python 根据雨滴谱清洗的异常值截断看看这5000多个数据有多少个大于异常值

#!usr/bin/env python
# -*- coding:utf-8 -*-
"""
@author: Suyue
@file: hhh.py
@time: 2025/04/27
@desc:
"""
import os


def find_files_above_threshold(folder_path, threshold=250):
    result_files = set()  # 使用集合避免重复

    # 遍历文件夹中的所有文件
    for filename in os.listdir(folder_path):
        if filename.endswith('.txt'):
            file_path = os.path.join(folder_path, filename)

            try:
                with open(file_path, 'r') as file:
                    lines = file.readlines()

                    # 检查每个数值行
                    for i in range(1, len(lines), 4):
                        if i < len(lines):
                            try:
                                value = float(lines[i].strip())
                                if value > threshold:
                                    result_files.add(filename)
                                    break  # 找到一个就足够，跳出循环检查下一个文件
                            except ValueError:
                                continue
            except Exception as e:
                print(f"处理文件 {filename} 时出错: {e}")
                continue

    return sorted(result_files)  # 返回排序后的列表


# 使用示例
folder_path = 'G:/装备科/论文/03-雨滴谱/雨滴谱数据/物理参量/训练数据（未进行异常值截断）/雨水含量'
threshold = 25
above_threshold_files = find_files_above_threshold(folder_path, threshold)

print(f"数浓度值大于 {threshold} 的文件共有 {len(above_threshold_files)} 个：")
for file in above_threshold_files:
    print(file)