如何从一个文件夹中的1000个txt文件执行TF IDF？

Question

import nltk
from nltk.corpus import PlaintextCorpusReader
from sklearn.feature_extraction.text import TfidfVectorizer
import pandas as pd

#file directory, contains 1000 files
doc_dirname_politics = "E:/s10/SENTIMENT ANALISYS/SESI3/NLP-Data-sets/Dats sets/mini_newsgroups/mini_newsgroups/talk.politics.misc"
doc_dirname_comps = "E:/s10/SENTIMENT ANALISYS/SESI3/NLP-Data-sets/Dats sets/mini_newsgroups/mini_newsgroups/comp.os.ms-windows.misc"

politics_news_corpus = PlaintextCorpusReader(doc_dirname_politics,'.*')

comp_news_corpus = PlaintextCorpusReader(doc_dirname_comps, '.*')

import re
from nltk.stem.porter import PorterStemmer

stemmer = PorterStemmer()
from nltk.corpus import stopwords 
stop_words = set(stopwords.words('english'))
from nltk.stem import WordNetLemmatizer 
lemmatizer = WordNetLemmatizer() 

def custom_preprocessor(text):
    text = re.sub(r'\W+|\d+|_', ' ', text)    #removing numbers and 
    punctuations
    text = nltk.word_tokenize(text)       #tokenizing
    text = [word for word in text if not word in stop_words] #English 
    Stopwords
    text = [lemmatizer.lemmatize(word) for word in text]              
    return text

这就是源代码。如果要在TF IDF中实例化的文件中执行doc_dirname_politics，该使用哪种代码。我已经找到了该教程，但是没有找到可以解决我问题的教程。