Book Image

Amazon SageMaker Best Practices

By : Sireesha Muppala, Randy DeFauw, Shelbee Eigenbrode
Book Image

Amazon SageMaker Best Practices

By: Sireesha Muppala, Randy DeFauw, Shelbee Eigenbrode

Overview of this book

Amazon SageMaker is a fully managed AWS service that provides the ability to build, train, deploy, and monitor machine learning models. The book begins with a high-level overview of Amazon SageMaker capabilities that map to the various phases of the machine learning process to help set the right foundation. You'll learn efficient tactics to address data science challenges such as processing data at scale, data preparation, connecting to big data pipelines, identifying data bias, running A/B tests, and model explainability using Amazon SageMaker. As you advance, you'll understand how you can tackle the challenge of training at scale, including how to use large data sets while saving costs, monitoring training resources to identify bottlenecks, speeding up long training jobs, and tracking multiple models trained for a common goal. Moving ahead, you'll find out how you can integrate Amazon SageMaker with other AWS to build reliable, cost-optimized, and automated machine learning applications. In addition to this, you'll build ML pipelines integrated with MLOps principles and apply best practices to build secure and performant solutions. By the end of the book, you'll confidently be able to apply Amazon SageMaker's wide range of capabilities to the full spectrum of machine learning workflows.
Table of Contents (20 chapters)
1
Section 1: Processing Data at Scale
7
Section 2: Model Training Challenges
10
Section 3: Manage and Monitor Models
15
Section 4: Automate and Operationalize Machine Learning

Bias detection and explainability with Data Wrangler and Clarify

Now that we've done some initial work in exploring and preparing our data, let's do a sanity check on our input data. While bias can mean many things, one particular symptom is a dataset that has many more samples of one type of data than another, which will affect our model's performance. We'll use Data Wrangler to see if our input data is imbalanced and understand which features are most important to our model.

To begin, add an analysis to the flow. Choose Bias Report from the list of available transformations and use the mobile column as the label, with 1 as the predicted value. Choose city as the column to use for bias analysis, then click Check for bias. In this scenario, we want to determine whether our dataset is somehow imbalanced with respect to the city and whether the data was collected at a mobile station. If the quality of data from mobile sources is inferior to non-mobile sources,...