测试代码

import re
import pandas as pd

# 定义函数从字符串中获取第一个数字
def get_first_number(string):
    match = re.match(r'\d+(\.\d+)?', str(string))
    if match:
        return match.group()
    else:
        return None

def load_data(file_path):
    try:
        data = pd.read_csv(file_path)
        return data
    except FileNotFoundError:
        print(f"错误: 文件 {file_path} 未找到。")
        return None
    except Exception as e:
        print(f"错误: 加载文件时发生未知错误: {e}")
        return None

# 假设的文件路径，你需要替换为实际的文件路径
file_path = '/home/xie.zhongwei/workspace/comparison_results.csv'
data = load_data(file_path)

if data is not None:
    def calculate_score(row, column):
        ground_truth = str(row['output_ground_truth'])
        response = str(row[column])
        has_yes_ground_truth = "Yes" in ground_truth
        has_no_ground_truth = "No" in ground_truth

        if has_yes_ground_truth:
            return 1 if "Yes" in response else 0
        elif has_no_ground_truth:
            return 1 if "No" in response else 0
        else:
            return 1 if get_first_number(response) == get_first_number(ground_truth) else 0

    # 计算 response_op 与 output_ground_truth 的得分
    data['score_op'] = data.apply(lambda row: calculate_score(row, 'response_op'), axis=1)

    # 计算 response_nop 与 output_ground_truth 的得分
    data['score_nop'] = data.apply(lambda row: calculate_score(row, 'response_nop'), axis=1)

    # 输出结果
    print(data[['response_op', 'response_nop', 'output_ground_truth', 'score_op', 'score_nop']])