Clean the marked folder

One 、 Preface

It is often used Ai After marking , Many categories are different from what we need .

For example, some boxes have no selected category , So when marking, this box is -1, This needs cleaning before training

There is also the need to delete empty annotation files

For this reason, I simply wrote about cleaning everything in the folder txt Procedure of documents

Two 、 Cleaning procedure

import os
'''  Enter the folder address ：  Output the relative addresses of all files in this folder  '''
def getFilePath(fileDo):
    allFilePath=[]
    for file in os.listdir(fileDo):
        allFilePath.append(os.path.join(fileDo, file))
        #print(file)
    return allFilePath

'''  Enter a list containing file addresses ：  Function to traverse the file and execute the following instructions  1、 Delete the category as -1 The item  2、 Change other categories to specified values k 3、 Delete empty files  '''
def PreData(allFilePath,k):
    for FilePath in allFilePath:
        if FilePath.endswith('txt'):
            tem = []  #  Set category not to -1 Save the items of 
            with open(FilePath, 'r', encoding='utf-8') as f:
                while True:
                    line = f.readline()
                    if line == '':
                        break
                    if line[0] != '-':  # Complete the deletion of category -1 The task of 
                        line=str(k)+line[1:]
                        tem.append(line)
                    else:
                        print(line)
            # If , The text , What can be inserted normally is empty , Just delete the file 
            if len(tem)==0:
                os.remove(FilePath)
                print(' Delete file '+FilePath)
            # If the part is empty, write 
            else:
                with open(FilePath, 'w', encoding='utf-8') as w:
                    for line in tem:
                        w.write(str(line))# Rewrite the previously cached values 

def main():

    #fileDo = './ human beings / human beings - Baidu - Tag data '
    fileDo=input(' Please enter the relative address of the folder to be cleaned ：')
    #print(fileDo)
    #  Output to this folder , The relative address of all files and returned to the variable 
    allFilePath=getFilePath(fileDo)
    print(' All documents in the address are as follows ：')
    print(allFilePath)

    #  Normalize folders 
    PreData(allFilePath,3)

if __name__ =='__main__':
    main()