def test_timestamp_api():
host = '127.0.0.1'
user = '******'
password = '******'
algorithm = ['luminol']
rng = np.random.RandomState(42)
np.random.seed(42)
conn, cursor = connect_server(host, user, password)
ground_truth_whole = insert_demo_data(conn,
cursor,
'db',
't',
ground_truth_flag=True)
data, ground_truth = query_data(conn,
cursor,
'db',
't',
time_serie_name='ts',
ground_truth=ground_truth_whole,
start_time='2019-07-20 00:00:00',
end_time='2019-08-20 00:00:00',
time_serie=True,
ground_truth_flag=True)
for alg in algorithm:
clf = algorithm_selection(alg, random_state=rng, contamination=0.1)
print('Start processing:')
start_time = time.clock()
clf.fit(data)
prediction_result = clf.predict(data)
outlierness = clf.decision_function(data)
output_performance(alg, ground_truth, prediction_result,
time.clock() - start_time, outlierness)
conn.close()
def test_static_api():
host = '127.0.0.1'
user = '******'
password = '******'
algorithm = [
'iforest', 'ocsvm', 'lof', 'robustcovariance', 'cblof', 'knn', 'hbos',
'sod', 'pca', 'dagmm', 'autoencoder', 'lstm_ad', 'lstm_ed',
'staticautoencoder'
]
rng = np.random.RandomState(42)
np.random.seed(42)
conn, cursor = connect_server(host, user, password)
ground_truth_whole = insert_demo_data(conn,
cursor,
'db',
't',
ground_truth_flag=True)
data, ground_truth = query_data(conn,
cursor,
'db',
't',
time_serie_name='ts',
ground_truth=ground_truth_whole,
start_time='2019-07-20 00:00:00',
end_time='2019-08-20 00:00:00',
time_serie=False,
ground_truth_flag=True)
for alg in algorithm:
clf = algorithm_selection(alg, random_state=rng, contamination=0.1)
print('Start processing:')
start_time = time.clock()
clf.fit(data)
prediction_result = clf.predict(data)
outlierness = clf.decision_function(data)
output_performance(alg, ground_truth, prediction_result,
time.clock() - start_time, outlierness)
data, ground_truth = query_data(conn,
cursor,
'db',
't',
time_serie_name='ts',
ground_truth=ground_truth_whole,
start_time=None,
end_time=None,
time_serie=False,
ground_truth_flag=True)
data, ground_truth = query_data(conn,
cursor,
'db',
't',
time_serie_name='ts',
ground_truth=ground_truth_whole,
start_time=None,
end_time=None,
time_serie=False,
ground_truth_flag=False)
conn.close()
def test_io_static():
host = '127.0.0.1'
user = '******'
password = '******'
alg = 'iforest'
rng = np.random.RandomState(42)
np.random.seed(42)
conn, cursor = connect_server(host, user, password)
ground_truth_whole = insert_demo_data(conn,
cursor,
'db',
't',
ground_truth_flag=True)
data, ground_truth = query_data(conn,
cursor,
'db',
't',
time_serie_name='ts',
ground_truth=ground_truth_whole,
start_time='2019-07-20 00:00:00',
end_time='2019-08-20 00:00:00',
time_serie=False,
ground_truth_flag=True)
clf = algorithm_selection(alg, random_state=rng, contamination=0.1)
print('Start processing:')
start_time = time.clock()
clf.fit(data)
prediction_result = clf.predict(data)
outlierness = clf.decision_function(data)
output_performance(alg, ground_truth, prediction_result,
time.clock() - start_time, outlierness)
visualize_distribution_static(data, prediction_result, outlierness)
visualize_distribution(data, prediction_result, outlierness)
visualize_outlierscore(outlierness, prediction_result, contamination=0.1)
data, ground_truth = query_data(conn,
cursor,
'db',
't',
time_serie_name='ts',
ground_truth=ground_truth_whole,
start_time=None,
end_time='2019-08-20 00:00:00',
time_serie=False,
ground_truth_flag=True)
data, ground_truth = query_data(conn,
cursor,
'db',
't',
time_serie_name='ts',
ground_truth=ground_truth_whole,
start_time='2019-07-20 00:00:00',
end_time=None,
time_serie=False,
ground_truth_flag=True)
args.start_time,
args.end_time,
args.time_serie_name,
time_serie=args.time_stamp,
ground_truth_flag=args.ground_truth)
print('Loading cost: %.6f seconds' % (time.clock() - start_time))
print('Load data successful')
#Algorithm Selection
if args.ground_truth:
alg_selector = Cash(data, ground_truth)
clf = alg_selector.model_selector(max_evals=2)
else:
clf = algorithm_selection(args.algorithm,
random_state=rng,
contamination=args.contamination)
start_time = time.clock()
clf.fit(data)
prediction_result = clf.predict(data)
outlierness = clf.decision_function(data)
anomaly_scores = clf.anomaly_likelihood(data)
if args.ground_truth:
output_performance(args.algorithm, ground_truth, prediction_result,
time.clock() - start_time, anomaly_scores)
if args.visualize_distribution and args.ground_truth:
if not args.time_stamp:
visualize_distribution_static(data, prediction_result, outlierness,
])
from IPython.display import display, HTML
#display(df)
return df
training_features = extract_features(training_FileList)
from pyodds.utils.importAlgorithm import algorithm_selection
from pyodds.utils import utilities
from pyodds.utils.plotUtils import visualize_distribution_static, visualize_distribution_time_serie, visualize_outlierscore, visualize_distribution
#import ipdb; ipdb.set_trace()
clf = algorithm_selection('lof', 1, 0.3)
clf.fit(training_features)
#import pandas as pd
print("Extracting test_features")
test_features = []
#import ipdb; ipdb.set_trace()
for filepath in test_FileList:
if os.path.basename(filepath) in file_name_col:
label_index = np.where(
file_name_col == os.path.basename(filepath))[0][0]
gtruth = labels[label_index][1].astype(int)
test_features = extract_features([filepath])
prediction_result = clf.predict(test_features)
outlierness_score = clf.decision_function(test_features)
print(gtruth, prediction_result)
def __init__(self, features):
self.clf = algorithm_selection('lof', 1, 0.3)
self.clf.fit(features)
self.test_features = []
