#! /usr/bin/env python3 import sys import os import subprocess from shutil import which def printUsageAndExit() : print("USAGE : %s file.conllu embeddingsSize"%sys.argv[0], file=sys.stderr) exit(1) if __name__ == "__main__" : if len(sys.argv) != 3 : printUsageAndExit() pathToFile = sys.argv[1] embeddingsSize = int(sys.argv[2]) splited = os.path.splitext(pathToFile) target = splited[0] + ".w2v" if which("word2vec") is None : exit(0) p = subprocess.Popen("word2vec -cbow 0 -size %s -window 10 -negative 5 -hs 0 -sample 1e-1 -threads 2 -binary 0 -iter 15 -min-count 2 -train %s -output %s"%(embeddingsSize, pathToFile, target), stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True) p.wait()