Merge branch 'main' of github.com:Hestia-Homes/Model into mlmodel

.github/workflows/deploy_sap_model_lambda.yml

@@ -56,7 +56,7 @@ jobs:
 
       # Building and pushing Docker image with caching
       - name: Build and push Docker image
-        uses: docker/build-push-action@v4
+        uses: docker/build-push-action@v3
         with:
           context: ./model_data/simulation_system
           file: ./model_data/simulation_system/Dockerfiles/Dockerfile.prediction.lambda
@@ -65,12 +65,14 @@ jobs:
           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: ${{ github.ref_name }}
           MODEL_DIRECTORY_BUCKET: 'retrofit-model-directory-${{ github.ref_name }}'
           PREDICTIONS_BUCKET: 'retrofit-sap-predictions-${{ github.ref_name }}'
+          DATA_BUCKET: 'retrofit-data-${{ github.ref_name }}'
           DOMAIN_NAME: ${{ steps.set_domain.outputs.domain }}
           ECR_URI: ${{ steps.set_ecr_credentials.outputs.ecr_uri }}
           GITHUB_SHA: ${{ github.sha }}

model_data/simulation_system/handlers/predictions_app.py

@@ -1,7 +1,11 @@
 import os
-import urllib.parse
+import logging
+
 from predictions import prediction
 
+logger = logging.getLogger()
+logger.setLevel(logging.INFO)
+
 RUNTIME_ENVIRONMENT = os.environ.get("RUNTIME_ENVIRONMENT", "dev")
 
 
@@ -10,14 +14,15 @@ def handler(event, context):
     Take in event and trigger the prediction pipeline
     """
 
+    logger.info("received event: " + str(event))
+
     # Assuming a file in a bucket landing for now?
     # Assuming we have a model to use
 
-    payload = event["body"]
-    data_path = payload["file_location"]
-    property_id = payload["property_id"]
-    portfolio_id = payload["portfolio_id"]
-    created_at = payload["created_at"]
+    data_path = event["file_location"]
+    property_id = event["property_id"]
+    portfolio_id = event["portfolio_id"]
+    created_at = event["created_at"]
 
     try:
         # We could fix the model path but for the moment, we just take the best model path based on the registry
@@ -30,8 +35,8 @@ def handler(event, context):
         return storage_filepath
 
     except (Exception, KeyError, ValueError) as e:
-        print("Prediction failed")
-        print(e)
+        logger.info("Prediction failed")
+        logger.info(e)
 
 
 if __name__ == "__main__":

sapmodel.serverless.yml

@@ -8,6 +8,7 @@ provider:
     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: ${env:GITHUB_SHA}
@@ -52,7 +53,7 @@ resources:
             PolicyDocument:
               Version: '2012-10-17'
               Statement:
-                # Allow reading from MODEL_DIRECTORY_BUCKET
+                # Allow reading from MODEL_DIRECTORY_BUCKET and DATA_BUCKET
                 - Effect: Allow
                   Action:
                     - s3:GetObject
@@ -60,6 +61,8 @@ resources:
                   Resource:
                     - arn:aws:s3:::${env:MODEL_DIRECTORY_BUCKET}
                     - arn:aws:s3:::${env:MODEL_DIRECTORY_BUCKET}/*
+                    - arn:aws:s3:::${env:DATA_BUCKET}
+                    - arn:aws:s3:::${env:DATA_BUCKET}/*
                 # Allow reading and writing to PREDICTIONS_BUCKET
                 - Effect: Allow
                   Action:
@@ -68,4 +71,4 @@ resources:
                     - s3:ListBucket
                   Resource:
                     - arn:aws:s3:::${env:PREDICTIONS_BUCKET}
-                    - arn:aws:s3:::${env:PREDICTIONS_BUCKET}/*
+                    - arn:aws:s3:::${env:PREDICTIONS_BUCKET}/*