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
Author(s): Noah Gift
Series: Addison Wesley Data & Analytics
Edition: 1
Publisher: Addison-Wesley Professional
Year: 2018
Language: English
Commentary: Vector PDF
Pages: 272
City: Upper Saddle River, NJ
Tags: DevOps; Google Cloud Platform; Amazon Web Services; Cloud Computing; Command Line; Machine Learning; To Read; Natural Language Processing; Unsupervised Learning; Programming; Python; Slack; Pipelines; Docker; Excel; scikit-learn; Flask; Web Scraping; NumPy; pandas; Social Media; Jupyter; iPython; AWS Lambda; AWS Batch; AWS SageMaker; AWS Elastic Compute Cloud; Elementary
Cover
Half Title
Title Page
Copyright Page
Dedication
Contents
Preface
Acknowledgments
About the Author
I: Introduction to Pragmatic AI
1 Introduction to Pragmatic AI
Functional Introduction to Python
Procedural Statements
Printing
Create Variable and Use Variable
Multiple Procedural Statements
Adding Numbers
Adding Phrases
Complex Statements
Strings and String Formatting
Adding and Subtracting Numbers
Multiplication with Decimals
Using Exponents
Converting Between Different Numerical Types
Rounding Numbers
Data Structures
Dictionaries
Lists
Functions
Using Control Structures in Python
for Loops
While Loops
If/Else
Intermediate Topics
Final Thoughts
2 AI and ML Toolchain
Python Data Science Ecosystem: IPython, Pandas, NumPy, Jupyter Notebook, Sklearn
R, RStudio, Shiny, and ggplot
Spreadsheets: Excel and Google Sheets
Cloud AI Development with Amazon Web Services
DevOps on AWS
Continuous Delivery
Creating a Software Development Environment for AWS
Integrating Jupyter Notebook
Integrating Command-Line Tools
Integrating AWS CodePipeline
Basic Docker Setup for Data Science
Other Build Servers: Jenkins, CircleCI, and Travis
Summary
3 Spartan AI Lifecycle
Pragmatic Production Feedback Loop
AWS SageMaker
AWS Glue Feedback Loop
AWS Batch
Docker-based Feedback Loops
Summary
II: AI in the Cloud
4 Cloud AI Development with Google Cloud Platform
GCP Overview
Colaboratory
Datalab
Extending Datalab with Docker and Google Container Registry
Launching Powerful Machines with Datalab
BigQuery
Moving Data into BigQuery from the Command Line
Google Cloud AI Services
Classifying my Crossbreed Dog with the Google Vision API
Cloud TPU and TensorFlow
Running MNIST on Cloud TPUs
Summary
5 Cloud AI Development with Amazon Web Services
Building Augmented Reality and Virtual Reality Solutions on AWS
Computer Vision: AR/VR Pipelines with EFS and Flask
Data Engineering Pipeline with EFS, Flask, and Pandas
Summary
III: Creating Practical AI Applications from Scratch
6 Predicting Social-Media Influence in the NBA
Phrasing the Problem
Gathering the Data
Collecting Challenging Data Sources
Collecting Wikipedia Pageviews for Athletes
Collecting Twitter Engagement for Athletes
Exploring NBA Athlete Data
Unsupervised Machine Learning on NBA Players
Faceting Cluster Plotting in R on NBA Players
Putting it All Together: Teams, Players, Power, and Endorsements
Further Pragmatic Steps and Learnings
Summary
7 Creating an Intelligent Slackbot on AWS
Creating a Bot
Converting the Library into a Command-Line Tool
Taking the Bot to the Next Level with AWS Step Functions
Getting IAM Credentials Set Up
Working with Chalice
Building Out the Step Function
Summary
8 Finding Project Management Insights from a GitHub Organization
Overview of the Problems in Software Project Management
Exploratory Questions to Consider
Creating an Initial Data Science Project Skeleton
Collecting and Transforming the Data
Talking to an Entire GitHub Organization
Creating Domain-specific Stats
Wiring a Data Science Project into a CLI
Using Jupyter Notebook to Explore a GitHub Organization
Pallets GitHub Project
Looking at File Metadata in the CPython Project
Looking at Deleted Files in the CPython Project
Deploying a Project to the Python Package Index
Summary
9 Dynamically Optimizing EC2 Instances on AWS
Running Jobs on AWS
Spot Instances
Summary
10 Real Estate
Exploring Real Estate Values in the United States
Interactive Data Visualization in Python
Clustering on Size Rank and Price
Summary
11 Production AI for User-Generated Content
The Netflix Prize Wasn’t Implemented in Production
Key Concepts in Recommendation Systems
Using the Surprise Framework in Python
Cloud Solutions to Recommendation Systems
Real-World Production Issues with Recommendations
Real-World Recommendation Problems: Integration with Production APIs
Cloud NLP and Sentiment Analysis
NLP on Azure
NLP on GCP
Exploring the Entity API
Production Serverless AI Pipeline for NLP on AWS
Summary
A: AI Accelerators
B: Deciding on Cluster Size
Index
