average_precision_score.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.
"""Average precision score."""

import datasets
from sklearn.metrics import average_precision_score

import evaluate


_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}
}
"""


_DESCRIPTION = """\
Average precision score.
"""

_KWARGS_DESCRIPTION = """
    Note: To be consistent with the `evaluate` input conventions the scikit-learn inputs are renamed:
    - `y_true`: `references`
    - `y_pred`: `prediction_scores`

    Scikit-learn docstring:
    Average precision score.

    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.
    Note: this implementation is restricted to the binary classification task
    or multilabel classification task.
    Read more in the :ref:`User Guide <precision_recall_f_measure_metrics>`.
    Parameters
    ----------
    y_true : ndarray of shape (n_samples,) or (n_samples, n_classes)
        True binary labels or binary label indicators.
    y_score : ndarray of shape (n_samples,) or (n_samples, n_classes)
        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 ``y_true`` is binary.
    pos_label : int or str, default=1
        The label of the positive class. Only applied to binary ``y_true``.
        For multilabel-indicator ``y_true``, ``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.
    See Also
    --------
    roc_auc_score : Compute the area under the ROC curve.
    precision_recall_curve : Compute precision-recall pairs for different
        probability thresholds.
    Notes
    -----
    .. versionchanged:: 0.19
      Instead of linearly interpolating between operating points, precisions
      are weighted by the change in recall since the last operating point.
    References
    ----------
    .. [1] `Wikipedia entry for the Average precision
           <https://en.wikipedia.org/w/index.php?title=Information_retrieval&
           oldid=793358396#Average_precision>`_
    Examples
    --------
    >>> import numpy as np
    >>> from sklearn.metrics import average_precision_score
    >>> y_true = np.array([0, 0, 1, 1])
    >>> y_scores = np.array([0.1, 0.4, 0.35, 0.8])
    >>> average_precision_score(y_true, y_scores)
    0.83...
"""


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class AveragePrecisionScore(evaluate.Metric):
    """Average precision score."""

    def _info(self):
        return evaluate.MetricInfo(
            # This is the description that will appear on the modules page.
            module_type="metric",
            description=_DESCRIPTION,
            citation=_CITATION,
            inputs_description=_KWARGS_DESCRIPTION,
            # This defines the format of each prediction and reference
            features=[
                datasets.Features(
                    {
                        "references": datasets.Value("int64"),
                        "prediction_scores": datasets.Value("float"),
                    }
                ),
                datasets.Features(
                    {
                        "references": datasets.Sequence(datasets.Value("int64")),
                        "prediction_scores": datasets.Sequence(datasets.Value("float")),
                    }
                ),
            ],
            # Homepage of the module for documentation
            homepage="https://scikit-learn.org/stable/modules/generated/sklearn.metrics.average_precision_score.html",
            # Additional links to the codebase or references
            codebase_urls=["https://github.com/scikit-learn/scikit-learn"],
            reference_urls=["https://scikit-learn.org/stable/index.html"],
        )

    def _compute(
        self,
        references,
        prediction_scores,
        average="macro",
        pos_label=1,
        sample_weight=None,
    ):
        """Returns the scores."""
        return {
            "average_precision_score": average_precision_score(
                y_true=references,
                y_score=prediction_scores,
                average=average,
                pos_label=pos_label,
                sample_weight=sample_weight,
            )
        }