1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
|
# Author: Virgile Fritsch <virgile.fritsch@inria.fr>
#
# License: BSD 3 clause
import numpy as np
import warnings
from . import MinCovDet
from ..utils.validation import check_is_fitted, check_array
from ..metrics import accuracy_score
from ..base import OutlierMixin
class EllipticEnvelope(MinCovDet, OutlierMixin):
"""An object for detecting outliers in a Gaussian distributed dataset.
Read more in the :ref:`User Guide <outlier_detection>`.
Parameters
----------
store_precision : boolean, optional (default=True)
Specify if the estimated precision is stored.
assume_centered : boolean, optional (default=False)
If True, the support of robust location and covariance estimates
is computed, and a covariance estimate is recomputed from it,
without centering the data.
Useful to work with data whose mean is significantly equal to
zero but is not exactly zero.
If False, the robust location and covariance are directly computed
with the FastMCD algorithm without additional treatment.
support_fraction : float in (0., 1.), optional (default=None)
The proportion of points to be included in the support of the raw
MCD estimate. If None, the minimum value of support_fraction will
be used within the algorithm: `[n_sample + n_features + 1] / 2`.
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.
random_state : int, RandomState instance or None, optional (default=None)
The seed of the pseudo random number generator to use when shuffling
the data. 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
----------
location_ : array-like, shape (n_features,)
Estimated robust location
covariance_ : array-like, shape (n_features, n_features)
Estimated robust covariance matrix
precision_ : array-like, shape (n_features, n_features)
Estimated pseudo inverse matrix.
(stored only if store_precision is True)
support_ : array-like, shape (n_samples,)
A mask of the observations that have been used to compute the
robust estimates of location and shape.
offset_ : float
Offset used to define the decision function from the raw scores.
We have the relation: ``decision_function = score_samples - offset_``.
The offset depends on the contamination parameter and is defined in
such a way we obtain the expected number of outliers (samples with
decision function < 0) in training.
See Also
--------
EmpiricalCovariance, MinCovDet
Notes
-----
Outlier detection from covariance estimation may break or not
perform well in high-dimensional settings. In particular, one will
always take care to work with ``n_samples > n_features ** 2``.
References
----------
.. [1] Rousseeuw, P.J., Van Driessen, K. "A fast algorithm for the
minimum covariance determinant estimator" Technometrics 41(3), 212
(1999)
"""
def __init__(self, store_precision=True, assume_centered=False,
support_fraction=None, contamination=0.1,
random_state=None):
super(EllipticEnvelope, self).__init__(
store_precision=store_precision,
assume_centered=assume_centered,
support_fraction=support_fraction,
random_state=random_state)
self.contamination = contamination
def fit(self, X, y=None):
"""Fit the EllipticEnvelope model.
Parameters
----------
X : numpy array or sparse matrix, shape (n_samples, n_features).
Training data
y : Ignored
not used, present for API consistency by convention.
"""
super(EllipticEnvelope, self).fit(X)
self.offset_ = np.percentile(-self.dist_, 100. * self.contamination)
return self
def decision_function(self, X, raw_values=None):
"""Compute the decision function of the given observations.
Parameters
----------
X : array-like, shape (n_samples, n_features)
raw_values : bool, optional
Whether or not to consider raw Mahalanobis distances as the
decision function. Must be False (default) for compatibility
with the others outlier detection tools.
.. deprecated:: 0.20
``raw_values`` has been deprecated in 0.20 and will be removed
in 0.22.
Returns
-------
decision : array-like, shape (n_samples, )
Decision function of the samples.
It is equal to the shifted Mahalanobis distances.
The threshold for being an outlier is 0, which ensures a
compatibility with other outlier detection algorithms.
"""
check_is_fitted(self, 'offset_')
negative_mahal_dist = self.score_samples(X)
# raw_values deprecation:
if raw_values is not None:
warnings.warn("raw_values parameter is deprecated in 0.20 and will"
" be removed in 0.22.", DeprecationWarning)
if not raw_values:
return (-self.offset_) ** 0.33 - (-negative_mahal_dist) ** 0.33
return negative_mahal_dist - self.offset_
def score_samples(self, X):
"""Compute the negative Mahalanobis distances.
Parameters
----------
X : array-like, shape (n_samples, n_features)
Returns
-------
negative_mahal_distances : array-like, shape (n_samples, )
Opposite of the Mahalanobis distances.
"""
check_is_fitted(self, 'offset_')
return -self.mahalanobis(X)
def predict(self, X):
"""
Predict the labels (1 inlier, -1 outlier) of X according to the
fitted model.
Parameters
----------
X : array-like, shape (n_samples, n_features)
Returns
-------
is_inlier : array, shape (n_samples,)
Returns -1 for anomalies/outliers and +1 for inliers.
"""
X = check_array(X)
is_inlier = np.full(X.shape[0], -1, dtype=int)
values = self.decision_function(X)
is_inlier[values >= 0] = 1
return is_inlier
def score(self, X, y, sample_weight=None):
"""Returns the mean accuracy on the given test data and labels.
In multi-label classification, this is the subset accuracy
which is a harsh metric since you require for each sample that
each label set be correctly predicted.
Parameters
----------
X : array-like, shape (n_samples, n_features)
Test samples.
y : array-like, shape (n_samples,) or (n_samples, n_outputs)
True labels for X.
sample_weight : array-like, shape (n_samples,), optional
Sample weights.
Returns
-------
score : float
Mean accuracy of self.predict(X) wrt. y.
"""
return accuracy_score(y, self.predict(X), sample_weight=sample_weight)
@property
def threshold_(self):
warnings.warn("threshold_ attribute is deprecated in 0.20 and will"
" be removed in 0.22.", DeprecationWarning)
return self.offset_
|
