def _get_targets(cls, data: d3m_dataframe, hyperparams: Hyperparams):
if not hyperparams['use_semantic_types']:
return data, list(data.columns), []
metadata = data.metadata
def can_produce_column(column_index: int) -> bool:
accepted_semantic_types = set()
accepted_semantic_types.add(
"https://metadata.datadrivendiscovery.org/types/TrueTarget")
column_metadata = metadata.query(
(metadata_base.ALL_ELEMENTS, column_index))
semantic_types = set(column_metadata.get('semantic_types', []))
if len(semantic_types) == 0:
cls.logger.warning(
"No semantic types found in column metadata")
return False
# Making sure all accepted_semantic_types are available in semantic_types
if len(accepted_semantic_types - semantic_types) == 0:
return True
return False
target_column_indices, target_columns_not_to_produce = common_utils.get_columns_to_use(
metadata,
use_columns=hyperparams['use_output_columns'],
exclude_columns=hyperparams['exclude_output_columns'],
can_use_column=can_produce_column)
targets = common_utils.select_columns(data, target_column_indices)
target_column_names = []
for idx in target_column_indices:
target_column_names.append(data.columns[idx])
return targets, target_column_names, target_column_indices
def _get_columns(
cls, inputs_metadata: metadata_base.DataMetadata,
hyperparams: hyperparams.Hyperparams) -> typing.Sequence[int]:
def can_use_column(column_index: int) -> bool:
return cls._can_use_column(inputs_metadata, column_index)
columns_to_use, columns_not_to_use = utils.get_columns_to_use(
inputs_metadata, hyperparams['use_columns'],
hyperparams['exclude_columns'], can_use_column)
return columns_to_use
def _get_columns_to_fit(cls, inputs: Inputs, hyperparams: LablerHyperparams):
if not hyperparams['use_semantic_types']:
return inputs, list(range(len(inputs.columns)))
inputs_metadata = inputs.metadata
def can_produce_column(column_index: int) -> bool:
return cls._can_produce_column(inputs_metadata, column_index, hyperparams)
columns_to_produce, columns_not_to_produce = common_utils.get_columns_to_use(
inputs_metadata, use_columns=hyperparams['use_columns'], exclude_columns=hyperparams['exclude_columns'],
can_use_column=can_produce_column)
return inputs.iloc[:, columns_to_produce], columns_to_produce
