book

Automated Machine Learning with Microsoft Azure

Name: Automated Machine Learning with Microsoft Azure
Author: Dennis Sawyers
ISBN: 9781800565319

by Dennis Sawyers

April 2021

Intermediate to advanced

340 pages

7h 15m

English

Packt Publishing

Read now

Unlock full access

Automated Machine Learning with Microsoft Azure
ContributorsAbout the authorAbout the reviewer
Preface
Who this book is forWhat this book coversTo get the most out of this bookDownload the example code filesDownload the color imagesConventions usedGet in touchReviews
Section 1: AutoML Explained – Why, What, and How
Chapter 1: Introducing AutoML
Explaining data science's ROI problemDefining machine learning, data science, and AIMachine learning versus traditional softwareThe five steps to machine learning successPutting it all togetherAnalyzing why AI projects fail slowlySolving the ROI problem with AutoMLSummary
Chapter 2: Getting Started with Azure Machine Learning Service
Technical requirementsCreating your first AMLS workspaceCreating an Azure account Creating an AMLS workspaceCreating an AMLS workspace with codeNavigating AML studioBuilding compute to run your AutoML jobsCreating a compute instanceCreating a compute clusterCreating a compute cluster and compute instance with the Azure CLIWorking with data in AMLSCreating a dataset using the GUICreating a dataset using codeUnderstanding how AutoML works on AzureEnsuring data quality with data guardrailsImproving data with intelligent feature engineeringNormalizing data for ML with iterative data transformationTraining models quickly with iterative ML model buildingGetting the best results with ML model ensemblingSummary
Chapter 3: Training Your First AutoML Model
Technical requirementsLoading data into AMLS for AutoMLCreating an AutoML solutionInterpreting your AutoML resultsUnderstanding data guardrailsUnderstanding model metricsExplaining your AutoML modelObtaining better AutoML performanceSummary
Section 2: AutoML for Regression, Classification, and Forecasting – A Step-by-Step Guide
Chapter 4: Building an AutoML Regression Solution
Technical requirementsPreparing data for AutoML regressionSetting up your Jupyter environmentPreparing your data for AutoMLTraining an AutoML regression modelRegistering your trained regression modelFine-tuning your AutoML regression modelImproving AutoML regression modelsUnderstanding AutoML regression algorithmsSummary
Chapter 5: Building an AutoML Classification Solution
Technical requirementsPrepping data for AutoML classificationNavigating to your Jupyter environmentLoading and transforming your dataTraining an AutoML classification modelRegistering your trained classification modelTraining an AutoML multiclass modelFine-tuning your AutoML classification modelImproving AutoML classification modelsUnderstanding AutoML classification algorithmsSummary
Chapter 6: Building an AutoML Forecasting Solution
Technical requirementsPrepping data for AutoML forecastingNavigating to your Jupyter environmentLoading and transforming your dataTraining an AutoML forecasting modelTraining a forecasting model with standard algorithmsTraining a forecasting model with Prophet and ARIMARegistering your trained forecasting modelFine-tuning your AutoML forecasting modelImproving AutoML forecasting models Understanding AutoML forecasting algorithmsSummary

Chapter 7: Using the Many Models Solution Accelerator
Technical requirementsInstalling the many models solution acceleratorCreating a new notebook in your Jupyter environmentInstalling the MMSA from GitHubPrepping data for many modelsPrepping the sample OJ datasetPrepping a pandas dataframeTraining many models simultaneouslyTraining the sample OJ datasetTraining your sample dataset with the MMSAScoring new data for many modelsScoring OJ sales data with the MMSAScoring your sample dataset with many modelsImproving your many models resultsSummary
Section 3: AutoML in Production – Automating Real-Time and Batch Scoring Solutions
Chapter 8: Choosing Real-Time versus Batch Scoring
Technical requirementsArchitecting batch scoring solutionsUnderstanding the five-step batch scoring processScheduling your batch scoring solutionScoring data in batches and delivering resultsChoosing batch over real timeArchitecting real-time scoring solutionsUnderstanding the four-step real-time scoring processTraining a model for real-time deployment Delivering results in real timeKnowing when to use real-time scoringChoosing real-time over batch solutionsDetermining batch versus real-time scoring scenariosScenarios for real-time or batch scoringAnswers for the type of solution appropriate for each scenarioSummary
Chapter 9: Implementing a Batch Scoring Solution
Technical requirementsCreating an ML pipelineCoding the first three steps of your ML scoring pipeline Creating a Python script to score data in your ML pipelineCreating and containerizing an environmentConfiguring and running your ML scoring pipeline Accessing your scored predictions via AML studioCreating a parallel scoring pipelineCoding the first three steps of your ML parallel scoring pipeline Creating Python scripts to score data in your ML parallel pipelineConfiguring and running your ML parallel scoring pipelineCreating an AutoML training pipelineCoding the first two steps of your AutoML training pipelineConfiguring your AutoML model training settings and stepCreating a Python script to register your modelConfiguring and running your AutoML training pipelineTriggering and scheduling your ML pipelinesTriggering your published pipeline from the GUITriggering and scheduling a published pipeline through codeSummary
Chapter 10: Creating End-to-End AutoML Solutions
Technical requirementsConnecting AMLS to ADFCreating an ADFCreating a service principal and granting accessCreating a linked service to connect ADF with AMLSScheduling a machine learning pipeline in ADFTransferring data using ADFInstalling a self-hosted integration runtimeCreating an Azure Blob storage linked serviceCreating a linked service to your PCCreating an ADF pipeline to copy dataAutomating an end-to-end scoring solutionEditing an ML pipeline to score new dataCreating an ADF pipeline to run your ML pipelineAdding a trigger to your ADF pipelineAutomating an end-to-end training solutionCreating a pipeline to copy data into AzureEditing an ML pipeline to train with new data Adding a Machine Learning Execute Pipeline activity to your ADF pipelineSummary
Chapter 11: Implementing a Real-Time Scoring Solution
Technical requirementsCreating real-time endpoints through the UICreating an ACI-hosted endpoint through the UICreating an AKS cluster through the UICreating an AKS-hosted endpoint through the UICreating real-time endpoints through the SDKCreating and testing a real-time endpoint with ACI through PythonCreating an AKS cluster through PythonCreating and testing a real-time endpoint with AKS through PythonImproving performance on your AKS clusterSummary
Chapter 12: Realizing Business Value with AutoML
Technical requirementsArchitecting AutoML solutionsMaking key architectural decisions for AutoML solutionsArchitecting a batch solutionArchitecting a real-time solutionVisualizing AutoML modeling resultsVisualizing the results of classificationVisualizing the results of forecasting and regressionExplaining AutoML results to your businessUsing AutoML in other Microsoft productsUsing AutoML within PowerBIUsing AutoML within Azure Synapse AnalyticsUsing AutoML with ML.NETUsing AutoML on SQL Server, HDInsight, and Azure DatabricksRealizing business valueGetting the business to adopt a new, automated solution Getting the business to replace an older, automated processGetting the business to adopt a new, decision-assistance toolGetting the business to replace an old decision assistance toolSummary
Why subscribe?
Other Books You May EnjoyPackt is searching for authors like youLeave a review - let other readers know what you think

Overview

"Automated Machine Learning with Microsoft Azure" is your comprehensive guide to building advanced AI solutions using Azure AutoML. By following the detailed instructions in this book, you will be able to train, deploy, and scale machine learning models efficiently. This book equips you with the tools to harness automatic machine learning to create impactful AI applications.

What this Book will help me do

Learn how to train classification, regression, and forecasting models using Azure AutoML.
Gain expertise in preparing data for training and deployment within the Azure environment.
Master the configuration of AutoML settings to optimize model accuracy.
Understand the distinction between batch and real-time scoring solution, and when to apply each.
Deploy and scale machine learning models for production using Azure Kubernetes Service.

Author(s)

Dennis Michael Sawyers has extensive experience in data science and machine learning, focusing on automating workflows to enhance productivity. With a background in computer science and artificial intelligence, Dennis brings a practical perspective to teaching technical concepts. His approach emphasizes real-world applications, making AI accessible and impactful.

Who is it for?

This book is for data scientists, machine learning engineers, and business professionals looking to integrate AI into their workflows. While beginner AI knowledge will work, this book is designed for those with some technical background in fields like computer science or IT. It particularly suits readers who want to deploy scalable AI solutions using Microsoft Azure and Python.

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Practical Automated Machine Learning on Azure

Publisher Resources

ISBN: 9781800565319

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills