word2vec.py

import gensim
import os
 
os.system("taskset -p 0xff %d" % os.getpid())
 
def read_corpus(path_to_corpus):
    sentences = gensim.models.word2vec.LineSentence(path_to_corpus)
    print("training word2vec...")
    model = gensim.models.Word2Vec(sentences, min_count=10, size=500, window=10, sg=1, workers=4)
    print("finished training word2vec")
    model.save("/mnt/data/word2vec.model")
    
read_corpus("/mnt/data/corpus")