def _prepare_for_training(self, job_name=None):
if job_name is not None:
self._current_job_name = job_name
else:
base_name = self.base_tuning_job_name or base_name_from_image(
self.estimator.train_image())
self._current_job_name = name_from_base(
base_name,
max_length=self.TUNING_JOB_NAME_MAX_LENGTH,
short=True)
self.static_hyperparameters = {
to_str(k): to_str(v)
for (k, v) in self.estimator.hyperparameters().items()
}
for hyperparameter_name in self._hyperparameter_ranges.keys():
self.static_hyperparameters.pop(hyperparameter_name, None)
# For attach() to know what estimator to use for non-1P algorithms
# (1P algorithms don't accept extra hyperparameters)
if not isinstance(self.estimator, AmazonAlgorithmEstimatorBase):
self.static_hyperparameters[
self.SAGEMAKER_ESTIMATOR_CLASS_NAME] = json.dumps(
self.estimator.__class__.__name__)
self.static_hyperparameters[
self.SAGEMAKER_ESTIMATOR_MODULE] = json.dumps(
self.estimator.__module__)
def _prepare_for_training(self, job_name=None, include_cls_metadata=False):
"""
Args:
job_name:
include_cls_metadata:
"""
if job_name is not None:
self._current_job_name = job_name
else:
base_name = self.base_tuning_job_name or base_name_from_image(
self.estimator.train_image()
)
self._current_job_name = name_from_base(
base_name, max_length=self.TUNING_JOB_NAME_MAX_LENGTH, short=True
)
self.static_hyperparameters = {
to_str(k): to_str(v) for (k, v) in self.estimator.hyperparameters().items()
}
for hyperparameter_name in self._hyperparameter_ranges.keys():
self.static_hyperparameters.pop(hyperparameter_name, None)
# For attach() to know what estimator to use for frameworks
# (other algorithms may not accept extra hyperparameters)
if include_cls_metadata or isinstance(self.estimator, Framework):
self.static_hyperparameters[self.SAGEMAKER_ESTIMATOR_CLASS_NAME] = json.dumps(
self.estimator.__class__.__name__
)
self.static_hyperparameters[self.SAGEMAKER_ESTIMATOR_MODULE] = json.dumps(
self.estimator.__module__
)
def __init__(self, values): # pylint: disable=super-init-not-called
"""Initialize a ``CategoricalParameter``.
Args:
values (list or object): The possible values for the hyperparameter. This input will
be converted into a list of strings.
"""
if isinstance(values, list):
self.values = [to_str(v) for v in values]
else:
self.values = [to_str(values)]
def __init__(self, values):
"""Initialize a ``CategoricalParameter``.
Args:
values (list or object): The possible values for the hyperparameter. This input will
be converted into a list of strings.
"""
if isinstance(values, list):
self.values = [to_str(v) for v in values]
else:
self.values = [to_str(values)]
def as_tuning_range(self, name):
"""Represent the parameter range as a dicionary suitable for a request to
create an Amazon SageMaker hyperparameter tuning job.
Args:
name (str): The name of the hyperparameter.
Returns:
dict[str, str]: A dictionary that contains the name and values of the hyperparameter.
"""
return {'Name': name,
'MinValue': to_str(self.min_value),
'MaxValue': to_str(self.max_value)}
def as_tuning_range(self, name):
"""Represent the parameter range as a dicionary suitable for a request to
create an Amazon SageMaker hyperparameter tuning job.
Args:
name (str): The name of the hyperparameter.
Returns:
dict[str, str]: A dictionary that contains the name and values of the hyperparameter.
"""
return {'Name': name,
'MinValue': to_str(self.min_value),
'MaxValue': to_str(self.max_value)}
def _prepare_for_training(self, job_name=None, include_cls_metadata=True):
if job_name is not None:
self._current_job_name = job_name
else:
base_name = self.base_tuning_job_name or base_name_from_image(self.estimator.train_image())
self._current_job_name = name_from_base(base_name, max_length=self.TUNING_JOB_NAME_MAX_LENGTH, short=True)
self.static_hyperparameters = {to_str(k): to_str(v) for (k, v) in self.estimator.hyperparameters().items()}
for hyperparameter_name in self._hyperparameter_ranges.keys():
self.static_hyperparameters.pop(hyperparameter_name, None)
# For attach() to know what estimator to use for non-1P algorithms
# (1P algorithms don't accept extra hyperparameters)
if include_cls_metadata and not isinstance(self.estimator, AmazonAlgorithmEstimatorBase):
self.static_hyperparameters[self.SAGEMAKER_ESTIMATOR_CLASS_NAME] = json.dumps(
self.estimator.__class__.__name__)
self.static_hyperparameters[self.SAGEMAKER_ESTIMATOR_MODULE] = json.dumps(self.estimator.__module__)
def __init__(self, values):
if isinstance(values, list):
self.values = [to_str(v) for v in values]
else:
self.values = [to_str(values)]
def as_tuning_range(self, name):
return {
'Name': name,
'MinValue': to_str(self.min_value),
'MaxValue': to_str(self.max_value)
}
def tuning_config(tuner, inputs, job_name=None):
"""Export Airflow tuning config from an estimator
Args:
tuner (sagemaker.tuner.HyperparameterTuner): The tuner to export tuning
config from.
inputs: Information about the training data. Please refer to the ``fit()``
method of the associated estimator in the tuner, as this can take any of the
following forms:
* (str) - The S3 location where training data is saved.
* (dict[str, str] or dict[str, sagemaker.session.s3_input]) - If using multiple
channels for training data, you can specify a dict mapping channel names to
strings or :func:`~sagemaker.session.s3_input` objects.
* (sagemaker.session.s3_input) - Channel configuration for S3 data sources that can
provide additional information about the training dataset. See
:func:`sagemaker.session.s3_input` for full details.
* (sagemaker.amazon.amazon_estimator.RecordSet) - A collection of
Amazon :class:~`Record` objects serialized and stored in S3.
For use with an estimator for an Amazon algorithm.
* (list[sagemaker.amazon.amazon_estimator.RecordSet]) - A list of
:class:~`sagemaker.amazon.amazon_estimator.RecordSet` objects,
where each instance is a different channel of training data.
job_name (str): Specify a tuning job name if needed.
Returns:
dict: Tuning config that can be directly used by SageMakerTuningOperator in Airflow.
"""
train_config = training_base_config(tuner.estimator, inputs)
hyperparameters = train_config.pop("HyperParameters", None)
s3_operations = train_config.pop("S3Operations", None)
if hyperparameters and len(hyperparameters) > 0:
tuner.static_hyperparameters = {
utils.to_str(k): utils.to_str(v) for (k, v) in hyperparameters.items()
}
if job_name is not None:
tuner._current_job_name = job_name
else:
base_name = tuner.base_tuning_job_name or utils.base_name_from_image(
tuner.estimator.train_image()
)
tuner._current_job_name = utils.name_from_base(
base_name, tuner.TUNING_JOB_NAME_MAX_LENGTH, True
)
for hyperparameter_name in tuner._hyperparameter_ranges.keys():
tuner.static_hyperparameters.pop(hyperparameter_name, None)
train_config["StaticHyperParameters"] = tuner.static_hyperparameters
tune_config = {
"HyperParameterTuningJobName": tuner._current_job_name,
"HyperParameterTuningJobConfig": {
"Strategy": tuner.strategy,
"HyperParameterTuningJobObjective": {
"Type": tuner.objective_type,
"MetricName": tuner.objective_metric_name,
},
"ResourceLimits": {
"MaxNumberOfTrainingJobs": tuner.max_jobs,
"MaxParallelTrainingJobs": tuner.max_parallel_jobs,
},
"ParameterRanges": tuner.hyperparameter_ranges(),
},
"TrainingJobDefinition": train_config,
}
if tuner.metric_definitions is not None:
tune_config["TrainingJobDefinition"]["AlgorithmSpecification"][
"MetricDefinitions"
] = tuner.metric_definitions
if tuner.tags is not None:
tune_config["Tags"] = tuner.tags
if s3_operations is not None:
tune_config["S3Operations"] = s3_operations
return tune_config
def cast_to_type(cls, value):
return to_str(value)
def test_to_str_with_unicode_string():
value = u'åñøthér strîng'
assert to_str(value) == value
def test_to_str_with_native_string():
value = 'some string'
assert to_str(value) == value
def cast_to_type(cls, value):
"""
Args:
value:
"""
return to_str(value)
def test_to_str_with_unicode_string():
value = u'åñøthér strîng'
assert to_str(value) == value
def test_to_str_with_native_string():
value = 'some string'
assert to_str(value) == value
