def test_validation_only_considers_columns_in_df(self):
catalog = read_data_json("distribution_missing_column_in_data.json")
distrib_meta = catalog.get_distribution(identifier="125.1")
df = catalog.load_ts_distribution("125.1")
ValuesAreNumericValidation(df, distrib_meta, catalog).validate()
def test_validate_time_series_catalog(self):
catalog = read_data_json("valid_catalog.json")
validation = catalog.validate_time_series_catalog()
self.assertEqual(validation["status"], "OK")
def test_distribution_with_no_field_description_raises_error(self):
catalog = read_data_json("missing_field_description.json")
distribution = catalog.get_distributions()[0]
df = None
with self.assertRaises(NonExistentDescriptionError):
FieldDescriptionsValidation(df, distribution, catalog).validate()
def test_valid_catalog_has_empty_errors(self):
catalog = read_data_json("valid_catalog.json")
validation = catalog.validate_time_series_catalog()
self.assertFalse(validation["errors"])
def test_invalid_catalog_has_errors(self):
catalog = read_data_json("repeated_field_id.json")
validation = catalog.validate_time_series_catalog()
self.assertTrue(validation["errors"]["125.1"])
def test_xlsx_read(self):
catalog = read_data_json("catalog.xlsx")
self.assertTrue(catalog.get_distributions())
def test_invalid_catalog(self):
catalog = read_data_json("repeated_field_id.json")
validation = catalog.validate_time_series_catalog()
self.assertEqual(validation["status"], "ERROR")
def test_invalid_format_catalog(self):
catalog = read_data_json("missing_dataset_title.json")
validation = catalog.validate_catalog()
self.assertEqual(validation["status"], "ERROR")
def test_missing_field_identifier(self):
catalog = read_data_json("missing_dataset_title.json")
validation = catalog.validate_catalog()
self.assertEqual(validation["status"], "ERROR")
def test_multiple_errors(self):
data_json = read_data_json("repeated_field_id_and_description.json")
errors = get_distribution_errors(data_json, "125.1")
error_classes = [x.__class__ for x in errors]
self.assertIn(FieldIdRepetitionError, error_classes)
self.assertIn(FieldDescriptionRepetitionError, error_classes)
def test_get_errors_repeated_field_id_catalog(self):
data_json = read_data_json("repeated_field_id.json")
errors = get_distribution_errors(data_json, "125.1")
self.assertIn(FieldIdRepetitionError, [x.__class__ for x in errors])
def test_get_errors_of_valid_distribution_empty(self):
data_json = read_data_json("data.json")
errors = get_distribution_errors(data_json, "125.1")
self.assertFalse(errors)
def _read_csv(self, filename):
data_json = read_data_json(filename)
distribution = data_json.get_distributions()[0]
df = CSVReader(distribution).read()
return df
def test_read_from_file_source(self):
data_json = read_data_json("daily_periodicity_latin1.json")
distribution = data_json.get_distributions()[0]
path = csv_path("sample_data.csv")
df = CSVReader(distribution, file_source=path).read()
self.assertIn("title1", list(df.columns))
