An Introduction to Statistical Learning, with Applications in R by Gareth James, Daniela Witten, Trevor Hastie, and Rob Tibshirani was released in 2021. They, along with Jonathan Taylor, just released an alternate version with applications in Python. So if Python is your thing, have at it. Like the R version, it is free to download as a PDF.

This might surprise you, but the grass at the Wimbledon tennis tournament is not the same as the grass in people’s backyards. It has to stay short so that tennis balls maintain speed and bounce and strong enough to hold up to professional tennis play. For Reuters, Travis Hartman and Ally J. Levine illustrate the differences between court surfaces and how grass impacts play.

I’m into the tennis textures used throughout the piece.

For NYT Opinion, Richard Arum and Mitchell L. Stevens, with graphics by Quoctrung Bui, turn their attention to the four-year colleges that accept most applicants, which is most schools:

While the Supreme Court’s decision is a blow to Black and Hispanic students who dream of attending the most competitive universities, improving and better supporting the institutions that serve the lion’s share of students of color will do far more to advance the cause of racial equality in this country than anything that admissions officers can do in Cambridge, Palo Alto and Chapel Hill.

The selective schools get all the attention, but there are a surprising percentage of programs that accept just about everyone. The beeswarm bubbles fill to the edge of the screen to highlight the point.

There are many tools, which makes it tempting to learn them all. Instead, learn one tool really well and the logic carries over to the others.

The Washington Post provides an introduction to fonts with mini-quizzes and straightforward examples. You can also change the font of the article:

You make font choices every day. You pick type designs each time you use a word processor, read an e-book, send an email, prepare a presentation, craft a wedding invite and make an Instagram story.

It might seem like just a question of style, but research reveals fonts can dramatically shape what you communicate and how you read.

Everyone knows Comic Sans is always the best choice.

xkcd provides the analysis we all need. I can’t believe Jupiter scored so low.

Nathan’s Famous hot dog eating contest, so gross to watch but impossible to look away, is coming up in celebration of America’s independence. Joey Chestnut is likely to win another title. For The Washington Post, Carson TerBush provides the timeline and explains the physical requirements to shove multiple hot dogs into your mouth in a small amount of time.

I knew Chestnut has been improving over the years, but I’m surprised the rest of the competition hasn’t really followed. Also, plus points for the cute, little hot dog symbols on the time series chart.

From the University of Washington Interactive Data Lab, Mosaic is a research project that aims to make it easier to show a lot of data and make it interactive between views:

Mosaic is a framework for linking data visualizations, tables, input widgets, and other data-driven components, while leveraging a database for scalable processing. With Mosaic, you can interactively visualize and explore millions and even billions of data points.

A key idea is that interface components – Mosaic clients – publish their data needs as queries that are managed by a central coordinator. The coordinator may further optimize queries before issuing them to a backing data source such as DuckDB.

Advertising funds a big chunk of the web, but for advertisers to continue to spend, their placements have to deliver results. So companies collect data about people’s online activity and create profiles based on the behavior. For The Markup, Jon Keegan and Joel Eastwood, dig in to the specificity of these profiles.

Profiles get stuck in segments or groups, and advertisers can choose which segment to put ads in front of. The above are finance-based segments. I’ve always dreamed of being a “Silver Sophisticate” myself.

You can download the data the project is based on here.

Here’s the good stuff for June.

It seems to have grown more common for basketball fans to complain that whoever wins the championship didn’t have to go through a legitimate challenge. If so and so wasn’t injured on the opposing team, so the naysayers claim, then such and such team wouldn’t have won. For The Pudding, Russell Samora made it easier to whine, based on an aptly named metric called CRUTCH.

The New York Times explores how noise impacts health:

Anyone who lives in a noisy environment, like the neighborhoods near this Brooklyn highway, may feel they have adapted to the cacophony. But data shows the opposite: Prior noise exposure primes the body to overreact, amplifying the negative effects.

I’m going to use this for the new reason my kids need quiet time.

Password rules seem to get more strict and weird over time. Neal Agarwal takes it to a ridiculous level, as Neal Agarwal likes to do. Enter a password that fits the rules, and another rule pops up until you find yourself with a password with a thousand wingdings.

United Airlines sold a lifetime unlimited pass in 1990 for $290,000. Tom Stuker bought one and has since flown 23 million miles over the decades. For The Washington Post, Rick Reilly, with graphics by Youyou Zhou, described the flight patterns of a man who figured out how to turn his unlimited miles into unlimited upgrades and gift cards.

To power the United States with more clean energy, you might think it’s just a matter of building more solar farms and wind turbines. But of course it’s more complicated. For The New York Times, Nadja Popovich and Brad Plumer describe and map the challenges:

America’s fragmented electric grid, which was largely built to accommodate coal and gas plants, is becoming a major obstacle to efforts to fight climate change.

Tapping into the nation’s vast supplies of wind and solar energy would be one of the cheapest ways to cut the emissions that are dangerously heating the planet, studies have found. That would mean building thousands of wind turbines across the gusty Great Plains and acres of solar arrays across the South, creating clean, low-cost electricity to power homes, vehicles and factories.

Andrew Hahn crocheted a map of Lake Mendota in Wisconsin. Each stitch represents 300 square meters and each layer represents 10 meters of depth. I should learn to crochet.

Learn more about your data and have more to visualize.

Color and contrast choices often are a product of personal preferences, but you can of course go deeper with it. Nate Baldwin provides an interactive guide on the perception of color and ties it to how it matters in the design of user interfaces:

This website is for designers to learn about color, contrast, and how it can affect experiences of a user interface. It provides quick access to relevant information at any point in the design process.

The content is thorough, but concise, and provides contextual insight to assist you in making educated decisions about color and contrast.

If you’re looking to switch or just want to expand your skills, this starter guide by Stephanie Lo provides some translations:

Are you curious about delving into the world of R programming? While Python remains the dominant choice amongst the data science community, with approximately 60% of developers using it in 2022, there are instances where R may pop up now and again. That’s because R is optimized for statistics and data. If you, like me, have a foundation in Python but now encounter job listings and internal company tasks that demand R skills, this article aims to break that down. We will explore the fundamental distinctions between Python and R and wrap the project into a data cleaning and visualization tutorial to ensure a smooth transition to R.

I mostly use R, but have always found it helpful to know some Python, especially when there’s some fun library to try.

Philippe Vandenbroeck and Santiago Ortiz were curious about a system that incorporated knowledge from a real person and ChatGPT, which is good for smushing text together in a coherent format. So they embedded text from Vandenbroeck into the ChatGPT model so that he could chat with himself. Ortiz describes the technical aspects of the system here.

See also the AI chatbot modeled on texts from a fiancee who passed. Looking back on our lives in a few decades is going to be weird.