def main():
scalers = ['no', 'std', 'minmax']
root = 'Unsupervised_Anamaly_Detection_csv'
start = 0
counts = 90
CPUS = 3
CPUS_Models = 4
sklearn_models = [
'AvgKNN', 'LargestKNN', 'MedKNN', 'PCA', 'COF', 'LODA', 'LOF', 'HBOS',
'MCD', 'AvgBagging', 'MaxBagging', 'IForest', 'CBLOF', 'COPOD', 'SOD',
'LSCPwithLODA', 'AveLMDD', 'VarLMDD', 'IqrLMDD', 'SoGaal', 'MoGaal',
'VAE', 'AutoEncoder'
]
models = {
'BRM': BRM(bootstrap_sample_percent=70),
'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'),
'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(),
'MoGaal': MO_GAAL(),
'VAE': VAE(encoder_neurons=[8, 4, 2]),
'AutoEncoder': AutoEncoder(hidden_neurons=[6, 3, 3, 6]),
'OCKRA': m_OCKRA(),
}
name = "30_Models"
Parallel(n_jobs=CPUS) \
(delayed(runByScaler)
(root, scaler, models, start, counts,
other_models=sklearn_models,
CPUS=CPUS_Models,
save_name=name)
for scaler in scalers)
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 = LMDD(contamination=self.contamination, random_state=42)
self.clf.fit(self.X_train)
def test_check_parameters(self):
with assert_raises(ValueError):
LMDD(contamination=10.)
with assert_raises(ValueError):
LMDD(dis_measure='unknown')
with assert_raises(TypeError):
LMDD(dis_measure=5)
with assert_raises(TypeError):
LMDD(n_iter='not int')
with assert_raises(ValueError):
LMDD(n_iter=-1)
with assert_raises(ValueError):
LMDD(random_state='not valid')
with assert_raises(ValueError):
LMDD(random_state=-1)
class TestCOF(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 = LMDD(contamination=self.contamination, random_state=42)
self.clf.fit(self.X_train)
def test_sklearn_estimator(self):
# check_estimator(self.clf)
pass
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, 'dis_measure_')
and self.clf.dis_measure_ is not None)
assert (hasattr(self.clf, 'n_iter_') and self.clf.n_iter_ is not None)
assert (hasattr(self.clf, 'random_state_')
and self.clf.random_state_ 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_check_parameters(self):
with assert_raises(ValueError):
LMDD(contamination=10.)
with assert_raises(ValueError):
LMDD(dis_measure='unknown')
with assert_raises(TypeError):
LMDD(dis_measure=5)
with assert_raises(TypeError):
LMDD(n_iter='not int')
with assert_raises(ValueError):
LMDD(n_iter=-1)
with assert_raises(ValueError):
LMDD(random_state='not valid')
with assert_raises(ValueError):
LMDD(random_state=-1)
def test_model_clone(self):
clone_clf = clone(self.clf)
def tearDown(self):
pass
def main():
# PART 1:
# Getting the predictions for each classifier
# SK means: The classifier is from sklearn or works like sklearn
# PY means: The classifier is from pyod or works like pyod
models = {
'SK_EE': EllipticEnvelope(),
'SK_GM': GaussianMixture(),
'SK_IF': IsolationForest(),
'SK_OCSVM': OneClassSVM(),
'SK_FA': FactorAnalysis(),
'SK_KD': KernelDensity(),
'PY_PCA': PCA(),
'PY_COF': COF(),
'PY_LODA': LODA(),
'PY_LOF': LOF(),
'PY_HBOS': HBOS(),
'PY_MCD': MCD(),
'PY_AvgKNN': KNN(method='mean'),
'PY_LargestKNN': KNN(method='largest'),
'PY_MedKNN': KNN(method='median'),
'PY_AvgBagging': FeatureBagging(combination='average'),
'PY_MaxBagging': FeatureBagging(combination='max'),
'PY_CBLOF': CBLOF(n_clusters=10, n_jobs=4),
'PY_COPOD': COPOD(),
'PY_SOD': SOD(),
'PY_LSCPwithLODA': LSCP([LODA(), LODA()]),
'PY_AveLMDD': LMDD(dis_measure='aad'),
'PY_VarLMDD': LMDD(dis_measure='var'),
'PY_IqrLMDD': LMDD(dis_measure='iqr'),
'PY_VAE': VAE(encoder_neurons=[8, 4, 2]),
'PY_AutoEncoder': AutoEncoder(hidden_neurons=[6, 3, 3, 6]),
'SK_BRM': BRM(bootstrap_sample_percent=70),
'SK_OCKRA': m_OCKRA(),
'PY_SoGaal': SO_GAAL(),
'PY_MoGaal': MO_GAAL()
}
ranker = ADRanker(data="datasets", models=models)
ranker.get_predictions()
# PART 2:
# After predictions, we can evaluate our classifiers using different scores
# You can add manually a new metric by modifying 'metrics.py'
ranker.get_scores(scores={'auc': Metrics.get_roc, 'ave': Metrics.get_ave})
# PART 3:
# Finally, it is time to summarize the results by plotting different graphs
# You can add your own graphs by modifying ' plots.py'
plot = Plots()
plot.make_plot_basic(paths=[
'results/scores/auc/no/results.csv',
'results/scores/auc/minmax/results.csv',
'results/scores/auc/std/results.csv',
'results/scores/ave/no/results.csv',
'results/scores/ave/minmax/results.csv',
'results/scores/ave/std/results.csv'
],
scalers=[
'Without scaler', 'Min max scaler',
'Standard scaler', 'Without scaler',
'Min max scaler', 'Standard scaler'
])
plot.make_cd_plot(
paths=[
'results/scores/auc/minmax/results.csv',
'results/scores/ave/no/results.csv',
'results/scores/auc/no/results.csv',
'results/scores/ave/no/results.csv',
'results/scores/auc/std/results.csv',
'results/scores/ave/std/results.csv'
],
names=[
'CD auc minmax scale', 'CD ave minmax scale', 'CD auc no scale',
'CD ave no scale', 'CD auc std scale', 'CD ave std scale'
],
titles=[
'CD diagram - AUC with min max scaling',
'CD diagram - Average precision with min max scaling',
'CD diagram - AUC without scaling',
'CD diagram - Average precision without scaling',
'CD diagram - AUC with standard scaling',
'CD diagram - Average precision with standard scaling'
])
lr_d=0.01,
lr_g=0.0001,
decay=1e-06,
momentum=0.9,
contamination=0.1), 'MO_GAAL'),
# SO_GAAL pyod
(SO_GAAL(stop_epochs=20,
lr_d=0.01,
lr_g=0.0001,
decay=1e-06,
momentum=0.9,
contamination=0.1), 'SO_GAAL'),
# OCKRA github
(m_ockra.m_OCKRA(), 'OCKRA'),
# VAR LMDD pyOD
(LMDD(dis_measure='var', random_state=rs), 'VAR_LMDD'),
# LOCI pyod
(LSCP(detector_list,
local_region_size=30,
local_max_features=1.0,
n_bins=10,
random_state=None,
contamination=0.1), 'LSCP')
]
# Select the model location with i to run
i = 8
had_error = []
# Initialize the class anomaly
#for i in range(1,8):
# try:
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 LMDD detector
clf_name = 'LMDD'
clf = LMDD(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:")
evaluate_print(clf_name, y_test, y_test_scores)
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
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
'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(),
#'MoGaal':MO_GAAL(),
'VAE': VAE(encoder_neurons=[8, 4, 2]),
'AutoEncoder': AutoEncoder(hidden_neurons=[6, 3, 3, 6])
}
models = {
'XGBOD': XGBOD(),
'BRM': BRM(),
'GM': GaussianMixture(),
'IF': IsolationForest(),
'OCSVM': OneClassSVM(),
'EE': EllipticEnvelope(),
def outlier_detection(df):
testing_df = df[(df['Chassis_Number'] == 'WBA1C11080J829552')]
# testing_df = df[(df['Chassis_Number'] == 'VF3LCYHZPJS332137')]
clf = LOF(
n_neighbors=10,
contamination=0.1
)
data_reshaped = np.array(testing_df['Kms'].values).reshape(-1, 1)
data_reshaped = np.round(data_reshaped, 0)
clf.fit(data_reshaped)
y_pred = clf.predict(np.array(data_reshaped).reshape(-1, 1))
# y_pred[y_pred < 0] = 0.0
testing_df['outlier_score_lof'] = y_pred
clf = LMDD(
n_iter=100,
contamination=0.1
)
data_reshaped = np.array(testing_df['Kms'].values).reshape(-1, 1)
data_reshaped = np.round(data_reshaped, 0)
clf.fit(data_reshaped)
y_pred = clf.predict(np.array(data_reshaped).reshape(-1, 1))
# y_pred[y_pred < 0] = 0.0
testing_df['outlier_score_lmdd'] = y_pred
clf = IsolationForest(
n_estimators=100,
contamination=0.1
)
data_reshaped = np.array(testing_df['Kms'].values).reshape(-1, 1)
data_reshaped = np.round(data_reshaped, 0)
clf.fit(data_reshaped)
y_pred = clf.predict(np.array(data_reshaped).reshape(-1, 1))
# y_pred[y_pred < 0] = 0.0
testing_df['outlier_score_isolation_forest'] = y_pred
clf = KNN(
method='mean',
n_neighbors=3,
contamination=0.1
)
data_reshaped = np.array(testing_df['Kms'].values).reshape(-1, 1)
data_reshaped = np.round(data_reshaped, 0)
clf.fit(data_reshaped)
y_pred = clf.predict(np.array(data_reshaped).reshape(-1, 1))
# y_pred[y_pred < 0] = 0.0
testing_df['outlier_score_knn_mean'] = y_pred
clf = KNN(
method='median',
n_neighbors=3,
contamination=0.1
)
data_reshaped = np.array(testing_df['Kms'].values).reshape(-1, 1)
data_reshaped = np.round(data_reshaped, 0)
clf.fit(data_reshaped)
y_pred = clf.predict(np.array(data_reshaped).reshape(-1, 1))
# y_pred[y_pred < 0] = 0.0
testing_df['outlier_score_knn_median'] = y_pred
print(testing_df[['Movement_Date', 'Kms', 'Kms_diff', 'outlier_score_lof', 'outlier_score_lmdd', 'outlier_score_isolation_forest', 'outlier_score_knn_mean', 'outlier_score_knn_median']])
return
df.to_csv(self.model_name + '_results.csv', index=False)
print('\nFinished ' + self.model_name)
return None
if __name__ == '__main__':
# Specify the root directory
rootDir = 'G:/My Drive/Github/ml-group-col/One-Class-models/Anomaly_Datasets_csv/'
# specify the random state
rs = 10
# Save how to run the models
models = [
(IsolationForest(random_state=rs), 'ISOF'),
(EllipticEnvelope(random_state=rs), 'EE'),
(LMDD(dis_measure='aad', random_state=rs), 'AAD_LMDD'),
(COPOD(), 'COPOD'),
(FeatureBagging(combination='average',
random_state=rs), 'AVE_Bagging'), # n_jobs
(LMDD(dis_measure='iqr', random_state=rs), 'IQR_LMDD'),
(KNN(method='largest'), 'Largest_KNN'), # n_jobs
(LODA(), 'LODA'),
(FeatureBagging(combination='max', n_jobs=-1,
random_state=rs), 'MAX_Bagging'),
(MCD(random_state=rs), 'MCD'),
(XGBOD(random_state=rs), 'XGBOD'), # n_jobs
(GaussianMixture(random_state=rs), 'GMM'),
(LocalOutlierFactor(novelty=True), 'LOF'),
(KNN(method='median'), 'Median_KNN'), # n_jobs
(KNN(method='mean'), 'Avg_KNN'), # n_jobs
(CBLOF(n_clusters=10, random_state=rs), 'CBLOF'),