oppo_refuse_match.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.
"""Oppo Refuse Match metric."""
import re
import string

import datasets
import numpy as np

import evaluate
from .eval import has_answer

_DESCRIPTION = """
Returns the rate at which the input predicted strings exactly match the refuse list
"""

_KWARGS_DESCRIPTION = """
Args:
    predictions: List of predicted texts. -> [prediction] only one
    references: not use
    
Returns:
    oppo_refuse_match: Dictionary containing oppo_refuse_match rate. Possible values are 0 or 1
Examples:
    
"""

_CITATION = """ the dpr exact match
"""


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class OppoRefuseMatch(evaluate.Metric):
    def _info(self):
        return evaluate.MetricInfo(
            description=_DESCRIPTION,
            citation=_CITATION,
            inputs_description=_KWARGS_DESCRIPTION,
            features=datasets.Features(
                {
                    "predictions": datasets.Value("string", id="sequence")
                }
            ),
            reference_urls=[],
        )

    def _compute(
        self,
        predictions
    ):
        patterns = [
        r"There is no", r"no", r"non-existent", r"not a", r"none"
    ]
        score_list=0
        for prediction in predictions:
            if has_answer(prediction,patterns):
                score_list+=1
        return {"oppo_refuse_match": score_list/len(predictions)}