def compute_f1_from_tokens()

in utils/evaluate_qa.py [0:0]

• 11 lines of code
• 5 McCabe index (conditional complexity)

def compute_f1_from_tokens(gold_toks: List[str], pred_toks: List[str]) -> float:
    """Compute the F1 score from tokenized gold answer and prediction."""
    common = collections.Counter(gold_toks) & collections.Counter(pred_toks)
    num_same = sum(common.values())

    if len(gold_toks) == 0 or len(pred_toks) == 0:
        # If either is no-answer, then F1 is 1 if they agree, 0 otherwise
        return int(gold_toks == pred_toks)

    if num_same == 0:
        return 0

    precision = 1.0 * num_same / len(pred_toks)
    recall = 1.0 * num_same / len(gold_toks)
    f1 = (2 * precision * recall) / (precision + recall)
    return f1