Book Image

AWS Certified Machine Learning Specialty: MLS-C01 Certification Guide

By : Somanath Nanda, Weslley Moura
Book Image

AWS Certified Machine Learning Specialty: MLS-C01 Certification Guide

By: Somanath Nanda, Weslley Moura

Overview of this book

The AWS Certified Machine Learning Specialty exam tests your competency to perform machine learning (ML) on AWS infrastructure. This book covers the entire exam syllabus using practical examples to help you with your real-world machine learning projects on AWS. Starting with an introduction to machine learning on AWS, you'll learn the fundamentals of machine learning and explore important AWS services for artificial intelligence (AI). You'll then see how to prepare data for machine learning and discover a wide variety of techniques for data manipulation and transformation for different types of variables. The book also shows you how to handle missing data and outliers and takes you through various machine learning tasks such as classification, regression, clustering, forecasting, anomaly detection, text mining, and image processing, along with the specific ML algorithms you need to know to pass the exam. Finally, you'll explore model evaluation, optimization, and deployment and get to grips with deploying models in a production environment and monitoring them. By the end of this book, you'll have gained knowledge of the key challenges in machine learning and the solutions that AWS has released for each of them, along with the tools, methods, and techniques commonly used in each domain of AWS ML.
Table of Contents (14 chapters)
Section 1: Introduction to Machine Learning
Section 2: Data Engineering and Exploratory Data Analysis
Section 3: Data Modeling

Storing and transforming real-time data using Kinesis Data Firehose

There are a lot of use cases demanding the data to be streamed and stored for future analytics purposes. To overcome such problems, you can write a kinesis consumer to read the Kinesis stream and store the data in S3. This solution needs an instance or a machine to run the code with the required access to read from the stream and write to S3. The other possible option would be to run a Lambda function that gets triggered on the putRecord or putRecords API made to the stream and reads the data from the stream to store in the S3 bucket:

  • To make this easy, Amazon provides a separate service called Kinesis Data Firehose. This can easily be plugged into a Kinesis data stream and it will require essential IAM roles to write data into S3. This is a fully managed service to reduce the load of managing servers and code. It also supports loading the streamed data into Amazon Redshift, Amazon Elasticsearch Service, and...