def load(self):
filepath, _ = self.get_filepath_hash()
call_specific_db_func(
self.secuml_conf.db_type, 'load_idents',
(self.cursor, filepath, self.dataset_conf.dataset_id))
self.secuml_conf.logger.info(
'Idents file for the dataset %s/%s '
'loaded into the database (%s).' %
(self.dataset_conf.project, self.dataset_conf.dataset, filepath))
def load_partial_annotations(self, filename, annotations_id):
filename = path.join(self.dataset_conf.input_dir(self.secuml_conf),
'annotations', filename)
if not path.isfile(filename):
raise SecuMLexpException(
'The annotations file %s does not exist.' % filename)
conn = self.session.connection().connection
cursor = conn.cursor()
call_specific_db_func(
self.secuml_conf.db_type, 'load_partial_annotations',
(cursor, filename, annotations_id, self.dataset_conf.dataset_id))
self.session.flush()
def load(self):
filepath, _ = self.get_filepath_hash()
self.exists = filepath is not None
if not self.exists:
return
call_specific_db_func(
self.secuml_conf.db_type, 'load_ground_truth',
(self.cursor, filepath, self.dataset_conf.dataset_id))
self.secuml_conf.logger.info(
'Ground-truth file for the dataset %s/%s '
'loaded into the database (%s).' %
(self.dataset_conf.project, self.dataset_conf.dataset, filepath))
def getAlerts(exp_id, analysis_type):
exp = update_curr_exp(exp_id)
# With proba ? With scores ?
query = session.query(DiademExpAlchemy)
query = query.filter(DiademExpAlchemy.exp_id == exp_id)
diadem_exp = query.one()
with_proba, with_scores = diadem_exp.proba, diadem_exp.with_scoring
# Get alerts
query = session.query(PredictionsAlchemy)
query = query.filter(PredictionsAlchemy.exp_id == exp_id)
if with_proba:
threshold = exp.exp_conf.core_conf.detection_threshold
query = query.filter(PredictionsAlchemy.proba >= threshold)
else:
query = query.filter(PredictionsAlchemy.value == MALICIOUS)
if analysis_type == 'topN' and (with_proba or with_scores):
if with_proba:
query = query.order_by(PredictionsAlchemy.proba.desc())
else:
query = query.order_by(PredictionsAlchemy.score.desc())
elif analysis_type == 'random':
query = call_specific_db_func(secuml_conf.db_type, 'random_order',
(query, ))
query = query.limit(NUM_MAX_DISPLAY)
return jsonify(_predictions_results(query))
def getAlerts(exp_id, analysis_type):
exp = update_curr_exp(exp_id)
# With proba ?
query = session.query(DiademExpAlchemy)
query = query.filter(DiademExpAlchemy.exp_id == exp_id)
with_proba = query.one().proba
threshold = None
if with_proba:
threshold = exp.exp_conf.core_conf.detection_threshold
# Get alerts
query = session.query(PredictionsAlchemy)
query = query.filter(PredictionsAlchemy.exp_id == exp_id)
if with_proba:
query = query.filter(PredictionsAlchemy.proba >= threshold)
if analysis_type == 'topN' and with_proba:
query = query.order_by(PredictionsAlchemy.proba.desc())
elif analysis_type == 'random':
query = call_specific_db_func(secuml_conf.db_type, 'random_order',
(query,))
query = query.limit(TOP_N_ALERTS)
predictions = query.all()
if predictions:
ids, probas = zip(*[(r.instance_id, r.proba) for r in predictions])
else:
ids = []
probas = []
return jsonify({'instances': ids, 'proba': probas})
def getPredictionsScores(exp_id, range_, label):
score_min, score_max = [float(x) for x in range_.split(' - ')]
query = session.query(PredictionsAlchemy)
query = query.filter(PredictionsAlchemy.exp_id == exp_id)
query = query.filter(PredictionsAlchemy.score >= score_min)
query = query.filter(PredictionsAlchemy.score <= score_max)
query = query.order_by(PredictionsAlchemy.score.asc())
if label != 'all':
query = query.join(PredictionsAlchemy.instance)
query = query.join(InstancesAlchemy.ground_truth)
query = query.filter(GroundTruthAlchemy.label == label)
query = call_specific_db_func(secuml_conf.db_type, 'random_order',
(query, ))
query = query.limit(NUM_MAX_DISPLAY)
return jsonify(_predictions_results(query))
def _get_errors(exp_id, fn_fp):
if fn_fp == 'FN':
predicted_value = 'benign'
ground_truth = 'malicious'
else:
predicted_value = 'malicious'
ground_truth = 'benign'
query = session.query(PredictionsAlchemy)
query = query.filter(PredictionsAlchemy.exp_id == exp_id)
query = query.filter(PredictionsAlchemy.value == predicted_value)
query = query.join(PredictionsAlchemy.instance)
query = query.join(InstancesAlchemy.ground_truth)
query = query.filter(GroundTruthAlchemy.label == ground_truth)
query = call_specific_db_func(secuml_conf.db_type, 'random_order',
(query, ))
query = query.limit(NUM_MAX_DISPLAY)
return _predictions_results(query)
def getPredictionsProbas(exp_id, index, label):
index = int(index)
proba_min = index * 0.1
proba_max = (index + 1) * 0.1
query = session.query(PredictionsAlchemy)
query = query.filter(PredictionsAlchemy.exp_id == exp_id)
query = query.filter(PredictionsAlchemy.proba >= proba_min)
query = query.filter(PredictionsAlchemy.proba <= proba_max)
query = query.order_by(PredictionsAlchemy.proba.asc())
if label != 'all':
query = query.join(PredictionsAlchemy.instance)
query = query.join(InstancesAlchemy.ground_truth)
query = query.filter(GroundTruthAlchemy.label == label)
query = call_specific_db_func(secuml_conf.db_type, 'random_order',
(query, ))
query = query.limit(NUM_MAX_DISPLAY)
return jsonify(_predictions_results(query))
def getPredictions(exp_id, predicted_value, right_wrong, multiclass):
multiclass = multiclass == 'true'
query = session.query(PredictionsAlchemy)
query = query.filter(PredictionsAlchemy.exp_id == exp_id)
query = query.filter(PredictionsAlchemy.value == predicted_value)
if right_wrong != 'all':
query = query.join(PredictionsAlchemy.instance)
query = query.join(InstancesAlchemy.ground_truth)
field = 'family' if multiclass else 'label'
if right_wrong == 'right':
query = query.filter(
getattr(GroundTruthAlchemy, field) == predicted_value)
elif right_wrong == 'wrong':
query = query.filter(
getattr(GroundTruthAlchemy, field) != predicted_value)
else:
assert (False)
query = call_specific_db_func(secuml_conf.db_type, 'random_order',
(query, ))
query = query.limit(NUM_MAX_DISPLAY)
return jsonify(_predictions_results(query))
def get_engine(self):
return call_specific_db_func(self.db_type, 'get_engine',
(self.db_uri,))