Masthash

#rstats

CRAN Package Updates
1 hour ago

New CRAN package zonohedra with initial version 0.2-1
#rstats
https://cran.r-project.org/package=zonohedra

CRAN Package Updates
1 hour ago

New CRAN package ScatterDensity with initial version 0.0.1
#rstats
https://cran.r-project.org/package=ScatterDensity

CRAN Package Updates
1 hour ago

New CRAN package matrixset with initial version 0.1.1
#rstats
https://cran.r-project.org/package=matrixset

CRAN Package Updates
1 hour ago

New CRAN package EEAaq with initial version 0.0.1
#rstats
https://cran.r-project.org/package=EEAaq

CRAN Package Updates
2 hours ago

CRAN updates: escalation #rstats

CRAN Package Updates
3 hours ago

CRAN updates: meteoland SHAPforxgboost #rstats

CRAN Package Updates
3 hours ago

New CRAN package nlpsem with initial version 0.1.0
#rstats
https://cran.r-project.org/package=nlpsem

CRAN Package Updates
3 hours ago

New CRAN package MVPBT with initial version 1.1-1
#rstats
https://cran.r-project.org/package=MVPBT

CRAN Package Updates
3 hours ago

New CRAN package EntropicStatistics with initial version 0.1.0
#rstats
https://cran.r-project.org/package=EntropicStatistics

I can not remember who said it (possibly @jennybryan), but there is a refrain that goes something like "if you do not test your software, your users are the tests."

Does anyone have a source on this?

#RStats #UnitTesting #TestThat #LazyWeb

Elio Campitelli
4 hours ago

I'm transferring ~120GB from a remote server with a relatively slow connection and rsync is not very good with progress bars, transfer speed and eta, so I cooked up something in #RStats:

https://gist.github.com/eliocamp/d9a9c0ccd42ea81fda4f47ce135af075

Screenshot of the code (you can see it in the gist). It checks the size of a folder every 5 seconds, computes the change in size from the previous run to estimate the speed and the eta (using the known total download size) and prints that using a progressbar with the progress package.
A screenshot of the progress bar showing the bar, the current size of the folder (15GB), the percentage (19%), the speed (8MB/s)  and the ETA (3 hours).
rOpenSci
4 hours ago

@rweekly highlights gave a shout out to @steffilazerte's post about scheduling Mastodon posts in R with rtoot and GitHub actions!

Post: https://ropensci.org/blog/2023/05/17/scheduling-mastodon/

Pod Cast: https://rweekly.fireside.fm/123?t=1752
R-weekly: https://rweekly.org/2023-W21.html

#RStats
@rstats

CRAN Package Updates
4 hours ago

CRAN updates: delaunay geostan kim tidyREDCap #rstats

CRAN Package Updates
4 hours ago

New CRAN package EBEN with initial version 5.1
#rstats
https://cran.r-project.org/package=EBEN

CRAN Package Updates
4 hours ago

CRAN removals: pgenlibr #rstats

jeremy_data :rstats:
5 hours ago

Sipping on whiskey and writing #rstats code. Good day.

Josiah :rstat:
5 hours ago

{vetiver} docker deployment with {valve}? yes please.

:rstat: 🪠
#rstats

R command of `valve_write_vetiver()` 

and the output is the contents of a dockerfile
rOpenSci
5 hours ago

rOpenSci is proud to welcome a new package to our software suite! 🎉

dwctaxon: Edit and Validate Darwin Core Taxon Data by @joelnitta

Docs: https://docs.ropensci.org/dwctaxon
Peer review: https://github.com/ropensci/software-review/issues/574

🙏 Thank you to reviewers @collinschwantes and Stephen Formel!

#RStats
@rstats

CRAN Package Updates
5 hours ago

CRAN updates: alone curvHDR jstable LRTesteR #rstats

Physalia-courses
6 hours ago

📣 Exciting news! The next edition of our Generalised Additive Models in R course with @gavinsimpson will be in Nov!
Get ready to unleash the power of GAMs and take your data analysis skills to the next level🚀
🔗https://physalia-courses.org/courses-workshops/gams-in-r/
Don't miss out!
#GAMs #Rstats #DataAnalysis

Georgios Karamanis
7 hours ago

Europe with constrained triangulation for last week's #MapPromptMonday, Book Cover

Code: https://github.com/gkaramanis/mappromptmonday/tree/master/2023/2023-week_21

#Rstats #dataviz

Minimalistic, black and white map of Europe and surrounding areas in Asia and Africa. The European countries have lines according to constrained triangulation so that they keep their shape.
Nicola Rennie
11 hours ago

I'm really looking forward to the R / Medicine conference next week 💡 The slides for my talk are now online - there's still time to register!

Session link: https://rmed2023a.sched.com/event/1MwUo/using-tidymodels-to-detect-heart-murmurs-nicola-rennie-lancaster-university

#RStats #RMed23

Screenshot of slides for presentation. Shows presentation title reading Using {tidymodels} to detect heart murmurs, the conference name R / Medicine 2023, and the speakers name Nicola Rennie.
Datascience :verified:
11 hours ago

Enrich your ggplots with extra panels along the x and y axis: https://github.com/jtlandis/ggside #ggplot #dataviz #rstats

coolbutuseless
13 hours ago
António Domingues
13 hours ago

@rfortunes @koantig sad to see the bot leave but thank you for the laughs, and how the bot helps appreciate the massive leaps the #RStats community took in terms of community inclusion in last ten years or so.

CRAN Package Updates
14 hours ago

CRAN removals: woodendesc #rstats

aRtsy_package
15 hours ago

Today's artwork generated with #rstats and #ggplot2:

CRAN Package Updates
18 hours ago

CRAN updates: varTestnlme #rstats

CRAN Package Updates
19 hours ago

CRAN updates: maptools #rstats

rstatspkgbot
20 hours ago

📦 geofacet
📝 'ggplot2' Faceting Utilities for Geographical Data

🔗 https://cran.r-project.org/web/packages/geofacet/index.html

🤖#RStats

CRAN Package Updates
20 hours ago

CRAN updates: ucminf #rstats

CRAN Package Updates
21 hours ago

CRAN updates: echarty gdalraster ggdag httptest lingtypology nanonext #rstats

CRAN Package Updates
21 hours ago

New CRAN package crosstable with initial version 0.6.2
#rstats
https://cran.r-project.org/package=crosstable

Josiah :rstat:
21 hours ago

Has anyone ever figured out the CSS to change a {pkgdown} site version number? I cannot find the incantations.

#rstats

Scott Dickson
1 day ago

@rfortunes @koantig I enjoyed them while they lasted. Sorry to see it go. Maybe the #rstats fortunes package needs to be updated to remove what didn’t age well and add some newer more relevant quotes.

Elio Campitelli
1 day ago

New version of #ggnewscale now fixes a long-standing bug that was introduced a few versions ago and was really hard to debug. Now you can actually add more than 2 scales if the scale is implicit in the geom/stat.

#RStats #ggplot2
https://eliocamp.github.io/ggnewscale/

ggplot2 figure of four cluster of tiles with different colour scales and 4 different colour legends.
Nicola Rennie
1 day ago
Black background with grey and white lines, points, and circles generative art
Pink, purple, and teal coloured polygons arranged with symmetry then jittered slightly to create generative art
White background with grey and black lines, points, and circles generative art
Blue, white, and orange coloured polygons arranged with symmetry then jittered slightly to create generative art
Carwil Bjork-James
1 day ago

Trying out Meld, a simple but incredibly useful tool for tracking changes in code side-by-side…

App: https://meld.app/
Homebrew installation on OSX: https://formulae.brew.sh/cask/meld

#rstats #git #codingtools

A window in the OS X application Meld shows two versions of R code in parallel columns. Blue highlighted regions show changes between the two columns. Green highlighted regions show additions on one side. Both highlights have X's allowing the user to cancel/remove what's on one side of the code.
Sebastian Krantz
1 day ago

Released a minor update {collapse} v1.9.6, which, notably, includes a new vignette on how {collapse} handles R objects - a quick view behind the scenes of its class-agnostic R programming framework: https://sebkrantz.github.io/collapse/articles/collapse_object_handling.html #rcollapse #rstats

jonthegeek
1 day ago

My talk for @ShinyConf #ShinyConf2023 "Baking JavaScript into a #RShiny Package" is up on the @appsilon YouTube! https://youtu.be/QLvd-q3c0Xc
Check it out, along with my {cookies} #RStats package! https://r4ds.github.io/cookies/

Dan Oehm 🌲⛰️
1 day ago

#TidyTuesday week 21: Squirrels 🐿️

Dabbled in some #GenAI this week. The tree and all squirrels were generated using Dalle. Not perfect but kinda cool.

Bit iffy on what the actual data represents though

🔗 http://github.com/doehm/tidytues
#Rstats #dataviz #r4ds #ggplot2

Datascience :verified:
1 day ago

R doesnt need to be a hard and scientific tool 📈. You can use it to make art 🎨: https://github.com/cutterkom/generativeart #rstats #generativeart #art @cutterkom

aRtsy_package
2 days ago

Today's artwork generated with #rstats and #ggplot2:

todd ellis
2 days ago

An R veteran of over 8 years and a total chump:

I've only just learned to use `dev.new()` to S T O P that annoying 'Plots' pane that barely ever functions correctly and sometimes just straight errors complex plots on my tiny laptop screen. Hello, `dev.new()`.

#RStats

Josiah :rstat:
2 days ago

{valve} now has
- auto-connection pooling
- auto-termination

So thats auto-scaling your plumber API.

:rstat: 🦀

This is such a fun project and im learning so so so much.

https://github.com/JosiahParry/valve
#rstats #rustlang

Elio Campitelli
2 days ago

The other day I saw a guy at the gym taking a picture of his sweat all over the floor, probably to share on on Instagram or whatever. At first I was judgy, thinking "why would you share something so dumb". But then I realise that when I write #rstats code that I'm proud of, I like sharing it with the community and I guess it must be similar for him and the workout scene, so I decided I was the asshole for judging him.

Betsy McCall
2 days ago

In the fall, I'm doing an independent study on data exploration in #rstats with one of my former students. I'm primarily planning on using the #tidyverse, but any other packages out there that might be useful to play around with? i'd rather have too many ideas than not enough.

Nicola Rennie
2 days ago

The making of this week's #TidyTuesday recorded with {camcorder} in #RStats! 📹📷

YouTube: https://youtu.be/vobupMY8RpU

Gif showing the progress of making the chart in the linked post
Adam H. Sparks
3 days ago

I've said it before, but I'll keep saying it. THANK YOU to @sckottie and @maelle for all your work to make API packages in R possible. This is a gem of a resource, https://books.ropensci.org/http-testing/index.html and {vcr} is such a great tool to use. 🙏👏 #RStats

Mara Averick
3 days ago

🗃️ Using walk() to write many files, feat. file-system navigation with {fs}:
🚶 "purrr::walk()` this way" https://www.tidyverse.org/blog/2023/05/purrr-walk-this-way/ #RStats

Cédric Scherer
3 days ago

Long version with all 190 countries that experienced a change of at least 1 percentage point

⬆️ 9
⬇️ 181

#rstats #ggplot2 #dataviz

The same dumbbell graph asin the tweet before but showing the full data set with only countries with almost no change being excluded.
Cédric Scherer
3 days ago

Striking drop in annual growth of GDP per capita from 2019 to 2020 💸

A series of #dataviz|es as alternatives to two choropleth maps, comparing the trends per year as shared by Max Roser (OurWorldInData).

3️⃣ Dumbbell graph showing trends for countries that inhabit ~20M people

(plus a long version with all countries with a noticeable change in the replies)

🛠️ #rstats + #ggplot2

A dumbbell graph showing the trends in GDP per capita growth from 2019 to 2020 with countries with a decrease being colored in red (dark red if it crosses zero, pale red otherwise) and those two with an increase (namely Turkey and Iran) being colored in blue. The country labels are placed on the left (in case of a decrease) and the right (in case of an increase) to further highlight the huge number of countries with a decrease in average income from 2019 to 2020. For most countries, the GDP per capita growth turned from positive to negative.
terence
3 days ago

What if we have forest cover over shaded relief? We get this map of El Salvador!

#rayshader adventures, an #rstats tale

A forest cover over relief map of El Salvador using data from 2019
Mara Averick
3 days ago

🚰 Re-direct R-code output to files w/ sink():
📝 “What is the sink() function? Capturing Output to External Files” by Steven P. Sanderson
https://www.spsanderson.com/steveondata/posts/2023-05-23/ #RStats

terence
3 days ago

A map showing the forest cover of Guatemala using data from 2019.

#rayshader adventures, an #rstats tale

A map showing the forest cover of Guatemala using data from 2019
aRtsy_package
4 days ago

Today's artwork generated with #rstats and #ggplot2:

Josiah :rstat:
4 days ago

🚰 :rstat: :🔧 {valve} is ready for some test users!

Parallelize your {plumber} APIs with literally one function.

Any brave souls willing to give it a shot? (particularly windows users)

👀 read the README to understand why this is so powerful!

https://github.com/josiahParry/valve

#rstats

drill benchmark results for a plumber api compared to the same one ran by valve. plumber makers 1.97 requests a second whereas valve makes 9.78 a second.
robjhyndman
4 days ago

My latest podcast interview on forecasting software with Fede Garza and Eric Stellwagen https://forecastingimpact.buzzsprout.com/1641538/12809499-forecasting-software-panel #rstats #forecasting

Julia Silge
4 days ago

Today @isabelizimm and I have a new guide published on how to use vetiver 🏺 to store model metrics as ✨metadata✨, in either #rstats or #python:

https://vetiver.rstudio.com/learn-more/metrics-metadata.html

Luis Apiolaza
4 days ago

Was checking student code—for a bunch of data manipulation, matrixy stuff—and at the beginning started with:
library(tidyverse)

but only used %>% and filter(). I pointed out that he could get away with:
library(dplyr)

but, even easier, could use:
|> and subset(), for no tidyverse dependency whatsoever.

The code has other 3 dependencies (pedigree, asreml and rrBLUP), but why use more than you really need?

#Rstats

terence
4 days ago

Back to forest cover maps with one of México.

#rayshader adventures, an #rstats tale

A forest cover map of Mexico using data from 2019
posit::glimpse()
4 days ago

Starting with the mechanics of understaning how LLMs work can help foster durable intuitions that will inform our usage of these models now & in the future. (Especially if the future is one where LLMs are a staple of the data scientist’s toolbox, as common as an lm() function call).

And what better way is there to learn than by doing!

Tomasz Kalinowski walks through an implementation of LLaMA, a Large Language Model, in R, with TensorFlow and Keras.

https://blogs.rstudio.com/ai/posts/2023-05-25-llama-tensorflow-keras/

#rstats #ai #ml

Brian O'Meara
4 days ago

@will I think @rOpenSci does a pretty good job with this. https://contributing.ropensci.org/ . #rstats

Deepali Kank
4 days ago

#TidyTuesday week 21 - Central Park Squirrels. Made an infographic this time with the help of #canva and R.
#dataviz #rstats

Infographic about squirrels in central park
Sharon Machlis
4 days ago

I asked Bing Chat the same question. Answer: dplyr, tidyr, stringr, lubridate, reshape2, data.table, magrittr, and purrr, each with a description, ex:
dplyr: "This package is used for data manipulation and is one of the most popular packages in R. It provides a set of functions that can be used to filter, arrange, group, and summarize data." and data.table: "This package is used for fast data manipulation and is especially useful for large datasets." for data.table
2/2
#rstats #AI #GenerativeAI

There are many R packages that can be used for data wrangling. Some of the most popular ones include:

dplyr: This package is used for data manipulation and is one of the most popular packages in R. It provides a set of functions that can be used to filter, arrange, group, and summarize data.

tidyr: This package is used for data tidying and provides functions for converting data between wide and long formats.

stringr: This package provides functions for working with strings in R.

lubridate: This package provides functions for working with dates and times in R.

reshape2: This package provides functions for reshaping data between wide and long formats.

data.table: This package is used for fast data manipulation and is especially useful for large datasets.

magrittr: This package provides a set of operators that can be used to create more readable code.

purrr: This package provides a set of functions for working with lists and vectors.

I hope this helps! Let me know if you have any other questions.

Learn more:
1. data-flair.training
2. r-bloggers.com
3. rstudio.com
4. computerworld.com
5. udacity.com
6. bookdown.org
+3 more
Sharon Machlis
4 days ago

I just asked Google Bard: What are the best R packages for wrangling data?
Answer: dplyr, tidyr, data.table, reshape2, and stringr, each with 📦 details. Plus a comment that there are others and you can search CRAN to find more. 1/2

#rstats #GoogleBard #AI #GenerativeAI

There are many R packages that can be used for data wrangling. Some of the most popular include:

dplyr is a powerful package for data manipulation and transformation. It provides a consistent set of verbs for working with data frames, making it easy to perform common tasks such as filtering, selecting, and summarizing data.
dplyr R package logo
tidyr is a package for tidying data. It provides functions for converting data into a "tidy" format, which is a standard format for storing data that makes it easy to work with.
tidyr R package logo
data.table is a fast and efficient package for data manipulation and analysis. It provides a wide range of functions for working with data tables, including functions for joining, aggregating, and summarizing data.
data.table R package logo
Sharon Machlis
4 days ago

The {ggautomap} #rstats 📦 “provides #ggplot2 geometries that make use of cartographer, a framework for matching place names with map data. With ggautomap your input dataset doesn’t need to be spatially aware: The geometries will automatically attach the map data (providing it’s been registered with cartographer).”
https://cidm-ph.github.io/ggautomap/index.html
By Carl Suster, on CRAN
#RSpatial #GIS @rstats

Image of a point map with an inset and the following text:

Insets
To show a zoomed in part of the map as an inset, you can configure an inset and provide it to each relevant geom. The geoms in this package are all inset-aware. See ggmapinset for details.

covid_cases_nsw %>%
  ggplot(aes(location = lga))  
  geom_boundaries(feature_type = "nswgeo.lga")  
  geom_geoscatter(aes(colour = type), size = 0.5)  
  geom_inset_frame()  
  coord_automap(feature_type = "nswgeo.lga", inset = configure_inset(
    centre = "Blacktown", radius = 40, units = "km",
    scale = 7, translation = c(400, -100)
  ))  
  theme_void()
Sharon Machlis
4 days ago

find.not.numeric.value() is a function that finds where in a vector there are values that can't be converted to numbers. For example

find.not.numeric.value(myvector)

Part of the {infun} #rstats 📦 containing several R utility functions. uBy Mao Kobayashi
https://github.com/indenkun/infun

Jeff Hollister
4 days ago

@metamattj Good to see you on here! Overall I like the experience here, its just different (in a good way). It is easy to find the #rstats, #opensource, and #openscience folks!

R-Podcast (Eric) :pci:
4 days ago

Episode 123 of the @rstats @rweekly Highlights Podcast blends nicely with the R community! https://podverse.fm/episode/DmcMBmplP

🕸 HTTP Testing with R @maelle @RConsortium
💹 Introducing {ggblend} @mjskay
📆 Handling dates in R & Excel @AbrahamsAmieroh@twitter.com @jumpingrivers

Happy with your current podcast app but want to send a boost? You can do that directly on the Podcast Index! Find us at https://podcastindex.org/podcast/1062040

h/t @mike_thomas @batool664@twitter.com 🙏

#rstats #datascience #podcasting2.0 #v4v

Datascience :verified:
4 days ago

Are you interested in how dependency-heavy your (or another) package is and why? https://github.com/jokergoo/pkgndep #rstats

Till Grallert
4 days ago

I thoroughly enjoyed presenting my data-driven research on late Ottoman #Arabic #Periodicals at #DigHis23. The paper introduces stylometric authorship attribution for answering the question whether editors/publishers of magazines could or should be considered the authors of the bulk of anonymous texts in their periodicals. The method relies on collaborative work with Maxim Romanov on establishing parameters for reliable authorship attribution in Arabic for the `stylo()` package in #R (#Rstats).

Slides are available at https://tinyurl.com/dighis23-grallert

#MultilingualDH #DigitalHumanities #DigitalHistory #PeriodicalStudies #Stylometry

#!/usr/bin/env Rscript

## License: Share and Enjoy

Ult.QoL <- function(){
require("towel")

message("Don't panic!")

# "Six by nine. Forty two. That's it. That's all there is."
return(6*9)
}

If( Ult.QoL() == 42 ){
message("I always thought something was fundamentally wrong with the universe.")
}

#thgttg #rstats #TowelDay

Phil McAleer
5 days ago

One reason I love the markr approach is that by having all the feedback in one place, before generating the feedback documents, I can review the feedback easily across the cohort and then update and add more general feedback for all to the feedback documents based on any themes I hadn’t quite spotted in the individual feedback. Likewise, it is great for developing my own future teaching as it becomes easier to see what students understood well or not so well.

#SoTL #Feedback #rstats #PsyTeachR

Cédric Scherer
5 days ago

Striking drop in annual growth of GDP per capita from 2019 to 2020 💸

A series of #dataviz|es as alternatives to two choropleth maps, comparing the trends per year as shared by Max Roser (OurWorldInData).

2️⃣ Slope graphs per country as tile grid map showing trends for each of the 186 countries featured.

🛠️ #rstats + #ggplot, in combination with the #geofacet ️📦 and #Figma to add the "how to" section + continent labels

A geofacet (a tile grid map that represents the [most] countries of the world as equally sized rectangles, mimicking the original geographic topology as closely as possible) with colored slope charts for each country. The world map is overall very red highlighting that "average income has decreased in almost all countries from 2019 to 2020, with GDP per capita growth turning from positive to negative in most cases".  

Each rectangle (slope chart) features a country code and continent labels are added to help to distinguish the original spatial shape. A "how to interpret the slope chart" box showcases how to read the chart by using the trend for Great Britain, summarizing that: "From 2019 to 2020, the annual growth of GDP per capita of Great Britain has decreased by approx. 10 percentage points, turning from positive to negative."
Cédric Scherer
6 days ago

Striking drop in annual growth of GDP per capita from 2019 to 2020 💸

A series of #dataviz|es as alternatives to two choropleth maps, comparing the trends per year as shared by Max Roser (OurWorldInData).

1⃣ Slope graph showing trends for 196 countries, overall and split per continent

🛠️ #rstats + #ggplot2, using the new #ggblend 📦

A large slope graph (upper row) and five small multiples showing annual change in GDP per capita in percent (~income) overall and splitted by continent. The title reads "Average income has decreased in 185 countries from 2019 to 2020, with GDP per capita growth turning negative in 72% of these cases". 

Boxplots placed to both sides show the overall distribution per year, color indicates the difference (percentage points) ranging from red (negative) to blue (positive). Small horizontal bars using the same color encoding placed below the slope charts summarize the trends.  Overall, only 11 out of 196 countries show a positive trend. 

Data: World Bank and OECD via OurWorldInData (https://ourworldindata.org/grapher/gdp-per-capita-growth)
Sharon Machlis
6 days ago

The {pins} #rstats 📦 now supports reading and writing parquet files! 🎉Via @juliasilge
https://posit.co/blog/announcing-pins-1-2-0/

@rstats

terence
6 days ago

A population density over shaded relief map of Iran. I rather like how this turned out. What do you think?

#rayshader adventures, an #rstats tale

A population density over shaded relief map of Iran
Datascience :verified:
6 days ago

Need some data to test a plot idea or algorithm? On https://drawdata.xyz/ you can draw the data you want... #rstats #synthetic #dataviz

Sharon Machlis
1 week ago

The {appeears} #rstats 📦 "provides easy access to the AppEEARS API directly from R", accordng to pkg author @koen_hufkens. That API lets you subset and download geospatial datasets from several different US gov't sources. (A free NASA Earth Data account needed.)
Pkg info: https://bluegreen-labs.github.io/appeears/
#rstats #RSpatial #GIS @rstats

terence
1 week ago

A population density over shaded relief map of Japan. Was pleasantly surprised to spot Mount Fuji so I added a label.

#rayshader adventures, an #rstats tale

A population density over shaded relief map of Japan
Shannon Pileggi
1 week ago

We are hiring a Data Scientist II at the The Prostate Cancer Clinical Trials Consortium (PCCTC)! 🎉We are excited to grow our Data Science team, and we look forward to working with #rstats programmers 🛠️with an interest in clinical research.

Please apply if you are interested! https://bit.ly/3IySWXk

Matthew Kay
1 week ago

The #ggblend #rstats package is now on CRAN!! https://mjskay.github.io/ggblend/

ggblend is a small algebra of operations for blending, copying, adjusting, and compositing layers in ggplot2

One problem it solves is making plots independent of draw order: e.g. by using commutative blends, like "lighten" or "multiply"

Two versions of a scatterplot of two partially-overlapping groups (a and b). Each version has a different draw order: a then b or b then a. When a is drawn first, its points are obscured by b (and vice versa).
Two versions of a scatterplot of two partially-overlapping groups (a and b). Each version has a different draw order: a then b or b then a. Commutative blends (lighten and multiply) are used to ensure that the final plot output is independent of draw order.

I've made a lightweight glossary #rstats package for quarto and R Markdown documents. You just tag words in your text like `r glossary("term")` and create a glossary table at the end of the section with `glossary_table()`. The definitions can be set in each glossary() function, or pulled from a YAML file.

I'm hoping to submit to CRAN soon, but would love if anyone had time for a quick test and feedback.

https://debruine.github.io/glossary/

Sharon Machlis
1 week ago

“Knowing just a bit of HTML and CSS can unlock the full potential of R tools like {gt}, {ggtext}, {shiny}, and Quarto.”

Video: HTML and CSS for R Users - presentation at the Harvard Data Science Initiative R User Group by Albert Rapp
https://youtu.be/Y80iGc5Vjyc

Blog post: https://albert-rapp.de/posts/16_html_css_for_r/16_html_css_for_r.html
#rstats @rstats #css #QuartoPub #quarto @rappa753 #RShiny

Sharon Machlis
1 week ago

“A brand-new version of the #rstats tidycensus package is now on CRAN, supporting the brand-new 2022 Population Estimates (which you can't get from the API). Download the new version today and start making charts like this!” - 📦 author Kyle Walker
https://walker-data.com/tidycensus

#Census #USCensus #ddj

Horizontal bar chart showing 20 fastest growing US cities by percent growth, for cities with at least 250,000 residents. Top was North Las Vegas NV at 3.47% followed by Irvine CA 2.82, Henderson NV 2.79 and Seattle 2.43.
Julia Silge
1 week ago

The #rstats code is available on my blog: https://juliasilge.com/blog/tornadoes/

Helped someone debug some tidyverse data processing issues. It turns out "NA" was a legitimate code used in their data and readr by default interprets it as NA, not a string. Careful folks! #rstats

Edit: for anyone who doesn't know, `read_csv()` has an `na` parameter. The default is `na = c("", "NA")`. Setting it to `na = ""` fixed the issue.

terence
1 week ago

A forest cover map of Uruguay using data from Copernicus Land Cover 2019.

#rayshader adventures, an #rstats tale

A forest cover map of Uruguay using data from Copernicus Land Cover 2019
Jason Heppler ⧖
1 week ago

Is there a straightforward way in #rstats to add Interstate and highway icons to a ggplot map?

I'd totally forgotten about this quirk of #rstats functions: arguments are not evaulated until they are used, so if argument b defaults to the value of argument a, you need to use argument b in the code before you make any changes to a (or of course don't change a)

((I spent half an hour debugging something due to this today))

x <- function(a, b = a) {
a = 1
return(b) # first use of b sets the value b = a = 1
}

x(2) # returns 1

y <- function(a, b = a) {
b # sets the value of b = a = 2
a = 1
return(b)
}

y(2) # returns 2

Sharon Machlis
1 week ago

Git Version Control and RStudio
@NHSrCommunity webinar on Thursday, May 25
3:30 pm – 4:30 pm BST / 10:30 am EDT
With Ryan Johnson – Data Science Advisor, @Posit

https://nhsrcommunity.com/events/may-2023-webinar-version-control-and-rstudio-ryan-johnson-data-science-advisor-posit/

#rstats #RStudio #git