lucko515 / chatbot-startkit Goto Github PK

sentences = {}
with open('cornell movie-dialogs corpus/movie_lines.txt', 'r') as f:
    for line in f.readlines():
        sentences[line.split(' +++$+++ ')[0]] = line.split(' +++$+++ ')[-1].replace('\n', "")

---------------------------------------------------------------------------
UnicodeDecodeError                        Traceback (most recent call last)
<ipython-input-35-66409f9e14a9> in <module>()
      1 sentences = {}
      2 with open('cornell movie-dialogs corpus/movie_lines.txt', 'r') as f:
----> 3     for line in f.readlines():
      4         sentences[line.split(' +++$+++ ')[0]] = line.split(' +++$+++ ')[-1].replace('\n', "")

//anaconda/envs/tensorflow/lib/python3.5/codecs.py in decode(self, input, final)
    319         # decode input (taking the buffer into account)
    320         data = self.buffer + input
--> 321         (result, consumed) = self._buffer_decode(data, self.errors, final)
    322         # keep undecoded input until the next call
    323         self.buffer = data[consumed:]

UnicodeDecodeError: 'utf-8' codec can't decode byte 0xad in position 3767: invalid start byte

---------------------------------------------------------------------------
UnicodeDecodeError                        Traceback (most recent call last)
<ipython-input-38-ae6b005fad2b> in <module>()
      4 with open('movie_questions_2.txt', 'r', encoding='utf-8') as f:
      5 
----> 6     lines = f.readlines()
      7 
      8     for text in lines:

//anaconda/envs/tensorflow/lib/python3.5/codecs.py in decode(self, input, final)
    319         # decode input (taking the buffer into account)
    320         data = self.buffer + input
--> 321         (result, consumed) = self._buffer_decode(data, self.errors, final)
    322         # keep undecoded input until the next call
    323         self.buffer = data[consumed:]

UnicodeDecodeError: 'utf-8' codec can't decode byte 0xad in position 1085: invalid start byte