/sagemaker-byoc-pmml-example

Primary LanguageJupyter Notebook

Serving JPMML-based Tree-based models on Amazon SageMaker

This example notebook demonstrates how to bring your own java-based container and serve PMML based Models on Amazon SageMaker for Inference.

Getting Started

  • Open AWS Console
  • Search “SageMaker” and click “Amazon Sagemaker”

image

  • Click Notebook -> Notebook Instances -> Create notebook Instances

image

  • Create Notebook Instance with the following details

    Notebook instance name – “sagemaker-immersion-day”

    Notebook instance type – “ml.m5.xlarge”

  • Go back to Notebook instance tab page and Open the notebook instance when status is InService -> Click “Open JupyterLab”. This will open a JupyterLab Interface.

  • Go to "Git" from the top menu and select "Clone a Repository" as shown below

Notebook-git-clone

- Clone this repo - https://github.com/dhawalkp/sagemaker-byoc-pmml-example.git as shown below

Notebook-git-clone-w-url

  • Click “sagemaker-byoc-pmml-example” folder -> JPMML_Models_SageMaker.ipynb and follow the instructions

image

  • Select conda_python3 as the kernel in order to execute the notebook.