def profiling_column(self, variable_metadata: VariableMetadata,
column: pd.Series) -> VariableMetadata:
"""Profiling single column for necessary fields of metadata, if data is present .
Args:
variable_metadata: the original VariableMetadata instance.
column: the column to profile.
Returns:
profiled VariableMetadata instance
"""
if not variable_metadata.name:
variable_metadata.name = column.name
if not variable_metadata.description:
variable_metadata.description = self.profiler.construct_variable_description(
column)
if variable_metadata.named_entity is None:
variable_metadata.named_entity = self.profiler.profile_named_entity(
column)
if variable_metadata.temporal_coverage:
if variable_metadata.temporal_coverage[
'start'] or not variable_metadata.temporal_coverage['end']:
variable_metadata.temporal_coverage = self.profiler.profile_temporal_coverage(
variable_metadata.temporal_coverage, column)
return variable_metadata
def basic_profiling_column(cls, description: dict,
variable_metadata: VariableMetadata,
column: pd.Series) -> VariableMetadata:
"""Profiling single column for necessary fields of metadata, if data is present .
Args:
description: description dict about the column.
variable_metadata: the original VariableMetadata instance.
column: the column to profile.
Returns:
profiled VariableMetadata instance
"""
if not variable_metadata.name:
variable_metadata.name = str(column.name)
if not variable_metadata.description:
variable_metadata.description = cls.construct_variable_description(
column)
if variable_metadata.named_entity is None:
variable_metadata.named_entity = cls.profile_named_entity(column)
elif variable_metadata.named_entity is False and not description:
if cls.named_entity_column_recognize(column):
variable_metadata.named_entity = cls.profile_named_entity(
column)
if variable_metadata.temporal_coverage is not False:
if not variable_metadata.temporal_coverage[
'start'] or not variable_metadata.temporal_coverage['end']:
variable_metadata.temporal_coverage = cls.profile_temporal_coverage(
column=column,
coverage=variable_metadata.temporal_coverage)
elif not description:
temporal_coverage = cls.profile_temporal_coverage(column=column)
if temporal_coverage:
variable_metadata.temporal_coverage = temporal_coverage
if not variable_metadata.semantic_type:
variable_metadata.semantic_type = cls.profile_semantic_type(column)
return variable_metadata