Scatter plot showing a positive correlation between review text sentiment and review scores for Animal Crossing, with a fitted S-curve. Reviews with positive sentiment cluster around scores of 8–10, while negative sentiment reviews are spread across all score levels.

Bar chart showing the distribution of Animal Crossing review scores on Metacritic. The distribution is strongly U-shaped, with scores of 0 (approximately 1,100 reviews) and 10 (approximately 650 reviews) dominating, and scores in the middle range (5–7) receiving the fewest reviews.

Day 15: Correlation

Are Animal crossing review ratings correlated with review text sentiment?

Yes... but rating scores are not normally distributed.

#30DayChartChallenge #TidyTuesday #tidyplots

year <- 2020
week <- 19

Kiwi founded shoe company Allbirds pivots to AI The company said it was now going to focus on Artificial Intelligence rather than sneakers, under the new name of NewBird AI.

A couple of weeks late for April Fools Day??

www.rnz.co.nz/news/busines...

Wide landscape photo of a calm lake with small ripples, bordered by a pebbled beach in the foreground. Two people stand near the water’s edge on the right, looking out across the lake. On the left, a line of tall trees with golden autumn leaves runs along the shore. Snow-capped mountains rise in the distance under a clear, bright blue sky.

New snow view on my walk today

📦 tidytuesdayR 1.3.2 is on its way to CRAN 🎉
Changes center around Dataset Curation functions

➕ Curation works on Positron
🧑‍💻 tt_meta() gains options for attribution/social media
✅ tt_submit() checks & deals with more things

dslc-io.github.io/tidytuesdayR...
#RStats #DataBS #TidyTuesday

Pea, Cabbage, Parmesan and Mint Salad Adapted from a recipe by Karen Martini, a famous Australian chef. Fast to make with everyday ingredients. So good you'll want to eat the whole salad as a meal!

my fav salad recipes come from Hetty McKinnon- she has a great book called Community that has lots of variety, she now writes recipes for the NYT. Also, my kids ate this slaw the other day which tells me it is really good www.recipetineats.com/pea-cabbage-...

Two side-by-side heatmaps titled “Ocean Temperature by Depth in Nova Scotia.” The left panel shows shallow water (2 m) and the right panel shows deep water (40 m). The x-axis displays years from 2018 to 2025, and the y-axis lists months from January to December. Each cell is colored on a blue gradient representing average temperature, with darker blues indicating colder temperatures and lighter blues indicating warmer temperatures. Missing data appears as grey tiles scattered across some months and years. In the shallow water panel, temperatures show strong seasonal variation: darker blues (colder) in winter months (January–March), transitioning to much lighter blues (warmer) in summer (July–September), then cooling again toward December. In the deep water panel, temperatures are more stable across months, with less contrast between seasons, though slightly warmer tones appear in late summer and early autumn. Overall, shallow waters exhibit larger seasonal temperature swings than deep waters.

Day 11: Physical

Ocean Temperatures by Depth in Nova Scotia

#30DayChartChallenge #TidyTuesday #tidyplots

year <- 2026
week <- 13

jenrichmond.github.io/charts26/202...

Notes re the #tidyplots package so far: it makes donuts really easy (no need for coord_polar silliness) but doesn't seem to work with `patchwork`. Also not sure how to add both a title and subtitle to a plot.

Day 8: Circular

As conflict wears on, the number of people displaced within their own country increases.

#30DayChartChallenge #TidyTuesday #tidyplots

year <- 2023
week <- 34

jenrichmond.github.io/charts26/202...

A scatter plot titled “Taller palm trees have more leaves” showing the relationship between maximum leaf number (x-axis) and maximum height in meters (y-axis). Each point represents a palm tree species. The points are widely scattered but show an upward trend, with a red regression line sloping upward from left to right. Most observations cluster at lower leaf counts (around 5–25 leaves) and lower heights (under 20 meters), with a few taller and leafier outliers reaching above 60 meters and around 70 leaves. A note in the top left reports a moderate positive correlation (R = 0.42, p < 0.001). A footer reads “TidyTuesday 2025 Week 11 | Data from ‘palmtrees’ R package.”

Day 4: Slope

Taller palm trees have more leaves

#30DayChartChallenge #TidyTuesday

year <- 2025
week <- 11

jenrichmond.github.io/charts26/202...

A stacked bar chart titled “Gender Pay Gaps in Australia” showing that of 1,105 occupations, only 7% pay women more than men. The single vertical bar is mostly dark blue (men earn more than women) with a small red section at the top (women earn more than men). The y-axis is labeled “Number of occupations” and ranges up to about 1,250. The red portion represents a small minority compared to the large blue majority. A legend on the right distinguishes “Women > Men” (red) and “Men > Women” (dark blue). A footer notes “TidyTuesday 2018 Week 4 | Data from data.gov.au.

This year for the #30DayChartChallenge I am going to pick a #TidyTuesday dataset at random and use it to make a chart with #ggplot and then see if I can reproduce it with #tidyplots.

Day 1: Part-to-whole, Australian Salary data

year <- 2018
week <- 4

jenrichmond.github.io/charts26/202...

PIPING HOT DATA: The case for variable labels in R Labelled data workflows with applications in data dictionaries, summary tables, ggplot, and exporting.

Shannon @pipinghotdata.com is the `labelled` QUEEN, her posit talk is definitely worth a look www.youtube.com/watch?v=eoI9...

yes!! I have been looking forward to this recording!!

I think of the recommendations in this paper a bit like the Twelve Commandments of Spreadsheets... follow them and save yourself HOURS at the other end. We assume that students/researchers know this stuff, but no one has explicitly been taught it.

Another hidden curriculum beauty...

Shannon Pileggi - Context is King YouTube video by Posit PBC

One of my favourite talks at positconf24 was @pipinghotdata.com talking about labelling data. Recording: youtu.be/eoI9QZdHBMw?...

Barbie driving down the road singing, text reads "downloading data for reuse. bottom panel: barbie and Ken screaming with text reading "there's no README"

It's important for the public to be able to reuse #RescuedData, but the context a README or similar documentation provides is necessary for understanding.

Be like Barbie. Help yourself have a great day every day, and on this #MemeMonday, remember to document your data.

Posit Cloud - Do, share, teach, and learn data science

On the free tier, every user gets 25 compute hours/month.

posit.cloud/plans

You can set up a project in the cloud so all students need to do to get going is follow a URL and make an account. Posit Cloud has a 25 hours per month limit. Once they have spent 25 hours in posit cloud, installing on their machine is a bit less daunting.

I think the RStudio interface is good for beginners and have had success with starting students out in Posit Cloud. It looks just like RStudio on your machine and allows you to kick the (sometimes) complicated R/RStudio install process down the road a little bit.

seriously @cghlewis.bsky.social, you are the meme queen. AND because you are also the data management queen, you have them beautifully organised in a github repo!!! 🥳

github.com/Cghlewis/dat...

OneDrive cloud sync is more trouble than it is worth.

The learning curve on Git and Github is steep, but you are always in control and you can make them work like a magic time machine.

#OpenScience #databs

Screenshot of introduction text from Crystal Lewis's book Data Management in Large scale Education Research book https://datamgmtinedresearch.com/intro. Sentence about mentoring and "winging it" being a common method of learning data management is highlighted in yellow.

Been thinking a lot about the "hidden curriculum" of research training recently and @cghlewis.bsky.social 's book is so great.

She argues that most of us learn how to manage data by mentoring and "winging" it.

What did you learn the hard way? Ill start...

#OpenScience #databs

A moody view from my walk.

Please stop sending me your datasets. YouTube video by Darren Dahly

For old times' sake:

www.youtube.com/watch?v=vxdQ...

a creek winds through willows and flax, opening into the lake with mountains behind.

A view from my walk.

A peek through the manuka to the calm lake, shadowy mountains in the background and sun poking through clouds to reveal blue sky.

A view from my walk.

I'm guessing the reason excel does this is that classes are determined at the cell, rather than at the column?? #rstats

This is basically my villain origin story.

"How old are you?" (unique responses)

Love this!! Mint is easy but it is a good idea plant it in a pot. It will take over your whole garden.

I started making this R package 6 years ago. I finally have it in a state I'm happy with, thanks to Claude Code #Rstats github.com/MattCowgill/...

A graph with the title "Sheep to people ratio in Aotearoa/NZ: Data from 1935–2024 by 5-year averages" on a light blue background with a pale green area resembling land. The x-axis shows years by 5-year increments and the y-axis shows the rounded number of sheep per people. Between 1935 and 1980, the ratio is about 20:1, but then rapidly dropping to about 5:1 in the 2020s. The top corner shows an outline of Aotearoa. Caption reads: "Packages: {tidyverse, marquee, patchwork, rnaturalearth, rvest}; Data: StatsNZ & Statista via TidyTuesday & Wikipedia; Visualization: C. Börstell"

Sheep to people ratio in Aotearoa/NZ for #TidyTuesday

🐑:👤 🇳🇿🌿

#R4DS #DataViz #ggplot2

Code: github.com/borstell/tid...