dataset_json = sc.textFile("data/my_data.json")
    dataset = dataset_json.map(lambda x: json.loads(x))
    dataset.persist()
    dataset.take(2)

[{'movie': 'movie_name1',
  'release_date': '2011-01-11T10:26:12Z',
  'actor': 'actor_name1'},
 {'movie': 'movie_name2',
  'release_date': '2010-04-08T04:14:23Z',
  'actor': 'actor_name2'}]

dataset2 = dataset.filter(lambda line: line.lookup('release_date'))
    dataset2.first()

attributes = dataset.filter (lambda x: x.keys())
    attributes.take(2)

[{'movie': 'movie_name1',
  'release_date': '2011-01-11T10:26:12Z',
  'actor': 'actor_name1'},
 {'movie': 'movie_name2',
  'release_date': '2010-04-08T04:14:23Z',
  'actor': 'actor_name2'}]