Jon Harmon (he/him/his)
LightNews LightNews
banner
jonthegeek.com
Jon Harmon (he/him/his)
@jonthegeek.com
5.9K followers 1K following 550 posts
🗣️#RStats #DataScience #Dogs
@dslc.io Executive Director
#TidyTuesday poster

🔗http://linkedin.com/in/jonthegeek
🔗http://github.com/jonthegeek
Posts Replies Media Videos
jonthegeek.com
And he's home! Walking to the car was EXHAUSTING, but he was very happy to get out of that place and come home!
An old black dog with a "powdered sugar" muzzle smiling but resting his head on the center console of a car.
November 20, 2025 at 11:46 PM
jonthegeek.com
Westley (the Dread Puppy Roberts), my almost-14-years-old "black-mouthed cur", woke up this morning with a ruptured spleen. The good news: so far it doesn't look like metasticized cancer! That means he gets to go under the knife shortly to have that spleen removed and biopsied 🙃
Westley (the Dread Puppy Roberts), an older dog that looks mostly like a lab but he's really a mix of many things, stoicly prepares for surgery. Westley (the Dread Puppy Roberts), an older dog that looks mostly like a lab but he's really a mix of many things, receives his favorite thing: butt scratches.
November 18, 2025 at 9:51 PM
jonthegeek.com
@dslc.io welcomes you to week 46 of #TidyTuesday! We're exploring The Complete Sherlock Holmes!

📂 https://tidytues.day/2025/2025-11-18
🗞️ https://sherlock-holm.es/ascii/

#RStats #PyData #JuliaLang #DataViz #tidyverse #r4ds
Logo for the #TidyTuesday Project. The words TidyTuesday, A weekly data project from the Data Science Learning Community (dslc.io) overlaying a black paint splash. TidyTuesday is a weekly social data project. All are welcome to participate! Please remember to share the code used to generate your results! TidyTuesday is organized by the Data Science Learning Community. Join our Slack for free online help with R and other data-related topics, or to participate in a data-related book club! How to Participate Data is posted to social media every Monday morning. Follow the instructions in the new post for how to download the data. Explore the data, watching out for interesting relationships. We would like to emphasize that you should not draw conclusions about causation in the data. Create a visualization, a model, a shiny app, or some other piece of data-science-related output, using R or another programming language. Share your output and the code used to generate it on social media with the #TidyTuesday hashtag. Hex sticker for the sherlock R package created by Emil Hvitfeldt. The image depicts a silhouette of Sherlock Holmes with his typical deerstalker hat and calabash pipe. The word sherlock appears in blue over the silhouette, and the background is a pale green hexagon with a gray-green border.
November 17, 2025 at 1:42 PM
jonthegeek.com
@dslc.io welcomes you to week 45 of #TidyTuesday! We're exploring WHO TB Burden Data: Incidence, Mortality, and Population!

📁 https://tidytues.day/2025/2025-11-11
📰 https://samabbott.co.uk/getTBinR/index.html

#RStats #PyData #JuliaLang #DataViz #tidyverse #r4ds
Logo for the #TidyTuesday Project. The words TidyTuesday, A weekly data project from the Data Science Learning Community (dslc.io) overlaying a black paint splash. TidyTuesday is a weekly social data project. All are welcome to participate! Please remember to share the code used to generate your results! TidyTuesday is organized by the Data Science Learning Community. Join our Slack for free online help with R and other data-related topics, or to participate in a data-related book club! How to Participate Data is posted to social media every Monday morning. Follow the instructions in the new post for how to download the data. Explore the data, watching out for interesting relationships. We would like to emphasize that you should not draw conclusions about causation in the data. Create a visualization, a model, a shiny app, or some other piece of data-science-related output, using R or another programming language. Share your output and the code used to generate it on social media with the #TidyTuesday hashtag. World map showing estimated TB incidence rates per 100,000 population. Countries range from light green (low incidence) to dark purple (high incidence), with highest rates in Sub-Saharan Africa and South/Southeast Asia. Map sourced from WHO and rendered using getTBinR::map_tb_burden() in R.
November 10, 2025 at 1:48 PM
jonthegeek.com
This is in a branch named "encounters" of a package I'm working on.
An RStudio console pain showing a prompt with the word encounters and the time 8:33:33. The prompt runs this code: penguines |> tibble::as_tibble() The console displays the penguins dataset as a tibble, then a new propmpt with the word encounters then the time 8:33:42.
November 8, 2025 at 2:36 PM
jonthegeek.com
Curator: @jenrichmondPhD
@dslc.io welcomes you to week 44 of #TidyTuesday! We're exploring Lead concentration in Flint water samples in 2015!

📂 https://tidytues.day/2025/2025-11-04
📰 https://academic.oup.com/jrssig/article/14/2/16/7029247

#RStats #PyData #JuliaLang #DataViz #tidyverse #r4ds
Logo for the #TidyTuesday Project. The words TidyTuesday, A weekly data project from the Data Science Learning Community (dslc.io) overlaying a black paint splash. TidyTuesday is a weekly social data project. All are welcome to participate! Please remember to share the code used to generate your results! TidyTuesday is organized by the Data Science Learning Community. Join our Slack for free online help with R and other data-related topics, or to participate in a data-related book club! How to Participate Data is posted to social media every Monday morning. Follow the instructions in the new post for how to download the data. Explore the data, watching out for interesting relationships. We would like to emphasize that you should not draw conclusions about causation in the data. Create a visualization, a model, a shiny app, or some other piece of data-science-related output, using R or another programming language. Share your output and the code used to generate it on social media with the #TidyTuesday hashtag. This histogram shows the distribution of lead concentrations in water samples collected by Flint city officials from January to June 2015, during the Flint water crisis. The x-axis shows lead levels in parts per billion (ppb), with ND indicating non-detectable amounts, and the y-axis shows the number of samples at each concentration level. Most samples cluster at low concentrations, creating a right-skewed distribution with a long tail extending to very high values. Three vertical lines mark important regulatory levels. The blue dashed line is labeled The 90th percentile after excluding two high outliers, the black dashed line is labeled The EPA's lead action level, and the red dashed line is labeled The original 90th percentile before exclusions. Two samples shown in red were excluded from the official calculations, one at 20 ppb and another at 104 ppb.
November 3, 2025 at 1:40 PM
jonthegeek.com
@dslc.io welcomes you to week 43 of #TidyTuesday! We're exploring Selected British Literary Prizes (1990-2022)!

📁 https://tidytues.day/2025/2025-10-28
🗞️ https://theconversation.com/why-we-still-need-a-womens-prize-for-fiction-257494

#RStats #PyData #JuliaLang #DataViz #tidyverse #r4ds
Logo for the #TidyTuesday Project. The words TidyTuesday, A weekly data project from the Data Science Learning Community (dslc.io) overlaying a black paint splash. TidyTuesday is a weekly social data project. All are welcome to participate! Please remember to share the code used to generate your results! TidyTuesday is organized by the Data Science Learning Community. Join our Slack for free online help with R and other data-related topics, or to participate in a data-related book club! How to Participate Data is posted to social media every Monday morning. Follow the instructions in the new post for how to download the data. Explore the data, watching out for interesting relationships. We would like to emphasize that you should not draw conclusions about causation in the data. Create a visualization, a model, a shiny app, or some other piece of data-science-related output, using R or another programming language. Share your output and the code used to generate it on social media with the #TidyTuesday hashtag. This horizontal bar chart shows gender distribution of winners across British literary awards. Each bar displays the percentage and count of women (blue), men (green), and non-binary (yellow) winners. The Women's Prize for Fiction is 100% women by design. Other awards show varying gender representation, with women most represented in children's literature (Costa Children's Book Award at 71%) and poetry (Ted Hughes Award at 50%). Most other prizes show male majorities, ranging from slight (Costa awards around 52% men) to substantial (BSFA Award at 79% men). The data reveals significant gender imbalances across most literary prizes, with men winning the majority of awards except in women-specific and children's categories.
October 27, 2025 at 1:52 PM
jonthegeek.com
@dslc.io welcomes you to week 42 of #TidyTuesday! We're exploring Historic UK Meteorological & Climate Data!

📂 https://tidytues.day/2025/2025-10-21
🗞️ https://www.metoffice.gov.uk/research/climate/maps-and-data/historic-station-data

#RStats #PyData #JuliaLang #DataViz #tidyverse #r4ds
Logo for the #TidyTuesday Project. The words TidyTuesday, A weekly data project from the Data Science Learning Community (dslc.io) overlaying a black paint splash. TidyTuesday is a weekly social data project. All are welcome to participate! Please remember to share the code used to generate your results! TidyTuesday is organized by the Data Science Learning Community. Join our Slack for free online help with R and other data-related topics, or to participate in a data-related book club! How to Participate Data is posted to social media every Monday morning. Follow the instructions in the new post for how to download the data. Explore the data, watching out for interesting relationships. We would like to emphasize that you should not draw conclusions about causation in the data. Create a visualization, a model, a shiny app, or some other piece of data-science-related output, using R or another programming language. Share your output and the code used to generate it on social media with the #TidyTuesday hashtag. A map of 37 long-running meteorological monitoring stations run by the UK Met Office. Most stations span the full range of Great Britain, from Camborne in the far South-West of England up to Lerwick on the Shetland Islands. Two of the stations are found in Northern Ireland.
October 20, 2025 at 1:39 PM
jonthegeek.com
Curator: @jonthegeek.com
@dslc.io welcomes you to week 41 of #TidyTuesday! We're exploring World Food Day!

📁 https://tidytues.day/2025/2025-10-14
🗞️ https://en.wikipedia.org/wiki/World_Food_Day

#RStats #PyData #JuliaLang #DataViz #tidyverse #r4ds
Logo for the #TidyTuesday Project. The words TidyTuesday, A weekly data project from the Data Science Learning Community (dslc.io) overlaying a black paint splash. TidyTuesday is a weekly social data project. All are welcome to participate! Please remember to share the code used to generate your results! TidyTuesday is organized by the Data Science Learning Community. Join our Slack for free online help with R and other data-related topics, or to participate in a data-related book club! How to Participate Data is posted to social media every Monday morning. Follow the instructions in the new post for how to download the data. Explore the data, watching out for interesting relationships. We would like to emphasize that you should not draw conclusions about causation in the data. Create a visualization, a model, a shiny app, or some other piece of data-science-related output, using R or another programming language. Share your output and the code used to generate it on social media with the #TidyTuesday hashtag. Logo of the Food and Agriculture Organization of the United Nations. On the left, a circular emblem features a stylized ear of wheat with the letters 'FAO' above the Latin phrase 'Fiat Panis,' meaning 'Let there be bread.' To the right, the organization's full name appears in blue text.
October 13, 2025 at 1:39 PM
jonthegeek.com
@dslc.io welcomes you to week 40 of #TidyTuesday! We're exploring EuroLeague Basketball!

📁 https://tidytues.day/2025/2025-10-07
🗞️ https://en.wikipedia.org/wiki/EuroLeague

#RStats #PyData #JuliaLang #DataViz #tidyverse #r4ds
Logo for the #TidyTuesday Project. The words TidyTuesday, A weekly data project from the Data Science Learning Community (dslc.io) overlaying a black paint splash. TidyTuesday is a weekly social data project. All are welcome to participate! Please remember to share the code used to generate your results! TidyTuesday is organized by the Data Science Learning Community. Join our Slack for free online help with R and other data-related topics, or to participate in a data-related book club! How to Participate Data is posted to social media every Monday morning. Follow the instructions in the new post for how to download the data. Explore the data, watching out for interesting relationships. We would like to emphasize that you should not draw conclusions about causation in the data. Create a visualization, a model, a shiny app, or some other piece of data-science-related output, using R or another programming language. Share your output and the code used to generate it on social media with the #TidyTuesday hashtag. Lollipop chart showing the seating capacities of EuroLeague arenas by team.
October 6, 2025 at 1:38 PM
jonthegeek.com
As of yesterday, what I think of as my "Bonsai Tomatoes" have been growing in my Aerogarden for a full year. They still produce tomatoes (I just harvested, so you can't see any red in the photo), but, more importantly, they still produce a ton of leaves, which I can trim to enter a meditative state.
Tomato plants growing in an aerogarden hydroponic garden. A pair of gardening scissors are poking in from the side, ready to prune leaves.
October 1, 2025 at 10:38 AM
jonthegeek.com
@dslc.io welcomes you to week 39 of #TidyTuesday! We're exploring Crane Observations at Lake Hornborgasjön, Sweden (1994–2024)!

📁 https://tidytues.day/2025/2025-09-30

#RStats #PyData #JuliaLang #DataViz #tidyverse #r4ds
Logo for the #TidyTuesday Project. The words TidyTuesday, A weekly data project from the Data Science Learning Community (dslc.io) overlaying a black paint splash. TidyTuesday is a weekly social data project. All are welcome to participate! Please remember to share the code used to generate your results! TidyTuesday is organized by the Data Science Learning Community. Join our Slack for free online help with R and other data-related topics, or to participate in a data-related book club! How to Participate Data is posted to social media every Monday morning. Follow the instructions in the new post for how to download the data. Explore the data, watching out for interesting relationships. We would like to emphasize that you should not draw conclusions about causation in the data. Create a visualization, a model, a shiny app, or some other piece of data-science-related output, using R or another programming language. Share your output and the code used to generate it on social media with the #TidyTuesday hashtag. Large flock of cranes gathered in a grassy field during golden hour, with some birds in flight overhead and autumn-colored vegetation in the background. Line chart showing the number of cranes per day at Lake Hornborga in Sweden during March and April from 2014-2021. Multiple gray lines represent different years, with the 2018 and 2021 seasons highlighted in blue. The chart shows crane migration patterns starting near zero in early March, building to peak numbers of 15,000-27,000 birds between March 30 and April 8 (highlighted in beige), then declining through late April. The highest recorded count was 27,300 cranes on April 3rd, 2019. Dashed lines indicate days when weather conditions made accurate counting difficult. A note explains that 2018 had unusually cold February temperatures causing later arrival. The chart is credited to Anna Thieme from Länsstyrelsen VG at https://transtat.lansstyrelsen.se/
September 29, 2025 at 1:38 PM
jonthegeek.com
@dslc.io welcomes you to week 38 of #TidyTuesday! We're exploring FIDE Chess Player Ratings!

📁 https://tidytues.day/2025/2025-09-23
📰 https://www.fide.com/fide-september-2025-rating-list-vincent-keymer-debuts-in-top-10-open/

#RStats #PyData #JuliaLang #DataViz #tidyverse #r4ds
Logo for the #TidyTuesday Project. The words TidyTuesday, A weekly data project from the Data Science Learning Community (dslc.io) overlaying a black paint splash. TidyTuesday is a weekly social data project. All are welcome to participate! Please remember to share the code used to generate your results! TidyTuesday is organized by the Data Science Learning Community. Join our Slack for free online help with R and other data-related topics, or to participate in a data-related book club! How to Participate Data is posted to social media every Monday morning. Follow the instructions in the new post for how to download the data. Explore the data, watching out for interesting relationships. We would like to emphasize that you should not draw conclusions about causation in the data. Create a visualization, a model, a shiny app, or some other piece of data-science-related output, using R or another programming language. Share your output and the code used to generate it on social media with the #TidyTuesday hashtag. FIDE Rating List Top 10 as of September 1, 2025. At the top of the graphic, three players are featured prominently. Magnus Carlsen of Norway in first place with a rating of 2839, Hikaru Nakamura of the United States in second with 2807, and Fabiano Caruana of the United States in third with 2789, marked with a green +5 for his recent rating gain. Below them, the list continues. Fourth is Praggnanandhaa R of India with 2785 (+6), fifth is Arjun Erigaisi of India with 2771 (–5), sixth is Gukesh D of India with 2767 (–9), seventh is Wesley So of the United States with 2756 (+11), eighth is Alireza Firouzja of France with 2754 (–12), ninth is Wei Yi of China with 2753, and tenth is Vincent Keymer of Germany with 2751 (+21). The left side of the graphic features the FIDE logo and text reading 'FIDE Rating List Top 10' and 'September 1, 2025' in yellow on a black background.
September 22, 2025 at 1:38 PM
jonthegeek.com
Looks like I'll see y'all in Houston next year for #PositConf2026! Note: much like Austin, Houston isn't IN Texas so much as (almost) SURROUNDED BY Texas. I can understand if certain insane and evil policies of our government keep people away, though! #PositConf2025
Posit conf 2026 will be in Houston and virtual Sept 14-16, plus a European version TBD
September 18, 2025 at 9:21 PM
jonthegeek.com
This whole 10X developer thing is wrong! And boring! The last paper here points out that the whole thing is based at bad data (0.1x data science leads to "10x developer" nonsense?)
This whole 10X developer thing is wrong! MERITOCRACY BIAS: INDIVIDUAL EXPLANATIONS ARE MORE COGNITIVELY ACCESSIBLE SO WE DISCOUNT TRUE SYSTEMIC EXPLANATIONS Hadden et al., 2025 MERITOCRACY MESSAGES IN ORGANIZATIONS MAKE MANAGERS MORE BIASED WHEN EVALUATING PERFORMANCE Castilla & Benard, 2010 "10X" PROGRAMMER MYTH BASED ON POOR EVIDENCE FOR INDIVIDUAL DIFFERENCES Hicks & Hevesi, 2024
September 18, 2025 at 2:00 PM
jonthegeek.com
www.drcathicks.com/new-developer

"The New Developer:
AI Skill Threat, Identity Change & Developer Thriving in the Transition to AI-Assisted Software Development"
Surveyed more than 5000 developers and managers in more than 12 industries. Cumulative cultures had a lower percentage of developers with AI skill threat than lone genius cultures. Hicks, C. M., Lee, C. S., & Foster-Marks, K. (2025). The New Developer: Al Skill Threat, Identity Change & Developer Thriving in the Transition to Al-Assisted Software Development.
September 18, 2025 at 1:52 PM
jonthegeek.com
Soil & seed metaphor
Mindset by context Seed: an adaptive psychological belief/perspective creates resilient behavior cycles Soil: social context affords the adaptive belief, allows our continual "hypothesis testing" to validate the new belief Metaphor from Walton, Gregory M., and David S. Yeager. "Seed and soil: Psychological affordances in contexts help to explain where wise interventions succeed or fail." Current Directions in Psychological Science 29.3 (2020): 219-226.
September 18, 2025 at 1:45 PM
jonthegeek.com
The performance paradox
The performance paradoc 1. IN OUR COGNITION PERFORMANCE != LEARNING Soderstrom & Bjork, 2015 Bjork et al., 2013 Bjork & Bjork, 2019 2. IN OUR CAREERS FIXATING ON DEMONSTRATING PERFORMANCE MAKES US FRAGILE UNDER PRESSURE Pintrich, 2000 Darnon et al., 2007 Elliot & Church, 1997 3. IN OUR COMMUNITIES A FOCUS ON "BRILLIANCE" DECREASES FIELD INNOVATION & RECOGNITION OF TALENT Cimpian & Leslie, 2017 Bian et al., 2018
September 18, 2025 at 1:42 PM
jonthegeek.com
Cumulative culture teams win on productivity!
Plot from a paper "Developer Thriving: Can the LABS model show that cumulative cultures teams win on productivity?" Lots of dots on a plot of productivity vs developer thriving, with a trend toward the top-right quadrant. Labs is defined as learning culture, agency, belonging, and self-efficacy & motivation
September 18, 2025 at 1:37 PM
jonthegeek.com
Psych affordanced that signal we can engage in cumulative culture
Psych affordanced that signal we can engage in cumulative culture: Learning culture, sense of agency, self-efficacy & motivation, sense of belonging. Text is shown on top of a pleasant field of flowers.
September 18, 2025 at 1:34 PM
jonthegeek.com
We ask
We experiment
We calibrate
Repeat
WE ASK "What does it mean to be a productive/successful developer here?" WE EXPERIMENT What narratives and actions are possible *in this place* and *for me*? WE CALIBRATE Our behaviors & the social-psychological messages we send to others
September 18, 2025 at 1:26 PM
jonthegeek.com
LEARNING DEBT SABOTAGES THE CUMULATIVE CULTURE
LEARNING DEBT SABOTAGES THE CUMULATIVE CULTURE Active Learning Code writers build mental models of codebase without learning support Code reviews Formal processes meet with hypocrisy and social cues that devalue active learning Environment Code writers return to solo work, keep learning hidden, and contribute to an environment that discourages learning
September 18, 2025 at 1:24 PM
jonthegeek.com
* no human told me about it before Joe. I can't say for sure that no human caught it. A lot of the people examining #TidyTuesday data are more likely to assume they're wrong than to assume I'm wrong. Still a very compelling example but I want to make sure we don't forget who we are 😊
A drawing of an airplane with red dots showing where airplanes that came back from bombing runs got hit, an example of survivorship bias
September 17, 2025 at 10:49 PM
jonthegeek.com
The BID Framework
Interpret user needs
Notice friction points
Anticipate cognitive biases
Structure information flow
Validate understanding
The BID Framework Interpret user needs Notice friction points Anticipate cognitive biases Structure information flow Validate understanding Flow chart of interpret to a notice, anticipate, structure triad, to validate, and back to interpret.
September 17, 2025 at 3:13 PM
jonthegeek.com
@jmcphers.bsky.social is on stage, showing us his brain (as captured obsessively in Obsidian).
Jonathan's brain captured as a knowledge graph of notes in Obsidian. A label points out that it's not to scale.
September 17, 2025 at 1:17 PM