def test_invert_order(self):
target = np.array([-0.1, -0.3, -0.5, -0.7, -0.2, -0.1]).ravel()
scores1 = invert_order(self.scores1)
assert_allclose(scores1, target)
scores2 = invert_order(self.scores2)
assert_allclose(scores2, target)
target = np.array([0.6, 0.4, 0.2, 0, 0.5, 0.6]).ravel()
scores2 = invert_order(self.scores2, method='subtraction')
assert_allclose(scores2, target)
def fit(self, X, y=None):
"""Fit detector. y is ignored in unsupervised methods.
Parameters
----------
X : numpy array of shape (n_samples, n_features)
The input samples.
y : Ignored
Not used, present for API consistency by convention.
sample_weight : array-like, shape (n_samples,)
Per-sample weights. Rescale C per sample. Higher weights
force the classifier to put more emphasis on these points.
Returns
-------
self : object
Fitted estimator.
"""
# validate inputs X and y (optional)
X = check_array(X)
self._set_n_classes(y)
self.detector_ = GaussianMixture(
n_components=self.n_components,
covariance_type=self.covariance_type,
tol=self.tol,
reg_covar=self.reg_covar,
max_iter=self.max_iter,
n_init=self.n_init,
init_params=self.init_params,
weights_init=self.weights_init,
means_init=self.means_init,
precisions_init=self.precisions_init,
random_state=self.random_state,
warm_start=self.warm_start,
)
self.detector_.fit(X=X, y=y)
# invert decision_scores_. Outliers comes with higher outlier scores
self.decision_scores_ = invert_order(self.detector_.score_samples(X))
self._process_decision_scores()
return self
def decision_function(self, X):
"""Predict raw anomaly score of X using the fitted detector.
The anomaly score of an input sample is computed based on different
detector algorithms. For consistency, outliers are assigned with
larger anomaly scores.
Parameters
----------
X : numpy array of shape (n_samples, n_features)
The training input samples. Sparse matrices are accepted only
if they are supported by the base estimator.
Returns
-------
anomaly_scores : numpy array of shape (n_samples,)
The anomaly score of the input samples.
"""
check_is_fitted(self, ["decision_scores_", "threshold_", "labels_"])
# Invert outlier scores. Outliers come with higher outlier scores
return invert_order(self.detector_.score_samples(X))