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_light_curve_data_val_and_test_data(
light_curve_data: DataBase, first_loop_data: DataBase,
is_separate_files: bool = False,
initial_training: Union[str, int] = 'original',
is_queryable: bool = False, number_of_classes: int = 2) -> DataBase:
"""
Updates initial light curve validation and test data
Parameters
----------
light_curve_data
initial light curve training data
first_loop_data
first loop light curve data
is_queryable
If True, allow queries only on objects flagged as queryable.
Default is True.
is_separate_files
If True, consider samples separately read
from independent files. Default is False.
initial_training
Choice of initial training sample.
If 'original': begin from the train sample flagged in the file
eilf 'previous': read training and queried from previous run.
If int: choose the required number of samples at random,
ensuring that at least half are SN Ia
Default is 'original'.
number_of_classes
Number of classes to consider in the classification
Currently only number_of_classes == 2 is implemented.
"""
if is_separate_files:
light_curve_data.build_samples(
nclass=number_of_classes, queryable=is_queryable,
sep_files=is_separate_files, initial_training=initial_training)
else:
light_curve_data.test_features = first_loop_data.pool_features
light_curve_data.test_metadata = first_loop_data.pool_metadata
light_curve_data.test_labels = first_loop_data.pool_labels
light_curve_data.validation_features = first_loop_data.pool_features
light_curve_data.validation_metadata = first_loop_data.pool_metadata
light_curve_data.validation_labels = first_loop_data.pool_labels
return light_curve_data
def _update_next_day_val_and_test_data(
next_day_data: DataBase, metadata_value: int,
id_key_name: str) -> DataBase:
"""
Removes metadata value data from next day validation and test samples
Parameters
----------
next_day_data
next day light curve data
metadata_value
metadata object value
id_key_name
object identification key name
"""
if (len(next_day_data.validation_metadata) > 0 and metadata_value
in next_day_data.validation_metadata[id_key_name].values):
val_indices = list(next_day_data.validation_metadata[
id_key_name].values).index(metadata_value)
next_day_data.validation_metadata = (
next_day_data.validation_metadata.drop(
next_day_data.validation_metadata.index[val_indices]))
next_day_data.validation_labels = np.delete(
next_day_data.validation_labels, val_indices, axis=0)
next_day_data.validation_features = np.delete(
next_day_data.validation_features, val_indices, axis=0)
if (len(next_day_data.test_metadata) > 0 and metadata_value
in next_day_data.test_metadata[id_key_name].values):
test_indices = list(next_day_data.test_metadata[
id_key_name].values).index(metadata_value)
next_day_data.test_metadata = (
next_day_data.test_metadata.drop(
next_day_data.test_metadata.index[test_indices]))
next_day_data.test_labels = np.delete(
next_day_data.test_labels, test_indices, axis=0)
next_day_data.test_features = np.delete(
next_day_data.test_features, test_indices, axis=0)
return next_day_data
