def test_marketplace_transform_job_from_model_package(sagemaker_session,
cpu_instance_type):
data_path = os.path.join(DATA_DIR, "marketplace", "training")
shape = pandas.read_csv(data_path + "/iris.csv", header=None).drop([0],
axis=1)
TRANSFORM_WORKDIR = DATA_DIR + "/marketplace/transform"
shape.to_csv(TRANSFORM_WORKDIR + "/batchtransform_test.csv",
index=False,
header=False)
transform_input = sagemaker_session.upload_data(
TRANSFORM_WORKDIR, key_prefix="integ-test-data/marketplace/transform")
region = sagemaker_session.boto_region_name
account = REGION_ACCOUNT_MAP[region]
model_package_arn = MODEL_PACKAGE_ARN.format(
partition=_aws_partition(region), region=region, account=account)
model = ModelPackage(
role="SageMakerRole",
model_package_arn=model_package_arn,
sagemaker_session=sagemaker_session,
)
transformer = model.transformer(1, cpu_instance_type)
transformer.transform(transform_input, content_type="text/csv")
transformer.wait()
def test_marketplace_transform_job_from_model_package(sagemaker_session):
data_path = os.path.join(DATA_DIR, 'marketplace', 'training')
shape = pandas.read_csv(data_path + '/iris.csv', header=None).drop([0], axis=1)
TRANSFORM_WORKDIR = DATA_DIR + '/marketplace/transform'
shape.to_csv(TRANSFORM_WORKDIR + '/batchtransform_test.csv', index=False, header=False)
transform_input = sagemaker_session.upload_data(
TRANSFORM_WORKDIR,
key_prefix='integ-test-data/marketplace/transform')
model = ModelPackage(role='SageMakerRole',
model_package_arn=(MODEL_PACKAGE_ARN % sagemaker_session.boto_region_name),
sagemaker_session=sagemaker_session)
transformer = model.transformer(1, 'ml.m4.xlarge')
transformer.transform(transform_input, content_type='text/csv')
transformer.wait()
def cli():
"""
Simply run this script with '--help' to see all options.
"""
desc = "Pipeline to train a AWS Marketplace model on Woocommerce data and upload cross-sell product recommendations"
logging.basicConfig(format="%(asctime)s : %(levelname)s : %(message)s",
level=logging.INFO)
parser = argparse.ArgumentParser(description=desc)
parser.add_argument("-i",
"--input",
help="input path",
dest="input",
required=True)
parser.add_argument("-o",
"--output",
help="output_path",
dest="output",
required=True)
args = parser.parse_args()
logging.info("configure services")
config = Configuration("configs/config.json").parameters
s3 = S3(
region_name=config["s3"]["region_name"],
access_key=config["aws_keys"]["access_key"],
secret_key=config["aws_keys"]["secret_key"],
bucket=config["s3"]["bucket"],
)
woocommerce = Woocommerce(
url=config["woocommerce"]["url"],
consumer_key=config["woocommerce"]["consumer_key"],
consumer_secret=config["woocommerce"]["consumer_secret"],
)
logging.info("download data from Woocommerce")
woocommerce.download_data(args.input)
logging.info("upload data to S3")
s3.upload(args.input, config["s3"]["input_file"])
logging.info("configure Batch Transform Job")
model_package_arn = config["batch_transform_job"]["model_package_arn"]
iam = boto3.client("iam")
role = iam.get_role(
RoleName=config["batch_transform_job"]["role_name"])["Role"]["Arn"]
sagemaker_session = sagemaker.Session()
model = ModelPackage(
model_package_arn=model_package_arn,
role=role,
sagemaker_session=sagemaker_session,
)
output_path = "s3://" + os.path.join(config["s3"]["bucket"], "output")
transformer = model.transformer(
instance_count=config["batch_transform_job"]["instance_count"],
instance_type=config["batch_transform_job"]["instance_type"],
output_path=output_path,
)
input_path = "s3://" + os.path.join(config["s3"]["bucket"],
config["s3"]["input_file"])
transformer.transform(input_path, content_type="text/csv")
logging.info('batch transform job starting')
transformer.wait()
logging.info("downloading recommendations from S3")
bucket_folder = transformer.output_path.rsplit("/")[3]
key = os.path.join(bucket_folder,
config["s3"]["input_file"].split("/")[-1] + ".out")
s3.download(key, args.output)
logging.info("Push recommendations to Woocommerce")
woocommerce.upload_recommendations(args.output)