multiclass_fpr_weighted.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 evaluate
import datasets


# TODO: Add BibTeX citation
_CITATION = """\
@InProceedings{huggingface:module,
title = {A great new module},
authors={huggingface, Inc.},
year={2020}
}
"""

# TODO: Add description of the module here
_DESCRIPTION = """\
This new module is designed to solve this great ML task and is crafted with a lot of care.
"""


# TODO: Add description of the arguments of the module here
_KWARGS_DESCRIPTION = """
Calculates how good are predictions given some references, using certain scores
Args:
    predictions: list of predictions to score. Each predictions
        should be a string with tokens separated by spaces.
    references: list of reference for each prediction. Each
        reference should be a string with tokens separated by spaces.
Returns:
    accuracy: description of the first score,
    another_score: description of the second score,
Examples:
    Examples should be written in doctest format, and should illustrate how
    to use the function.

    >>> my_new_module = evaluate.load("my_new_module")
    >>> results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
    >>> print(results)
    {'accuracy': 1.0}
"""

# TODO: Define external resources urls if needed
BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class multiclass_fpr_weighted(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({
                'predictions': datasets.Value('int64'),
                'references': datasets.Value('int64'),
            }),
            # Homepage of the module for documentation
            homepage="http://module.homepage",
            # Additional links to the codebase or references
            codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
            reference_urls=["http://path.to.reference.url/new_module"]
        )

    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):
        from collections import defaultdict

        """Returns the scores"""
        # TODO: Compute the different scores of the module

        # Count false positives, true negatives, and false instance counts for each class
        fp_counts = defaultdict(int)
        tn_counts = defaultdict(int)
        false_counts = defaultdict(int)

        for true_label, pred_label in zip(references, predictions):
            if true_label != pred_label:
                fp_counts[pred_label] += 1
                false_counts[pred_label] += 1
            else:
                for class_label in set(references) - {true_label}:
                    tn_counts[class_label] += 1
                    false_counts[class_label] += 1

        # Calculate class-wise false positive rate
        class_fpr = {}
        total_weight = sum(false_counts.values())
        weighted_sum = 0.0

        for class_label in set(references):
            fp = fp_counts[class_label]
            tn = tn_counts[class_label]
            false_instances = false_counts[class_label]

            fpr = fp / (fp + tn) if (fp + tn) > 0 else 0
            class_fpr[class_label] = fpr
            weighted_sum += fpr * false_instances

        weighted_avg_fpr = weighted_sum / total_weight if total_weight > 0 else 0
        return {
            "weighted_fpr": weighted_avg_fpr,
        }