def run_module(uri,
args,
env_vars=None,
name=DEFAULT_MODULE_NAME,
cache=None,
wait=True,
capture_error=False):
# type: (str, list, dict, str, bool, bool, bool) -> Popen
"""Download, prepare and executes a compressed tar file from S3 or provided directory as a module.
SageMaker Python SDK saves the user provided scripts as compressed tar files in S3
https://github.com/aws/sagemaker-python-sdk.
This function downloads this compressed file, transforms it as a module, and executes it.
Args:
uri (str): the location of the module.
args (list): A list of program arguments.
env_vars (dict): A map containing the environment variables to be written.
name (str): name of the script or module.
cache (bool): If True it will avoid downloading the module again, if already installed.
wait (bool): If True run_module will wait for the user module to exit and check the exit code,
otherwise it will launch the user module with subprocess and return the process object.
"""
_warning_cache_deprecation(cache)
env_vars = env_vars or {}
env_vars = env_vars.copy()
_files.download_and_extract(uri, name, _env.code_dir)
prepare(_env.code_dir, name)
install(_env.code_dir)
_env.write_env_vars(env_vars)
return run(name, args, env_vars, wait, capture_error)
def run(uri,
user_entry_point,
args,
env_vars=None,
wait=True,
capture_error=False,
runner=_runner.ProcessRunnerType):
# type: (str, str, List[str], Dict[str, str], bool, bool, _runner.RunnerType) -> None
"""Download, prepare and executes a compressed tar file from S3 or provided directory as an user
entrypoint. Runs the user entry point, passing env_vars as environment variables and args as command
arguments.
If the entry point is:
- A Python package: executes the packages as >>> env_vars python -m module_name + args
- A Python script: executes the script as >>> env_vars python module_name + args
- Any other: executes the command as >>> env_vars /bin/sh -c ./module_name + args
Example:
>>>import sagemaker_containers
>>>from sagemaker_containers.beta.framework import entry_point
>>>env = sagemaker_containers.training_env()
{'channel-input-dirs': {'training': '/opt/ml/input/training'}, 'model_dir': '/opt/ml/model', ...}
>>>hyperparameters = env.hyperparameters
{'batch-size': 128, 'model_dir': '/opt/ml/model'}
>>>args = mapping.to_cmd_args(hyperparameters)
['--batch-size', '128', '--model_dir', '/opt/ml/model']
>>>env_vars = mapping.to_env_vars()
['SAGEMAKER_CHANNELS':'training', 'SAGEMAKER_CHANNEL_TRAINING':'/opt/ml/input/training',
'MODEL_DIR':'/opt/ml/model', ...}
>>>entry_point.run('user_script', args, env_vars)
SAGEMAKER_CHANNELS=training SAGEMAKER_CHANNEL_TRAINING=/opt/ml/input/training \
SAGEMAKER_MODEL_DIR=/opt/ml/model python -m user_script --batch-size 128 --model_dir /opt/ml/model
Args:
user_entry_point (str): name of the user provided entry point
args (list): A list of program arguments.
env_vars (dict): A map containing the environment variables to be written.
uri (str): the location of the module.
capture_error (bool): Default false. If True, the running process captures the
stderr, and appends it to the returned Exception message in case of errors.
"""
env_vars = env_vars or {}
env_vars = env_vars.copy()
_files.download_and_extract(uri, user_entry_point, _env.code_dir)
install(user_entry_point, _env.code_dir, capture_error)
_env.write_env_vars(env_vars)
return _runner.get(runner).run(wait, capture_error)
def train(training_environment):
"""Run XGBoost training in either algorithm mode or using a user supplied module in local SageMaker environment.
The user supplied module and its dependencies are downloaded from S3.
Training is invoked by calling a "train" function in the user supplied module.
Args:
training_environment: training environment object containing environment variables,
training arguments and hyperparameters
"""
if training_environment.user_entry_point is not None:
logger.info('Invoking user training script.')
framework.modules.run_module(training_environment.module_dir, training_environment.to_cmd_args(),
training_environment.to_env_vars(), training_environment.module_name,
capture_error=True)
else:
logger.info("Running XGBoost Sagemaker in algorithm mode")
_env.write_env_vars(training_environment.to_env_vars())
run_algorithm_mode()
def run(
uri,
user_entry_point,
args,
env_vars=None,
wait=True,
capture_error=False,
runner=_runner.ProcessRunnerType,
extra_opts=None,
):
# type: (str, str, List[str], Dict[str, str], bool, bool, _runner.RunnerType,Dict[str, str]) -> None # pylint: disable=line-too-long # noqa ignore=E501
"""Download, prepare and executes a compressed tar file from S3 or provided directory as an user
entrypoint. Runs the user entry point, passing env_vars as environment variables and args
as command arguments.
If the entry point is:
- A Python package: executes the packages as >>> env_vars python -m module_name + args
- A Python script: executes the script as >>> env_vars python module_name + args
- Any other: executes the command as >>> env_vars /bin/sh -c ./module_name + args
Example:
>>>import sagemaker_containers
>>>from sagemaker_containers.beta.framework import entry_point
>>>env = sagemaker_containers.training_env()
{'channel-input-dirs': {'training': '/opt/ml/input/training'},
'model_dir': '/opt/ml/model', ...}
>>>hyperparameters = env.hyperparameters
{'batch-size': 128, 'model_dir': '/opt/ml/model'}
>>>args = mapping.to_cmd_args(hyperparameters)
['--batch-size', '128', '--model_dir', '/opt/ml/model']
>>>env_vars = mapping.to_env_vars()
['SAGEMAKER_CHANNELS':'training', 'SAGEMAKER_CHANNEL_TRAINING':'/opt/ml/input/training',
'MODEL_DIR':'/opt/ml/model', ...}
>>>entry_point.run('user_script', args, env_vars)
SAGEMAKER_CHANNELS=training SAGEMAKER_CHANNEL_TRAINING=/opt/ml/input/training \
SAGEMAKER_MODEL_DIR=/opt/ml/model python -m user_script --batch-size 128
--model_dir /opt/ml/model
Args:
uri (str): the location of the module.
user_entry_point (str): name of the user provided entry point
args (list): A list of program arguments.
env_vars (dict): A map containing the environment variables to be written (default: None).
wait (bool): If the user entry point should be run to completion before this method returns
(default: True).
capture_error (bool): Default false. If True, the running process captures the
stderr, and appends it to the returned Exception message in case of errors.
runner (sagemaker_containers.beta.framework.runner.RunnerType): the type of runner object to
be created (default: sagemaker_containers.beta.framework.runner.ProcessRunnerType).
extra_opts (dict): Additional options for running the entry point (default: None).
Currently, this only applies for MPI.
Returns:
sagemaker_containers.beta.framework.process.ProcessRunner: the runner object responsible for
executing the entry point.
"""
env_vars = env_vars or {}
env_vars = env_vars.copy()
_files.download_and_extract(uri, _env.code_dir)
install(user_entry_point, _env.code_dir, capture_error)
_env.write_env_vars(env_vars)
_wait_hostname_resolution()
return _runner.get(runner, user_entry_point, args, env_vars,
extra_opts).run(wait, capture_error)
