Encoding tokenized text with gensim.models.Word2Vec

gensim_word2vec.py

from gensim.models import Word2Vec

w2v_model  = None
model_path = f'models/word2vec.model'

# Load the Word2Vec model if it exists
if os.path.exists(model_path):
        w2v_model = Word2Vec.load(model_path)
else:
    w2v_model = Word2Vec(
        documents,
        size=EMBEDDING_SIZE,
        min_count=1,
        window=5,
        workers=NUM_CORES,
        seed=1337
    )
    w2v_model.save(model_path)

# Show that similar words to 'program' print
w2v_model.wv.most_similar(positive='program')

# Encode the documents using the new embedding
encoded_docs = [[w2v_model.wv[word] for word in post] for post in documents]