convert.py

'''
Convert Yelp Academic Dataset from JSON to CSV

Requires Pandas (https://pypi.python.org/pypi/pandas)

By Paul Butler, No Rights Reserved
'''

import json
import pandas as pd
from glob import glob

def convert(x):
    ''' Convert a json string to a flat python dictionary
    which can be passed into Pandas. '''
    ob = json.loads(x)
    for k, v in ob.items():
        if isinstance(v, list):
            ob[k] = ','.join(v)
        elif isinstance(v, dict):
            for kk, vv in v.items():
                ob['%s_%s' % (k, kk)] = vv
            del ob[k]
    return ob

for json_filename in glob('*.json'):
    csv_filename = '%s.csv' % json_filename[:-5]
    print 'Converting %s to %s' % (json_filename, csv_filename)
    df = pd.DataFrame([convert(line) for line in file(json_filename)])
    df.to_csv(csv_filename, encoding='utf-8', index=False)

For some reason this code works for all of the json files except the user one. Any ideas? Here is the error msg:

TypeError Traceback (most recent call last)
C:\Files\Masters\455\Yelp\convert4.py in ()
29
30 for fname in FILES:
---> 31 df = pd.DataFrame([convert(line) for line in file('%s.json' % fname)])
32 df.to_csv('%s.csv' % fname, encoding='utf-8')

C:\Files\Masters\455\Yelp\convert4.py in convert(x)
21 for k, v in ob.items():
22 if isinstance(v, list):
---> 23 ob[k] = ','.join(v)
24 elif isinstance(v, dict):
25 for kk, vv in v.items():

TypeError: sequence item 0: expected string, int found