formatted

.github/workflows/Deploy.yml

@@ -0,0 +1,115 @@
+name: Sap Change Model Deploy
+
+on:
+  push:
+    branches: [ sap_change-dev, sap_change-prod ]
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.10.12
+
+      - name: Install Serverless and plugins
+        run: |
+          npm install -g serverless
+          npm install -g serverless-domain-manager
+
+      - name: AWS credentials for dev
+        if: github.ref == 'refs/heads/dev'
+        uses: aws-actions/configure-aws-credentials@v1
+        with:
+          aws-access-key-id: ${{ secrets.DEV_AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.DEV_AWS_SECRET_ACCESS_KEY }}
+          aws-region: eu-west-2
+
+      - name: AWS credentials for prod
+        if: github.ref == 'refs/heads/prod'
+        uses: aws-actions/configure-aws-credentials@v1
+        with:
+          aws-access-key-id: ${{ secrets.PROD_AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.PROD_AWS_SECRET_ACCESS_KEY }}
+          aws-region: eu-west-2
+
+      # Set up all of the secrets required for the deployment
+      - name: set secret prefix which is used across multiple steps
+        id: secret_prefix
+        run: |
+            # Convert branch name to uppercase and replace hyphens with underscores
+            echo "::set-output name=secret_prefix::$(echo "${{ github.ref_name }}" | tr 'a-z-' 'A-Z_')"
+
+      - name: Set domain name
+        id: set_domain
+        run: echo "::set-output name=domain::${{ secrets[format('{0}_DOMAIN_NAME', steps.secret_prefix.outputs.secret_prefix)] }}"
+
+      - name: Set ECR credentials
+        id: set_ecr_credentials
+        run: |
+          # Fetch the secret using the secret prefix
+          echo "::set-output name=ecr_uri::${{ secrets[format('{0}_ECR_URI', steps.secret_prefix.outputs.secret_prefix)] }}"
+
+      - name: Set S3 buckets
+        id: set_s3_buckets
+        run: |
+          # Fetch the secret using the secret prefix
+          echo "::set-output name=data_bucket::${{ secrets[format('{0}_DATA_BUCKET', steps.secret_prefix.outputs.secret_prefix)] }}"
+          echo "::set-output name=predictions_bucket::${{ secrets[format('{0}_PREDICTIONS_BUCKET', steps.secret_prefix.outputs.secret_prefix)] }}"
+          echo "::set-output name=model_directory_bucket::${{ secrets[format('{0}_MODEL_DIRECTORY_BUCKET', steps.secret_prefix.outputs.secret_prefix)] }}"
+
+      - name: Set stack_name
+        id: set_stack_name
+        run: |
+          if [[ "${{ github.ref_name }}" == "sap_change-dev" || "${{ github.ref_name }}" == "sap_change-prod" ]]; then
+            echo "::set-output name=stack_name::sapmodel"
+          else
+            echo "::set-output name=stack_name::"
+          fi
+
+      - name: Set runtime_environment
+        id: set_runtime_environment
+        run: |
+          # Extract the suffix after the hyphen from the branch name
+          runtime_environment=$(echo "${{ github.ref_name }}" | awk -F'-' '{print $NF}')
+          echo "::set-output name=runtime_environment::$runtime_environment"
+
+
+      - name: Setup Docker
+        uses: docker/setup-buildx-action@v1
+
+      - name: Login to ECR
+        run: |
+          aws ecr get-login-password --region eu-west-2 | docker login --username AWS --password-stdin ${{ steps.set_ecr_credentials.outputs.ecr_uri }}
+
+      # Building and pushing Docker image with caching
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v3
+        with:
+          context: ./model_data/simulation_system
+          file: ./model_data/simulation_system/Dockerfiles/Dockerfile.prediction.lambda
+          push: true
+          tags: ${{ steps.set_ecr_credentials.outputs.ecr_uri }}:${{ github.sha }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          platform: linux/amd64
+          provenance: false
+
+      - name: Deploy to AWS Lambda via Serverless
+        env:
+          RUNTIME_ENVIRONMENT: ${{ steps.set_runtime_environment.outputs.runtime_environment }}
+          MODEL_DIRECTORY_BUCKET: ${{ steps.s3_buckets.outputs.model_directory_bucket }}
+          PREDICTIONS_BUCKET: ${{ steps.s3_buckets.outputs.predictions_bucket }}
+          DATA_BUCKET:  ${{ steps.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 }}
+          STACK_NAME: ${{ steps.set_stack_name.outputs.stack_name }}
+        run: |
+          # Deploy to AWS Lambda via Serverless
+          sls deploy --config serverless.yml --stage ${{ steps.set_runtime_environment.outputs.runtime_environment }} --verbose

README.md

@@ -19,5 +19,24 @@ These branches will differ by the configuration files that define the data used
 
 # Deployment
 
-TBD
+Scripts associated to deployment can be found in the deployment/ folder.
 
+Deployment is automated via Github Actions, where a deployment is triggered by a push to one of the
+protected branch, with one of dev or prod as the suffix, describing the target environment.
+
+The github actions file will build and push a docker image to ECR and then deploy a lambda
+which produces predictions for the relevant model.
+
+In order for this to be set up, some key environment variables needs to be inserted into Github
+secrets. Each different model and protected branch has its own set of secrets which allows for flexibility
+between different pipelines.
+
+For example, for the branch sap_change-dev, the prefix=SAP_CHANGE_DEV, and the following secrets are:
+
+- {prefix}_ECR_URI, which is the URI of the ECR repository to push to. For example, for the
+   sap change model this is the lambda-sap-prediction-dev repository.
+- {prefix}_DOMAIN_NAME, is the custom domain name. This is likely going to be the same across the different
+   models, but is still included in the secrets for flexibility.
+- {prefix}_DATA_BUCKET, is the name of the s3 data bucket where data to be scored by the model is stored
+- {prefix}_MODEL_BUCKET, is the name of the s3 bucket where the model is stored
+- {prefix}_PREDICTIONS_BUCKET, is the name of the s3 bucket where the predictions are stored

deployment/Dockerfile.prediction.lambda

@@ -0,0 +1,21 @@
+FROM public.ecr.aws/lambda/python:3.10
+
+# Set the working directory
+WORKDIR ${LAMBDA_TASK_ROOT}
+ENV PYTHONPATH "${PYTHONPATH}:${LAMBDA_TASK_ROOT}"
+
+# Install necessary build tools - required to test locally
+RUN yum install -y gcc python3-devel
+
+# Install python packages
+COPY modules/ml-pipeline/src/requirements/predictions/requirements.txt ./requirements.txt
+RUN pip install --no-cache-dir -r ./requirements.txt
+
+# Copy the project code
+COPY modules/ml-pipeline/src/pipeline ./pipeline
+# Copy the handler
+COPY deployment/handlers/prediction_app.py prediction_app.py
+# Get the model
+# RUN dev pull -r ${RUNTIME_ENVIRONMENT}
+
+CMD [ "prediction_handler.handler" ]

deployment/handlers/prediction_app.py

@@ -0,0 +1,93 @@
+"""
+This script is the handler for the lambda prediction function, responsible
+for producting predictions for a model
+"""
+
+import boto3
+from botocore.exceptions import NoCredentialsError
+import json
+from io import StringIO
+import os
+import logging
+
+logger = logging.getLogger()
+logger.setLevel(logging.INFO)
+
+RUNTIME_ENVIRONMENT = os.environ.get("RUNTIME_ENVIRONMENT", "dev")
+
+
+def upload_dataframe_to_s3(df, bucket, s3_file_name):
+    """
+    Upload a pandas DataFrame to an S3 bucket as CSV
+
+    :param df: DataFrame to upload
+    :param bucket: Bucket to upload to
+    :param s3_file_name: S3 object name
+    :return: True if file was uploaded, else False
+    """
+
+    # Initialize the S3 client
+    s3 = boto3.client("s3")
+    csv_buffer = StringIO()
+
+    # Write the DataFrame to the buffer as CSV
+    df.to_csv(csv_buffer, index=False)
+
+    try:
+        # Upload the CSV from the buffer to S3
+        s3.put_object(Bucket=bucket, Key=s3_file_name, Body=csv_buffer.getvalue())
+        print(f"Successfully uploaded DataFrame to {bucket}/{s3_file_name}")
+        return True
+    except NoCredentialsError:
+        print("Credentials not available")
+        return False
+
+
+def handler(event, context):
+    """
+    Take in event and trigger the prediction pipeline
+    """
+
+    logger.info("received event: " + str(event))
+
+    try:
+        body = (
+            json.loads(event["body"])
+            if not isinstance(event["body"], dict)
+            else event["body"]
+        )
+
+        logger.info("Inside handler with body: " + str(body))
+
+        data_path = body["file_location"]
+        property_id = body["property_id"]
+        portfolio_id = body["portfolio_id"]
+        created_at = body["created_at"]
+
+        # TODO: Implement the loading of the model and prediction
+
+        storage_filepath = f"{portfolio_id}/{property_id}/{created_at}.csv"
+
+        # upload_dataframe_to_s3(
+        #     df=outputs,
+        #     bucket=f"retrofit-sap-predictions-{RUNTIME_ENVIRONMENT}",
+        #     s3_file_name=storage_filepath
+        # )
+
+        return {
+            "statusCode": 200,
+            "body": json.dumps(
+                {
+                    "message": "Successfully processed input",
+                    "storage_filepath": storage_filepath,
+                }
+            ),
+        }
+
+    except (Exception, KeyError, ValueError) as e:
+        logger.info("Prediction failed")
+        logger.info(e)
+        return {
+            "statusCode": 500,
+            "body": json.dumps({"message": "Prediction failed", "error": str(e)}),
+        }

deployment/serverless.yml

@@ -0,0 +1,56 @@
+service: ${env:STACK_NAME}
+
+provider:
+  name: aws
+  region: eu-west-2
+  architecture: x86_64
+  environment:
+    RUNTIME_ENVIRONMENT: ${env:RUNTIME_ENVIRONMENT}
+    MODEL_DIRECTORY_BUCKET: ${env:MODEL_DIRECTORY_BUCKET}
+    PREDICTIONS_BUCKET: ${env:PREDICTIONS_BUCKET}
+    DATA_BUCKET: ${env:DATA_BUCKET}
+    DOMAIN_NAME: ${env:DOMAIN_NAME}
+    ECR_URI: ${env:ECR_URI}
+    GITHUB_SHA: ${env:GITHUB_SHA}
+  iam:
+    role:
+      name: ${env:STACK_NAME}_s3_access
+      statements:
+        # Allow reading from MODEL_DIRECTORY_BUCKET and DATA_BUCKET
+        - Effect: Allow
+          Action:
+            - s3:*
+          Resource:
+            - arn:aws:s3:::${env:MODEL_DIRECTORY_BUCKET}
+            - arn:aws:s3:::${env:MODEL_DIRECTORY_BUCKET}/*
+            - arn:aws:s3:::${env:DATA_BUCKET}
+            - arn:aws:s3:::${env:DATA_BUCKET}/*
+        # Allow reading and writing to PREDICTIONS_BUCKET
+        - Effect: Allow
+          Action:
+            - s3:*
+          Resource:
+            - arn:aws:s3:::${env:PREDICTIONS_BUCKET}
+            - arn:aws:s3:::${env:PREDICTIONS_BUCKET}/*
+
+
+
+plugins:
+  - serverless-domain-manager
+
+custom:
+  customDomain:
+    domainName: api.${self:provider.environment.DOMAIN_NAME}
+    basePath: ${env:STACK_NAME}
+    createRoute53Record: true
+    certificateArn: ${ssm:/ssl_certificate_arn}
+
+functions:
+  sap_prediction_lambda:
+    image:
+      uri: ${env:ECR_URI}:${env:GITHUB_SHA}
+    events:
+      - http:
+          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