Last active
September 15, 2022 16:25
-
-
Save tam17aki/f05f6c2d7bca67c106d2a43ea83c94af to your computer and use it in GitHub Desktop.
Unsupervised Outlier Detection based on Random Projection Outlyingness (RPO).
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 -*- | |
"""Unsupervised Outlier Detection based on Random Projection Outlyingness (RPO). | |
""" | |
# Author: Akira Tamamori <tamamori5917@gmail.com> | |
# License: BSD 2 clause | |
from __future__ import division, print_function | |
import numpy as np | |
from pyod.models.base import BaseDetector | |
from scipy import stats | |
from sklearn.preprocessing import normalize | |
from sklearn.utils import check_array, check_random_state | |
from sklearn.utils.validation import check_is_fitted | |
class RPO(BaseDetector): | |
"""RPO class for outlier detection. | |
Random Projection Outlyingness (RPO) is a measure of outlyingness of data point. | |
In one-dimensional case, outlyingness from the center of the data distribution | |
can be evaluated by using the median and the median absolute deviation. | |
They are known to be less sensitive to outliers. | |
The definition can be extended so that the outlyingness calculated for | |
one-dimensional data can also be calculated for d-dimensional data. | |
The d-dimensional projection axis is randomly sampled from the d-dimensional unit | |
hypersphere, and the entire dataset is projected onto one-dimensional space. | |
The outlyingness is then calculated over a one-dimensional dataset. | |
Donoho, D. L., Gasko, M., et al. Breakdown properties of | |
location estimates based on halfspace depth and projected | |
outlyingness. The Annals of Statistics, 20(4):1803–1827, 1992. | |
Parameters | |
---------- | |
n_projections : int (0, n_samples), optional (default=100) | |
The number of random projection axes. | |
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. | |
random_state : int, RandomState instance or None, optional (default=None) | |
If int, random_state is the seed used by the random number generator; | |
If RandomState instance, random_state is the random number generator; | |
If None, the random number generator is the RandomState instance | |
used by np.random. | |
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, n_projections=100, random_state=None): | |
super().__init__(contamination=contamination) | |
self.n_projections = n_projections | |
self.random_state = check_random_state(random_state) | |
self.decision_scores_ = None | |
self.proj_axes = None | |
self.median = None | |
self.median_dev = 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) | |
# draw random axes on hypersphere | |
self.proj_axes = self.random_state.randn(X.shape[1], self.n_projections) | |
self.proj_axes = normalize(self.proj_axes) # normalized vectors on hypersphere | |
# project X onto random axis via inner product | |
proj_data = X.dot(self.proj_axes) # (n_samples, n_proj) | |
self.median = np.median(proj_data, axis=0) # (n_proj) | |
self.median = np.expand_dims(self.median, axis=0) # (1, n_proj) | |
self.median_dev = stats.median_abs_deviation(proj_data, axis=0) # (n_proj) | |
self.median_dev = np.expand_dims(self.median_dev, axis=0) # (1, n_proj) | |
# compute random projection outlyingness | |
self.decision_scores_ = np.max( | |
np.abs(proj_data - self.median) / self.median_dev, axis=1 | |
) | |
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) | |
proj_data = X.dot(self.proj_axes) # project X onto random axis | |
anomaly_scores = np.max( | |
np.abs(proj_data - self.median) / self.median_dev, axis=1 | |
) | |
return anomaly_scores |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment