For some models that are known to tidymodels, you can trick it into just working:
gist.github.com/topepo/0d6f7...
gist.github.com/topepo/0d6f7...
November 5, 2025 at 7:33 PM
For some models that are known to tidymodels, you can trick it into just working:
gist.github.com/topepo/0d6f7...
gist.github.com/topepo/0d6f7...
You could create a small function/class/package that encapsulates the object and allows for predictions. The pain is making it work with tidymodels, especially if that involves some novel model type.
Avoid estimation for a model in tidymodels
Avoid estimation for a model in tidymodels. GitHub Gist: instantly share code, notes, and snippets.
gist.github.com
November 5, 2025 at 7:32 PM
You could create a small function/class/package that encapsulates the object and allows for predictions. The pain is making it work with tidymodels, especially if that involves some novel model type.
How to fit a model without estimating any parameters?
Use a formula with
y ~ 0 + offset(...)
This works with any formula interface, and with #tidymodels this can be passed to add_model().
#rstats
Use a formula with
y ~ 0 + offset(...)
This works with any formula interface, and with #tidymodels this can be passed to add_model().
#rstats
November 5, 2025 at 10:56 AM
How to fit a model without estimating any parameters?
Use a formula with
y ~ 0 + offset(...)
This works with any formula interface, and with #tidymodels this can be passed to add_model().
#rstats
Use a formula with
y ~ 0 + offset(...)
This works with any formula interface, and with #tidymodels this can be passed to add_model().
#rstats
Today's challenge: build a model with fixed parameters (that do not need to be estimated) that can still be used with #tidymodels functionality.
I found a solution (that didn't require setting up a new type of model) - will post some code later - but I wonder how @topepo.bsky.social would do this?
I found a solution (that didn't require setting up a new type of model) - will post some code later - but I wonder how @topepo.bsky.social would do this?
November 4, 2025 at 3:33 PM
Today's challenge: build a model with fixed parameters (that do not need to be estimated) that can still be used with #tidymodels functionality.
I found a solution (that didn't require setting up a new type of model) - will post some code later - but I wonder how @topepo.bsky.social would do this?
I found a solution (that didn't require setting up a new type of model) - will post some code later - but I wonder how @topepo.bsky.social would do this?
@jeremy-data.bsky.social biology based on #Bioconductor (and I’m a BioJava contributor) - also model building in health informatics (I’d use #tidymodels and #vetiver now) vs Python
October 30, 2025 at 2:25 PM
@jeremy-data.bsky.social biology based on #Bioconductor (and I’m a BioJava contributor) - also model building in health informatics (I’d use #tidymodels and #vetiver now) vs Python
tidymodels is almost too convenient that sometimes I have to slow down lest I miss something important. ALMOST.
October 30, 2025 at 4:58 AM
tidymodels is almost too convenient that sometimes I have to slow down lest I miss something important. ALMOST.
Working with data where columns contain nested data structures is easier in R (e.g. JSON). Packages like {purrr} and {dplyr} let you to manipulate columns of arbitrary types using the same APIs. The NSE in R is also very helpful here.
I also think {tidymodels} has the best UX for ML work.
I also think {tidymodels} has the best UX for ML work.
October 30, 2025 at 2:50 AM
Working with data where columns contain nested data structures is easier in R (e.g. JSON). Packages like {purrr} and {dplyr} let you to manipulate columns of arbitrary types using the same APIs. The NSE in R is also very helpful here.
I also think {tidymodels} has the best UX for ML work.
I also think {tidymodels} has the best UX for ML work.
🌍 Blog series: Spatial Machine Learning with R
From caret to tidymodels, mlr3, and specialized spatial ML packages — explore how spatial context changes the way we build ML models in R.
Start with Part 1 👉 geocompx.org/post/2025/sm...
#RStats #SpatialML #MachineLearning #RSpatial
From caret to tidymodels, mlr3, and specialized spatial ML packages — explore how spatial context changes the way we build ML models in R.
Start with Part 1 👉 geocompx.org/post/2025/sm...
#RStats #SpatialML #MachineLearning #RSpatial
October 22, 2025 at 1:05 PM
🌍 Blog series: Spatial Machine Learning with R
From caret to tidymodels, mlr3, and specialized spatial ML packages — explore how spatial context changes the way we build ML models in R.
Start with Part 1 👉 geocompx.org/post/2025/sm...
#RStats #SpatialML #MachineLearning #RSpatial
From caret to tidymodels, mlr3, and specialized spatial ML packages — explore how spatial context changes the way we build ML models in R.
Start with Part 1 👉 geocompx.org/post/2025/sm...
#RStats #SpatialML #MachineLearning #RSpatial
🌍 Blog series: Spatial Machine Learning with R
From caret to tidymodels, mlr3, and specialized spatial ML packages — explore how spatial context changes the way we build ML models in R.
Start with Part 1 👉 https://geocompx.org/post/2025/sml-bp1/
#rstats #spatialml #machinelearning #rspatial
From caret to tidymodels, mlr3, and specialized spatial ML packages — explore how spatial context changes the way we build ML models in R.
Start with Part 1 👉 https://geocompx.org/post/2025/sml-bp1/
#rstats #spatialml #machinelearning #rspatial
October 22, 2025 at 1:02 PM
🌍 Blog series: Spatial Machine Learning with R
From caret to tidymodels, mlr3, and specialized spatial ML packages — explore how spatial context changes the way we build ML models in R.
Start with Part 1 👉 https://geocompx.org/post/2025/sml-bp1/
#rstats #spatialml #machinelearning #rspatial
From caret to tidymodels, mlr3, and specialized spatial ML packages — explore how spatial context changes the way we build ML models in R.
Start with Part 1 👉 https://geocompx.org/post/2025/sml-bp1/
#rstats #spatialml #machinelearning #rspatial
Mostly learned from this book & looking at open source packages on GitHub for ideas r-pkgs.org
For any extension package related to tidymodels, tidymodels, etc. they also contain vignettes for developers that come in handy
For any extension package related to tidymodels, tidymodels, etc. they also contain vignettes for developers that come in handy
R Packages (2e)
Learn how to create a package, the fundamental unit of shareable, reusable, and reproducible R code.
r-pkgs.org
October 18, 2025 at 3:41 PM
Mostly learned from this book & looking at open source packages on GitHub for ideas r-pkgs.org
For any extension package related to tidymodels, tidymodels, etc. they also contain vignettes for developers that come in handy
For any extension package related to tidymodels, tidymodels, etc. they also contain vignettes for developers that come in handy
I'll be going live in 2.5 hours for Socal RUG, talking about how to use orbital to do model predictions in the cloud.
This is a joint in-person and online event
www.meetup.com/socal-rug/ev...
#rstats #tidymodels #databs
This is a joint in-person and online event
www.meetup.com/socal-rug/ev...
#rstats #tidymodels #databs
Stop Horsing Around - Ship the Query!, Thu, Oct 16, 2025, 6:30 PM | Meetup
Ready to launch models straight from SQL? Join SoCal RUG with presenter **Emil Hvitfeldt,** a Software Engineer at Posit, on **Orbital**, a new tool that converts scikit-le
www.meetup.com
October 16, 2025 at 11:33 PM
I'll be going live in 2.5 hours for Socal RUG, talking about how to use orbital to do model predictions in the cloud.
This is a joint in-person and online event
www.meetup.com/socal-rug/ev...
#rstats #tidymodels #databs
This is a joint in-person and online event
www.meetup.com/socal-rug/ev...
#rstats #tidymodels #databs
Integrating Python Forecasting with R’s Tidyverse
"In this article, we executed a successful integration of a non-standard Python forecasting model into the R Tidyverse/Tidymodels framework, primarily leveraging the reticulate package. 1. The Objective (The Challenge) The goal was to utilize ..."
"In this article, we executed a successful integration of a non-standard Python forecasting model into the R Tidyverse/Tidymodels framework, primarily leveraging the reticulate package. 1. The Objective (The Challenge) The goal was to utilize ..."
October 14, 2025 at 6:41 PM
Integrating Python Forecasting with R’s Tidyverse
"In this article, we executed a successful integration of a non-standard Python forecasting model into the R Tidyverse/Tidymodels framework, primarily leveraging the reticulate package. 1. The Objective (The Challenge) The goal was to utilize ..."
"In this article, we executed a successful integration of a non-standard Python forecasting model into the R Tidyverse/Tidymodels framework, primarily leveraging the reticulate package. 1. The Objective (The Challenge) The goal was to utilize ..."
I still don't know a single person who's successfully used tidymodels
October 7, 2025 at 3:46 PM
I still don't know a single person who's successfully used tidymodels
Me: explains about data leakage, shows how to use #tidymodels {recipes} functions to avoid it.
Student: writes* horrendous code, with insane loops, data leakage all over the place.
Why? Just why?
*The resulting SO-looking code was most likely produced with an LLM.
Student: writes* horrendous code, with insane loops, data leakage all over the place.
Why? Just why?
*The resulting SO-looking code was most likely produced with an LLM.
Finished marking papers in one of my courses. It's painful to see bright minds atrophied by the integration of LLMs into the "learning" process.
Instead of building an understanding, e.g. by trying to generalize examples seen in exercises, LLMs are used in an effort to "just do". Poorly.
Shame.
Instead of building an understanding, e.g. by trying to generalize examples seen in exercises, LLMs are used in an effort to "just do". Poorly.
Shame.
October 5, 2025 at 1:25 PM
Me: explains about data leakage, shows how to use #tidymodels {recipes} functions to avoid it.
Student: writes* horrendous code, with insane loops, data leakage all over the place.
Why? Just why?
*The resulting SO-looking code was most likely produced with an LLM.
Student: writes* horrendous code, with insane loops, data leakage all over the place.
Why? Just why?
*The resulting SO-looking code was most likely produced with an LLM.
Excited to watch the webinar on "Modular, interoperable, and extensible topological data analysis in R" next week by Jason Cory Brunson and Aymeric Stamm
r-consortium.org/webinars/mod...
#tidymodels
r-consortium.org/webinars/mod...
#tidymodels
Modular, interoperable, and extensible topological data analysis in R – R Consortium
r-consortium.org
October 3, 2025 at 7:41 PM
Excited to watch the webinar on "Modular, interoperable, and extensible topological data analysis in R" next week by Jason Cory Brunson and Aymeric Stamm
r-consortium.org/webinars/mod...
#tidymodels
r-consortium.org/webinars/mod...
#tidymodels
Using the hai_data_trig() function from my package healthyR.ai
Reference: www.spsanderson.com/healthyR.ai/...
#R #RStats #datatransformation #DataScience #data #tidy #recipes #tidymodels
Reference: www.spsanderson.com/healthyR.ai/...
#R #RStats #datatransformation #DataScience #data #tidy #recipes #tidymodels
October 3, 2025 at 2:38 PM
Using the hai_data_trig() function from my package healthyR.ai
Reference: www.spsanderson.com/healthyR.ai/...
#R #RStats #datatransformation #DataScience #data #tidy #recipes #tidymodels
Reference: www.spsanderson.com/healthyR.ai/...
#R #RStats #datatransformation #DataScience #data #tidy #recipes #tidymodels
Yayyy, welcome to the Tidy Tuesday crew!! This was a fun week. I have been missing modeling, so I did the quickest RF model ever just to test out tidymodels!
September 25, 2025 at 5:01 AM
Yayyy, welcome to the Tidy Tuesday crew!! This was a fun week. I have been missing modeling, so I did the quickest RF model ever just to test out tidymodels!
SoCal RUG is back! @emilhvitfeldt.bsky.social will be demoing Orbital, a framework to convert your fit model workflows from scikit-learn (Python) or tidymodels (R) to native SQL for in-database prediction! 🛸 Please RSVP for this hybrid in-person + YouTube Live event: meetu.ps/e/Py49Y/v02v...
Stop Horsing Around - Ship the Query!, Thu, Oct 16, 2025, 6:30 PM | Meetup
Ready to launch models straight from SQL? Join SoCal RUG with presenter **Emil Hvitfeldt,** a Software Engineer at Posit, on **Orbital**, a new tool that converts scikit-le
meetu.ps
September 23, 2025 at 7:37 PM
SoCal RUG is back! @emilhvitfeldt.bsky.social will be demoing Orbital, a framework to convert your fit model workflows from scikit-learn (Python) or tidymodels (R) to native SQL for in-database prediction! 🛸 Please RSVP for this hybrid in-person + YouTube Live event: meetu.ps/e/Py49Y/v02v...
On this, the tidiest of Tuesdays, all I wanted was to do something stats or ML related. I've been missing data work. So, with my 30 mins, I built a random forest model with #tidymodels just to do it. Yes, it was therapeutic. Yes, I did use 42 as my random seed. It felt like coming home. #TidyTuesday
September 23, 2025 at 4:13 PM
On this, the tidiest of Tuesdays, all I wanted was to do something stats or ML related. I've been missing data work. So, with my 30 mins, I built a random forest model with #tidymodels just to do it. Yes, it was therapeutic. Yes, I did use 42 as my random seed. It felt like coming home. #TidyTuesday
My first Tidy Dev Day! Contributed to #tidymodels fixes!
September 23, 2025 at 4:59 AM
My first Tidy Dev Day! Contributed to #tidymodels fixes!
For those curious, this is the first book (that I am aware of) that utilizes a myriad of the growing "tidyverse," such as tidynetworks, tidymodels, and tidytext. Despite the name, it does not focus only on utilizing the tidy approach and deals with situations where base-R is more practical.
September 18, 2025 at 10:11 PM
For those curious, this is the first book (that I am aware of) that utilizes a myriad of the growing "tidyverse," such as tidynetworks, tidymodels, and tidytext. Despite the name, it does not focus only on utilizing the tidy approach and deals with situations where base-R is more practical.
I'm looking for a co-author to re-work my tidyAML package
#GitHub github.com/spsanderson/...
#RStats #parsnip #tidymodels
Anyone interested?
#GitHub github.com/spsanderson/...
#RStats #parsnip #tidymodels
Anyone interested?
GitHub - spsanderson/tidyAML: Auto ML for the tidyverse
Auto ML for the tidyverse. Contribute to spsanderson/tidyAML development by creating an account on GitHub.
github.com
September 16, 2025 at 2:26 AM
I'm looking for a co-author to re-work my tidyAML package
#GitHub github.com/spsanderson/...
#RStats #parsnip #tidymodels
Anyone interested?
#GitHub github.com/spsanderson/...
#RStats #parsnip #tidymodels
Anyone interested?
In the past I've used the DALEX explain_tidymodels / model_parts as well (mainly from www.tmwr.org/explain).
From my (very limited) usage thus far of these new tidymodels packages, I'd say the biggest benefit is the easy tie in with feature selection recipe steps.
Certainly no need to change.
From my (very limited) usage thus far of these new tidymodels packages, I'd say the biggest benefit is the easy tie in with feature selection recipe steps.
Certainly no need to change.
September 12, 2025 at 7:51 PM
In the past I've used the DALEX explain_tidymodels / model_parts as well (mainly from www.tmwr.org/explain).
From my (very limited) usage thus far of these new tidymodels packages, I'd say the biggest benefit is the easy tie in with feature selection recipe steps.
Certainly no need to change.
From my (very limited) usage thus far of these new tidymodels packages, I'd say the biggest benefit is the easy tie in with feature selection recipe steps.
Certainly no need to change.
I use DALEX::model_parts or vip::vi_model (see link) that both support tidymodels nicely. Other than staying within tidymodels, any reason to prefer {important}?
Machine-Learning-foR-Psychologists/07 explain predictions/explain predictions.R at main · mattansb/Machine-Learning-foR-Psychologists
Lesson files used in the Machine Learning foR Psychologists - mattansb/Machine-Learning-foR-Psychologists
github.com
September 12, 2025 at 7:37 PM
I use DALEX::model_parts or vip::vi_model (see link) that both support tidymodels nicely. Other than staying within tidymodels, any reason to prefer {important}?
I'm all in on @topepo.bsky.social and co's new {important} and other variable importance/feature selection tools in tidymodels! #rstats
September 12, 2025 at 6:17 PM
I'm all in on @topepo.bsky.social and co's new {important} and other variable importance/feature selection tools in tidymodels! #rstats