def _sqlalchemy(cls, column, value_set, parse_strings_as_datetimes,
**kwargs):
if parse_strings_as_datetimes:
parsed_value_set = parse_value_set(value_set)
else:
parsed_value_set = value_set
return column.notin_(tuple(parsed_value_set))
def _validate(
self,
configuration: ExpectationConfiguration,
metrics: Dict,
runtime_configuration: dict = None,
execution_engine: ExecutionEngine = None,
):
parse_strings_as_datetimes = self.get_success_kwargs(configuration).get(
"parse_strings_as_datetimes"
)
observed_value_counts = metrics.get("column.value_counts")
observed_value_set = set(observed_value_counts.index)
value_set = self.get_success_kwargs(configuration).get("value_set") or []
if parse_strings_as_datetimes:
parsed_value_set = parse_value_set(value_set)
else:
parsed_value_set = value_set
expected_value_set = set(parsed_value_set)
if not expected_value_set:
success = True
else:
success = observed_value_set.issubset(expected_value_set)
return {
"success": success,
"result": {
"observed_value": sorted(list(observed_value_set)),
"details": {"value_counts": observed_value_counts},
},
}
def _pandas(
cls,
column,
value_set,
**kwargs,
):
# no need to parse as datetime; just compare the strings as is
parse_strings_as_datetimes: bool = (
kwargs.get("parse_strings_as_datetimes") or False
)
if parse_strings_as_datetimes:
# deprecated-v0.13.41
warnings.warn(
"""The parameter "parse_strings_as_datetimes" is deprecated as of v0.13.41 in \
v0.16. As part of the V3 API transition, we've moved away from input transformation. For more information, \
please see: https://greatexpectations.io/blog/why_we_dont_do_transformations_for_expectations/
""",
DeprecationWarning,
)
if value_set is None:
# Vacuously true
return np.ones(len(column), dtype=np.bool_)
if pd.api.types.is_datetime64_any_dtype(column):
parsed_value_set = parse_value_set(value_set=value_set)
else:
parsed_value_set = value_set
return ~column.isin(parsed_value_set)
def _pandas(
cls,
column,
value_set,
**kwargs,
):
# no need to parse as datetime; just compare the strings as is
parse_strings_as_datetimes: bool = (
kwargs.get("parse_strings_as_datetimes") or False)
if parse_strings_as_datetimes:
warnings.warn(
f"""The parameter "parse_strings_as_datetimes" is no longer supported and will be deprecated in a \
future release. Please update code accordingly. Moreover, in "{cls.__name__}._pandas()", it is not used.
""",
DeprecationWarning,
)
if value_set is None:
# Vacuously true
return np.ones(len(column), dtype=np.bool_)
if pd.api.types.is_datetime64_any_dtype(column):
parsed_value_set = parse_value_set(value_set=value_set)
else:
parsed_value_set = value_set
return ~column.isin(parsed_value_set)
def _pandas(cls, column, value_set, **kwargs):
if value_set is None:
# Vacuously true
return np.ones(len(column), dtype=np.bool_)
if pd.api.types.is_datetime64_any_dtype(column):
parsed_value_set = parse_value_set(value_set=value_set)
else:
parsed_value_set = value_set
return ~column.isin(parsed_value_set)
def _validate(
self,
configuration: ExpectationConfiguration,
metrics: Dict,
runtime_configuration: dict = None,
execution_engine: ExecutionEngine = None,
):
parse_strings_as_datetimes = self.get_success_kwargs(
configuration).get("parse_strings_as_datetimes")
observed_value_counts = metrics.get("column.value_counts")
value_set = self.get_success_kwargs(configuration).get("value_set")
if parse_strings_as_datetimes:
# deprecated-v0.13.41
warnings.warn(
"""The parameter "parse_strings_as_datetimes" is deprecated as of v0.13.41 in \
v0.16. As part of the V3 API transition, we've moved away from input transformation. For more information, \
please see: https://greatexpectations.io/blog/why_we_dont_do_transformations_for_expectations/
""",
DeprecationWarning,
)
parsed_value_set = parse_value_set(value_set)
observed_value_counts.index = pd.to_datetime(
observed_value_counts.index)
else:
parsed_value_set = value_set
observed_value_set = set(observed_value_counts.index)
expected_value_set = set(parsed_value_set)
return {
"success": observed_value_set.issuperset(expected_value_set),
"result": {
"observed_value": sorted(list(observed_value_set)),
"details": {
"value_counts": observed_value_counts
},
},
}
def _validate(
self,
configuration: ExpectationConfiguration,
metrics: Dict,
runtime_configuration: dict = None,
execution_engine: ExecutionEngine = None,
):
parse_strings_as_datetimes = self.get_success_kwargs(
configuration).get("parse_strings_as_datetimes")
observed_value_counts = metrics.get("column.value_counts")
value_set = self.get_success_kwargs(configuration).get("value_set")
if parse_strings_as_datetimes:
warnings.warn(
"""The parameter "parse_strings_as_datetimes" is no longer supported and will be deprecated in a \
future release. Please update code accordingly.
""",
DeprecationWarning,
)
parsed_value_set = parse_value_set(value_set)
observed_value_counts.index = pd.to_datetime(
observed_value_counts.index)
else:
parsed_value_set = value_set
observed_value_set = set(observed_value_counts.index)
expected_value_set = set(parsed_value_set)
return {
"success": observed_value_set.issuperset(expected_value_set),
"result": {
"observed_value": sorted(list(observed_value_set)),
"details": {
"value_counts": observed_value_counts
},
},
}