def test_fit_pca(sagemaker_session, tuner):
pca = PCA(ROLE, TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE, NUM_COMPONENTS,
base_job_name='pca', sagemaker_session=sagemaker_session)
pca.algorithm_mode = 'randomized'
pca.subtract_mean = True
pca.extra_components = 5
tuner.estimator = pca
tags = [{'Name': 'some-tag-without-a-value'}]
tuner.tags = tags
hyperparameter_ranges = {'num_components': IntegerParameter(2, 4),
'algorithm_mode': CategoricalParameter(['regular', 'randomized'])}
tuner._hyperparameter_ranges = hyperparameter_ranges
records = RecordSet(s3_data=INPUTS, num_records=1, feature_dim=1)
tuner.fit(records, mini_batch_size=9999)
_, _, tune_kwargs = sagemaker_session.tune.mock_calls[0]
assert len(tune_kwargs['static_hyperparameters']) == 4
assert tune_kwargs['static_hyperparameters']['extra_components'] == '5'
assert len(tune_kwargs['parameter_ranges']['IntegerParameterRanges']) == 1
assert tune_kwargs['job_name'].startswith('pca')
assert tune_kwargs['tags'] == tags
assert tuner.estimator.mini_batch_size == 9999
def test_fit_pca(sagemaker_session, tuner):
pca = PCA(ROLE, TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE, NUM_COMPONENTS,
base_job_name='pca', sagemaker_session=sagemaker_session)
pca.algorithm_mode = 'randomized'
pca.subtract_mean = True
pca.extra_components = 5
tuner.estimator = pca
tags = [{'Name': 'some-tag-without-a-value'}]
tuner.tags = tags
hyperparameter_ranges = {'num_components': IntegerParameter(2, 4),
'algorithm_mode': CategoricalParameter(['regular', 'randomized'])}
tuner._hyperparameter_ranges = hyperparameter_ranges
records = RecordSet(s3_data=INPUTS, num_records=1, feature_dim=1)
tuner.fit(records, mini_batch_size=9999)
_, _, tune_kwargs = sagemaker_session.tune.mock_calls[0]
assert len(tune_kwargs['static_hyperparameters']) == 4
assert tune_kwargs['static_hyperparameters']['extra_components'] == '5'
assert len(tune_kwargs['parameter_ranges']['IntegerParameterRanges']) == 1
assert tune_kwargs['job_name'].startswith('pca')
assert tune_kwargs['tags'] == tags
assert tuner.estimator.mini_batch_size == 9999
def pca_estimator(sagemaker_role_arn):
pca_estimator = PCA(
role=sagemaker_role_arn,
num_components=1,
train_instance_count=1,
train_instance_type='ml.m5.large',
)
pca_estimator.feature_dim = 500
pca_estimator.subtract_mean = True,
pca_estimator.algorithm_mode = 'randomized'
pca_estimator.mini_batch_size = 128
return pca_estimator
def test_fit_pca(sagemaker_session, tuner):
pca = PCA(
ROLE,
TRAIN_INSTANCE_COUNT,
TRAIN_INSTANCE_TYPE,
NUM_COMPONENTS,
base_job_name="pca",
sagemaker_session=sagemaker_session,
)
pca.algorithm_mode = "randomized"
pca.subtract_mean = True
pca.extra_components = 5
tuner.estimator = pca
tags = [{"Name": "some-tag-without-a-value"}]
tuner.tags = tags
hyperparameter_ranges = {
"num_components": IntegerParameter(2, 4),
"algorithm_mode": CategoricalParameter(["regular", "randomized"]),
}
tuner._hyperparameter_ranges = hyperparameter_ranges
records = RecordSet(s3_data=INPUTS, num_records=1, feature_dim=1)
tuner.fit(records, mini_batch_size=9999)
_, _, tune_kwargs = sagemaker_session.tune.mock_calls[0]
assert len(tune_kwargs["static_hyperparameters"]) == 4
assert tune_kwargs["static_hyperparameters"]["extra_components"] == "5"
assert len(tune_kwargs["parameter_ranges"]["IntegerParameterRanges"]) == 1
assert tune_kwargs["job_name"].startswith("pca")
assert tune_kwargs["tags"] == tags
assert tune_kwargs["early_stopping_type"] == "Off"
assert tuner.estimator.mini_batch_size == 9999