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 = SOS(contamination=self.contamination)
self.clf.fit(self.X_train)
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=5,
contamination=self.contamination, random_state=42)
self.clf = SOS(contamination=self.contamination)
self.clf.fit(self.X_train)
def getOulierSOS(dataset):
'''
@brief Function that executes SOS 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
sos = SOS()
# Fits the data and obtains labels
sos.fit(dataset)
# Return labels
return sos.labels_
def fit_transform(self, df_train, df_corrupted):
pyod_model = SOS(contamination=0.25)
df_outliers_num = self.num_out_detect(df_train, df_corrupted,
pyod_model)
df_outliers_cat = self.cat_out_detect(df_train, df_corrupted)
df_outliers = df_outliers_num.join(df_outliers_cat, how='inner')
for col in df_corrupted.columns:
for i in df_outliers.index:
if df_outliers.loc[i, col + "_outlier"] == 1:
df_outliers.loc[i, col] = np.nan
return df_outliers, self.predictors
def choose_model(model, nnet):
""" among implemented in PyOD """
clfs = {
'AE':
AutoEncoder(hidden_neurons=nnet, contamination=0.1, epochs=15),
'VAE':
VAE(encoder_neurons=nnet[:5],
decoder_neurons=nnet[4:],
contamination=0.1,
epochs=13),
'ABOD':
ABOD(),
'FeatureBagging':
FeatureBagging(),
'HBOS':
HBOS(),
'IForest':
IForest(),
'KNN':
KNN(),
'LOF':
LOF(),
'OCSVM':
OCSVM(),
'PCA':
PCA(),
'SOS':
SOS(),
'COF':
COF(),
'CBLOF':
CBLOF(),
'SOD':
SOD(),
'LOCI':
LOCI(),
'MCD':
MCD()
}
return clfs[model]
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, 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 kNN detector
clf_name = 'KNN'
clf = SOS()
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 TestSOS(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=5,
contamination=self.contamination, random_state=42)
self.clf = SOS(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_prediction_proba_parameter(self):
with assert_raises(ValueError):
self.clf.predict_proba(self.X_test, method='something')
def test_prediction_labels_confidence(self):
pred_labels, confidence = self.clf.predict(self.X_test,
return_confidence=True)
assert_equal(pred_labels.shape, self.y_test.shape)
assert_equal(confidence.shape, self.y_test.shape)
assert (confidence.min() >= 0)
assert (confidence.max() <= 1)
def test_prediction_proba_linear_confidence(self):
pred_proba, confidence = self.clf.predict_proba(self.X_test,
method='linear',
return_confidence=True)
assert (pred_proba.min() >= 0)
assert (pred_proba.max() <= 1)
assert_equal(confidence.shape, self.y_test.shape)
assert (confidence.min() >= 0)
assert (confidence.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=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)
# todo: fix clone issue
def test_model_clone(self):
pass
# clone_clf = clone(self.clf)
def tearDown(self):
pass
def initialise_pyod_classifiers(self, outlier_fraction):
#Testing every query to every class and then predicting only if it belongs to the same class
classifiers = {}
#Proximity based
classifiers['K Nearest Neighbors (KNN)'] = []
classifiers['Average K Nearest Neighbors (AvgKNN)'] = []
classifiers['Median K Nearest Neighbors (MedKNN)'] = []
classifiers['Local Outlier Factor (LOF)'] = []
classifiers['Connectivity-Based Outlier Factor (COF)'] = []
#classifiers['Clustering-Based Local Outlier Factor (CBLOF)'] = []
classifiers['LOCI'] = []
#classifiers['Histogram-based Outlier Score (HBOS)'] = []
classifiers['Subspace Outlier Detection (SOD)'] = []
#Linear models
classifiers['Principal Component Analysis (PCA)'] = []
#classifiers['Minimum Covariance Determinant (MCD)'] = [] #To slow
classifiers['One-Class Support Vector Machines (OCSVM)'] = []
classifiers['Deviation-based Outlier Detection (LMDD)'] = []
#Probabilistic
classifiers['Angle-Based Outlier Detection (ABOD)'] = []
classifiers['Stochastic Outlier Selection (SOS)'] = []
#Outlier Ensembles
classifiers['Isolation Forest (IForest)'] = []
classifiers['Feature Bagging'] = []
classifiers['Lightweight On-line Detector of Anomalies (LODA)'] = []
for i in range(self.k_way):
for i in range(self.k_way):
classifiers['K Nearest Neighbors (KNN)'].append(
KNN(method='largest',
n_neighbors=int(self.n_shot / 3) + 1,
contamination=outlier_fraction))
classifiers['Average K Nearest Neighbors (AvgKNN)'].append(
KNN(method='mean',
n_neighbors=int(self.n_shot / 3) + 1,
contamination=outlier_fraction))
classifiers['Median K Nearest Neighbors (MedKNN)'].append(
KNN(method='median',
n_neighbors=int(self.n_shot / 3) + 1,
contamination=outlier_fraction))
classifiers['Local Outlier Factor (LOF)'].append(
LOF(n_neighbors=int(self.n_shot / 3) + 1,
contamination=outlier_fraction))
classifiers['Connectivity-Based Outlier Factor (COF)'].append(
COF(n_neighbors=int(self.n_shot / 3) + 1,
contamination=outlier_fraction))
classifiers['LOCI'].append(
LOCI(contamination=outlier_fraction))
classifiers['Subspace Outlier Detection (SOD)'].append(
SOD(n_neighbors=int(self.n_shot / 3) + 2,
contamination=outlier_fraction,
ref_set=max(2, int((int(self.n_shot / 3) + 2) / 3))))
classifiers['Principal Component Analysis (PCA)'].append(
PCA(contamination=outlier_fraction))
classifiers[
'One-Class Support Vector Machines (OCSVM)'].append(
OCSVM(contamination=outlier_fraction))
classifiers['Deviation-based Outlier Detection (LMDD)'].append(
LMDD(contamination=outlier_fraction))
classifiers['Angle-Based Outlier Detection (ABOD)'].append(
ABOD(contamination=outlier_fraction))
classifiers['Stochastic Outlier Selection (SOS)'].append(
SOS(contamination=outlier_fraction))
classifiers['Isolation Forest (IForest)'].append(
IForest(contamination=outlier_fraction))
classifiers['Feature Bagging'].append(
FeatureBagging(contamination=outlier_fraction))
classifiers[
'Lightweight On-line Detector of Anomalies (LODA)'].append(
LODA(contamination=outlier_fraction))
self.num_different_models = len(classifiers)
return classifiers
class TestSOS(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=5,
contamination=self.contamination, random_state=42)
self.clf = SOS(contamination=self.contamination)
self.clf.fit(self.X_train)
def test_sklearn_estimator(self):
# TODO: sklearn check does not support Numba optimization
# check_estimator(self.clf)
pass
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)
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
f.write("Model: " + modelname + "\n")
f.write("Dataset " + str(datasetnumber) + ": " + datasetname + "\n")
f.write("Time taken: " + str(time) + " seg.\n")
f.write("Accuracy: " + str(accuracy) + "\n")
if accuracy!=None:
f.write("@scores\n")
for score in model.decision_scores_:
f.write(str(score) + "\n")
f.close()
# This is based on executing the script from the folder experiments
ROUTE = "../datasets/outlier_ground_truth/"
# List of datasets
datasets = ["annthyroid.mat", "arrhythmia.mat", "breastw.mat", "cardio.mat", "glass.mat", "ionosphere.mat", "letter.mat", "lympho.mat", "mammography.mat", "mnist.mat", "musk.mat", "optdigits.mat", "pendigits.mat", "pima.mat", "satellite.mat", "satimage-2.mat", "speech.mat", "thyroid.mat", "vertebral.mat", "vowels.mat", "wbc.mat", "wine.mat"]
# List of models and names
models = [ABOD(), COF(), HBOS(), KNN(), LOF(), MCD(), OCSVM(), PCA(), SOD(), SOS()]
names = ["ABOD", "COF", "HBOS", "KNN", "LOF", "MCD", "OCSVM", "PCA", "SOD", "SOS"]
accuracies = []
for name, model in zip(names, models):
print("\n\n#################################################################")
print("MODEL " + name + " " + str(names.index(name)+1) + "/" + str(len(names)))
print("#################################################################")
acc = []
for dat in datasets:
if name=="ABOD" and dat in ["breastw.mat", "letter.mat", "satellite.mat"]:
result = None
else:
print("Computing dataset " + dat + " " + str(datasets.index(dat)+1) + "/" + str(len(datasets)))
# Read dataset
dataset, labels = readDataset(ROUTE + dat)
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, 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 SOS detector
clf_name = 'SOS'
clf = SOS()
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)
import pandas as pd
from pyod.models.sos import SOS
iris = pd.read_csv("http://bit.ly/iris-csv")
X = iris.drop("Name", axis=1).values
detector = SOS()
detector.fit(X)
iris["score"] = detector.decision_scores_
print(iris.sort_values("score", ascending=False).head(10))
def run_all_models(all_array, labels, pca, data_set_name):
picture_name = all_array.get("# img", 1)
all_array = all_array.drop("# img", 1)
# standardizing data for processing
all_array = standardizer(all_array)
y = labels.get("in").to_numpy()
x_train, x_test, y_train, y_test, picture_train, picture_test = train_test_split(all_array, y, picture_name,
test_size=0.4)
if pca:
transformer = IncrementalPCA()
all_array = transformer.fit_transform(all_array)
print("OCSVM")
now = time()
clf = OCSVM()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("OCSVM", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("Auto-encoder")
now = time()
clf = AutoEncoder(epochs=30)
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("Auto-encoder", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("HBOS")
now = time()
clf = HBOS()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("HBOS", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("SO_GAAL")
now = time()
clf = SO_GAAL()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("SO_GAAL", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("MO_GAAL")
now = time()
clf = MO_GAAL()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("MO_GAAL", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("MCD")
now = time()
clf = MCD()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("MCD", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("SOS")
now = time()
clf = SOS()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("SOS", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("IForest")
now = time()
clf = IForest()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("IFrorest", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("KNN")
now = time()
clf = KNN()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("KNN", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("PCA")
now = time()
clf = PCA()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("PCA", all_array.shape, temp, data_set_name, time() - now, scores_train))