(1)  # 每一行
2013-01-01    0.872735
2013-01-02    1.431621
2013-01-03    0.707731
2013-01-04    1.395042
2013-01-05    1.883656
2013-01-06    1.592306
Freq: D, dtype: float64

>>> s = pd.Series([1,3,5,np.nan,6,8], index=dates).shift(2)
>>> s              # shift(2)，值往下移两位
2013-01-01    NaN
2013-01-02    NaN
2013-01-03    1.0
2013-01-04    3.0
2013-01-05    5.0
2013-01-06    NaN
Freq: D, dtype: float64
>>> df.sub(s, axis='index')  # 维度不一样，pandas自动broadcast
                   A         B         C    D    F
2013-01-01       NaN       NaN       NaN  NaN  NaN
2013-01-02       NaN       NaN       NaN  NaN  NaN
2013-01-03 -1.861849 -3.104569 -1.494929  4.0  1.0
2013-01-04 -2.278445 -3.706771 -4.039575  2.0  0.0
2013-01-05 -5.424972 -4.432980 -4.723768  0.0 -1.0
2013-01-06       NaN       NaN       NaN  NaN  NaN


#应用函数
>>> df.apply(np.cumsum)
                   A         B         C   D     F
2013-01-01  0.000000  0.000000 -1.509059   5   NaN
2013-01-02  1.212112 -0.173215 -1.389850  10   1.0
2013-01-03  0.350263 -2.277784 -1.884779  15   3.0
2013-01-04  1.071818 -2.984555 -2.924354  20   6.0
2013-01-05  0.646846 -2.417535 -2.648122  25  10.0
2013-01-06 -0.026844 -2.303886 -4.126549  30  15.0
>>> df.apply(lambda x: x.max() - x.min())
A    2.073961
B    2.671590
C    1.785291
D    0.000000
F    4.000000
dtype: float64

连接等操作

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
# concat
>>> df = pd.DataFrame(np.random.randn(10, 4))
>>> df
          0         1         2         3
0 -0.548702  1.467327 -1.015962 -0.483075
1  1.637550 -1.217659 -0.291519 -1.745505
2 -0.263952  0.991460 -0.919069  0.266046
3 -0.709661  1.669052  1.037882 -1.705775
4 -0.919854 -0.042379  1.247642 -0.009920
5  0.290213  0.495767  0.362949  1.548106
6 -1.131345 -0.089329  0.337863 -0.945867
7 -0.932132  1.956030  0.017587 -0.016692
8 -0.575247  0.254161 -1.143704  0.215897
9  1.193555 -0.077118 -0.408530 -0.862495
>>> pieces = [df[:3], df[3:7], df[7:]]
>>> pd.concat(pieces)
          0         1         2         3
0 -0.548702  1.467327 -1.015962 -0.483075
1  1.637550 -1.217659 -0.291519 -1.745505
2 -0.263952  0.991460 -0.919069  0.266046
3 -0.709661  1.669052  1.037882 -1.705775
4 -0.919854 -0.042379  1.247642 -0.009920
5  0.290213  0.495767  0.362949  1.548106
6 -1.131345 -0.089329  0.337863 -0.945867
7 -0.932132  1.956030  0.017587 -0.016692
8 -0.575247  0.254161 -1.143704  0.215897
9  1.193555 -0.077118 -0.408530 -0.862495

# join
>>> 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

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

# append
>>> df = pd.DataFrame(np.random.randn(8, 4), columns=['A','B','C','D'])
>>> df
          A         B         C         D
0  1.346061  1.511763  1.627081 -0.990582
1 -0.441652  1.211526  0.268520  0.024580
2 -1.577585  0.396823 -0.105381 -0.532532
3  1.453749  1.208843 -0.080952 -0.264610
4 -0.727965 -0.589346  0.339969 -0.693205
5 -0.339355  0.593616  0.884345  1.591431
6  0.141809  0.220390  0.435589  0.192451
7 -0.096701  0.803351  1.715071 -0.708758
>>> s = df.iloc[3]
>>> df.append(s, ignore_index=True)
          A         B         C         D
0  1.346061  1.511763  1.627081 -0.990582
1 -0.441652  1.211526  0.268520  0.024580
2 -1.577585  0.396823 -0.105381 -0.532532
3  1.453749  1.208843 -0.080952 -0.264610
4 -0.727965 -0.589346  0.339969 -0.693205
5 -0.339355  0.593616  0.884345  1.591431
6  0.141809  0.220390  0.435589  0.192451
7 -0.096701  0.803351  1.715071 -0.708758
8  1.453749  1.208843 -0.080952 -0.264610

Grouping

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
>>> 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 -1.202872 -0.055224
1  bar    one -1.814470  2.395985
2  foo    two  1.018601  1.552825
3  bar  three -0.595447  0.166599
4  foo    two  1.395433  0.047609
5  bar    two -0.392670 -0.136473
6  foo    one  0.007207 -0.561757
7  foo  three  1.928123 -1.623033
>>> df.groupby('A').sum()
            C        D
A                     
bar -2.802588  2.42611
foo  3.146492 -0.63958
>>> df.groupby(['A','B']).sum()
                  C         D
A   B                        
bar one   -1.814470  2.395985
    three -0.595447  0.166599
    two   -0.392670 -0.136473
foo one   -1.195665 -0.616981
    three  1.928123 -1.623033
    two    2.414034  1.600434

Reshaping

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
#Stack
>>>  tuples = list(zip(*[['bar', 'bar', 'baz', 'baz',
...                       'foo', 'foo', 'qux', 'qux'],
...                      ['one', 'two', 'one', 'two',
...                       'one', 'two', 'one', 'two']]))
...
>>> index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second'])
>>> df = pd.DataFrame(np.random.randn(8, 2), index=index, columns=['A', 'B'])
>>> df2 = df[:4]
>>> df2
                     A         B
first second                    
bar   one     0.029399 -0.542108
      two     0.282696 -0.087302
baz   one    -1.575170  1.771208
      two     0.816482  1.100230
>>> stacked = df2.stack()  # 压缩columns
>>> stacked
first  second   
bar    one     A    0.029399
               B   -0.542108
       two     A    0.282696
               B   -0.087302
baz    one     A   -1.575170
               B    1.771208
       two     A    0.816482
               B    1.100230
dtype: float64
>>> stacked.unstack()
                     A         B
first second                    
bar   one     0.029399 -0.542108
      two     0.282696 -0.087302
baz   one    -1.575170  1.771208
      two     0.816482  1.100230
>>> stacked.unstack(1)
second        one       two
first                      
bar   A  0.029399  0.282696
      B -0.542108 -0.087302
baz   A -1.575170  0.816482
      B  1.771208  1.100230
>>> stacked.unstack(0)
first          bar       baz
second                      
one    A  0.029399 -1.575170
       B -0.542108  1.771208
two    A  0.282696  0.816482
       B -0.087302  1.100230

#Pivot Tables
>>> 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  1.418757 -0.179666
1     one  B  foo -1.879024  1.291836
2     two  C  foo  0.536826 -0.009614
3   three  A  bar  1.006160  0.392149
4     one  B  bar -0.029716  0.264599
5     one  C  bar -1.146178 -0.057409
6     two  A  foo  0.100900 -1.425638
7   three  B  foo -1.035018  1.024098
8     one  C  foo  0.314665 -0.106062
9     one  A  bar -0.773723  1.824375
10    two  B  bar -1.170653  0.595974
11  three  C  bar  0.648740  1.167115
>>> pd.pivot_table(df, values='D', index=['A', 'B'], columns=['C'])
C             bar       foo
A     B                    
one   A -0.773723  1.418757
      B -0.029716 -1.879024
      C -1.146178  0.314665
three A  1.006160       NaN
      B       NaN -1.035018
      C  0.648740       NaN
two   A       NaN  0.100900
      B -1.170653       NaN
      C       NaN  0.536826

Categoricals

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
>>> df = pd.DataFrame({"id":[1,2,3,4,5,6], "raw_grade":['a', 'b', 'b', 'a', 'a', 'e']})
>>> df["grade"] = df["raw_grade"].astype("category")
>>> df["grade"]
0    a
1    b
2    b
3    a
4    a
5    e
Name: grade, dtype: category
Categories (3, object): [a, b, e]
>>> df["grade"].cat.categories = ["very good", "good", "very bad"]
>>> df["grade"] = df["grade"].cat.set_categories(["very bad", "bad", "medium", "good", "very good"])
>>>  df["grade"]
0    very good
1         good
2         good
3    very good
4    very good
5     very bad
Name: grade, dtype: category
Categories (5, object): [very bad, bad, medium, good, very good]
>>> df.sort_values(by="grade")
   id raw_grade      grade
5   6         e   very bad
1   2         b       good
2   3         b       good
0   1         a  very good
3   4         a  very good
4   5         a  very good
>>> df.groupby("grade").size()
grade
very bad     1
bad          0
medium       0
good         2
very good    3
dtype: int64

plotting

1
2
3
4
5
6
7
8
9
>>> ts = pd.Series(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000))
>>> ts = ts.cumsum()  # 累计值
>>> ts.plot()

>>> df = pd.DataFrame(np.random.randn(1000, 4), index=ts.index,
...                   columns=['A', 'B', 'C', 'D'])
...
>>> df = df.cumsum()
>>> plt.figure(); df.plot(); plt.legend(loc='best')

读写文件

1
2
3
4
5
6
7
8
9
10
11
#CSV
>>> df.to_csv('foo.csv')
>>> pd.read_csv('foo.csv')

#HDF5
>>> df.to_hdf('foo.h5','df')
>>> pd.read_hdf('foo.h5','df')

#Excel
>>> df.to_excel('foo.xlsx', sheet_name='Sheet1')
>>> pd.read_excel('foo.xlsx', 'Sheet1', index_col=None, na_values=['NA'])

其实啊，这边基本都是那个官方文档里面的，感觉这样复制一遍，记得多一点》》》