Ошибка кодирования при токенизации.Я пытаюсь сделать ссылку учебника Kaggle, приведенную в описании, но получаю некоторую ошибку

Question

Я пытаюсь повторить работу в данном уроке мешок слов с словами - Часть 2 вектора слов , делая это на этапе, который включает в себя «токенизацию».Получаю ошибку кодирования, хотя при загрузке набора данных я уже установил кодировку в utf-8.Я уже пробовал это решение ошибка кодирования

import nltk.data
tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
def review_to_sentences( review, remove_stopwords=False ):
    # 1. Use the NLTK tokenizer to split the paragraph into sentences
    raw_sentences = tokenizer.tokenize(review.strip())
    #raw_sentences = tokenizer.tokenize(review.decode('utf8').strip())

    # 2. Loop over each sentence
    sentences = []
    for raw_sentence in raw_sentences:
         # If a sentence is empty, skip it
         if len(raw_sentence) > 0:
             # Otherwise, call review_to_wordlist to get a list of words
             sentences.append( review_to_wordlist( raw_sentence,remove_stopwords ))

    return sentences 


 #function call
 sentences = []  # Initialize an empty list of sentences
 print ("Parsing sentences from training set")
 for review in train["review"]:
       sentences += review_to_sentences(review )

Это ошибка, которую я получаю

       ---------------------------------------------------------------------------

  TypeError                                 Traceback (most recent call last)
  <ipython-input-60-9241f5864c9f> in <module>()
  2 print ("Parsing sentences from training set")
  3 for review in train["review"]:
  ----> 4     sentences += review_to_sentences(review )

  <ipython-input-59-798565b6a57a> in review_to_sentences(review, remove_stopwords)
   21         if len(raw_sentence) > 0:
   22             # Otherwise, call review_to_wordlist to get a list of words
   ---> 23             sentences.append( review_to_wordlist( raw_sentence,remove_stopwords ))
   24     #
   25     # Return the list of sentences (each sentence is a list of words,

   <ipython-input-58-edff2925e1af> in review_to_wordlist(review, remove_stopwords)
    9     #
   10     # 1. Remove HTML
   ---> 11     review_text = BeautifulSoup(review).get_text()
   12     #
   13     # 2. Remove non-letters

   ~/anaconda3/envs/Py35/lib/python3.5/site-packages/bs4/__init__.py in __init__(self, markup, features, builder, parse_only, from_encoding, exclude_encodings, **kwargs)
   280             self.reset()
   281             try:
   --> 282                 self._feed()
   283                 break
   284             except ParserRejectedMarkup:

   ~/anaconda3/envs/Py35/lib/python3.5/site-packages/bs4/__init__.py in _feed(self)
   341         self.builder.reset()
   342 
   --> 343         self.builder.feed(self.markup)
   344         # Close out any unfinished strings and close all the open tags.
   345         self.endData()

   ~/anaconda3/envs/Py35/lib/python3.5/site-packages/bs4/builder/_html5lib.py in feed(self, markup)
   70             else:
   71                 extra_kwargs['encoding'] = self.user_specified_encoding   
   ---> 72         doc = parser.parse(markup, **extra_kwargs)
   73 
   74         # Set the character encoding detected by the tokenizer.

   ~/anaconda3/envs/Py35/lib/python3.5/site-packages/html5lib/html5parser.py in parse(self, stream, *args, **kwargs)
    287             "diffuseconstant": "diffuseConstant",
    288             "edgemode": "edgeMode",
    --> 289             "externalresourcesrequired": "externalResourcesRequired",
    290             "filterres": "filterRes",
    291             "filterunits": "filterUnits",

   ~/anaconda3/envs/Py35/lib/python3.5/site-packages/html5lib/html5parser.py in _parse(self, stream, innerHTML, container, scripting, **kwargs)
     128 
     129         self.beforeRCDataPhase = None
     --> 130 
     131         self.framesetOK = True
     132 

     ~/anaconda3/envs/Py35/lib/python3.5/site-packages/html5lib/_tokenizer.py in __init__(self, stream, parser, **kwargs)

      ~/anaconda3/envs/Py35/lib/python3.5/site-packages/html5lib/_inputstream.py in HTMLInputStream(source, **kwargs)

    TypeError: __init__() got an unexpected keyword argument 'encoding'