def perform_outlier_detection_all_combos(self, X):
# LOF on all features
scores = {'temporal': {}, 'content': {}, 'user': {}, 'network': {}}
print "Starting anomaly detection loop"
for key, value in X.iteritems():
clf = IsolationForest()
clf.fit(value)
scores[key]['iforest'] = clf.decision_function(value)
#print "Finished iforest"
clf = LocalOutlierFactor(n_neighbors=20)
clf.fit(value)
scores[key]['lof'] = clf._decision_function(value)
clf = DBOD()
clf.fit(value)
scores[key]['dbod'] = clf.decision_function_distance(value)
scores[key]['abod'] = clf.decision_function_angle(value)
print "Finished anomaly detection loop"
with open(
'clique_expansion/long_experiment/' + self.seed_user +
'_unnormalized_scores.csv', 'w') as f:
for domain, value in scores.iteritems():
for type_score, all_scores in value.iteritems():
f.write(domain + ' ' + type_score + ',')
for item in all_scores:
f.write(str(item) + ',')
f.write('\n')
combined_scores = self.combine_all(scores)
scores = None
new_scores = combined_scores[self.len_priors:]
user_scores = sorted(zip(self.current_level_users, new_scores),
key=lambda x: x[1],
reverse=True)
threshold = np.percentile(new_scores, 8)
outliers = [u[0] for u in user_scores if u[1] <= threshold]
return outliers
