SpaCy:如何加载 Google 新闻 word2vec 向量? [英] SpaCy: how to load Google news word2vec vectors?

问题描述

我尝试了几种加载谷歌新闻 word2vec 向量的方法(https://code.google.com/archive/p/word2vec/):

I've tried several methods of loading the google news word2vec vectors (https://code.google.com/archive/p/word2vec/):

en_nlp = spacy.load('en',vector=False)
en_nlp.vocab.load_vectors_from_bin_loc('GoogleNews-vectors-negative300.bin')

以上给出:

MemoryError: Error assigning 18446744072820359357 bytes

我也尝试过使用 .gz 压缩向量；或者通过 gensim 加载并保存它们为新格式:

I've also tried with the .gz packed vectors; or by loading and saving them with gensim to a new format:

from gensim.models.word2vec import Word2Vec
model = Word2Vec.load_word2vec_format('GoogleNews-vectors-negative300.bin', binary=True)
model.save_word2vec_format('googlenews2.txt')

这个文件然后在每一行包含单词和它们的词向量.我试图加载它们:

This file then contains the words and their word vectors on each line. I tried to load them with:

en_nlp.vocab.load_vectors('googlenews2.txt')

但它返回0".

这样做的正确方法是什么?

What is the correct way to do this?

更新:

我可以将自己创建的文件加载到 spacy 中.我在每一行使用一个带有string 0.0 0.0 ...."的 test.txt 文件.然后用 .bzip2 将这个 txt 压缩到 test.txt.bz2.然后我创建了一个兼容 spacy 的二进制文件:

I can load my own created file into spacy. I use a test.txt file with "string 0.0 0.0 ...." on each line. Then zip this txt with .bzip2 to test.txt.bz2. Then I create a spacy compatible binary file:

spacy.vocab.write_binary_vectors('test.txt.bz2', 'test.bin')

我可以加载到 spacy:

That I can load into spacy:

nlp.vocab.load_vectors_from_bin_loc('test.bin')

这有效！但是，当我对 googlenews2.txt 执行相同的过程时，出现以下错误:

This works! However, when I do the same process for the googlenews2.txt, I get the following error:

lib/python3.6/site-packages/spacy/cfile.pyx in spacy.cfile.CFile.read_into (spacy/cfile.cpp:1279)()

OSError: 

推荐答案

对于 spacy 1.x，将 Google 新闻向量加载到 gensim 并转换为新格式(.txt 中的每一行都包含一个向量:string, vec):

For spacy 1.x, load Google news vectors into gensim and convert to a new format (each line in .txt contains a single vector: string, vec):

from gensim.models.word2vec import Word2Vec
from gensim.models import KeyedVectors
model = KeyedVectors.load_word2vec_format('GoogleNews-vectors-negative300.bin', binary=True)
model.wv.save_word2vec_format('googlenews.txt')

删除.txt的第一行:

Remove the first line of the .txt:

tail -n +2 googlenews.txt > googlenews.new && mv -f googlenews.new googlenews.txt

将txt压缩为.bz2:

Compress the txt as .bz2:

bzip2 googlenews.txt

创建一个 SpaCy 兼容的二进制文件:

Create a SpaCy compatible binary file:

spacy.vocab.write_binary_vectors('googlenews.txt.bz2','googlenews.bin')

将 googlenews.bin 移动到您的 Python 环境的/lib/python/site-packages/spacy/data/en_google-1.0.0/vocab/googlenews.bin.

Move the googlenews.bin to /lib/python/site-packages/spacy/data/en_google-1.0.0/vocab/googlenews.bin of your python environment.

然后加载词向量:

import spacy
nlp = spacy.load('en',vectors='en_google')

或稍后加载它们:

nlp.vocab.load_vectors_from_bin_loc('googlenews.bin')

这篇关于SpaCy:如何加载 Google 新闻 word2vec 向量?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！