Data Science for Business With R

by Jeffrey S. Saltz, Jeffrey Morgan Stanton

Overview

Data Science for Business with R, written by Jeffrey S. Saltz and Jeffrey M. Stanton, focuses on the concepts foundational for students starting a business analytics or data science degree program. To keep the book practical and applied, the authors feature a running case using a global airline business’s customer survey dataset to illustrate how to turn data in business decisions, in addition to numerous examples throughout. To aid in usability beyond the classroom, the text features full integration of freely-available R and RStudio software, one of the most popular data science tools available.

Designed for students with little to no experience in related areas like computer science, the book chapters follow a logical order from introduction and installation of R and RStudio, working with data architecture, undertaking data collection, performing data analysis, and transitioning to data archiving and presentation. Each chapter follows a familiar structure, starting with learning objectives and background, following the basic steps of functions alongside simple examples, applying these functions to the case study, and ending with chapter challenge questions, sources, and a list of R functions so students know what to expect in each step of their data science course. Data Science for Business with R provides readers with a straightforward and applied guide to this new and evolving field.

Product Details

ISBN-13:	9781544370453
Publisher:	SAGE Publications
Publication date:	03/03/2021
Pages:	424
Product dimensions:	7.38(w) x 9.12(h) x (d)

About the Author

Jeffrey S. Saltz is an Associate Professor at Syracuse University in the School of Information Studies and Director of the school's Master's of Science program in Applied Data Science. His research and teaching focus on helping organizations leverage information technology and data for competitive advantage. Specifically, his current research focuses on the socio-technical aspects of data science projects, such as how to coordinate and manage data science teams. In order to stay connected to the “real world”, Dr. Saltz consults with clients ranging from professional football teams to Fortune 500 organizations. Prior to becoming a professor, Dr. Saltz's two decades of industry experience focused on leveraging emerging technologies and data analytics to deliver innovative business solutions. In his last corporate role, at JPMorgan Chase, he reported to the firm's Chief Information Officer and drove technology innovation across the organization. Jeff also held several other key technology management positions at the company, including CTO and Chief Information Architect. He also served as Chief Technology Officer and Principal Investor at Goldman Sachs, where he helped incubate technology start-ups. He started his career as a programmer, project leader and consulting engineer with Digital Equipment Corp. Dr. Saltz holds a B.S. degree in computer science from Cornell University, an M.B.A. from The Wharton School at the University of Pennsylvania, and a Ph D in Information Systems from the New Jersey Institute of Technology.

Jeffrey M. Stanton, Ph.D. is a Professor at Syracuse University in the School of Information Studies. Dr. Stanton’s research focuses on the impacts of machine learning on organizations and individuals. He is the author of Reasoning with Data (2017), an introductory statistics textbook. Stanton has also published many scholarly articles in peer-reviewed behavioral science journals, such as the Journal of Applied Psychology, Personnel Psychology, and Human Performance. His articles also appear in Journal of Computational Science Education, Computers and Security, Communications of the ACM, Computers in Human Behavior, the International Journal of Human-Computer Interaction, Information Technology and People, the Journal of Information Systems Education, the Journal of Digital Information, Surveillance and Society, and Behaviour & Information Technology. He also has published numerous book chapters on data science, privacy, research methods, and program evaluation. Dr. Stanton's research has been supported through 19 grants and supplements including the National Science Foundation’s CAREER award. Before getting his Ph D, Stanton was a software developer who worked at startup companies in the publishing and professional audio industries. He holds a bachelor's degree in Computer Science from Dartmouth College, and a master's and Ph.D. in Psychology from the University of Connecticut.

Table of Contents

Instructor Preface xiii

Teaching Resources xv

Introduction: Data Science, Many Skills xvii

What Is Data Science? xviii

The Steps in Doing Data Science xix

The Skills Needed to Do Data Science xx

Identifying Data Problems xxii

Additional Introductory Thoughts xxv

Case Study Overview: Customer Churn in the Airline Industry xxvii

Net Promoter Score xxviii

Southeast and Us Regional Airline Partners xxviii

The Data Available xxix

Attribute Names xxix

Chapter Challenges xxxii

Sources xxxii

Chapter 1 Begin at the Beginning With R 1

Installing R 3

Using R 4

Creating and Using Vectors 5

Subsetting Vectors 8

The Command Console 10

Using an Integrated Development Environment 11

Installing R Studio 12

Creating R Scripts 13

Case Study: Calculating NPS 17

Chapter Challenges 19

Sources 19

R Functions Used in This Chapter 19

Chapter 2 Rows and Columns 21

Creating Dataframes 24

Exploring Dataframes 27

Accessing Columns in a Dataframe 31

Case Study: Calculating NPS Using a Dataframe 34

Chapter Challenges 37

Sources 37

R Functions Used in This Chapter 38

Chapter 3 Data Munging 39

Reading a CSV Text File 40

Removing Rows and Columns 44

Renaming Rows and Columns 46

Cleaning up the Elements 47

Sorting and Subsetting Dataframes 49

Tidy verse: An Introduction and How to Install the Package 51

Sorting and Subsetting Dataframes Using Tidyverse 53

Case Study: Reading, Cleaning, and Exploring a Survey Dataset 55

Chapter Challenges 59

Sources 60

R Functions Used in This Chapter 60

Chapter 4 What's My Function? 61

Why Create and Use Functions? 62

Creating Functions in R 63

Defensive Coding 68

Installing a Package to Access a Function 70

Case Study: Creating and Using a Calculate NPS Function 72

Chapter Challenges 76

Sources 76

R Functions Used in This Chapter 77

Chapter 5 Beer, Farms, Peas, and the Use of Statistics 79

Historical Perspective 80

Sampling a Population 82

Understanding Descriptive Statistics 82

Using Descriptive Statistics 84

Using Histograms to Understand a Distribution 88

Normal Distributions 91

Case Study: Exploring LTR Distributions 92

Chapter Challenges 95

Sources 95

R Functions Used in This Chapter 96

Chapter 6 Sample in a Jar 97

Sampling in R 100

Repeating our Sampling 101

Law of Large Numbers and the Central Limit Theorem 103

Comparing Two Samples 107

Case Study: Analyzing the Impact of a New Treatment 112

Chapter Challenges 116

Sources 116

R Functions Used in This Chapter 117

Chapter 7 Storage Wars 119

Importing Data Using RStudio 121

Accessing Excel Data 124

Working with Data From External Databases 129

Accessing a Database 130

Comparing SQL and R/Tidyverse for Accessing a Dataset 135

Accessing JSON Data 139

Case Study: Reading, Cleaning, and Exploring a Survey Dataset 145

Chapter Challenges 150

Sources 151

R Functions Used in This Chapter 151

Chapter 8 Pictures Versus Numbers 153

A Visualization Overview 155

Basic Plots in R 157

Using the ggplot2 Package 158

More-Advanced Visualizations 166

Case Study: Visualizing Key Attributes Related to NPS 171

Chapter Challenges 179

Sources 179

R Functions Used in This Chapter 180

Chapter 9 Map Mashup 181

Creating Map Visualizations With ggplot2 183

Showing Points on a Map 192

Zooming Into a Subset of a Map 198

Case Study: Explore NPS by State and City 200

Chapter Challenges 204

Sources 204

R Functions Used in This Chapter 205

Chapter 10 Lining Up Our Models 207

What is a Model? 208

Supervised and Unsupervised Machine Learning 208

Linear Modeling 210

An Example-Car Maintenance 212

Using the Caret Package 221

Partitioning into Training and Cross Validation Datasets 223

Using k-fold Cross Validation 228

Case Study: Building a Linear Model Using Survey Data 231

Chapter Challenges 236

Sources 236

R Functions Used in This Chapter 237

Chapter 11 What's Your Vector, Victor? 239

More Supervised Learning 240

A Classification Example 240

Supervised Learning via Support Vector Machines 247

Support Vector Machines in R 250

Supervised Learning via Classification and Regression Trees 261

Case Study: Building Supervised Models From the Survey 266

Chapter Challenges 274

Sources 274

R Functions Used in This Chapter 275

Chapter 12 Hi No, Hi Ho-Data Mining We Go 277

Data Mining Processes 279

Association Rules Data 280

Association Rules Mining 281

Exploring How the Association Rules Algorithm Works 287

Building Association Rules in R 288

Case Study: Exploring Association Rules Within the Survey 295

Chapter Challenges 300

Sources 301

R Functions Used in This Chapter 301

Chapter 13 Word Perfect (Text Mining) 303

Reading-In Text Files 305

Creating Word Clouds Using the Quanteda Package 307

Exploring the Text via Sentiment Analysis 311

Topic Modeling 314

Other Uses of Text Mining 318

Case Study: Connecting Topics to NPS 319

Chapter Challenges 332

Sources 332

R Functions Used in This Chapter 333

Chapter 14 Shiny® Web Apps 335

Creating Web Applications in R 336

Deploying the Application 341

Case Study: Visualizing NPS by Key Attributes 347

Chapter Challenges 351

Sources 351

R Functions Used in This Chapter 351

Chapter 15 Time for a Deep Dive 353

The Impact of Deep Learning 354

Deep Learning Is Supervised Learning 355

How Does Deep Learning Work? 356

Deep Learning in R-An Example 358

Deep Learning in R-An Image Analysis Example 365

Deep Learning in R-Using a Prebuilt Model 374

Case Study: Building Neural Networks From the Survey 378

Chapter Challenges 381

Sources 382

R Functions Used in This Chapter 383

Index 385