Similarity of two words in GloVe

Question

How to find similarity of two words in Glove? We have model.similarity(word1, word2) in Word2vec. Is there a similar way in GloVe? How to save and load trained GloVe model?

Answer 1

You can also use scikit-learn

from sklearn.metrics.pairwise import cosine_similarity
cosine_similarity([[1, 0, -1]], [[-1,-1, 0]])
array([[-0.5]])

Answer 2

You can use cosine similarity.

EDIT

You can use SciPy package. Python code for cosine similarity:

from scipy import spatial

word_1 = [3, 45, 7, 2]
word_2 = [2, 54, 13, 15]
result = 1 - spatial.distance.cosine(word_1, word_2)