在window下使用gemsim.models.word2vec.LineSentence加载中文*语料库（已分词）时报如下错误：
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xca in position 0: invalid continuation byte
这种编码问题真的很让人头疼，这种问题都是出现在xxx.decode("utf-8")的时候，所以接下来我们来看看gensim中的源码：
class LineSentence(object):
"""Iterate over a file that contains sentences: one line = one sentence.
Words must be already preprocessed and separated by whitespace. """
def __init__(self, source, max_sentence_length=MAX_WORDS_IN_BATCH, limit=None):
""" Parameters
----------
source : string or a file-like object
Path to the file on disk, or an already-open file object (must support `seek(0)`).
limit : int or None
Clip the file to the first `limit` lines. Do no clipping if `limit is None` (the default). Examples
--------
.. sourcecode:: pycon >>> from gensim.test.utils import datapath
>>> sentences = LineSentence(datapath('lee_background.cor'))
>>> for sentence in sentences:
... pass """
self.source = source
self.max_sentence_length = max_sentence_length
self.limit = limit def __iter__(self):
"""Iterate through the lines in the source."""
try:
# Assume it is a file-like object and try treating it as such
# Things that don't have seek will trigger an exception
self.source.seek(0)
for line in itertools.islice(self.source, self.limit):
line = utils.to_unicode(line).split()
i = 0
while i < len(line):
yield line[i: i + self.max_sentence_length]
i += self.max_sentence_length
except AttributeError:
# If it didn't work like a file, use it as a string filename
with utils.smart_open(self.source) as fin:
for line in itertools.islice(fin, self.limit):
line = utils.to_unicode(line).split()
i = 0
while i < len(line):
yield line[i: i + self.max_sentence_length]
i += self.max_sentence_length
从源码中可以看到__iter__方法让LineSentence成为了一个可迭代的对象，而且文件读取的方法也都定义在__iter__方法中。一般我们输入的source参数都是一个文件路径（也就是一个字符串形式），因此在try时，self.source.seek(0)会报“字符串没有seek方法”的错，所以真正执行的代码是在except中。
接下来我们有两种方法来解决我们的问题：
1）from gensim import utils
utils.samrt_open(url, mode="rb", **kw)
在源码中用utils.smart_open()方法打开文件时默认是用二进制的形式打开的，可以将mode=“rb” 改成mode=“r”。
2）from gensim import utils
utils.to_unicode(text, encoding='utf8', errors='strict')
在源码中在decode("utf8")时，其默认errors=“strict”, 可以将其改成errors="ignore"。即utils.to_unicode(line, errors="ignore")
不过建议大家不要直接在源码上修改，可以直接将源码复制下来，例如：
import logging
import itertools
import gensim
from gensim.models import word2vec
from gensim import utils logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO) class LineSentence(object):
"""Iterate over a file that contains sentences: one line = one sentence.
Words must be already preprocessed and separated by whitespace. """
def __init__(self, source, max_sentence_length=10000, limit=None):
""" Parameters
----------
source : string or a file-like object
Path to the file on disk, or an already-open file object (must support `seek(0)`).
limit : int or None
Clip the file to the first `limit` lines. Do no clipping if `limit is None` (the default). Examples
--------
.. sourcecode:: pycon >>> from gensim.test.utils import datapath
>>> sentences = LineSentence(datapath('lee_background.cor'))
>>> for sentence in sentences:
... pass """
self.source = source
self.max_sentence_length = max_sentence_length
self.limit = limit def __iter__(self):
"""Iterate through the lines in the source."""
try:
# Assume it is a file-like object and try treating it as such
# Things that don't have seek will trigger an exception
self.source.seek(0)
for line in itertools.islice(self.source, self.limit):
line = utils.to_unicode(line).split()
i = 0
while i < len(line):
yield line[i: i + self.max_sentence_length]
i += self.max_sentence_length
except AttributeError:
# If it didn't work like a file, use it as a string filename
with utils.smart_open(self.source, mode="r") as fin:
for line in itertools.islice(fin, self.limit):
line = utils.to_unicode(line).split()
i = 0
while i < len(line):
yield line[i: i + self.max_sentence_length]
i += self.max_sentence_length our_sentences = LineSentence("./zhwiki_token.txt")
model = gensim.models.Word2Vec(our_sentences, size=200, iter=30) # 大语料，用CBOW，适当的增大迭代次数
# model.save(save_model_file)
model.save("./mathWord2Vec" + ".model") # 以该形式保存模型以便之后可以继续增量训练