def test_save(self):
for dataset_name in self.TEST_DATASETS:
dataset = Dataset().save(self.test_dataset_ids[dataset_name])
record = dataset.record
self.assertTrue(isinstance(record, dict))
self.assertTrue('_id' in record.keys())
def setUp(self):
TestBase.setUp(self)
self.dataset = Dataset()
self.dataset.save(
self.test_dataset_ids['good_eats_with_calculations.csv'])
dframe = recognize_dates(
self.get_data('good_eats_with_calculations.csv'))
self.dataset.save_observations(dframe)
self.group = None
self.places = 5
def test_aggregations_datasets_with_multigroup(self):
self.dataset_id = self._post_file()
group = 'food_type,rating'
self._post_calculations(self.default_formulae + ['sum(amount)'], group)
results = self._test_aggregations([group])
# only so we can split
dataset = Dataset()
row_keys = (dataset.split_groups(group) + ['sum_amount_']).sort()
for row in results:
sorted_row_keys = row.keys().sort()
self.assertEqual(sorted_row_keys, row_keys)
self.assertTrue(isinstance(row.values()[0], basestring))
self.assertTrue(isinstance(row.values()[1], basestring))
self.assertTrue(isinstance(row.values()[2], float))
def test_summary_with_multigroup(self):
dataset_id = self._post_file()
group_columns = 'rating,food_type'
results = self.controller.summary(
dataset_id,
group=group_columns,
select=self.controller.SELECT_ALL_FOR_SUMMARY)
results = self._test_summary_results(results)
self.assertFalse(Datasets.ERROR in results.keys())
self.assertTrue(group_columns in results.keys())
# for split
dataset = Dataset()
self.assertEqual(
len(dataset.split_groups(results[group_columns].keys()[0])),
len(dataset.split_groups(group_columns)))
def __create_or_update(self, url=None, csv_file=None, json_file=None,
schema=None, na_values=[], perish=0,
dataset_id=None):
result = None
error = 'url, csv_file or schema required'
try:
if schema or url or csv_file or json_file:
if dataset_id is None:
dataset = Dataset()
dataset.save()
else:
dataset = Dataset.find_one(dataset_id)
Observation.delete_all(dataset)
if schema:
dataset.import_schema(schema)
na_values = safe_json_loads(na_values)
if url:
dataset.import_from_url(url, na_values=na_values)
elif csv_file:
dataset.import_from_csv(csv_file, na_values=na_values)
elif json_file:
dataset.import_from_json(json_file)
result = {Dataset.ID: dataset.dataset_id}
perish = parse_int(perish)
perish and dataset.delete(countdown=perish)
except urllib2.URLError:
error = 'could not load: %s' % url
except IOError:
error = 'could not get a filehandle for: %s' % csv_file
except JSONError as e:
error = e.__str__()
self.set_response_params(result, success_status_code=201)
return self._dump_or_error(result, error)
def setUp(self):
TestBase.setUp(self)
self.dataset = Dataset()
self.dataset.save(self.test_dataset_ids['good_eats.csv'])
self.formula = 'rating'
self.name = 'test'
def setUp(self):
TestBase.setUp(self)
self.dataset = Dataset()
self.dataset.save(self.test_dataset_ids['good_eats.csv'])
self.query_args = QueryArgs({"rating": "delectible"})
