def removeClusterLabel(experiment_id, selected_cluster, num_results):
selected_cluster = int(selected_cluster)
num_results = int(num_results)
experiment = updateCurrentExperiment(experiment_id)
clustering = Clustering.fromJson(experiment)
clustering.removeClusterLabel(selected_cluster, num_results)
return ''
def getValidationDataset(experiment_id):
experiment = updateCurrentExperiment(experiment_id)
test_conf = experiment.classification_conf.test_conf
if test_conf.method == 'test_dataset':
return test_conf.test_dataset
else:
return experiment.dataset
def activeLearningSuggestionsMonitoring(experiment_id, iteration):
experiment = updateCurrentExperiment(experiment_id)
filename = experiment.getOutputDirectory() + str(int(iteration) - 1) + '/'
filename += 'suggestions_accuracy/'
filename += 'labels_families'
filename += '_high_confidence_suggestions.png'
return send_file(filename)
def getInstancesToAnnotate(experiment_id, iteration, predicted_label):
experiment = updateCurrentExperiment(experiment_id)
filename = experiment.getOutputDirectory() + str(iteration) + '/'
filename += 'toannotate_' + predicted_label + '.csv'
df = pd.read_csv(filename)
queries = list(df.instance_id)
return jsonify({'instances': queries})
def getNumComponents(experiment_id):
experiment = updateCurrentExperiment(experiment_id)
directory = experiment.getOutputDirectory()
filename = directory + 'projection_matrix.csv'
with open(filename, 'r') as f:
header = f.readline()
num_components = len(header.split(',')) - 1
return str(num_components)
def getClusterLabelFamilyIds(experiment_id, selected_cluster, label, family, num_results):
selected_cluster = int(selected_cluster)
num_results = int(num_results)
experiment = updateCurrentExperiment(experiment_id)
clustering = Clustering.fromJson(experiment)
ids = clustering.getClusterLabelFamilyIds(selected_cluster, label, family)
res = listResultWebFormat(ids, num_results)
return jsonify(res)
def getNumElements(experiment_id, selected_cluster):
selected_cluster = int(selected_cluster)
experiment = updateCurrentExperiment(experiment_id)
clustering = Clustering.fromJson(experiment)
cluster = clustering.clusters[selected_cluster]
res = {}
res['num_elements'] = cluster.numInstances()
return jsonify(res)
def getStatsPlot(experiment_id, plot_type, feature):
experiment = updateCurrentExperiment(experiment_id)
filename = experiment.getOutputDirectory() + feature + '/'
if plot_type.find('histogram') >= 0:
filename += plot_type + '.json'
else:
filename += plot_type + '.png'
return send_file(filename)
def addClusterLabel(experiment_id, selected_cluster, num_results, label,
family, label_iteration, label_method):
selected_cluster = int(selected_cluster)
num_results = int(num_results)
experiment = updateCurrentExperiment(experiment_id)
clustering = Clustering.fromJson(experiment)
clustering.addClusterLabel(selected_cluster, num_results, label, family,
label_iteration, label_method)
return ''
def getLabelsFamilies(experiment_id, iteration_max):
experiment = updateCurrentExperiment(experiment_id)
if iteration_max == 'None':
iteration_max = None
else:
iteration_max = int(iteration_max)
labels_families = labels_tools.getLabelsFamilies(
session, experiment.labels_id, iteration_max=iteration_max)
return jsonify(labels_families)
def getClustersLabels(experiment_id):
experiment = updateCurrentExperiment(experiment_id)
clustering = Clustering.fromJson(experiment)
# Do not consider empty clusters for visualization
clusters = []
for c in range(clustering.num_clusters):
#if clustering.clusters[c].numInstances() > 0:
clusters.append({'id': c, 'label': clustering.clusters[c].label})
return jsonify({'clusters': clusters})
def supervisedLearningMonitoring(experiment_id, train_test, kind):
experiment = updateCurrentExperiment(experiment_id)
filename = experiment.getOutputDirectory() + train_test + '/'
filename += kind
if kind == 'ROC':
filename += '.png'
else:
filename += '.json'
return send_file(filename)
def getClusterInstancesVisu(experiment_id, selected_cluster, c_e_r, num_results):
num_results = int(num_results)
selected_cluster = int(selected_cluster)
experiment = updateCurrentExperiment(experiment_id)
clustering = Clustering.fromJson(experiment)
selected_cluster_ids = {}
selected_cluster_ids[selected_cluster] = \
clustering.getClusterInstancesVisu(
selected_cluster, num_results, random = True)[c_e_r]
return jsonify(selected_cluster_ids)
def getIterationSupervisedExperiment(experiment_id, iteration):
experiment = updateCurrentExperiment(experiment_id)
active_learning = Iteration(experiment, int(iteration))
binary_multiclass = 'multiclass'
if 'binary' in experiment.conf.models_conf.keys():
binary_multiclass = 'binary'
models_exp_file = experiment.getOutputDirectory()
models_exp_file += str(iteration) + '/models_experiments.json'
with open(models_exp_file, 'r') as f:
models_exp = json.load(f)
return str(models_exp[binary_multiclass])
def getInstance(experiment_id, view_id, instance_id, ident):
try:
if view_id == 'None':
view_id = None
experiment = updateCurrentExperiment(experiment_id)
project = experiment.project
module = importlib.import_module('SecuML_web.base.views.Projects.' +
project)
return module.getInstance(experiment, view_id, instance_id, ident)
except IOError as e:
app.logger.error(e)
return 'Unable to display the instance', ident
def getLabeledInstances(experiment_id):
experiment = updateCurrentExperiment(experiment_id)
experiment_label_id = experiment.labels_id
res = {}
res['malicious'] = labels_tools.getLabelIds(session,
'malicious',
experiment_label_id,
annotation=True)
res['benign'] = labels_tools.getLabelIds(session,
'benign',
experiment_label_id,
annotation=True)
return jsonify(res)
def activeLearningModelsMonitoring(experiment_id, iteration, train_cv_validation):
experiment = updateCurrentExperiment(experiment_id)
active_learning = Iteration(experiment, int(iteration))
binary_multiclass = 'multiclass'
estimator = 'accuracy'
if 'binary' in experiment.conf.models_conf.keys():
binary_multiclass = 'binary'
estimator = 'auc'
directory = active_learning.output_directory
filename = directory
filename += 'models_performance/'
filename += binary_multiclass + '_' + train_cv_validation + '_' + estimator + '_monitoring.png'
return send_file(filename, mimetype='image/png')
def runNextIteration(experiment_id, iteration_number):
res = str(celeryRunNextIteration.s().apply_async())
if user_exp:
experiment = updateCurrentExperiment(experiment_id)
filename = experiment.getOutputDirectory()
filename += 'user_actions.log'
file_exists = dir_tools.checkFileExists(filename)
mode = 'a' if file_exists else 'w'
to_print = [datetime.datetime.now(), 'nextIteration', iteration_number]
to_print = map(str, to_print)
to_print = ','.join(to_print)
with open(filename, mode) as f:
print >> f, to_print
return res
def getPredictions(experiment_id, train_test, index):
experiment = updateCurrentExperiment(experiment_id)
filename = experiment.getOutputDirectory()
filename += train_test + '/predictions.csv'
index = int(index)
min_value = index * 0.1
max_value = (index + 1) * 0.1
with open(filename, 'r') as f:
data = pd.read_csv(f, header=0, index_col=0)
data = matrix_tools.extractRowsWithThresholds(data, min_value,
max_value,
'predicted_proba')
selected_instances = list(data.index.values)
proba = list(data['predicted_proba'])
return jsonify({'instances': selected_instances, 'proba': proba})
def removeLabel(experiment_id, inst_experiment_label_id, iteration_number,
instance_id):
labels_tools.removeLabel(session, inst_experiment_label_id, instance_id)
if user_exp:
experiment = updateCurrentExperiment(experiment_id)
filename = experiment.getOutputDirectory()
filename += 'user_actions.log'
file_exists = dir_tools.checkFileExists(filename)
mode = 'a' if file_exists else 'w'
to_print = [datetime.datetime.now(), 'removeLabel', instance_id]
to_print = map(str, to_print)
to_print = ','.join(to_print)
with open(filename, mode) as f:
print >> f, to_print
return ''
def currentAnnotations(experiment_id, iteration):
experiment = updateCurrentExperiment(experiment_id)
page = render_template('ActiveLearning/current_annotations.html',
project=experiment.project)
if user_exp:
filename = experiment.getOutputDirectory()
filename += 'user_actions.log'
file_exists = dir_tools.checkFileExists(filename)
mode = 'a' if file_exists else 'w'
to_print = [datetime.datetime.now(), 'displayAnnotatedInstances']
to_print = map(str, to_print)
to_print = ','.join(to_print)
with open(filename, mode) as f:
print >> f, to_print
return page
def activeLearningMonitoring(experiment_id, iteration, kind, sub_kind):
experiment = updateCurrentExperiment(experiment_id)
active_learning = Iteration(experiment, int(iteration))
directory = active_learning.output_directory
if kind == 'labels':
filename = directory + 'labels_monitoring/'
filename += 'iteration' + '_' + sub_kind + '.png'
if kind == 'families':
filename = directory + 'labels_monitoring/' + 'families_monitoring.png'
if kind == 'clustering':
filename = directory + 'clustering_evaluation/'
filename += sub_kind + '_monitoring.png'
if kind == 'time':
filename = directory
filename += 'execution_time_monitoring.png'
return send_file(filename, mimetype='image/png')
def getFamiliesInstances(experiment_id, label, iteration_max):
experiment = updateCurrentExperiment(experiment_id)
if iteration_max == 'None':
iteration_max = None
else:
iteration_max = int(iteration_max)
families = labels_tools.getLabelsFamilies(
session, experiment.labels_id, iteration_max=iteration_max)[label]
families_instances = {}
for f in families:
families_instances[f] = labels_tools.getLabelFamilyIds(
session,
experiment.labels_id,
label,
family=f,
iteration_max=iteration_max)
return jsonify(families_instances)
def getAlerts(experiment_id, analysis_type):
experiment = updateCurrentExperiment(experiment_id)
filename = experiment.getOutputDirectory()
filename += 'alerts.csv'
with open(filename, 'r') as f:
data = pd.read_csv(f, header=0, index_col=0)
num_max_alerts = experiment.classification_conf.test_conf.alerts_conf.num_max_alerts
alerts = list(data[['predicted_proba']].itertuples())
if num_max_alerts < len(alerts):
if analysis_type == 'topN':
alerts = alerts[:num_max_alerts]
elif analysis_type == 'random':
alerts = random.sample(alerts, num_max_alerts)
return jsonify({
'instances': [alert[0] for alert in alerts],
'proba': dict(alerts)
})
def changeFamilyLabel(experiment_id, label, family):
experiment = updateCurrentExperiment(experiment_id)
experiment_label_id = experiment.labels_id
labels_tools.changeFamilyLabel(session, label, family, experiment_label_id)
if user_exp:
filename = experiment.getOutputDirectory()
filename += 'user_actions.log'
file_exists = dir_tools.checkFileExists(filename)
mode = 'a' if file_exists else 'w'
to_print = [
datetime.datetime.now(), 'changeFamilyLabel', family, label
]
to_print = map(str, to_print)
to_print = ','.join(to_print)
with open(filename, mode) as f:
print >> f, to_print
return ''
def mergeFamilies(experiment_id, label, families, new_family_name):
experiment = updateCurrentExperiment(experiment_id)
experiment_label_id = experiment.labels_id
families = families.split(',')
labels_tools.mergeFamilies(session, label, families, new_family_name,
experiment_label_id)
if user_exp:
filename = experiment.getOutputDirectory()
filename += 'user_actions.log'
file_exists = dir_tools.checkFileExists(filename)
mode = 'a' if file_exists else 'w'
to_print = [datetime.datetime.now(), 'mergeFamilies', new_family_name]
to_print += map(str, families)
to_print = map(str, to_print)
to_print = ','.join(to_print)
with open(filename, mode) as f:
print >> f, to_print
return ''
def getClusterStats(experiment_id):
experiment = updateCurrentExperiment(experiment_id)
clustering = Clustering.fromJson(experiment)
num_clusters = clustering.num_clusters
num_instances_v = []
labels = []
for c in range(num_clusters):
instances_in_cluster = clustering.clusters[c].instances_ids
num_instances = len(instances_in_cluster)
# the empty clusters are not displayed
#if num_instances > 0:
num_instances_v.append(num_instances)
#labels.append('c_' + str(c))
labels.append(clustering.clusters[c].label)
barplot = BarPlot(labels)
dataset = PlotDataset(num_instances_v, 'Num. Instances')
barplot.addDataset(dataset)
return jsonify(barplot.toJson())
def addLabel(experiment_id, inst_experiment_label_id, iteration_number,
instance_id, label, family, method, annotation):
annotation = annotation == 'true'
labels_tools.addLabel(session, inst_experiment_label_id, instance_id,
label, family, iteration_number, method, annotation)
if user_exp:
experiment = updateCurrentExperiment(experiment_id)
filename = experiment.getOutputDirectory()
filename += 'user_actions.log'
file_exists = dir_tools.checkFileExists(filename)
mode = 'a' if file_exists else 'w'
to_print = [
datetime.datetime.now(), 'addLabel', iteration_number, instance_id,
label, family, method, annotation
]
to_print = map(str, to_print)
to_print = ','.join(to_print)
with open(filename, mode) as f:
print >> f, to_print
return ''
def getFamiliesBarplot(experiment_id, iteration, label):
experiment = updateCurrentExperiment(experiment_id)
experiment_label_id = experiment.labels_id
if iteration == 'None':
iteration = None
family_counts = labels_tools.getFamiliesCounts(experiment.session,
experiment_label_id,
iteration_max=iteration,
label=label)
df = pd.DataFrame({
'families':
family_counts.keys(),
'counts': [family_counts[k] for k in family_counts.keys()]
})
matrix_tools.sortDataFrame(df, 'families', ascending=True, inplace=True)
barplot = BarPlot(list(df['families']))
dataset = PlotDataset(list(df['counts']), 'Num. Instances')
dataset.setColor(colors_tools.getLabelColor(label))
barplot.addDataset(dataset)
return jsonify(barplot.toJson())
def getFamiliesPerformance(experiment_id, train_test, label, threshold):
experiment = updateCurrentExperiment(experiment_id)
filename = experiment.getOutputDirectory() + train_test + '/families/'
if label == 'malicious':
filename += 'tp_'
tp_fp = 'Detection Rate'
elif label == 'benign':
filename += 'fp_'
tp_fp = 'False Positive Rate'
filename += 'families_thresholds.csv'
with open(filename, 'r') as f:
perf = pd.read_csv(f, header=0, index_col=0)
families = list(perf.columns.values[:-1])
threshold = float(threshold) / 100
thresholds = list(perf.index[:-1])
threshold_value = min(enumerate(thresholds),
key=lambda x: abs(x[1] - threshold))[1]
perf = list(perf.loc[threshold_value])
barplot = BarPlot(families)
barplot.addDataset(PlotDataset(perf, tp_fp))
return jsonify(barplot.toJson())