pr_auc.py

# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
#
# 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.
"""Precision-recall AUC metric."""

import datasets
from sklearn.metrics import average_precision_score

import evaluate


_DESCRIPTION = """
Compute average precision (AP) from prediction scores.

    AP summarizes a precision-recall curve as the weighted mean of precisions
    achieved at each threshold, with the increase in recall from the previous
    threshold used as the weight:

    .. math::
        \\text{AP} = \\sum_n (R_n - R_{n-1}) P_n

    where :math:`P_n` and :math:`R_n` are the precision and recall at the nth
    threshold [1]_. This implementation is not interpolated and is different
    from computing the area under the precision-recall curve with the
    trapezoidal rule, which uses linear interpolation and can be too
    optimistic.
"""

_KWARGS_DESCRIPTION = """
Parameters
    ----------
    references : array-like of shape (n_samples,)
        True binary labels or binary label indicators.

    prediction_scores : array-like of shape (n_samples,)
        Target scores, can either be probability estimates of the positive
        class, confidence values, or non-thresholded measure of decisions
        (as returned by :term:`decision_function` on some classifiers).

    average : {'micro', 'samples', 'weighted', 'macro'} or None, \
            default='macro'
        If ``None``, the scores for each class are returned. Otherwise,
        this determines the type of averaging performed on the data:

        ``'micro'``:
            Calculate metrics globally by considering each element of the label
            indicator matrix as a label.
        ``'macro'``:
            Calculate metrics for each label, and find their unweighted
            mean.  This does not take label imbalance into account.
        ``'weighted'``:
            Calculate metrics for each label, and find their average, weighted
            by support (the number of true instances for each label).
        ``'samples'``:
            Calculate metrics for each instance, and find their average.

        Will be ignored when ``references`` is binary.

    pos_label : int, float, bool or str, default=1
        The label of the positive class. Only applied to binary ``references``.
        For multilabel-indicator ``references``, ``pos_label`` is fixed to 1.

    sample_weight : array-like of shape (n_samples,), default=None
        Sample weights.

    Returns
    -------
    average_precision : float
        Average precision score.
"""

_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 PRAUC(evaluate.Metric):
    def _info(self):
        return evaluate.MetricInfo(
            description=_DESCRIPTION,
            citation=_CITATION,
            inputs_description=_KWARGS_DESCRIPTION,
            features=datasets.Features(
                {
                    "references": datasets.Value("int32"),
                    "prediction_scores": datasets.Value("float"),
                }
            ),
            reference_urls=["https://scikit-learn.org/stable/modules/generated/sklearn.metrics.average_precision_score.html"],
        )

    def _compute(
        self,
        references,
        prediction_scores,
        average="macro",
        sample_weight=None,
        pos_label=1,
    ):
        return {
            "pr_auc": average_precision_score(
                references,
                prediction_scores,
                average=average,
                sample_weight=sample_weight,
                pos_label=pos_label
            )
        }