Created
October 31, 2019 10:38
-
-
Save kleysonr/2b414a5aceaf37898e3a86f0f3837dc3 to your computer and use it in GitHub Desktop.
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
import gensim | |
import codecs | |
import logging | |
from nltk.tokenize import word_tokenize | |
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO) | |
def read_data(txtfile): | |
with codecs.open(txtfile, 'r', 'utf-8') as f: | |
for i,line in enumerate (f): | |
if (i%10000==0): | |
logging.info ("read {0} documents".format (i)) | |
t = line.rstrip() | |
yield word_tokenize(t) | |
documents = [line for line in read_data('dataset/preprocessed_data.txt')] | |
model = gensim.models.Word2Vec(documents, size=100, window=5, min_count=1, workers=7) | |
model.train(documents,total_examples=len(documents),epochs=10) | |
# Save embedding file | |
model.wv.save_word2vec_format('embeddings/word2vec-s100.vec') | |
# Save model | |
model.save('models/word2vec-s100.model') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment