Function compute_metrics

advanced_source/semi_structured_sparse.py:299–356

(start_logits, end_logits, features, examples)

def compute_metrics(start_logits, end_logits, features, examples):
    n_best = 20
    max_answer_length = 30
    metric = evaluate.load("squad")

    example_to_features = collections.defaultdict(list)
    for idx, feature in enumerate(features):
        example_to_features[feature["example_id"]].append(idx)

    predicted_answers = []
    # for example in ``tqdm`` (examples):
    for example in examples:
        example_id = example["id"]
        context = example["context"]
        answers = []

        # Loop through all features associated with that example
        for feature_index in example_to_features[example_id]:
            start_logit = start_logits[feature_index]
            end_logit = end_logits[feature_index]
            offsets = features[feature_index]["offset_mapping"]

            start_indexes = np.argsort(start_logit)[-1 : -n_best - 1 : -1].tolist()
            end_indexes = np.argsort(end_logit)[-1 : -n_best - 1 : -1].tolist()
            for start_index in start_indexes:
                for end_index in end_indexes:
                    # Skip answers that are not fully in the context
                    if offsets[start_index] is None or offsets[end_index] is None:
                        continue
                    # Skip answers with a length that is either < 0
                    # or > max_answer_length
                    if (
                        end_index < start_index
                        or end_index - start_index + 1 > max_answer_length
                    ):
                        continue

                    answer = {
                        "text": context[
                            offsets[start_index][0] : offsets[end_index][1]
                        ],
                        "logit_score": start_logit[start_index] + end_logit[end_index],
                    }
                    answers.append(answer)

        # Select the answer with the best score
        if len(answers) > 0:
            best_answer = max(answers, key=lambda x: x["logit_score"])
            predicted_answers.append(
                {"id": example_id, "prediction_text": best_answer["text"]}
            )
        else:
            predicted_answers.append({"id": example_id, "prediction_text": ""})

    theoretical_answers = [
        {"id": ex["id"], "answers": ex["answers"]} for ex in examples
    ]
    return metric.compute(predictions=predicted_answers, references=theoretical_answers)