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_prepare_for_training_list(sagemaker_session):
pca = PCA(num_components=55, sagemaker_session=sagemaker_session, **COMMON_ARGS)
train = [[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 8.0], [44.0, 55.0, 66.0]]
labels = [99, 85, 87, 2]
records = [pca.record_set(np.array(train), np.array(labels))]
pca._prepare_for_training(records, mini_batch_size=1)
assert pca.feature_dim == 3
assert pca.mini_batch_size == 1
def test_prepare_for_training_list_no_train_channel(sagemaker_session):
pca = PCA(num_components=55, sagemaker_session=sagemaker_session, **COMMON_ARGS)
train = [[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 8.0], [44.0, 55.0, 66.0]]
labels = [99, 85, 87, 2]
records = [pca.record_set(np.array(train), np.array(labels), 'test')]
with pytest.raises(ValueError) as ex:
pca._prepare_for_training(records, mini_batch_size=1)
assert 'Must provide train channel.' in str(ex)
def test_fit_ndarray(time, sagemaker_session):
mock_s3 = Mock()
mock_object = Mock()
mock_s3.Object = Mock(return_value=mock_object)
sagemaker_session.boto_session.resource = Mock(return_value=mock_s3)
kwargs = dict(COMMON_ARGS)
kwargs['train_instance_count'] = 3
pca = PCA(num_components=55, sagemaker_session=sagemaker_session,
data_location='s3://{}/key-prefix/'.format(BUCKET_NAME), **kwargs)
train = [[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 8.0], [44.0, 55.0, 66.0]]
labels = [99, 85, 87, 2]
pca.fit(pca.record_set(np.array(train), np.array(labels)))
mock_s3.Object.assert_any_call(
BUCKET_NAME, 'key-prefix/PCA-2017-11-06-14:14:15.671/matrix_0.pbr'.format(TIMESTAMP))
mock_s3.Object.assert_any_call(
BUCKET_NAME, 'key-prefix/PCA-2017-11-06-14:14:15.671/matrix_1.pbr'.format(TIMESTAMP))
mock_s3.Object.assert_any_call(
BUCKET_NAME, 'key-prefix/PCA-2017-11-06-14:14:15.671/matrix_2.pbr'.format(TIMESTAMP))
mock_s3.Object.assert_any_call(
BUCKET_NAME, 'key-prefix/PCA-2017-11-06-14:14:15.671/.amazon.manifest'.format(TIMESTAMP))
assert mock_object.put.call_count == 4
def test_init(sagemaker_session):
pca = PCA(num_components=55,
sagemaker_session=sagemaker_session,
**COMMON_ARGS)
assert pca.num_components == 55
assert pca.enable_network_isolation() is False
def test_data_location_validation(sagemaker_session):
pca = PCA(num_components=2,
sagemaker_session=sagemaker_session,
**COMMON_ARGS)
with pytest.raises(ValueError):
pca.data_location = "nots3://abcd/efgh"
def test_init(sagemaker_session):
pca = PCA(num_components=55,
sagemaker_session=sagemaker_session,
**COMMON_ARGS)
assert pca.num_components == 55
ESTIMATOR_NAME_TWO = "estimator_name_two"
SAGEMAKER_SESSION = Mock()
ESTIMATOR = Estimator(
IMAGE_NAME,
ROLE,
TRAIN_INSTANCE_COUNT,
TRAIN_INSTANCE_TYPE,
output_path="s3://bucket/prefix",
sagemaker_session=SAGEMAKER_SESSION,
)
ESTIMATOR_TWO = PCA(
ROLE,
TRAIN_INSTANCE_COUNT,
TRAIN_INSTANCE_TYPE,
NUM_COMPONENTS,
sagemaker_session=SAGEMAKER_SESSION,
)
WARM_START_CONFIG = WarmStartConfig(
warm_start_type=WarmStartTypes.IDENTICAL_DATA_AND_ALGORITHM, parents={"p1", "p2", "p3"}
)
TUNING_JOB_DETAILS = {
"HyperParameterTuningJobConfig": {
"ResourceLimits": {"MaxParallelTrainingJobs": 1, "MaxNumberOfTrainingJobs": 1},
"HyperParameterTuningJobObjective": {
"MetricName": OBJECTIVE_METRIC_NAME,
"Type": "Minimize",
},
def test_required_hyper_parameters_value(sagemaker_session, required_hyper_parameters, value):
with pytest.raises(ValueError):
test_params = ALL_REQ_ARGS.copy()
test_params[required_hyper_parameters] = value
PCA(sagemaker_session=sagemaker_session, **test_params)
def test_image(sagemaker_session):
pca = PCA(sagemaker_session=sagemaker_session, **ALL_REQ_ARGS)
assert pca.train_image() == registry(REGION, 'pca') + '/pca:1'
def test_init_required_positional(sagemaker_session):
pca = PCA(ROLE, TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE, NUM_COMPONENTS, sagemaker_session=sagemaker_session)
assert pca.role == ROLE
assert pca.train_instance_count == TRAIN_INSTANCE_COUNT
assert pca.train_instance_type == TRAIN_INSTANCE_TYPE
assert pca.num_components == NUM_COMPONENTS
def test_optional_hyper_parameters_value(sagemaker_session, optional_hyper_parameters, value):
with pytest.raises(ValueError):
test_params = ALL_REQ_ARGS.copy()
test_params.update({optional_hyper_parameters: value})
PCA(sagemaker_session=sagemaker_session, **test_params)
def test_data_location_validation(sagemaker_session):
pca = PCA(num_components=2, sagemaker_session=sagemaker_session, **COMMON_ARGS)
with pytest.raises(ValueError):
pca.data_location = "nots3://abcd/efgh"
def test_image(sagemaker_session):
pca = PCA(sagemaker_session=sagemaker_session, **ALL_REQ_ARGS)
assert image_uris.retrieve("pca", REGION) == pca.training_image_uri()
def test_image(sagemaker_session):
pca = PCA(num_components=55,
sagemaker_session=sagemaker_session,
**COMMON_ARGS)
assert pca.train_image() == registry('us-west-2') + '/pca:1'
def test_data_location_does_not_call_default_bucket(sagemaker_session):
data_location = "s3://my-bucket/path/"
pca = PCA(num_components=2, sagemaker_session=sagemaker_session, data_location=data_location, **COMMON_ARGS)
assert pca.data_location == data_location
assert not sagemaker_session.default_bucket.called