Python '；utf-8'；编解码器可以'；t解码87字2VEC gensim位置的字节0xe3

我有密码

import time
import multiprocessing
from datetime import timedelta
from gensim.models import word2vec
start_time = time.time()
print('Training Word2Vec Model...')
sentences = word2vec.LineSentence('data/data_text.txt')
id_w2v = word2vec.Word2Vec(sentences, size=300, workers=multiprocessing.cpu_count()-1)
id_w2v.save('model_terbaru/word2vec_300.model')

当我制作模型时，我有一个错误

Traceback (most recent call last):

File"<ipython-input-10-fc7016864a34>", line 1, in <module>

        runfile('F:/pa reza/model.py', wdir='F:/pa reza')

File "C:\ProgramData\Anaconda\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 704, in runfile
    execfile(filename, namespace)

File "C:\ProgramData\Anaconda\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 108, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)

File "F:/pa reza/model.py", line 13, in <module>
    iter=10)

---

帮帮我吧……

你把回溯缩短了一点。如果您告诉我们以下哪一行导致了问题，而不仅仅是问题本身，您可能会得到更快的答案。我猜

句子

是

ISO-8859-1

或

ISO-8859-7

编码的或类似的东西。这意味着

id\u w2v.save（）

将无法执行'unicode（文本、编码、错误=错误）`文件

data\u text.txt

是如何获取或创建的？（它可能有一些意外字符编码的数据，最好的修复方法可能是改进创建它的过程。）

 File "C:\ProgramData\Anaconda\lib\site-packages\gensim\models\base_any2vec.py", line 335, in __init__
        self.build_vocab(sentences, trim_rule=trim_rule)

File "C:\ProgramData\Anaconda\lib\site-packages\gensim\models\base_any2vec.py", line 480, in build_vocab
    sentences, progress_per=progress_per, trim_rule=trim_rule)

File "C:\ProgramData\Anaconda\lib\site-packages\gensim\models\word2vec.py", line 1151, in scan_vocab
    for sentence_no, sentence in enumerate(sentences):

File "C:\ProgramData\Anaconda\lib\site-packages\gensim\models\word2vec.py", line 1073, in __iter__
    line = utils.to_unicode(line).split()

File "C:\ProgramData\Anaconda\lib\site-packages\gensim\utils.py", line 359, in any2unicode

return unicode(text, encoding, errors=errors)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe3 in position 87: invalid continuation byte