def test__detect_anoms_no_num_obs_per_period(self):
with self.assertRaises(AssertionError):
_detect_anoms(self.data1,
k=0.02,
alpha=0.05,
num_obs_per_period=None,
use_decomp=False,
use_esd=False,
direction='both')
def test__detect_anoms(data):
shesd = detts._detect_anoms(data,
k=0.02,
alpha=0.05,
num_obs_per_period=1440,
use_decomp=True,
use_esd=False,
direction='both',
verbose=False)
def test__detect_anoms_use_esd_true(self):
shesd = _detect_anoms(self.data1,
k=0.02,
alpha=0.05,
num_obs_per_period=1440,
use_decomp=True,
use_esd=True,
direction='both')
self.assertEquals(133, len(shesd['anoms']))
def test__detect_anoms_neg(self):
shesd = _detect_anoms(self.data1,
k=0.02,
alpha=0.05,
num_obs_per_period=1440,
use_decomp=True,
use_esd=False,
direction='neg')
self.assertEquals(85, len(shesd['anoms']))
def test__detect_anoms_use_decomp_false(self):
shesd = _detect_anoms(self.data1,
k=0.02,
alpha=0.05,
num_obs_per_period=1440,
use_decomp=False,
use_esd=False,
direction='both',
verbose=False)
self.assertEquals(133, len(shesd['anoms']))
def test__detect_anoms_pos_multithreaded(self):
shesd = _detect_anoms(self.data1,
k=0.02,
alpha=0.05,
num_obs_per_period=1440,
use_decomp=True,
use_esd=False,
direction='pos',
verbose=False,
multithreaded=True)
self.assertEquals(50, len(shesd['anoms']))
def anomaly_detect_vec(x, max_anoms=0.1, direction="pos", alpha=0.05,
period=None, only_last=False, threshold=None, e_value=False,
longterm_period=None, plot=False, y_log=False, xlabel="",
ylabel="count", title="", verbose=False):
assert isinstance(x, pd.Series), 'x must be pandas series'
assert max_anoms < 0.5, 'max_anoms must be < 0.5'
assert direction in ['pos', 'neg', 'both'], 'direction should be one of "pos", "neg", "both"'
assert period, "Period must be set to the number of data points in a single period"
__verbose_if((alpha < 0.01 or alpha > 0.1) and verbose,
"Warning: alpha is the statistical significance, and is usually between 0.01 and 0.1")
max_anoms = 1.0 / x.size if max_anoms < 1.0 / x.size else max_anoms
step = int(np.ceil(x.size / longterm_period)
) if longterm_period else x.size
all_data = [x.iloc[i:i + step] for i in range(0, x.size, step)]
one_tail = True if direction in ['pos', 'neg'] else False
upper_tail = True if direction in ['pos', 'both'] else False
all_anoms = pd.Series()
seasonal_plus_trend = pd.Series()
for ts in all_data:
tmp = _detect_anoms(
ts, k=max_anoms, alpha=alpha, num_obs_per_period=period, use_decomp=True,
use_esd=False, direction=direction, verbose=verbose)
s_h_esd_timestamps = tmp['anoms'].keys()
data_decomp = tmp['stl']
anoms = ts.loc[s_h_esd_timestamps]
if threshold:
end = longterm_period - 1 if longterm_period else x.size - 1
periodic_maxs = [ts.iloc[i: i + period].max()
for i in range(0, end, period)]
if threshold == "med_max":
thresh = periodic_maxs.median()
elif threshold == "p95":
thresh = periodic_maxs.quantile(0.95)
elif threshold == "p99":
thresh = periodic_maxs.quantile(0.99)
anoms = anoms[anoms >= thresh]
all_anoms.append(anoms)
seasonal_plus_trend.append(data_decomp)
all_anoms.drop_duplicates(inplace=True)
seasonal_plus_trend.drop_duplicates(inplace=True)
return anoms
