R for Data Science: Import, Tidy, Transform, Visualize, and Model Data

As a beginner to R, I bought this book at the recommendation from Data Science for Fundraising: Build Data-Driven Solutions Using R and am so glad that I did. R4DS provides useful content to get started with R. The book consists of 5 main sections: 1. Getting started (Explore) 2. Data manipulation (Wrangle) 3. Scripting (Program) 4. Build models 5. Presenting information (Communicate) Here’s a brief overview of each section: Explore I was a bit puzzled as the book jumps directly into plotting using the ggplot library. Although the authors are clear that the purpose of introducing ggplot is to keep our motivation high, seeing the ggplot syntax without a whole lot of background can be confusing at first. But then the authors do a great job at explaining the various aspects of ggplot. So my advice to other R beginners is to just keep going forward! After the intro to ggplot, you learn about the basics of R, such as variables and functions, as well as intermediate topics such as writing scripts, manipulating data using dplyr, and lastly EDA. This section ends with a good overview of how to use RStudio to saves script files. Wrangle This section starts with an intro to tibbles, which is a new concept for handling data in R. This section is important since most of the functions in later chapters use tibbles, such as reading data from various sources. There are many important concepts that seem useful such as “tidying up” your data and cleaning data points (string and dates). Program This is a function section that introduces data pipes. This section explores how to chain complicated data operations together. You also get to see some good practice in writing human readable code. Then the book jumps into using the power of R as a functional programming language. Once I feel more proficient, I will take a deeper look at purr. Model Now, depending on your situation, you may not be interested in this section, which is focuses on predictive modeling. There are quite a few recipes that explore “why” questions. Definitely planning to come back to this chapter later. Communicate This section is useful because it introduces how to create reusablereports. Overall, this is my go-to book along with the book I previously mentioned. This book is a solid reference book for learning R. Another good thing is that the companion website is regularly updated and you can copy and paste the code examples directly into RStudio. I’m looking forward to further exploring R and learning how to create my own data visualizations.

Wickham and Grolemund have produced an excellent book that would help a beginning R user become very efficient in explanatory analysis. Unsurprisingly the approach that they expound utilises the "hadleyverse" a collection of packages (ggplot2 for visualisation, tidyr for reshaping, dplyr for selecting and filtering, purrr for functional programming, broom for linear models etc) that dramatically speed up most of the common steps involved in an analysis. One benefit of Wickham's involvement in these packages has been a coherent philosophy that sits behind them. It can be a little tricky when learning this philosophy, but the long term benefits are enormous. The book is broken up into a number of sections that effectively builds up the ability to ingest, transform, visualise and model datasets. A good portion of the book is available in an online version, to give you a taste of how it is written. Many have been following it as it was written. I have passed on copies of the book to a number of colleagues who were just starting out and the response has been uniformly positive. In my own case I was familiar with some of the these packages; ggplot2, dplyr, tidyr, but found the book taught me purrr and how to better use the packages together. Probably my two biggest caveats to readers are that there are situations where packages from outside the "hadleyverse" maybe required. The authors do a great job of pointing this out, but it does pay in my experience to know data.table and lattice for example. Both because they can occasionally fit a problem better but also because you inevitably come across other people's code where these packages are used. The other caveat is that the modelling is a little rudimentary. Most of the examples are just fitting independent regression models, whereas it seems to me that a hierarchical model would be a better fit. Still these are small things and it would be silly to expect a single book to cover all of these areas. In short this is the book I would give to someone who was keen to learn about how to use R for data science. It reads really well building up the different components whilst still being a valuable reference if you just need a reminder of a particular package (what is the difference between tibbles and data frames again?). Even though a good portion of the book is available online, it is well worth it to have the full thing on your bookshelf (digital or otherwise). On a broader note with Max Kuhn (author of the excellent "Applied Predictive Modelling" with Kjell Johnson) joining Wickham and Grolemund at RStudio, it is a great time to start your R journey.

I am very happy with this book. Its easy to read and the exercises/code work and are applicable. The text is clearly written and the supporting graphics are well constructed. I have started working through some of the exercises in R and find them very helpful. I bought this book after completing a graduate course in data analysis using R. Much of the course was constructed around Hadley Wickham's work. We used ggplot2 and tidyverse extensively. We did not use this book in the course and I now wish we had used it as a desk reference. This book is answering many of the questions I had. It is also providing an overview of many basic concepts and tools in R and would have been helpful to have at my fingertips during my graduate course. Google is a great resource, but a well written and easily sourced desktop resource like this is indispensable. I am learning something new about R constantly...I would consider myself a late beginner to early intermediate user of R for data science/data analysis. I often find books that cover the basics extremely useful, because its easy to forget. So for me, this was a good buy - regardless of my skill level. Others will have to make their own decision. This book does not cover mapping in R. In fact, there is a sentence in Chapter 1 that states - this book does not cover mapping. I would like to have had more on that topic or a follow-up book committed to mapping and integration with other tools like Leaflet or ArcGIS.

できるだけR-studioとHadleyに依存しないように、base Rだけで、と考えてきました。これを読んで、そんな考えを改めました。素晴らしく操作性が向上するパッケージとそれらの使い方の解説、文章も素晴らしく、平易です。時々、ハッとする引用があります「全てのモデルは正しくない、けど中には有用なものがある」など。http://r4ds.had.co.nzで無料で読めますが、印刷物を購入しました。

The book is intended for a reader, that is not experienced in data science. As an experienced data scientist, that just needed to learn R syntax better, the book was unnecessarily verbose for me and sometimes it was really painful to read many pages explaining obvious. Nevertheless it was a well spend time, because: - There is usually more than one way to do given task in R. The book describes packages/commands that are generally considered to be the best/standard procedures. - The book describes best practices (coding style etc.) that are really beneficial. - The print quality is very high (nice paper, colorful graphs and even frequent code snippets are printed with colorful syntax highlighting).

Although my apprenticeship has free on-line books I like a physical book so you can flip back and fore. It is important you practice with R Studio but this book is well written and a pleasant read. Please note there is a new edition August 2023 so it might be worth waiting.

No cabe duda de que Hadley Wickham es el rey del rock en lo que a R y RStudio se refiere, de modo que estamos de suerte al poder estudiar un libro coescrito por él y Garrett Grolemund en que se nos pone al corriente sobre una nueva forma de escribir código en R basada en la suite tidyverse, un súper-paquete formado por otros paquetes, de entre los cuales destaca, como la joya de la corona, ggplot2 para dibujar gráficos de alta calidad. Además, nuestra suerte se multiplica al saber que Wickham y Grolemund han tenido el detallazo de permitir el acceso gratuito en la Web a su libro (en PDF) y al código que lo acompaña. De modo que el que quiera puede leer el Nuevo Testamento del programa R sin gastarse un duro. El Antiguo Testamento, la forma tradicional de programar en R, sigue vigente, desde luego, para quien así lo desee, pero no está de más conocer la buena nueva que nos traen Wickham y Grolemund porque indiscutiblemente mejora algunos aspectos del software R. Debe quedar claro que éste no es un libro para aprender estadística con R (sólo en el apartado 4, dedicado a la modelización, hay un tenue contacto con la estadística, pero sólo se araña la superficie del asunto), sino más bien un libro para familiarizarse con el manejo de R de una forma mejorada. La obra de Wickham y Grolemund tiene por objeto enseñarnos a importar datos, ordenarlos, entenderlos (mediante modelización, transformación y visualización) y comunicar los resultados. Pero los autores no tienen un pelo de tontos y comienzan y acaban el texto con las partes más entretenidas de este proceso: la visualización (con ggplot2) y la comunicación (mediante R Markdown). Dejando las regiones más áridas entremedias. Confieso, a este respecto, que me ha resultado especialmente aburrido el tratamiento de las fechas con el paquete lubridate, escrito por Grolemund. En fin, un libro de lectura indispensable para quien quiera manejar R con solidez pero no igual de ameno en todo su recorrido.

O livro é excelente. Com uma abordagem aplicada e bem didática, os autores apresentam o universo do tidyverse de forma bastante descomplicada. O tidyverse, por sua vez, é um pacote de ferramentas incríveis, que nos possibilitam fazer muito do trabalho de um cientista de dados com poucas linhas de código e de forma bastante intuitiva. Ao final de cada capítulo há uma lista de exercícios para testar os conhecimentos adquiridos, embora o nível de dificuldade exija do leitor algum conhecimento prévio (básico) de programação em R (e, sobretudo, de lógica de programação). Super recomendo a compra!