data-science-environment-quickstart.yaml

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: MIT-0

AWSTemplateFormatVersion: '2010-09-09'
Description: |
  This template provisions an end-to-end secure Data Science environment with MLOps project template.
  It deploys:
     - a VPC with two private and public subnets
     - two NAT gateways: one in each availability zone
     - route tables
     - security groups
     - VPC endpoints
     - IAM roles and KMS keys
     - Amazon S3 buckets for SageMaker data and models
     - SageMaker Studio domain and default user profile
     - AWS Service Catalog portfolios and products
  **WARNING** This template creates AWS resources. You will be billed for the AWS
  resources used if you create a stack from this template.

Metadata:
  AWS::CloudFormation::Interface:
    ParameterGroups:
      - Label: 
          default: Data Science environment
        Parameters:
          - EnvName
          - EnvType
      - Label:
          default: Deployment Options
        Parameters:
          - CreateSharedServices
      - Label:
          default: S3 Bucket Name with MLOps Seed Code
        Parameters:
          - SeedCodeS3BucketName
      - Label:
          default: Network Configuration
        Parameters:
          - VPCCIDR
          - PrivateSubnet1ACIDR
          - PrivateSubnet2ACIDR
          - PrivateSubnet3ACIDR
          - PublicSubnet1CIDR
          - PublicSubnet2CIDR
          - PublicSubnet3CIDR

    ParameterLabels:
      EnvName:
        default: Environment name
      EnvType:
        default: Environment type
      CreateSharedServices:
        default: Create Shared Services (PyPI mirror)
      SeedCodeS3BucketName:
        default: Existing S3 bucket name where MLOps seed code will be stored
      VPCCIDR:
        default: VPC CIDR block
      PrivateSubnet1ACIDR:
        default: Private subnet 1A CIDR
      PrivateSubnet2ACIDR:
        default: Private subnet 2A CIDR
      PublicSubnet1CIDR:
        default: Public subnet 1 CIDR
      PublicSubnet2CIDR:
        default: Public subnet 2 CIDR

Outputs:
  AssumeDSAdministratorRole:
    Description: URL for assuming the role of a cross-environment data science admin
    Value: !GetAtt DataScienceCore.Outputs.AssumeDSAdministratorRole

  AssumeTeamAdminRole:
    Description: URL for assuming the role of a environment admin
    Value: !GetAtt DataScienceEnvironment.Outputs.AssumeTeamAdminRole

  AssumeDataScientistRole:
    Description: URL for assuming the role of a environment user
    Value: !GetAtt DataScienceEnvironment.Outputs.AssumeDataScientistRole

  SageMakerDomainId:
    Description: SageMaker Domain Id
    Value: !GetAtt DataScienceEnvironment.Outputs.SageMakerDomainId

Parameters:
  EnvName:
    Type: String
    AllowedPattern: '[a-z0-9\-]*'
    Description: Please specify your data science environment name.  Used as a prefix for environment resource names.

  EnvType:
    Description: System Environment (e.g. dev, test, prod). Used as a prefix for environment resource names.
    Type: String
    Default: dev

  CreateSharedServices:
    Type: String
    Default: 'NO'
    AllowedValues:
        - 'YES'
        - 'NO'
    Description: Set to YES if you do want to provision the shared services VPC network and PyPi mirror repository

  SeedCodeS3BucketName:
    Description: S3 bucket name to store MLOps seed code (the S3 bucket must exist)
    Type: String

  VPCCIDR:
    AllowedPattern: ^(([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])\.){3}([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])(\/(1[6-9]|2[0-8]))$
    ConstraintDescription: CIDR block parameter must be in the form x.x.x.x/16-28
    Default: 10.0.0.0/16
    Description: CIDR block for the new VPC
    Type: String

  PrivateSubnet1ACIDR:
    AllowedPattern: ^(([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])\.){3}([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])(\/(1[6-9]|2[0-8]))$
    ConstraintDescription: CIDR block parameter must be in the form x.x.x.x/16-28
    Default: 10.0.0.0/19
    Description: CIDR block for private subnet 1A located in Availability Zone 1
    Type: String

  PrivateSubnet2ACIDR:
    AllowedPattern: ^(([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])\.){3}([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])(\/(1[6-9]|2[0-8]))$
    ConstraintDescription: CIDR block parameter must be in the form x.x.x.x/16-28
    Default: 10.0.32.0/19
    Description: CIDR block for private subnet 2A located in Availability Zone 2
    Type: String

  PrivateSubnet3ACIDR:
    AllowedPattern: ^(([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])\.){3}([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])(\/(1[6-9]|2[0-8]))$
    ConstraintDescription: CIDR block parameter must be in the form x.x.x.x/16-28
    Default: 10.0.64.0/19
    Description: CIDR block for private subnet 3A located in Availability Zone 3
    Type: String

  PublicSubnet1CIDR:
    AllowedPattern: ^(([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])\.){3}([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])(\/(1[6-9]|2[0-8]))$
    ConstraintDescription: CIDR block parameter must be in the form x.x.x.x/16-28
    Default: 10.0.128.0/20
    Description: CIDR block for the public DMZ subnet 1 located in Availability Zone 1
    Type: String

  PublicSubnet2CIDR:
    AllowedPattern: ^(([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])\.){3}([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])(\/(1[6-9]|2[0-8]))$
    ConstraintDescription: CIDR block parameter must be in the form x.x.x.x/16-28
    Default: 10.0.144.0/20
    Description: CIDR block for the public DMZ subnet 2 located in Availability Zone 2
    Type: String

  PublicSubnet3CIDR:
    AllowedPattern: ^(([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])\.){3}([0-9]|[1-9][0-9]|1[0-9]{2}|2[0-4][0-9]|25[0-5])(\/(1[6-9]|2[0-8]))$
    ConstraintDescription: CIDR block parameter must be in the form x.x.x.x/16-28
    Default: 10.0.160.0/20
    Description: CIDR block for the public DMZ subnet 3 located in Availability Zone 3
    Type: String

Rules:  
  CIDR:
    Assertions:
      - Assert: !And
          - !Not [ !Equals [ !Ref VPCCIDR, '' ] ]
          - !Not [ !Equals [ !Ref PrivateSubnet1ACIDR, '' ] ]
          - !Not [ !Equals [ !Ref PrivateSubnet2ACIDR, '' ] ]
          - !Not [ !Equals [ !Ref PrivateSubnet3ACIDR, '' ] ]
          - !Not [ !Equals [ !Ref PublicSubnet1CIDR, '' ] ]
          - !Not [ !Equals [ !Ref PublicSubnet2CIDR, '' ] ]
          - !Not [ !Equals [ !Ref PublicSubnet3CIDR, '' ] ]
        AssertDescription: You must provide all CIDR blocks for VPC, three private and three public subnets

Conditions:
  SharedServicesCondition: !Equals [ !Ref CreateSharedServices, 'YES' ]

Resources:
  # Core and shared services
  DataScienceCore:
    Type: AWS::CloudFormation::Stack
    Properties:
      Parameters:
        StackSetName: 'ds-quickstart'
        CreateSharedServices: !Ref CreateSharedServices
      TemplateURL: core-main.yaml
      Tags:
        - Key: EnvironmentName
          Value: !Ref EnvName
        - Key: EnvironmentType
          Value: !Ref EnvType

  # Data Science environment
  DataScienceEnvironment:
    Type: AWS::CloudFormation::Stack
    DependsOn: 'DataScienceCore'
    Properties:
      Parameters:
        EnvName: !Ref EnvName
        EnvType: !Ref EnvType
        StartKernelGatewayApps: 'YES'
        UseSharedServicesPyPiMirror: !If [ SharedServicesCondition, 'YES', 'NO' ]
        AvailabilityZones: !Join
          - ','
          - - !Sub '${AWS::Region}a'
            - !Sub '${AWS::Region}b'
        NumberOfAZs: '2'
        VPCCIDR: !Ref VPCCIDR
        PrivateSubnet1ACIDR: !Ref PrivateSubnet1ACIDR
        PrivateSubnet2ACIDR: !Ref PrivateSubnet2ACIDR
        PublicSubnet1CIDR: !Ref PublicSubnet1CIDR
        PublicSubnet2CIDR: !Ref PublicSubnet2CIDR
        SeedCodeS3BucketName: !Ref SeedCodeS3BucketName
      TemplateURL: env-main.yaml
      Tags:
        - Key: EnvironmentName
          Value: !Ref EnvName
        - Key: EnvironmentType
          Value: !Ref EnvType