python - 有没有因为它的编码方式而运行缓慢的原因？ Python

Question

所以我这里有一些代码可以循环访问一个目录中的 10 个文件。每个文件可能有数千行。然后代码逐行过滤掉这些文件中的一些单词。我知道这可能需要一段时间，但我的代码是否可以以某种方式改进以加快此过程。我是否在某个地方犯了导致瓶颈的编码错误？任何帮助或建议将不胜感激!这是我的代码:

import os

def remove_stop_words(string, stopwords_list):
    string_to_list = string.split()
    x = (' '.join(i for i in string_to_list if i.lower() not in (x.lower() for x in stopwords_list)))
    x = x+'\n'
    return x

def get_stop_words_list(stopwords_path):
    with open(stopwords_path, 'r') as f:
        stopwords = f.read().split()
    return stopwords

def main():
    input_location = 'C:/Users/User/Desktop/mini_mouse'
    output_location = 'C:/Users/User/Desktop/test/'
    stop_words_path = 'C:/Users/User/Desktop/NLTK-stop-word-list.txt'
    stopwords = get_stop_words_list(stop_words_path)
    #print(stopwords)

    for root, dirs, files in os.walk(input_location):
        for name in files:
            file_path = os.path.join(root, name) # joins the new path of the file to the current file in order to access the file
            with open(file_path, 'r') as f: # open the file
                for line in f: # read file line by line
                    x = remove_stop_words(line,stopwords)
                    new_file_path = os.path.join(output_location, name) + '_filtered' # creates a new file of the file that is currenlty being filtered of stopwords
                    with open(new_file_path, 'a') as output_file: # opens output file
                        output_file.write(x) # writes the newly filtered text to the new output file



if __name__ == "__main__":
    main()

Answer 1

这是一个逐个文件而不是逐行写入的解决方案:

for root, dirs, files in os.walk(input_location):
    for name in files:
        file_path = os.path.join(root, name) # joins the new path of the file to the current file in order to access the file

        filestring = ''
        with open(file_path, 'r') as f: # open the file
            for line in f: # read file line by line
                x = remove_stop_words(line,stopwords)
                filestring+=x
                filestring+='\n' #Create new line

        new_file_path = os.path.join(output_location, name) + '_filtered' # creates a new file of the file that is currenlty being filtered of stopwords
        with open(new_file_path, 'a') as output_file: # opens output file
            output_file.write(filestring) # writes the newly filtered text to the new output file