def test_sr(sr_params):
window_amp, window_local, n_est_points, return_instance_score = sr_params
threshold = 2.5
od = SpectralResidual(threshold=threshold,
window_amp=window_amp,
window_local=window_local,
n_est_points=n_est_points)
assert od.threshold == threshold
assert od.meta == {
'name': 'SpectralResidual',
'detector_type': 'online',
'data_type': 'time-series',
'version': __version__
}
preds_in = od.predict(X, t, return_instance_score=return_instance_score)
assert preds_in['data']['is_outlier'].sum() <= 2.
if return_instance_score:
assert preds_in['data']['is_outlier'].sum() == (
preds_in['data']['instance_score'] >
od.threshold).astype(int).sum()
else:
assert preds_in['data']['instance_score'] is None
preds_out = od.predict(X_pert,
t,
return_instance_score=return_instance_score)
assert preds_out['data']['is_outlier'].sum() > 0
if return_instance_score:
assert preds_out['data']['is_outlier'].sum() == (
preds_out['data']['instance_score'] >
od.threshold).astype(int).sum()
else:
assert preds_out['data']['instance_score'] is None
assert preds_out['meta'] == od.meta
def test_detector(signal, window_amp, window_local, n_est_points,
return_instance_score):
t, X, X_pert = signal["t"], signal['X'], signal['X_pert']
threshold = 6
od = SpectralResidual(threshold=threshold,
window_amp=window_amp,
window_local=window_local,
n_est_points=n_est_points)
assert od.threshold == threshold
assert od.meta == {
'name': 'SpectralResidual',
'detector_type': 'online',
'data_type': 'time-series',
'version': __version__
}
preds_in = od.predict(X, t, return_instance_score=return_instance_score)
assert preds_in['data']['is_outlier'].sum() <= 2.
if return_instance_score:
assert preds_in['data']['is_outlier'].sum() == (
preds_in['data']['instance_score'] >
od.threshold).astype(int).sum()
else:
assert preds_in['data']['instance_score'] is None
preds_out = od.predict(X_pert,
t,
return_instance_score=return_instance_score)
assert preds_out['data']['is_outlier'].sum(
) >= 10 # check if we detect at least the number of perturbed points
if return_instance_score:
assert preds_out['data']['is_outlier'].sum() == (
preds_out['data']['instance_score'] >
od.threshold).astype(int).sum()
else:
assert preds_out['data']['instance_score'] is None
assert preds_out['meta'] == od.meta
def spectral_residual(df):
od = SpectralResidual(
threshold=None, # threshold for outlier score
window_amp=20, # window for the average log amplitude
window_local=20, # window for the average saliency map
n_est_points=
20 # nb of estimated points padded to the end of the sequence
)
X_outlier = np.array(df['value'])
time_samples = np.arange(0, len(df))
od.infer_threshold(X_outlier, time_samples, threshold_perc=99)
od_preds = od.predict(X_outlier, time_samples, return_instance_score=True)
pred = (od_preds['data']['is_outlier'] == 1)
a = df.loc[pred]
return a
def find_anoms(hosts, df):
start = time.time()
kpis = dict(tuple(df.groupby(['cmdb_id', 'name'])))
res = {}
anoms = []
df_info = pd.read_csv('kpi_summary_info.data')
df_thresh = pd.read_csv('thresh_99_999.data')
for key in kpis:
kpis[key]['timestamp'] = kpis[key]['timestamp'].apply(
lambda x: datetime.fromtimestamp(x / 1000.0))
kpis[key] = kpis[key].set_index('timestamp').sort_index()
per1_kpis = df_info[(df_info.interval == '1min')
& (df_info.is_flat == False)]['kpi'].unique()
per5_kpis = df_info[(df_info.interval == '5min')
& ((df_info.is_flat == False))]['kpi'].unique()
print('Calculating rolling window')
for key in kpis:
if key[0] in hosts:
if kpis[key]['value'].std() == 0:
continue
elif key[1] in per1_kpis:
d = kpis[key]['value'].resample('T').mean().interpolate()
elif key[1] in per5_kpis:
d = kpis[key]['value'].resample('5T').mean().interpolate()
else:
continue
d = (d - d.mean()) / d.std()
res[key] = d.rolling(10).mean()
for key in res:
print('Determining threshold for', key)
if len(df_thresh[(df_thresh.host == key[0])
& (df_thresh.name == key[1])]) == 0:
print('Anomaly, std in train was 0, now its not')
anoms.append((key[1], key[0]))
continue
thresh = df_thresh[(df_thresh.host == key[0])
& (df_thresh.name == key[1])]['thresh'].values[0]
if np.isnan(thresh):
print(
"SR didn't generate threshhold because of low std for window > 10, skipping"
)
continue
d = res[key].dropna()
od = SpectralResidual(threshold=thresh,
window_amp=10,
window_local=10,
n_est_points=5,
n_grad_points=5)
if len(d) < 10:
print('Rolling window data empty! Skipping')
continue
outliers = od.predict(d.values)['data']
if np.sum(np.sum(outliers['is_outlier'][-5:-2])) > 0:
print(outliers['is_outlier'])
print("ST Threshold Anomaly!")
anoms.append((key[1], key[0]))
print("It took",
time.time() - start, "seconds to find", len(anoms), "anomalies")
return anoms
