def getOulierMOGAAL(dataset):
'''
@brief Function that executes MO_GAAL algorithm on the dataset and obtains the
labels of the dataset indicating which instance is an inlier (0) or outlier (1)
@param dataset Dataset on which to try the algorithm
@return It returns a list of labels 0 means inlier, 1 means outlier
'''
# Initializating the model
mg = MO_GAAL()
# Fits the data and obtains labels
mg.fit(dataset)
# Return labels
return mg.labels_
class TestMO_GAAL(unittest.TestCase):
"""
Notes: GAN may yield unstable results, so the test is design for running
models only, without any performance check.
"""
def setUp(self):
self.n_train = 1000
self.n_test = 200
self.n_features = 2
self.contamination = 0.1
# GAN may yield unstable results; turning performance check off
# 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=self.n_features,
contamination=self.contamination,
random_state=42)
self.clf = MO_GAAL(k=1,
stop_epochs=2,
contamination=self.contamination)
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)
assert (hasattr(self.clf, '_mu') and self.clf._mu is not None)
assert (hasattr(self.clf, '_sigma') and self.clf._sigma is not None)
assert (hasattr(self.clf, 'discriminator')
and self.clf.discriminator is not None)
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])
# check performance
# assert (roc_auc_score(self.y_test, pred_scores) >= self.roc_floor)
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(self):
pred_proba = self.clf.predict_proba(self.X_test)
assert (pred_proba.min() >= 0)
assert (pred_proba.max() <= 1)
def test_prediction_proba_linear(self):
pred_proba = self.clf.predict_proba(self.X_test, method='linear')
assert (pred_proba.min() >= 0)
assert (pred_proba.max() <= 1)
def test_prediction_proba_unify(self):
pred_proba = self.clf.predict_proba(self.X_test, method='unify')
assert (pred_proba.min() >= 0)
assert (pred_proba.max() <= 1)
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 tearDown(self):
pass
n_train = 20000 # number of training points
n_test = 2000 # number of testing points
n_features = 300 # number of features
# Generate sample data
X_train, y_train, X_test, y_test = \
generate_data(n_train=n_train,
n_test=n_test,
n_features=n_features,
contamination=contamination,
random_state=42)
# train MO_GAAL detector
clf_name = 'MO_GAAL'
clf = MO_GAAL(k=3, stop_epochs=2, contamination=contamination)
clf.fit(X_train)
# get the prediction labels and outlier scores of the training data
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)
class TestMO_GAAL(unittest.TestCase):
def setUp(self):
self.n_train = 3000
self.n_test = 1000
self.n_features = 10
self.contamination = 0.1
# TODO: GAN may yield unstable results; turning performance check off
# 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=self.n_features, contamination=self.contamination,
random_state=42)
self.clf = MO_GAAL(k=1, stop_epochs=2,
contamination=self.contamination)
self.clf.fit(self.X_train)
def test_parameters(self):
assert_true(hasattr(self.clf, 'decision_scores_') and
self.clf.decision_scores_ is not None)
assert_true(hasattr(self.clf, 'labels_') and
self.clf.labels_ is not None)
assert_true(hasattr(self.clf, 'threshold_') and
self.clf.threshold_ is not None)
assert_true(hasattr(self.clf, '_mu') and
self.clf._mu is not None)
assert_true(hasattr(self.clf, '_sigma') and
self.clf._sigma is not None)
assert_true(hasattr(self.clf, 'discriminator') and
self.clf.discriminator is not None)
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])
# check performance
# assert_greater(roc_auc_score(self.y_test, pred_scores), self.roc_floor)
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(self):
pred_proba = self.clf.predict_proba(self.X_test)
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
def test_prediction_proba_linear(self):
pred_proba = self.clf.predict_proba(self.X_test, method='linear')
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
def test_prediction_proba_unify(self):
pred_proba = self.clf.predict_proba(self.X_test, method='unify')
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
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 tearDown(self):
pass
X = df.to_numpy() scaler = StandardScaler() # Representation 1 & 4 #X_scaled = scaler.fit_transform(X) # Representation 2 # times & TFIDF: Scale times only separately #X_times_scaled = scaler.fit_transform(X[:,:len(TIME_FIELDS)]) #X_scaled = np.hstack([X_times_scaled, X[:,len(TIME_FIELDS):]]) # Representation 3 # times & TFIDF: Scale all # X_scaled = scaler.fit_transform(X) # Representation 5 # times & TFIDF: Scale times only and TFIDF features separately. TFIDF vectors are made L2 norm = 1 X_times_scaled = scaler.fit_transform(X[:, :len(TIME_FIELDS) - 1]) scaler_tfidf = Normalizer() X_tfidf = scaler_tfidf.fit_transform(X[:, len(TIME_FIELDS) - 1:]) X_scaled = np.hstack([X_times_scaled, X_tfidf]) clf = MO_GAAL(contamination=0.05) clf.fit(X_scaled) df_all['scores'] = clf.decision_scores_ df_all['labels'] = clf.labels_ df_out = df_all.where(df_all['labels'] == 1).dropna() df_out = df_out.loc[:, (df_out != 0).any(axis=0)] df_out.to_excel(os.path.join(OUT_PATH, OUT_FILE))