UnicodeDecodeError：'ascii'编解码器无法解码，使用gensim，python3.5

我在Windows和Linux上都使用python 3.5但是得到了同样的错误：UnicodeDecodeError：'ascii'编解码器无法解码位置0中的字节0xc1：序号不在范围内（128）错误日志如下：重载模块：lazylinker_ext Traceback（最近一次调用最后一次）：

File "<ipython-input-2-d60a2349532e>", line 1, in <module>
    runfile('C:/Users/YZC/Google     Drive/sunday/data/RA/data_20100101_20150622/w2v_coherence.py',     wdir='C:/Users/YZC/Google Drive/sunday/data/RA/data_20100101_20150622')

  File "C:\Users\YZC\Anaconda3\lib\site-    packages\spyderlib\widgets\externalshell\sitecustomize.py", line 699, in runfile
    execfile(filename, namespace)

  File "C:\Users\YZC\Anaconda3\lib\site-    packages\spyderlib\widgets\externalshell\sitecustomize.py", line 88, in execfile
    exec(compile(open(filename, 'rb').read(), filename, 'exec'), namespace)

  File "C:/Users/YZC/Google     Drive/sunday/data/RA/data_20100101_20150622/w2v_coherence.py", line 70, in     <module>
    model = gensim.models.Word2Vec.load('model_all_no_lemma')

  File "C:\Users\YZC\Anaconda3\lib\site-packages\gensim\models\word2vec.py",     line 1485, in load
    model = super(Word2Vec, cls).load(*args, **kwargs)

  File "C:\Users\YZC\Anaconda3\lib\site-packages\gensim\utils.py", line 248,     in load
    obj = unpickle(fname)

  File "C:\Users\YZC\Anaconda3\lib\site-packages\gensim\utils.py", line 912, in unpickle
    return _pickle.loads(f.read())

UnicodeDecodeError: 'ascii' codec can't decode byte 0xc1 in position 0:     ordinal not in range(128)

1.我检查并发现默认的解码方法是utf-8：import sys sys.getdefaultencoding（）Out [2]：'utf-8'

• 读取文件时，我还添加了.decode（'utf-8'）

• 我在开头添加了shepang行并声明了utf-8所以我真的不知道为什么python无法读取该文件 . 有人可以帮帮我吗？

这是代码：

# -*- coding: utf-8 -*-
import gensim
import csv
import numpy as np
import math
import string
from nltk.corpus import stopwords, wordnet
from nltk.stem import WordNetLemmatizer
from textblob import TextBlob, Word



class SpeechParser(object):

    def __init__(self, filename):
        self.filename = filename
        self.lemmatize = WordNetLemmatizer().lemmatize
        self.cached_stopwords = stopwords.words('english')

    def __iter__(self):

        with open(self.filename, 'rb', encoding='utf-8') as csvfile:
            file_reader = csv.reader(csvfile, delimiter=',', quotechar='|', )
            headers = file_reader.next()
            for row in file_reader:
                parsed_row = self.parse_speech(row[-2])
                yield parsed_row

    def parse_speech(self, row):

        speech_words =  row.replace('\r\n', ' ').strip().lower().translate(None, string.punctuation).decode('utf-8', 'ignore')         

        return speech_words.split()

    # -- source: https://github.com/prateekpg2455/U.S-Presidential-    Speeches/blob/master/speech.py --
    def pos(self, tag):
        if tag.startswith('J'):
            return wordnet.ADJ
        elif tag.startswith('V'):
            return wordnet.VERB
        elif tag.startswith('N'):
            return wordnet.NOUN
        elif tag.startswith('R'):
            return wordnet.ADV
        else:
            return ''

if __name__ == '__main__':

    # instantiate object
    sentences = SpeechParser("sample.csv")

    # load an existing model
    model = gensim.models.Word2Vec.load('model_all_no_lemma')



    print('\n-----------------------------------------------------------')
    print('MODEL:\t{0}'.format(model))

    vocab = model.vocab

    # print log-probability of first 10 sentences
    row_count = 0
    print('\n------------- Scores for first 10 documents: -------------')
    for doc in sentences: 
        print(sum(model.score(doc))/len(doc))
        row_count += 1
        if row_count > 10:
            break
    print('\n-----------------------------------------------------------')