Data Wrangling with R

ISBN-13: 9783319455983 / Angielski / Miękka / 2016 / 238 str.

Bradley Boehmke

Opis

This guide for practicing statisticians, data scientists, and R users and programmers will teach the essentials of preprocessing: data leveraging the R programming language to easily and quickly turn noisy data into usable pieces of information. Data wrangling, which is also commonly referred to as data munging, transformation, manipulation, janitor work, etc., can be a painstakingly laborious process. Roughly 80% of data analysis is spent on cleaning and preparing data; however, being a prerequisite to the rest of the data analysis workflow (visualization, analysis, reporting), it is essential that one become fluent and efficient in data wrangling techniques.This book will guide the user through the data wrangling process via a step-by-step tutorial approach and provide a solid foundation for working with data in R. The author's goal is to teach the user how to easily wrangle data in order to spend more time on understanding the content of the data. By the end of the book, the user will have learned:

• How to work with different types of data such as numerics, characters, regular expressions, factors, and dates
• The difference between different data structures and how to create, add additional components to, and subset each data structure
• How to acquire and parse data from locations previously inaccessible
• How to develop functions and use loop control structures to reduce code redundancy
• How to use pipe operators to simplify code and make it more readable
• How to reshape the layout of data and manipulate, summarize, and join data sets

Spis treści

1. Preface

 

2. Introduction 

a. The Role of Data Wrangling 

i. Introduction to R 

1. Open Source 

2. Flexibility 

3. Community 

ii. R Basics 

1. Assignment & Evaluation 

2. Vectorization 

3. Getting help 

4. Workspace 

5. Working with packages 

6. Style guide 

3. Working with Different Types of Data in R 

a. Dealing with Numbers 

i. Integer vs. Double 

 ii. Generating sequence of non-random numbers 

iii. Generating sequence of random numbers 

iv. Setting the seed for reproducible random numbers 

v. Comparing numeric values 

vi. Rounding numbers 

b. Dealing with Character Strings 

i. Character string basics 

ii. String manipulation with base R 

iii. String manipulation with stringr 

iv. Set operatons for character strings 

c. Dealing with Regular Expressions 

i. Regex Syntax 

ii. Regex Functions 

iii. Additional resources 

d. Dealing with Factors 

i. Creating, converting & inspecting factors 

ii. Ordering levels 

iii. Revalue levels 

iv. Dropping levels 

e. Dealing with Dates 

i. Getting current date & time 

 ii. Converting strings to dates 

iii. Extract & manipulate parts of dates 

iv. Creating date sequences 

v. Calculations with dates 

vi. Dealing with time zones & daylight savings 

vii. Additional resources 

<4. Managing Data Structures in R 

a. Data Structure Basics 

i. Identifying the Structure 

ii. Attributes 

 b. Managing Vectors 

i. Creating 

ii. Adding on to 

iii. Adding attributes 

iv. Subsetting 

c. Managing Lists 

i. Creating 

iii. Adding attributes 

iv. Subsetting 

d. Managing Matrices 

i. Creating 

ii. Adding on to 

iii. Adding attributes 

iv. Subsetting 

e. Managing Data Frames 

i. Creating 

ii. Adding on to 

iii. Adding attributes 

iv. Subsetting 

f. Dealing with Missing Values 

i. Testing for missing values 

ii. Recoding missing values  iii. Excluding missing values 

5. Importing, Scraping, and Exporting Data with R 

a. Importing Data 

i. Reading data from text files 

ii. Reading data from Excel files 

iii. Load data from saved R object file 

iv. Additional resources 

b. Scraping Data 

i. Importing tabular and Excel files stored online 

ii. Scraping HTML text 

iii. Scraping HTML table data 

iv. Working with APIs 

v. Additional Resources 

c. Exporting Data 

i. Writing data to text files 

ii. Writing data to Excel files 

iii. Saving data as an R object file 

iv. Additional resources 

6. Creating Efficient & Readable Code in R 

a. Functions 

i. Function Components 

ii. Arguments 

iii. Scoping Rules 

iv. Lazy Evaluation 

v. Returning Multiple Outputs from a Function 

vi. Dealing with Invalid Parameters 

vii. Saving and Sourcing Functions 

viii. Additional Resources 

b. Loop Control Statements 

i. Basic control statements (i.e. if, for, while, etc.) 

ii. Apply family 

iii. Other useful “loop-like” functions 

iv. Additional Resources 

c. Simplify Your Code with %>% 

i. Pipe (%>%) Operator 

ii. Additional Functions 

iii. Additional Pipe Operators 

iv. Additional Resources 

7. Shaping & Transforming Your Data with R 

a. Reshaping Your Data with tidyr 

i. Making wide data long 

ii. Making long data wide  iii. Splitting a single column into multiple columns 

iv. Combining multiple columns into a single column 

v. Additional tidyr functions 

vi. Sequencing your tidyr operations 

vii. Additional resources 

b. Transforming Your Data with dplyr 

i. Selecting variables of interest 

ii. Filtering rows 

iii. Grouping data by categorical variables 

iv. Performing summary statistics on variables 

v. Arranging variables by value 

vi. Joining datasets 

vii. Creating new variables 

viii. Additional resources

O autorze

Brad Boehmke, Ph.D., is an Operations Research Analyst at Headquarters Air Force Materiel Command, Studies and Analyses Division.  He is also Assistant Professor in the Operational Sciences Department at the Air Force Institute of Technology.  Dr. Boehmke's research interests are in the areas of cost analysis, economic modeling, decision analysis, and developing applied modeling applications through the R statistical language.

Blurb

This guide for practicing statisticians, data scientists, and R users and programmers will teach the essentials of preprocessing: data leveraging the R programming language to easily and quickly turn noisy data into usable pieces of information. Data wrangling, which is also commonly referred to as data munging, transformation, manipulation, janitor work, etc., can be a painstakingly laborious process. Roughly 80% of data analysis is spent on cleaning and preparing data; however, being a prerequisite to the rest of the data analysis workflow (visualization, analysis, reporting), it is essential that one become fluent and efficient in data wrangling techniques.

This book will guide the user through the data wrangling process via a step-by-step tutorial approach and provide a solid foundation working with data in R. The author's goal is to teach the user how to easily wrangle data in order to spend more time on understanding the content of the data. By the end of the book, the user will have learned: 

• How to work with different types of data such as numerics, characters, regular expressions, factors, and dates
• The difference between different data structures and how to create, add additional components to, and subset each data structure
• How to acquire and parse data from locations previously inaccessible
• How to develop functions and use loop control structures to reduce code redundancy
• How to use pipe operators to simplify code and make it more readable
• How to reshape the layout of data and manipulate, summarize, and join data sets
  

In essence, the user will have the data wrangling toolbox required for modern day data analysis.

Brad Boehmke, Ph.D., is an Operations Research Analyst at Headquarters Air Force Materiel Command, Studies and Analyses Division. He is also Assistant Professor in the Operational Sciences Department at the Air Force Institute of Technology. Dr. Boehmke's research interests are in the areas of cost analysis, economic modeling, decision analysis, and developing applied modeling applications through the R statistical language.