Book Image

Architecting Google Cloud Solutions

By : Victor Dantas
Book Image

Architecting Google Cloud Solutions

By: Victor Dantas

Overview of this book

Google has been one of the top players in the public cloud domain thanks to its agility and performance capabilities. This book will help you design, develop, and manage robust, secure, and dynamic solutions to successfully meet your business needs. You'll learn how to plan and design network, compute, storage, and big data systems that incorporate security and compliance from the ground up. The chapters will cover simple to complex use cases for devising solutions to business problems, before focusing on how to leverage Google Cloud's Platform-as-a-Service (PaaS) and Software-as-a-Service (SaaS) capabilities for designing modern no-operations platforms. Throughout this book, you'll discover how to design for scalability, resiliency, and high availability. Later, you'll find out how to use Google Cloud to design modern applications using microservices architecture, automation, and Infrastructure-as-Code (IaC) practices. The concluding chapters then demonstrate how to apply machine learning and artificial intelligence (AI) to derive insights from your data. Finally, you will discover best practices for operating and monitoring your cloud solutions, as well as performing troubleshooting and quality assurance. By the end of this Google Cloud book, you'll be able to design robust enterprise-grade solutions using Google Cloud Platform.
Table of Contents (17 chapters)
1
Section 1: Introduction to Google Cloud
4
Section 2: Designing Great Solutions in Google Cloud
10
Section 3: Designing for the Modern Enterprise

Building custom ML models with Cloud AI Platform and BigQuery ML

Before getting to the different components and capabilities within Cloud AI Platform (Unified) – hereafter referred to as AI Platform – it's useful to understand the ML workflow stages. A typical production-ready workflow for a supervised ML application is represented in the following diagram:

Figure 11.5 – The ML workflow

Let's break this down.

The first and most fundamental step is that of identifying the business goals and formulating the business case. Ensure the problem is well defined by answering the following two questions at a minimum:

  1. What information are you trying to get out of the model?
  2. Why will this information be useful?

Sometimes these questions generate hypotheses to be tested. Therefore, you must determine the project's feasibility and whether you can afford to fall short of achieving the outcomes. A machine learning...