Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Serverless Machine Learning with Amazon Redshift ML

You're reading from   Serverless Machine Learning with Amazon Redshift ML Create, train, and deploy machine learning models using familiar SQL commands

Arrow left icon
Product type Paperback
Published in Aug 2023
Publisher Packt
ISBN-13 9781804619285
Length 290 pages
Edition 1st Edition
Languages
Arrow right icon
Authors (4):
Arrow left icon
Phil Bates Phil Bates
Author Profile Icon Phil Bates
Phil Bates
Sumeet Joshi Sumeet Joshi
Author Profile Icon Sumeet Joshi
Sumeet Joshi
Debu Panda Debu Panda
Author Profile Icon Debu Panda
Debu Panda
Bhanu Pittampally Bhanu Pittampally
Author Profile Icon Bhanu Pittampally
Bhanu Pittampally
Arrow right icon
View More author details
Toc

Table of Contents (19) Chapters Close

Preface 1. Part 1:Redshift Overview: Getting Started with Redshift Serverless and an Introduction to Machine Learning
2. Chapter 1: Introduction to Amazon Redshift Serverless FREE CHAPTER 3. Chapter 2: Data Loading and Analytics on Redshift Serverless 4. Chapter 3: Applying Machine Learning in Your Data Warehouse 5. Part 2:Getting Started with Redshift ML
6. Chapter 4: Leveraging Amazon Redshift ML 7. Chapter 5: Building Your First Machine Learning Model 8. Chapter 6: Building Classification Models 9. Chapter 7: Building Regression Models 10. Chapter 8: Building Unsupervised Models with K-Means Clustering 11. Part 3:Deploying Models with Redshift ML
12. Chapter 9: Deep Learning with Redshift ML 13. Chapter 10: Creating a Custom ML Model with XGBoost 14. Chapter 11: Bringing Your Own Models for Database Inference 15. Chapter 12: Time-Series Forecasting in Your Data Warehouse 16. Chapter 13: Operationalizing and Optimizing Amazon Redshift ML Models 17. Index 18. Other Books You May Enjoy

Optimizing the Redshift models’ accuracy

In this section, we will review best practices for maintaining the optimal accuracy of your models.

You will need to continually monitor your models over time to ensure the scores stay stable between model training runs. Consider the new version of the model we created here:

Figure 13.4 – New model output

Figure 13.4 – New model output

Create a table similar to this and track each week’s mean square error (MSE) score from the SHOW MODEL output:

CREATE TABLE chapter13.model_score_history (
    model_name character varying(500),
    schema_name character varying(500),
    score integer,
    variance integer,
    training_date date
)
DISTSTYLE AUTO;

The variance will be the difference in the score of each successive version of a model.

Check how your models are trending by writing a query like this:

Select model_name...
lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at £16.99/month. Cancel anytime