Merge pull request #168 from Hestia-Homes/heat_baseline-dev-model

Initial model for heat_baseline

.github/workflows/Deploy.yml

@@ -2,7 +2,17 @@ name: Sap Change Model Deploy
 
 on:
   push:
-    branches: [ sap-dev, sap-prod, heat-dev, heat-prod, carbon-dev, carbon-prod]
+    branches:
+      [
+        sap-dev,
+        sap-prod,
+        heat-dev,
+        heat-prod,
+        carbon-dev,
+        carbon-prod,
+        heat_baseline-dev,
+        heat_baseline-prod,
+      ]
 
 jobs:
   deploy:
@@ -31,8 +41,8 @@ jobs:
       - name: set secret prefix which is used across multiple steps
         id: secret_prefix
         run: |
-            # Convert branch name to uppercase and replace hyphens with underscores
+          # Convert branch name to uppercase and replace hyphens with underscores
-            echo "::set-output name=secret_prefix::$(echo "${{ github.ref_name }}" | tr 'a-z-' 'A-Z_')"
+          echo "::set-output name=secret_prefix::$(echo "${{ github.ref_name }}" | tr 'a-z-' 'A-Z_')"
 
       - name: Set domain name
         id: set_domain
@@ -116,7 +126,7 @@ jobs:
         env:
           RUNTIME_ENVIRONMENT: ${{ steps.set_runtime_environment.outputs.runtime_environment }}
           PREDICTIONS_BUCKET: ${{ steps.set_s3_buckets.outputs.predictions_bucket }}
-          DATA_BUCKET:  ${{ steps.set_s3_buckets.outputs.data_bucket }}
+          DATA_BUCKET: ${{ steps.set_s3_buckets.outputs.data_bucket }}
           DOMAIN_NAME: ${{ steps.set_domain.outputs.domain }}
           ECR_URI: ${{ steps.set_ecr_credentials.outputs.ecr_uri }}
           GITHUB_SHA: ${{ github.sha }}

.github/workflows/MLPipelinePostMerge.yml

@@ -13,6 +13,7 @@ on:
       - "sap-dev"
       - "heat-dev"
       - "carbon-dev"
+      - "heat_baseline-dev"
 
 permissions: write-all
 
@@ -21,166 +22,171 @@ jobs:
     if: ${{ (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'major')) }}
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v4
+      - uses: actions/checkout@v4
-      with:
+        with:
-        fetch-depth: 0
+          fetch-depth: 0
 
-    - name: Install packages to register model
+      - name: Install packages to register model
-      run: |
+        run: |
-        pip install --upgrade pip
+          pip install --upgrade pip
-        pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
+          pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
 
-    - name: Register Model
+      - name: Register Model
-      run: |
+        run: |
-        REGISTER_MODEL_NAME=$(echo ${{ github.event.pull_request.head.ref }} | awk -F"-" '{print $1}')
+          REGISTER_MODEL_NAME=$(echo ${{ github.event.pull_request.head.ref }} | awk -F"-" '{print $1}')
-        # REGISTER_MODEL_NAME=$(echo ${{github.ref_name}} | awk -F"-" '{print $1}')
+          # REGISTER_MODEL_NAME=$(echo ${{github.ref_name}} | awk -F"-" '{print $1}')
 
-        git config user.name "Github-Bot"
+          git config user.name "Github-Bot"
-        git config user.email "Github-Bot@no-reply.com"
+          git config user.email "Github-Bot@no-reply.com"
 
-        latest_version=$(gto show ${REGISTER_MODEL_NAME}@latest --ref | awk -F"@v" '{print $2}') || false
+          latest_version=$(gto show ${REGISTER_MODEL_NAME}@latest --ref | awk -F"@v" '{print $2}') || false
-        if [ -z "${latest_version}" ]; then
+          if [ -z "${latest_version}" ]; then
-          increment_version="1.0.0"
+            increment_version="1.0.0"
-        else
+          else
-          increment_version=$(echo ${latest_version} | awk 'BEGIN {
+            increment_version=$(echo ${latest_version} | awk 'BEGIN {
-              FS="\\."   # Set the field separator to a period
+                FS="\\."   # Set the field separator to a period
-              OFS="."    # Set the output field separator to a period
+                OFS="."    # Set the output field separator to a period
-          }
+            }
-          {
+            {
-              major = $1 + 1   # Increment the major version
+                major = $1 + 1   # Increment the major version
-              print major, "0", "0"   # Print the new version
+                print major, "0", "0"   # Print the new version
-          }')
+            }')
-        fi
+          fi
 
-        new_tag=${REGISTER_MODEL_NAME}@v${increment_version}
+          new_tag=${REGISTER_MODEL_NAME}@v${increment_version}
 
-        git tag -a ${new_tag} -m "Registering new Major Version"
+          git tag -a ${new_tag} -m "Registering new Major Version"
-        git push origin ${new_tag}
+          git push origin ${new_tag}
 
-        gto show --json > MODEL_REGISTRY.md
+          gto show --json > MODEL_REGISTRY.md
-        git add .
+          git add .
-        git commit -m "Update Registry"
+          git commit -m "Update Registry"
-        git push
+          git push
 
   Register-Minor-Model-Dev:
     if: ${{ (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'minor')) }}
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v4
+      - uses: actions/checkout@v4
-      with:
+        with:
-        fetch-depth: 0
+          fetch-depth: 0
 
-    - name: Install packages to register model
+      - name: Install packages to register model
-      run: |
+        run: |
-        pip install --upgrade pip
+          pip install --upgrade pip
-        pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
+          pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
 
-    - name: Register Model
+      - name: Register Model
-      run: |
+        run: |
-        REGISTER_MODEL_NAME=$(echo ${{ github.event.pull_request.head.ref }} | awk -F"-" '{print $1}')
+          REGISTER_MODEL_NAME=$(echo ${{ github.event.pull_request.head.ref }} | awk -F"-" '{print $1}')
-        # REGISTER_MODEL_NAME=$(echo ${{github.ref_name}} | awk -F"-" '{print $1}')
+          # REGISTER_MODEL_NAME=$(echo ${{github.ref_name}} | awk -F"-" '{print $1}')
 
-        git config user.name "Github-Bot"
+          git config user.name "Github-Bot"
-        git config user.email "Github-Bot@no-reply.com"
+          git config user.email "Github-Bot@no-reply.com"
 
-        latest_version=$(gto show ${REGISTER_MODEL_NAME}@latest --ref | awk -F"@v" '{print $2}')
+          latest_version=$(gto show ${REGISTER_MODEL_NAME}@latest --ref | awk -F"@v" '{print $2}')
-        if [ -z "${latest_version}" ]; then
+          if [ -z "${latest_version}" ]; then
-          increment_version="0.1.0"
+            increment_version="0.1.0"
-        else
+          else
-          increment_version=$(echo ${latest_version} | awk 'BEGIN {
+            increment_version=$(echo ${latest_version} | awk 'BEGIN {
-              FS="\\."   # Set the field separator to a period
+                FS="\\."   # Set the field separator to a period
-              OFS="."    # Set the output field separator to a period
+                OFS="."    # Set the output field separator to a period
-          }
+            }
-          {
+            {
-              minor = $2 + 1   # Increment the minor version
+                minor = $2 + 1   # Increment the minor version
-              print $1, minor, "0"   # Print the new version
+                print $1, minor, "0"   # Print the new version
-          }')
+            }')
-        fi
+          fi
 
-        new_tag=${REGISTER_MODEL_NAME}@v${increment_version}
+          new_tag=${REGISTER_MODEL_NAME}@v${increment_version}
 
-        git tag -a ${new_tag} -m "Registering new Minor Version"
+          git tag -a ${new_tag} -m "Registering new Minor Version"
-        git push origin ${new_tag}
+          git push origin ${new_tag}
 
-        gto show --json > MODEL_REGISTRY.md
+          gto show --json > MODEL_REGISTRY.md
-        git add .
+          git add .
-        git commit -m "Update Registry"
+          git commit -m "Update Registry"
-        git push
+          git push
 
   Register-Patch-Model-Dev:
     if: ${{ (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'patch')) }}
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v4
+      - uses: actions/checkout@v4
-      with:
+        with:
-        fetch-depth: 0
+          fetch-depth: 0
 
-    - name: Install packages to register model
+      - name: Install packages to register model
-      run: |
+        run: |
-        pip install --upgrade pip
+          pip install --upgrade pip
-        pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
+          pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
 
-    - name: Register Model
+      - name: Register Model
-      run: |
+        run: |
-        REGISTER_MODEL_NAME=$(echo ${{ github.event.pull_request.head.ref }} | awk -F"-" '{print $1}')
+          REGISTER_MODEL_NAME=$(echo ${{ github.event.pull_request.head.ref }} | awk -F"-" '{print $1}')
-        # REGISTER_MODEL_NAME=$(echo ${{github.ref_name}} | awk -F"-" '{print $1}')
+          # REGISTER_MODEL_NAME=$(echo ${{github.ref_name}} | awk -F"-" '{print $1}')
 
-        git config user.name "Github-Bot"
+          git config user.name "Github-Bot"
-        git config user.email "Github-Bot@no-reply.com"
+          git config user.email "Github-Bot@no-reply.com"
 
-        latest_version=$(gto show ${REGISTER_MODEL_NAME}@latest --ref | awk -F"@v" '{print $2}')
+          latest_version=$(gto show ${REGISTER_MODEL_NAME}@latest --ref | awk -F"@v" '{print $2}')
-        if [ -z "${latest_version}" ]; then
+          if [ -z "${latest_version}" ]; then
-          increment_version="0.0.1"
+            increment_version="0.0.1"
-        else
+          else
-          increment_version=$(echo ${latest_version} | awk 'BEGIN {
+            increment_version=$(echo ${latest_version} | awk 'BEGIN {
-              FS="\\."   # Set the field separator to a period
+                FS="\\."   # Set the field separator to a period
-              OFS="."    # Set the output field separator to a period
+                OFS="."    # Set the output field separator to a period
-          }
+            }
-          {
+            {
-              patch = $3 + 1   # Increment the patch version
+                patch = $3 + 1   # Increment the patch version
-              print $1, $2, patch   # Print the new version
+                print $1, $2, patch   # Print the new version
-          }')
+            }')
-        fi
+          fi
 
-        new_tag=${REGISTER_MODEL_NAME}@v${increment_version}
+          new_tag=${REGISTER_MODEL_NAME}@v${increment_version}
 
-        git tag -a ${new_tag} -m "Registering new Patch Version"
+          git tag -a ${new_tag} -m "Registering new Patch Version"
-        git push origin ${new_tag}
+          git push origin ${new_tag}
 
-        gto show --json > MODEL_REGISTRY.md
+          gto show --json > MODEL_REGISTRY.md
-        git add .
+          git add .
-        git commit -m "Update Registry"
+          git commit -m "Update Registry"
-        git push
+          git push
 
   Promote-Artefacts-To-Dev:
     if: github.event.pull_request.merged == true
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v3
-    - name: Install packages to retrieve artifacts
+      - name: Install packages to retrieve artifacts
-      run: |
+        run: |
-        pip install --upgrade pip
+          pip install --upgrade pip
-        pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
+          pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
 
-    - name: Retrieve artifacts (dvc.lock)
+      - name: Retrieve artifacts (dvc.lock)
-      env:
+        env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
+          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
-      run: |
+        run: |
-        cd modules/ml-pipeline/src/pipeline
+          cd modules/ml-pipeline/src/pipeline
-        dvc pull -r experiments
+          dvc pull -r experiments
 
-    - name: Push artifacts to Dev
+      - name: Push artifacts to Dev
-      env:
+        env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
+          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
-      run: |
+        run: |
-        cd modules/ml-pipeline/src/pipeline
+          cd modules/ml-pipeline/src/pipeline
-        dvc push -r dev
+          dvc push -r dev
 
   Register-New-Model-Dev:
-    needs: [Register-Major-Model-Dev, Register-Minor-Model-Dev, Register-Patch-Model-Dev]
+    needs:
+      [
+        Register-Major-Model-Dev,
+        Register-Minor-Model-Dev,
+        Register-Patch-Model-Dev,
+      ]
     if: |
       always() &&
       (needs.Register-Major-Model-Dev.result == 'success' || needs.Register-Major-Model-Dev.result == 'skipped') &&
@@ -189,50 +195,50 @@ jobs:
 
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v3
-      with:
+        with:
-        fetch-depth: 0
+          fetch-depth: 0
 
-    - name: Install packages to register model
+      - name: Install packages to register model
-      run: |
+        run: |
-        pip install --upgrade pip
+          pip install --upgrade pip
-        pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
+          pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
 
-    - name: Register Model
+      - name: Register Model
-      env:
+        env:
-        TARGET_BRANCH: ${{ github.base_ref }}
+          TARGET_BRANCH: ${{ github.base_ref }}
-      run: |
+        run: |
 
-        REGISTER_MODEL_NAME=$(echo ${{ github.event.pull_request.head.ref }} | awk -F"-" '{print $1}')
+          REGISTER_MODEL_NAME=$(echo ${{ github.event.pull_request.head.ref }} | awk -F"-" '{print $1}')
-        # REGISTER_MODEL_NAME=$(echo ${{github.ref_name}} | awk -F"-" '{print $1}')
+          # REGISTER_MODEL_NAME=$(echo ${{github.ref_name}} | awk -F"-" '{print $1}')
 
-        git config user.name "Github-Bot"
+          git config user.name "Github-Bot"
-        git config user.email "Github-Bot@no-reply.com"
+          git config user.email "Github-Bot@no-reply.com"
 
-        latest_dev_version=$(gto history ${REGISTER_MODEL_NAME} --asc --plain | awk '{print $NF}' | awk '/dev/' | awk 'END {print}')
+          latest_dev_version=$(gto history ${REGISTER_MODEL_NAME} --asc --plain | awk '{print $NF}' | awk '/dev/' | awk 'END {print}')
-        if [ -z "${latest_dev_version}" ]; then
+          if [ -z "${latest_dev_version}" ]; then
-          increment_version="1"
+            increment_version="1"
-        else
+          else
-          increment_version=$(echo ${latest_dev_version} | awk '{print $NF}' | awk -F"#" '{print $3}' | awk '{$1++; print}')
+            increment_version=$(echo ${latest_dev_version} | awk '{print $NF}' | awk -F"#" '{print $3}' | awk '{$1++; print}')
-        fi
+          fi
 
-        new_tag=${REGISTER_MODEL_NAME}#dev#${increment_version}
+          new_tag=${REGISTER_MODEL_NAME}#dev#${increment_version}
-        latest_version=$(gto show ${REGISTER_MODEL_NAME}@latest --ref | awk -F"@" '{print $2}')
+          latest_version=$(gto show ${REGISTER_MODEL_NAME}@latest --ref | awk -F"@" '{print $2}')
 
-        echo ${new_tag}
+          echo ${new_tag}
 
-        commit_hash=$(gto history ${REGISTER_MODEL_NAME} --asc --plain | awk "/${latest_version}/" | awk '{print $(NF-1)}')
+          commit_hash=$(gto history ${REGISTER_MODEL_NAME} --asc --plain | awk "/${latest_version}/" | awk '{print $(NF-1)}')
-        git checkout ${commit_hash}
+          git checkout ${commit_hash}
 
-        # git pull #Get new model registry md file changes
+          # git pull #Get new model registry md file changes
-        git tag -a ${new_tag} -m "Assigning stage dev to artifact ${REGISTER_MODEL_NAME} version ${latest_version}"
+          git tag -a ${new_tag} -m "Assigning stage dev to artifact ${REGISTER_MODEL_NAME} version ${latest_version}"
-        git push origin ${new_tag}
+          git push origin ${new_tag}
 
-        git checkout ${TARGET_BRANCH}
+          git checkout ${TARGET_BRANCH}
-        git fetch --all
+          git fetch --all
-        git pull
+          git pull
 
-        gto show --json > MODEL_REGISTRY.md
+          gto show --json > MODEL_REGISTRY.md
-        git add .
+          git add .
-        git commit -m "Update Registry"
+          git commit -m "Update Registry"
-        git push origin ${TARGET_BRANCH}
+          git push origin ${TARGET_BRANCH}

.github/workflows/MLPipelinePullRequest.yml

@@ -5,22 +5,21 @@ on:
   #   branches:
   #     - "model-**"
   pull_request:
-    branches: ["sap-dev", "heat-dev", "carbon-dev"]
+    branches: ["sap-dev", "heat-dev", "carbon-dev", "heat_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
+      - uses: yogevbd/enforce-label-action@2.1.0
-      with:
+        with:
-        REQUIRED_LABELS_ANY: "major,minor,patch"
+          REQUIRED_LABELS_ANY: "major,minor,patch"
-        REQUIRED_LABELS_ANY_DESCRIPTION: "Select at least one label ['major','minor','patch']"
+          REQUIRED_LABELS_ANY_DESCRIPTION: "Select at least one label ['major','minor','patch']"
-        BANNED_LABELS: "banned"
+          BANNED_LABELS: "banned"
 
   # No-Label:
   #   if: ${{ github.event.label.name != 'major' }} || ${{ github.event.label.name != 'minor' }}  || ${{ github.event.label.name != 'patch' }}
@@ -32,86 +31,168 @@ jobs:
   #       echo "Please choose one of these tags: 'major', 'major', 'patch'"
   #       exit(1)
 
-  Verify-Model:
+  Verify-Lambda:
-
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v3
-    - name: Install packages to retrieve artifacts
+      - name: Install packages to retrieve artifacts
-      env:
+        env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
+          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
-      run: |
+        run: |
-        pip install --upgrade pip
+          pip install --upgrade pip
-        pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
+          pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
 
-    - name: Retrieve artifacts (dvc.lock)
+      - name: Retrieve artifacts (dvc.lock)
-      env:
+        env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
+          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
-      run: |
+        run: |
-        cd modules/ml-pipeline/src/pipeline
+          cd modules/ml-pipeline/src/pipeline
-        dvc pull -r experiments
+          dvc pull -r experiments
 
-    - name: Build Prediction docker Image
+      - name: Set timestamp
-      run: |
+        id: set_timestamp
-        cd modules/ml-pipeline/src/
+        run: |
-        docker build . --file Prediction.Dockerfile --tag prediction_test
+          echo "timestamp=$(date +%Y%m%d)" >> $GITHUB_ENV
+          echo "Generated timestamp: ${timestamp}"
 
-    - name: Run Prediction docker container
+      - name: Upload sample row dataset to S3
-      run: |
+        env:
-        docker run prediction_test
+          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
+      - uses: actions/checkout@v3
-    - name: Install packages to retrieve artifacts
+      - name: Install packages to retrieve artifacts
-      run: |
+        run: |
-        pip install --upgrade pip
+          pip install --upgrade pip
-        pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
+          pip install -r modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt
 
-    - name: Retrieve artifacts (dvc.lock)
+      - name: Retrieve artifacts (dvc.lock)
-      env:
+        env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
+          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
-      run: |
+        run: |
-        cd modules/ml-pipeline/src/pipeline
+          cd modules/ml-pipeline/src/pipeline
-        dvc pull -r experiments
+          dvc pull -r experiments
 
-    - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v4
-    - uses: iterative/setup-cml@v1
+      - uses: iterative/setup-cml@v1
-    - name: Generate report
+      - name: Generate report
-      env:
+        env:
-        AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
+          AWS_ACCESS_KEY_ID: ${{ secrets.ROBOT_AWS_ACCESS_KEY_ID }}
-        AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.ROBOT_AWS_SECRET_ACCESS_KEY }}
-        REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        TARGET_BRANCH: ${{ github.base_ref }}
+          TARGET_BRANCH: ${{ github.base_ref }}
-      run: |
+        run: |
-        cd modules/ml-pipeline/src/pipeline
+          cd modules/ml-pipeline/src/pipeline
-        echo "## Model metrics" > report.md
+          echo "## Model metrics" > report.md
 
-        # Compare metrics to master
+          # Compare metrics to master
-        git fetch --depth=1 origin ${TARGET_BRANCH}:${TARGET_BRANCH}
+          git fetch --depth=1 origin ${TARGET_BRANCH}:${TARGET_BRANCH}
-        dvc metrics diff --md --all ${TARGET_BRANCH} >> report.md
+          dvc metrics diff --md --all ${TARGET_BRANCH} >> report.md
 
-        echo "## Scenario comparison" >> report.md
+          echo "## Scenario comparison" >> report.md
 
-        cat metrics/scenario_table.md >> report.md
+          cat metrics/scenario_table.md >> report.md
 
-        echo "" >> report.md
+          echo "" >> report.md
 
-        echo "## Scenario metrics" >> report.md
+          echo "## Scenario metrics" >> report.md
 
-        cat metrics/scenario_metrics.md >> report.md
+          cat metrics/scenario_metrics.md >> report.md
 
-        cml comment create report.md
+          cml comment create report.md
 
-        # echo "## Residuals plot from model" >> report.md
+          # echo "## Residuals plot from model" >> report.md
-        # metrics_location=$(find . -maxdepth 10 -name "residuals.png")
+          # metrics_location=$(find . -maxdepth 10 -name "residuals.png")
-        # echo $metrics_location
+          # echo $metrics_location
-        # cd $metric_location
+          # cd $metric_location
-        # echo "![](./residuals.png)" >> report.md
+          # echo "![](./residuals.png)" >> report.md

MODEL_REGISTRY.md

@@ -8,25 +8,65 @@
         "active": true
     },
     "sap": {
-        "version": "v0.14.0",
+        "version": "v0.17.5",
         "stage": {
-            "dev": "v0.14.0"
+            "dev": "v0.17.5"
         },
         "registered": true,
         "active": true
     },
     "heat": {
-        "version": "v0.5.0",
+        "version": "v0.8.0",
         "stage": {
-            "dev": "v0.5.0"
+            "dev": "v0.8.0"
         },
         "registered": true,
         "active": true
     },
     "carbon": {
-        "version": "v0.5.0",
+        "version": "v0.8.0",
         "stage": {
-            "dev": "v0.5.0"
+            "dev": "v0.7.0"
+        },
+        "registered": true,
+        "active": true
+    },
+    "hotwater": {
+        "version": "v1.0.0",
+        "stage": {
+            "dev": "v1.0.0"
+        },
+        "registered": true,
+        "active": true
+    },
+    "heating": {
+        "version": "v1.0.0",
+        "stage": {
+            "dev": "v1.0.0"
+        },
+        "registered": true,
+        "active": true
+    },
+    "lighting": {
+        "version": "v1.0.0",
+        "stage": {
+            "dev": "v1.0.0"
+        },
+        "registered": true,
+        "active": true
+    },
+    "hotwaterkwh": {
+        "version": "v1.3.0",
+        "stage": {
+            "dev": "v1.3.0"
+        },
+        "registered": true,
+        "active": true
+    },
+    "heatingkwh": {
+        "version": "v1.5.0",
+        "stage": {
+            "dev": "v1.5.0"
         },
         "registered": true,
         "active": true

README.md

@@ -83,3 +83,13 @@ curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d
 ```
 
 This will send a POST request to the running Lambda function and pass in the required data as JSON.
+
+For the testing of warm or testing of the lambda, use:
+
+```json
+curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": "{\"file_location\": \"s3://retrofit-data-dev/sap_change_model/one_sample_test_dataset.parquet\", \"property_id\": 1, \"portfolio_id\": 4, \"created_at\": \"now\", \"testing\": \"true\"}"}'
+```
+or
+```json
+curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": "{\"file_location\": \"s3://retrofit-data-dev/sap_change_model/one_sample_test_dataset.parquet\", \"property_id\": 1, \"portfolio_id\": 4, \"created_at\": \"now\", \"warm\": \"true\"}"}'
+```

deployment/Dockerfile.prediction.lambda

@@ -1,19 +1,24 @@
-FROM public.ecr.aws/lambda/python:3.10
+FROM public.ecr.aws/lambda/python:3.12
 
 # Set the working directory
 WORKDIR ${LAMBDA_TASK_ROOT}
-ENV PYTHONPATH "${PYTHONPATH}:${LAMBDA_TASK_ROOT}"
+ENV PYTHONPATH="${PYTHONPATH}:${LAMBDA_TASK_ROOT}"
+ENV MPLCONFIGDIR="/tmp/matplotlib"
 
 # Environment variables
 ARG RUNTIME_ENVIRONMENT
 ENV RUNTIME_ENVIRONMENT=${RUNTIME_ENVIRONMENT}
 
 # Install necessary build tools - required to test locally
-RUN yum install -y gcc python3-devel gcc-c++
+RUN dnf install -y gcc python3-devel gcc-c++
 
 # Install python packages
 COPY modules/ml-pipeline/src/pipeline/requirements/predictions/requirements.txt ./requirements.txt
-RUN pip install --no-cache-dir -r ./requirements.txt
+
+RUN pip install uv
+
+RUN uv pip install -r requirements.txt --system
+# RUN pip install --no-cache-dir -r ./requirements.txt
 
 # Copy the project code
 COPY modules/ml-pipeline/src/pipeline ./pipeline
@@ -22,4 +27,4 @@ COPY deployment/handlers/prediction_app.py ./pipeline/prediction_app.py
 WORKDIR ${LAMBDA_TASK_ROOT}/pipeline
 
 
-CMD [ "prediction_app.handler" ]
+CMD [ "prediction_app.handler" ]

deployment/handlers/prediction_app.py

@@ -47,6 +47,30 @@ def upload_dataframe_to_s3(df, bucket, s3_file_name):
         return False
 
 
+def warming_up_invocation(
+    model,
+    model_filepath: str,
+):
+    """
+    Function to handle warm up invocations
+    """
+    import pandas as pd
+    import numpy as np
+
+    model.load_model(model_filepath)
+
+    warmup_df = pd.DataFrame(
+        np.zeros((1, len(model.model.original_features))),
+        columns=model.model.original_features,
+    )
+
+    # model_names = model.model.model_names()
+    # if "NeuralNetFastAI" in model_names:
+    #     model.model.predict(warmup_df, model="NeuralNetFastAI")
+    # else:
+    model.predict(data=warmup_df)
+
+
 def handler(event, context):
     """
     Take in event and trigger the prediction pipeline
@@ -66,9 +90,6 @@ def handler(event, context):
         created_at = body["created_at"]
 
         # TODO: Implement the loading of the model and prediction
-
-        storage_filepath = f"s3://{PREDICTIONS_BUCKET}/{portfolio_id}/{property_id}/{created_at}.parquet"
-
         logger.info(f"--- Initiate MLModel ---")
 
         build_model_params = settings.build_model
@@ -78,6 +99,32 @@ def handler(event, context):
 
         model = model_factory(build_model_params["model_type"])
 
+        model_filepath = build_model_params["model_save_filepath"]
+
+        if "warm" in body:
+            logger.info("Warm up invocation - synthetic prediction")
+
+            warming_up_invocation(model=model, model_filepath=model_filepath)
+
+            return {
+                "statusCode": 200,
+                "body": json.dumps(
+                    {
+                        "message": "Successfully warmed up invocation",
+                    }
+                ),
+            }
+
+        if "testing" in body:
+            logger.info(
+                "Testing invocation for CI/CD - save file to same location in S3"
+            )
+            storage_filepath = body["file_location"].replace(
+                ".parquet", "_output.parquet"
+            )
+        else:
+            storage_filepath = f"s3://{PREDICTIONS_BUCKET}/{portfolio_id}/{property_id}/{created_at}.parquet"
+
         logger.info(f"--- Initiate Input DataClient ---")
         input_dataclient = dataclient_factory(
             dataclient_type="aws-s3",
@@ -95,7 +142,7 @@ def handler(event, context):
             output_dataclient=output_dataclient,
             model=model,
             target=feature_process_params["feature_processor_config"]["target"],
-            model_filepath=build_model_params["model_save_filepath"],
+            model_filepath=model_filepath,
             test_data_filepath=body["file_location"],
             predictions_output_filepath=storage_filepath,
             predictions_column_name=generate_predictions_params[

deployment/serverless.yml

@@ -51,3 +51,4 @@ functions:
           path: /predict
           method: POST
     timeout: 120 # Set max run time to 2 minutes - we shouldn't need this much time so this can be reviewed
+    memorySize: 3008

modules/ml-pipeline/Makefile

@@ -1,7 +1,8 @@
 export PYENV_ROOT=$(HOME)/.pyenv
 export PATH := $(PYENV_ROOT)/bin:$(PATH)
-PYTHON_VERSION ?= 3.10.12
+PYTHON_VERSION ?= 3.12.12
 CONDA_ENV=dev_env_pipeline
+CONDA_ACTIVATE=source $$(conda info --base)/etc/profile.d/conda.sh ; conda deactivate ; conda activate
 
 .PHONY: init
 init: dev-conda
@@ -12,11 +13,15 @@ dev-conda:
 	# conda remove --name ${CONDA_ENV} --all -y || echo "No environment created previously"
 	conda create --name ${CONDA_ENV} python=$(PYTHON_VERSION) -y
 	conda init bash
-	conda run -v -n ${CONDA_ENV} pip install --upgrade pip
+	${CONDA_ACTIVATE} ${CONDA_ENV} && \
-	conda run -v -n ${CONDA_ENV} pip install -r src/pipeline/requirements/training/requirements-dev.txt
+		which pip && \
-	conda run -v -n ${CONDA_ENV} pip install -r src/pipeline/requirements/version_control/requirements.txt
+		pip install --upgrade pip && \
-	conda run -v -n ${CONDA_ENV} pre-commit install
+		pip install uv && \
-	conda run -v -n ${CONDA_ENV} pip install ipykernel
+		uv pip install -r src/pipeline/requirements/training/requirements-dev.txt && \
+		uv pip install -r src/pipeline/requirements/version_control/requirements.txt && \
+		pre-commit install && \
+		uv pip install ipykernel && \
+		conda install llvm-openmp -y
 	echo "TO ACTIVATE ENVIRONMENT, USE THE FOLLOWING COMMAND"
 	echo "conda activate ${CONDA_ENV}"
 
@@ -33,4 +38,4 @@ dev-pyenv:
 
 .PHONY: dvc-init
 dvc-init:
-	. .dev_env_pipeline/bin/activate && dvc init --subdir
+	. .dev_env_pipeline/bin/activate && dvc init --subdir

modules/ml-pipeline/src/Prediction.Dockerfile

@@ -1,16 +1,21 @@
 # Dockerfile that can be used to test loading a model to generate a prediction (part of CI/CD flow)
-FROM python:3.10.12-slim
+FROM python:3.12.12-slim
 
 RUN apt-get update && apt-get install -y libgomp1 gcc python3-dev
 
 COPY pipeline/requirements/predictions/requirements.txt requirements.txt
 
 RUN pip install --upgrade pip
-RUN pip install -r requirements.txt
+
+RUN pip install uv
+
+RUN uv pip install -r requirements.txt --system
+
+# RUN pip install -r requirements.txt
 
 # Assuming in the CI/CD step, there will be a dvc pull step to get data and model, so will just need to run a single script
 COPY pipeline/ /home/pipeline/
 
 WORKDIR /home/pipeline/
 
-CMD [ "python", "3_generate_predictions.py"]
+CMD [ "python", "3_generate_predictions.py"]

modules/ml-pipeline/src/pipeline/1_prepare_data.py

@@ -29,6 +29,7 @@ data_filepath = prepare_data_params["data_filepath"]
 train_proportion = prepare_data_params["train_proportion"]
 output_train_filepath = prepare_data_params["output_train_filepath"]
 output_test_filepath = prepare_data_params["output_test_filepath"]
+sample_test_filepath = prepare_data_params["sample_test_filepath"]
 feature_processor_config = feature_process_params["feature_processor_config"]
 
 logger.info(f"--- Initiate DataClient ---")
@@ -99,6 +100,10 @@ def prepare_data(
 
     logger.info("--- Outputting data ---")
 
+    output_dataclient.save_data(
+        obj=data.sample(1), location=sample_test_filepath, save_config=None
+    )
+
     output_dataclient.save_data(
         obj=train, location=output_train_filepath, save_config=None
     )

modules/ml-pipeline/src/pipeline/4_generate_metrics.py

@@ -4,9 +4,7 @@ After the model is built, we can evaluate its performance
 """
 
 import os
-import yaml
 import pandas as pd
-from pathlib import Path
 from core.interface.InterfaceModels import MLModel
 from core.interface.InterfaceMetrics import MLMetrics
 from core.interface.InterfaceDataClient import DataClient

modules/ml-pipeline/src/pipeline/5_generate_scenarios.py

@@ -99,6 +99,12 @@ def generate_scenario_predictions(
             ]
         )
 
+    # TEMPORARY FIX: ADD is_post_sap10_starting and is_post_sap10_ending if not present
+    if "is_post_sap10_starting" not in scenario_data.columns:
+        scenario_data["is_post_sap10_starting"] = False
+    if "is_post_sap10_ending" not in scenario_data.columns:
+        scenario_data["is_post_sap10_ending"] = False
+
     logger.info("--- Loading Model ---")
 
     model.load_model(model_filepath)

modules/ml-pipeline/src/pipeline/configs/build_model.yaml

@@ -14,9 +14,23 @@ default:
       output_filepath: ./data/model/allmodels/
       problem_type: regression
       eval_metric: mean_squared_error #mean_absolute_error
-      time_limit: 1800
+      time_limit: 3600
       presets: medium_quality
-      excluded_model_types: ['RF', 'CAT', 'NN_TORCH', 'KNN', 'XT']
+      excluded_model_types: ['RF', 'CAT', 'NN_TORCH', 'KNN', 'XT', 'FASTAI']
-      infer_limit: 0.05
+      infer_limit: 1
       infer_limit_batch_size: 10000
+      fit_strategy: "parallel"
       ag_args_ensemble: {'num_folds_parallel': 2}
+      num_gpus: 0
+      hyperparameters:
+        {
+        'NN_TORCH': [{}],
+        'GBM': [{'extra_trees': True, 'ag_args': {'name_suffix': 'XT'}}, {}, {'learning_rate': 0.03, 'num_leaves': 128, 'feature_fraction': 0.9, 'min_data_in_leaf': 3, 'ag_args': {'name_suffix': 'Large', 'priority': 0,}}],
+        # 'GBM': [{}],
+        'CAT': [{}],
+        'XGB': [{}],
+        'FASTAI': [{}],
+        'RF': [{'criterion': 'gini', 'ag_args': {'name_suffix': 'Gini', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'entropy', 'ag_args': {'name_suffix': 'Entr', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'squared_error', 'ag_args': {'name_suffix': 'MSE', 'problem_types': ['regression', 'quantile']}}],
+        'XT': [{'criterion': 'gini', 'ag_args': {'name_suffix': 'Gini', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'entropy', 'ag_args': {'name_suffix': 'Entr', 'problem_types': ['binary', 'multiclass']}}, {'criterion': 'squared_error', 'ag_args': {'name_suffix': 'MSE', 'problem_types': ['regression', 'quantile']}}],
+        'KNN': [{'weights': 'uniform', 'ag_args': {'name_suffix': 'Unif'}}, {'weights': 'distance', 'ag_args': {'name_suffix': 'Dist'}}],
+        }

modules/ml-pipeline/src/pipeline/configs/feature_processor_logic.py

@@ -18,30 +18,60 @@ def remove_starting_columns(df):
     return df
 
 
-def remove_floor_height_ending(df):
+def keep_negative_heat_change(df):
-    # df.describe(percentiles=[0.005,0.99])['FLOOR_HEIGHT_ENDING']
+    df = df[df["heat_demand_change"] < 0]
-    # shows bottom 0.5 percentile is 1.665
-    # So keep anything above this
-    df = df[df["floor_height_ending"] > 1.665].reset_index(drop=True)
-    print("we in here")
     return df
 
 
-def remove_minimum_habitable_room_size(df):
+def keep_negative_carbon_change(df):
-    # Need minimum of 6.5m per habitable room
+    df = df[df["carbon_change"] < 0]
-    df = df[
-        df["total_floor_area_ending"] / df["number_habitable_rooms"] > 6.5
-    ].reset_index(drop=True)
     return df
 
 
-def keep_flats(df):
+# TODO: Move to ETL pipeline
-    df = df[df["property_type"] == "Flat"]
+def remove_unreasonable_habitable_rooms(df):
+    """
+    Assumption is that proportion of floor area to habitable rooms should be at least 6.5m2
+    """
+    minimum_room_size_index = (
+        df["total_floor_area_ending"] / df["number_habitable_rooms"] >= 6.5
+    )
+    df = df[minimum_room_size_index]
     return df
 
 
-def keep_non_zero_rdsap(df):
+def remove_top_1_percent_heat_demand_starting(df):
-    df = df[df["rdsap_change"] != 0]
+    # threshold_value = df.describe(percentiles=[0.99])['HEAT_DEMAND_STARTING']['99%']
+    threshold_value = 860
+    df = df[df["heat_demand_starting"] < threshold_value]
+    return df
+
+
+def remove_negative_heat_demand_starting(df):
+    # threshold_value = df.describe(percentiles=[0.99])['HEAT_DEMAND_STARTING']['99%']
+    threshold_value = 0
+    df = df[df["heat_demand_starting"] > threshold_value]
+    return df
+
+
+# def remove_top_1_percent_heat_demand_ending(df):
+#     # threshold_value = df.describe(percentiles=[0.99])['HEAT_DEMAND_STARTING']['99%']
+#     threshold_value = 593
+#     df = df[df["heat_demand_ending"] < threshold_value]
+#     return df
+
+
+def remove_negative_heat_demand_ending(df):
+    # threshold_value = df.describe(percentiles=[0.99])['HEAT_DEMAND_STARTING']['99%']
+    threshold_value = 0
+    df = df[df["heat_demand_ending"] > threshold_value]
+    return df
+
+
+def remove_top_1_percent_carbon(df):
+    # threshold_value = df.describe(percentiles=[0.99])['CARBON_STARTING']['99%']
+    threshold_value = 18
+    df = df[df["carbon_starting"] < threshold_value]
     return df
 
 
@@ -54,10 +84,14 @@ def keep_non_zero_rdsap(df):
 #     return df
 
 business_logic = {
-    # "keep_non_zero_rdsap": keep_non_zero_rdsap,
+    "remove_unreasonable_habitable_rooms": remove_unreasonable_habitable_rooms,
-    # "keep_flats": keep_flats,
+    "keep_negative_heat_change": keep_negative_heat_change,
-    # "remove_minimum_habitable_room_size": remove_minimum_habitable_room_size,
+    "keep_negative_carbon_change": keep_negative_carbon_change,
-    # "remove_floor_height_ending": remove_floor_height_ending
+    "remove_top_1_percent_heat_demand": remove_top_1_percent_heat_demand_starting,
+    "remove_negative_heat_demand_starting": remove_negative_heat_demand_starting,
+    # "remove_top_1_percent_heat_demand_ending": remove_top_1_percent_heat_demand_ending,
+    "remove_negative_heat_demand_ending": remove_negative_heat_demand_ending,
+    "remove_top_1_percent_carbon": remove_top_1_percent_carbon,
     # "remove_starting_columns": remove_starting_columns
     # "keep_ENDING_COLUMNS": keep_ending_columns
 }

modules/ml-pipeline/src/pipeline/configs/post_prediction_logic.py

@@ -1,6 +1,7 @@
 """
 After predictions, we may want to apply some post processing to the predictions
 """
+
 import pandas as pd
 
 
@@ -13,10 +14,11 @@ def clip_predictions_to_minimum_value(
     predictions_df = pd.concat([data, predictions], axis=1)
     # We expect all prediction to be atleast one point improvement
     replace_index = (
-        predictions_df["sap_starting"] + minimum_value > predictions_df["predictions"]
+        predictions_df["predictions"]
+        > predictions_df["heat_demand_starting"] - minimum_value
     )
     predictions_df.loc[replace_index, "predictions"] = (
-        predictions_df.loc[replace_index, "sap_starting"] + minimum_value
+        predictions_df.loc[replace_index, "heat_demand_starting"] - minimum_value
     )
 
     predictions_new = predictions_df["predictions"]
@@ -30,6 +32,6 @@ def clip_predictions_to_minimum_value(
 
 
 post_prediction_logic = {
-    "clip_predictions_to_minimum_value": clip_predictions_to_minimum_value,
+    # "clip_predictions_to_minimum_value": clip_predictions_to_minimum_value,
     # "round_predictions": round_predictions
 }

modules/ml-pipeline/src/pipeline/configs/scenarios.yaml

@@ -8,6 +8,6 @@ default:
       # - s3://retrofit-data-dev/scenario_data/27-03-2024-11-38-15/recommendations_scoring_data.parquet
       # - s3://retrofit-data-dev/scenario_data/26-05-2024-08-47-45/recommendations_scoring_data.parquet
       # - s3://retrofit-data-dev/scenario_data/26-05-2024-10-44-53/recommendations_scoring_data.parquet
-      - s3://retrofit-data-dev/scenario_data/28-05-2024-19-22-41/recommendations_scoring_data.parquet
+      # - s3://retrofit-data-dev/scenario_data/28-05-2024-19-22-41/recommendations_scoring_data.parquet
     comparison_output_filepath: ./metrics/scenario_table.md
     metrics_output_filepath: ./metrics/scenario_metrics.md

modules/ml-pipeline/src/pipeline/configs/settings.yaml

@@ -12,32 +12,163 @@ default:
       AWS_ACCESS_KEY_ID: minio
       AWS_SECRET_ACCESS_KEY: minio123
       ENDPOINT_URL: http://localhost:9000
-    local:
+    local: null
-      null
 
   prepare_data:
     input_dataclient_type: aws-s3
     output_dataclient_type: local
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-03-22-18-56-53/dataset_rooms.parquet
+    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-06-09-10-36-53/dataset_rooms.parquet
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-25-08-36-36/dataset_rooms.parquet
+    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-10-03-22-57-23/dataset_rooms.parquet
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-26-10-31-39/dataset_rooms.parquet
+    data_filepath: s3://retrofit-data-dev/sap_change_model/2025-11-02-09-32-42/dataset_rooms.parquet
-    data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/dataset_rooms.parquet
     train_proportion: 0.9
     output_train_filepath: ./data/prepared_data/train.parquet
     output_test_filepath: ./data/prepared_data/test.parquet
+    sample_test_filepath: ./data/prepared_data/sample_test.parquet
 
   feature_processor:
     feature_processor_type: dataframe
     feature_processor_config:
       subsample_amount: null
       subsample_seed: 0
-      target: sap_ending
+      target: heat_demand_starting
       identifier_columns: ["uprn"]
-      # drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending", "days_to_starting", "days_to_ending"]
+      drop_columns:
-      drop_columns: [
+        [
-        "heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending", "days_to_starting", "days_to_ending",
+          "heat_demand_ending",
-        'number_habitable_rooms_starting', 'number_habitable_rooms_ending', 'number_heated_rooms_starting', 'number_heated_rooms_ending',
+          "potential_energy_efficiency",
-        'number_habitable_rooms', 'number_heated_rooms']
+          "environment_impact_potential",
+          "energy_consumption_potential",
+          "co2_emissions_potential",
+          "heat_demand_change",
+          "carbon_change",
+          "rdsap_change",
+          "sap_starting",
+          "sap_ending",
+          "carbon_starting",
+          "carbon_ending",
+          "days_to_starting",
+          "days_to_ending",
+          "number_habitable_rooms_starting",
+          "number_habitable_rooms_ending",
+          "number_heated_rooms_starting",
+          "number_heated_rooms_ending",
+          "number_habitable_rooms",
+          "number_heated_rooms",
+          "lighting_cost_starting",
+          "lighting_cost_ending",
+          "heating_cost_starting",
+          "heating_cost_ending",
+          "hot_water_cost_starting",
+          "hot_water_cost_ending",
+          "floor_thermal_transmittance",
+          "floor_thermal_transmittance_ending",
+          "lodgement_date_starting",
+          "lodgement_date_ending",
+          "walls_thermal_transmittance_ending",
+          "walls_thermal_transmittance_unit_ending",
+          "is_filled_cavity_ending",
+          "is_as_built_ending",
+          "walls_is_assumed_ending",
+          "is_park_home_ending",
+          "walls_insulation_thickness_ending",
+          "external_insulation_ending",
+          "internal_insulation_ending",
+          "floor_insulation_thickness_ending",
+          "roof_thermal_transmittance_ending",
+          "is_at_rafters_ending",
+          "roof_insulation_thickness_ending",
+          "heater_type_ending",
+          "system_type_ending",
+          "thermostat_characteristics_ending",
+          "heating_scope_ending",
+          "energy_recovery_ending",
+          "hotwater_tariff_type_ending",
+          "extra_features_ending",
+          "chp_systems_ending",
+          "distribution_system_ending",
+          "no_system_present_ending",
+          "appliance_ending",
+          "has_radiators_ending",
+          "has_fan_coil_units_ending",
+          "has_pipes_in_screed_above_insulation_ending",
+          "has_pipes_in_insulated_timber_floor_ending",
+          "has_pipes_in_concrete_slab_ending",
+          "has_boiler_ending",
+          "has_air_source_heat_pump_ending",
+          "has_room_heaters_ending",
+          "has_electric_storage_heaters_ending",
+          "has_warm_air_ending",
+          "has_electric_underfloor_heating_ending",
+          "has_electric_ceiling_heating_ending",
+          "has_community_scheme_ending",
+          "has_ground_source_heat_pump_ending",
+          "has_no_system_present_ending",
+          "has_portable_electric_heaters_ending",
+          "has_water_source_heat_pump_ending",
+          "has_electric_heat_pump_ending",
+          "has_micro-cogeneration_ending",
+          "has_solar_assisted_heat_pump_ending",
+          "has_exhaust_source_heat_pump_ending",
+          "has_community_heat_pump_ending",
+          "has_hot-water-only_ending",
+          "has_electric_ending",
+          "has_mains_gas_ending",
+          "has_wood_logs_ending",
+          "has_coal_ending",
+          "has_oil_ending",
+          "has_wood_pellets_ending",
+          "has_anthracite_ending",
+          "has_dual_fuel_mineral_and_wood_ending",
+          "has_smokeless_fuel_ending",
+          "has_lpg_ending",
+          "has_b30k_ending",
+          "has_mineral_and_wood_ending",
+          "has_dual_fuel_appliance_ending",
+          "has_electricaire_ending",
+          "has_assumed_for_most_rooms_ending",
+          "has_underfloor_heating_ending",
+          "thermostatic_control_ending",
+          "charging_system_ending",
+          "switch_system_ending",
+          "no_control_ending",
+          "dhw_control_ending",
+          "community_heating_ending",
+          "multiple_room_thermostats_ending",
+          "auxiliary_systems_ending",
+          "trvs_ending",
+          "rate_control_ending",
+          "glazing_type_ending",
+          "fuel_type_ending",
+          "main-fuel_tariff_type_ending",
+          "is_community_ending",
+          "no_individual_heating_or_community_network_ending",
+          "complex_fuel_type_ending",
+          "mechanical_ventilation_ending",
+          "secondheat_description_ending",
+          "glazed_type_ending",
+          "multi_glaze_proportion_ending",
+          "low_energy_lighting_ending",
+          "number_open_fireplaces_ending",
+          "solar_water_heating_flag_ending",
+          "photo_supply_ending",
+          "transaction_type_ending",
+          "energy_tariff_ending",
+          "extension_count_ending",
+          "total_floor_area_ending",
+          "floor_height_ending",
+          "hot_water_energy_eff_ending",
+          "floor_energy_eff_ending",
+          "windows_energy_eff_ending",
+          "walls_energy_eff_ending",
+          "sheating_energy_eff_ending",
+          "roof_energy_eff_ending",
+          "mainheat_energy_eff_ending",
+          "mainheatc_energy_eff_ending",
+          "lighting_energy_eff_ending",
+          "is_post_sap10_ending",
+          "estimated_perimeter_ending",
+        ]
+      # retain_features: ["SAP_STARTING", "TOTAL_FLOOR_AREA_DIFF"]
       retain_features: null
       # retain_features: ['uprn', 'sap_starting', 'hot_water_energy_eff_ending',
       #  'mainheat_energy_eff_ending', 'constituency', 'roof_energy_eff_ending',
@@ -78,4 +209,4 @@ default:
 
 dev:
   generate_predictions:
-      input_dataclient_type: aws-s3
+    input_dataclient_type: aws-s3

modules/ml-pipeline/src/pipeline/core/MLModels.py

@@ -1,4 +1,4 @@
-""""
+""" "
 Implementations of MLModels, all of which will have four methods to:
 - Load model
 - Save Model
@@ -11,9 +11,6 @@ import joblib
 import pandas as pd
 from pathlib import Path
 from typing import Union, List
-from sklearn import linear_model
-from sklearn.svm import SVR
-from autogluon.tabular import TabularDataset, TabularPredictor
 from core.interface.InterfaceModels import MLModel
 from core.Logger import logger
 
@@ -69,6 +66,8 @@ class SKLearnLinearRegression:
         """
         Method to train a model
         """
+        from sklearn import linear_model
+
         self.model = linear_model.LinearRegression()
 
         x_train = data.iloc[:, data.columns != target]
@@ -117,6 +116,7 @@ class SKLearnSVMRegression:
         """
         Method to train a model
         """
+        from sklearn.svm import SVR
 
         validate_dict_keys(
             list(model_hyperparameters.keys()),
@@ -152,12 +152,17 @@ class AutogluonAutoML:
         "infer_limit",
         "infer_limit_batch_size",
         "ag_args_ensemble",
+        "fit_strategy",
+        "num_gpus",
+        "hyperparameters",
     ]
 
     def load_model(self, path: Union[Path, str]) -> None:
         """
         Method to load a model
         """
+        from autogluon.tabular import TabularPredictor
+
         filepath = str(path)
         self.model = TabularPredictor.load(path=filepath)
 
@@ -183,6 +188,10 @@ class AutogluonAutoML:
         """
         Method to train a model
         """
+        from autogluon.tabular import TabularDataset, TabularPredictor
+
+        # Force Parallel Model fitting
+        os.environ["AG_FORCE_PARALLEL"] = "True"
 
         validate_dict_keys(
             keys_1=list(model_hyperparameters.keys()),
@@ -209,6 +218,9 @@ class AutogluonAutoML:
             infer_limit=model_hyperparameters["infer_limit"],
             infer_limit_batch_size=model_hyperparameters["infer_limit_batch_size"],
             ag_args_ensemble=model_hyperparameters["ag_args_ensemble"],
+            fit_strategy=model_hyperparameters["fit_strategy"],
+            num_gpus=model_hyperparameters["num_gpus"],
+            hyperparameters=model_hyperparameters["hyperparameters"].to_dict(),
         )
 
     def predict(

modules/ml-pipeline/src/pipeline/dvc.lock

@@ -16,15 +16,22 @@ stages:
     deps:
     - path: 1_prepare_data.py
       hash: md5
-      md5: 11a3b8bfdfe199ab7ecc39ccc5652649
+      md5: a5ce162e1c402c0f811a80ef78cf4dd5
-      size: 4298
+      size: 4481
     params:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
+        - heat_demand_ending
+        - potential_energy_efficiency
+        - environment_impact_potential
+        - energy_consumption_potential
+        - co2_emissions_potential
         - heat_demand_change
         - carbon_change
         - rdsap_change
-        - heat_demand_ending
+        - sap_starting
+        - sap_ending
+        - carbon_starting
         - carbon_ending
         - days_to_starting
         - days_to_ending
@@ -34,24 +41,140 @@ stages:
         - number_heated_rooms_ending
         - number_habitable_rooms
         - number_heated_rooms
+        - lighting_cost_starting
+        - lighting_cost_ending
+        - heating_cost_starting
+        - heating_cost_ending
+        - hot_water_cost_starting
+        - hot_water_cost_ending
+        - floor_thermal_transmittance
+        - floor_thermal_transmittance_ending
+        - lodgement_date_starting
+        - lodgement_date_ending
+        - walls_thermal_transmittance_ending
+        - walls_thermal_transmittance_unit_ending
+        - is_filled_cavity_ending
+        - is_as_built_ending
+        - walls_is_assumed_ending
+        - is_park_home_ending
+        - walls_insulation_thickness_ending
+        - external_insulation_ending
+        - internal_insulation_ending
+        - floor_insulation_thickness_ending
+        - roof_thermal_transmittance_ending
+        - is_at_rafters_ending
+        - roof_insulation_thickness_ending
+        - heater_type_ending
+        - system_type_ending
+        - thermostat_characteristics_ending
+        - heating_scope_ending
+        - energy_recovery_ending
+        - hotwater_tariff_type_ending
+        - extra_features_ending
+        - chp_systems_ending
+        - distribution_system_ending
+        - no_system_present_ending
+        - appliance_ending
+        - has_radiators_ending
+        - has_fan_coil_units_ending
+        - has_pipes_in_screed_above_insulation_ending
+        - has_pipes_in_insulated_timber_floor_ending
+        - has_pipes_in_concrete_slab_ending
+        - has_boiler_ending
+        - has_air_source_heat_pump_ending
+        - has_room_heaters_ending
+        - has_electric_storage_heaters_ending
+        - has_warm_air_ending
+        - has_electric_underfloor_heating_ending
+        - has_electric_ceiling_heating_ending
+        - has_community_scheme_ending
+        - has_ground_source_heat_pump_ending
+        - has_no_system_present_ending
+        - has_portable_electric_heaters_ending
+        - has_water_source_heat_pump_ending
+        - has_electric_heat_pump_ending
+        - has_micro-cogeneration_ending
+        - has_solar_assisted_heat_pump_ending
+        - has_exhaust_source_heat_pump_ending
+        - has_community_heat_pump_ending
+        - has_hot-water-only_ending
+        - has_electric_ending
+        - has_mains_gas_ending
+        - has_wood_logs_ending
+        - has_coal_ending
+        - has_oil_ending
+        - has_wood_pellets_ending
+        - has_anthracite_ending
+        - has_dual_fuel_mineral_and_wood_ending
+        - has_smokeless_fuel_ending
+        - has_lpg_ending
+        - has_b30k_ending
+        - has_mineral_and_wood_ending
+        - has_dual_fuel_appliance_ending
+        - has_electricaire_ending
+        - has_assumed_for_most_rooms_ending
+        - has_underfloor_heating_ending
+        - thermostatic_control_ending
+        - charging_system_ending
+        - switch_system_ending
+        - no_control_ending
+        - dhw_control_ending
+        - community_heating_ending
+        - multiple_room_thermostats_ending
+        - auxiliary_systems_ending
+        - trvs_ending
+        - rate_control_ending
+        - glazing_type_ending
+        - fuel_type_ending
+        - main-fuel_tariff_type_ending
+        - is_community_ending
+        - no_individual_heating_or_community_network_ending
+        - complex_fuel_type_ending
+        - mechanical_ventilation_ending
+        - secondheat_description_ending
+        - glazed_type_ending
+        - multi_glaze_proportion_ending
+        - low_energy_lighting_ending
+        - number_open_fireplaces_ending
+        - solar_water_heating_flag_ending
+        - photo_supply_ending
+        - transaction_type_ending
+        - energy_tariff_ending
+        - extension_count_ending
+        - total_floor_area_ending
+        - floor_height_ending
+        - hot_water_energy_eff_ending
+        - floor_energy_eff_ending
+        - windows_energy_eff_ending
+        - walls_energy_eff_ending
+        - sheating_energy_eff_ending
+        - roof_energy_eff_ending
+        - mainheat_energy_eff_ending
+        - mainheatc_energy_eff_ending
+        - lighting_energy_eff_ending
+        - is_post_sap10_ending
+        - estimated_perimeter_ending
         default.feature_processor.feature_processor_config.retain_features:
         default.feature_processor.feature_processor_config.subsample_amount:
         default.feature_processor.feature_processor_config.subsample_seed: 0
-        default.feature_processor.feature_processor_config.target: sap_ending
+        default.feature_processor.feature_processor_config.target: 
+          heat_demand_starting
         default.feature_processor.feature_processor_type: dataframe
-        default.prepare_data.data_filepath:
+        default.prepare_data.data_filepath: 
-          s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/dataset_rooms.parquet
+          s3://retrofit-data-dev/sap_change_model/2025-11-02-09-32-42/dataset_rooms.parquet
         default.prepare_data.input_dataclient_type: aws-s3
         default.prepare_data.output_dataclient_type: local
-        default.prepare_data.output_test_filepath: ./data/prepared_data/test.parquet
+        default.prepare_data.output_test_filepath: 
-        default.prepare_data.output_train_filepath: ./data/prepared_data/train.parquet
+          ./data/prepared_data/test.parquet
+        default.prepare_data.output_train_filepath: 
+          ./data/prepared_data/train.parquet
         default.prepare_data.train_proportion: 0.9
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: c293fbc1658af932f0d09cdce25acf67.dir
-      size: 45056059
+      size: 21779190
-      nfiles: 2
+      nfiles: 3
   build_model:
     cmd: python 2_build_model.py
     deps:
@@ -61,9 +184,9 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: c293fbc1658af932f0d09cdce25acf67.dir
-      size: 45056059
+      size: 21779190
-      nfiles: 2
+      nfiles: 3
     params:
       configs/build_model.yaml:
         default:
@@ -79,7 +202,7 @@ stages:
               output_filepath: ./data/model/allmodels/
               problem_type: regression
               eval_metric: mean_squared_error
-              time_limit: 1800
+              time_limit: 3600
               presets: medium_quality
               excluded_model_types:
               - RF
@@ -87,25 +210,94 @@ stages:
               - NN_TORCH
               - KNN
               - XT
-              infer_limit: 0.05
+              - FASTAI
+              infer_limit: 1
               infer_limit_batch_size: 10000
+              fit_strategy: parallel
               ag_args_ensemble:
                 num_folds_parallel: 2
+              num_gpus: 0
+              hyperparameters:
+                NN_TORCH:
+                - {}
+                GBM:
+                - extra_trees: true
+                  ag_args:
+                    name_suffix: XT
+                - {}
+                - learning_rate: 0.03
+                  num_leaves: 128
+                  feature_fraction: 0.9
+                  min_data_in_leaf: 3
+                  ag_args:
+                    name_suffix: Large
+                    priority: 0
+                CAT:
+                - {}
+                XGB:
+                - {}
+                FASTAI:
+                - {}
+                RF:
+                - criterion: gini
+                  ag_args:
+                    name_suffix: Gini
+                    problem_types:
+                    - binary
+                    - multiclass
+                - criterion: entropy
+                  ag_args:
+                    name_suffix: Entr
+                    problem_types:
+                    - binary
+                    - multiclass
+                - criterion: squared_error
+                  ag_args:
+                    name_suffix: MSE
+                    problem_types:
+                    - regression
+                    - quantile
+                XT:
+                - criterion: gini
+                  ag_args:
+                    name_suffix: Gini
+                    problem_types:
+                    - binary
+                    - multiclass
+                - criterion: entropy
+                  ag_args:
+                    name_suffix: Entr
+                    problem_types:
+                    - binary
+                    - multiclass
+                - criterion: squared_error
+                  ag_args:
+                    name_suffix: MSE
+                    problem_types:
+                    - regression
+                    - quantile
+                KNN:
+                - weights: uniform
+                  ag_args:
+                    name_suffix: Unif
+                - weights: distance
+                  ag_args:
+                    name_suffix: Dist
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: d9c9afc05e8780db47c0548b19bf7d19.dir
+      md5: 6c4de55effeb468e37ee3db3838109db.dir
-      size: 3349989
+      size: 2976628
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
+      md5: 2ff63da0312853b1fd9338cac62ba0b0.dir
-      size: 773523079
+      size: 592460869
-      nfiles: 36
+      nfiles: 31
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 2ff70a2a45813e1bcdf2ea3aa8e07d4a
+      md5: c00465e99e9368afdb3302a52fca99b9
-      size: 224
+      size: 223
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -115,44 +307,46 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
+      md5: 2ff63da0312853b1fd9338cac62ba0b0.dir
-      size: 773523079
+      size: 592460869
-      nfiles: 36
+      nfiles: 31
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: c293fbc1658af932f0d09cdce25acf67.dir
-      size: 45056059
+      size: 21779190
-      nfiles: 2
+      nfiles: 3
     params:
       configs/settings.yaml:
         default.generate_predictions.input_dataclient_type: local
         default.generate_predictions.output_dataclient_type: local
         default.generate_predictions.predictions_column_name: predictions
-        default.generate_predictions.predictions_output_filepath: ./data/predictions/predictions.parquet
+        default.generate_predictions.predictions_output_filepath: 
-        default.generate_predictions.test_data_filepath: ./data/prepared_data/test.parquet
+          ./data/predictions/predictions.parquet
+        default.generate_predictions.test_data_filepath: 
+          ./data/prepared_data/test.parquet
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
+      md5: a960cadf88d5f38cc55942781a2db51e.dir
-      size: 463197
+      size: 392728
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
     deps:
     - path: 4_generate_metrics.py
       hash: md5
-      md5: 4fedb86d89d528f0a6597934ba3890a0
+      md5: d61bb524f706917f6a3eb72b1ab8bc61
-      size: 3484
+      size: 3447
     - path: data/predictions
       hash: md5
-      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
+      md5: a960cadf88d5f38cc55942781a2db51e.dir
-      size: 463197
+      size: 392728
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: c293fbc1658af932f0d09cdce25acf67.dir
-      size: 45056059
+      size: 21779190
-      nfiles: 2
+      nfiles: 3
     params:
       configs/settings.yaml:
         default.generate_metrics.dataclient_type: local
@@ -161,30 +355,29 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 3e08df02fd5c5d094bcf936e1338d596
+      md5: c0241381a23b29831b18be3f063f75fd
-      size: 223
+      size: 218
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
     deps:
     - path: 5_generate_scenarios.py
       hash: md5
-      md5: 40506749fefd926d47c60ff5b16db307
+      md5: 872b0c762ce1c8933fcbc5f54d5d4b5d
-      size: 5337
+      size: 5658
     params:
       configs/scenarios.yaml:
         default.scenarios:
           input_dataclient_type: aws-s3
           output_dataclient_type: local
           scenario_data_filepaths:
-          - s3://retrofit-data-dev/scenario_data/28-05-2024-19-22-41/recommendations_scoring_data.parquet
           comparison_output_filepath: ./metrics/scenario_table.md
           metrics_output_filepath: ./metrics/scenario_metrics.md
     outs:
     - path: metrics/scenario_metrics.md
       hash: md5
-      md5: fa4d6d7bbd7818613800da5f8f37ea96
+      md5: d41d8cd98f00b204e9800998ecf8427e
-      size: 363
+      size: 0
     - path: metrics/scenario_table.md
       hash: md5
-      md5: d6baf100a1623cc2467c2f8221d314c9
+      md5: d41d8cd98f00b204e9800998ecf8427e
-      size: 2133
+      size: 0

modules/ml-pipeline/src/pipeline/eda.py

@@ -1,6 +1,7 @@
 """
 Doing some eda on dataset
 """
+
 # Look at response variable
 
 from matplotlib import pyplot as plt
@@ -38,7 +39,6 @@ train_df[[target, "SAP_STARTING"]].plot(y=target, x="SAP_STARTING", style="o")
 train_df[[target, "HEAT_DEMAND_STARTING"]].plot(
     x=target, y="HEAT_DEMAND_STARTING", style="o"
 )
-
 # Both make sense: i.e. the higher the sap, the lower we predict and the higher the heat demand, the higher we predict
 
 # Load the autogluon model and check feature importance
@@ -176,6 +176,8 @@ plot_permutation_importance(exp, fig_kw={"figwidth": 7, "figheight": 6})
 #
 #
 
+from core.MLMetrics import metrics_factory
+
 from core.MLModels import model_factory
 from core.DataClient import dataclient_factory
 import pandas as pd
@@ -216,6 +218,12 @@ mix_df["residual"] = abs(mix_df[predictions_column_name] - mix_df[target])
 mix_df = mix_df.sort_values("residual", ascending=False)
 
 cosine_similarity_df = mix_df[mix_df.columns.difference(["predictions", "residual"])]
+metrics = metrics_factory("Regression")
+metrics.generate_metrics(mix_df["predictions"], mix_df["HEAT_DEMAND_ENDING"])
+
+cosine_similarity_df = mix_df[
+    mix_df.columns.difference(["predictions", "residual", "SAP_ENDING"])
+]
 from sklearn.metrics.pairwise import cosine_similarity
 
 row_index = 0

modules/ml-pipeline/src/pipeline/requirements/predictions/requirements-dev.txt

@@ -1,7 +1,7 @@
-joblib==1.3.2
+joblib==1.5.2
-boto3==1.28.17
+boto3==1.40.61
-pandas==2.1.4
+pandas==2.3.3
-autogluon.tabular[all]==1.0.0
+autogluon.tabular[all]==1.4.0
-dynaconf==3.2.1
+dynaconf==3.2.12
-pyarrow==13.0.0
+pyarrow==20.0.0
-pre-commit==3.3.3
+pre-commit==4.3.0

modules/ml-pipeline/src/pipeline/requirements/predictions/requirements.txt

@@ -1,7 +1,7 @@
-joblib==1.3.2
+joblib==1.5.2
-boto3==1.28.17
+boto3==1.40.61
-pandas==2.1.4
+pandas==2.3.3
-autogluon.tabular[all]==1.0.0
+autogluon.tabular[all]==1.4.0
-dynaconf==3.2.1
+dynaconf==3.2.12
-pyarrow==13.0.0
+pyarrow==20.0.0
-PyYAML==6.0.1
+PyYAML==6.0.3

modules/ml-pipeline/src/pipeline/requirements/training/requirements-dev.txt

@@ -1,10 +1,10 @@
-joblib==1.3.2
+joblib==1.5.2
-boto3==1.28.17
+boto3==1.40.61
-pandas==2.1.4
+pandas==2.3.3
-autogluon.tabular[all]==1.0.0
+autogluon.tabular[all]==1.4.0
-ray==2.6.3
+ray==2.44.1
-dynaconf==3.2.1
+dynaconf==3.2.12
-alibi==0.9.5
+# alibi
-shap==0.42.1
+shap==0.49.1
-pyarrow==13.0.0
+pyarrow==20.0.0
-pre-commit==3.3.3
+pre-commit==4.3.0

modules/ml-pipeline/src/pipeline/requirements/training/requirements.txt

@@ -1,4 +1,4 @@
-boto3==1.28.41
+boto3==1.40.61
-pandas==2.1.4
+pandas==2.3.3
-autogluon.tabular[all]==1.0.0
+autogluon.tabular[all]==1.4.0
-dynaconf==3.2.1
+dynaconf==3.2.12

modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt

@@ -1,4 +1,4 @@
-dvc==3.51.0
+dvc==3.66.0
-dvc-s3==3.2.0
+dvc-s3==3.2.2
-gto==1.7.1
+gto==1.9.0
-pyOpenSSL==23.3.0
+pyOpenSSL==23.3.0