erickrf

import json
import os
import argparse

parser = argparse.ArgumentParser()
parser.add_argument('input_dir', help='Directory with wiki json files')
parser.add_argument('output', help='Txt file output')
args = parser.parse_args()

for filename in os.listdir(args.input_dir):

erickrf

import argparse
from collections import defaultdict

parser = argparse.ArgumentParser()
parser.add_argument('input', 
                    help='Input file in CoNLLU format')
parser.add_argument('-u', action='store_true', dest='upos', 
                    help='Use UPOS to disambiguate')
parser.add_argument('-x', action='store_true', dest='xpos',
                    help='Use XPOS to disambiguate')

erickrf

# -*- coding: utf-8 -*-

'''
Functions to read the OpenWordnetPT from RDF files and provide
access to it.
'''

import rdflib
from six.moves import cPickle

erickrf

import numpy as	np
import argparse

parser = argparse.ArgumentParser()
parser.add_argument('input', help='Single embedding file')
parser.add_argument('output', help='Output basename without extension')
args = parser.parse_args()

embeddings_file = args.output + '.npy'
vocabulary_file = args.output + '.txt'

erickrf

# -*- coding: utf-8 -*-

from __future__ import unicode_literals
from nltk.tokenize import RegexpTokenizer
import argparse
import os

"""
Script for tokenizing Portuguese text according to the Universal Dependencies
(UD) tokenization standards. This script was not created by the UD team; it was