-
Notifications
You must be signed in to change notification settings - Fork 388
/
specificity.py
161 lines (132 loc) · 7.35 KB
/
specificity.py
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
# Copyright The PyTorch Lightning team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import Any, Optional
import torch
from torch import Tensor
from torchmetrics.classification.stat_scores import StatScores
from torchmetrics.functional.classification.specificity import _specificity_compute
from torchmetrics.utilities.enums import AverageMethod
class Specificity(StatScores):
r"""Computes `Specificity`_:
.. math:: \text{Specificity} = \frac{\text{TN}}{\text{TN} + \text{FP}}
Where :math:`\text{TN}` and :math:`\text{FP}` represent the number of true negatives and
false positives respecitively. With the use of ``top_k`` parameter, this metric can
generalize to Specificity@K.
The reduction method (how the specificity scores are aggregated) is controlled by the
``average`` parameter, and additionally by the ``mdmc_average`` parameter in the
multi-dimensional multi-class case. Accepts all inputs listed in :ref:`pages/classification:input types`.
Args:
num_classes:
Number of classes. Necessary for ``'macro'``, ``'weighted'`` and ``None`` average methods.
threshold:
Threshold probability value for transforming probability predictions to binary
(0,1) predictions, in the case of binary or multi-label inputs.
average:
Defines the reduction that is applied. Should be one of the following:
- ``'micro'`` [default]: Calculate the metric globally, across all samples and classes.
- ``'macro'``: Calculate the metric for each class separately, and average the
metrics across classes (with equal weights for each class).
- ``'weighted'``: Calculate the metric for each class separately, and average the
metrics across classes, weighting each class by its support (``tn + fp``).
- ``'none'`` or ``None``: Calculate the metric for each class separately, and return
the metric for every class.
- ``'samples'``: Calculate the metric for each sample, and average the metrics
across samples (with equal weights for each sample).
.. note:: What is considered a sample in the multi-dimensional multi-class case
depends on the value of ``mdmc_average``.
mdmc_average:
Defines how averaging is done for multi-dimensional multi-class inputs (on top of the
``average`` parameter). Should be one of the following:
- ``None`` [default]: Should be left unchanged if your data is not multi-dimensional
multi-class.
- ``'samplewise'``: In this case, the statistics are computed separately for each
sample on the ``N`` axis, and then averaged over samples.
The computation for each sample is done by treating the flattened extra axes ``...``
(see :ref:`pages/classification:input types`) as the ``N`` dimension within the sample,
and computing the metric for the sample based on that.
- ``'global'``: In this case the ``N`` and ``...`` dimensions of the inputs
(see :ref:`pages/classification:input types`)
are flattened into a new ``N_X`` sample axis, i.e. the inputs are treated as if they
were ``(N_X, C)``. From here on the ``average`` parameter applies as usual.
ignore_index:
Integer specifying a target class to ignore. If given, this class index does not contribute
to the returned score, regardless of reduction method. If an index is ignored, and ``average=None``
or ``'none'``, the score for the ignored class will be returned as ``nan``.
top_k:
Number of the highest probability entries for each sample to convert to 1s - relevant
only for inputs with probability predictions. If this parameter is set for multi-label
inputs, it will take precedence over ``threshold``. For (multi-dim) multi-class inputs,
this parameter defaults to 1.
Should be left unset (``None``) for inputs with label predictions.
multiclass:
Used only in certain special cases, where you want to treat inputs as a different type
than what they appear to be. See the parameter's
:ref:`documentation section <pages/classification:using the multiclass parameter>`
for a more detailed explanation and examples.
kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
Raises:
ValueError:
If ``average`` is none of ``"micro"``, ``"macro"``, ``"weighted"``, ``"samples"``, ``"none"``, ``None``.
Example:
>>> from torchmetrics import Specificity
>>> preds = torch.tensor([2, 0, 2, 1])
>>> target = torch.tensor([1, 1, 2, 0])
>>> specificity = Specificity(average='macro', num_classes=3)
>>> specificity(preds, target)
tensor(0.6111)
>>> specificity = Specificity(average='micro')
>>> specificity(preds, target)
tensor(0.6250)
"""
is_differentiable: bool = False
higher_is_better: bool = True
full_state_update: bool = False
def __init__(
self,
num_classes: Optional[int] = None,
threshold: float = 0.5,
average: Optional[str] = "micro",
mdmc_average: Optional[str] = None,
ignore_index: Optional[int] = None,
top_k: Optional[int] = None,
multiclass: Optional[bool] = None,
**kwargs: Any,
) -> None:
allowed_average = ["micro", "macro", "weighted", "samples", "none", None]
if average not in allowed_average:
raise ValueError(f"The `average` has to be one of {allowed_average}, got {average}.")
_reduce_options = (AverageMethod.WEIGHTED, AverageMethod.NONE, None)
if "reduce" not in kwargs:
kwargs["reduce"] = AverageMethod.MACRO if average in _reduce_options else average
if "mdmc_reduce" not in kwargs:
kwargs["mdmc_reduce"] = mdmc_average
super().__init__(
threshold=threshold,
top_k=top_k,
num_classes=num_classes,
multiclass=multiclass,
ignore_index=ignore_index,
**kwargs,
)
self.average = average
def compute(self) -> Tensor:
"""Computes the specificity score based on inputs passed in to ``update`` previously.
Return:
The shape of the returned tensor depends on the ``average`` parameter:
- If ``average in ['micro', 'macro', 'weighted', 'samples']``, a one-element tensor will be returned
- If ``average in ['none', None]``, the shape will be ``(C,)``, where ``C`` stands for the number
of classes
"""
tp, fp, tn, fn = self._get_final_stats()
return _specificity_compute(tp, fp, tn, fn, self.average, self.mdmc_reduce)