def execute(self):
name = 'AL%d-Iter%d-main' % (self.exp.exp_id, self.iteration.iter_num)
features_conf = FeaturesConf(
self.exp.exp_conf.features_conf.input_features,
self.exp.exp_conf.features_conf.sparse,
self.exp.exp_conf.features_conf.logger,
filter_in_f=self.exp.exp_conf.features_conf.filter_in_f,
filter_out_f=self.exp.exp_conf.features_conf.filter_out_f)
exp_conf = DiademConf(self.exp.exp_conf.secuml_conf,
self.exp.exp_conf.dataset_conf,
features_conf,
self.exp.exp_conf.annotations_conf,
self.model_conf,
None,
name=name,
parent=self.exp.exp_id)
self.model_exp = DiademExp(exp_conf, session=self.exp.session)
classifier_type = get_classifier_type(
self.model_conf.classifier_conf.__class__)
cv_monitoring = classifier_type == ClassifierType.supervised
prev_classifier = None
prev_iter = self.iteration.prev_iter
if prev_iter is not None:
prev_classifier = prev_iter.update_model.classifier
self.model_exp.run(instances=self.iteration.datasets.instances,
cv_monitoring=cv_monitoring,
init_classifier=prev_classifier)
self._set_exec_time()
self.classifier = self.model_exp.get_train_exp().classifier
def get_naive_bayes_conf(self):
name = '-'.join([
'AL%d' % self.exp.exp_id,
'Iter%d' % self.iteration.iter_num, 'all', 'NaiveBayes'
])
classifier_conf = self.exp.exp_conf.core_conf.classifier_conf
optim_conf = classifier_conf.hyperparam_conf.optim_conf
multiclass = True
factory = classifiers.get_factory()
naive_bayes_conf = factory.get_default('GaussianNaiveBayes',
optim_conf.num_folds,
optim_conf.n_jobs, multiclass,
self.exp.logger)
test_conf = UnlabeledLabeledConf(self.exp.logger)
classification_conf = ClassificationConf(naive_bayes_conf, test_conf,
self.exp.logger)
features_conf = FeaturesConf(
self.exp.exp_conf.features_conf.input_features,
self.exp.exp_conf.features_conf.sparse,
self.exp.exp_conf.features_conf.logger,
filter_in_f=self.exp.exp_conf.features_conf.filter_in_f,
filter_out_f=self.exp.exp_conf.features_conf.filter_out_f)
exp_conf = DiademConf(self.exp.exp_conf.secuml_conf,
self.exp.exp_conf.dataset_conf,
features_conf,
self.exp.exp_conf.annotations_conf,
classification_conf,
None,
name=name,
parent=self.exp.exp_id)
DiademExp(exp_conf, session=self.exp.session)
return naive_bayes_conf
def _run_logistic_regression(self):
name = '-'.join([
'AL%d' % (self.exp.exp_id),
'Iter%d' % (self.iteration.iter_num), 'all', 'LogisticRegression'
])
features_conf = FeaturesConf(
self.exp.exp_conf.features_conf.input_features,
self.exp.exp_conf.features_conf.sparse,
self.exp.exp_conf.features_conf.logger,
filter_in_f=self.exp.exp_conf.features_conf.filter_in_f,
filter_out_f=self.exp.exp_conf.features_conf.filter_out_f)
exp_conf = DiademConf(self.exp.exp_conf.secuml_conf,
self.exp.exp_conf.dataset_conf,
features_conf,
self.exp.exp_conf.annotations_conf,
self.exp.exp_conf.core_conf.multiclass_model,
None,
name=name,
parent=self.exp.exp_id)
model_exp = DiademExp(exp_conf, session=self.exp.session)
model_exp.run(instances=self.iteration.datasets.instances,
cv_monitoring=False)
train_exp = model_exp.get_train_exp()
test_exp = model_exp.get_detection_exp('test')
self.lr_predicted_proba = test_exp.predictions.all_probas
self.lr_predicted_labels = test_exp.predictions.values
self.lr_class_labels = train_exp.classifier.class_labels
self.lr_time = train_exp.monitoring.exec_times.total()
self.lr_time += test_exp.monitoring.exec_time.predictions
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.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_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_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_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)
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_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 = 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):
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):
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 _create_clustering_exp(self, core_clustering_conf):
exp_conf = self.test_exp.exp_conf
features_conf = FeaturesConf(
exp_conf.features_conf.input_features,
exp_conf.features_conf.sparse,
exp_conf.features_conf.logger,
filter_in_f=exp_conf.features_conf.filter_in_f,
filter_out_f=exp_conf.features_conf.filter_out_f)
conf = ClusteringConf(exp_conf.secuml_conf,
exp_conf.dataset_conf,
features_conf,
exp_conf.annotations_conf,
core_clustering_conf,
name='Alerts_%i' % exp_conf.exp_id,
parent=exp_conf.exp_id)
return AlertsClusteringExp(conf,
self.test_exp.exp_conf.parent,
create=True,
session=self.test_exp.session)
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 _get_multiclass_conf(self):
conf = self.rcd_conf.classification_conf
name = '-'.join(['AL%d' % self.exp.exp_id,
'Iter%d' % self.iteration.iter_num,
self.label,
'analysis'])
features_conf = FeaturesConf(
self.exp.exp_conf.features_conf.input_features,
self.exp.exp_conf.features_conf.sparse,
self.exp.exp_conf.features_conf.logger,
filter_in_f=self.exp.exp_conf.features_conf.filter_in_f,
filter_out_f=self.exp.exp_conf.features_conf.filter_out_f)
exp_conf = DiademConf(self.exp.exp_conf.secuml_conf,
self.exp.exp_conf.dataset_conf,
features_conf,
self.exp.exp_conf.annotations_conf,
conf, None, name=name, parent=self.exp.exp_id)
self.multiclass_exp = DiademExp(exp_conf, session=self.exp.session)
return 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)
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_clustering_exp(self):
core_conf = CoreClusteringConf(self.exp.exp_conf.logger,
self.categories.num_categories)
name = '-'.join(['AL%d' % self.exp.exp_id,
'Iter%d' % self.iteration.iter_num,
self.label,
'clustering'])
features_conf = FeaturesConf(
self.exp.exp_conf.features_conf.input_features,
self.exp.exp_conf.features_conf.sparse,
self.exp.exp_conf.features_conf.logger,
filter_in_f=self.exp.exp_conf.features_conf.filter_in_f,
filter_out_f=self.exp.exp_conf.features_conf.filter_out_f)
exp_conf = ClusteringConf(self.exp.exp_conf.secuml_conf,
self.exp.exp_conf.dataset_conf,
features_conf,
self.exp.exp_conf.annotations_conf,
core_conf, name=name, parent=self.exp.exp_id)
clustering_exp = ClusteringExperiment(exp_conf,
session=self.exp.session)
return clustering_exp
def create_exp(self):
Experiment.create_exp(self)
# create projection experiment
self.projection_exp = None
if self.exp_conf.core_conf is None:
return
projection_core_conf = self.exp_conf.core_conf.projection_conf
if projection_core_conf is not None:
features_conf = FeaturesConf(
self.exp_conf.features_conf.input_features,
self.exp_conf.secuml_conf.logger)
projection_conf = ProjectionConf(self.exp_conf.secuml_conf,
self.exp_conf.dataset_conf,
features_conf,
self.exp_conf.annotations_conf,
projection_core_conf,
name='-'.join(
[self.exp_conf.name, 'proj']),
parent=self.exp_id)
self.projection_exp = ProjectionExperiment(projection_conf,
session=self.session)
