Last active
August 23, 2019 22:25
-
-
Save rjurney/f498fda909d91661fae9774a875c79d0 to your computer and use it in GitHub Desktop.
Creating a gensim Word2Vec Encoding
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from os import path | |
from gensim.models import Word2Vec | |
VOCAB_SIZE = 5000 | |
MAX_LENGTH = 100 | |
EMBEDDING_SIZE = 50 | |
NUM_CORES = 64 | |
w2v_model = None | |
model_path = "data/word2vec.50000.model" | |
# Load the Word2Vec model if it exists | |
if path.exists(model_path): | |
w2v_model = Word2Vec.load(model_path) | |
# Otherwise generate it | |
else: | |
w2v_model = Word2Vec( | |
documents, | |
size=EMBEDDING_SIZE, | |
min_count=1, | |
window=10, | |
workers=NUM_CORES, | |
iter=10, | |
seed=33 | |
) | |
w2v_model.save(model_path) | |
print('Word2Vec model built!') | |
# Show that similar words to 'program' print | |
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] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment