我正在编写一个Python脚本，它可以解析目录中的所有文件夹，并将多个文件夹中的所有数据存储到一个Panda数据框中，然后将数据框保存到CSV文件中，但当我尝试运行此代码时，我会收到一个错误
错误：重新索引仅对唯一值的Index对象有效

import os
import pandas as pd

def read_excel_files_in_folder(folder_path):
    data = []
    for root, dirs, files in os.walk(folder_path):
        for file in files:
            if file.endswith(".xlsx"):
                file_path = os.path.join(root, file)
                df = pd.read_excel(file_path)

                # Remove duplicate rows
                df = df.drop_duplicates()

                # Remove leading and trailing whitespaces from string columns
                df = df.apply(lambda x: x.str.strip() if x.dtype == "O" else x)

                data.append({'File': file_path, 'Data': df})
    return data

def main(input_folder, output_csv):
    # desired column
    columns = [
           # all the column in the excell file 
    ]
    main_df = pd.DataFrame(columns=columns)

    # Read data from all Excel files in the given folder
    data = read_excel_files_in_folder(input_folder)

    # Populate the main DataFrame with the cleaned data
    for entry in data:
        entry_df = pd.DataFrame({'File': [entry['File']], 'Data': [entry['Data']]})

        # Check for duplicates in index
        if main_df.index.duplicated().any():
            main_df.reset_index(drop=True, inplace=True)

        main_df = pd.concat([main_df, entry_df], ignore_index=True)

    # Save the main DataFrame to a CSV file
    main_df.to_csv(os.path.join(output_csv, 'Datalab_output_data.csv'), index=False)

if __name__ == "__main__":
  
    input_folder = r"C:\Users\Edopi\OneDrive\Desktop\2022_2023"

    output_csv = r'C:\Users\Edopi\OneDrive\Desktop\2023-24b-fai1-adsai-EdoardoPierezza231412\Deliverables\Data_lab_preparetion'

    main(input_folder, output_csv)

字符串
我正在编写一个Python脚本，它可以解析目录中的所有文件夹，并将多个文件夹中的所有数据存储到一个panda数据框中，然后将我的数据框保存到csv文件中