def main(argv=None):
parser = create_parser()
args = parser.parse_args(argv)
logging.getLogger().setLevel(logging.INFO)
client = _utils.get_sagemaker_client(args.region, args.endpoint_url)
logging.info('Submitting Processing Job to SageMaker...')
job_name = _utils.create_processing_job(client, vars(args))
logging.info('Job request submitted. Waiting for completion...')
try:
_utils.wait_for_processing_job(client, job_name)
except:
raise
finally:
cw_client = _utils.get_cloudwatch_client(args.region)
_utils.print_logs_for_job(cw_client, '/aws/sagemaker/ProcessingJobs',
job_name)
outputs = _utils.get_processing_job_outputs(client, job_name)
with open('/tmp/job_name.txt', 'w') as f:
f.write(job_name)
with open('/tmp/output_artifacts.txt', 'w') as f:
f.write(json.dumps(outputs))
logging.info('Job completed.')
def main(argv=None):
parser = create_parser()
args = parser.parse_args(argv)
logging.getLogger().setLevel(logging.INFO)
client = _utils.get_sagemaker_client(args.region, args.endpoint_url)
logging.info('Submitting Training Job to SageMaker...')
job_name = _utils.create_training_job(client, vars(args))
def signal_term_handler(signalNumber, frame):
_utils.stop_training_job(client, job_name)
logging.info(f"Training Job: {job_name} request submitted to Stop")
signal.signal(signal.SIGTERM, signal_term_handler)
logging.info('Job request submitted. Waiting for completion...')
try:
_utils.wait_for_training_job(client, job_name)
_utils.wait_for_debug_rules(client, job_name)
except:
raise
finally:
cw_client = _utils.get_cloudwatch_client(args.region)
_utils.print_logs_for_job(cw_client, '/aws/sagemaker/TrainingJobs', job_name)
image = _utils.get_image_from_job(client, job_name)
model_artifact_url = _utils.get_model_artifacts_from_job(client, job_name)
logging.info('Get model artifacts %s from training job %s.', model_artifact_url, job_name)
_utils.write_output(args.model_artifact_url_output_path, model_artifact_url)
_utils.write_output(args.job_name_output_path, job_name)
_utils.write_output(args.training_image_output_path, image)
logging.info('Job completed.')
def main(argv=None):
parser = create_parser()
args = parser.parse_args(argv)
logging.getLogger().setLevel(logging.INFO)
client = _utils.get_sagemaker_client(args.region, args.endpoint_url)
logging.info('Submitting Training Job to SageMaker...')
job_name = _utils.create_training_job(client, vars(args))
logging.info('Job request submitted. Waiting for completion...')
try:
_utils.wait_for_training_job(client, job_name)
except:
raise
finally:
cw_client = _utils.get_cloudwatch_client(args.region)
_utils.print_logs_for_job(cw_client, '/aws/sagemaker/TrainingJobs',
job_name)
image = _utils.get_image_from_job(client, job_name)
model_artifact_url = _utils.get_model_artifacts_from_job(client, job_name)
logging.info('Get model artifacts %s from training job %s.',
model_artifact_url, job_name)
with open('/tmp/model_artifact_url.txt', 'w') as f:
f.write(model_artifact_url)
with open('/tmp/job_name.txt', 'w') as f:
f.write(job_name)
with open('/tmp/training_image.txt', 'w') as f:
f.write(image)
logging.info('Job completed.')
def main(argv=None):
parser = create_parser()
args = parser.parse_args(argv)
logging.getLogger().setLevel(logging.INFO)
client = _utils.get_sagemaker_client(args.region,
args.endpoint_url,
assume_role_arn=args.assume_role)
logging.info('Submitting Batch Transformation request to SageMaker...')
batch_job_name = _utils.create_transform_job(client, vars(args))
def signal_term_handler(signalNumber, frame):
_utils.stop_transform_job(client, batch_job_name)
logging.info(
f"Transform job: {batch_job_name} request submitted to Stop")
signal.signal(signal.SIGTERM, signal_term_handler)
logging.info('Batch Job request submitted. Waiting for completion...')
try:
_utils.wait_for_transform_job(client, batch_job_name)
except:
raise
finally:
cw_client = _utils.get_cloudwatch_client(
args.region, assume_role_arn=args.assume_role)
_utils.print_logs_for_job(cw_client, '/aws/sagemaker/TransformJobs',
batch_job_name)
_utils.write_output(args.output_location_output_path, args.output_location)
logging.info('Batch Transformation creation completed.')
def main(argv=None):
parser = create_parser()
args = parser.parse_args(argv)
logging.getLogger().setLevel(logging.INFO)
client = _utils.get_sagemaker_client(args.region, args.endpoint_url)
logging.info('Submitting Batch Transformation request to SageMaker...')
batch_job_name = _utils.create_transform_job(client, vars(args))
logging.info('Batch Job request submitted. Waiting for completion...')
try:
_utils.wait_for_transform_job(client, batch_job_name)
except:
raise
finally:
cw_client = _utils.get_cloudwatch_client(args.region)
_utils.print_logs_for_job(cw_client, '/aws/sagemaker/TransformJobs',
batch_job_name)
_utils.write_output(args.output_location_output_path, args.output_location)
logging.info('Batch Transformation creation completed.')
def main(argv=None):
parser = create_parser()
args = parser.parse_args(argv)
logging.getLogger().setLevel(logging.INFO)
client = _utils.get_sagemaker_client(args.region,
args.endpoint_url,
assume_role_arn=args.assume_role)
logging.info('Submitting Processing Job to SageMaker...')
job_name = _utils.create_processing_job(client, vars(args))
def signal_term_handler(signalNumber, frame):
logging.info(f"Stopping Processing Job: {job_name}")
_utils.stop_processing_job(client, job_name)
logging.info(f"Processing Job: {job_name} request submitted to Stop")
signal.signal(signal.SIGTERM, signal_term_handler)
logging.info('Job request submitted. Waiting for completion...')
try:
_utils.wait_for_processing_job(client, job_name)
except:
raise
finally:
cw_client = _utils.get_cloudwatch_client(
args.region, assume_role_arn=args.assume_role)
_utils.print_logs_for_job(cw_client, '/aws/sagemaker/ProcessingJobs',
job_name)
outputs = _utils.get_processing_job_outputs(client, job_name)
_utils.write_output(args.job_name_output_path, job_name)
_utils.write_output(args.output_artifacts_output_path,
outputs,
json_encode=True)
logging.info('Job completed.')
