accuracy_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.
"""TODO: Add a description here."""

import datasets
from sklearn.metrics import accuracy_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 = """\
Accuracy classification score.
"""


_KWARGS_DESCRIPTION = """
    Note: To be consistent with the `evaluate` input conventions the scikit-learn inputs are renamed:
    - `y_true`: `references`
    - `y_pred`: `predictions`
    
    Scikit-learn docstring:
    Accuracy classification score.

    In multilabel classification, this function computes subset accuracy:
    the set of labels predicted for a sample must *exactly* match the
    corresponding set of labels in y_true.

    Read more in the :ref:`User Guide <accuracy_score>`.

    Parameters
    ----------
    y_true : 1d array-like, or label indicator array / sparse matrix
        Ground truth (correct) labels.

    y_pred : 1d array-like, or label indicator array / sparse matrix
        Predicted labels, as returned by a classifier.

    normalize : bool, default=True
        If ``False``, return the number of correctly classified samples.
        Otherwise, return the fraction of correctly classified samples.

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

    Returns
    -------
    score : float
        If ``normalize == True``, return the fraction of correctly
        classified samples (float), else returns the number of correctly
        classified samples (int).

        The best performance is 1 with ``normalize == True`` and the number
        of samples with ``normalize == False``.

    See Also
    --------
    balanced_accuracy_score : Compute the balanced accuracy to deal with
        imbalanced datasets.
    jaccard_score : Compute the Jaccard similarity coefficient score.
    hamming_loss : Compute the average Hamming loss or Hamming distance between
        two sets of samples.
    zero_one_loss : Compute the Zero-one classification loss. By default, the
        function will return the percentage of imperfectly predicted subsets.

    Notes
    -----
    In binary classification, this function is equal to the `jaccard_score`
    function.

    Examples
    --------
    >>> from sklearn.metrics import accuracy_score
    >>> y_pred = [0, 2, 1, 3]
    >>> y_true = [0, 1, 2, 3]
    >>> accuracy_score(y_true, y_pred)
    0.5
    >>> accuracy_score(y_true, y_pred, normalize=False)
    2

    In the multilabel case with binary label indicators:

    >>> import numpy as np
    >>> accuracy_score(np.array([[0, 1], [1, 1]]), np.ones((2, 2)))
    0.5
    

"""


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class AccuracyScore(evaluate.Metric):
    """Accuracy classification 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(
                    {
                        "predictions": datasets.Sequence(datasets.Value("int32")),
                        "references": datasets.Sequence(datasets.Value("int32")),
                    }
                ),
                datasets.Features(
                    {"predictions": datasets.Sequence(datasets.Value("int32")), "references": datasets.Value("int32")}
                ),
                datasets.Features(
                    {"predictions": datasets.Value("int32"), "references": datasets.Sequence(datasets.Value("int32"))}
                ),
                datasets.Features({"predictions": datasets.Value("int32"), "references": datasets.Value("int32")}),
            ],
            # Homepage of the module for documentation
            homepage="https://scikit-learn.org/stable/modules/generated/sklearn.metrics.accuracy_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, predictions, references, normalize=True, sample_weight=None):
        """Returns the scores"""

        score = accuracy_score(y_true=references, y_pred=predictions, normalize=normalize, sample_weight=sample_weight)

        return {"accuracy_score": score}