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 = LOF(contamination=self.contamination)
self.clf.fit(self.X_train)
from pyod.utils.data import generate_data
from pyod.utils.data import evaluate_print
from pyod.utils.data import visualize
if __name__ == "__main__":
contamination = 0.1 # percentage of outliers
n_train = 200 # number of training points
n_test = 100 # number of testing points
X_train, y_train, X_test, y_test = generate_data(
n_train=n_train, n_test=n_test, contamination=contamination)
# train LOF detector
clf_name = 'LOF'
clf = LOF()
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)
for doc in csvlist:
print(doc)
df = pd.read_csv(doc,encoding='utf-8')
#x =df.loc[:,('V1','V2','V3','V4','V5','V6','V7')]
x = df.loc[:, ('R', 'G', 'B')]
#x=df.iloc[:,6:57]
y=df.loc[:,'original.label']
roc_list=[count,doc]
count=count+1
roc_mat = np.zeros(6)
# 设置 5%的离群点数据
random_state = np.random.RandomState(42)
outliers_fraction = 0.02
# 定义6个后续会使用的离群点检测模型
classifiers = {
"Feature Bagging": FeatureBagging(LOF(n_neighbors=35), contamination=outliers_fraction, check_estimator=False,
random_state=random_state),
"Isolation Forest": IForest(contamination=outliers_fraction, random_state=random_state),
"Average KNN": KNN(contamination=outliers_fraction),
'Local Outlier Factor (LOF)': LOF(
contamination=outliers_fraction),
'One-class SVM (OCSVM)': OCSVM(contamination=outliers_fraction),
'Principal Component Analysis (PCA)': PCA(
contamination=outliers_fraction, random_state=random_state),
}
classifiers_indices = {
'Feature Bagging': 0,
'Isolation Forest': 1,
"Average KNN":2,
'Local Outlier Factor (LOF)':3,
'One-class SVM (OCSVM)':4,
clusters_separation = [0]
# Compare given classifiers under given settings
xx, yy = np.meshgrid(np.linspace(-7, 7, 100), np.linspace(-7, 7, 100))
n_inliers = int((1. - outliers_fraction) * n_samples)
n_outliers = int(outliers_fraction * n_samples)
ground_truth = np.zeros(n_samples, dtype=int)
ground_truth[-n_outliers:] = 1
random_state = np.random.RandomState(42)
# Define nine outlier detection tools to be compared
classifiers = {'Angle-based Outlier Detector (ABOD)':
ABOD(n_neighbors=10,
contamination=outliers_fraction),
'Feature Bagging':
FeatureBagging(LOF(n_neighbors=35),
contamination=outliers_fraction,
random_state=random_state),
'Histogram-base Outlier Detection (HBOS)': HBOS(
contamination=outliers_fraction),
'Isolation Forest': IForest(contamination=outliers_fraction,
random_state=random_state),
'K Nearest Neighbors (KNN)': KNN(
contamination=outliers_fraction),
'Local Outlier Factor (LOF)':
LOF(n_neighbors=35,
contamination=outliers_fraction),
'Minimum Covariance Determinant (MCD)': MCD(
contamination=outliers_fraction, random_state=random_state),
'One-class SVM (OCSVM)': OCSVM(contamination=outliers_fraction),
'Principal Component Analysis (PCA)': PCA(
X1 = df['SF Ratio'].values.reshape(-1,1)
X2 = df['PD Ratio'].values.reshape(-1,1)
X3 = df['AE Ratio'].values.reshape(-1,1)
X4 = df['SAE Ratio'].values.reshape(-1,1)
X5 = df['discontinued patients Ratio'].values.reshape(-1,1)
X = np.concatenate((X1,X2,X3,X4,X5),axis=1)
random_state = np.random.RandomState(42)
outliers_fraction = 0.05
# Define seven outlier detection tools to be compared
classifiers = {
'Angle-based Outlier Detector (ABOD)': ABOD(contamination=outliers_fraction),
'Cluster-based Local Outlier Factor (CBLOF)':CBLOF(contamination=outliers_fraction,check_estimator=False, random_state=random_state),
'Feature Bagging':FeatureBagging(LOF(n_neighbors=35),contamination=outliers_fraction,check_estimator=False,random_state=random_state),
'Histogram-base Outlier Detection (HBOS)': HBOS(contamination=outliers_fraction),
'Isolation Forest': IForest(contamination=outliers_fraction,random_state=random_state),
'K Nearest Neighbors (KNN)': KNN(contamination=outliers_fraction),
'Average KNN': KNN(method='mean',contamination=outliers_fraction)
}
xx, yy = np.meshgrid(np.linspace(0, 1, 200), np.linspace(0, 1, 200))
total=[]
for i, (clf_name, clf) in enumerate(classifiers.items()):
clf.fit(X)
# predict raw anomaly score
scores_pred = clf.decision_function(X) * -1
toeplitz_roc = []
toeplitz_prn = []
toeplitz_time = []
pca_roc = []
pca_prn = []
pca_time = []
rp_roc = []
rp_prn = []
rp_time = []
for j in range(n_iter):
start = time.time()
clf = LOF() # change this to other detection algorithms
clf.fit(X)
y_train_scores = clf.decision_scores_
original_time.append(time.time() - start)
original_roc.append(roc_auc_score(y, y_train_scores))
original_prn.append(precision_n_scores(y, y_train_scores))
X_transformed, _ = jl_fit_transform(X, dim_new, "basic")
start = time.time()
clf.fit(X_transformed)
y_train_scores = clf.decision_scores_
basic_time.append(time.time() - start)
basic_roc.append(roc_auc_score(y, y_train_scores))
basic_prn.append(precision_n_scores(y, y_train_scores))
X_transformed, _ = jl_fit_transform(X, dim_new, "discrete")
y_train = np.append(np.zeros(100 + number_outliers_1),
np.ones(100 + number_outliers_2)).astype(int)
class_1_test = np.random.normal(mean_class_1, var_class_1,
(samples_class_1, 2))
class_2_test = np.random.normal(mean_class_2, var_class_2,
(samples_class_2, 2))
x_test = np.concatenate((class_1_test, class_2_test))
y_test = np.append(np.zeros(samples_class_1),
np.ones(samples_class_2)).astype(int)
acc_normal = accuracy_test(
x_train,
y_train,
x_test,
y_test,
outlierScoreAlgorithm=LOF(contamination=0.23))
results_normal.append(acc_normal)
normal_class_1 = np.random.normal(mean_class_1[1], var_class_1[1],
samples_class_1_outliers)
skew_class_1 = skewnorm.rvs(alpha_1,
size=samples_class_1_outliers,
scale=omega_1,
loc=mean_class_1[0])
class_1_outliers_test = np.array([
np.array([x, y]) for x, y in zip(skew_class_1, normal_class_1)
])
normal_class_2 = np.random.normal(mean_class_2[1], var_class_2[1],
samples_class_2_outliers)
skew_class_2 = skewnorm.rvs(alpha_2,
size=samples_class_2_outliers,
'OCSVM', 'LOF', 'CBLOF', 'HBOS', 'KNN',
'ABOD', 'COPOD'),
index=0)
# train the COPOD detector
if model == 'IForest':
clf = IForest()
elif model == 'FeatureBagging':
clf = FeatureBagging()
elif model == 'PCA':
clf = PCA()
elif model == 'MCD':
clf = MCD()
elif model == 'OCSVM':
clf = OCSVM()
elif model == 'LOF':
clf = LOF()
elif model == 'CBLOF':
clf = CBLOF()
elif model == 'HBOS':
clf = HBOS()
elif model == 'KNN':
clf = KNN()
elif model == 'ABOD':
clf = ABOD()
else:
clf = COPOD()
# fit the model
clf.fit(X)
# get outlier scores
scores = clf.decision_scores_ # raw outlier scores
def pyod_init(model, n_features=None):
# initial model set up
if model == 'abod':
from pyod.models.abod import ABOD
clf = ABOD()
elif model == 'auto_encoder' and n_features:
#import os
#os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
from pyod.models.auto_encoder import AutoEncoder
clf = AutoEncoder(hidden_neurons=[
n_features, n_features * 5, n_features * 5, n_features
],
epochs=5,
batch_size=64,
preprocessing=False)
elif model == 'cblof':
from pyod.models.cblof import CBLOF
clf = CBLOF(n_clusters=4)
elif model == 'hbos':
from pyod.models.hbos import HBOS
clf = HBOS()
elif model == 'iforest':
from pyod.models.iforest import IForest
clf = IForest()
elif model == 'knn':
from pyod.models.knn import KNN
clf = KNN()
elif model == 'lmdd':
from pyod.models.lmdd import LMDD
clf = LMDD()
elif model == 'loci':
from pyod.models.loci import LOCI
clf = LOCI()
elif model == 'loda':
from pyod.models.loda import LODA
clf = LODA()
elif model == 'lof':
from pyod.models.lof import LOF
clf = LOF()
elif model == 'mcd':
from pyod.models.mcd import MCD
clf = MCD()
elif model == 'ocsvm':
from pyod.models.ocsvm import OCSVM
clf = OCSVM()
elif model == 'pca':
from pyod.models.pca import PCA
clf = PCA()
elif model == 'sod':
from pyod.models.sod import SOD
clf = SOD()
elif model == 'vae':
from pyod.models.vae import VAE
clf = VAE()
elif model == 'xgbod':
from pyod.models.xgbod import XGBOD
clf = XGBOD()
else:
#raise ValueError(f"unknown model {model}")
clf = PyODDefaultModel()
return clf
'AutoEncoder'
]
models = {
'BRM': BRM(),
'GM': GaussianMixture(),
'IF': IsolationForest(),
'OCSVM': OneClassSVM(),
'EE': EllipticEnvelope(),
'AvgKNN': KNN(method='mean'),
'LargestKNN': KNN(method='largest'),
'MedKNN': KNN(method='median'),
'PCA': PCA(),
'COF': COF(),
'LODA': LODA(),
'LOF': LOF(),
'HBOS': HBOS(),
'MCD': MCD(),
'AvgBagging': FeatureBagging(combination='average'),
'MaxBagging': FeatureBagging(combination='max'),
'IForest': IForest(),
'CBLOF': CBLOF(n_clusters=10, n_jobs=4),
'FactorAnalysis': FactorAnalysis(),
'KernelDensity': KernelDensity(),
'COPOD': COPOD(),
'SOD': SOD(),
'LSCPwithLODA': LSCP([LODA(), LODA()]),
'AveLMDD': LMDD(dis_measure='aad'),
'VarLMDD': LMDD(dis_measure='var'),
'IqrLMDD': LMDD(dis_measure='iqr'),
'SoGaal': SO_GAAL(),
np.load(os.path.join("multimodality", "baseline_wen_embeding.npy")),
np.load(os.path.join("multimodality", "vae_joint_representation.npy")),
np.concatenate([
np.load(
os.path.join("unimodality", "image", "train_image_embedding.npy")),
np.load(os.path.join("unimodality", "language", "word2vec.npy"))
],
axis=1)
]
unimodality = [
"image", "word2vec", "bert", "concat_joint", "vae_joint", "simple_concat"
]
clfs = [
IForest(random_state=42),
LOF(),
OCSVM(),
PCA(),
KNN(),
HBOS(),
COPOD(),
AutoEncoder(verbose=0),
VAE(latent_dim=32, verbosity=0)
]
for embedding, modality in zip(unimodal_embeddings, unimodality):
print()
print(modality)
print()
embedding_scaled = standardizer(embedding)
#FeatureSelector().select_features(write=True)
#a = pd.Series( DataProcessor().get_all_commands_series())
#print a
#commands = pd.Series(DataProcessor().get_all_commands_series())
#print commands.keys()
sample_df = pd.read_csv(sample_submission_file)
result_df = pd.read_csv('outputs/FeatureSelector/all_500_500.csv')
cols = select_k_best(result_df, 200)
result_df = result_df[cols]
result_df.loc[:, 'Label'] = FeatureSelector().get_labels_array_all()
result_df.to_csv('outputs/FeatureSelector/selected_all.csv')
v = pd.read_csv(validation_file)
validation_set = v['Label']
classification_res = []
clf = LOF(n_neighbors=20, contamination=0.1)
#for num in range(0, 40):
# print "******* User {} ********".format(num)
# ClassificationModel(user_num=num, df=result_df).optimize_parameters()
for num in range(0, 10):
print "******* User {} ********".format(num)
classification_res.extend(
ClassificationModel(user_num=num, df=result_df,
model=clf).predictLabels())
validation(classification_res, validation_set)
for num in range(10, 40):
print "******* User {} ********".format(num)
classification_res = ClassificationModel(user_num=num,
def make_mlo(hub, data, train):
'''
Create the Machine Learning Object used for this sequence
'''
return LOF(contamination=0.01)
X = np.concatenate((X1, X2), axis=1)
random_state = np.random.RandomState(42)
outliers_fraction = 0.05
# Running PyOD Algorithms to detect outliers
classifiers = {
'Angle-based Outlier Detector (ABOD)':
ABOD(contamination=outliers_fraction),
'Cluster-based Local Outlier Factor (CBLOF)':
CBLOF(contamination=outliers_fraction,
check_estimator=False,
random_state=random_state),
'Feature Bagging':
FeatureBagging(LOF(n_neighbors=35),
contamination=outliers_fraction,
check_estimator=False,
random_state=random_state),
#'Histogram-base Outlier Detection (HBOS)': HBOS(contamination=outliers_fraction),
'Isolation Forest':
IForest(contamination=outliers_fraction, random_state=random_state),
'K Nearest Neighbors (KNN)':
KNN(contamination=outliers_fraction),
'Average KNN':
KNN(method='mean', contamination=outliers_fraction)
}
xx, yy = np.meshgrid(np.linspace(0, 1, 200), np.linspace(0, 1, 200))
for i, (clf_name, clf) in enumerate(classifiers.items()):
class TestLOF(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 = LOF(contamination=self.contamination)
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, 'n_neighbors_') and
self.clf.n_neighbors_ 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)
print(pred_ranks)
print(pred_ranks)
# 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
def get_estimators(contamination):
"""Internal method to create a list of 600 random base outlier detectors.
Parameters
----------
contamination : float in (0., 0.5), optional (default=0.1)
The amount of contamination of the data set,
i.e. the proportion of outliers in the data set. Used when fitting to
define the threshold on the decision function.
Returns
-------
base_detectors : list
A list of initialized random base outlier detectors.
"""
BASE_ESTIMATORS = [
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
ABOD(n_neighbors=5, contamination=contamination),
ABOD(n_neighbors=10, contamination=contamination),
ABOD(n_neighbors=15, contamination=contamination),
ABOD(n_neighbors=20, contamination=contamination),
ABOD(n_neighbors=25, contamination=contamination),
ABOD(n_neighbors=30, contamination=contamination),
ABOD(n_neighbors=35, contamination=contamination),
ABOD(n_neighbors=40, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
KNN(n_neighbors=5, contamination=contamination),
KNN(n_neighbors=15, contamination=contamination),
KNN(n_neighbors=25, contamination=contamination),
KNN(n_neighbors=35, contamination=contamination),
KNN(n_neighbors=45, contamination=contamination),
KNN(n_neighbors=50, contamination=contamination),
KNN(n_neighbors=55, contamination=contamination),
KNN(n_neighbors=65, contamination=contamination),
KNN(n_neighbors=75, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=95, contamination=contamination),
KNN(n_neighbors=100, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
KNN(n_neighbors=5, contamination=contamination),
KNN(n_neighbors=15, contamination=contamination),
KNN(n_neighbors=25, contamination=contamination),
KNN(n_neighbors=35, contamination=contamination),
KNN(n_neighbors=45, contamination=contamination),
KNN(n_neighbors=50, contamination=contamination),
KNN(n_neighbors=55, contamination=contamination),
KNN(n_neighbors=65, contamination=contamination),
KNN(n_neighbors=75, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=95, contamination=contamination),
KNN(n_neighbors=100, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
KNN(n_neighbors=5, contamination=contamination),
KNN(n_neighbors=15, contamination=contamination),
KNN(n_neighbors=25, contamination=contamination),
KNN(n_neighbors=35, contamination=contamination),
KNN(n_neighbors=45, contamination=contamination),
KNN(n_neighbors=50, contamination=contamination),
KNN(n_neighbors=55, contamination=contamination),
KNN(n_neighbors=65, contamination=contamination),
KNN(n_neighbors=75, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=95, contamination=contamination),
KNN(n_neighbors=100, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
ABOD(n_neighbors=5, contamination=contamination),
ABOD(n_neighbors=10, contamination=contamination),
ABOD(n_neighbors=15, contamination=contamination),
ABOD(n_neighbors=20, contamination=contamination),
ABOD(n_neighbors=25, contamination=contamination),
ABOD(n_neighbors=30, contamination=contamination),
ABOD(n_neighbors=35, contamination=contamination),
ABOD(n_neighbors=40, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
KNN(n_neighbors=5, contamination=contamination),
KNN(n_neighbors=15, contamination=contamination),
KNN(n_neighbors=25, contamination=contamination),
KNN(n_neighbors=35, contamination=contamination),
KNN(n_neighbors=45, contamination=contamination),
KNN(n_neighbors=50, contamination=contamination),
KNN(n_neighbors=55, contamination=contamination),
KNN(n_neighbors=65, contamination=contamination),
KNN(n_neighbors=75, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=95, contamination=contamination),
KNN(n_neighbors=100, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
ABOD(n_neighbors=5, contamination=contamination),
ABOD(n_neighbors=10, contamination=contamination),
ABOD(n_neighbors=15, contamination=contamination),
ABOD(n_neighbors=20, contamination=contamination),
ABOD(n_neighbors=25, contamination=contamination),
ABOD(n_neighbors=30, contamination=contamination),
ABOD(n_neighbors=35, contamination=contamination),
ABOD(n_neighbors=40, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
HBOS(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
PCA(contamination=contamination),
KNN(n_neighbors=5, contamination=contamination),
KNN(n_neighbors=15, contamination=contamination),
KNN(n_neighbors=25, contamination=contamination),
KNN(n_neighbors=35, contamination=contamination),
KNN(n_neighbors=45, contamination=contamination),
KNN(n_neighbors=50, contamination=contamination),
KNN(n_neighbors=55, contamination=contamination),
KNN(n_neighbors=65, contamination=contamination),
KNN(n_neighbors=75, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=85, contamination=contamination),
KNN(n_neighbors=95, contamination=contamination),
KNN(n_neighbors=100, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
IForest(n_estimators=50, contamination=contamination),
IForest(n_estimators=100, contamination=contamination),
IForest(n_estimators=150, contamination=contamination),
IForest(n_estimators=200, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=10, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=50, contamination=contamination),
LOF(n_neighbors=55, contamination=contamination),
LOF(n_neighbors=60, contamination=contamination),
LOF(n_neighbors=65, contamination=contamination),
LOF(n_neighbors=70, contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
ABOD(n_neighbors=5, contamination=contamination),
ABOD(n_neighbors=10, contamination=contamination),
ABOD(n_neighbors=15, contamination=contamination),
ABOD(n_neighbors=20, contamination=contamination),
ABOD(n_neighbors=25, contamination=contamination),
ABOD(n_neighbors=30, contamination=contamination),
ABOD(n_neighbors=35, contamination=contamination),
ABOD(n_neighbors=40, contamination=contamination),
ABOD(n_neighbors=45, contamination=contamination),
OCSVM(contamination=contamination),
OCSVM(contamination=contamination),
OCSVM(contamination=contamination),
OCSVM(contamination=contamination),
OCSVM(contamination=contamination),
OCSVM(contamination=contamination),
OCSVM(contamination=contamination),
OCSVM(contamination=contamination),
OCSVM(contamination=contamination),
OCSVM(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
MCD(contamination=contamination),
LOF(n_neighbors=75, contamination=contamination),
LOF(n_neighbors=80, contamination=contamination),
LOF(n_neighbors=85, contamination=contamination),
LOF(n_neighbors=90, contamination=contamination),
LOF(n_neighbors=95, contamination=contamination),
LOF(n_neighbors=100, contamination=contamination),
ABOD(n_neighbors=5, contamination=contamination),
ABOD(n_neighbors=10, contamination=contamination),
ABOD(n_neighbors=15, contamination=contamination),
ABOD(n_neighbors=20, contamination=contamination),
ABOD(n_neighbors=25, contamination=contamination),
ABOD(n_neighbors=30, contamination=contamination),
ABOD(n_neighbors=35, contamination=contamination),
ABOD(n_neighbors=40, contamination=contamination),
]
return BASE_ESTIMATORS
CBLOF(contamination=outliers_fraction,
check_estimator=False,
random_state=random_state),
'Feature Bagging':
FeatureBagging(contamination=outliers_fraction,
check_estimator=False,
random_state=random_state),
'Histogram-base Outlier Detection (HBOS)':
HBOS(contamination=outliers_fraction),
'Isolation Forest':
IForest(contamination=outliers_fraction,
random_state=random_state),
'K Nearest Neighbors (KNN)':
KNN(contamination=outliers_fraction),
'Local Outlier Factor (LOF)':
LOF(contamination=outliers_fraction),
'Minimum Covariance Determinant (MCD)':
MCD(contamination=outliers_fraction, random_state=random_state),
'One-class SVM (OCSVM)':
OCSVM(contamination=outliers_fraction, random_state=random_state),
'Principal Component Analysis (PCA)':
PCA(contamination=outliers_fraction, random_state=random_state),
}
classifiers_indices = {
'Angle-based Outlier Detector (ABOD)': 0,
'Cluster-based Local Outlier Factor': 1,
'Feature Bagging': 2,
'Histogram-base Outlier Detection (HBOS)': 3,
'Isolation Forest': 4,
'K Nearest Neighbors (KNN)': 5,
'Local Outlier Factor (LOF)': 6,
print("\n... Processing", mat_file_name, '...')
mat = sp.io.loadmat(os.path.join('../datasets', mat_file))
X = mat['X']
y = mat['y'].ravel()
outliers_fraction = np.sum(y) / len(y)
X = StandardScaler().fit_transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
classifiers = {
'Angle-based Outlier Detector (ABOD)': ABOD(n_neighbors=10,
contamination=outliers_fraction),
'Cluster-based Local Outlier Factor (CBLOF)':
CBLOF(contamination=outliers_fraction, check_estimator=False),
'Feature Bagging': FeatureBagging(LOF(), contamination=outliers_fraction),
'Histogram-base Outlier Detection (HBOS)': HBOS(
contamination=outliers_fraction),
'Isolation Forest': IForest(contamination=outliers_fraction),
'K Nearest Neighbors (KNN)': KNN(contamination=outliers_fraction),
'Average KNN': KNN(method='mean', contamination=outliers_fraction),
'Local Outlier Factor (LOF)': LOF(contamination=outliers_fraction),
'Minimum Covariance Determinant (MCD)': MCD(
contamination=outliers_fraction),
'One-class SVM (OCSVM)': OCSVM(contamination=outliers_fraction),
'Principal Component Analysis (PCA)': PCA(contamination=outliers_fraction)
}
stat_mat_all = np.zeros([len(classifiers), 10])
report_list = ['train_roc_orig', 'train_p@n_orig', 'train_roc_psa',
'train_p@n_psa',
# Define the number of inliers and outliers
n_samples = 200
outliers_fraction = 0.25
clusters_separation = [0]
# Compare given detectors under given settings
# Initialize the data
xx, yy = np.meshgrid(np.linspace(-7, 7, 100), np.linspace(-7, 7, 100))
n_inliers = int((1. - outliers_fraction) * n_samples)
n_outliers = int(outliers_fraction * n_samples)
ground_truth = np.zeros(n_samples, dtype=int)
ground_truth[-n_outliers:] = 1
# initialize a set of detectors for LSCP
detector_list = [
LOF(n_neighbors=5),
LOF(n_neighbors=10),
LOF(n_neighbors=15),
LOF(n_neighbors=20),
LOF(n_neighbors=25),
LOF(n_neighbors=30),
LOF(n_neighbors=35),
LOF(n_neighbors=40),
LOF(n_neighbors=45),
LOF(n_neighbors=50)
]
# Show the statics of the data
print('Number of inliers: %i' % n_inliers)
print('Number of outliers: %i' % n_outliers)
print(
def getDetectors(self, parameterdict):
detectors = []
windowSize = [
value for key, value in parameterdict.items()
if "windowsize_" in key.lower()
][0]
featureset = [
value for key, value in parameterdict.items()
if "featureset_" in key.lower()
][0]
detectortype = [
value for key, value in parameterdict.items()
if "type_" in key.lower()
][0]
detectorlist = detectortype.split()
features = self.featureGenerator.getSlidingWindowFeaturesEvents(
int(windowSize), int(featureset))
X = features[0]
y = features[1]
for detector in detectorlist:
if (detector.rstrip() == "OCSVM"):
kernel = [
value for key, value in parameterdict.items()
if "kernel_" in key.lower()
][0]
nu = [
value for key, value in parameterdict.items()
if "nu_" in key.lower()
][0]
clf = OCSVM(kernel=kernel, nu=nu, max_iter=100)
if (detector.rstrip() == "IForest"):
num_estimators = [
value for key, value in parameterdict.items()
if "num_estimators_" in key.lower()
][0]
max_samples = [
value for key, value in parameterdict.items()
if "max_samples_" in key.lower()
][0]
clf = IForest(n_estimators=int(num_estimators),
max_samples=int(max_samples))
if (detector.rstrip() == "PCA"):
clf = PCA()
if (detector.rstrip() == "LOF"):
n_neighbors = [
value for key, value in parameterdict.items()
if "lof_n_neighbors_" in key.lower()
][0]
clf = LOF(n_neighbors=int(n_neighbors))
if (detector.rstrip() == "KNN"):
n_neighbors = [
value for key, value in parameterdict.items()
if "knn_n_neighbors_" in key.lower()
][0]
clf = KNN(n_neighbors=int(n_neighbors))
with HiddenPrints():
clf.fit_predict_score(X, y, scoring='roc_auc_score')
detectors.append(clf)
return detectors, detectorlist, y, X
from combo.models.detector_lscp import LSCP
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)
detectors = [KNN(), LOF(), OCSVM()]
clf = LSCP(base_estimators=detectors)
clf_name = 'LSCP'
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:")
print("\n... Processing", mat_file_name, '...')
mat = sp.io.loadmat(os.path.join('', 'datasets', mat_file))
X = mat['X']
y = mat['y']
# standardize data to be digestible for most algorithms
X = StandardScaler().fit_transform(X)
X, X, y_train, y_test = \
train_test_split(X, y, test_size=0.4, random_state=42)
contamination = y.sum() / len(y)
base_estimators = [
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
LOF(n_neighbors=15, contamination=contamination),
LOF(n_neighbors=25, contamination=contamination),
LOF(n_neighbors=35, contamination=contamination),
LOF(n_neighbors=45, contamination=contamination),
LOF(n_neighbors=5, contamination=contamination),
def compare(inputdata, labels, n_clusters, dset_name):
"""
Compute the AUC, Fgap, Frank score on all conventional outlier detectors for the given dataset
Args:
inputdata: input data
labels: ground truth outlier labels
n_clusters: number of clusters, for some cluster-based detectors
dset_name: dataset
Returns: AUC, Fgap, Frank
"""
print(
"Competing with conventional unsupervised outlier detection algorithms..."
)
random_state = np.random.RandomState(1)
if inputdata.shape[1] < 64:
AEneurons = [16, 8, 8, 16]
VAEneurons = [16, 8, 4], [4, 8, 16]
else:
AEneurons = [64, 32, 32, 64]
VAEneurons = [128, 64, 32], [32, 64, 128]
classifiers = {
'PCA':
PCA(random_state=random_state),
'AutoEncoder':
AutoEncoder(batch_size=100,
hidden_neurons=AEneurons,
random_state=random_state),
'VAE':
VAE(batch_size=100,
encoder_neurons=VAEneurons[0],
decoder_neurons=VAEneurons[1],
random_state=random_state),
'COPOD':
COPOD(),
'Iforest':
IForest(random_state=random_state),
'AutoEncoder':
AutoEncoder(batch_size=100, random_state=random_state),
'VAE':
VAE(batch_size=100, random_state=random_state),
'LODA':
LODA(),
'OCSVM':
OCSVM(),
'ABOD':
ABOD(n_neighbors=20),
'Fb':
FeatureBagging(random_state=random_state),
'CBLOF':
CBLOF(n_clusters=n_clusters,
check_estimator=False,
random_state=random_state),
'LOF':
LOF(),
'COF':
COF()
}
for clf_name, clf in classifiers.items():
print(f"Using {clf_name} method")
starttime = time.time()
clf.fit(inputdata)
time_taken = time.time() - starttime
test_scores = clf.decision_scores_
# -----fix some broken scores----- #
for i in range(len(test_scores)):
cur = test_scores[i]
if np.isnan(cur) or not np.isfinite(cur):
test_scores[i] = 0
np.save(f'{dset_name}/{clf_name}_raw.npy', test_scores)
auc = roc_auc_score(labels, test_scores)
print('AUC:', auc)
fetch(normalize(test_scores), f'../datasets/{dset_name.upper()}_Y.npy',
f'{dset_name}/attribute.npy')
print('time_taken:', time_taken)
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 SUOD
clf_name = 'SUOD'
# initialized a group of outlier detectors for acceleration
detector_list = [
LOF(n_neighbors=15),
LOF(n_neighbors=20),
LOF(n_neighbors=25),
LOF(n_neighbors=35),
COPOD(),
IForest(n_estimators=100),
IForest(n_estimators=200)
]
# decide the number of parallel process, and the combination method
clf = SUOD(base_estimators=detector_list,
n_jobs=2,
combination='average',
verbose=False)
# or to use the default detectors
mat = sp.io.loadmat(os.path.join('../datasets', mat_file))
X = mat['X']
y = mat['y'].ravel()
outliers_fraction = np.sum(y) / len(y)
X = StandardScaler().fit_transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
classifiers = {
'Angle-based Outlier Detector (ABOD)':
ABOD(n_neighbors=10, contamination=outliers_fraction),
'Cluster-based Local Outlier Factor (CBLOF)':
CBLOF(contamination=outliers_fraction, check_estimator=False),
'Feature Bagging':
FeatureBagging(LOF(), contamination=outliers_fraction),
'Histogram-base Outlier Detection (HBOS)':
HBOS(contamination=outliers_fraction),
'Isolation Forest':
IForest(contamination=outliers_fraction),
'K Nearest Neighbors (KNN)':
KNN(contamination=outliers_fraction),
'Average KNN':
KNN(method='mean', contamination=outliers_fraction),
'Local Outlier Factor (LOF)':
LOF(contamination=outliers_fraction),
'Minimum Covariance Determinant (MCD)':
MCD(contamination=outliers_fraction),
'One-class SVM (OCSVM)':
OCSVM(contamination=outliers_fraction),
'Principal Component Analysis (PCA)':
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.4,random_state=random_state)
x_train_norm, x_test_norm = standardizer(x_train, x_test)
classifiers = {'Angle-based Outlier Detector (ABOD)': ABOD(
contamination=outliers_fraction),
'Cluster-based Local Outlier Factor': CBLOF(
contamination=outliers_fraction, check_estimator=False,
random_state=random_state),
'Feature Bagging': FeatureBagging(contamination=outliers_fraction,
random_state=random_state),
'Histogram-base Outlier Detection (HBOS)': HBOS(
contamination=outliers_fraction),
'Isolation Forest': IForest(contamination=outliers_fraction,
random_state=random_state),
'K Nearest Neighbors (KNN)': KNN(contamination=outliers_fraction),
'Local Outlier Factor (LOF)': LOF(
contamination=outliers_fraction),
'Minimum Covariance Determinant (MCD)': MCD(
contamination=outliers_fraction, random_state=random_state),
'One-class SVM (OCSVM)': OCSVM(contamination=outliers_fraction),
'Principal Component Analysis (PCA)': PCA(
contamination=outliers_fraction, random_state=random_state),
}
for clf_name, clf in classifiers.items():
try:
t0 = time()
clf.fit(x_train_norm)
test_scores = clf.decision_function(x_test_norm)
t1 = time()
duration = round(t1 - t0, ndigits=4)
roc = round(roc_auc_score(y_test, test_scores), ndigits=4)
# detector_list, contamination=outliers_fraction,
# random_state=random_state)
#}
#%%
file_no, plotp = 3, 0
anomalies = anomalies_3
data = preprocess(data_3, plotp)
start_date = data.head(1).index.date[0]
end_date = data.tail(1).index.date[0]
middle_date = start_date + (end_date - start_date) / 2
datatotrain, datatotest, datatotrain_normalized, datatotest_normalized, dataanomaly_normalized, train_data, test_data, mix_data = createtraintest(
data, anomalies, file_no)
X_train, X_test, X_outliers = datatotrain_normalized, datatotest_normalized, dataanomaly_normalized
#%%
clf = LOF(n_neighbors=10, contamination=0.1)
clf.fit(X_train)
#%%
#y_pred = clf.fit_predict(X_test)
i = 0
for dt in rrule(DAILY, dtstart=start_date, until=end_date):
try:
if (data.loc[dt.strftime("%Y-%m-%d")]['value']).values.size != 0:
data.loc[dt.strftime("%Y-%m-%d"), 'ocsvm_score'] = clf.predict(
preprocessing.normalize(
data.loc[dt.strftime("%Y-%m-%d")].value.values.reshape(
1, -1)))
i = i + 1
except:
print(dt, i)
continue
encodings_train = np.concatenate(encodings_train, 0) print(encodings_train.shape) # train the KNN detector from pyod.models.knn import KNN 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)
class TestLOF(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 = LOF(contamination=self.contamination)
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, 'n_neighbors_')
and self.clf.n_neighbors_ 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)
print(pred_ranks)
print(pred_ranks)
# 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
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 LOF detector
clf_name = 'LOF'
clf = LOF()
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)
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,
contamination=contamination,
random_state=42)
X_train, X_test = standardizer(X_train, X_test)
# train lscp
clf_name = 'LSCP'
detector_list = [LOF(), LOF()]
clf = LSCP(detector_list, random_state=42)
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:")
# -*- coding: utf-8 -*-
"""
Created on Tue Dec 24 15:51:40 2019
@author: zixing.mei
"""
from pyod.models.lof import LOF
#训练异常检测模型，然后输出训练集样本的异常分
clf = LOF(n_neighbors=20,
algorithm='auto',
leaf_size=30,
metric='minkowski',
p=2,
metric_params=None,
contamination=0.1,
n_jobs=1)
clf.fit(x)
#异常分
out_pred = clf.predict_proba(x, method='linear')[:, 1]
train['out_pred'] = out_pred
#异常分在0.9百分位以下的样本删掉
key = train['out_pred'].quantile(0.9)
x = train[train.out_pred < key][feature_lst]
y = train[train.out_pred < key]['bad_ind']
val_x = val[feature_lst]
#df = pd.DataFrame(datax) # ##scatter_matrix(df, alpha=0.2, diagonal='kde') #from pandas.tools.plotting import lag_plot #lag_plot(data.value) #%% #clf = LOF(n_neighbors=10, contamination=0.1) #clf.fit(data_n) #clf1 = LOF(n_neighbors=10, contamination=0.1) #clf1.fit(data_n[:,0:48]) #clf2 = LOF(n_neighbors=10, contamination=0.1) #clf2.fit(data_n[:,48:96]) #clf3 = LOF(n_neighbors=10, contamination=0.1) #clf3.fit(data_n[:,96:144]) #%% clf = LOF(n_neighbors=10, contamination=0.1) clf.fit(X_train) clf1 = LOF(n_neighbors=10, contamination=0.1) clf1.fit(X_train[:, 0:48]) clf2 = LOF(n_neighbors=10, contamination=0.1) clf2.fit(X_train[:, 48:96]) clf3 = LOF(n_neighbors=10, contamination=0.1) clf3.fit(X_train[:, 96:144]) #%% clf = HBOS(contamination=outliers_fraction) clf.fit(X_train) clf1 = HBOS(contamination=outliers_fraction) clf1.fit(X_train[:, 0:48]) clf2 = HBOS(contamination=outliers_fraction) clf2.fit(X_train[:, 48:96])
