【无标题】

专题4：按车辆ID筛选后将不同文件夹下相同名称的csv文件进行合并_ngsim教程-优快云博客https://blog.youkuaiyun.com/weixin_50632459/article/details/124746073用这个代码没跑出来，用ai改了代码，成功了，分享代码如下：

import pandas as pd
import os
import csv
import time


class FileProcessor:
    def __init__(self, source_path, target_path):
        self.source_path = source_path
        self.target_path = target_path
        self.file_index = {}

    def collect_files(self):
        """
        一次性收集所有 CSV 文件和路径，并根据车辆 ID 组织。
        """
        for root, _, files in os.walk(self.source_path):
            for file in files:
                if file.endswith('.csv'):
                    vehicle_id = self.extract_vehicle_id(file)
                    if vehicle_id is not None:
                        self.file_index.setdefault(vehicle_id, []).append(os.path.join(root, file))

    def extract_vehicle_id(self, filename):
        """
        提取文件名中的车辆 ID。
        """
        try:
            return int(filename.split('.')[0])  # 假设文件名以“车辆ID.csv”格式命名
        except ValueError:
            return None  # 跳过无法提取 ID 的文件

    def process_files(self):
        """
        创建目标路径、合并文件，并删除空文件夹。
        """
        os.makedirs(self.target_path, exist_ok=True)
        for vehicle_id, file_paths in self.file_index.items():
            vehicle_folder = os.path.join(self.target_path, f"Vehicle_{vehicle_id}")
            os.makedirs(vehicle_folder, exist_ok=True)

            combined_file = os.path.join(vehicle_folder, f"{vehicle_id}_combined.csv")
            self.combine_files(file_paths, combined_file)

    def combine_files(self, file_paths, output_file):
        """
        合并多个 CSV 文件到一个目标文件。
        """
        columns = ['Vehicle_ID', 'Frame_ID', 'Total_Frames', 'Global_Time', 'Local_X', 'Local_Y',
                   'Global_X', 'Global_Y', 'v_length', 'v_Width', 'v_Class', 'v_Vel', 'v_Acc',
                   'Lane_ID', 'O_Zone', 'D_Zone', 'Int_ID', 'Section_ID', 'Direction', 'Movement',
                   'Preceding', 'Following', 'Space_Headway', 'Time_Headway', 'Location']

        with open(output_file, "w", newline="", encoding="utf-8") as out_file:
            writer = csv.writer(out_file)
            writer.writerow(columns)  # 写入表头

            for file_path in file_paths:
                try:
                    df = pd.read_csv(file_path)
                    df.to_csv(out_file, header=False, index=False, mode="a")
                except Exception as e:
                    print(f"合并时出错，跳过文件：{file_path}, 错误信息：{e}")

    def delete_empty_folders(self, path):
        """
        删除空文件夹。
        """
        for root, dirs, files in os.walk(path, topdown=False):
            for dir_name in dirs:
                dir_path = os.path.join(root, dir_name)
                if not os.listdir(dir_path):
                    os.rmdir(dir_path)

    def run(self):
        start_time = time.time()
        print("开始收集文件...")
        self.collect_files()
        print(f"文件收集完成，用时：{time.time() - start_time:.2f} 秒")

        print("开始处理文件...")
        self.process_files()
        print(f"文件处理完成，用时：{time.time() - start_time:.2f} 秒")

        print("清理空文件夹...")
        self.delete_empty_folders(self.target_path)
        print(f"清理完成，用时：{time.time() - start_time:.2f} 秒")


if __name__ == "__main__":
    # 设置路径
    source_path = r"C:\Users\DELL\Desktop\NGSIM_data_processing\split_NGSIM_Data\veh_selection_NGSIM_Data_1"
    target_path = r"C:\Users\DELL\Desktop\NGSIM_data_processing\split_NGSIM_Data\veh_combine_NGSIM_Data_2"

    # 实例化并运行
    processor = FileProcessor(source_path, target_path)
    processor.run()