In [1]:

    

import json
import pandas as pd


    

In [2]:

    

dataset = pd.read_csv('EVA_restoswithlocationsANDfixes.csv')
dataset.head(n=5)


    

    
Out[2]:






  

    

      

      
city
      
name
      
street
      
tags
      
zipcode
      
full_address
      
latlon
      
missing
    
  
  

    

      
0
      
Neerijse
      
Biesbemd
      
Kamstraat 33
      
['Approved by EVA', 'EVA voordeel', 'Veganvrie...
      
3040
      
Kamstraat 33 3040 Neerijse
      
(50.8127340562564, 4.622892881244533)
      
False
    
    

      
1
      
Antwerpen
      
Falafel Shami
      
Hoogstraat 47
      
['Snack', '100% vegetarisch', 'Approved by EVA...
      
2000
      
Hoogstraat 47 2000 Antwerpen
      
(51.21912277399896, 4.39791278664577)
      
False
    
    

      
2
      
Antwerpen
      
Falafel Tof
      
Hoogstraat 32
      
['Eethuis', 'Snack', '100% vegetarisch', 'Appr...
      
2000
      
Hoogstraat 32 2000 Antwerpen
      
(51.219967595445304, 4.398256839416387)
      
False
    
    

      
3
      
Antwerpen
      
Falafeltof
      
Hoogstraat 32
      
['Snack', '100% vegetarisch', 'Approved by EVA...
      
2000
      
Hoogstraat 32 2000 Antwerpen
      
(51.219967595445304, 4.398256839416387)
      
False
    
    

      
4
      
Deurle
      
Markies de Salade
      
Xavier de Cocklaan 69
      
['Eethuis', '100% plantaardig', '100% vegetari...
      
9831
      
Xavier de Cocklaan 69 9831 Deurle
      
(51.00079815695149, 3.614998033550879)
      
False
    
  

In [5]:

    

dataset[dataset['missing'] == True].shape


    

    
Out[5]:





(0, 8)

In [11]:

    

interesting_cols = ['city', 'name', 'street', 'tags', 'zipcode', 'latlon']
dataset = dataset[interesting_cols]


    

In [13]:

    

dataset.head(n=3)


    

    
Out[13]:






  

    

      

      
city
      
name
      
street
      
tags
      
zipcode
      
latlon
    
  
  

    

      
0
      
Neerijse
      
Biesbemd
      
Kamstraat 33
      
['Approved by EVA', 'EVA voordeel', 'Veganvrie...
      
3040
      
(50.8127340562564, 4.622892881244533)
    
    

      
1
      
Antwerpen
      
Falafel Shami
      
Hoogstraat 47
      
['Snack', '100% vegetarisch', 'Approved by EVA...
      
2000
      
(51.21912277399896, 4.39791278664577)
    
    

      
2
      
Antwerpen
      
Falafel Tof
      
Hoogstraat 32
      
['Eethuis', 'Snack', '100% vegetarisch', 'Appr...
      
2000
      
(51.219967595445304, 4.398256839416387)
    
  

In [18]:

    

dataset['lat'] = dataset['latlon'].apply(lambda l: l[1:len(l)-1].split(',')[0])
dataset['lon'] = dataset['latlon'].apply(lambda l: l[1:len(l)-1].split(',')[1])


    

In [20]:

    

interesting_cols = ['city', 'name', 'street', 'tags', 'zipcode', 'lat', 'lon']
dataset = dataset[interesting_cols]


    

In [24]:

    

tempfile = 'testjsonrestos.json'
dataset.to_json(tempfile, orient='records')


    

In [26]:

    

data = []
with open(tempfile) as f:
    for line in f:
        data.append(json.loads(line))


    

In [46]:

    

records = data[0]

parsedRecs = []

for rec in records:
    testObj = {
        'city'   : rec['city'],
        'lat'    : float(rec['lat']),
        'lon'    : float(rec['lon']),
        'name'   : rec['name'],
        'street' : rec['street'],
        'tags'   : eval(rec['tags']),
        'zip'    : rec['zipcode']
    }
    
    parsedRecs.append(testObj)


    

In [49]:

    

with open('restodata.json', 'w') as outfile:
    json.dump(parsedRecs, outfile, sort_keys=True, indent=4, separators=(',', ':'))


    

In [42]:

    

testobj = {}
testobj['city']


    

    




['Approved by EVA', 'EVA voordeel', 'Veganvriendelijk']

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    

json.dumps(, sort_keys=True, indent=2, separators=(',', ': '))