def _update_canonical_ids(light_curve_data: DataBase,
canonical_file_name: str,
is_restrict_canonical: bool) -> Tuple[
DataBase, DataBase]:
"""
Updates canonical ids
Parameters
----------
light_curve_data
initial light curve training data
canonical_file_name
Path to canonical sample features files.
It is only used if "strategy==canonical".
is_restrict_canonical
If True, restrict the search to the canonical sample.
"""
database_class = None
if is_restrict_canonical:
database_class = DataBase()
database_class.load_features(path_to_file=canonical_file_name)
light_curve_data.queryable_ids = database_class.queryable_ids
return light_curve_data, database_class
def load_features(database_class: DataBase,
path_to_features: Union[str, dict],
survey: str,
features_method: str,
number_of_classes: int,
training_method: str,
is_queryable: bool,
separate_files: bool = False,
save_samples: bool = False) -> DataBase:
"""
Load features according to feature extraction method
Parameters
----------
database_class
An instance of DataBase class
path_to_features
Complete path to input features file.
if dict, keywords should be 'train' and 'test',
and values must contain the path for separate train
and test sample files.
survey
'DES' or 'LSST'. Default is 'DES'.
Name of the survey which characterizes filter set.
features_method
Feature extraction method. Currently only 'Bazin' is implemented.
number_of_classes
Number of classes to consider in the classification
Currently only nclass == 2 is implemented.
training_method
Choice of initial training sample.
If 'original': begin from the train sample flagged in the file
If int: choose the required number of samples at random,
ensuring that at least half are SN Ia
Default is 'original'.
is_queryable
If True, check if randomly chosen object is queryable.
Default is False.
separate_files: bool (optional)
If True, consider train and test samples separately read
from independent files. Default is False.
save_samples: bool (optional)
If True, save training and test samples to file.
Default is False.
"""
if isinstance(path_to_features, str):
database_class.load_features(path_to_file=path_to_features,
method=features_method,
survey=survey)
else:
features_set_names = ['train', 'test', 'validation', 'pool']
for sample_name in features_set_names:
if sample_name in path_to_features.keys():
database_class.load_features(path_to_features[sample_name],
method=features_method,
survey=survey,
sample=sample_name)
else:
logging.warning(f'Path to {sample_name} not given.'
f' Proceeding without this sample')
database_class.build_samples(initial_training=training_method,
nclass=number_of_classes,
queryable=is_queryable,
sep_files=separate_files,
save_samples=save_samples)
return database_class
def learn_loop(nloops: int, strategy: str, path_to_features: str,
output_diag_file: str, output_queried_file: str,
features_method='Bazin', classifier='RandomForest',
training='original', batch=1, screen=True, survey='DES',
perc=0.1, nclass=2):
"""Perform the active learning loop. All results are saved to file.
Parameters
----------
nloops: int
Number of active learning loops to run.
strategy: str
Query strategy. Options are 'UncSampling' and 'RandomSampling'.
path_to_features: str or dict
Complete path to input features file.
if dict, keywords should be 'train' and 'test',
and values must contain the path for separate train
and test sample files.
output_diag_file: str
Full path to output file to store diagnostics of each loop.
output_queried_file: str
Full path to output file to store the queried sample.
features_method: str (optional)
Feature extraction method. Currently only 'Bazin' is implemented.
classifier: str (optional)
Machine Learning algorithm.
Currently only 'RandomForest' is implemented.
training: str or int (optional)
Choice of initial training sample.
If 'original': begin from the train sample flagged in the file
If int: choose the required number of samples at random,
ensuring that at least half are SN Ia
Default is 'original'.
batch: int (optional)
Size of batch to be queried in each loop. Default is 1.
screen: bool (optional)
If True, print on screen number of light curves processed.
survey: str (optional)
'DES' or 'LSST'. Default is 'DES'.
Name of the survey which characterizes filter set.
perc: float in [0,1] (optioal)
Percentile chosen to identify the new query.
Only used for PercentileSampling.
Default is 0.1.
nclass: int (optional)
Number of classes to consider in the classification
Currently only nclass == 2 is implemented.
"""
## This module will need to be expanded for RESSPECT
# initiate object
data = DataBase()
# load features
if isinstance(path_to_features, str):
data.load_features(path_to_features, method=features_method,
screen=screen, survey=survey)
# separate training and test samples
data.build_samples(initial_training=training, nclass=nclass)
else:
data.load_features(path_to_features['train'], method=features_method,
screen=screen, survey=survey, sample='train')
data.load_features(path_to_features['test'], method=features_method,
screen=screen, survey=survey, sample='test')
data.build_samples(initial_training=training, nclass=nclass,
screen=screen, sep_files=True)
for loop in range(nloops):
if screen:
print('Processing... ', loop)
# classify
data.classify(method=classifier)
# calculate metrics
data.evaluate_classification()
# choose object to query
indx = data.make_query(strategy=strategy, batch=batch, perc=perc)
# update training and test samples
data.update_samples(indx, loop=loop)
# save diagnostics for current state
data.save_metrics(loop=loop, output_metrics_file=output_diag_file,
batch=batch, epoch=loop)
# save query sample to file
data.save_queried_sample(output_queried_file, loop=loop,
full_sample=False)
def time_domain_loop(days: list, output_diag_file: str,
output_queried_file: str,
path_to_features_dir: str, strategy: str,
batch=1, canonical = False, classifier='RandomForest',
features_method='Bazin', path_to_canonical="",
path_to_full_lc_features="",
screen=True, training='original'):
"""Perform the active learning loop. All results are saved to file.
Parameters
----------
days: list
List of 2 elements. First and last day of observations since the
beginning of the survey.
output_diag_file: str
Full path to output file to store diagnostics of each loop.
output_queried_file: str
Full path to output file to store the queried sample.
path_to_features_dir: str
Complete path to directory holding features files for all days.
strategy: str
Query strategy. Options are 'UncSampling' and 'RandomSampling'.
batch: int (optional)
Size of batch to be queried in each loop. Default is 1.
canonical: bool (optional)
If True, restrict the search to the canonical sample.
classifier: str (optional)
Machine Learning algorithm.
Currently only 'RandomForest' is implemented.
features_method: str (optional)
Feature extraction method. Currently only 'Bazin' is implemented.
path_to_canonical: str (optional)
Path to canonical sample features files.
It is only used if "strategy==canonical".
path_to_full_lc_features: str (optional)
Path to full light curve features file.
Only used if training is a number.
screen: bool (optional)
If True, print on screen number of light curves processed.
training: str or int (optional)
Choice of initial training sample.
If 'original': begin from the train sample flagged in the file
If int: choose the required number of samples at random,
ensuring that at least half are SN Ia
Default is 'original'.
"""
## This will need to change for RESSPECT
# initiate object
data = DataBase()
# load features for the first day
path_to_features = path_to_features_dir + 'day_' + str(int(days[0])) + '.dat'
data.load_features(path_to_features, method=features_method,
screen=screen)
# change training
if training == 'original':
data.build_samples(initial_training='original')
full_lc_features = get_original_training(path_to_features=path_to_full_lc_features)
data.train_metadata = full_lc_features.train_metadata
data.train_labels = full_lc_features.train_labels
data.train_features = full_lc_features.train_features
else:
data.build_samples(initial_training=int(training))
# get list of canonical ids
if canonical:
canonical = DataBase()
canonical.load_features(path_to_file=path_to_canonical)
data.queryable_ids = canonical.queryable_ids
for night in range(int(days[0]), int(days[-1]) - 1):
if screen:
print('Processing night: ', night)
# cont loop
loop = night - int(days[0])
# classify
data.classify(method=classifier)
# calculate metrics
data.evaluate_classification()
# choose object to query
indx = data.make_query(strategy=strategy, batch=batch)
# update training and test samples
data.update_samples(indx, loop=loop)
# save diagnostics for current state
data.save_metrics(loop=loop, output_metrics_file=output_diag_file,
batch=batch, epoch=night)
# save query sample to file
data.save_queried_sample(output_queried_file, loop=loop,
full_sample=False)
# load features for next day
path_to_features2 = path_to_features_dir + 'day_' + str(night + 1) + '.dat'
data_tomorrow = DataBase()
data_tomorrow.load_features(path_to_features2, method=features_method,
screen=False)
# identify objects in the new day which must be in training
train_flag = np.array([item in data.train_metadata['id'].values
for item in data_tomorrow.metadata['id'].values])
# use new data
data.train_metadata = data_tomorrow.metadata[train_flag]
data.train_features = data_tomorrow.features.values[train_flag]
data.test_metadata = data_tomorrow.metadata[~train_flag]
data.test_features = data_tomorrow.features.values[~train_flag]
# new labels
data.train_labels = np.array([int(item == 'Ia') for item in
data.train_metadata['type'].values])
data.test_labels = np.array([int(item == 'Ia') for item in
data.test_metadata['type'].values])
if strategy == 'canonical':
data.queryable_ids = canonical.queryable_ids
if queryable:
queryable_flag = data_tomorrow.metadata['queryable'].values
queryable_test_flag = np.logical_and(~train_flag, queryable_flag)
data.queryable_ids = data_tomorrow.metadata['id'].values[queryable_test_flag]
else:
data.queryable_ids = data_tomorrow.metadata['id'].values[~train_flag]
if screen:
print('Training set size: ', data.train_metadata.shape[0])
print('Test set size: ', data.test_metadata.shape[0])
def load_dataset(file_names_dict: dict, survey_name: str = 'DES',
initial_training: Union[str, int] = 'original',
ia_training_fraction: float = 0.5, is_queryable: bool = False,
is_separate_files: bool = False, samples_list: list = [None],
is_load_build_samples: bool = True,
number_of_classes: int = 2,
feature_extraction_method: str = 'Bazin',
is_save_samples: bool = False) -> DataBase:
"""
Reads a data sample from file.
Parameters
----------
file_names_dict: dict
Path to light curve features file.
#if "sep_files == True", dictionary keywords must contain identify
#different samples: ['train', 'test','validation', 'pool', None]
ia_training_fraction: float in [0,1] (optional)
Fraction of Ia required in initial training sample.
Only used if "initial_training" is a number. Default is 0.5.
initial_training: str or int (optional)
Choice of initial training sample.
If 'original': begin from the train sample flagged in the file
elif int: choose the required number of samples at random,
ensuring that at least "ia_frac" are SN Ia.
Default is 'original'.
is_queryable: bool (optional)
If True, allow queries only on objects flagged as queryable.
Default is True.
is_separate_files: bool (optional)
If True, consider samples separately read
from independent files. Default is False.
survey_name: str (optional)
Name of survey to be analyzed. Accepts 'DES' or 'LSST'.
Default is DES.
samples_list: list (optional)
If None, sample is given by a column within the given file.
else, read independent files for 'train' and 'test'.
Default is None.
number_of_classes
Number of classes to consider in the classification
Currently only nclass == 2 is implemented.
feature_extraction_method: str (optional)
Feature extraction method. The current implementation only
accepts method=='Bazin' or 'photometry'.
Default is 'Bazin'.
is_save_samples: bool (optional)
If True, save training and test samples to file.
Default is False.
is_load_build_samples
if database.build_samples method should be called
"""
# initiate object
database_class = DataBase()
for sample in samples_list:
database_class.load_features(
file_names_dict[sample], survey=survey_name, sample=sample,
method=feature_extraction_method)
if is_load_build_samples:
database_class.build_samples(
initial_training=initial_training, nclass=number_of_classes,
Ia_frac=ia_training_fraction, queryable=is_queryable,
save_samples=is_save_samples, sep_files=is_separate_files,
survey=survey_name)
return database_class