Data visualization exists to help us learn things from, and about, data. It helps us answer questions like these: What are the trends in the data? What data is most common and most unusual? What information is important and what’s not? Appropriately, this week’s Data Driven Digest is all about learning: Learning about words, learning about complex concepts, and learning about education. We can all take a lesson or two from these three great examples. Warning: We get a little geeky this week.
Word Nerds: We love data visualizations that analyze words, and a fabulous example appeared this week. The mysteriously named Abacaba has created the beautiful, almost hypnotic video above to visualize word frequency in written English. The video is based on the work of Peter Norvig, director of research at Google; Norvig analyzed the entire contents of Google Books, finding 97,565 words, used 743,842,922,321 times. His paper on the project, English Letter Frequency Counts: Mayzner Revisited or ETAOIN SRHLDCU, is charmingly written and great reading. Abacaba has two similarly wonderful videos on a YouTube channel.
Know the Code: Do you want to understand machine learning, but don’t know where to start? You can’t do better than R2D3.us, where you’ll find A Visual Introduction to Machine Learning. We love everything about this site: Its fluid, data-driven storytelling; its clear, interactive data visualizations (a static snippet of which is above, but click through for the full, animated experience); even its clever pun name. (Its creators are Stephanie Yee, who interprets R2, and Tony Chu, who visualizes data with D3; both work at Sift Science.) We can’t wait for the next post.
School’s In: Thinking about pursuing a degree in data science? Ryan Swanstrom recently compiled a huge list of academic programs globally, and Alex Salkever used Swanstrom’s data to build an interactive site (on Silk.co) that makes the data fun and easy to explore. Salkever wrote about his project on KD Nuggets, noting “While data science is probably closer to computer science than anything, business schools offer more programs than any other department type.” If you’re not ready to go back to school, another place to start is our blog post, 7 Free or Cheap Ways to Learn Data Science.
Like what you see? Every Friday we share great data visualizations and embedded analytics. If you have a favorite or trending example, tell us: Submit ideas to blogactuate@actuate.com or add a comment below. Subscribe (at left) and we’ll email you when new entries are posted.
Recent Data Driven Digests:
July 17: Streaming video, data science at Netflix, TV ratings visualized
July 10: NYSE freeze, market complexity, China’s stock market