def validate_multiple_dataset_shape(
self, datasets: Dict[str, pd.DataFrame]) -> Dict:
"""Validates all datasets and returns map of dataset_name -> failures.
If map is empty, then all dataset shapes are valid."""
return common.ge_results_to_failure_map({
dataset_name: self._get_shape_expectations(dataset).validate()
for dataset_name, dataset in datasets.items()
})
def validate_multiple(self, field_mappings: FieldMappings) -> Dict[str, Dict]:
"""Returns map of field_name -> failures. If map is empty, the field mapping approvals are valid."""
return ge_results_to_failure_map(
{
field_name: self._get_expectations(field_mapping).validate()
for field_name, field_mapping in field_mappings.items()
}
)
def test_failure_map_values_unique(self):
dataset_ge = ge.from_pandas(TEST_DATA)
dataset_ge.set_default_expectation_argument("result_format",
"COMPLETE")
dataset_ge.expect_column_values_to_be_unique("column_one")
failure_map = common.ge_results_to_failure_map(
{"dataset": dataset_ge.validate()})
self.assertEqual(
{
"dataset": {
common.EXPECT_VALUES_UNIQUE_KEY: {
common.COLUMN_NAME_KEY: "column_one",
common.FAILED_VALUES_KEY: ["value1"],
}
}
},
failure_map,
)
def test_failure_map_values(self):
dataset_ge = ge.from_pandas(TEST_DATA,
dataset_class=ShapePandasDataset)
dataset_ge.set_default_expectation_argument("result_format",
"COMPLETE")
dataset_ge.expect_table_columns_to_be_in_set(
set(["column_one", "other_column"]))
failure_map = common.ge_results_to_failure_map(
{"dataset": dataset_ge.validate()})
self.assertEqual(
{
"dataset": {
common.EXPECT_COLUMNS_IN_SET_KEY: {
common.FAILED_VALUES_KEY: ["column_two"]
}
}
},
failure_map,
)
def test_failure_map_values_in_set(self):
dataset_ge = ge.from_pandas(TEST_DATA)
dataset_ge.set_default_expectation_argument("result_format",
"COMPLETE")
dataset_ge.expect_column_values_to_be_in_set(
"column_two", set(["invalid_value", "row1_col2"]))
failure_map = common.ge_results_to_failure_map(
{"dataset": dataset_ge.validate()})
self.assertEqual(
{
"dataset": {
common.EXPECT_VALUES_IN_SET_KEY: {
common.COLUMN_NAME_KEY: "column_two",
common.FAILED_VALUES_KEY: ["row2_col2"],
}
}
},
failure_map,
)
def test_failure_map_column_ordered_list(self):
dataset_ge = ge.from_pandas(TEST_DATA)
dataset_ge.set_default_expectation_argument("result_format",
"COMPLETE")
dataset_ge.expect_table_columns_to_match_ordered_list(
["column_one", "other_column"])
failure_map = common.ge_results_to_failure_map(
{"dataset": dataset_ge.validate()})
self.assertEqual(
{
"dataset": {
common.EXPECT_COLUMNS_MATCH_KEY: {
common.EXPECTED_ORDERED_LIST_KEY: [
"column_one",
"other_column",
],
common.FAILED_VALUES_KEY: ["column_two"],
}
}
},
failure_map,
)