def test_invocation(self):
X_2D = self.X_train[:, 0:2]
X_3D = self.X_train[:, 0:3]
X_4D = self.X_train
with assert_raises(IndexError):
rod_3D(X_2D)
assert_array_equal(ROD().decision_function(X_2D),
rod_3D(np.hstack((X_2D, np.zeros(shape=(X_2D.shape[0], 3 - X_2D.shape[1])))))[0])
assert_array_equal(ROD().decision_function(X_3D), rod_3D(X_3D)[0])
assert_array_equal(ROD().decision_function(X_4D), rod_nD(X_4D, False, self.gm, self.data_scaler,
self.angles_scalers1, self.angles_scalers2)[0])
def test_invocation(self):
X_2D = self.X_train[:, 0:2]
X_3D = self.X_train[:, 0:3]
X_4D = self.X_train
with assert_raises(IndexError):
rod_3D(X_2D)
assert_array_equal(
ROD().decision_function(X_2D),
rod_3D(
np.hstack(
(X_2D, np.zeros(shape=(X_2D.shape[0],
3 - X_2D.shape[1]))))))
assert_array_equal(ROD().decision_function(X_3D), rod_3D(X_3D))
assert_array_equal(ROD().decision_function(X_4D),
rod_nD(X_4D, parallel=False))
def test_parameters(self):
assert (hasattr(self.clf, 'decision_scores_')
and self.clf.decision_scores_ is not None)
assert (hasattr(self.clf, 'labels_') and self.clf.labels_ is not None)
assert (hasattr(self.clf, 'threshold_')
and self.clf.threshold_ is not None)
with assert_raises(TypeError):
ROD(parallel_execution='str')
def setUp(self):
self.n_train = 100
self.n_test = 50
self.contamination = 0.1
self.roc_floor = 0.8
self.X_train, self.y_train, self.X_test, self.y_test = generate_data(
n_train=self.n_train,
n_test=self.n_test,
n_features=4,
contamination=self.contamination,
random_state=42)
self.clf = ROD()
self.clf.fit(self.X_train)
def setUp(self):
self.n_train = 100
self.n_test = 50
self.contamination = 0.1
self.roc_floor = 0.8
self.gm = None
self.median = None
self.data_scaler = None
self.angles_scalers1 = None
self.angles_scalers2 = None
self.X_train, self.y_train, self.X_test, self.y_test = generate_data(
n_train=self.n_train, n_test=self.n_test, n_features=4,
contamination=self.contamination, random_state=42)
self.clf = ROD()
self.clf.fit(self.X_train)
if __name__ == "__main__":
contamination = 0.1 # percentage of outliers
n_train = 200 # number of training points
n_test = 100 # number of testing points
# Generate sample data
X_train, y_train, X_test, y_test = generate_data(n_train=n_train,
n_test=n_test,
n_features=2,
contamination=contamination,
random_state=42)
# train ROD detector
clf_name = 'ROD'
clf = ROD()
clf.fit(X_train)
y_train_pred = clf.labels_ # binary labels (0: inliers, 1: outliers)
y_train_scores = clf.decision_scores_ # raw outlier scores
# get the prediction on the test data
y_test_pred = clf.predict(X_test) # outlier labels (0 or 1)
y_test_scores = clf.decision_function(X_test) # outlier scores
# evaluate and print the results
print("\nOn Training Data:")
evaluate_print(clf_name, y_train, y_train_scores)
print("\nOn Test Data:")
evaluate_print(clf_name, y_test, y_test_scores)
