def test_data_generate_cluster5(self):
with assert_raises(ValueError):
X_train, y_train, X_test, y_test = \
generate_data_clusters(n_train=self.n_train,
n_test=self.n_test,
n_features=3,
n_clusters='e',
contamination=self.contamination,
random_state=self.random_state)
with assert_raises(ValueError):
X_train, y_train, X_test, y_test = \
generate_data_clusters(n_train=self.n_train,
n_test=self.n_test,
n_features='e',
contamination=self.contamination,
random_state=self.random_state)
with assert_raises(ValueError):
X_train, y_train, X_test, y_test = \
generate_data_clusters(n_train=self.n_train,
n_test=self.n_test,
n_features=3,
contamination='e',
random_state=self.random_state)
with assert_raises(ValueError):
X_train, y_train, X_test, y_test = \
generate_data_clusters(n_train=self.n_train,
n_test=self.n_test,
n_features=3,
contamination=self.contamination,
dist='e',
random_state=self.random_state)
def test_data_generate_cluster3(self):
X_train, y_train, X_test, y_test = \
generate_data_clusters(n_train=self.n_train,
n_test=self.n_test,
n_features=3,
contamination=self.contamination,
random_state=self.random_state)
X_train2, y_train2, X_test2, y_test2 = \
generate_data_clusters(n_train=self.n_train,
n_test=self.n_test,
n_features=3,
contamination=self.contamination,
random_state=self.random_state)
assert_allclose(X_train, X_train2)
assert_allclose(X_test, X_test2)
assert_allclose(y_train, y_train2)
assert_allclose(y_test, y_test2)
def test_data_generate_cluster2(self):
X_train, X_test, y_train, y_test = \
generate_data_clusters(n_train=self.n_train,
n_test=self.n_test,
n_features=4,
contamination=self.contamination,
random_state=self.random_state)
assert_allclose(X_train.shape, (self.n_train, 4))
assert_allclose(X_test.shape, (self.n_test, 4))
def setUp(self):
self.n_train = 200
self.n_test = 100
self.contamination = 0.1
self.n_components = 4
self.roc_floor = 0.8
self.X_train, self.X_test, self.y_train, self.y_test = generate_data_clusters(
n_train=self.n_train,
n_test=self.n_test,
n_clusters=self.n_components,
contamination=self.contamination,
random_state=42,
)
self.clf = GMM(n_components=self.n_components, contamination=self.contamination)
self.clf.fit(self.X_train)
def test_data_generate_cluster(self):
X_train, X_test, y_train, y_test = \
generate_data_clusters(n_train=self.n_train,
n_test=self.n_test,
n_features=2,
contamination=self.contamination,
random_state=self.random_state)
assert_equal(y_train.shape[0], X_train.shape[0])
assert_equal(y_test.shape[0], X_test.shape[0])
assert (self.n_train - X_train.shape[0] <= 1)
assert_equal(X_train.shape[1], 2)
assert (self.n_test - X_test.shape[0] <= 1)
assert_equal(X_test.shape[1], 2)
out_perc = (np.sum(y_train) + np.sum(y_test)) / (
self.n_train + self.n_test)
assert_allclose(self.contamination, out_perc, atol=0.01)
# temporary solution for relative imports in case pyod is not installed
# if pyod is installed, no need to use the following line
sys.path.append(
os.path.abspath(os.path.join(os.path.dirname("__file__"), "..")))
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, X_test, y_train, y_test = generate_data_clusters(
n_train=n_train,
n_test=n_test,
n_features=2,
n_clusters=4,
contamination=contamination,
random_state=42,
)
# train kNN detector
clf_name = "GMM"
clf = GMM(n_components=4)
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)
from pyod.models.lof import LOF
from pyod.utils.data import generate_data_clusters
from pyod.utils.example import data_visualize
from pyod.utils.example import visualize
from pyod.utils.data import evaluate_print
if __name__ == "__main__":
contamination = 0.1 # percentage of outliers
# Generate sample data in clusters
X, y = generate_data_clusters(n_train=450,
n_test=50,
n_clusters=3,
n_features=2,
contamination=contamination,
size='different',
density='different',
dist=0.2,
random_state=42,
return_in_clusters=True)
# visualize the results
data_visualize(X, y, show_figure=True, save_figure=False)
# test on the generated datasets
# Generate sample data in clusters
X_train, X_test, y_train, y_test = generate_data_clusters(
n_train=450,
n_test=50,
n_clusters=3,
