def _combine(self, scores):
"""
Wrapping for PyOD the ensembler.
Args:
scores (np.float array of shape (num_anomaly_detectors, )) List of scores from multiple anomaly detectors.
Returns:
float: Resulting anomaly score.
"""
return maximization(scores)
def define_combination_methods(normalizer_name, k, norm_results):
combination_methods = {
normalizer_name + ' Average_' + str(k): average(norm_results),
normalizer_name + ' Maximization_' + str(k):
maximization(norm_results),
normalizer_name + ' Aom_' + str(k): aom(norm_results, int(k / 2)),
normalizer_name + ' Moa_' + str(k): moa(norm_results, int(k / 2))
}
return combination_methods
def __train_classifiers(self):
scaler = MinMaxScaler(feature_range=(0, 1))
X = scaler.fit_transform(self.df.copy())
classifiers = self.__load_classifiers()
scores = np.zeros([X.shape[0], len(classifiers)])
for i, (clf_name, clf) in enumerate(classifiers.items()):
try:
clf.fit(X)
scores[:, i] = clf.decision_scores_
except Exception as e:
print("Failed for ", clf_name)
print("because of ", e)
standard_scores = standardizer(scores)
combined_scores = maximization(standard_scores)
return combined_scores
train_scores = np.zeros([X_train.shape[0], n_clf])
test_scores = np.zeros([X_test.shape[0], n_clf])
for i in range(n_clf):
k = k_list[i]
clf = KNN(n_neighbors=k, method='largest')
clf.fit(X_train_norm)
train_scores[:, i] = clf.decision_scores_
test_scores[:, i] = clf.decision_function(X_test_norm)
# decision scores have to be normalized before combination
train_scores_norm, test_scores_norm = standardizer(train_scores,
test_scores)
# combination by average
y_by_average = average(test_scores_norm)
evaluate_print('Combination by Average', y_test, y_by_average)
# combination by max
y_by_maximization = maximization(test_scores_norm)
evaluate_print('Combination by Maximization', y_test, y_by_maximization)
# combination by aom
y_by_aom = aom(test_scores_norm, n_buckets=5)
evaluate_print('Combination by AOM', y_test, y_by_aom)
# combination by moa
y_by_moa = moa(test_scores_norm, n_buckets=5)
evaluate_print('Combination by MOA', y_test, y_by_moa)
def test_maximization(self):
score = maximization(self.scores)
assert_allclose(score, np.array([2, 4, 6]))
print('Combining {n_clf} kNN detectors'.format(n_clf=n_clf))
for i in range(n_clf):
k = k_list[i]
clf = KNN(n_neighbors=k, method='largest')
clf.fit(X_train_norm)
train_scores[:, i] = clf.decision_scores_
test_scores[:, i] = clf.decision_function(X_test_norm)
# Decision scores have to be normalized before combination
train_scores_norm, test_scores_norm = standardizer(train_scores,
test_scores)
# Combination by average
y_by_average = average(test_scores_norm)
evaluate_print('Combination by Average', y_test, y_by_average)
# Combination by max
y_by_maximization = maximization(test_scores_norm)
evaluate_print('Combination by Maximization', y_test, y_by_maximization)
# Combination by aom
y_by_aom = aom(test_scores_norm, n_buckets=5)
evaluate_print('Combination by AOM', y_test, y_by_aom)
# Combination by moa
y_by_moa = moa(test_scores_norm, n_buckets=5)
evaluate_print('Combination by MOA', y_test, y_by_moa)
def test_maximization(self):
score = maximization(self.scores)
assert_allclose(score, np.array([2, 4, 6]))
