def main():
config = load_config()
with open(os.path.join(config.cooccurrence_dir, "vocab.pkl"), "rb") as f:
vocab = pickle.load(f)
model = GloVe(
vocab_size=config.vocab_size,
embedding_size=config.embedding_size,
x_max=config.x_max,
alpha=config.alpha
)
model.load_state_dict(torch.load(config.output_filepath))
keyed_vectors = KeyedVectors(vector_size=config.embedding_size)
keyed_vectors.add_vectors(
keys=[vocab.get_token(index) for index in range(config.vocab_size)],
weights=(model.weight.weight.detach()
+ model.weight_tilde.weight.detach()).numpy()
)
print("How similar is man and woman:")
print(keyed_vectors.similarity("woman", "man"))
print("How similar is man and apple:")
print(keyed_vectors.similarity("apple", "man"))
print("How similar is woman and apple:")
print(keyed_vectors.similarity("apple", "woman"))
for word in ["computer", "united", "early"]:
print(f"Most similar words of {word}:")
most_similar_words = [word for word, _ in keyed_vectors.similar_by_word(word)]
print(most_similar_words)
def user_eval_similarity(model: KeyedVectors):
ws = input(
"two words to compare for similarity seperated by space: ").split()
similarity = model.similarity(ws[0], ws[1])
print("cosine similarity = {}".format(similarity))
