def extract_answer_map()

in evaluation/parser.py [0:0]

• 63 lines of code
• 25 McCabe index (conditional complexity)

def extract_answer_map(x, data_name, col = "pred", use_last_number=True):
    pred_str = x[col]
    pred_str = pred_str.replace("\u043a\u0438", "")
    if data_name in ["mmlu_stem", "sat_math", "aqua", "gaokao2023"]:
        # TODO check multiple choice
        return choice_answer_clean(pred_str)

    if "final answer is $" in pred_str and "$. I hope" in pred_str:
        # minerva_math
        tmp = pred_str.split("final answer is $", 1)[1]
        pred = tmp.split("$. I hope", 1)[0].strip()
    elif "boxed" in pred_str:
        ans = pred_str.split("boxed")[-1]
        if len(ans) == 0:
            a = ""
        elif ans[0] == "{":
            stack = 1
            a = ""
            for c in ans[1:]:
                if c == "{":
                    stack += 1
                    a += c
                elif c == "}":
                    stack -= 1
                    if stack == 0:
                        break
                    a += c
                else:
                    a += c
        else:
            a = ans.split("$")[0].strip()
        pred = a
    elif "he answer is" in pred_str:
        pred = pred_str.split("he answer is")[-1].strip()
    elif "final answer is" in pred_str:
        pred = pred_str.split("final answer is")[-1].strip()
    elif "答案是" in pred_str:
        # Handle Chinese few-shot multiple choice problem answer extraction
        pred = pred_str.split("答案是")[1].strip().split("\n\n")[0].strip()
    else:  # use the last number
        if use_last_number:
            pattern = "-?\d*\.?\d+"
            pred = re.findall(pattern, pred_str.replace(",", ""))
            if len(pred) >= 1:
                pred = pred[-1]
            else:
                pred = ""
        else:
            pred = ""

    # choice answer
    if (
        data_name in ["sat_math", "aqua"]
        or "mmlu" in data_name
    ):
        tmp = re.findall(r"\b(A|B|C|D|E)\b", pred.upper())
        if tmp:
            pred = tmp[-1]
        else:
            pred = pred.strip().strip(".")

    # multiple line
    # pred = pred.split("\n")[0]
    pred = re.sub(r"\n\s*", "", pred)
    if pred != "" and pred[0] == ":":
        pred = pred[1:]
    if pred != "" and pred[-1] == ".":
        pred = pred[:-1]
    if pred != "" and pred[-1] == "/":
        pred = pred[:-1]
    pred = strip_string(pred, skip_unit=data_name in ["carp_en", "minerva_math"])
    return {"pred": pred}