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(n_train=n_train,
n_test=n_test,
n_features=2,
contamination=contamination,
random_state=42)
# train LOCI detector
clf_name = 'LODA'
clf = LODA()
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 TestLODA(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 = LODA(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, 'projections_')
and self.clf.projections_ 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_model_clone(self):
clone_clf = clone(self.clf)
def tearDown(self):
pass
iterate_threshold = True
if __name__ == "__main__":
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s P%(process)d %(levelname)s %(message)s",
)
# load dataset
data_dict = load_dataset(
dataset,
subdataset,
"all",
)
x_train = data_dict["train"]
x_test = data_dict["test"]
x_test_labels = data_dict["test_labels"]
# data preprocessing for MSCRED
od = LODA(n_bins=n_bins, n_random_cuts=n_random_cuts)
od.fit(x_train)
# get outlier scores
anomaly_score = od.decision_function(x_test)
anomaly_label = x_test_labels
# Make evaluation
evaluate_all(anomaly_score, anomaly_label)
random_state=42)
# load pretrained models
prepare_trained_model()
# recommended models
selected_models = select_model(X_train, n_selection=100)
print("Showing the top recommended models...")
for i, model in enumerate(selected_models):
print(i, model)
print()
model_1 = LODA(n_bins=5, n_random_cuts=100)
print(
"1st model Average Precision",
average_precision_score(y_train,
model_1.fit(X_train).decision_scores_))
model_10 = LODA(n_bins=5, n_random_cuts=20)
print(
"10th model Average Precision",
average_precision_score(y_train,
model_10.fit(X_train).decision_scores_))
model_50 = OCSVM(kernel='sigmoid', nu=0.6)
print(
"50th model Average Precision",
average_precision_score(y_train,
model_50.fit(X_train).decision_scores_))
# grogger
df['arr86'] = (df['narr86'] >= 1).astype(int)
Y = df['arr86']
X = df[[
'pcnv', 'avgsen', 'tottime', 'ptime86', 'inc86', 'black', 'hispan',
'born60'
]]
print(i, X.shape, Y.shape)
if OD_Flag:
# clf = HBOS(contamination=0.05)
# clf = IForest(contamination=0.05)
clf = LODA(contamination=0.05)
clf.fit(X)
# remove outliers
X = X.loc[np.where(clf.labels_ == 0)]
Y = Y.loc[np.where(clf.labels_ == 0)]
X = sm.add_constant(X)
# general OLS
# https://www.statsmodels.org/stable/generated/statsmodels.regression.linear_model.OLS.html
# model=sm.OLS(Y, X.astype(float))
# robust regression
# https://www.statsmodels.org/stable/generated/statsmodels.robust.robust_linear_model.RLM.html
# model=sm.RLM(Y, X.astype(float))
sklearn_score_anomalies = clf.decision_function(X_test)
original_paper_score = [-1 * s + 0.5 for s in sklearn_score_anomalies]
auc_svm_ws = evaluate.AUC(original_paper_score, y_test)
# --- LOF --- #
lof = LocalOutlierFactor(novelty=True)
lof.fit(X_train)
sklearn_score_anomalies = lof.decision_function(X_test)
original_paper_score = [-1 * s + 0.5 for s in sklearn_score_anomalies]
auc_lof_ws = evaluate.AUC(original_paper_score, y_test)
# --- LODA --- #
aucs_loda_ws = np.zeros(num_of_experiments)
for r in tqdm(range(num_of_experiments)):
loda = LODA()
loda.fit(X_train)
y_pred_proba_loda = np.zeros(X_test.shape[0])
for i in tqdm(range(X_test.shape[0])):
loda.fit(X_test[i, :].reshape(1, -1))
y_pred_proba_loda[i] = loda.decision_function(X_test[i, :].reshape(
1, -1))
aucs_loda_ws[r] = evaluate.AUC(1 - y_pred_proba_loda, y_test)
auc_loda_ws = np.mean(aucs_loda_ws)
# --- HalfSpaceTrees --- #
aucs_hst_ws = np.zeros(num_of_experiments)
for r in tqdm(range(num_of_experiments)):
hst = HalfSpaceTrees(n_features=X_train_hst.shape[1], n_estimators=100)
hst.fit(X_train_hst, np.zeros(X_train_hst.shape[0]))
y_pred_proba_hst = np.zeros(X_test_hst.shape[0])
for i in tqdm(range(X_test_hst.shape[0])):