def transform(self, x):
if len(x) == 0:
return x
if len(self.X) < self.MIN_HISTORY_SIZE:
p_arr = [0.5 for i in range(len(x))]
else:
p_arr = [pvalue(x[i], self.X[:, i]) for i in range(len(x))]
self.P = np.vstack([self.P, p_arr])
self.X = np.vstack([self.X, x])
z = []
for i in range(len(x)):
z += self.aggregate(i)
return z
def transform_pvalue(self, x, aggregate=True):
if len(self.X) < self.MIN_HISTORY_SIZE:
p_arr = [0.5 for _ in range(len(x))]
else:
p_arr = [pvalue(x[i], self.X[:, i]) for i in range(len(x))]
self.P = np.vstack([self.P, p_arr])
self.X = np.vstack([self.X, x])
z = []
for i in range(len(x)):
pvalues = self.P[-self.w:, i]
if aggregate:
z += [1. - np.mean(pvalues)] if len(pvalues) >= 1 else [0.5]
else:
z += [1. - pvalues[-1]] if len(pvalues) >= 1 else [0.5]
return z
def predict(self, dtime, x, external=None):
'''Update the deviation level based on the new test sample x
Parameters:
-----------
dtime : datetime
datetime corresponding to the sample x
x : array-like, shape (n_features,)
Sample for which the strangeness, p-value and deviation level are computed
external: float (default None)
Used in case self.ref_group == "external" to construct the reference dataset from historical data
Returns:
--------
strangeness : float
Strangeness of x with respect to samples in Xref
pval : float, in [0, 1]
p-value that represents the proportion of samples in Xref that are stranger than x.
deviation : float, in [0, 1]
Normalized deviation level updated based on the last w_martingale steps
'''
self.T.append(dtime)
self._fit(dtime, x, external)
strangeness = self.strg.get(x)
self.S.append(strangeness)
pval = pvalue(strangeness, self.scores)
self.P.append(pval)
deviation = self._update_martingale(pval)
self.M.append(deviation)
is_deviating = deviation > self.dev_threshold
return DeviationContext(strangeness, pval, deviation, is_deviating)
def test_pvalue_special(self):
self.assertEqual(pvalue(0, [1, 2, 7, 9, 11]), 1)
self.assertEqual(pvalue(20, [1, 2, 7, 9, 11]), 0)
def test_pvalue_general(self):
self.assertEqual(pvalue(4, [1, 2, 7, 9, 11]), 3 / 5)
def test_pvalue_empty(self):
with self.assertRaises(InputValidationError):
pvalue(4, [])
