如何从word2vec的Google预训练模型中提取单词向量？

Question

The file GoogleNews-vectors-negative300.bin contains 300 million word-vectors. I think (not sure) this file is loaded when the following line is written:

from gensim.models.keyedvectors import KeyedVectors

I want to download the vectors for words that I give externally in a list called words . This is my code to do this:

import math
import sys
import gensim
import warnings
warnings.filterwarnings(action='ignore', category=UserWarning, module='gensim')

from gensim.models.keyedvectors import KeyedVectors

words = ['access', 'aeroway', 'airport', 'amenity', 'area', 'atm', 'barrier', 'bay', 'bench', 'boundary', 'bridge', 'building', 'bus', 'cafe', 'car', 'coast', 'continue', 'created', 'defibrillator', 'drinking', 'ele', 'embankment', 'entrance', 'ferry', 'foot', 'fountain', 'fuel', 'gate', 'golf', 'gps', 'grave', 'highway', 'horse', 'hospital', 'house', 'landuse', 'layer', 'leisure', 'man', 'manmade', 'market', 'marketplace', 'maxheight', 'name', 'natural', 'noexit', 'oneway', 'park', 'parking', 'pgs', 'place', 'worship', 'playground', 'police', 'police station', '', 'post', 'post box or mail', 'power', 'powerstation', 'private', 'public', 'railway', 'ref', 'residential', 'restaurant', 'road', 'route', 'school', 'shelter', 'shop', 'source', 'sport', 'toilet', 'toilets', 'tourism', 'unknown', 'vehicle', 'vending', 'vending machine', 'village', 'wall', 'waste', 'water', 'waterway', 'worship'];

model = gensim.models.KeyedVectors.load_word2vec_format(words, binary=True)

M = len(words)
count = 0
for i in range(1,M):
    wi = id2word[words[i]]
    if wi in word2vec.vocab:
        vector[:,count] = model[:,i]
        count = count+1

f = open('word_vectors.csv', 'w')
print(vector, file=f)
f.close()

But when I run the code, it just freezes up my system. Is it because it is loading the whole of the binary file before searching for the words in words ? If yes, how do I get around this issue? I think of this as I get the following warning, which is why I use the warning package to suppress it:

c:\Python35\lib\site-packages\gensim\utils.py:860: UserWarning: detected Windows; aliasing chunkize to chunkize_serial
  warnings.warn("detected Windows; aliasing chunkize to chunkize_serial")

And the error it gives is:

Traceback (most recent call last):
  File "word2vec.py", line 18, in <module>
    model = gensim.models.KeyedVectors.load_word2vec_format(topic, binary=True) 
  File "c:\Python35\lib\site-packages\gensim\models\keyedvectors.py", line 196, in load_word2vec_format
    with utils.smart_open(fname) as fin:
  File "c:\Python35\lib\site-packages\smart_open\smart_open_lib.py", line 208, in smart_open
    raise TypeError('don\'t know how to handle uri %s' % repr(uri))
TypeError: don't know how to handle uri [['access'], ['aeroway'], ['airport'], ['amenity'], ['area'], ['atm'], ['barrier'], ['bay'], ['bench'], ['boundary'], ['bridge'], ['building'], ['bus'], ['cafe'], ['car'], ['coast'], ['continue'], ['created'], ['defibrillator'], ['drinking'], ['ele'], ['embankment'], ['entrance'], ['ferry'], ['foot'], ['fountain'], ['fuel'], ['gate'], ['golf'], ['gps'], ['grave'], ['highway'], ['horse'], ['hospital'], ['house'], ['landuse'], ['layer'], ['leisure'], ['man'], ['manmade'], ['market'], ['marketplace'], ['maxheight'], ['name'], ['natural'], ['noexit'], ['oneway'], ['park'], ['parking'], ['pgs'], ['place'], ['worship'], ['playground'], ['police'], ['police station'], [''], ['post'], ['post box or mail'], ['power'], ['powerstation'], ['private'], ['public'], ['railway'], ['ref'], ['residential'], ['restaurant'], ['road'], ['route'], ['school'], ['shelter'], ['shop'], ['source'], ['sport'], ['toilet'], ['toilets'], ['tourism'], ['unknown'], ['vehicle'], ['vending'], ['vending machine'], ['village'], ['wall'], ['waste'], ['water'], ['waterway'], ['worship']]

This I guess means that the program is not able to search for the words in the binary file. So, how to solve it?

Answer 1

Use the following code to extract the word vector from the Google trained model for word2vec:

import math
import sys
import gensim
import warnings
warnings.filterwarnings(action='ignore', category=UserWarning, module='gensim')

# this line doesn't load the trained model 
from gensim.models.keyedvectors import KeyedVectors

words = ['access', 'aeroway', 'airport']

# this is how you load the model
model = KeyedVectors.load_word2vec_format(path_to_model, binary=True)

# to extract word vector
print(model[words[0]])  #access

Result vector:

[ -8.74023438e-02  -1.86523438e-01 .. ]

Your system is freezing because of the large size of model. Try using system with more memory or you can limit the size of model you are loading.

Limit model size while loading

model = KeyedVectors.load_word2vec_format(path_to_model, binary=True, limit=20000)