Book Image

Professional Cloud Architect Google Cloud Certification Guide - Second Edition

By : Konrad Cłapa, Brian Gerrard
5 (1)
Book Image

Professional Cloud Architect Google Cloud Certification Guide - Second Edition

5 (1)
By: Konrad Cłapa, Brian Gerrard

Overview of this book

Google Cloud Platform (GCP) is one of the industry leaders thanks to its array of services that can be leveraged by organizations to bring the best out of their infrastructure. This book is a comprehensive guide for learning methods to effectively utilize GCP services and help you become acquainted with the topics required to pass Google's Professional Cloud Architect certification exam. Following the Professional Cloud Architect's official exam syllabus, you'll first be introduced to the GCP. The book then covers the core services that GCP offers, such as computing and storage, and takes you through effective methods of scaling and automating your cloud infrastructure. As you progress through the chapters, you'll get to grips with containers and services and discover best practices related to the design and process. This revised second edition features new topics such as Cloud Run, Anthos, Data Fusion, Composer, and Data Catalog. By the end of this book, you'll have gained the knowledge required to take and pass the Google Cloud Certification – Professional Cloud Architect exam and become an expert in GCP services.
Table of Contents (25 chapters)
1
Section 1: Introduction to GCP
5
Section 2: Manage, Design, and Plan a Cloud Solution Architecture
14
Chapter 12: Exploring Storage and Database Options in GCP – Part 2
17
Section 3: Secure, Manage and Monitor a Google Cloud Solution
21
Section 4: Exam Focus

The seven steps of ML

Google indicates that there are seven steps of ML:

  1. Gathering the data
  2. Preparing the data
  3. Choosing a model
  4. Training
  5. Evaluation
  6. Hyperparameter tuning
  7. Prediction

Let's go through each of the steps with an example. Let's say we are training the model to check whether a piece of fruit is an apple or a lemon. We need to choose the features that we will use to train our model. There are lots of possible alternatives, including shape, color, taste, and skin smoothness:

Figure 14.2 – Objects for the ML experiment

For this particular training, we will use color and sugar content. The second measurement is probably not the simplest one to obtain, but for this test, let's assume that we have the proper equipment to do so.

Gathering and preparing the data

Let's start gathering data by buying multiple apples and lemons. We will start with the creation of tables with two features...