This repository has been archived by the owner on Jul 10, 2023. It is now read-only.
Changed
- Removed code to manage the Pinpoint Event Stream, Kinesis Firehose, and Glue Database configuration.
- Added dependency on the Digital User Engagement Events Database to manage the Pinpoint Event Stream and event database creation.
- Modified logic to write a ChurnPrediction Metric to the Endpoints allowing for a Dynamic Predicted to Churn segment instead of a static imported segment.
- Providing a Parquet formatted file for the sample pinpoint events to match the database configuration.
- Added manual schema registration in Glue for the Pinpoint endpoint exports, removing dependency on a Glue crawler.
- Removed static customer data file and moved attributes for ML predictions to endpoints with the creation of the SampleImport.csv file.
- SageMaker notebook instance placed inside of a VPC for enhanced security of customer data files.
- Updated SageMaker notebook to use the latest version of the SageMaker Python SDK.
Refer to changelog for more information.