This is a sample solution to build a safe deployment pipeline for Amazon SageMaker. This example could be useful for any organization looking to operationalize machine learning with native AWS development tools such as AWS CodePipeline, AWS CodeBuild and AWS CodeDeploy.

This solution provides as safe deployment by creating an AWS Lambda API that calls into an Amazon SageMaker Endpoint for real-time inference.

Following is a diagram of the continuous delivery stages in the AWS Code Pipeline.

1. Build Artifacts: Runs a AWS CodeBuild job to create AWS CloudFormation templates.
2. Train: Trains an Amazon SageMaker pipeline and Baseline Processing Job
3. Deploy Dev: Deploys a development Amazon SageMaker Endpoint
4. Deploy Prod: Deploys an AWS API Gateway Lambda in front of Amazon SageMaker Endpoints using AWS CodeDeploy for blue/green deployment and rollback.

• AWS SageMaker – This solution uses SageMaker to train the model to be used and host the model at an endpoint, where it can be accessed via HTTP/HTTPS requests
• AWS CodePipeline – CodePipeline has various stages defined in CloudFormation which step through which actions must be taken in which order to go from source code to creation of the production endpoint.
• AWS CodeBuild – This solution uses CodeBuild to build the source code from GitHub
• AWS CloudFormation – This solution uses the CloudFormation Template language, in either YAML or JSON, to create each resource including custom resource.
• AWS S3 – Artifacts created throughout the pipeline as well as the data for the model is stored in an Simple Storage Service (S3) Bucket.

Following is the list of steps required to get up and running with this sample.

Create your AWS account at http://aws.amazon.com by following the instructions on the site.

1. Fork a copy of this repository into your own GitHub account by clicking the Fork in the upper right-hand corner.
2. Follow the steps in the GitHub documentation to create a new (OAuth 2) token with the following scopes (permissions): admin:repo_hook and repo. If you already have a token with these permissions, you can use that. You can find a list of all your personal access tokens in https://github.com/settings/tokens.
3. Copy the access token to your clipboard. For security reasons, after you navigate off the page, you will not be able to see the token again. If you have lost your token, you can regenerate your token.

Click on the Launch Stack button below to launch the CloudFormation Stack to set up the SageMaker safe deployment pipeline.

Provide a stack name eg sagemaker-safe-deployment-pipeline and specify the parameters

You can launch the same stack using the AWS CLI. Here's an example:

aws cloudformation create-stack --stack-name sagemaker-safe-deployment \ --template-body file://pipeline.yml \ --capabilities CAPABILITY_IAM \ --parameters \ ParameterKey=ModelName,ParameterValue=mymodelname \ ParameterKey=GitHubUser,[email protected] \ ParameterKey=GitHubToken,ParameterValue=YOURGITHUBTOKEN12345ab1234234

Once the deployment has completed, there will be a new AWS CodePipeline created linked to your GitHub source. You will notice initially that it will be in a Failed state as it is waiting on an S3 data source.

Launch the newly created SageMaker Notebook in your AWS console, navigate to the notebook directory and opening the notebook by clicking on the mlops.ipynb link.

Once the notebook is running, you will be guided through a series of steps starting with downloading the New York City Taxi dataset, uploading this to an Amazon SageMaker S3 bucket along with the data source meta data to trigger a new build in the AWS CodePipeline.

Once your pipeline is kicked off it will run model training and deploy a development SageMaker Endpoint.

There is a manual approval step which you can action directly within the SageMaker Notebook to promote this to production, send some traffic to the live endpoint and create a REST API.

Subsequent deployments of the pipeline will use AWS CodeDeploy to perform a blue/green deployment to shift traffic from the Original to Replacement endpoint over a period of 5 minutes.

Finally, the SageMaker Notebook provides the ability to retrieve the results from the Monitoring Schedule that is run on the hour.

Following is a lis of approximate running times fo the pipeline

• Full Pipeline: 35 minutes
• Start Build: 2 Minutes
• Model Training and Baseline: 5 Minutes
• Launch Dev Endpoint: 10 minutes
• Launch Prod Endpoint: 15 minutes
• Monitoring Schedule: Runs on the hour

This project is written in Python, and design to be customized for your own model and API.

.
├── api
│   ├── __init__.py
│   ├── app.py
│   ├── post_traffic_hook.py
│   └── pre_traffic_hook.py
├── model
│   ├── buildspec.yml
│   ├── requirements.txt
│   └── run.py
├── notebook
│   └── mlops.ipynb
└── pipeline.yml

Edit the get_training_params method in the model/run.py script that is run as part of the AWS CodeBuild step to add your own estimator or model definition.

Extend the AWS Lambda hooks in api/pre_traffic_hook.py and api/post_traffic_hook.py to add your own validation or inference against the deployed Amazon SageMaker endpoints. Also you can edit the api/app.py lambda to add any enrichment or transformation to the request/response payload.

This section outlines cost considerations for running the SageMaker Safe Deployment Pipeline. Completing the pipeline will deploy development and production SageMaker endpoints which will cost less than $10 per day. Further cost breakdowns are below.

• CodeBuild – Charges per minute used. First 100 minutes each month come at no charge. For information on pricing beyond the first 100 minutes, see AWS CodeBuild Pricing.
• CodeCommit – $1/month if you didn't opt to use your own GitHub repository.
• CodeDeploy – No cost with AWS Lambda.
• CodePipeline – CodePipeline costs $1 per active pipeline* per month. Pipelines are free for the first 30 days after creation. More can be found at AWS CodePipeline Pricing.
• CloudWatch - This template includes a Canary, 1 dashboard and 4 alarms (2 for deployment, 1 for model drift and 1 for canary) which costs less than $10 per month.
  • Canaries cost $0.0012 per run, or $5/month if they run every 10 minutes.
  • Dashboards cost $3/month.
  • Alarm metrics cost $0.10 per alarm.
• KMS – $1/month for the key created.
• Lambda - Low cost, $0.20 per 1 million request see Amazon Lambda Pricing
• SageMaker – Prices vary based on EC2 instance usage for the Notebook Instances, Model Hosting, Model Training and Model Monitoring; each charged per hour of use. For more information, see Amazon SageMaker Pricing.
  • The ml.t3.medium instance notebook costs $0.0582 an hour.
  • The ml.m4.xlarge instance for the training job costs $0.28 an hour.
  • The ml.m5.xlarge instance for the monitoring baseline costs $0.269 an hour.
  • The ml.t2.medium instance for the dev hosting endpoint costs $0.065 an hour.
  • The two ml.m5.large instances for production hosting endpoint costs 2 x $0.134 per hour.
  • The ml.m5.xlarge instance for the hourly scheduled monitoring job costs $0.269 an hour.
• S3 – Prices Vary, depends on size of model/artifacts stored. For first 50 TB each month, costs only $0.023 per GB stored. For more information, see Amazon S3 Pricing.

First delete the stacks used as part of the pipeline for deployment, training job and suggest baseline. For a model name of nyctaxi that would be.

• nyctaxi-devploy-prd
• nyctaxi-devploy-dev
• nyctaxi-training-job
• nyctaxi-suggest-baseline

Then delete the stack you created.

See CONTRIBUTING for more information.

This library is licensed under the MIT-0 License. See the LICENSE file.