O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Pragmatic AI: An Introduction to Cloud-Based Machine Learning, First Edition

Book Description

Master Powerful Off-the-Shelf Business Solutions for AI and Machine Learning


Pragmatic AI will help you solve real-world problems with contemporary machine learning, artificial intelligence, and cloud computing tools. Noah Gift demystifies all the concepts and tools you need to get results—even if you don’t have a strong background in math or data science.


Gift illuminates powerful off-the-shelf cloud offerings from Amazon, Google, and Microsoft, and demonstrates proven techniques using the Python data science ecosystem. His workflows and examples help you streamline and simplify every step, from deployment to production, and build exceptionally scalable solutions. As you learn how machine language (ML) solutions work, you’ll gain a more intuitive understanding of what you can achieve with them and how to maximize their value.


Building on these fundamentals, you’ll walk step-by-step through building cloud-based AI/ML applications to address realistic issues in sports marketing, project management, product pricing, real estate, and beyond. Whether you’re a business professional, decision-maker, student, or programmer, Gift’s expert guidance and wide-ranging case studies will prepare you to solve data science problems in virtually any environment.

  • Get and configure all the tools you’ll need
  • Quickly review all the Python you need to start building machine learning applications
  • Master the AI and ML toolchain and project lifecycle
  • Work with Python data science tools such as IPython, Pandas, Numpy, Juypter Notebook, and Sklearn
  • Incorporate a pragmatic feedback loop that continually improves the efficiency of your workflows and systems
  • Develop cloud AI solutions with Google Cloud Platform, including TPU, Colaboratory, and Datalab services
  • Define Amazon Web Services cloud AI workflows, including spot instances, code pipelines, boto, and more
  • Work with Microsoft Azure AI APIs
  • Walk through building six real-world AI applications, from start to finish

Register your book for convenient access to downloads, updates, and/or corrections as they become available. See inside book for details.

Table of Contents

  1. Cover Page
  2. Title Page
  3. Contents
  4. Preface
    1. Who Should Read This Book
    2. How This Book Is Organized
    3. Example Code
    4. Conventions Used in This Book
  5. I: Introduction to Pragmatic AI
    1. 1. Introduction to Pragmatic AI
      1. Functional Introduction to Python
      2. Using Control Structures in Python
      3. Final Thoughts
    2. 2. AI and ML Toolchain
      1. Python Data Science Ecosystem: IPython, Pandas, NumPy, Jupyter Notebook, Sklearn
      2. R, RStudio, Shiny, and ggplot
      3. Spreadsheets: Excel and Google Sheets
      4. Cloud AI Development with Amazon Web Services
      5. DevOps on AWS
      6. Basic Docker Setup for Data Science
      7. Other Build Servers: Jenkins, CircleCI, and Travis
      8. Summary
    3. 3. Spartan AI Lifecycle
      1. Pragmatic Production Feedback Loop
      2. AWS SageMaker
      3. AWS Glue Feedback Loop
      4. AWS Batch
      5. Docker-based Feedback Loops
      6. Summary
  6. II: AI in the Cloud
    1. 4. Cloud AI Development with Google Cloud Platform
      1. GCP Overview
      2. Colaboratory
      3. Datalab
      4. BigQuery
      5. Google Cloud AI Services
      6. Cloud TPU and TensorFlow
      7. Summary
    2. 5. Cloud AI Development with Amazon Web Services
      1. Building Augmented Reality and Virtual Reality Solutions on AWS
      2. Summary
  7. III: Creating Practical AI Applications from Scratch
    1. 6. Predicting Social-Media Influence in the NBA
      1. Phrasing the Problem
      2. Collecting Challenging Data Sources
      3. Unsupervised Machine Learning on NBA Players
      4. Further Pragmatic Steps and Learnings
      5. Summary
    2. 7. Creating an Intelligent Slackbot on AWS
      1. Creating a Bot
      2. Converting the Library into a Command-Line Tool
      3. Taking the Bot to the Next Level with AWS Step Functions
      4. Getting IAM Credentials Set Up
      5. Building Out the Step Function
      6. Summary
    3. 8. Finding Project Management Insights from a GitHub Organization
      1. Overview of the Problems in Software Project Management
      2. Creating an Initial Data Science Project Skeleton
      3. Collecting and Transforming the Data
      4. Talking to an Entire GitHub Organization
      5. Creating Domain-specific Stats
      6. Wiring a Data Science Project into a CLI
      7. Using Jupyter Notebook to Explore a GitHub Organization
      8. Looking at File Metadata in the CPython Project
      9. Looking at Deleted Files in the CPython Project
      10. Deploying Project to the Python Package Index
      11. Summary
    4. 9. Dynamically Optimizing EC2 Instances on AWS
      1. Running Jobs on AWS
      2. Summary
    5. 10. Real Estate
      1. Exploring Real Estate Values in the United States
      2. Interactive Data Visualization in Python
      3. Clustering on Size Rank and Price
      4. Summary
    6. 11. Production AI for User-Generated Content
      1. The Netflix Prize Wasn’t Implemented in Production
      2. Key Concepts in Recommendation Systems
      3. Using the Surprise Framework in Python
      4. Cloud Solutions to Recommendation Systems
      5. Real-World Production Issues with Recommendations
      6. Cloud NLP and Sentiment Analysis
      7. NLP on Azure
      8. NLP on GCP
      9. Exploring the Entity API
      10. Production Serverless AI Pipeline for NLP on AWS
      11. Summary
  8. A. AI Accelerators
  9. B. Deciding on Cluster Size