Amazon SageMaker Studio for Data Scientists

This course includes presentations, demonstrations, discussions and exercises. At the end of the course, you will practice creating an end-to-end ML project for tabular data using SageMaker Studio and the SageMaker Python SDK.

Module 1: Amazon SageMaker - Setup and navigation

• Launching SageMaker Studio from the AWS Service Catalog
• Navigating the SageMaker Studio user interface
• Demo 1: SageMaker UI Walkthrough
• Exercise 1: Starting SageMaker Studio from the AWS Service Catalog

Module 2: Data processing

• Using Amazon SageMaker Studio to collect, cleanse, visualize, analyze and transform data
• Set up a repeatable process for data processing
• Use of SageMaker to check whether the collected data is ML-capable
• Recognize biases in the collected data and estimate the accuracy of the base model
• Exercise 2: Analyzing and preparing data with SageMaker Data Wrangler
• Exercise 3: Analyzing and preparing data at scale with Amazon EMR
• Exercise 4: Data processing with SageMaker Processing and the SageMaker Python SDK
• Exercise 5: Feature Engineering with the SageMaker Feature Store

Module 3: Model development

• Using Amazon SageMaker Studio to develop, tune and evaluate an ML model against business objectives and best practices for fairness and explainability
• Fine-tuning of ML models using the automatic hyperparameter optimization function
• Use the SageMaker debugger to uncover problems during model development
• Demo 2: Autopilot
• Exercise 6: Tracking iterations of training and tuning models with SageMaker experiments
• Exercise 7: Analyze, detect and set warnings with the SageMaker debugger
• Exercise 8: Recognize distortions with the help of SageMaker Clarify

Module 4: Deployment and inference

• Use Model Registry to create a model group, register, view and manage model versions, change model approval status and deploy a model
• Design and implement a deployment solution that meets the requirements of the "Inference" use case
• Create, automate and manage end-to-end ML workflows with Amazon SageMaker Pipelines
• Exercise 9: Inferencing with SageMaker Studio
• Exercise 10: Using SageMaker Pipelines and the SageMaker Model Registry with SageMaker Studio

Module 5: Monitoring

• Configure a SageMaker Model Monitor solution to detect issues and trigger alerts for changes in data quality, model quality, bias drift and feature attribution (explainability) drift
• Create a monitoring plan with a predefined interval
• Demo 3: Model monitoring

Module 6: Managing SageMaker Studio resources and updates

• List resources for which fees are incurred
• Remember when instances need to be shut down
• Explain how to shut down instances, notebooks, terminals and kernels
• Understanding the process of updating SageMaker Studio

Capstone

The Capstone Lab brings together the various SageMaker Studio features covered in this course. attendees will have the opportunity to prepare, create, train, and deploy a model using a tabular data set that was not included in previous exercises. attendees can choose between a basic, intermediate and advanced version of the tutorial.

Capstone Lab: Creating an End-to-End Tabular Data ML Project with SageMaker Studio and the SageMaker Python SDK