def test_prepare_for_training_no_mini_batch_size(sagemaker_session):
pca = PCA(base_job_name='pca', sagemaker_session=sagemaker_session, **ALL_REQ_ARGS)
data = RecordSet('s3://{}/{}'.format(BUCKET_NAME, PREFIX), num_records=1, feature_dim=FEATURE_DIM,
channel='train')
pca._prepare_for_training(data)
assert pca.mini_batch_size == 1
def test_prepare_for_training_multiple_channel(sagemaker_session):
lr = PCA(base_job_name='lr', sagemaker_session=sagemaker_session, **ALL_REQ_ARGS)
data = RecordSet('s3://{}/{}'.format(BUCKET_NAME, PREFIX), num_records=1, feature_dim=FEATURE_DIM,
channel='train')
lr._prepare_for_training([data, data])
assert lr.mini_batch_size == 1
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_multiple_channel_no_train(sagemaker_session):
lr = PCA(base_job_name='lr', sagemaker_session=sagemaker_session, **ALL_REQ_ARGS)
data = RecordSet('s3://{}/{}'.format(BUCKET_NAME, PREFIX), num_records=1, feature_dim=FEATURE_DIM,
channel='mock')
with pytest.raises(ValueError) as ex:
lr._prepare_for_training([data, data])
assert 'Must provide train channel.' in str(ex)
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_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)
