Quick reference on how to work with pre-trained word2vec vectors in Python.

wordvec_example.py

# wordvec_example.py
#
# This file shows one way to work with word2vec data in Python.
#
# Setup:
#
# 1. Install gensim:
#
#     pip install gensim
#
# 2. Download 
#
# Use your favorite download tool (eg curl, wget, your browser) to d/l from:
# https://drive.google.com/file/d/0B7XkCwpI5KDYNlNUTTlSS21pQmM/edit?usp=sharing
#
# That ought to give you a file called GoogleNews-vectors-negative300.bin, which
# you can put anywhere you like; this code assumes it lives in '~/Downloads'.
#

import gensim
filepath = '~/Downloads/GoogleNews-vectors-negative300.bin'
model = gensim.models.KeyedVectors.load_word2vec_format(filepath, binary=True)

# As an example, print out words similar to 'chicken':
print(model.most_similar(positive=['chicken']))

# Docs covering some methods of `model` are here:
# https://radimrehurek.com/gensim/models/keyedvectors.html#gensim.models.keyedvectors.EuclideanKeyedVectors