Build a no-code ML workflow with Snowflake, Amazon SageMaker Canvas and Amazon Quick – Part 1: Setting up your Snowflake environment
aws ·
This AWS blog post is Part 1 of a three-part series on building a no-code machine learning workflow using Snowflake, Amazon SageMaker Canvas, and Amazon QuickSight. It describes a healthcare organization with extensive operational data in Snowflake but limited data science resources, making it difficult to generate predictive insights. The proposed solution uses Amazon SageMaker Canvas to let business users visually explore data, build models, and generate predictions without writing code, with results visualized through QuickSight dashboards. This first part focuses on setting up the AWS and Snowflake environments, including creating a Snowflake database and warehouse, defining a fraud detection table, and generating sample transaction data with a SQL script. The post also explains how to run verification queries and retrieve the Snowflake organization account name needed for connecting to SageMaker Canvas in Part 2. The overall architecture is designed to extend the value of existing Snowflake investments while reducing dependence on specialized ML engineering resources.
aws