Amazon Machine Learning
Amazon Machine Learning
An Introduction
About the Book
Would you like to perform machine learning without setting up any infrastructure? Amazon Machine Learning (AML) lets you do supervised learning against datasets in S3, RDS and Redshift and build models that can be accessed via realtime or batch predictions. In this book I'll cover how to get your data up to Amazon, how to build your model and how to use your model. We'll also cover areas where AML might not be a good fit, and how to access your model via the API.
About the Author
Table of Contents
- Introduction
-
What is Machine Learning
- Common Issues
- Why It Matters
-
What is Amazon Machine Learning
- Key Elements
- Interface
- Regional Availability And Data Sources
- Support
- AML concepts
-
Types of Data Sources
- S3
- Redshift
- RDS
- External data
- Conclusion
-
Loading Your Data
- Real data
- Prepping Your Data
- IAM roles
- Uploading Your Data To S3
- Creating the Data Source
- Statistics
- Failure
-
Data Nuts and Bolts
- Excluded Attributes
- Known Data Types
- Missing values
- Data type differences
- Row Identifiers
- Statistics
-
Data considerations
- How much data makes sense
- Protecting your data
- Server Side Encryption
- Transformations Before You Create a Data Source
- Anonymize your data
-
Initial Model Build
- Building from the console
- Custom Settings
- Experiment
-
More About Your Model
- Shuffling
- Using recipes to modify the data your model sees
- Transformations available
- Example Recipe
- Which recipe should you use
-
Batch vs real time predictions
- How to decide
- Batch
- Real-time
- Pick based on use case
-
More About Batch Predictions
- Location of observations
- Kicking off a batch prediction
- How do you know when you’re done
- Results
- More About Real Time Predictions
-
Why Manage Your Models
- Creating and Comparing Models With the Same Data Schema
- Creating and Comparing Models With Different Schemas
- Combining Model Results
- Managing Via the API
- Creating models via the API
- Other Use Cases
-
Limits of AML
- Read only models
- Only structured text data
- No model insight
- Number of features
- Category cardinality
- Limited configurability
- No model export
- Server side encrypted data
- Ill Fitting Use Cases
- Alternatives
- Conclusion
The Leanpub 60 Day 100% Happiness Guarantee
Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.
Now, this is technically risky for us, since you'll have the book or course files either way. But we're so confident in our products and services, and in our authors and readers, that we're happy to offer a full money back guarantee for everything we sell.
You can only find out how good something is by trying it, and because of our 100% money back guarantee there's literally no risk to do so!
So, there's no reason not to click the Add to Cart button, is there?
See full terms...
80% Royalties. Earn $16 on a $20 book.
We pay 80% royalties. That's not a typo: you earn $16 on a $20 sale. If we sell 5000 non-refunded copies of your book or course for $20, you'll earn $80,000.
(Yes, some authors have already earned much more than that on Leanpub.)
In fact, authors have earnedover $13 millionwriting, publishing and selling on Leanpub.
Learn more about writing on Leanpub
Free Updates. DRM Free.
If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).
Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.
Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.
Learn more about Leanpub's ebook formats and where to read them
