Last active
August 22, 2021 10:22
-
-
Save tam17aki/480a2c3155e1e06d59231c8f5eac65f4 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
""" | |
Python script for outlier detection based on Kernel Density Estimation. | |
Copyright (C) 2021 by Akira TAMAMORI | |
Permission is hereby granted, free of charge, to any person obtaining | |
a copy of this software and associated documentation files (the | |
"Software"), to deal in the Software without restriction, including | |
without limitation the rights to use, copy, modify, merge, publish, | |
distribute, sublicense, and/or sell copies of the Software, and to | |
permit persons to whom the Software is furnished to do so, subject to | |
the following conditions: | |
The above copyright notice and this permission notice shall be | |
included in all copies or substantial portions of the Software. | |
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, | |
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF | |
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND | |
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE | |
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION | |
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION | |
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. | |
""" | |
from __future__ import division, print_function | |
from warnings import warn | |
from pyod.models.base import BaseDetector | |
from pyod.utils.utility import invert_order | |
from sklearn.neighbors import KernelDensity | |
from sklearn.utils import check_array | |
from sklearn.utils.validation import check_is_fitted | |
class KDE(BaseDetector): | |
"""KDE class for outlier detection. | |
For an observation, its negative log probabilitiy density could be viewed | |
as the outlying score. | |
Parameters | |
---------- | |
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. Used when fitting to | |
define the threshold on the decision function. | |
bandwidth : float, optional (default=1.0) | |
The bandwidth of the kernel. | |
algorithm : {'auto', 'ball_tree', 'kd_tree'}, optional | |
Algorithm used to compute the kernel density estimator: | |
- 'ball_tree' will use BallTree | |
- 'kd_tree' will use KDTree | |
- 'auto' will attempt to decide the most appropriate algorithm | |
based on the values passed to :meth:`fit` method. | |
leaf_size : int, optional (default = 30) | |
Leaf size passed to BallTree. 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 to use for distance computation. Any metric from scikit-learn | |
or scipy.spatial.distance can be used. | |
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. | |
Distance matrices are not supported. | |
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. | |
metric_params : dict, optional (default = None) | |
Additional keyword arguments for the metric function. | |
Attributes | |
---------- | |
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, contamination=0.1, bandwidth=1.0, algorithm='auto', | |
leaf_size=30, metric='minkowski', metric_params=None): | |
super().__init__(contamination=contamination) | |
self.bandwidth = bandwidth | |
self.algorithm = algorithm | |
self.leaf_size = leaf_size | |
self.metric = metric | |
self.metric_params = metric_params | |
if self.algorithm != 'auto' and self.algorithm != 'ball_tree': | |
warn('algorithm parameter is deprecated and will be removed ' | |
'in version 0.7.6. By default, ball_tree will be used.', | |
FutureWarning) | |
self.kde_ = KernelDensity( | |
bandwidth=self.bandwidth, | |
algorithm=self.algorithm, | |
leaf_size=self.leaf_size, | |
metric=self.metric, | |
metric_params=self.metric_params) | |
self.decision_scores_ = None | |
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.kde_.fit(X) | |
# invert decision_scores_. Outliers comes with higher outlier scores. | |
self.decision_scores_ = invert_order(self.kde_.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_']) | |
X = check_array(X) | |
# invert outlier scores. Outliers comes with higher outlier scores. | |
return invert_order(self.kde_.score_samples(X)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment