# -*- coding: utf-8 -*-
"""Local Outlier Factor (LOF). Implemented on scikit-learn library.
"""
# Author: Yue Zhao <zhaoy@cmu.edu>
# License: BSD 2 clause
from __future__ import division
from __future__ import print_function
from sklearn.neighbors import LocalOutlierFactor
from sklearn.utils.validation import check_array
from sklearn.utils.validation import check_is_fitted
from .base import BaseDetector
from ..utils.utility import invert_order
# noinspection PyProtectedMember
[docs]
class LOF(BaseDetector):
"""Wrapper of scikit-learn LOF Class with more functionalities.
Unsupervised Outlier Detection using Local Outlier Factor (LOF).
The anomaly score of each sample is called Local Outlier Factor.
It measures the local deviation of density of a given sample with
respect to its neighbors.
It is local in that the anomaly score depends on how isolated the object
is with respect to the surrounding neighborhood.
More precisely, locality is given by k-nearest neighbors, whose distance
is used to estimate the local density.
By comparing the local density of a sample to the local densities of
its neighbors, one can identify samples that have a substantially lower
density than their neighbors. These are considered outliers.
See :cite:`breunig2000lof` for details.
Parameters
----------
n_neighbors : int, optional (default=20)
Number of neighbors to use by default for `kneighbors` queries.
If n_neighbors is larger than the number of samples provided,
all samples will be used.
algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, optional
Algorithm used to compute the nearest neighbors:
- 'ball_tree' will use BallTree
- 'kd_tree' will use KDTree
- 'brute' will use a brute-force search.
- 'auto' will attempt to decide the most appropriate algorithm
based on the values passed to :meth:`fit` method.
Note: fitting on sparse input will override the setting of
this parameter, using brute force.
leaf_size : int, optional (default=30)
Leaf size passed to `BallTree` or `KDTree`. This can
affect the speed of the construction and query, as well as the memory
required to store the tree. The optimal value depends on the
nature of the problem.
metric : string or callable, default 'minkowski'
metric used for the distance computation. Any metric from scikit-learn
or scipy.spatial.distance can be used.
If 'precomputed', the training input X is expected to be a distance
matrix.
If metric is a callable function, it is called on each
pair of instances (rows) and the resulting value recorded. The callable
should take two arrays as input and return one value indicating the
distance between them. This works for Scipy's metrics, but is less
efficient than passing the metric name as a string.
Valid values for metric are:
- from scikit-learn: ['cityblock', 'cosine', 'euclidean', 'l1', 'l2',
'manhattan']
- from scipy.spatial.distance: ['braycurtis', 'canberra', 'chebyshev',
'correlation', 'dice', 'hamming', 'jaccard', 'kulsinski',
'mahalanobis', 'matching', 'minkowski', 'rogerstanimoto',
'russellrao', 'seuclidean', 'sokalmichener', 'sokalsneath',
'sqeuclidean', 'yule']
See the documentation for scipy.spatial.distance for details on these
metrics:
http://docs.scipy.org/doc/scipy/reference/spatial.distance.html
p : integer, optional (default = 2)
Parameter for the Minkowski metric from
sklearn.metrics.pairwise.pairwise_distances. When p = 1, this is
equivalent to using manhattan_distance (l1), and euclidean_distance
(l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used.
See http://scikit-learn.org/stable/modules/generated/sklearn.metrics.pairwise.pairwise_distances
metric_params : dict, optional (default = None)
Additional keyword arguments for the metric function.
contamination : float in (0., 0.5), optional (default=0.1)
The amount of contamination of the data set, i.e. the proportion
of outliers in the data set. When fitting this is used to define the
threshold on the decision function.
n_jobs : int, optional (default = 1)
The number of parallel jobs to run for neighbors search.
If ``-1``, then the number of jobs is set to the number of CPU cores.
Affects only kneighbors and kneighbors_graph methods.
novelty : bool (default=False)
By default, LocalOutlierFactor is only meant to be used for outlier
detection (novelty=False). Set novelty to True if you want to use
LocalOutlierFactor for novelty detection. In this case be aware that
that you should only use predict, decision_function and score_samples
on new unseen data and not on the training set.
Attributes
----------
n_neighbors_ : int
The actual number of neighbors used for `kneighbors` queries.
decision_scores_ : numpy array of shape (n_samples,)
The outlier scores of the training data.
The higher, the more abnormal. Outliers tend to have higher
scores. This value is available once the detector is
fitted.
threshold_ : float
The threshold is based on ``contamination``. It is the
``n_samples * contamination`` most abnormal samples in
``decision_scores_``. The threshold is calculated for generating
binary outlier labels.
labels_ : int, either 0 or 1
The binary labels of the training data. 0 stands for inliers
and 1 for outliers/anomalies. It is generated by applying
``threshold_`` on ``decision_scores_``.
"""
def __init__(self, n_neighbors=20, algorithm='auto', leaf_size=30,
metric='minkowski', p=2, metric_params=None,
contamination=0.1, n_jobs=1, novelty=True):
super(LOF, self).__init__(contamination=contamination)
self.n_neighbors = n_neighbors
self.algorithm = algorithm
self.leaf_size = leaf_size
self.metric = metric
self.p = p
self.metric_params = metric_params
self.n_jobs = n_jobs
self.novelty = novelty
# noinspection PyIncorrectDocstring
[docs]
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.
"""
# validate inputs X and y (optional)
X = check_array(X)
self._set_n_classes(y)
self.detector_ = LocalOutlierFactor(n_neighbors=self.n_neighbors,
algorithm=self.algorithm,
leaf_size=self.leaf_size,
metric=self.metric,
p=self.p,
metric_params=self.metric_params,
contamination=self.contamination,
n_jobs=self.n_jobs,
novelty=self.novelty)
self.detector_.fit(X=X, y=y)
# Invert decision_scores_. Outliers comes with higher outlier scores
self.decision_scores_ = invert_order(
self.detector_.negative_outlier_factor_)
self._process_decision_scores()
return self
[docs]
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 comes with higher outlier scores
# noinspection PyProtectedMember
try:
return invert_order(self.detector_._score_samples(X))
except AttributeError:
try:
return invert_order(self.detector_._decision_function(X))
except AttributeError:
return invert_order(self.detector_.score_samples(X))
@property
def n_neighbors_(self):
"""The actual number of neighbors used for kneighbors queries.
Decorator for scikit-learn LOF attributes.
"""
return self.detector_.n_neighbors_