def _create_detection_exp(self, kind, classifier_conf, fold_id=None):
diadem_id = self.exp_conf.exp_id
exp_name = 'DIADEM_%i_Detection_%s' % (diadem_id, kind)
if fold_id is not None:
exp_name = '%s_fold_%i' % (exp_name, fold_id)
secuml_conf = self.exp_conf.secuml_conf
logger = secuml_conf.logger
if kind == 'validation':
dataset_conf = DatasetConf(self.exp_conf.dataset_conf.project,
self.validation_conf.test_dataset,
self.exp_conf.secuml_conf.logger)
annotations_conf = AnnotationsConf('ground_truth.csv', None,
logger)
elif kind == 'test' and self.test_conf.method == 'dataset':
dataset_conf = DatasetConf(self.exp_conf.dataset_conf.project,
self.test_conf.test_dataset,
self.exp_conf.secuml_conf.logger)
annotations_conf = AnnotationsConf('ground_truth.csv', None,
logger)
else:
dataset_conf = self.exp_conf.dataset_conf
annotations_conf = self.exp_conf.annotations_conf
features_conf = self.exp_conf.features_conf
test_exp_conf = DetectionConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
self._get_alerts_conf(fold_id),
name=exp_name,
parent=diadem_id,
fold_id=fold_id,
kind=kind)
return DetectionExp(test_exp_conf, session=self.session)
def _create_test_exp(self, fold_id=None):
diadem_id = self.exp_conf.exp_id
exp_name = 'DIADEM_%i_Test' % diadem_id
if fold_id is not None:
exp_name = '%s_fold_%i' % (exp_name, fold_id)
secuml_conf = self.exp_conf.secuml_conf
logger = secuml_conf.logger
if self.test_conf.method == 'dataset':
dataset_conf = DatasetConf(self.exp_conf.dataset_conf.project,
self.test_conf.test_dataset,
self.exp_conf.secuml_conf.logger)
annotations_conf = AnnotationsConf('ground_truth.csv', None,
logger)
else:
dataset_conf = self.exp_conf.dataset_conf
annotations_conf = self.exp_conf.annotations_conf
features_conf = self.exp_conf.features_conf
test_exp_conf = TestConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
self.exp_conf.core_conf.classifier_conf,
name=exp_name,
parent=diadem_id,
fold_id=fold_id,
kind='test')
return TestExp(test_exp_conf,
alerts_conf=self._get_alerts_conf(fold_id),
session=self.session)
def from_args(args):
secuml_conf = ExpConf.secuml_conf_from_args(args)
logger = secuml_conf.logger
dataset_conf = DatasetConf.from_args(args, logger)
features_conf = FeaturesConf.from_args(args, logger)
annotations_conf = AnnotationsConf(args.annotations_file, None, logger)
core_conf = strategies_conf.get_factory().from_args('Rcd', args,
logger)
return RcdConf(secuml_conf, dataset_conf, features_conf,
annotations_conf, core_conf, name=args.exp_name)
def from_args(args):
secuml_conf = ExpConf.common_from_args(args)
dataset_conf = DatasetConf.from_args(args, secuml_conf.logger)
features_conf = FeaturesConf.from_args(args, secuml_conf.logger)
annotations_conf = AnnotationsConf(args.annotations_file, None,
secuml_conf.logger)
core_conf = projection_conf.get_factory().from_args(args.algo, args,
secuml_conf.logger)
return ProjectionConf(secuml_conf, dataset_conf, features_conf,
annotations_conf, core_conf, name=args.exp_name)
def from_args(args):
secuml_conf = ExpConf.common_from_args(args)
dataset_conf = DatasetConf.from_args(args, secuml_conf.logger)
features_conf = FeaturesConf.from_args(args, secuml_conf.logger)
annotations_conf = AnnotationsConf(args.annotations_file, None,
secuml_conf.logger)
return FeaturesAnalysisConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
None,
name=args.exp_name)
def from_args(args):
secuml_conf = ExpConf.secuml_conf_from_args(args)
dataset_conf = DatasetConf.from_args(args, secuml_conf.logger)
features_conf = FeaturesConf.from_args(args, secuml_conf.logger)
annotations_conf = AnnotationsConf(args.annotations_file, None,
secuml_conf.logger)
core_conf = strategies_conf.get_factory().from_args(args.strategy,
args,
secuml_conf.logger)
return ActiveLearningConf(secuml_conf, dataset_conf, features_conf,
annotations_conf, core_conf,
name=args.exp_name)
def from_json(conf_json, secuml_conf):
logger = secuml_conf.logger
dataset_conf = DatasetConf.from_json(conf_json['dataset_conf'], logger)
features_conf = FeaturesConf.from_json(conf_json['features_conf'],
logger)
annotations_conf = AnnotationsConf.from_json(
conf_json['annotations_conf'],
logger)
factory = strategies_conf.get_factory()
core_conf = factory.from_json(conf_json['core_conf'], logger)
conf = RcdConf(secuml_conf, dataset_conf, features_conf,
annotations_conf, core_conf, name=conf_json['name'],
parent=conf_json['parent'])
conf.exp_id = conf_json['exp_id']
return conf
def from_args(args):
secuml_conf = ExpConf.common_from_args(args)
already_trained = None
core_conf = ClassificationConf.from_args(args, secuml_conf.logger)
if args.model_class != 'AlreadyTrained':
annotations_conf = AnnotationsConf(args.annotations_file, None,
secuml_conf.logger)
else:
already_trained = args.model_exp_id
annotations_conf = AnnotationsConf(None, None, secuml_conf.logger)
dataset_conf = DatasetConf.from_args(args, secuml_conf.logger)
features_conf = FeaturesConf.from_args(args, secuml_conf.logger)
return DiademConf(secuml_conf, dataset_conf, features_conf,
annotations_conf, core_conf, name=args.exp_name,
already_trained=already_trained)
def from_args(args):
secuml_conf = ExpConf.secuml_conf_from_args(args)
dataset_conf = DatasetConf.from_args(args, secuml_conf.logger)
features_conf = FeaturesConf.from_args(args, secuml_conf.logger)
annotations_conf = AnnotationsConf(args.annotations_file, None,
secuml_conf.logger)
core_conf = clustering_conf.get_factory().from_args(
args.algo, args, secuml_conf.logger)
conf = ClusteringConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
core_conf,
name=args.exp_name,
label=args.label)
return conf
def from_json(conf_json, secuml_conf):
dataset_conf = DatasetConf.from_json(conf_json['dataset_conf'],
secuml_conf.logger)
features_conf = FeaturesConf.from_json(conf_json['features_conf'],
secuml_conf.logger)
annotations_conf = AnnotationsConf.from_json(
conf_json['annotations_conf'], secuml_conf.logger)
conf = FeaturesAnalysisConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
None,
name=conf_json['name'],
parent=conf_json['parent'])
conf.exp_id = conf_json['exp_id']
return conf
def from_args(args):
secuml_conf = ExpConf.secuml_conf_from_args(args)
classif_conf = ClassificationConf.from_args(args, secuml_conf.logger)
model_class = classifiers.get_factory().get_class(args.model_class)
classifier_type = get_classifier_type(model_class)
if classifier_type in [
ClassifierType.supervised, ClassifierType.semisupervised
]:
annotations_conf = AnnotationsConf(args.annotations_file, None,
secuml_conf.logger)
else:
annotations_conf = AnnotationsConf(None, None, secuml_conf.logger)
already_trained = None
if args.model_class == 'AlreadyTrained':
already_trained = args.model_exp_id
alerts_conf = AlertsConf.from_args(args, secuml_conf.logger)
if (classifier_type == ClassifierType.unsupervised
and alerts_conf.classifier_conf is not None):
raise InvalidInputArguments('Supervised classification of the '
'alerts is not supported for '
'unsupervised model classes. ')
if classif_conf.classifier_conf.multiclass:
if alerts_conf.with_analysis():
raise InvalidInputArguments('Alerts analysis is not supported '
'for multiclass models. ')
else:
alerts_conf = None
if (classif_conf.test_conf.method == 'dataset'
and classif_conf.test_conf.streaming
and alerts_conf.with_analysis()):
raise InvalidInputArguments('Alerts analysis is not supported '
'in streaming mode. ')
dataset_conf = DatasetConf.from_args(args, secuml_conf.logger)
features_conf = FeaturesConf.from_args(args, secuml_conf.logger)
if (features_conf.sparse
and not classif_conf.classifier_conf.accept_sparse):
raise InvalidInputArguments('%s does not support sparse '
'features. ' % args.model_class)
return DiademConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
classif_conf,
alerts_conf,
name=args.exp_name,
already_trained=already_trained,
no_training_detection=args.no_training_detection)
def from_json(conf_json, secuml_conf):
dataset_conf = DatasetConf.from_json(conf_json['dataset_conf'],
secuml_conf.logger)
features_conf = FeaturesConf.from_json(conf_json['features_conf'],
secuml_conf.logger)
annotations_conf = AnnotationsConf.from_json(
conf_json['annotations_conf'],
secuml_conf.logger)
core_conf = projection_conf.get_factory().from_json(
conf_json['core_conf'],
secuml_conf.logger)
conf = ProjectionConf(secuml_conf, dataset_conf, features_conf,
annotations_conf, core_conf,
name=conf_json['name'],
parent=conf_json['parent'])
conf.exp_id = conf_json['exp_id']
return conf
def from_json(conf_json, secuml_conf):
dataset_conf = DatasetConf.from_json(conf_json['dataset_conf'],
secuml_conf.logger)
features_conf = FeaturesConf.from_json(conf_json['features_conf'],
secuml_conf.logger)
annotations_conf = AnnotationsConf.from_json(
conf_json['annotations_conf'],
secuml_conf.logger)
core_conf = ClassificationConf.from_json(conf_json['core_conf'],
secuml_conf.logger)
exp_conf = DiademConf(secuml_conf, dataset_conf, features_conf,
annotations_conf, core_conf,
name=conf_json['name'],
parent=conf_json['parent'],
already_trained=conf_json['already_trained'])
exp_conf.exp_id = conf_json['exp_id']
return exp_conf
def from_json(conf_json, secuml_conf):
logger = secuml_conf.logger
dataset_conf = DatasetConf.from_json(conf_json['dataset_conf'], logger)
features_conf = FeaturesConf.from_json(conf_json['features_conf'],
logger)
annotations_conf = AnnotationsConf.from_json(
conf_json['annotations_conf'],
logger)
factory = classifiers.get_factory()
classifier_conf = factory.from_json(conf_json['core_conf'], logger)
exp_conf = TestConf(secuml_conf, dataset_conf, features_conf,
annotations_conf, classifier_conf,
name=conf_json['name'], parent=conf_json['parent'],
fold_id=conf_json['fold_id'],
kind=conf_json['kind'])
exp_conf.exp_id = conf_json['exp_id']
return exp_conf
def from_args(args):
if args.annotations_file is None and args.multiclass:
raise InvalidInputArguments('--annotations <file> is required. '
'An annotation file must be specified '
'to group the instances according to '
'their families.')
secuml_conf = ExpConf.secuml_conf_from_args(args)
dataset_conf = DatasetConf.from_args(args, secuml_conf.logger)
features_conf = FeaturesConf.from_args(args, secuml_conf.logger)
annotations_conf = AnnotationsConf(args.annotations_file, None,
secuml_conf.logger)
return FeaturesAnalysisConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
args.multiclass,
name=args.exp_name)
def from_args(args):
secuml_conf = ExpConf.secuml_conf_from_args(args)
classif_conf = ClassificationConf.from_args(args, secuml_conf.logger)
model_class = classifiers.get_factory().get_class(args.model_class)
classifier_type = get_classifier_type(model_class)
if classifier_type in [ClassifierType.supervised,
ClassifierType.semisupervised]:
annotations_conf = AnnotationsConf(args.annotations_file, None,
secuml_conf.logger)
else:
annotations_conf = AnnotationsConf(None, None, secuml_conf.logger)
already_trained = None
if args.model_class == 'AlreadyTrained':
already_trained = args.model_exp_id
dataset_conf = DatasetConf.from_args(args, secuml_conf.logger)
features_conf = FeaturesConf.from_args(args, secuml_conf.logger)
return DiademConf(secuml_conf, dataset_conf, features_conf,
annotations_conf, classif_conf, name=args.exp_name,
already_trained=already_trained)
def from_json(conf_json, secuml_conf):
logger = secuml_conf.logger
dataset_conf = DatasetConf.from_json(conf_json['dataset_conf'], logger)
features_conf = FeaturesConf.from_json(conf_json['features_conf'],
logger)
annotations_conf = AnnotationsConf.from_json(
conf_json['annotations_conf'],
logger)
if conf_json['core_conf'] is not None:
alerts_conf = AlertsConf.from_json(conf_json['core_conf'], logger)
else:
alerts_conf = None
exp_conf = DetectionConf(secuml_conf, dataset_conf, features_conf,
annotations_conf, alerts_conf,
name=conf_json['name'],
parent=conf_json['parent'],
fold_id=conf_json['fold_id'],
kind=conf_json['kind'])
exp_conf.exp_id = conf_json['exp_id']
return exp_conf
def from_json(conf_json, secuml_conf):
dataset_conf = DatasetConf.from_json(conf_json['dataset_conf'],
secuml_conf.logger)
features_conf = FeaturesConf.from_json(conf_json['features_conf'],
secuml_conf.logger)
annotations_conf = AnnotationsConf.from_json(
conf_json['annotations_conf'], secuml_conf.logger)
core_conf = None
if conf_json['core_conf'] is not None:
core_conf = clustering_conf.get_factory().from_json(
conf_json['core_conf'], secuml_conf.logger)
exp_conf = ClusteringConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
core_conf,
name=conf_json['name'],
parent=conf_json['parent'],
label=conf_json['label'])
exp_conf.exp_id = conf_json['exp_id']
return exp_conf
def _create_detection_conf(self, kind, classifier_conf, fold_id=None):
diadem_id = self.exp_conf.exp_id
exp_name = 'DIADEM_%i_Detection_%s' % (diadem_id, kind)
if fold_id is not None:
exp_name = '%s_fold_%i' % (exp_name, fold_id)
secuml_conf = self.exp_conf.secuml_conf
logger = secuml_conf.logger
if (kind == 'validation'
or (kind == 'test' and self.test_conf.method == 'datasets')):
validation_conf = getattr(self, '%s_conf' % kind)
annotations_conf = AnnotationsConf('ground_truth.csv', None,
logger)
features_conf = self.exp_conf.features_conf
if validation_conf.streaming:
stream_batch = validation_conf.stream_batch
features_conf = features_conf.copy_streaming(stream_batch)
dataset_confs = [
DatasetConf(self.exp_conf.dataset_conf.project, test_dataset,
self.exp_conf.secuml_conf.logger)
for test_dataset in validation_conf.validation_datasets
]
else:
dataset_confs = [self.exp_conf.dataset_conf]
annotations_conf = self.exp_conf.annotations_conf
features_conf = self.exp_conf.features_conf
alerts_conf = None
if fold_id is None and kind != 'train':
alerts_conf = self.exp_conf.alerts_conf
return [
DetectionConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
alerts_conf,
name=exp_name,
parent=diadem_id,
fold_id=fold_id,
kind=kind) for dataset_conf in dataset_confs
]
