import os
import pandas as pd
from glob import glob

# 定义路径
targets_dir = r"D:\PythonProject\Model\output_20250329_140816_results\targets_all_True"
csv_file = r"D:\PythonProject\Model\output_20250329_140816_results\detection_report.csv"
output_csv = r"D:\PythonProject\Model\output_20250329_140816_results\detection_report_updated.csv"

# 获取所有确认的阳性目标文件名
target_files = os.listdir(targets_dir)

# 从目标文件名中提取原始图像名称
confirmed_positives = set()
for target_file in target_files:
    # 提取原始图像名称（去掉时间戳和索引部分）
    parts = target_file.split('_')
    original_name = '_'.join(parts[:-2]) + '.jpg'  # 移除最后的时间戳和索引
    confirmed_positives.add(original_name)

# 读取CSV文件
df = pd.read_csv(csv_file)

# 添加新的标记列
df['Confirmed Positive'] = df['Image File'].apply(lambda x: os.path.basename(x) in confirmed_positives)

# 保存更新后的CSV文件
df.to_csv(output_csv, index=False)

print(f"处理完成！已更新 {len(confirmed_positives)} 个确认的阳性样本。")
print(f"更新后的CSV文件已保存至：{output_csv}")

# 显示统计信息
total_images = len(df)
confirmed_positive_count = df['Confirmed Positive'].sum()
print(f"\n统计信息：")
print(f"总图像数：{total_images}")
print(f"确认阳性数：{confirmed_positive_count}")
print(f"确认阳性比例：{confirmed_positive_count/total_images*100:.2f}%")