What this book covers
Chapter 1, Introduction to Amazon Redshift Serverless, presents an overview of Amazon Redshift and Redshift Serverless, walking you through how to get started in just a few minutes and connect using Redshift Query Editor v2. You will create a sample database and run queries using the Notebook feature.
Chapter 2, Data Loading and Analytics on Redshift Serverless, helps you learn different mechanisms to efficiently load data into Redshift Serverless.
Chapter 3, Applying Machine Learning in Your Data Warehouse, introduces machine learning and common use cases to apply to your data warehouse.
Chapter 4, Leveraging Amazon Redshift Machine Learning, builds on Chapter 3. Here, we dive into Amazon Redshift ML, learning how it works and how to leverage it to solve use cases.
Chapter 5, Building Your First Machine Learning Model, sees you get hands-on with Amazon Redshift ML and build your first model using simple CREATE MODEL syntax.
Chapter 6, Building Classification Models, covers classification problems and the algorithms you can use in Amazon Redshift ML to solve these problems and learn how to create a model with user guidance.
Chapter 7, Building Regression Models, helps you identify whether a problem involves regression and explores the different methods available in Amazon Redshift ML for training and building regression models.
Chapter 8, Building Unsupervised Models with K-Means Clustering, shows you how to build machine learning models with unlabeled data and make predictions at the observation level using K-means clustering.
Chapter 9, Deep Learning with Redshift ML, covers the use of deep learning in Amazon Redshift ML using the MLP model type for data that is not linearly separable.
Chapter 10, Creating Custom ML Model with XGBoost, shows you how to use the Auto Off option of Amazon Redshift ML to prepare data in order to build a custom model.
Chapter 11, Bring Your Own Models for In-Database Inference, goes beyond Redshift ML models. Up to this point in the book, we will have run inference queries only on models built directly in Amazon Redshift ML. This chapter shows how you can leverage models built outside of Amazon Redshift ML and execute inference queries inside Amazon Redshift ML.
Chapter 12, Time-Series Forecasting in Your Data Warehouse, dives into forecasting and time-series data using the integration of Amazon Forecast with Amazon Redshift ML.
Chapter 13, Operationalizing and Optimizing Amazon Redshift ML Models, concludes the book by showing techniques to refresh your model, create versions of your models, and optimize your Amazon Redshift ML models.
