def getOutlierMCD(dataset):
'''
@brief Function that executes MCD 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
mcd = MCD()
# Fits the data and obtains labels
mcd.fit(dataset)
# Return labels
return mcd.labels_
class TestMCD(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,
contamination=self.contamination, random_state=42)
self.clf = MCD(contamination=self.contamination, random_state=42)
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, 'raw_location_') and
self.clf.raw_location_ is not None)
assert (hasattr(self.clf, 'raw_covariance_') and
self.clf.raw_covariance_ is not None)
assert (hasattr(self.clf, 'raw_support_') and
self.clf.raw_support_ is not None)
assert (hasattr(self.clf, 'location_') and
self.clf.location_ is not None)
assert (hasattr(self.clf, 'covariance_') and
self.clf.covariance_ is not None)
assert (hasattr(self.clf, 'precision_') and
self.clf.precision_ is not None)
assert (hasattr(self.clf, 'support_') and
self.clf.support_ 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 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=2.5)
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=2.5)
assert_array_less(pred_ranks, 1.01)
assert_array_less(-0.1, pred_ranks)
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 LOF detector
clf_name = 'MCD'
clf = MCD()
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 TestMCD(unittest.TestCase):
def setUp(self):
self.n_train = 100
self.n_test = 50
self.contamination = 0.1
self.roc_floor = 0.6
self.X_train, self.y_train, self.X_test, self.y_test = generate_data(
n_train=self.n_train, n_test=self.n_test,
contamination=self.contamination, random_state=42)
self.clf = MCD(contamination=self.contamination, random_state=42)
self.clf.fit(self.X_train)
def test_sklearn_estimator(self):
check_estimator(self.clf)
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, 'raw_location_') and
self.clf.raw_location_ is not None)
assert_true(hasattr(self.clf, 'raw_covariance_') and
self.clf.raw_covariance_ is not None)
assert_true(hasattr(self.clf, 'raw_support_') and
self.clf.raw_support_ is not None)
assert_true(hasattr(self.clf, 'location_') and
self.clf.location_ is not None)
assert_true(hasattr(self.clf, 'covariance_') and
self.clf.covariance_ is not None)
assert_true(hasattr(self.clf, 'precision_') and
self.clf.precision_ is not None)
assert_true(hasattr(self.clf, 'support_') and
self.clf.support_ 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 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=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 tearDown(self):
pass
from pyod.models.pca import PCA from pyod.models.lof import LOF from pyod.models.cblof import CBLOF from pyod.models.mcd import MCD from pyod.models.lscp import LSCP # from pyod.models.auto_encoder import AutoEncoder clf_knn = KNN() clf_pca = PCA() clf_mcd = MCD() clf_lof = LOF() clf_cblof = CBLOF() # clf_lscp = LSCP([clf_knn, clf_pca, clf_mcd ]) # clf_ae = AutoEncoder(epochs=50) clf_mcd.fit(encodings_train) clf_pca.fit(encodings_train) clf_knn.fit(encodings_train) clf_lof.fit(encodings_train) clf_cblof.fit(encodings_train) # clf_lscp.fit(encodings_train) # clf_ae.fit(encodings_train) anomaly_scores_mcd = clf_mcd.decision_function(encodings_train) anomaly_scores_pca = clf_pca.decision_function(encodings_train) anomaly_scores_knn = clf_knn.decision_function(encodings_train) anomaly_scores_lof = clf_lof.decision_function(encodings_train) anomaly_scores_cblof = clf_cblof.decision_function(encodings_train) # anomaly_scores_lscp = clf_lscp.decision_function(encodings_train) # anomaly_scores_ae = clf_ae.predict_proba(encodings_train)
a.add_argument("--cluster",
help="Save cluster data to specified file []",
type=str,
required=False)
args = a.parse_args()
mongo = pymongo.MongoClient(args.db,
args.port,
username=args.dbuser,
password=str(args.dbpassword))
db = mongo[args.dbname]
for matching_control, df in every_control_dataframe(db, args):
print("Found {} hits for {}".format(len(df), matching_control))
df = df.set_index('xref')
deduped = df.drop_duplicates()
deduped.to_csv('/tmp/crap.txt', sep='\t')
if len(
deduped
) > 15: # require at least 15 different vectors to be suitable for analysis
mcd = MCD()
mcd.fit(deduped)
labels = mcd.predict(df)
print(labels)
else:
print(
"ERROR! Not enough de-duped datapoints ({}) for analysis - check /tmp/crap.txt for details"
.format(len(deduped)))
exit(0)
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 LOF detector
clf_name = 'MCD'
clf = MCD()
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)