Question

我正在尝试使用Gensim库建立模型。我正在使用python 3和Spyder。我也想加入维基语料库。代码如下所示：

enter code hereimport os
import sys
import bz2
import logging
import multiprocessing
import gensim

SCRIPT_PATH = os.path.dirname(os.path.realpath(__file__))
DATA_PATH   = os.path.join(SCRIPT_PATH, 'data/')
MODEL_PATH  = os.path.join(SCRIPT_PATH, 'model/')

DICTIONARY_FILEPATH = os.path.join(DATA_PATH, 'wiki-english_wordids.txt.bz2')
WIKI_DUMP_FILEPATH = os.path.join(DATA_PATH, 'enwiki-latest-pages- 
articles.xml.bz2')

if __name__ == '__main__':

# Check if the required files have been downloaded
if not WIKI_DUMP_FILEPATH:
    print('Wikipedia articles dump could not be found..')
    print('Please see README.md for instructions!')
    sys.exit()


# Get number of available cpus
cores = multiprocessing.cpu_count()

if not os.path.exists(MODEL_PATH):
    os.makedirs(MODEL_PATH)

# Initialize logging
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)

if not os.path.isfile(DICTIONARY_FILEPATH):
    logging.info('Dictionary has not been created yet..')
    logging.info('Creating dictionary (takes about 9h)..')

    # Construct corpus
    wiki = gensim.corpora.WikiCorpus(WIKI_DUMP_FILEPATH)

    # Remove words occuring less than 20 times, and words occuring in more
    # than 10% of the documents. (keep_n is the vocabulary size)
    wiki.dictionary.filter_extremes(no_below=20, no_above=0.1, keep_n=100000)

    # Save dictionary to file
    wiki.dictionary.save_as_text(DICTIONARY_FILEPATH)
    del wiki

# Load dictionary from file
dictionary = gensim.corpora.Dictionary.load_from_text(DICTIONARY_FILEPATH)

# Construct corpus using dictionary
wiki = gensim.corpora.WikiCorpus(WIKI_DUMP_FILEPATH, dictionary=dictionary)

class SentencesIterator:
    def __init__(self, wiki):
        self.wiki = wiki

    def __iter__(self):
        for sentence in self.wiki.get_texts():
            yield list(map(lambda x: x.decode('utf-8'), sentence))

# Initialize simple sentence iterator required for the Word2Vec model
sentences = SentencesIterator(wiki)

logging.info('Training word2vec model..')
model = gensim.models.Word2Vec(sentences=sentences, size=300, min_count=1, window=5, workers=cores)

# Save model
logging.info('Saving model..')
model.save(os.path.join(MODEL_PATH, 'word2vec.model'))
logging.info('Done training word2vec model!')

但是我遇到以下错误：

File "C:/Users/elli/.spyder-py3/temp.py", line 60, in <lambda>
yield list(map(lambda x: x.decode('utf-8'), sentence))

AttributeError: 'str' object has no attribute 'decode'

这段代码来自github的链接： https://github.com/LasseRegin/gensim-word2vec-model/blob/master/train.py。

我怀疑这应该是简单的排序。你能请教吗？

Answer 1

这是类SentencesIterator中的Unicode问题，您的示例代码适用于python2。对于python3，您可以删除解码部分并使它如下：

class TaggedWikiDocument(object):
    def __init__(self, wiki):
        self.wiki = wiki
        self.wiki.metadata = True
    def __iter__(self):
        for content, (page_id, title) in self.wiki.get_texts():
            yield TaggedDocument(content, [title])

Gensim Doc2Vec异常AttributeError：'str'对象没有属性'decode'

1 个答案: