使用sklearn基于NLP执行TF-IDF时的ValueError

Question

以下是代码：

 import nltk
 import string
 import os

 from sklearn.feature_extraction.text import TfidfVectorizer
 from nltk.stem.porter import PorterStemmer

 path = '/opt/datacourse/data/parts'
 token_dict = {}
 stemmer = PorterStemmer()

 def stem_tokens(tokens, stemmer):
       stemmed = []
       for item in tokens:
             stemmed.append(stemmer.stem(item))
       return stemmed

 def tokenize(text):
       tokens = nltk.word_tokenize(text)
       stems = stem_tokens(tokens, stemmer)
       return stems

 for subdir, dirs, files in os.walk(path):
       for file in files:
             file_path = subdir + os.path.sep + file
             shakes = open(file_path, 'r')
             text = shakes.read()
             lowers = text.lower()
             no_punctuation = lowers.translate(None, string.punctuation)
             token_dict[file] = no_punctuation

tfidf = TfidfVectorizer(tokenizer=tokenize, stop_words='english')
tfs = tfidf.fit_transform(token_dict.values())

跑完后，原来是：

File "D:\Python27\lib\site-packages\sklearn\feature_extraction\text.py", line 751, in _count_vocab
raise ValueError("empty vocabulary; perhaps the documents only"
ValueError: empty vocabulary; perhaps the documents only contain stop words

根据他人的说法＆＃39;回复，我已经chencked text.py并确认min_def = 1中的_init_

有谁能告诉我这是什么问题？非常感谢。