def test_validate_with_invalid_result(validate_result_dict):
with open(
file_relative_path(__file__, "./test_sets/titanic_expectations.json")
) as f:
my_expectation_suite = expectationSuiteSchema.loads(f.read())
with mock.patch("uuid.uuid1") as uuid:
uuid.return_value = "1234"
my_df = ge.read_csv(
file_relative_path(__file__, "./test_sets/Titanic.csv"),
expectation_suite=my_expectation_suite,
)
my_df.set_default_expectation_argument("result_format", "COMPLETE")
results = my_df.validate() # catch_exceptions=True is default
with open(
file_relative_path(
__file__,
"./test_sets/titanic_expected_data_asset_validate_results_with_exceptions.json",
)
) as f:
expected_results = expectationSuiteValidationResultSchema.loads(f.read())
del results.meta["great_expectations_version"]
del results.meta["expectation_suite_meta"]["great_expectations_version"]
for result in results.results:
result.exception_info.pop("exception_traceback")
assert results.to_json_dict() == expected_results.to_json_dict()
def test_validate_with_invalid_result_catch_exceptions_false(validate_result_dict):
with open(file_relative_path(__file__, "./test_sets/titanic_expectations.json")) as f:
my_expectation_suite = expectationSuiteSchema.loads(f.read())
with mock.patch("uuid.uuid1") as uuid:
uuid.return_value = "1234"
my_df = ge.read_csv(
file_relative_path(__file__, "./test_sets/Titanic.csv"),
expectation_suite=my_expectation_suite
)
my_df.set_default_expectation_argument("result_format", "COMPLETE")
with pytest.raises(InvalidCacheValueError):
my_df.validate(catch_exceptions=False)
def test_validate_with_invalid_result_catch_exceptions_false(empty_data_context):
context: DataContext = empty_data_context
with open(
file_relative_path(__file__, "./test_sets/titanic_expectations.json")
) as f:
my_expectation_suite_dict: dict = expectationSuiteSchema.loads(f.read())
my_expectation_suite: ExpectationSuite = ExpectationSuite(
**my_expectation_suite_dict, data_context=context
)
with mock.patch("uuid.uuid1") as uuid:
uuid.return_value = "1234"
my_df = ge.read_csv(
file_relative_path(__file__, "./test_sets/Titanic.csv"),
expectation_suite=my_expectation_suite,
)
my_df.set_default_expectation_argument("result_format", "COMPLETE")
with pytest.raises(InvalidCacheValueError):
with pytest.warns(Warning, match=r"No great_expectations version found"):
my_df.validate(catch_exceptions=False)
def test_validate():
with open(
file_relative_path(__file__, "./test_sets/titanic_expectations.json")
) as f:
my_expectation_suite = expectationSuiteSchema.loads(f.read())
with mock.patch("uuid.uuid1") as uuid:
uuid.return_value = "1234"
my_df = ge.read_csv(
file_relative_path(__file__, "./test_sets/Titanic.csv"),
expectation_suite=my_expectation_suite,
)
my_df.set_default_expectation_argument("result_format", "COMPLETE")
results = my_df.validate(catch_exceptions=False)
with open(
file_relative_path(
__file__, "./test_sets/titanic_expected_data_asset_validate_results.json"
)
) as f:
expected_results = expectationSuiteValidationResultSchema.loads(f.read())
del results.meta["great_expectations_version"]
del results.meta["expectation_suite_meta"]["great_expectations_version"]
assert results.to_json_dict() == expected_results.to_json_dict()
# Now, change the results and ensure they are no longer equal
results.results[0] = ExpectationValidationResult()
assert results.to_json_dict() != expected_results.to_json_dict()
# Finally, confirm that only_return_failures works
# and does not affect the "statistics" field.
validation_results = my_df.validate(only_return_failures=True)
del validation_results.meta["great_expectations_version"]
del validation_results.meta["expectation_suite_meta"]["great_expectations_version"]
expected_results = ExpectationSuiteValidationResult(
meta={
"expectation_suite_name": "titanic",
"run_id": {"run_name": None, "run_time": "1955-11-05T00:00:00+00:00"},
"validation_time": "19551105T000000.000000Z",
"batch_kwargs": {"ge_batch_id": "1234"},
"expectation_suite_meta": {},
"batch_markers": {},
"batch_parameters": {},
},
results=[
ExpectationValidationResult(
expectation_config=ExpectationConfiguration(
expectation_type="expect_column_values_to_be_in_set",
kwargs={"column": "PClass", "value_set": ["1st", "2nd", "3rd"]},
),
success=False,
exception_info={
"exception_message": None,
"exception_traceback": None,
"raised_exception": False,
},
result={
"partial_unexpected_index_list": [456],
"unexpected_count": 1,
"unexpected_list": ["*"],
"unexpected_percent": 0.07616146230007616,
"element_count": 1313,
"missing_percent": 0.0,
"partial_unexpected_counts": [{"count": 1, "value": "*"}],
"partial_unexpected_list": ["*"],
"unexpected_percent_total": 0.07616146230007616,
"unexpected_percent_nonmissing": 0.07616146230007616,
"missing_count": 0,
"unexpected_index_list": [456],
},
)
],
success=expected_results.success, # unaffected
statistics=expected_results["statistics"], # unaffected
)
assert validation_results.to_json_dict() == expected_results.to_json_dict()
def test_get_and_save_expectation_suite(tmp_path_factory):
directory_name = str(
tmp_path_factory.mktemp("test_get_and_save_expectation_config"))
df = ge.dataset.PandasDataset({
"x": [1, 2, 4],
"y": [1, 2, 5],
"z": ["hello", "jello", "mello"],
})
df.expect_column_values_to_be_in_set("x", [1, 2, 4])
df.expect_column_values_to_be_in_set("y", [1, 2, 4],
catch_exceptions=True,
include_config=True)
df.expect_column_values_to_match_regex("z", "ello")
### First test set ###
output_config = ExpectationSuite(
expectations=[
ExpectationConfiguration(
expectation_type="expect_column_values_to_be_in_set",
kwargs={
"column": "x",
"value_set": [1, 2, 4]
},
),
ExpectationConfiguration(
expectation_type="expect_column_values_to_match_regex",
kwargs={
"column": "z",
"regex": "ello"
},
),
],
expectation_suite_name="default",
data_asset_type="Dataset",
meta={"great_expectations_version": ge.__version__},
)
assert output_config == df.get_expectation_suite()
df.save_expectation_suite(directory_name + "/temp1.json")
with open(directory_name + "/temp1.json") as infile:
loaded_config = expectationSuiteSchema.loads(infile.read())
assert output_config == loaded_config
### Second test set ###
output_config = ExpectationSuite(
expectations=[
ExpectationConfiguration(
expectation_type="expect_column_values_to_be_in_set",
kwargs={
"column": "x",
"value_set": [1, 2, 4]
},
),
ExpectationConfiguration(
expectation_type="expect_column_values_to_be_in_set",
kwargs={
"column": "y",
"value_set": [1, 2, 4]
},
),
ExpectationConfiguration(
expectation_type="expect_column_values_to_match_regex",
kwargs={
"column": "z",
"regex": "ello"
},
),
],
expectation_suite_name="default",
data_asset_type="Dataset",
meta={"great_expectations_version": ge.__version__},
)
assert output_config == df.get_expectation_suite(
discard_failed_expectations=False)
df.save_expectation_suite(directory_name + "/temp2.json",
discard_failed_expectations=False)
with open(directory_name + "/temp2.json") as infile:
loaded_suite = expectationSuiteSchema.loads(infile.read())
assert output_config == loaded_suite
### Third test set ###
output_config = ExpectationSuite(
expectations=[
ExpectationConfiguration(
expectation_type="expect_column_values_to_be_in_set",
kwargs={
"column": "x",
"value_set": [1, 2, 4],
"result_format": "BASIC",
},
),
ExpectationConfiguration(
expectation_type="expect_column_values_to_match_regex",
kwargs={
"column": "z",
"regex": "ello",
"result_format": "BASIC"
},
),
],
expectation_suite_name="default",
data_asset_type="Dataset",
meta={"great_expectations_version": ge.__version__},
)
assert output_config == df.get_expectation_suite(
discard_result_format_kwargs=False,
discard_include_config_kwargs=False,
discard_catch_exceptions_kwargs=False,
)
df.save_expectation_suite(
directory_name + "/temp3.json",
discard_result_format_kwargs=False,
discard_include_config_kwargs=False,
discard_catch_exceptions_kwargs=False,
)
with open(directory_name + "/temp3.json") as infile:
loaded_suite = expectationSuiteSchema.loads(infile.read())
assert output_config == loaded_suite