from datetime import datetime
from sagemaker.transformer import Transformer
from sagemaker.inputs import BatchDataCaptureConfig

input_s3_data_location = "s3://bucket/prefix/batch-transform/input/input.json"
output_s3_data_location = "s3://bucket/prefix/batch-transform/output"
data_capture_destination = "s3://bucket/prefix/batch-transform/captured-data"
model_name = "my-previously-created-model"

transformer = Transformer(
    model_name=model_name,
    strategy="SingleRecord",
    instance_count=1,
    instance_type="ml.m5.large",
    output_path=output_s3_data_location,
    max_concurrent_transforms=1,
    max_payload=6,
    tags=[{"Key": "some-key", "Value": "some-value"}],
)

timestamp = datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
job_name = f"batch-transform-{timestamp}"

transform_arg = transformer.transform(
    job_name=job_name,
    data=input_s3_data_location,
    data_type="S3Prefix",
    content_type="application/json", 
    split_type="Line",
    wait=True,
    logs=True,
)

transform_arg = transformer.transform(
    batch_data_capture_config=BatchDataCaptureConfig(
        destination_s3_uri=data_capture_destination,
        generate_inference_id=True,
    ),
    job_name=job_name,
    data=input_s3_data_location,
    data_type="S3Prefix",
    content_type="application/json",
    split_type="Line",
    wait=True,
    logs=True,
)