charmatch.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
from Levenshtein import distance as lev

# 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 charmatch(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="Charmatch",
            citation="",
            inputs_description="input expected output",
            # This defines the format of each prediction and reference
            features=datasets.Features({
                'inputs': datasets.Value('string'),
                'expected': datasets.Value('string'),
                'outputs': datasets.Value('string')
            }),
            # 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, inputs, expected, outputs):
        def get_score(input, expected, output):
            print(input, expected, output)
            deduped = {input, expected, output}
            if len(deduped) == 1:
                return 1.0
            elif len(deduped) == 2:
                if expected == output:
                    return 1.0
                else:
                    return 0.0
            else:
                expected_corrections = lev(input, expected)
                distance_to_input = lev(input, output)
                distance_to_expected = lev(output, expected)
                print(f'dl(s,g): {expected_corrections}\ndl(s,h): {distance_to_input}\ndl(h,g): {distance_to_expected}')

                true_positives = min(expected_corrections, max(0, (expected_corrections + distance_to_input - distance_to_expected))) / 2
                print(f'T: {true_positives}')

                precision = true_positives / distance_to_input
                recall = true_positives / expected_corrections
                f_05 = (1 + 0.5**2) * (precision * recall) / (0.5**2 * precision + recall)
                print(f'P: {precision}\nR: {recall}')

                return f_05

        avg = sum([get_score(*row) for row in zip(inputs, expected, outputs)]) / len(inputs) * 100

        return {
            "fscore": avg
        }