In [2]:

    

train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')
sample = pd.read_csv('sampleSubmission.csv')


    

In [7]:

    

train.head(2)


    

    
Out[7]:






  

    

      

      
TRIP_ID
      
CALL_TYPE
      
ORIGIN_CALL
      
ORIGIN_STAND
      
TAXI_ID
      
TIMESTAMP
      
DAY_TYPE
      
MISSING_DATA
      
POLYLINE
    
  
  

    

      
0
      
 1372636858620000589
      
 C
      
NaN
      
NaN
      
 20000589
      
 1372636858
      
 A
      
 False
      
 [[-8.618643,41.141412],[-8.618499,41.141376],[...
    
    

      
1
      
 1372637303620000596
      
 B
      
NaN
      
  7
      
 20000596
      
 1372637303
      
 A
      
 False
      
 [[-8.639847,41.159826],[-8.640351,41.159871],[...
    
  

In [8]:

    

test.head(2)


    

    
Out[8]:






  

    

      

      
TRIP_ID
      
CALL_TYPE
      
ORIGIN_CALL
      
ORIGIN_STAND
      
TAXI_ID
      
TIMESTAMP
      
DAY_TYPE
      
MISSING_DATA
      
POLYLINE
    
  
  

    

      
0
      
 T1
      
 B
      
NaN
      
 15
      
 20000542
      
 1408039037
      
 A
      
 False
      
 [[-8.585676,41.148522],[-8.585712,41.148639],[...
    
    

      
1
      
 T2
      
 B
      
NaN
      
 57
      
 20000108
      
 1408038611
      
 A
      
 False
      
 [[-8.610876,41.14557],[-8.610858,41.145579],[-...
    
  

In [6]:

    

sample.head(2)


    

    
Out[6]:






  

    

      

      
TRIP_ID
      
LATITUDE
      
LONGITUDE
    
  
  

    

      
0
      
 T1
      
 41.146504
      
-8.611317
    
    

      
1
      
 T2
      
 41.146504
      
-8.611317
    
  

In [5]:

    

gps = pd.read_csv('metaData_taxistandsID_name_GPSlocation.csv')


    

In [10]:

    

print gps[:5]


    

    




   ID  Descricao       Latitude  Longitude
0   1       Agra  41.1771457135  -8.609670
1   2    Alameda    41.15618964  -8.591064
2   3     Aldoar  41.1705249231  -8.665876
3   4  Alfândega  41.1437639911  -8.621803
4   5      Amial  41.1835097223  -8.612726

In [4]:

    

import pandas as pd


    

In [11]:

    

# 머신러닝을 쓰지말고 가까운데만 계산해서 제출해보자
test = pd.read_csv('test.csv')
gps = pd.read_csv('metaData_taxistandsID_name_GPSlocation.csv')


    

In [15]:

    

tmp = test.POLYLINE[0]
print eval(tmp)
print eval(tmp)[-1]


    

    




[[-8.585676, 41.148522], [-8.585712, 41.148639], [-8.585685, 41.148855], [-8.58573, 41.148927], [-8.585982, 41.148963], [-8.586396, 41.148954], [-8.586072, 41.14872], [-8.586324, 41.147847], [-8.586999, 41.14746], [-8.586576, 41.147154], [-8.584884, 41.146623]]
[-8.584884, 41.146623]

In [22]:

    

test = pd.read_csv('test.csv', usecols=['POLYLINE','TRIP_ID'],
                   converters={'POLYLINE': lambda x: eval(x)[-1]})


    

In [19]:

    

print test.head(2)
print test.POLYLINE[0][0]


    

    




  TRIP_ID                POLYLINE
0      T1  [-8.584884, 41.146623]
1      T2  [-8.601894, 41.163597]
-8.584884

In [23]:

    

test['LONGITUDE'] = test.POLYLINE.apply(lambda x: x[0])
test['LATITUDE'] = test.POLYLINE.apply(lambda x: x[1])

# Create your submission file
submission = pd.DataFrame({"TRIP_ID": test['TRIP_ID'], "LONGITUDE" : test['LONGITUDE'], "LATITUDE" : test['LATITUDE']})
submission.to_csv("submission.csv", index=False)


    

In [25]:

    

# kaggle LB
# 3.31766 211/326


    

In [27]:

    

pwd


    

    
Out[27]:





u'/home/ubuntu/taxia'