Book Image

Effective Amazon Machine Learning

By : Alexis Perrier
Book Image

Effective Amazon Machine Learning

By: Alexis Perrier

Overview of this book

Predictive analytics is a complex domain requiring coding skills, an understanding of the mathematical concepts underpinning machine learning algorithms, and the ability to create compelling data visualizations. Following AWS simplifying Machine learning, this book will help you bring predictive analytics projects to fruition in three easy steps: data preparation, model tuning, and model selection. This book will introduce you to the Amazon Machine Learning platform and will implement core data science concepts such as classification, regression, regularization, overfitting, model selection, and evaluation. Furthermore, you will learn to leverage the Amazon Web Service (AWS) ecosystem for extended access to data sources, implement realtime predictions, and run Amazon Machine Learning projects via the command line and the Python SDK. Towards the end of the book, you will also learn how to apply these services to other problems, such as text mining, and to more complex datasets.

Related Content you might be interested in

Current Title:

Small book image
Effective Amazon Machine Learning
Alexis Perrier
Apr, 2017 | 306 pages
No titles found
Table of Contents (17 chapters)
Title Page
Title Page
Credits
Credits
About the Author
About the Author
About the Reviewer
About the Reviewer
www.PacktPub.com
www.PacktPub.com
Customer Feedback
Customer Feedback
Dedication
Dedication
Preface
Preface
Free Chapter
1
Introduction to Machine Learning and Predictive Analytics
Introduction to Machine Learning and Predictive Analytics
Introducing Amazon Machine Learning
Understanding predictive analytics
Diving further into linear modeling for prediction
Summary
2
Machine Learning Definitions and Concepts
Machine Learning Definitions and Concepts
What's an algorithm? What's a model?
Dealing with messy data
The predictive analytics workflow
Identifying and correcting poor performances
Evaluating the performance of your model
Summary
3
Overview of an Amazon Machine Learning Workflow
Overview of an Amazon Machine Learning Workflow
Opening an Amazon Web Services Account
Setting up the account
Overview of a standard Amazon Machine Learning workflow
Summary
4
Loading and Preparing the Dataset
Loading and Preparing the Dataset
Working with datasets
Preparing the data
Creating the datasource
Examining data statistics 
Feature engineering with Athena
Summary
5
Model Creation
Model Creation
Transforming data with recipes
Creating a model
Creating an evaluation
Analyzing the logs
Summary
6
Predictions and Performances
Predictions and Performances
Making batch predictions
Making real-time predictions
Summary
7
Command Line and SDK
Command Line and SDK
Getting started and setting up
A simple project using the CLI
Boto3, the Python SDK
Summary
8
Creating Datasources from Redshift
Creating Datasources from Redshift
Choosing between RDS and Redshift
Introducing polynomial regression
Polynomial regression in Amazon ML
Summary
9
Building a Streaming Data Analysis Pipeline
Building a Streaming Data Analysis Pipeline
Streaming Twitter sentiment analysis
Going beyond classification and regression
Summary

Summary

In this chapter, we leveraged the power of the AWS ecosystem to build a real-time streaming data classification pipeline. Our pipeline was able to classify streaming tweets using an Amazon ML classification endpoint.  The AWS data ecosystem is diverse and complex, and for a given problem, there are often several possible solutions and architectures. The Kinesis-Lambda-Redshift-MachineLearning architecture we built is simple, yet very powerful. 

The true strength of the Amazon ML service lies in its ease of use and simplicity. Training and evaluating a model from scratch can be done in a few minutes with a few clicks, and it can result in very good performances. Using the AWS CLI and the SDK, more complex data flows and model explorations can easily be implemented. The service is agile enough to become a part of a wider data flow by providing real-time classification and regression. 

Underneath the simple interface, the machine learning expertise of Amazon shines at many levels. From...

Previous Section
End of Chapter 9
Next Chapter