DeepLearningExamples/TensorFlow/LanguageModeling/Transformer-XL/prep_text8.py

#!/usr/bin/env python
# coding=utf-8

# BSD 3-Clause License
#
# Copyright (c) 2017,
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice, this
#   list of conditions and the following disclaimer.
#
# * Redistributions in binary form must reproduce the above copyright notice,
#   this list of conditions and the following disclaimer in the documentation
#   and/or other materials provided with the distribution.
#
# * Neither the name of the copyright holder nor the names of its
#   contributors may be used to endorse or promote products derived from
#   this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

import os
import sys
import zipfile

from io import open

if os.path.exists('train.txt'):
    print('Tokenized text8 already exists - skipping processing')
    sys.exit()

data = zipfile.ZipFile('text8.zip').extractall()
data = open('text8', 'r', encoding='utf-8').read()

print('Length of text8: {}'.format(len(data)))

num_test_chars = 5000000

train_data = data[: -2 * num_test_chars]
valid_data = data[-2 * num_test_chars: -num_test_chars]
test_data = data[-num_test_chars:]

for fn, part in [('train.txt', train_data), ('valid.txt', valid_data), ('test.txt', test_data)]:
    print('{} will have {} bytes'.format(fn, len(part)))
    print('- Tokenizing...')
    # Change space ' ' to underscore '_'
    part_str = ' '.join(['_' if c == ' ' else c for c in part.strip()])
    print('- Writing...')
    f = open(fn, 'w').write(part_str)
    f = open(fn + '.raw', 'w', encoding='utf-8').write(part)