jer.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."""

from typing import Iterable

import evaluate
import datasets
import numpy as np


# 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 = """\
Computes precision, recall, f1 scores for joint entity-relation extraction task.
"""


# 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}
"""

@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class jer(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.features.Sequence(datasets.Value('string')),
                'references': datasets.features.Sequence(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, predictions, references):
        """Returns the scores"""
        score_dicts = [
            self._compute_single(prediction=prediction, reference=reference) 
            for prediction, reference in zip(predictions, references)
        ]
        return {('mean_' + key): np.mean([scores[key] for scores in score_dicts]) for key in score_dicts[0].keys()}
    
    def _compute_single(self, *, prediction: Iterable[str | tuple | int], reference: Iterable[str | tuple | int]):
        reference_set = set(reference)
        assert len(reference) == len(reference_set), f"Duplicates found in the reference list {reference}"
        prediction_set = set(prediction)

        TP = len(reference_set & prediction_set)
        FP = len(prediction_set - reference_set)
        FN = len(reference_set - prediction_set)
        
        # Calculate metrics
        precision = TP / (TP + FP) if TP + FP > 0 else 0
        recall = TP / (TP + FN) if TP + FN > 0 else 0
        f1_score = 2 * (precision * recall) / (precision + recall) if precision + recall > 0 else 0
        
        return {
            'precision': precision,
            'recall': recall,
            'f1': f1_score
        }