def _update_data_by_remove_repeated_ids(first_loop_data: DataBase,
light_curve_data: DataBase,
id_key_name: str,
pool_labels_class: str = 'Ia') -> Tuple[
DataBase, DataBase]:
"""
Updates first loop and initial data by removing repetitive id indices
Parameters
----------
first_loop_data
first loop light curve data
light_curve_data
initial light curve training data
id_key_name
object identification key name
pool_labels_class
pool labels class name
"""
repeated_id_flags = np.in1d(
first_loop_data.pool_metadata[id_key_name].values,
light_curve_data.train_metadata[id_key_name].values)
first_loop_data.pool_metadata = first_loop_data.pool_metadata[
~repeated_id_flags]
first_loop_data.pool_features = first_loop_data.pool_features[
~repeated_id_flags]
pool_labels = (
first_loop_data.pool_metadata['type'].values == pool_labels_class)
first_loop_data.pool_labels = pool_labels.astype(int)
light_curve_data.pool_features = first_loop_data.pool_features
light_curve_data.pool_metadata = first_loop_data.pool_metadata
light_curve_data.pool_labels = first_loop_data.pool_labels
return first_loop_data, light_curve_data
def _update_light_curve_data_for_next_epoch(
light_curve_data: DataBase, next_day_data: DataBase,
canonical_data: DataBase, is_queryable: bool, strategy: str,
is_separate_files: bool) -> DataBase:
"""
Updates samples for next epoch
Parameters
----------
light_curve_data
light curve learning data
next_day_data
next day light curve data
canonical_data
canonical strategy light curve data
is_queryable
If True, allow queries only on objects flagged as queryable.
Default is True.
strategy
Query strategy. Options are (all can be run with budget):
"UncSampling", "UncSamplingEntropy", "UncSamplingLeastConfident",
"UncSamplingMargin", "QBDMI", "QBDEntropy", "RandomSampling",
is_separate_files
If True, consider samples separately read
from independent files. Default is False.
"""
light_curve_data.pool_metadata = next_day_data.pool_metadata
light_curve_data.pool_features = next_day_data.pool_features
light_curve_data.pool_labels = next_day_data.pool_labels
if not is_separate_files:
light_curve_data.test_metadata = next_day_data.test_metadata
light_curve_data.test_features = next_day_data.test_features
light_curve_data.test_labels = next_day_data.test_labels
light_curve_data.validation_metadata = next_day_data.validation_metadata
light_curve_data.validation_features = next_day_data.validation_features
light_curve_data.validation_labels = next_day_data.validation_labels
if strategy == 'canonical':
light_curve_data.queryable_ids = canonical_data.queryable_ids
if is_queryable:
queryable_flag = light_curve_data.pool_metadata['queryable'].values
light_curve_data.queryable_ids = light_curve_data.pool_metadata[
'id'].values[queryable_flag]
else:
light_curve_data.queryable_ids = light_curve_data.pool_metadata[
'id'].values
return light_curve_data
def _update_next_day_pool_data(next_day_data: DataBase,
next_day_pool_metadata_indices) -> DataBase:
"""
Removes metadata value data from next day pool sample
Parameters
----------
next_day_data
next day light curve data
next_day_pool_metadata_indices
indices of metadata value in next day light curve data
"""
# remove obj from pool sample
next_day_data.pool_metadata = next_day_data.pool_metadata.drop(
next_day_data.pool_metadata.index[next_day_pool_metadata_indices])
next_day_data.pool_labels = np.delete(
next_day_data.pool_labels, next_day_pool_metadata_indices, axis=0)
next_day_data.pool_features = np.delete(
next_day_data.pool_features, next_day_pool_metadata_indices, axis=0)
return next_day_data
