def generateParser():
parser = argparse.ArgumentParser(
description='Learn a detection model. '
'The ground-truth must be stored in '
'annotations/ground_truth.csv.')
ExpConf.generateParser(parser)
CoreClassificationConf.generateParser(parser)
models = [
'LogisticRegression', 'Svc', 'GaussianNaiveBayes', 'DecisionTree',
'RandomForest', 'GradientBoosting'
]
subparsers = parser.add_subparsers(dest='model_class')
subparsers.required = True
factory = ClassifierConfFactory.getFactory()
for model in models:
model_parser = subparsers.add_parser(model)
factory.generateParser(model, model_parser)
AnnotationsConf.generateParser(
model_parser,
required=True,
message='CSV file containing the annotations of some '
'or all the instances.')
## Add subparser for already trained model
already_trained = subparsers.add_parser('AlreadyTrained')
factory.generateParser('AlreadyTrained', already_trained)
return parser
def generateParser():
parser = argparse.ArgumentParser(
description='Clustering of the data for data exploration.')
ExpConf.generateParser(parser)
AnnotationsConf.generateParser(
parser,
message='CSV file containing the annotations of some '
'instances. These annotations are used for '
'semi-supervised projections.')
parser.add_argument(
'--label',
choices=['all', 'malicious', 'benign'],
default='all',
help='The clustering is built from all the instances in the '
'dataset, or only from the benign or malicious ones. '
'By default, the clustering is built from all the '
'instances. The malicious and benign instances are '
'selected according to the ground-truth stored in '
'annotations/ground_truth.csv.')
subparsers = parser.add_subparsers(dest='algo')
subparsers.required = True
factory = ClusteringConfFactory.getFactory()
for algo in factory.getMethods():
algo_parser = subparsers.add_parser(algo)
factory.generateParser(algo, algo_parser)
return parser
def generateParser():
parser = argparse.ArgumentParser(description='Features Analysis')
ExpConf.generateParser(parser, filters=False)
AnnotationsConf.generateParser(parser,
required=True,
message='CSV file containing the annotations of some or all'
' the instances.')
return parser
def generateParser():
parser = argparse.ArgumentParser(
description='Rare Category Detection',
formatter_class=argparse.RawTextHelpFormatter)
ExpConf.generateParser(parser)
AnnotationsConf.generateParser(
parser,
default='init_annotations.csv',
required=False,
message='CSV file containing the initial annotations '
'used to learn the first supervised detection '
'model.')
factory = ActiveLearningConfFactory.getFactory()
factory.generateParser('RareCategoryDetection', parser)
return parser
def __init__(self,
secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
core_conf,
experiment_name=None,
parent=None):
ExpConf.__init__(self,
secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
core_conf,
experiment_name=experiment_name,
parent=parent)
self.test_exp_conf = None
def generateParser():
parser = argparse.ArgumentParser(
description='Projection of the data for data visualization.')
ExpConf.generateParser(parser)
AnnotationsConf.generateParser(
parser,
message='CSV file containing the annotations of some'
' instances. These annotations are used for '
'semi-supervised projections.')
algos = ['Pca', 'Rca', 'Lda', 'Lmnn', 'Nca', 'Itml']
subparsers = parser.add_subparsers(dest='algo')
subparsers.required = True
factory = ProjectionConfFactory.getFactory()
for algo in algos:
algo_parser = subparsers.add_parser(algo)
factory.generateParser(algo, algo_parser)
return parser
def __init__(self,
secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
core_conf,
experiment_name=None,
parent=None,
label='all'):
ExpConf.__init__(self,
secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
core_conf,
experiment_name=experiment_name,
parent=parent)
self.label = label
def fromArgs(args):
secuml_conf = ExpConf.common_from_args(args)
dataset_conf = DatasetConf.fromArgs(args, secuml_conf.logger)
features_conf = FeaturesConf.fromArgs(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,
experiment_name=args.exp_name)
def generateParser():
parser = argparse.ArgumentParser(
description='Active Learning',
formatter_class=argparse.RawTextHelpFormatter)
ExpConf.generateParser(parser)
AnnotationsConf.generateParser(
parser,
default='init_annotations.csv',
required=False,
message='CSV file containing the initial annotations '
'used to learn the first supervised detection '
'model.')
subparsers = parser.add_subparsers(dest='strategy')
subparsers.required = True
factory = ActiveLearningConfFactory.getFactory()
strategies = factory.getMethods()
for strategy in strategies:
strategy_parser = subparsers.add_parser(strategy)
factory.generateParser(strategy, strategy_parser)
return parser
def fromArgs(args):
secuml_conf = ExpConf.common_from_args(args)
dataset_conf = DatasetConf.fromArgs(args, secuml_conf.logger)
features_conf = FeaturesConf.fromArgs(args, secuml_conf.logger)
annotations_conf = AnnotationsConf(args.annotations_file, None,
secuml_conf.logger)
factory = ActiveLearningConfFactory.getFactory()
core_conf = factory.fromArgs(args.strategy, args, secuml_conf.logger)
return ActiveLearningConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
core_conf,
experiment_name=args.exp_name)
def fromArgs(args):
secuml_conf = ExpConf.common_from_args(args)
dataset_conf = DatasetConf.fromArgs(args, secuml_conf.logger)
features_conf = FeaturesConf.fromArgs(args, secuml_conf.logger)
annotations_conf = AnnotationsConf(args.annotations_file, None,
secuml_conf.logger)
factory = ClusteringConfFactory.getFactory()
core_conf = factory.fromArgs(args.algo, args, secuml_conf.logger)
conf = ClusteringConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
core_conf,
experiment_name=args.exp_name,
label=args.label)
return conf
def fromArgs(args):
secuml_conf = ExpConf.common_from_args(args)
already_trained = None
if args.model_class != 'AlreadyTrained':
core_conf = CoreClassificationConf.fromArgs(
args, True, secuml_conf.logger)
annotations_conf = AnnotationsConf(args.annotations_file, None,
secuml_conf.logger)
else:
already_trained = args.model_exp_id
core_conf = CoreClassificationConf.fromArgs(
args, False, secuml_conf.logger)
annotations_conf = AnnotationsConf(None, None, secuml_conf.logger)
dataset_conf = DatasetConf.fromArgs(args, secuml_conf.logger)
features_conf = FeaturesConf.fromArgs(args, secuml_conf.logger)
return ClassificationConf(secuml_conf,
dataset_conf,
features_conf,
annotations_conf,
core_conf,
experiment_name=args.exp_name,
already_trained=already_trained)
def fieldsToExport(self):
fields = ExpConf.fieldsToExport(self)
fields.extend([('test_exp_conf', exportFieldMethod.obj)])
return fields
def fieldsToExport(self):
fields = ExpConf.fieldsToExport(self)
fields.extend([('label', exportFieldMethod.primitive)])
return fields
def _get_exp_name(self):
name = ''
if self.already_trained is not None:
name += 'AlreadyTrained_exp%i' % self.already_trained
name += ExpConf._get_exp_name(self)
return name
def fieldsToExport(self):
fields = ExpConf.fieldsToExport(self)
fields.extend([('already_trained', exportFieldMethod.primitive)])
fields.extend([('test_exp_conf', exportFieldMethod.obj)])
return fields