My data science journey started with the interest of learning different data visualization techniques. From the start of my career I had an influence of Concept Visualization. In the recent times, I even experimented Infographics into my resume. If you search on visualization on internet there will be plenty of resources around information graphics, presentations etc. I never thought there will be a book primarily on data visualization techniques (and not on the tools for graphics visualization). I picked this book from my library the moment I saw statistics in tagline. After reading I totally agree that it really is a guide as it states.
- Chapter 1 : Telling Stories with Data – It’s an age old saying that storytelling is an art. Time and again, It’s used by several successful people in the world to express their vision in front of the world, be it social, political or business discussions. On other side data is not new, it’s been there even before computing evolved. With the growth of data, drawing insights, making decisions & conveying discussions to stakeholders will continue to become complex. To make it simple you need to present in visually impressive mode & to the point by keeping less decoding for receivers of the data. This chapters explains precisely the same in a very short & simple language.
- Chapter 2 : Handling Data – The core is data so you need to understand how to gather it, where to look for sources, what if you have unstructured data, how will you get it in your hand with meaningful format/schema. This chapter gives you very good understanding about it. Going beyond, with a hands-on data scrapping exercise it will make sure you get familiar with real world data scattered over multiple web pages/sources into one file for analysis.
- Chapter 3 : Choosing Tools to Visualize – As the title suggest it’s about choosing visualization methods on given data. It covers variety of tools from Out-Of-the box commercial tools to scripting & programming options. The amount references given and supported by hands on exercise is the most important part for me. It’s very easy to refer something and drop the topic from high level. But making reading try some of it always makes him/her connect with the book.
- Chapter 4 : Visualizing Patterns over, Chapter 5 : Visualizing Proportions, Chapter 6 : Visualizing Relationships, Chapter 7 : Spotting Differences and Chapter 8 : Visualizing Spatial are at the heart of the book. With the hands on exercise in each chapter its explains how different type of objectives can be met on variety of dataset available for visualization. There many relevant examples shared in these chapters along with the instructions which you can try on your machine.
- Chapter 9 : Designing with a Purpose – The wrap up chapter nicely explains how the acquired knowledge can be enhanced. Like any communication it’s not just your views/words, it’s also about the recipients requirements, understanding of the topics, awareness of related contexts & most importantly interest in relating with your views and words. Preparing yourself to handle such things will make you not just better but a meaningful in data visualization.
So how did this book help me !!!
- First & super importantly it corrected my knowledge about the visualization. My knowledge was only limited to graphs & charts. It lifted me from there to basics plots to visualizing a data on to the maps. Yes by the end of the book, I was able to draw India map and do some sample analysis. I will post the learning in upcoming blog posts.
- It helped me learn Python & R. At the beginning of the book I was struggling to write python code. Because of the book I pushed myself to learn it well. To my surprise I wrote my own python code for data mining. The data mining part is completed but I am still working on analyzing and visualizing in R. Once completed, I will try to put a blog post about the experience.
- Sometime last year, I had taken a free course on R from online learning portals. This book just took me on to new levels for using R and I thoroughly enjoyed it. The book is full of R examples which will make you comfortable using the tool.
- I had an opportunity to try hands-on tools like Adobe Illustrator and Tableau. As I had to rely on trial version it was limited but good enough to get the basic context.
- The book has ~125 website references. I went through all of them reading at least the page referenced and what it had to explain in the context. About 80% of these were new websites for me, so you can imagine new learning I must have had through these references. Some of the references are about popular data sources/topics like world population, education & crime rates analysis in USA, Obama’s presidential run and analysis on debate topics, NBA games & player analysis etc. While others are around popular web sites for data science, blogs, tools, communities etc.
- I took a reading pause on this book as I was reading another on “How to become data scientist“. Looking back it nicely complemented my data science study. Most important “Visualize This” helped me get more serious & focused about data science.
So to conclude, this book not only helped me learn Data Visualization. This became catalyst in my data science study, it’s the prime motivator behind my Python & R learning, and will remain guide in my future data visualization assignments. Thanks Nathan Yau for writing this wonderful guide.
Lastly, stay tuned for my upcoming blog posts on learning used by me outside the datasets from this book.