topk_accuracy.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.
"""Top-k Accuracy metric."""

import datasets
from sklearn.metrics import top_k_accuracy_score

import evaluate


_DESCRIPTION = """
Accuracy is the proportion of correct predictions among the total number of cases processed. It can be computed with:
Accuracy = (TP + TN) / (TP + TN + FP + FN)
 Where:
TP: True positive
TN: True negative
FP: False positive
FN: False negative

Top-k Accuracy is the proportion of correct predictions among the top k predictions.
"""


_KWARGS_DESCRIPTION = """
Args:
    predictions (`list` of `list` of `float`): Model predictions.
    references (`list` of `int`): Ground truth labels.
    normalize (`boolean`): If set to False, returns the number of correctly classified samples. Otherwise, returns the fraction of correctly classified samples. Defaults to True.
    sample_weight (`list` of `float`): Sample weights Defaults to None.

Returns:
    accuracy (`float` or `int`): Top-k accuracy score. Minimum possible value is 0. Maximum possible value is 1.0, or the number of examples input, if `normalize` is set to `True`.. A higher score means higher accuracy.

Examples:

    >>> import numpy as np
    >>> from sklearn.metrics import top_k_accuracy_score
    >>> y_true = np.array([0, 1, 2, 2])
    >>> y_score = np.array([[0.5, 0.2, 0.2],  # 0 is in top 2
    ...                     [0.3, 0.4, 0.2],  # 1 is in top 2
    ...                     [0.2, 0.4, 0.3],  # 2 is in top 2
    ...                     [0.7, 0.2, 0.1]]) # 2 isn't in top 2
    >>> top_k_accuracy_score(y_true, y_score, k=2)
    0.75
    >>> # Not normalizing gives the number of "correctly" classified samples
    >>> top_k_accuracy_score(y_true, y_score, k=2, normalize=False)
    3
"""

_CITATION = """
"""


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class Accuracy(evaluate.Metric):
    def _info(self):
        return evaluate.MetricInfo(
            description=_DESCRIPTION,
            inputs_description=_KWARGS_DESCRIPTION,
            citation=_CITATION,
            features=datasets.Features(
                {
                    "predictions": datasets.Sequence(datasets.Sequence(datasets.Value("float32"))),
                    "references": datasets.Sequence(datasets.Value("int32")),
                }
                if self.config_name == "multilabel"
                else {
                    "predictions": datasets.Sequence(datasets.Value("float32")),
                    "references": datasets.Value("int32"),
                }
            ),
            reference_urls=["https://scikit-learn.org/stable/modules/generated/sklearn.metrics.top_k_accuracy_score.html"],
        )

    def _compute(self, predictions, references, normalize=True, sample_weight=None):
        return {
            "accuracy": float(
                top_k_accuracy_score(references, predictions, normalize=normalize, sample_weight=sample_weight)
            )
        }