def create_job(config, name, work_dir, train_file, model_file,
test_file, classif_file, memory=MEMORY):
"""\
Save configuration to a pickle file, create a corresponding cluster job
and run it.
"""
train_file = os.path.abspath(train_file)
cfg_file = append_name('config.pickle', name)
model_file = append_name(model_file, name)
if test_file is not None and classif_file is not None:
test_file = os.path.abspath(test_file)
classif_file = append_name(classif_file, name)
test_str = "'{0}', '{1}'".format(test_file, classif_file)
else:
test_str = 'None, None'
# save unfolded config file
fh = open(os.path.join(work_dir, cfg_file), mode='wb')
marshal_lambda(config, 'filter_attr')
marshal_lambda(config, 'postprocess')
pickle.dump(config, fh, pickle.HIGHEST_PROTOCOL)
fh.close()
# create the training job
job = Job(name=name, work_dir=work_dir)
job.header = "from flect.experiment.train_model import run_training\n"
job.code = "run_training('{0}', '{1}',".format(work_dir, cfg_file) + \
"'{0}', '{1}', {2})\n".format(train_file, model_file, test_str)
job.submit(memory=memory)
print 'Job', job, 'submitted.'
def train(self, das_file, ttree_file, data_portion=1.0, context_file=None, validation_files=None):
"""Run parallel perceptron training, start and manage workers."""
# initialize the ranker instance
log_info('Initializing...')
# run server to process registering clients
self._init_server()
# spawn training jobs
log_info('Spawning jobs...')
host_short, _ = self.host.split('.', 1) # short host name for job names
for j in xrange(self.jobs_number):
# set up debugging logfile only if we have it on the head
debug_logfile = ('"PRT%02d.debug-out.txt.gz"' % j) if is_debug_stream() else 'None'
job = Job(header='from tgen.parallel_seq2seq_train import run_training',
code=('run_training("%s", %d, %s)' %
(self.host, self.port, debug_logfile)),
name=self.experiment_id + ("PRT%02d-%s-%d" % (j, host_short, self.port)),
work_dir=self.work_dir)
job.submit(memory=self.job_memory, queue=self.queue_settings)
self.jobs.append(job)
# run the training passes
try:
cur_assign = 0
results = [None] * self.jobs_number
rnd_seeds = [rnd.random() for _ in xrange(self.jobs_number)]
# assign training and wait for it to finish
while cur_assign < self.jobs_number or self.pending_requests:
log_debug('Starting loop over services.')
# check if some of the pending computations have finished
for sc, job_no, req in list(self.pending_requests):
res = self._check_pending_request(sc, job_no, req)
if res is not None:
results[job_no] = res, sc
# check for free services and assign new computation
while cur_assign < self.jobs_number and self.free_services:
log_debug('Assigning request %d' % cur_assign)
sc = self.free_services.popleft()
log_info('Assigning request %d to %s:%d' % (cur_assign, sc.host, sc.port))
if validation_files is not None:
validation_files = ','.join([os.path.relpath(f, self.work_dir)
for f in validation_files.split(',')])
train_func = async(sc.conn.root.train)
req = train_func(rnd_seeds[cur_assign],
os.path.relpath(das_file, self.work_dir),
os.path.relpath(ttree_file, self.work_dir),
data_portion,
os.path.relpath(context_file, self.work_dir)
if context_file else None,
validation_files)
self.pending_requests.add((sc, cur_assign, req))
cur_assign += 1
log_debug('Assigned %d' % cur_assign)
# sleep for a while
log_debug('Sleeping.')
time.sleep(self.poll_interval)
log_info("Results:\n" + "\n".join("%.5f %s:%d" % (cost, sc.host, sc.port)
for cost, sc in results))
self.model_temp_path = os.path.join(self.work_dir, self.TEMPFILE_NAME)
results.sort(key=lambda res: res[0])
# average the computed models
if self.average_models:
log_info('Creating ensemble models...')
# use only top k if required
results_for_ensemble = (results[:self.average_models_top_k]
if self.average_models_top_k > 0
else results)
ensemble_model = self.build_ensemble_model(results_for_ensemble)
log_info('Saving the ensemble model temporarily to %s...' % self.model_temp_path)
ensemble_model.save_to_file(self.model_temp_path)
# select the best result on devel data + save it
else:
best_cost, best_sc = results[0]
log_info('Best cost: %f (computed at %s:%d).' % (best_cost, best_sc.host, best_sc.port))
log_info('Saving best generator temporarily to %s...' % self.model_temp_path)
# use relative path (working directory of worker jobs is different)
best_sc.conn.root.save_model(os.path.relpath(self.model_temp_path, self.work_dir))
# kill all jobs
finally:
for job in self.jobs:
job.delete()
def train(self, das_file, ttree_file, data_portion=1.0):
"""Run parallel perceptron training, start and manage workers."""
# initialize the ranker instance
log_info('Initializing...')
self.loc_ranker._init_training(das_file, ttree_file, data_portion)
# run server to process registering clients
self._init_server()
# spawn training jobs
log_info('Spawning jobs...')
host_short, _ = self.host.split('.',
1) # short host name for job names
for j in xrange(self.jobs_number):
# set up debugging logfile only if we have it on the head
debug_logfile = ('"PRT%02d.debug-out.txt.gz"' %
j) if is_debug_stream() else 'None'
job = Job(
header='from tgen.parallel_percrank_train import run_worker',
code=('run_worker("%s", %d, %s)' %
(self.host, self.port, debug_logfile)),
name=self.experiment_id + ("PRT%02d-%s-%d" %
(j, host_short, self.port)),
work_dir=self.work_dir)
job.submit(self.job_memory)
self.jobs.append(job)
# run the training passes
try:
for iter_no in xrange(1, self.loc_ranker.passes + 1):
log_info('Pass %d...' % iter_no)
log_debug('\n***\nTR%05d:' % iter_no)
iter_start_time = time.time()
cur_portion = 0
results = [None] * self.data_portions
w_dump = pickle.dumps(self.loc_ranker.get_weights(),
protocol=pickle.HIGHEST_PROTOCOL)
rnd_seeds = [rnd.random() for _ in xrange(self.data_portions)]
# wait for free services / assign computation
while cur_portion < self.data_portions or self.pending_requests:
log_debug('Starting loop over services.')
# check if some of the pending computations have finished
for sc, req_portion, req in list(self.pending_requests):
res = self._check_pending_request(
iter_no, sc, req_portion, req)
if res:
results[req_portion] = res
# check for free services and assign new computation
while cur_portion < self.data_portions and self.free_services:
log_debug('Assigning request %d' % cur_portion)
sc = self.free_services.popleft()
log_info('Assigning request %d / %d to %s:%d' %
(iter_no, cur_portion, sc.host, sc.port))
train_func = async (sc.conn.root.training_pass)
req = train_func(
w_dump, iter_no, rnd_seeds[cur_portion],
*self._get_portion_bounds(cur_portion))
self.pending_requests.add((sc, cur_portion, req))
cur_portion += 1
log_debug('Assigned %d' % cur_portion)
# sleep for a while
log_debug('Sleeping.')
time.sleep(self.poll_interval)
# delete the temporary ranker dump when the 1st iteration is complete
if self.ranker_dump_path:
log_info('Removing temporary ranker dump at %s.' %
self.ranker_dump_path)
os.remove(self.ranker_dump_path)
self.ranker_dump_path = None
# gather/average the diagnostic statistics
self.loc_ranker.set_diagnostics_average(
[d for _, d in results])
# take an average of weights; set it as new w
self.loc_ranker.set_weights_average([w for w, _ in results])
self.loc_ranker.store_iter_weights(
) # store a copy of w for averaged perceptron
# print statistics
log_debug(self.loc_ranker._feat_val_str(), '\n***')
self.loc_ranker._print_pass_stats(
iter_no,
datetime.timedelta(seconds=(time.time() -
iter_start_time)))
# after all passes: average weights if set to do so
if self.loc_ranker.averaging is True:
self.loc_ranker.set_weights_iter_average()
# kill all jobs
finally:
for job in self.jobs:
job.delete()