Book Overview & Buying
Table Of Contents

Mastering Machine Learning with Spark 2.x

By : Malohlava, Tellez, Max Pumperla

5 (1)

Buy this Book

Mastering Machine Learning with Spark 2.x

5 (1)

By: Malohlava, Tellez, Max Pumperla

Buy this Book

Overview of this book

The purpose of machine learning is to build systems that learn from data. Being able to understand trends and patterns in complex data is critical to success; it is one of the key strategies to unlock growth in the challenging contemporary marketplace today. With the meteoric rise of machine learning, developers are now keen on finding out how can they make their Spark applications smarter. This book gives you access to transform data into actionable knowledge. The book commences by defining machine learning primitives by the MLlib and H2O libraries. You will learn how to use Binary classification to detect the Higgs Boson particle in the huge amount of data produced by CERN particle collider and classify daily health activities using ensemble Methods for Multi-Class Classification. Next, you will solve a typical regression problem involving flight delay predictions and write sophisticated Spark pipelines. You will analyze Twitter data with help of the doc2vec algorithm and K-means clustering. Finally, you will build different pattern mining models using MLlib, perform complex manipulation of DataFrames using Spark and Spark SQL, and deploy your app in a Spark streaming environment.

Preface

What this book covers

What you need for this book

Who this book is for

Conventions

Reader feedback

Customer support

Free Chapter

Introduction to Large-Scale Machine Learning and Spark

Data science

The sexiest role of the 21st century – data scientist?

Introducing H2O.ai

What's the difference between H2O and Spark's MLlib?

Data munging

Data science - an iterative process

Summary

Detecting Dark Matter - The Higgs-Boson Particle

Type I versus type II error

Spark start and data load

Summary

Ensemble Methods for Multi-Class Classification

Data

Modeling goal

Summary

Predicting Movie Reviews Using NLP and Spark Streaming

NLP - a brief primer

The dataset

Feature extraction

Featurization - feature hashing

Let's do some (model) training!

Super learner

Summary

Word2vec for Prediction and Clustering

Motivation of word vectors

Word2vec explained

Doc2vec explained

Applying word2vec and exploring our data with vectors

Creating document vectors

Supervised learning task

Summary

Extracting Patterns from Clickstream Data

Frequent pattern mining

Pattern mining with Spark MLlib

Deploying a pattern mining application

Summary

Graph Analytics with GraphX

Basic graph theory

GraphX distributed graph processing engine

Graph algorithms and applications

Summary

Lending Club Loan Prediction

Motivation

Preparation of the environment

Data load

Exploration – data analysis

Summary

Data load

As usual, the first step involves the loading of data into memory. At this point, we can decide to use Spark or H2O data-loading capabilities. Since data is stored in the CSV file format, we will use the H2O parser to give us a quick visual insight into the data:

val DATASET_DIR = s"${sys.env.get("DATADIR").getOrElse("data")}"
val DATASETS = Array("LoanStats3a.CSV", "LoanStats3b.CSV")
import java.net.URI

import water.fvec.H2OFrame
val loanDataHf = new H2OFrame(DATASETS.map(name => URI.create(s"${DATASET_DIR}/${name}")):_*)

The loaded dataset can be directly explored in the H2O Flow UI. We can directly verify the number of rows, columns, and size of data stored in memory: