datasets.py [227:271]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return res

    def evaluate_dataset(self, data_args: DataTrainingArguments, model, device, batch_size: int, macro: bool = False) \
            -> Dict[str, float]:
        """
        Evaluate model on this dataset.
        """
        results = Counter()

        for example, output_sentence in self.generate_output_sentences(data_args, model, device, batch_size):
            new_result = self.evaluate_example(
                    example=example,
                    output_sentence=output_sentence,
                    model=model,
                    tokenizer=self.tokenizer,
                )
            results += new_result

        entity_precision, entity_recall, entity_f1 = get_precision_recall_f1(
            num_correct=results['correct_entities'],
            num_predicted=results['predicted_entities'],
            num_gt=results['gt_entities'],
        )

        entity_precision_no_type, entity_recall_no_type, entity_f1_no_type = get_precision_recall_f1(
            num_correct=results['correct_entities_no_type'],
            num_predicted=results['predicted_entities_no_type'],
            num_gt=results['gt_entities_no_type'],
        )

        entity_precision_by_type = []
        entity_recall_by_type = []
        entity_f1_by_type = []

        if macro:
            # compute also entity macro scores
            for entity_type in self.entity_types.values():
                precision, recall, f1 = get_precision_recall_f1(
                    num_correct=results['correct_entities', entity_type.natural],
                    num_predicted=results['predicted_entities', entity_type.natural],
                    num_gt=results['gt_entities', entity_type.natural],
                )
                entity_precision_by_type.append(precision)
                entity_recall_by_type.append(recall)
                entity_f1_by_type.append(f1)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



datasets.py [889:933]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return res

    def evaluate_dataset(self, data_args: DataTrainingArguments, model, device, batch_size: int, macro: bool = False) \
            -> Dict[str, float]:
        """
        Evaluate model on this dataset.
        """
        results = Counter()

        for example, output_sentence in self.generate_output_sentences(data_args, model, device, batch_size):
            new_result = self.evaluate_example(
                    example=example,
                    output_sentence=output_sentence,
                    model=model,
                    tokenizer=self.tokenizer,
                )
            results += new_result

        entity_precision, entity_recall, entity_f1 = get_precision_recall_f1(
            num_correct=results['correct_entities'],
            num_predicted=results['predicted_entities'],
            num_gt=results['gt_entities'],
        )

        entity_precision_no_type, entity_recall_no_type, entity_f1_no_type = get_precision_recall_f1(
            num_correct=results['correct_entities_no_type'],
            num_predicted=results['predicted_entities_no_type'],
            num_gt=results['gt_entities_no_type'],
        )

        entity_precision_by_type = []
        entity_recall_by_type = []
        entity_f1_by_type = []

        if macro:
            # compute also entity macro scores
            for entity_type in self.entity_types.values():
                precision, recall, f1 = get_precision_recall_f1(
                    num_correct=results['correct_entities', entity_type.natural],
                    num_predicted=results['predicted_entities', entity_type.natural],
                    num_gt=results['gt_entities', entity_type.natural],
                )
                entity_precision_by_type.append(precision)
                entity_recall_by_type.append(recall)
                entity_f1_by_type.append(f1)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -