azdo-ci-build-train.yml

pr: none
trigger:
  branches:
    include:
    - master
  paths:
    exclude:
    - docs/
    - environment_setup/
    - charts/
    - ml_service/util/create_scoring_image.py

variables:
- template: azdo-variables.yml
- group: devopsforai-aml-vg


stages:
- stage: 'Model_CI'
  displayName: 'Model CI'
  jobs:
  - job: "Model_CI_Pipeline"
    displayName: "Model CI Pipeline"
    pool:
      vmImage: 'ubuntu-latest'
    container: mcr.microsoft.com/mlops/python:latest
    timeoutInMinutes: 0
    steps:
    - template: azdo-base-pipeline.yml
    - script: |
        # Invoke the Python building and publishing a training pipeline
        python3 $(Build.SourcesDirectory)/ml_service/pipelines/${{ variables.BUILD_TRAIN_SCRIPT }}
      failOnStderr: 'false'
      env:
        SP_APP_SECRET: '$(SP_APP_SECRET)'
      displayName: 'Publish Azure Machine Learning Pipeline'
- stage: 'Trigger_AML_Pipeline'
  displayName: 'Train, evaluate, register model via previously published AML pipeline'
  jobs:
  - job: "Get_Pipeline_ID"
    condition: and(succeeded(), eq(coalesce(variables['auto-trigger-training'], 'true'), 'true'))
    displayName: "Get Pipeline ID for execution"
    pool:
      vmImage: 'ubuntu-latest'
    container: mcr.microsoft.com/mlops/python:latest
    timeoutInMinutes: 0
    steps:
    - script: |
        python $(Build.SourcesDirectory)/ml_service/pipelines/run_train_pipeline.py
        # Set AMLPIPELINEID variable for next AML Pipeline task in next job
        source $(Build.SourcesDirectory)/tmp.sh
        echo "##vso[task.setvariable variable=AMLPIPELINEID;isOutput=true]$AMLPIPELINE_ID"
        rm $(Build.SourcesDirectory)/tmp.sh
      name: 'getpipelineid'
      displayName: 'Get Pipeline ID'
      env:
        SP_APP_SECRET: '$(SP_APP_SECRET)'
  - job: "Run_ML_Pipeline"
    dependsOn: "Get_Pipeline_ID"
    displayName: "Trigger ML Training Pipeline"
    pool: server
    variables:
      AMLPIPELINE_ID: $[ dependencies.Get_Pipeline_ID.outputs['getpipelineid.AMLPIPELINEID'] ]
    steps:
    - task: ms-air-aiagility.vss-services-azureml.azureml-restApi-task.MLPublishedPipelineRestAPITask@0
      displayName: 'Invoke ML pipeline'
      inputs:
        azureSubscription: '$(WORKSPACE_SVC_CONNECTION)'
        PipelineId: '$(AMLPIPELINE_ID)'
        ExperimentName: '$(EXPERIMENT_NAME)'
        PipelineParameters: '"model_name": "sklearn_regression_model.pkl"'
  - job: "Training_Run_Report"
    dependsOn: "Run_ML_Pipeline"
    displayName: "Determine if evaluation succeeded and new model is registered"
    pool:
      vmImage: 'ubuntu-latest'
    container: mcr.microsoft.com/mlops/python:latest
    timeoutInMinutes: 0
    steps:
    - script: |
        python $(Build.SourcesDirectory)/code/register/register_model.py --build_id $(Build.BuildId) --validate True
      displayName: 'Check if new model registered'
      env:
        SP_APP_SECRET: '$(SP_APP_SECRET)'
    - task: CopyFiles@2
      displayName: 'Copy Files to: $(Build.ArtifactStagingDirectory)'
      inputs:
        SourceFolder: '$(Build.SourcesDirectory)'
        TargetFolder: '$(Build.ArtifactStagingDirectory)'
        Contents: |
          code/scoring/**
    - task: PublishBuildArtifacts@1
      displayName: 'Publish Artifact'
      inputs:
        ArtifactName: 'mlops-pipelines'
        publishLocation: 'container'
        pathtoPublish: '$(Build.ArtifactStagingDirectory)' 
        TargetPath: '$(Build.ArtifactStagingDirectory)'