def _get_domains(
self,
variables: Optional[ParameterContainer] = None,
) -> List[Domain]:
domains: List[Domain] = [Domain(domain_type=MetricDomainTypes.TABLE, )]
return domains
def _get_domains(
self,
variables: Optional[ParameterContainer] = None,
) -> List[Domain]:
"""
Obtains and returns domains for all columns of a table.
"""
batch_id: str = self.get_batch_id(variables=variables)
table_column_names: List[str] = self.get_validator(
variables=variables).get_metric(metric=MetricConfiguration(
metric_name="table.columns",
metric_domain_kwargs={
"batch_id": batch_id,
},
metric_value_kwargs=None,
metric_dependencies=None,
))
column_name: str
domains: List[Domain] = [
Domain(
domain_type=MetricDomainTypes.COLUMN,
domain_kwargs={
"column": column_name,
},
) for column_name in table_column_names
]
return domains
def column_Description_domain():
return Domain(
domain_type=MetricDomainTypes.COLUMN,
domain_kwargs={
"column": "Description",
"batch_id": "c260e179bb1bc81d84bba72a8110d8e2",
},
details=None,
)
def _get_domains(
self,
variables: Optional[ParameterContainer] = None,
) -> List[Domain]:
"""
Find the column suffix for each column and return all domains matching the specified suffix.
"""
column_name_suffixes: Union[str, Iterable,
List[str]] = self._column_name_suffixes
if isinstance(column_name_suffixes, str):
column_name_suffixes = [column_name_suffixes]
else:
if not isinstance(column_name_suffixes, (Iterable, List)):
raise ValueError(
"Unrecognized column_name_suffixes directive -- must be a list or a string."
)
batch_id: str = self.get_batch_id(variables=variables)
table_column_names: List[str] = self.get_validator(
variables=variables).get_metric(metric=MetricConfiguration(
metric_name="table.columns",
metric_domain_kwargs={
"batch_id": batch_id,
},
metric_value_kwargs=None,
metric_dependencies=None,
))
candidate_column_names: List[str] = list(
filter(
lambda candidate_column_name: candidate_column_name.endswith(
tuple(column_name_suffixes)),
table_column_names,
))
column_name: str
domains: List[Domain] = [
Domain(
domain_type=MetricDomainTypes.COLUMN,
domain_kwargs={
"column": column_name,
},
) for column_name in candidate_column_names
]
return domains
def _get_domains(
self,
variables: Optional[ParameterContainer] = None,
) -> List[Domain]:
"""
Find the semantic column type for each column and return all domains matching the specified type or types.
"""
batch_id: str = self.get_batch_id(variables=variables)
table_column_names: List[str] = self.get_validator(
variables=variables).get_metric(metric=MetricConfiguration(
metric_name="table.columns",
metric_domain_kwargs={
"batch_id": batch_id,
},
metric_value_kwargs=None,
metric_dependencies=None,
))
# First check the column name ends in "_id".
candidate_column_names: List[str] = list(
filter(
lambda candidate_column_name: candidate_column_name.endswith(
tuple(self._column_name_suffixes)),
table_column_names,
))
column_name: str
domains: List[Domain] = [
Domain(
domain_type=MetricDomainTypes.COLUMN,
domain_kwargs={
"column": column_name,
},
) for column_name in candidate_column_names
]
return domains
def table_Users_domain():
return Domain(
domain_type=MetricDomainTypes.TABLE,
domain_kwargs=None,
details=None,
)
def _get_domains(
self,
variables: Optional[ParameterContainer] = None,
) -> List[Domain]:
"""
Find the semantic column type for each column and return all domains matching the specified type or types.
"""
semantic_types: List[
SemanticDomainTypes] = _parse_semantic_domain_type_argument(
semantic_types=self._semantic_types)
batch_id: str = self.get_batch_id(variables=variables)
column_types_dict_list: List[Dict[str, Any]] = self.get_validator(
variables=variables).get_metric(metric=MetricConfiguration(
metric_name="table.column_types",
metric_domain_kwargs={
"batch_id": batch_id,
},
metric_value_kwargs={
"include_nested": True,
},
metric_dependencies=None,
))
table_column_names: List[str] = self.get_validator(
variables=variables).get_metric(metric=MetricConfiguration(
metric_name="table.columns",
metric_domain_kwargs={
"batch_id": batch_id,
},
metric_value_kwargs=None,
metric_dependencies=None,
))
column_name: str
# A semantic type is distinguished from the structured column type;
# An example structured column type would be "integer". The inferred semantic type would be "id".
table_column_name_to_inferred_semantic_domain_type_mapping: Dict[
str, SemanticDomainTypes] = {
column_name:
self.infer_semantic_domain_type_from_table_column_type(
column_types_dict_list=column_types_dict_list,
column_name=column_name,
).semantic_domain_type
for column_name in table_column_names
}
candidate_column_names: List[str] = list(
filter(
lambda candidate_column_name:
table_column_name_to_inferred_semantic_domain_type_mapping[
candidate_column_name] in semantic_types,
table_column_names,
))
domains: List[Domain] = [
Domain(
domain_type=MetricDomainTypes.COLUMN,
domain_kwargs={
"column": column_name,
},
details={
"inferred_semantic_domain_type":
table_column_name_to_inferred_semantic_domain_type_mapping[
column_name],
},
) for column_name in candidate_column_names
]
return domains