new_metric_script.py

# coding=utf-8
# 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


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

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


# TODO: Add description of the arguments of the metric 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,
"""

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


class NewMetric(datasets.Metric):
    """TODO: Short description of my metric."""

    def _info(self):
        # TODO: Specifies the datasets.MetricInfo object
        return datasets.MetricInfo(
            # This is the description that will appear on the metrics page.
            description=_DESCRIPTION,
            citation=_CITATION,
            inputs_description=_KWARGS_DESCRIPTION,
            # This defines the format of each prediction and reference
            features=datasets.Features({
                'predictions': datasets.Value('string'),
                'references': datasets.Value('string'),
            }),
            # Homepage of the metric for documentation
            homepage="http://metric.homepage",
            # Additional links to the codebase or references
            codebase_urls=["http://github.com/path/to/codebase/of/new_metric"],
            reference_urls=["http://path.to.reference.url/new_metric"]
        )

    def _download_and_prepare(self, dl_manager):
        """Optional: download external resources useful to compute the scores"""
        # TODO: Download external resources if needed
        bad_words_path = dl_manager.download_and_extract(BAD_WORDS_URL)
        self.bad_words = set([w.strip() for w in open(bad_words_path, "r", encoding="utf-8")])

    def _compute(self, predictions, references):
        """Returns the scores"""
        # TODO: Compute the different scores of the metric
        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)

        if self.config_name == "max":
            second_score = max(abs(len(i) - len(j)) for i, j in zip(predictions, references) if i not in self.bad_words)
        elif self.config_name == "mean":
            second_score = sum(abs(len(i) - len(j)) for i, j in zip(predictions, references) if i not in self.bad_words)
            second_score /= sum(i not in self.bad_words for i in predictions)
        else:
            raise ValueError("Invalid config name for NewMetric: {}. Please use 'max' or 'mean'.".format(self.config_name))

        return {
            "accuracy": accuracy,
            "second_score": second_score,
        }