def import_dataset(_file, dataset): """ For reading a URL and saving the corresponding dataset. """ dframe = read_csv(_file) Dataset.build_schema(dataset, dframe.dtypes) Observation.save(dframe, dataset)
def _save_records(self): records = Observation.save(self.test_data['good_eats.csv'], self.dataset) cursor = Observation.find(self.dataset) records = [x for x in cursor] self.assertTrue(isinstance(records, list)) self.assertTrue(isinstance(records[0], dict)) self.assertTrue('_id' in records[0].keys()) return records
def setUp(self): TestBase.setUp(self) self.dataset = Dataset.save(self.test_dataset_ids['good_eats.csv']) dframe = self.test_data['good_eats.csv'] Dataset.build_schema(self.dataset, dframe.dtypes) Observation.save(dframe, self.dataset) self.calculations = [ 'rating', 'gps', 'amount + gps_alt', 'amount - gps_alt', 'amount + 5', 'amount - gps_alt + 2.5', 'amount * gps_alt', 'amount / gps_alt', 'amount * gps_alt / 2.5', 'amount + gps_alt * gps_precision', '(amount + gps_alt) * gps_precision', 'amount = 2', '10 < amount', '10 < amount + gps_alt', 'not amount = 2', 'not(amount = 2)', 'amount = 2 and 10 < amount', 'amount = 2 or 10 < amount', 'not not amount = 2 or 10 < amount', 'not amount = 2 or 10 < amount', '(not amount = 2) or 10 < amount', 'not(amount = 2 or 10 < amount)', 'amount ^ 3', '(amount + gps_alt) ^ 2 + 100', '-amount', '-amount < gps_alt - 100', 'rating in ["delectible"]', 'risk_factor in ["low_risk"]', 'amount in ["9.0", "2.0", "20.0"]', '(risk_factor in ["low_risk"]) and (amount in ["9.0", "20.0"])', ] self.places = 5
def _save_observations_and_calculation(self, formula=None): if not formula: formula = self.formula Observation.save(self.test_data['good_eats.csv'], self.dataset) return Calculation.save(self.dataset, formula, self.name)
def test_save_over_bulk(self): Observation.save(self.test_data['good_eats_large.csv'], self.dataset) cursor = Observation.find(self.dataset) records = [x for x in cursor] self.assertEqual(len(records), 1001)
def _save_observations(self): return Observation.save(self.test_data['good_eats.csv'], self.dataset)