Low-Code Machine Learning on AWS

With Amazon SageMaker Data Wrangler and Amazon SageMaker Autopilot, data and research analysts can prepare data, train, and deploy machine learning (ML) models with minimal coding. You will learn to build ML models for tabular and time series data without deep knowledge of ML. You will also review the best practices for using SageMaker Data Wrangler and SageMaker Autopilot. 

After completing this course, you will be able to build ML models to support proofs of concept (POCs). You will also be able to assist data scientists with potential ML model candidates to solve business problems.

• Course level: Intermediate

• Duration: 4 hours

Activities

This course includes eLearning interactions and knowledge checks.

Course objectives

In this course, you will learn to:

• Describe ML concepts and life cycle phases

• Describe metrics used for evaluating model candidates

• Use SageMaker Data Wrangler to prepare tabular and time series data for training an ML model 

• Use SageMaker Autopilot to automatically build ML models and identify the best model from a list of model candidates based on your objective metric  

• Describe best practices for using SageMaker Data Wrangler and SageMaker Autopilot

Intended audience

This course is intended for:

• Data analysts

• Researchers from non-ML domains

• Operations research analysts

• Junior data scientists

Prerequisites

We recommend that attendees of this course have:

• Experience with analysis, cleansing, and transforming tabular or time series data  

• Basic understanding of statistical measures and regression

• AWS Technical Essentials

Course outline

Module 1: Introduction to Machine Learning

ML Introduction

• ML Basics

• Problems ML Can Solve

• ML Life Cycle

• Challenges in Processing Data and Deriving Insights

• Knowledge Check

Model Building and Evaluation Metrics

• Introduction to Model Building

• Applying Evaluation Metrics to Select a Model

• Building an ML Model

Wrap Up

• Knowledge Check

• Conclusion

Module 2: Exploratory Data Analysis and Data Preparation

Introduction to SageMaker Data Wrangler

• SageMaker Data Wrangler

• Data Analysis

Data Preparation

• Quick Model

• Transforming Data

• Developing and Scaling Data Transformations

Wrap Up

• Knowledge Check

• Conclusion

Module 3: Deep Dive on Amazon SageMaker Autopilot

• Introduction to SageMaker Autopilot

• Datasets, Problem Types, and Training Modes

• Validation and Metrics

• Automatic Model Deployment

Wrap Up

• Knowledge Check

• Conclusion

Module 4: Operational Best Practices

Best Practices for SageMaker Data Wrangler

• Environmental Optimization

• Cost Optimization

• Data Optimization

• Security Optimization

Best Practices for SageMaker Autopilot

• Best Practices and Recommendations

Wrap Up

• Knowledge Check

• Conclusion