def setUp(self):
self.X_train, self.y_train, _, self.X_test, self.y_test, _ = generate_data(
n_train=100, n_test=50, contamination=0.05)
# temporary solution for relative imports in case pyod is not installed
# if pyod is installed, no need to import sys and sys.path.append("..")
import sys
sys.path.append("..")
from pyod.models.knn import Knn
from pyod.models.combination import aom, moa
from pyod.utils.load_data import generate_data
from pyod.utils.utility import precision_n_scores
from pyod.utils.utility import standardizer
if __name__ == "__main__":
n_clf = 20 # number of base detectors
ite = 10 # number of iterations
X, y, _ = generate_data(contamination=0.05, train_only=True) # load data
# lists for storing roc information
roc_mean = []
roc_max = []
roc_aom = []
roc_moa = []
prn_mean = []
prn_max = []
prn_aom = []
prn_moa = []
for t in range(ite):
X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.4)
# temporary solution for relative imports in case pyod is not installed
# if pyod is installed, no need to import sys and sys.path.append("..")
import sys
sys.path.append("..")
from pyod.models.knn import Knn
from pyod.utils.load_data import generate_data
from pyod.utils.utility import precision_n_scores
if __name__ == "__main__":
contamination = 0.1 # percentage of outliers
n_train = 1000 # number of training points
n_test = 500 # number of testing points
X_train, y_train, c_train, X_test, y_test, c_test = generate_data(
n_train=n_train, n_test=n_test, contamination=contamination)
# train a k-NN detector (default parameters, k=10)
clf = Knn()
clf.fit(X_train)
# get the prediction label and scores on the training data
y_train_pred = clf.y_pred
y_train_score = clf.decision_scores
# get the prediction on the test data
y_test_pred = clf.predict(X_test) # outlier label (0 or 1)
y_test_score = clf.decision_function(X_test) # outlier scores
print('Train ROC:{roc}, precision@n:{prn}'.format(
roc=roc_auc_score(y_train, y_train_score),