def __init__(self, estimator_list, n_iterations=20, local_region_size=30, local_max_features=1.0, n_bins=10,
random_state=42, contamination=0.1):
super(LSCP, self).__init__(contamination=contamination)
self.estimator_list = estimator_list
self.n_clf = len(self.estimator_list)
self.n_iterations = n_iterations
self.local_region_size = local_region_size
self.local_region_min = 30
self.local_region_max = 100
self.local_max_features = local_max_features
self.local_min_features = 0.5
self.local_region_iterations = 20
self.local_region_threshold = int(self.local_region_iterations / 2)
self.n_bins = n_bins
self.n_selected = 1
self.random_state = random_state
assert len(estimator_list) > 1, "The estimator list has less than 2 estimators."
if self.n_bins >= self.n_clf:
warnings.warn("Number of histogram bins greater than number of classifiers, reducing n_bins to n_clf.")
self.n_bins = self.n_clf
for estimator in self.estimator_list:
check_detector(estimator)
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.
Returns
-------
self : object
Fitted estimator.
"""
# check detector_list
if len(self.detector_list) < 2:
raise ValueError("The detector list has less than 2 detectors.")
for detector in self.detector_list:
check_detector(detector)
# check random state and input
self.random_state = check_random_state(self.random_state)
X = check_array(X)
self._set_n_classes(y)
self.n_features_ = X.shape[1]
# normalize input data
self.X_train_norm_ = X
train_scores = np.zeros([self.X_train_norm_.shape[0], self.n_clf])
# fit each base detector and calculate standardized train scores
for k, detector in enumerate(self.detector_list):
detector.fit(self.X_train_norm_)
train_scores[:, k] = detector.decision_scores_
self.train_scores_ = train_scores
# set decision scores and threshold
self.decision_scores_ = self._get_decision_scores(X)
self._process_decision_scores()
return self
def fit(self, X, y=None):
""" Fit LSCP using X as training data
Parameters
----------
X : numpy array, shape (n_samples, n_features)
Training data
y : None, optional (default=None)
Labels not necessary for unsupervised method
Returns
-------
None
"""
# check detector_list
if len(self.detector_list) < 2:
raise ValueError("The detector list has less than 2 detectors.")
for detector in self.detector_list:
check_detector(detector)
# check random state and input
self.random_state = check_random_state(self.random_state)
X = check_array(X)
self._set_n_classes(y)
self.n_features_ = X.shape[1]
# normalize input data
self.X_train_norm_ = X
train_scores = np.zeros([self.X_train_norm_.shape[0], self.n_clf])
# fit each base detector and calculate standardized train scores
for k, detector in enumerate(self.detector_list):
detector.fit(self.X_train_norm_)
train_scores[:, k] = detector.decision_scores_
self.train_scores_ = train_scores
# set decision scores and threshold
self.decision_scores_ = self._get_decision_scores(X)
self._process_decision_scores()
return
def fit(self, X, y=None):
"""Fit detector. y is optional for unsupervised methods.
Parameters
----------
X : numpy array of shape (n_samples, n_features)
The input samples.
y : numpy array of shape (n_samples,), optional (default=None)
The ground truth of the input samples (labels).
"""
# check detector_list
if len(self.detector_list) < 2:
raise ValueError("The detector list has less than 2 detectors.")
for detector in self.detector_list:
check_detector(detector)
# check random state and input
self.random_state = check_random_state(self.random_state)
X = check_array(X)
self._set_n_classes(y)
self.n_features_ = X.shape[1]
# normalize input data
self.X_train_norm_ = X
train_scores = np.zeros([self.X_train_norm_.shape[0], self.n_clf])
# fit each base detector and calculate standardized train scores
for k, detector in enumerate(self.detector_list):
detector.fit(self.X_train_norm_)
train_scores[:, k] = detector.decision_scores_
self.train_scores_ = train_scores
# set decision scores and threshold
self.decision_scores_ = self._get_decision_scores(X)
self._process_decision_scores()
return self
def test_check_detector_negative(self):
with assert_raises(AttributeError):
check_detector(self.detector_negative)
def test_check_detector_positive(self):
check_detector(self.detector_positive)
