execution_accuracy.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 = """\
@misc{li2023llm,
      title={Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs}, 
      author={Jinyang Li and Binyuan Hui and Ge Qu and Jiaxi Yang and Binhua Li and Bowen Li and Bailin Wang and Bowen Qin and Rongyu Cao and Ruiying Geng and Nan Huo and Xuanhe Zhou and Chenhao Ma and Guoliang Li and Kevin C. C. Chang and Fei Huang and Reynold Cheng and Yongbin Li},
      year={2023},
      eprint={2305.03111},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
"""

# TODO: Add description of the module here
_DESCRIPTION = """\
This new module is designed to calculate the EX, which is defined as the proportion of examples in the evaluation set for
which the executed results of both the predicted and ground-truth SQLs are identical, relative to the
overall number of SQLs.
"""


# 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.
    execute_func: function that executes sql query on database.
    filter_func: function that returns true, if sql query can make changes to the database, 
        else false.
Returns:
    accuracy: description of the first 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 ExecutionAccuracy(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('string'),
                'references': 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, execute_func, filter_func=None):
        """Returns the scores"""
        # TODO: Compute the different scores of the module
        
        if len(predictions) != len(references):
            raise ValueError("Predictions and references must have the same number of elements.")
        
        # Run filter_func on predictions and references if needed
        filtered_predictions = []
        filtered_references = []
        divider = 0
        if filter_func is not None:
            for prediction, reference in zip(predictions, references):
                # Only keep if both prediction and reference pass the filter
                pred_bool = filter_func(prediction)
                ref_bool = filter_func(reference)
                if pred_bool and ref_bool:
                    filtered_predictions.append(prediction)
                    filtered_references.append(reference)
                    divider += 1
                # If only the reference passes the filter, count it
                elif pred_bool != ref_bool:
                    divider += 1
        else:
            filtered_predictions = predictions
            filtered_references = references
            divider = len(predictions)
        
        # If all preds and refs are filtered, execution accuracy makes no sense
        if divider == 0:
            divider = -1                    
        
        accuracy = sum(execute_func(i) == execute_func(j) for i, j in zip(filtered_predictions, filtered_references)) / divider
        
        return {
            "accuracy": accuracy,
        }