class TestROD(unittest.TestCase):
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 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 test_train_scores(self):
assert_equal(len(self.clf.decision_scores_), self.X_train.shape[0])
def test_prediction_scores(self):
pred_scores = self.clf.decision_function(self.X_test)
# check score shapes
assert_equal(pred_scores.shape[0], self.X_test.shape[0])
def test_prediction_labels(self):
pred_labels = self.clf.predict(self.X_test)
assert_equal(pred_labels.shape, self.y_test.shape)
def test_prediction_proba_parameter(self):
with assert_raises(ValueError):
self.clf.predict_proba(self.X_test, method='something')
def test_fit_predict(self):
pred_labels = self.clf.fit_predict(self.X_train)
assert_equal(pred_labels.shape, self.y_train.shape)
def test_fit_predict_score(self):
self.clf.fit_predict_score(self.X_test, self.y_test)
self.clf.fit_predict_score(self.X_test,
self.y_test,
scoring='roc_auc_score')
self.clf.fit_predict_score(self.X_test,
self.y_test,
scoring='prc_n_score')
with assert_raises(NotImplementedError):
self.clf.fit_predict_score(self.X_test,
self.y_test,
scoring='something')
def test_predict_rank(self):
pred_scores = self.clf.decision_function(self.X_test)
pred_ranks = self.clf._predict_rank(self.X_test)
print(pred_ranks)
# assert the order is reserved
assert_allclose(rankdata(pred_ranks), rankdata(pred_scores), atol=2)
assert_array_less(pred_ranks, self.X_train.shape[0] + 1)
assert_array_less(-0.1, pred_ranks)
def test_predict_rank_normalized(self):
pred_socres = self.clf.decision_function(self.X_test)
pred_ranks = self.clf._predict_rank(self.X_test, normalized=True)
# assert the order is reserved
assert_allclose(rankdata(pred_ranks), rankdata(pred_socres), atol=2)
assert_array_less(pred_ranks, 1.01)
assert_array_less(-0.1, pred_ranks)
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_angle(self):
assert_equal(0.0, angle(v1=[0, 0, 1], v2=[0, 0, 1]))
def test_sigmoid(self):
assert_equal(0.5, sigmoid(np.array([0.0])))
def test_process_sub(self):
subspace = np.array([[1, 1, 1], [2, 2, 2], [3, 3, 3]])
assert_equal([0.5, 0.5, 0.5], process_sub(subspace))
def test_parallel_vs_non_parallel(self):
assert_equal(rod_nD(self.X_train, parallel=False),
rod_nD(self.X_train, parallel=True))
def test_mad(self):
assert_equal([0.6745, 0.0, 0.6745], mad(np.array([1, 2, 3])))
def tearDown(self):
pass
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)
# visualize the results
visualize(clf_name, X_train, y_train, X_test, y_test, y_train_pred,
y_test_pred, show_figure=True, save_figure=False)