def test_deduplicate_evaluation_parameter_dependencies():
dependencies = {
"profile": [
{
"metric_kwargs_id": {
"column=norm":
["expect_column_mean_to_be_between.result.observed_value"]
}
},
{
"metric_kwargs_id": {
"column=norm": [
"expect_column_stdev_to_be_between.result.observed_value"
]
}
},
]
}
deduplicated = _deduplicate_evaluation_parameter_dependencies(dependencies)
# For test, use set to ignore order
deduplicated["profile"][0]["metric_kwargs_id"]["column=norm"] = set(
deduplicated["profile"][0]["metric_kwargs_id"]["column=norm"])
assert {
"profile": [{
"metric_kwargs_id": {
"column=norm": {
"expect_column_mean_to_be_between.result.observed_value",
"expect_column_stdev_to_be_between.result.observed_value",
}
}
}]
} == deduplicated
def get_evaluation_parameter_dependencies(self):
dependencies = {}
for expectation in self.expectations:
t = expectation.get_evaluation_parameter_dependencies()
nested_update(dependencies, t)
dependencies = _deduplicate_evaluation_parameter_dependencies(dependencies)
return dependencies
def get_evaluation_parameter_dependencies(self):
parsed_dependencies = dict()
for key, value in self.kwargs.items():
if isinstance(value, dict) and "$PARAMETER" in value:
param_string_dependencies = find_evaluation_parameter_dependencies(
value["$PARAMETER"]
)
nested_update(parsed_dependencies, param_string_dependencies)
dependencies = dict()
urns = parsed_dependencies.get("urns", [])
for string_urn in urns:
try:
urn = ge_urn.parseString(string_urn)
except ParserError:
logger.warning(
"Unable to parse great_expectations urn {}".format(
value["$PARAMETER"]
)
)
continue
if not urn.get("metric_kwargs"):
nested_update(
dependencies,
{urn["expectation_suite_name"]: [urn["metric_name"]]},
)
else:
nested_update(
dependencies,
{
urn["expectation_suite_name"]: [
{
"metric_kwargs_id": {
urn["metric_kwargs"]: [urn["metric_name"]]
}
}
]
},
)
dependencies = _deduplicate_evaluation_parameter_dependencies(dependencies)
return dependencies