Spaces:
Running
Running
File size: 4,870 Bytes
d7b729a 8eb6170 d7b729a |
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 |
"""Confusion Matrix metric."""
import datasets
import evaluate
from sklearn.metrics import confusion_matrix
_DESCRIPTION = """
Compute confusion matrix to evaluate the accuracy of a classification.
By definition a confusion matrix :math:`C` is such that :math:`C_{i, j}`
is equal to the number of observations known to be in group :math:`i` and
predicted to be in group :math:`j`.
Thus in binary classification, the count of true negatives is
:math:`C_{0,0}`, false negatives is :math:`C_{1,0}`, true positives is
:math:`C_{1,1}` and false positives is :math:`C_{0,1}`.
Read more in the :ref:`User Guide <confusion_matrix>`.
"""
_KWARGS_DESCRIPTION = """
Args:
y_true : array-like of shape (n_samples,)
Ground truth (correct) target values.
y_pred : array-like of shape (n_samples,)
Estimated targets as returned by a classifier.
labels : array-like of shape (n_classes), default=None
List of labels to index the matrix. This may be used to reorder
or select a subset of labels.
If ``None`` is given, those that appear at least once
in ``y_true`` or ``y_pred`` are used in sorted order.
sample_weight : array-like of shape (n_samples,), default=None
Sample weights.
.. versionadded:: 0.18
normalize : {'true', 'pred', 'all'}, default=None
Normalizes confusion matrix over the true (rows), predicted (columns)
conditions or all the population. If None, confusion matrix will not be
normalized.
Returns:
C : ndarray of shape (n_classes, n_classes)
Confusion matrix whose i-th row and j-th
column entry indicates the number of
samples with true label being i-th class
and predicted label being j-th class.
See Also:
ConfusionMatrixDisplay.from_estimator : Plot the confusion matrix
given an estimator, the data, and the label.
ConfusionMatrixDisplay.from_predictions : Plot the confusion matrix
given the true and predicted labels.
ConfusionMatrixDisplay : Confusion Matrix visualization.
References:
.. [1] `Wikipedia entry for the Confusion matrix
<https://en.wikipedia.org/wiki/Confusion_matrix>`_
(Wikipedia and other references may use a different
convention for axes).
Examples:
>>> from sklearn.metrics import confusion_matrix
>>> y_true = [2, 0, 2, 2, 0, 1]
>>> y_pred = [0, 0, 2, 2, 0, 2]
>>> confusion_matrix(y_true, y_pred)
array([[2, 0, 0],
[0, 0, 1],
[1, 0, 2]])
>>> y_true = ["cat", "ant", "cat", "cat", "ant", "bird"]
>>> y_pred = ["ant", "ant", "cat", "cat", "ant", "cat"]
>>> confusion_matrix(y_true, y_pred, labels=["ant", "bird", "cat"])
array([[2, 0, 0],
[0, 0, 1],
[1, 0, 2]])
In the binary case, we can extract true positives, etc as follows:
>>> tn, fp, fn, tp = confusion_matrix([0, 1, 0, 1], [1, 1, 1, 0]).ravel()
>>> (tn, fp, fn, tp)
(0, 2, 1, 1)
"""
_CITATION = """
@article{scikit-learn,
title={Scikit-learn: Machine Learning in {P}ython},
author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
journal={Journal of Machine Learning Research},
volume={12},
pages={2825--2830},
year={2011}
}
"""
@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class ConfusionMatrix(evaluate.Metric):
def _info(self):
return evaluate.MetricInfo(
description=_DESCRIPTION,
citation=_CITATION,
inputs_description=_KWARGS_DESCRIPTION,
features=datasets.Features(
{
"predictions": datasets.Sequence(datasets.Value("int32")),
"references": datasets.Sequence(datasets.Value("int32")),
}
if self.config_name == "multilabel"
else {
"predictions": datasets.Value("int32"),
"references": datasets.Value("int32"),
}
),
reference_urls=[
"https://scikit-learn.org/stable/modules/generated/sklearn.metrics.confusion_matrix.html"
],
)
def _compute(
self,
predictions,
references,
*,
labels=None,
sample_weight=None,
normalize=None
):
return {
"confusion_matrix": confusion_matrix(
y_true=references,
y_pred=predictions,
labels=labels,
sample_weight=sample_weight,
normalize=normalize,
)
}
|