def remove_outlier(data, x, row, contamination):
'''
data: which kind of data you are passing
x : 0 for live and 1 for spoof
'''
# 0 indicates all the live images
x1 = np.where(data[:, 512]==x) #512
x2 = data[x1][0:row, :]
train_features_x = x2[:,0:511]
clf = COPOD(contamination = contamination)
clf.fit(train_features_x)
z = clf.labels_
z = np.asarray(z).reshape(row,1)
z_final = np.hstack((x2, z))
x1_2 = np.where(z_final[:, 513]==0)
x2_2 = z_final[x1_2][:, :]
return x2_2
class TestCOPOD(unittest.TestCase):
def setUp(self):
self.n_train = 200
self.n_test = 100
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=10,
contamination=self.contamination, random_state=42)
self.clf = COPOD(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)
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_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_socres = self.clf.decision_function(self.X_test)
pred_ranks = self.clf._predict_rank(self.X_test)
# assert the order is reserved
assert_allclose(rankdata(pred_ranks), rankdata(pred_socres), atol=3)
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=3)
assert_array_less(pred_ranks, 1.01)
assert_array_less(-0.1, pred_ranks)
# def test_plot(self):
# os, cutoff1, cutoff2 = self.clf.explain_outlier(ind=1)
# assert_array_less(0, os)
def test_model_clone(self):
clone_clf = clone(self.clf)
def tearDown(self):
pass
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 COPOD detector
clf_name = 'COPOD'
clf = COPOD()
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)
''' Author: Christian O'Leary Email: [email protected] ''' import numpy as np from pyod.models.copod import COPOD from emmv import emmv_scores rng = np.random.RandomState(42) NUM_COLS = 2 # Generate train data X = 0.3 * rng.randn(100, NUM_COLS) X_train = np.r_[X + 2, X - 2] # Generate some regular novel observations X = 0.3 * rng.randn(20, NUM_COLS) X_regular = np.r_[X + 2, X - 2] # Generate some abnormal novel observations X_outliers = rng.uniform(low=-4, high=4, size=(20, NUM_COLS)) # fit the model model = COPOD() model.fit(X_train) # Get EM & MV scores X_test = np.concatenate((X_regular, X_outliers), axis=0) test_scores = emmv_scores(model, X_test) print('Excess Mass score;', test_scores['em']) print('Mass Volume score:', test_scores['mv'])
