

In [1]:

    
print 'hello world'









    



hello world

method in python



In [7]:

    
def add2(x):
    y = x + 2
    return y



In [8]:

    
i = 5



In [4]:

    
add2(i)









    Out[4]:





7



In [5]:

    
square = lambda x : x*x



In [6]:

    
square(3)









    Out[6]:





9

使用GraphLab Create



In [2]:

    
import graphlab



In [10]:

    
sf = graphlab.SFrame('board.csv')









    




Finished parsing file /Users/liubotong/Desktop/GitProject/code/ML_PY/board.csv






    




Parsing completed. Parsed 100 lines in 0.013068 secs.






    



------------------------------------------------------
Inferred types from first 100 line(s) of file as 
column_type_hints=[int,str,str,float,float,float,float]
If parsing fails due to incorrect types, you can correct
the inferred type list above and pass it to read_csv in
the column_type_hints argument
------------------------------------------------------






    




Finished parsing file /Users/liubotong/Desktop/GitProject/code/ML_PY/board.csv






    




Parsing completed. Parsed 942 lines in 0.015914 secs.



In [11]:

    
sf









    Out[11]:





    
        CityCode
        BoardId
        RoadName
        StartLon
        StartLat
        EndLon
        EndLat
    
    
        110000
        0010_103_001
        北京城市内快速路
        116.570446
        40.041606
        116.175351
        39.753424
    
    
        110000
        0010_105_001
        望京区域
        116.503079
        39.999301
        116.440662
        39.987544
    
    
        110000
        0010_105_002
        中关村区域
        116.317951
        39.985662
        116.305047
        39.975411
    
    
        110000
        0010_105_003
        北京CBD区域
        116.49044
        39.925039
        116.43419
        39.907748
    
    
        110000
        0010_105_004
        西单金融街区域
        116.374569
        39.92415
        116.355714
        39.906941
    
    
        110000
        0010_105_005
        工体三里屯区域
        116.462315
        39.941802
        116.433189
        39.922903
    
    
        110000
        0010_105_006
        东单王府井区域
        116.435875
        39.924635
        116.406065
        39.908152
    
    
        110000
        0010_105_007
        东直门区域
        116.447498
        39.951218
        116.416441
        39.933241
    
    
        110000
        0010_105_008
        西直门区域
        116.37341
        39.948227
        116.341493
        39.931744
    
    
        110000
        0010_105_009
        崇文门区域
        116.436086
        39.907991
        116.411858
        39.892235
    

[942 rows x 7 columns]
Note: Only the head of the SFrame is printed.
You can use print_rows(num_rows=m, num_columns=n) to print more rows and columns.



In [12]:

    
sf.head









    Out[12]:





<bound method SFrame.head of Columns:
	CityCode	int
	BoardId	str
	RoadName	str
	StartLon	float
	StartLat	float
	EndLon	float
	EndLat	float

Rows: 942

Data:
+----------+--------------+------------------+------------+-----------+
| CityCode |   BoardId    |     RoadName     |  StartLon  |  StartLat |
+----------+--------------+------------------+------------+-----------+
|  110000  | 0010_103_001 | 北京城市内快速路 | 116.570446 | 40.041606 |
|  110000  | 0010_105_001 |     望京区域     | 116.503079 | 39.999301 |
|  110000  | 0010_105_002 |    中关村区域    | 116.317951 | 39.985662 |
|  110000  | 0010_105_003 |   北京CBD区域    | 116.49044  | 39.925039 |
|  110000  | 0010_105_004 |  西单金融街区域  | 116.374569 |  39.92415 |
|  110000  | 0010_105_005 |  工体三里屯区域  | 116.462315 | 39.941802 |
|  110000  | 0010_105_006 |  东单王府井区域  | 116.435875 | 39.924635 |
|  110000  | 0010_105_007 |    东直门区域    | 116.447498 | 39.951218 |
|  110000  | 0010_105_008 |    西直门区域    | 116.37341  | 39.948227 |
|  110000  | 0010_105_009 |    崇文门区域    | 116.436086 | 39.907991 |
+----------+--------------+------------------+------------+-----------+
+------------+-----------+
|   EndLon   |   EndLat  |
+------------+-----------+
| 116.175351 | 39.753424 |
| 116.440662 | 39.987544 |
| 116.305047 | 39.975411 |
| 116.43419  | 39.907748 |
| 116.355714 | 39.906941 |
| 116.433189 | 39.922903 |
| 116.406065 | 39.908152 |
| 116.416441 | 39.933241 |
| 116.341493 | 39.931744 |
| 116.411858 | 39.892235 |
+------------+-----------+
[942 rows x 7 columns]
Note: Only the head of the SFrame is printed.
You can use print_rows(num_rows=m, num_columns=n) to print more rows and columns.>



In [13]:

    
sf.tail









    Out[13]:





<bound method SFrame.tail of Columns:
	CityCode	int
	BoardId	str
	RoadName	str
	StartLon	float
	StartLat	float
	EndLon	float
	EndLat	float

Rows: 942

Data:
+----------+--------------+------------------+------------+-----------+
| CityCode |   BoardId    |     RoadName     |  StartLon  |  StartLat |
+----------+--------------+------------------+------------+-----------+
|  110000  | 0010_103_001 | 北京城市内快速路 | 116.570446 | 40.041606 |
|  110000  | 0010_105_001 |     望京区域     | 116.503079 | 39.999301 |
|  110000  | 0010_105_002 |    中关村区域    | 116.317951 | 39.985662 |
|  110000  | 0010_105_003 |   北京CBD区域    | 116.49044  | 39.925039 |
|  110000  | 0010_105_004 |  西单金融街区域  | 116.374569 |  39.92415 |
|  110000  | 0010_105_005 |  工体三里屯区域  | 116.462315 | 39.941802 |
|  110000  | 0010_105_006 |  东单王府井区域  | 116.435875 | 39.924635 |
|  110000  | 0010_105_007 |    东直门区域    | 116.447498 | 39.951218 |
|  110000  | 0010_105_008 |    西直门区域    | 116.37341  | 39.948227 |
|  110000  | 0010_105_009 |    崇文门区域    | 116.436086 | 39.907991 |
+----------+--------------+------------------+------------+-----------+
+------------+-----------+
|   EndLon   |   EndLat  |
+------------+-----------+
| 116.175351 | 39.753424 |
| 116.440662 | 39.987544 |
| 116.305047 | 39.975411 |
| 116.43419  | 39.907748 |
| 116.355714 | 39.906941 |
| 116.433189 | 39.922903 |
| 116.406065 | 39.908152 |
| 116.416441 | 39.933241 |
| 116.341493 | 39.931744 |
| 116.411858 | 39.892235 |
+------------+-----------+
[942 rows x 7 columns]
Note: Only the head of the SFrame is printed.
You can use print_rows(num_rows=m, num_columns=n) to print more rows and columns.>

GraphLab Canvas



In [14]:

    
sf.show()









    



Canvas is accessible via web browser at the URL: http://localhost:55644/index.html
Opening Canvas in default web browser.



In [15]:

    
graphlab.canvas.set_target('ipynb')



In [19]:

    
sf['CityCode'].show(view='Categorical')

操作列数据



In [17]:

    
sf['CityCode']









    Out[17]:





dtype: int
Rows: 942
[110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 110000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, 310000, ... ]



In [18]:

    
sf['BoardId']









    Out[18]:





dtype: str
Rows: 942
['0010_103_001', '0010_105_001', '0010_105_002', '0010_105_003', '0010_105_004', '0010_105_005', '0010_105_006', '0010_105_007', '0010_105_008', '0010_105_009', '0010_105_010', '0010_105_011', '0010_105_012', '0010_106_001', '0010_106_002', '0010_106_003', '0010_106_004', '0010_106_005', '0010_106_006', '0010_106_007', '0010_106_008', '0010_106_009', '0010_106_010', '0010_106_011', '0010_106_012', '0010_106_013', '0010_106_014', '0010_106_015', '0010_106_016', '0010_106_017', '0010_106_018', '0010_106_019', '0010_106_020', '0010_106_021', '0010_106_022', '0010_106_023', '0010_106_024', '0010_106_025', '0010_106_026', '0010_106_027', '0010_106_028', '0010_106_029', '0010_106_030', '0010_106_031', '0010_106_032', '0010_106_033', '0010_106_034', '0010_106_035', '0010_106_036', '0010_106_037', '0010_106_038', '0010_106_039', '0010_106_040', '0010_106_041', '0010_106_042', '0010_106_043', '0010_106_044', '0010_106_045', '0010_106_046', '0010_106_047', '0010_106_048', '0021_103_001', '0021_105_001', '0021_105_002', '0021_105_003', '0021_105_004', '0021_105_005', '0021_105_006', '0021_105_007', '0021_105_008', '0021_106_001', '0021_106_002', '0021_106_003', '0021_106_004', '0021_106_005', '0021_106_006', '0021_106_007', '0021_106_008', '0021_106_009', '0021_106_010', '0021_106_011', '0021_106_012', '0021_106_013', '0021_106_014', '0021_106_015', '0021_106_016', '0021_106_017', '0021_106_018', '0021_106_019', '0021_106_020', '0021_106_021', '0021_106_022', '0021_106_023', '0021_106_024', '0021_106_025', '0021_106_026', '0021_106_027', '0021_106_028', '0021_106_029', '0021_106_030', ... ]



In [20]:

    
sf['CityCode'].mean()









    Out[20]:





331469.42675159225



In [21]:

    
sf['CityCode'].max()









    Out[21]:





610100

增加新列



In [36]:

    
sf['StartLocation'] = str(sf['StartLon']) + ',' + sf['RoadName']



In [37]:

    
sf









    Out[37]:





    
        CityCode
        BoardId
        RoadName
        StartLon
        StartLat
        EndLon
        EndLat
    
    
        110000
        0010_103_001
        北京城市内快速路
        116.570446
        40.041606
        116.175351
        39.753424
    
    
        110000
        0010_105_001
        望京区域
        116.503079
        39.999301
        116.440662
        39.987544
    
    
        110000
        0010_105_002
        中关村区域
        116.317951
        39.985662
        116.305047
        39.975411
    
    
        110000
        0010_105_003
        北京CBD区域
        116.49044
        39.925039
        116.43419
        39.907748
    
    
        110000
        0010_105_004
        西单金融街区域
        116.374569
        39.92415
        116.355714
        39.906941
    
    
        110000
        0010_105_005
        工体三里屯区域
        116.462315
        39.941802
        116.433189
        39.922903
    
    
        110000
        0010_105_006
        东单王府井区域
        116.435875
        39.924635
        116.406065
        39.908152
    
    
        110000
        0010_105_007
        东直门区域
        116.447498
        39.951218
        116.416441
        39.933241
    
    
        110000
        0010_105_008
        西直门区域
        116.37341
        39.948227
        116.341493
        39.931744
    
    
        110000
        0010_105_009
        崇文门区域
        116.436086
        39.907991
        116.411858
        39.892235
    


    
        StartLocation
    
    
        [116.570446, 116.503079,
116.317951, 116.49044, ...
    
    
        [116.570446, 116.503079,
116.317951, 116.49044, ...
    
    
        [116.570446, 116.503079,
116.317951, 116.49044, ...
    
    
        [116.570446, 116.503079,
116.317951, 116.49044, ...
    
    
        [116.570446, 116.503079,
116.317951, 116.49044, ...
    
    
        [116.570446, 116.503079,
116.317951, 116.49044, ...
    
    
        [116.570446, 116.503079,
116.317951, 116.49044, ...
    
    
        [116.570446, 116.503079,
116.317951, 116.49044, ...
    
    
        [116.570446, 116.503079,
116.317951, 116.49044, ...
    
    
        [116.570446, 116.503079,
116.317951, 116.49044, ...
    

[942 rows x 8 columns]
Note: Only the head of the SFrame is printed.
You can use print_rows(num_rows=m, num_columns=n) to print more rows and columns.



In [38]:

    
sf['CityCode'] +2









    Out[38]:





dtype: int
Rows: 942
[110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 110002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, 310002, ... ]



In [39]:

    
sf['CityCode'] * sf['CityCode']









    Out[39]:





dtype: int
Rows: 942
[12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 12100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, 96100000000, ... ]

应用apply函数来转换数据



In [ ]:

CityCode	BoardId	RoadName	StartLon	StartLat	EndLon	EndLat
110000	0010_103_001	北京城市内快速路	116.570446	40.041606	116.175351	39.753424
110000	0010_105_001	望京区域	116.503079	39.999301	116.440662	39.987544
110000	0010_105_002	中关村区域	116.317951	39.985662	116.305047	39.975411
110000	0010_105_003	北京CBD区域	116.49044	39.925039	116.43419	39.907748
110000	0010_105_004	西单金融街区域	116.374569	39.92415	116.355714	39.906941
110000	0010_105_005	工体三里屯区域	116.462315	39.941802	116.433189	39.922903
110000	0010_105_006	东单王府井区域	116.435875	39.924635	116.406065	39.908152
110000	0010_105_007	东直门区域	116.447498	39.951218	116.416441	39.933241
110000	0010_105_008	西直门区域	116.37341	39.948227	116.341493	39.931744
110000	0010_105_009	崇文门区域	116.436086	39.907991	116.411858	39.892235