def _step_init(self,
bilingual_corpora,
monolingual_corpora,
skip=False,
logger=None,
delete_on_exit=False):
training_folder = self._get_tempdir('training_corpora')
# if skip is true, then we are in resume mode, so return the already existing results
if skip:
bilingual_corpora, monolingual_corpora = BilingualCorpus.splitlist(
self._engine.source_lang,
self._engine.target_lang,
roots=training_folder)
# else perform the baseline domains extraction and domain mapping, and return its result
else:
domains = self._engine.db.insert(bilingual_corpora)
bilingual_corpora = [
domain.corpus.symlink(training_folder, name=str(domain.id))
for domain in domains
]
monolingual_corpora = [
corpus.symlink(training_folder)
for corpus in monolingual_corpora
]
return bilingual_corpora, monolingual_corpora
def _step_preprocess(self,
bilingual_corpora,
monolingual_corpora,
_,
skip=False,
logger=None,
delete_on_exit=False):
preprocessed_folder = self._get_tempdir('preprocessed')
cleaned_folder = self._get_tempdir('clean_corpora')
# if skip is true, then we are in resume mode, so return the already existing results
if skip:
processed_bicorpora, processed_monocorpora = BilingualCorpus.splitlist(
self._engine.source_lang,
self._engine.target_lang,
roots=preprocessed_folder)
cleaned_bicorpora = BilingualCorpus.list(cleaned_folder)
else:
processed_bicorpora, processed_monocorpora = self._engine.training_preprocessor.process(
bilingual_corpora + monolingual_corpora,
preprocessed_folder,
(self._engine.data_path if self._split_trainingset else None),
log=logger.stream)
cleaned_bicorpora = self._engine.training_preprocessor.clean(
processed_bicorpora, cleaned_folder)
return processed_bicorpora, processed_monocorpora, cleaned_bicorpora
def process(self, corpora, output_path, data_path=None):
args = [
'-s', self._source_lang, '-t', self._target_lang, '-v',
self._vocabulary_path, '--output', output_path, '--input'
]
input_paths = set([corpus.get_folder() for corpus in corpora])
for root in input_paths:
args.append(root)
if data_path is not None:
args.append('--dev')
args.append(
os.path.join(data_path, TrainingPreprocessor.DEV_FOLDER_NAME))
args.append('--test')
args.append(
os.path.join(data_path, TrainingPreprocessor.TEST_FOLDER_NAME))
command = mmt_javamain(self._java_mainclass, args)
shell.execute(command,
stdin=shell.DEVNULL,
stdout=shell.DEVNULL,
stderr=shell.DEVNULL)
return BilingualCorpus.splitlist(self._source_lang,
self._target_lang,
roots=output_path)
def clean(self, source, target, input_paths, output_path):
args = ['-s', source, '-t', target, '--output', output_path, '--input']
for root in input_paths:
args.append(root)
command = mmt_javamain(self._java_mainclass, args)
shell.execute(command, stdin=shell.DEVNULL, stdout=shell.DEVNULL, stderr=shell.DEVNULL)
return BilingualCorpus.splitlist(source, target, roots=output_path)[0]
def _make_training_folder(self, bilingual_corpora, monolingual_corpora, domains, folder):
for corpus in bilingual_corpora:
dest_corpus = BilingualCorpus.make_parallel(domains[corpus.name], folder, corpus.langs)
for lang in corpus.langs:
os.symlink(corpus.get_file(lang), dest_corpus.get_file(lang))
for corpus in monolingual_corpora:
dest_corpus = BilingualCorpus.make_parallel(corpus.name, folder, corpus.langs)
for lang in corpus.langs:
os.symlink(corpus.get_file(lang), dest_corpus.get_file(lang))
return BilingualCorpus.splitlist(self._source_lang, self._target_lang, roots=folder)
def _make_training_folder(self, bilingual_corpora, monolingual_corpora, domains, folder):
for corpus in bilingual_corpora:
dest_corpus = BilingualCorpus.make_parallel(domains[corpus.name], folder, corpus.langs)
for lang in corpus.langs:
os.symlink(corpus.get_file(lang), dest_corpus.get_file(lang))
for corpus in monolingual_corpora:
dest_corpus = BilingualCorpus.make_parallel(corpus.name, folder, corpus.langs)
for lang in corpus.langs:
os.symlink(corpus.get_file(lang), dest_corpus.get_file(lang))
return BilingualCorpus.splitlist(self._source_lang, self._target_lang, roots=folder)
def process(self, source, target, input_paths, output_path, data_path=None):
args = ['-s', source, '-t', target, '--output', output_path, '--input']
for root in input_paths:
args.append(root)
if data_path is not None:
args.append('--dev')
args.append(os.path.join(data_path, TrainingPreprocessor.DEV_FOLDER_NAME))
args.append('--test')
args.append(os.path.join(data_path, TrainingPreprocessor.TEST_FOLDER_NAME))
command = mmt_javamain(self._java_mainclass, args)
shell.execute(command, stdin=shell.DEVNULL, stdout=shell.DEVNULL, stderr=shell.DEVNULL)
return BilingualCorpus.splitlist(source, target, roots=output_path)
def process(self, corpora, output_path, data_path=None):
args = ['-s', self._source_lang, '-t', self._target_lang, '-v', self._vocabulary_path, '--output', output_path,
'--input']
input_paths = set([corpus.get_folder() for corpus in corpora])
for root in input_paths:
args.append(root)
if data_path is not None:
args.append('--dev')
args.append(os.path.join(data_path, TrainingPreprocessor.DEV_FOLDER_NAME))
args.append('--test')
args.append(os.path.join(data_path, TrainingPreprocessor.TEST_FOLDER_NAME))
command = mmt_javamain(self._java_mainclass, args)
shell.execute(command, stdin=shell.DEVNULL, stdout=shell.DEVNULL, stderr=shell.DEVNULL)
return BilingualCorpus.splitlist(self._source_lang, self._target_lang, roots=output_path)
def _build(self, resume=False):
self._temp_dir = self._engine.get_tempdir('training',
ensure=(not resume))
self._checkpoint_path = os.path.join(self._temp_dir, 'checkpoint.json')
self._passed_steps = []
if resume:
self.load_checkpoint()
else:
self.save_checkpoint()
# initialize thee checkpoint manager
source_lang = self._engine.source_lang
target_lang = self._engine.target_lang
# separate bilingual and monolingual corpora in separate lists, reading them from roots
bilingual_corpora, monolingual_corpora = BilingualCorpus.splitlist(
source_lang, target_lang, roots=self._roots)
# if no bilingual corpora are found, it is not possible to train the translation system
if len(bilingual_corpora) == 0:
raise IllegalArgumentException(
'you project does not include %s-%s data.' %
(source_lang.upper(), target_lang.upper()))
# if no old engines (i.e. engine folders) can be found, create a new one from scratch
# if we are not trying to resume an old one, create from scratch anyway
if not os.path.isdir(self._engine.path) or not resume:
shutil.rmtree(self._engine.path, ignore_errors=True)
os.makedirs(self._engine.path)
# Check if all requirements are fulfilled before launching engine training
self._check_constraints()
# Create a new logger for the building activities,
# passing it the amount of steps to perform (plus a non user-decidable step)
# and the name of the log file to create
logger = _builder_logger(
len(self._scheduled_steps) + 1,
self._engine.get_logfile('training'))
delete_on_exit = not self._debug
# Start the engine building (training) phases
try:
# tell the logger that the engine training has started
logger.start(self._engine, bilingual_corpora, monolingual_corpora)
# ~~~~~~~~~~~~~~~~~~~~~ RUN ALL STEPS ~~~~~~~~~~~~~~~~~~~~~
# Note: if resume is true, a step is only run if it was not in the previous attempt
# run tm_cleanup step on the bilingual_corpora if required.
# Obtain cleaned bicorpora
cleaned_bicorpora = self._run_step('tm_cleanup',
self._step_tm_cleanup,
logger=logger,
values=[bilingual_corpora],
delete_on_exit=delete_on_exit)
# run __db_map step (always: user can't skip it)
# on the cleaned bicorpora and the original monocorpora;
# obtain base bicorpora and base monocorpora
base_bicorpora, base_monocorpora = self._run_step(
'__db_map',
self._step_init,
forced=True,
values=[cleaned_bicorpora, monolingual_corpora],
delete_on_exit=delete_on_exit)
# run preprocess step if required.
# Return processed bi and mono corpora and cleaned bicorpora
processed_bicorpora, processed_monocorpora, cleaned_bicorpora = \
self._run_step('preprocess',
self._step_preprocess,
logger=logger,
values=[base_bicorpora, base_monocorpora, base_bicorpora],
delete_on_exit=delete_on_exit)
# run context_analyzer step base_bicorpora if required.
_ = self._run_step('context_analyzer',
self._step_context_analyzer,
logger=logger,
values=[base_bicorpora],
delete_on_exit=delete_on_exit)
# run aligner step cleaned_bicorpora if required.
_ = self._run_step('aligner',
self._step_aligner,
logger=logger,
values=[cleaned_bicorpora],
delete_on_exit=delete_on_exit)
# run tm step cleaned_bicorpora if required.
_ = self._run_step('tm',
self._step_tm,
logger=logger,
values=[cleaned_bicorpora],
delete_on_exit=delete_on_exit)
# run lm step on the joint list of processed_bicorpora and processed_monocorpora
_ = self._run_step(
'lm',
self._step_lm,
logger=logger,
values=[processed_bicorpora + processed_monocorpora],
delete_on_exit=delete_on_exit)
# Writing config file
with logger.step('Writing config files') as _:
self._engine.write_configs()
# tell the logger that the engine training has completed
logger.completed()
# if this is not debug mode, then the training temporary folder must be deleted
if not self._debug:
self._engine.clear_tempdir('training')
except:
logger.error()
raise
finally:
logger.close()
def build(self, roots, debug=False, steps=None, split_trainingset=True):
self._temp_dir = self._engine.get_tempdir('training', ensure=True)
source_lang = self._engine.source_lang
target_lang = self._engine.target_lang
bilingual_corpora, monolingual_corpora = BilingualCorpus.splitlist(source_lang, target_lang, roots=roots)
if len(bilingual_corpora) == 0:
raise IllegalArgumentException(
'you project does not include %s-%s data.' % (source_lang.upper(), target_lang.upper()))
if steps is None:
steps = self._engine.training_steps
else:
unknown_steps = [step for step in steps if step not in self._engine.training_steps]
if len(unknown_steps) > 0:
raise IllegalArgumentException('Unknown training steps: ' + str(unknown_steps))
cmdlogger = _builder_logger(len(steps) + 1)
cmdlogger.start(self._engine, bilingual_corpora, monolingual_corpora)
shutil.rmtree(self._engine.path, ignore_errors=True)
os.makedirs(self._engine.path)
# Check disk space constraints
free_space_on_disk = fileutils.df(self._engine.path)[2]
corpus_size_on_disk = 0
for root in roots:
corpus_size_on_disk += fileutils.du(root)
free_memory = fileutils.free()
recommended_mem = self.__GB * corpus_size_on_disk / (350 * self.__MB) # 1G RAM every 350M on disk
recommended_disk = 10 * corpus_size_on_disk
if free_memory < recommended_mem or free_space_on_disk < recommended_disk:
if free_memory < recommended_mem:
print '> WARNING: more than %.fG of RAM recommended, only %.fG available' % \
(recommended_mem / self.__GB, free_memory / self.__GB)
if free_space_on_disk < recommended_disk:
print '> WARNING: more than %.fG of storage recommended, only %.fG available' % \
(recommended_disk / self.__GB, free_space_on_disk / self.__GB)
print
try:
unprocessed_bicorpora = bilingual_corpora
unprocessed_monocorpora = monolingual_corpora
# TM draft-translations cleanup
if 'tm_cleanup' in steps:
with cmdlogger.step('TMs clean-up') as _:
unprocessed_bicorpora = self._engine.cleaner.clean(
unprocessed_bicorpora, self._get_tempdir('clean_tms')
)
cleaned_bicorpora = unprocessed_bicorpora
processed_bicorpora = unprocessed_bicorpora
processed_monocorpora = unprocessed_monocorpora
# Preprocessing
if 'preprocess' in steps:
with cmdlogger.step('Corpora preprocessing') as _:
unprocessed_bicorpora, unprocessed_monocorpora = self._engine.db.generate(
unprocessed_bicorpora, unprocessed_monocorpora, self._get_tempdir('training_corpora')
)
processed_bicorpora, processed_monocorpora = self._engine.training_preprocessor.process(
unprocessed_bicorpora + unprocessed_monocorpora, self._get_tempdir('preprocessed'),
(self._engine.data_path if split_trainingset else None)
)
cleaned_bicorpora = self._engine.training_preprocessor.clean(
processed_bicorpora, self._get_tempdir('clean_corpora')
)
# Training Context Analyzer
if 'context_analyzer' in steps:
with cmdlogger.step('Context Analyzer training') as _:
log_file = self._engine.get_logfile('training.context')
self._engine.analyzer.create_index(unprocessed_bicorpora, source_lang, log_file=log_file)
# Aligner
if 'aligner' in steps:
with cmdlogger.step('Aligner training') as _:
log_file = self._engine.get_logfile('training.aligner')
working_dir = self._get_tempdir('aligner')
self._engine.aligner.build(cleaned_bicorpora, working_dir, log_file)
# Training Translation Model
if 'tm' in steps:
with cmdlogger.step('Translation Model training') as _:
working_dir = self._get_tempdir('tm')
log_file = self._engine.get_logfile('training.tm')
self._engine.pt.train(cleaned_bicorpora, self._engine.aligner, working_dir, log_file)
# Training Adaptive Language Model
if 'lm' in steps:
with cmdlogger.step('Language Model training') as _:
working_dir = self._get_tempdir('lm')
log_file = self._engine.get_logfile('training.lm')
self._engine.lm.train(processed_bicorpora + processed_monocorpora, target_lang,
working_dir, log_file)
# Writing config file
with cmdlogger.step('Writing config files') as _:
self._engine.write_configs()
cmdlogger.completed()
finally:
if not debug:
self._engine.clear_tempdir('training')
def build(self, roots, debug=False, steps=None, split_trainingset=True):
self._temp_dir = self._engine.get_tempdir('training', ensure=True)
source_lang = self._engine.source_lang
target_lang = self._engine.target_lang
bilingual_corpora, monolingual_corpora = BilingualCorpus.splitlist(
source_lang, target_lang, roots=roots)
if len(bilingual_corpora) == 0:
raise IllegalArgumentException(
'you project does not include %s-%s data.' %
(source_lang.upper(), target_lang.upper()))
if steps is None:
steps = self._engine.training_steps
else:
unknown_steps = [
step for step in steps
if step not in self._engine.training_steps
]
if len(unknown_steps) > 0:
raise IllegalArgumentException('Unknown training steps: ' +
str(unknown_steps))
shutil.rmtree(self._engine.path, ignore_errors=True)
os.makedirs(self._engine.path)
# Check disk space constraints
free_space_on_disk = fileutils.df(self._engine.path)[2]
corpus_size_on_disk = 0
for root in roots:
corpus_size_on_disk += fileutils.du(root)
free_memory = fileutils.free()
recommended_mem = self.__GB * corpus_size_on_disk / (
350 * self.__MB) # 1G RAM every 350M on disk
recommended_disk = 10 * corpus_size_on_disk
if free_memory < recommended_mem or free_space_on_disk < recommended_disk:
if free_memory < recommended_mem:
print '> WARNING: more than %.fG of RAM recommended, only %.fG available' % \
(recommended_mem / self.__GB, free_memory / self.__GB)
if free_space_on_disk < recommended_disk:
print '> WARNING: more than %.fG of storage recommended, only %.fG available' % \
(recommended_disk / self.__GB, free_space_on_disk / self.__GB)
print
logger = _builder_logger(
len(steps) + 1, self._engine.get_logfile('training'))
try:
logger.start(self._engine, bilingual_corpora, monolingual_corpora)
unprocessed_bicorpora = bilingual_corpora
unprocessed_monocorpora = monolingual_corpora
# TM draft-translations cleanup
if 'tm_cleanup' in steps:
with logger.step('TMs clean-up') as _:
unprocessed_bicorpora = self._engine.cleaner.clean(
unprocessed_bicorpora,
self._get_tempdir('clean_tms'),
log=logger.stream)
cleaned_bicorpora = unprocessed_bicorpora
processed_bicorpora = unprocessed_bicorpora
processed_monocorpora = unprocessed_monocorpora
# Preprocessing
if 'preprocess' in steps:
with logger.step('Corpora preprocessing') as _:
unprocessed_bicorpora, unprocessed_monocorpora = self._engine.db.generate(
unprocessed_bicorpora,
unprocessed_monocorpora,
self._get_tempdir('training_corpora'),
log=logger.stream)
processed_bicorpora, processed_monocorpora = self._engine.training_preprocessor.process(
unprocessed_bicorpora + unprocessed_monocorpora,
self._get_tempdir('preprocessed'),
(self._engine.data_path
if split_trainingset else None),
log=logger.stream)
cleaned_bicorpora = self._engine.training_preprocessor.clean(
processed_bicorpora,
self._get_tempdir('clean_corpora'))
# Training Context Analyzer
if 'context_analyzer' in steps:
with logger.step('Context Analyzer training') as _:
self._engine.analyzer.create_index(unprocessed_bicorpora,
log=logger.stream)
# Aligner
if 'aligner' in steps:
with logger.step('Aligner training') as _:
working_dir = self._get_tempdir('aligner')
self._engine.aligner.build(cleaned_bicorpora,
working_dir,
log=logger.stream)
# Training Translation Model
if 'tm' in steps:
with logger.step('Translation Model training') as _:
working_dir = self._get_tempdir('tm')
self._engine.pt.train(cleaned_bicorpora,
self._engine.aligner,
working_dir,
log=logger.stream)
# Training Adaptive Language Model
if 'lm' in steps:
with logger.step('Language Model training') as _:
working_dir = self._get_tempdir('lm')
self._engine.lm.train(processed_bicorpora +
processed_monocorpora,
target_lang,
working_dir,
log=logger.stream)
# Writing config file
with logger.step('Writing config files') as _:
self._engine.write_configs()
logger.completed()
except:
logger.error()
raise
finally:
logger.close()
if not debug:
self._engine.clear_tempdir('training')
