def compute_precision_recall()

in metrics/cuad/compute_score.py [0:0]

• 36 lines of code
• 21 McCabe index (conditional complexity)

def compute_precision_recall(predictions, ground_truths, qa_id):
    tp, fp, fn = 0, 0, 0

    substr_ok = "Parties" in qa_id

    # first check if ground truth is empty
    if len(ground_truths) == 0:
        if len(predictions) > 0:
            fp += len(predictions)  # false positive for each one
    else:
        for ground_truth in ground_truths:
            assert len(ground_truth) > 0
            # check if there is a match
            match_found = False
            for pred in predictions:
                if substr_ok:
                    is_match = get_jaccard(pred, ground_truth) >= IOU_THRESH or ground_truth in pred
                else:
                    is_match = get_jaccard(pred, ground_truth) >= IOU_THRESH
                if is_match:
                    match_found = True

            if match_found:
                tp += 1
            else:
                fn += 1

        # now also get any fps by looping through preds
        for pred in predictions:
            # Check if there's a match. if so, don't count (don't want to double count based on the above)
            # but if there's no match, then this is a false positive.
            # (Note: we get the true positives in the above loop instead of this loop so that we don't double count
            # multiple predictions that are matched with the same answer.)
            match_found = False
            for ground_truth in ground_truths:
                assert len(ground_truth) > 0
                if substr_ok:
                    is_match = get_jaccard(pred, ground_truth) >= IOU_THRESH or ground_truth in pred
                else:
                    is_match = get_jaccard(pred, ground_truth) >= IOU_THRESH
                if is_match:
                    match_found = True

            if not match_found:
                fp += 1

    precision = tp / (tp + fp) if tp + fp > 0 else np.nan
    recall = tp / (tp + fn) if tp + fn > 0 else np.nan

    return precision, recall