# 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 evaluate
import datasets
from sklearn.metrics import roc_auc_score


# TODO: Add BibTeX citation
_CITATION = """\
@InProceedings{huggingface:module,
title = {Roc AUC Macro},
authors={Mike Frantz},
year={2022}
}
"""

# TODO: Add description of the module here
_DESCRIPTION = """\
This module makes scikit-learn's roc_auc_score with average='macro'
available as a metric in the hub for use in multi-class or multi-label
classification.
"""


# TODO: Add description of the arguments of the module here
_KWARGS_DESCRIPTION = """
Compute Area Under the Receiver Operating Characteristic Curve (ROC AUC) from prediction scores.
Calculates metrics for each label, and find their unweighted mean. This does not take label imbalance into account.
(FROM https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html)

Args:
    scores: An array of shape (n_samples, n_classes) of probability estimates.
        In the multi-class case, the probabilities must sum to 1 across classes.
        In the multi-label case, the probabilities, each output corresponds
        to a binary decision for a particular label.
    references: list of reference for each prediction. Each
        reference should be an array of shape (n_sampls, n_classes) with values
        of 0 or 1.
Returns:
    roc_auc_macro
Examples:
    Examples should be written in doctest format, and should illustrate how
    to use the function.

    >>> roc_auc_macro = evaluate.load("mgfrantz/roc_auc_macro")
    >>> results = my_new_module.compute(
            references=[[1, 0, 1], [0, 1, 0]], 
            scores=[[.8, .2, .9], [.1, .8, .6]]
        )
    >>> print(results)
    {'roc_auc_macro': 1.0}
"""


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class roc_auc_macro(evaluate.Metric):
    """TODO: Short description of my evaluation module."""

    def _info(self):
        # TODO: Specifies the evaluate.EvaluationModuleInfo object
        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({
                'scores': datasets.Value('float64'),
                'references': datasets.Value('int64'),
            }),
            # Homepage of the module for documentation
            homepage="N/A",
            # Additional links to the codebase or references
            codebase_urls=["N/A"],
            reference_urls=["N/A"]
        )

    def _download_and_prepare(self, dl_manager):
        """Optional: download external resources useful to compute the scores"""
        # TODO: Download external resources if needed
        pass

    def _compute(self, predictions, references):
        """Returns the scores"""
        return {
            "roc_auc_macro": roc_auc_score(references, scores, average='macro'),
        }