如何找到特定单词的TF-IDF？

Question

我有5个名为1500.txt，1600.txt ..... 1900.txt的文本文件。使用Python我从1500.txt中选择了200个最常用的单词，并将这些单词与其他文本文件进行了比较。我的代码如下： -

common_words_1500 = Counter()

 with open('E:\\Book\\1500.txt', "r", encoding='ISO-8859-1') as File_1500:
    stop_words = set(nltk.corpus.stopwords.words('english'))
    words = word_tokenize(File_1500.read())
    filtered_sentence = [w for w in words if not w.lower() in stop_words]


for line in filtered_sentence:
    for match in re.finditer(r'\w+', line.lower()):
        word = match.group()
        st=word.strip('_')
        if len(st) > 3:
            common_words_1500[st] += 1

common_words_1600 = Counter()

 with open('E:\\Book\\1600.txt', "r", encoding='ISO-8859-1') as File_1600:
    for line in File_1600:
      for match in re.finditer(r'\w+', line.lower()):
        word = match.group()
        if len(word) > 3:
            common_words_1600[word] += 1

common_words_1700 = Counter()

 with open('E:\\Book\\1700.txt', "r", encoding='ISO-8859-1') as File_1700:
   for line in File_1700:
    for match in re.finditer(r'\w+', line.lower()):
        word = match.group()
        if len(word) > 3:
            common_words_1700[word] += 1

common_words_1800 = Counter()

 with open('E:\\Book\\1800.txt', "r", encoding='ISO-8859-1') as File_1800:
   for line in File_1800:
    for match in re.finditer(r'\w+', line.lower()):
        word = match.group()
        if len(word) > 3:
            common_words_1800[word] += 1


common_words_1900 = Counter()

 with open('E:\\Book\\1900.txt', "r", encoding='ISO-8859-1') as File_1900:
   for line in File_1900:
    for match in re.finditer(r'\w+', line.lower()):
        word = match.group()
        if len(word) > 3:
            common_words_1900[word] += 1

for (word, count) in common_words_1500.most_common(200):
   try: 
    count_in_file2 = common_words_1600[word]
    count_in_file3 = common_words_1700[word]
    count_in_file4 = common_words_1800[word]
    count_in_file5 = common_words_1900[word]

   except KeyError: 
    # if the word is not present file2_common_words,
    # then its count is 0.
    count_in_file2 = 0
    count_in_file3 = 0
    count_in_file4 = 0
    count_in_file5 = 0

print("{0}\t{1}\t{2}\t{3}\t{4}\t{5}".format(word, count, count_in_file2,       
count_in_file3, count_in_file4, count_in_file5))

现在问题是，我想从每个文本文件计算这200个单词的TF-IDF。我希望你们都理解我的问题。