storycloze.py

import csv
from lm_eval.base import Task


class StoryCloze(Task):
    NEEDS_MANUAL_DL = True

    def download(self):
        #TODO: replace with Eye link
        pass

    def has_training_docs(self):
        return False

    def has_validation_docs(self):
        return True

    def has_test_docs(self):
        return True

    def training_docs(self):
        pass

    def load_doc(self, filename):
        with open(filename, newline='') as file:
            filereader = csv.reader(file)
            return list(filereader)
                

    def validation_docs(self):
        return self.load_doc("data/storycloze/cloze_test_val__winter2018-cloze_test_ALL_val - 1 - 1.csv")

    def test_docs(self):
        return self.load_doc("data/storycloze/cloze_test_test__winter2018-cloze_test_ALL_test - 1.csv")

    
    def fewshot_description(self):
        # TODO: figure out fewshot description
        return ""
    
    def doc_to_text(self, doc):
        return ' '.join([*doc[1:5]])

    def doc_to_target(self, doc):
        return " " + doc[int(doc[-1]) - 4]

    def construct_requests(self, doc, ctx):
        """ Uses RequestFactory to construct Requests and returns an iterable of 
        Requests which will be sent to the LM.

        :param doc:
            The document as returned from training_docs, validation_docs, or test_docs.
        :param ctx: str
            The context string, generated by fewshot_context. This includes the natural 
            language description, as well as the few shot examples, and the question
            part of the document for `doc`. 
        """
        # TODO: implement evaluation.
        raise NotImplementedError('Evaluation not implemented')
    
    def process_results(self, doc, results):
        """Take a single document and the LM results and evaluates, returning a 
        dict where keys are the names of submetrics and values are the values of 
        the metric for that one document

        :param doc:
            The document as returned from training_docs, validation_docs, or test_docs.
        :param results:
            The results of the requests created in construct_requests.
        """
        # TODO: implement evaluation.
        raise NotImplementedError('Evaluation not implemented')

    def aggregation(self):
        """
        :returns: {str: [float] -> float}
            A dictionary where keys are the names of submetrics and values are 
            functions that aggregate a list of metrics
        """
        # TODO: implement evaluation.
        raise NotImplementedError('Evaluation not implemented')

    def higher_is_better(self):
        """
        :returns: {str: bool}
            A dictionary where keys are the names of submetrics and values are 
            whether a higher value of the submetric is better
        """
        # TODO: implement evaluation.
        raise NotImplementedError('Evaluation not implemented')