ML/.github/workflows/MLPipelinePullRequest.yml

name: Build and test model using a dummy prediction pipeline

on:
  # push:
  #   branches:
  #     - "model-**"
  pull_request:
    branches: ["sap-dev", "heat-dev", "carbon-dev", "sap_baseline-dev"]
  label:
    types: ["created", "edited"]

permissions: write-all

jobs:
  Check-Label:
    runs-on: ubuntu-latest
    steps:
      - uses: yogevbd/enforce-label-action@2.1.0
        with:
          REQUIRED_LABELS_ANY: "major,minor,patch"
          REQUIRED_LABELS_ANY_DESCRIPTION: "Select at least one label ['major','minor','patch']"
          BANNED_LABELS: "banned"

  # No-Label:
  #   if: ${{ github.event.label.name != 'major' }} || ${{ github.event.label.name != 'minor' }}  || ${{ github.event.label.name != 'patch' }}
  #   runs-on: ubuntu-latest

  #   steps:
  #   - name: No label associated with PR
  #     run: |
  #       echo "Please choose one of these tags: 'major', 'major', 'patch'"
  #       exit(1)

  Verify-Lambda:
    runs-on: ubuntu-latest

    steps:
      - uses: actions/checkout@v3
      - name: Install packages to retrieve artifacts
        env:
          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
        run: |
          pip install --upgrade pip
          pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt

      - name: Retrieve artifacts (dvc.lock)
        env:
          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
        run: |
          cd modules/ml-pipeline/src/pipeline
          dvc pull -r experiments

      - name: Set timestamp
        id: set_timestamp
        run: |
          echo "timestamp=$(date +%Y%m%d)" >> $GITHUB_ENV
          echo "Generated timestamp: ${timestamp}"

      - name: Upload sample row dataset to S3
        env:
          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
        run: |
          cd modules/ml-pipeline/src/pipeline/data/prepared_data/
          aws s3 cp sample_test.parquet s3://retrofit-data-dev/sap_change_model/sample_data_for_cicd/${timestamp}/sample_test.parquet

      - name: Build Lambda docker Image
        run: |
          docker build . --file ./deployment/Dockerfile.prediction.lambda --tag lambda_test

      - name: Run lambda docker container
        env:
          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
        run: |
          docker run -d -p 9000:8080 \
            -e AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID} \
            -e AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY} \
            -e RUNTIME_ENVIRONMENT=dev \
            -e PREDICTIONS_BUCKET=retrofit-sap-predictions-dev lambda_test

      - name: Test Lambda endpoint
        run: |
          sleep 2
          curl -X POST "http://localhost:9000/2015-03-31/functions/function/invocations" \
            -H "Content-Type: application/json" \
            -d "{\"body\": \"{\\\"file_location\\\": \\\"s3://retrofit-data-dev/sap_change_model/sample_data_for_cicd/${timestamp}/sample_test.parquet\\\", \\\"property_id\\\": 1, \\\"portfolio_id\\\": 4, \\\"created_at\\\": \\\"now\\\", \\\"warm\\\": true}\"}"

      - name: Get Lambda logs
        run: |
          docker logs $(docker ps -al -q)

      - name: Test Lambda endpoint again
        run: |
          sleep 2
          curl -X POST "http://localhost:9000/2015-03-31/functions/function/invocations" \
            -H "Content-Type: application/json" \
            -d "{\"body\": \"{\\\"file_location\\\": \\\"s3://retrofit-data-dev/sap_change_model/sample_data_for_cicd/${timestamp}/sample_test.parquet\\\", \\\"property_id\\\": 1, \\\"portfolio_id\\\": 4, \\\"created_at\\\": \\\"now\\\", \\\"testing\\\": true}\"}"

      - name: Get Lambda logs
        run: |
          docker logs $(docker ps -al -q)

      - name: Stop Lambda container
        run: |
          docker stop lambda_test || echo "Container already stopped"

      - name: Remove uploaded sample row dataset from S3
        if: always()
        env:
          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
        run: |
          aws s3 rm --recursive s3://retrofit-data-dev/sap_change_model/sample_data_for_cicd/${timestamp}/

  Verify-Model:
    runs-on: ubuntu-latest

    steps:
      - uses: actions/checkout@v3
      - name: Install packages to retrieve artifacts
        env:
          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
        run: |
          pip install --upgrade pip
          pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt

      - name: Retrieve artifacts (dvc.lock)
        env:
          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
        run: |
          cd modules/ml-pipeline/src/pipeline
          dvc pull -r experiments

      - name: Build Prediction docker Image
        run: |
          cd modules/ml-pipeline/src/
          docker build . --file Prediction.Dockerfile --tag prediction_test

      - name: Run Prediction docker container
        run: |
          docker run prediction_test

  Trigger-CML:
    runs-on: ubuntu-latest

    steps:
      - uses: actions/checkout@v3
      - name: Install packages to retrieve artifacts
        run: |
          pip install --upgrade pip
          pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt

      - name: Retrieve artifacts (dvc.lock)
        env:
          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
        run: |
          cd modules/ml-pipeline/src/pipeline
          dvc pull -r experiments

      - uses: actions/setup-python@v4
      - uses: iterative/setup-cml@v1
      - name: Generate report
        env:
          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
          REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          TARGET_BRANCH: ${{ github.base_ref }}
        run: |
          cd modules/ml-pipeline/src/pipeline
          echo "## Model metrics" > report.md

          # Compare metrics to master
          git fetch --depth=1 origin ${TARGET_BRANCH}:${TARGET_BRANCH}
          dvc metrics diff --md --all ${TARGET_BRANCH} >> report.md

          echo "## Scenario comparison" >> report.md

          cat metrics/scenario_table.md >> report.md

          echo "" >> report.md

          echo "## Scenario metrics" >> report.md

          cat metrics/scenario_metrics.md >> report.md

          cml comment create report.md

          # echo "## Residuals plot from model" >> report.md
          # metrics_location=$(find . -maxdepth 10 -name "residuals.png")
          # echo $metrics_location
          # cd $metric_location
          # echo "![](./residuals.png)" >> report.md