The recording of my talk on "Using {tidymodels} to Detect Heart Murmurs" from the R/Medicine Conference is now available on the @RConsortium YouTube channel! 📹📹📹

https://youtu.be/xyxbhLb_aEs

#RStats #HealthDataScience #Tidymodels

#rstats hive mind, looking for some help understanding recipes. I’m trying to update a custom step function to account for terms_select being deprecated. The error references recipes_eval_select as the suggested replacement, but I can’t figure out where to sub it in. Any help or resources would be greatly appreciated #tidymodels #r

Is it possible to use the #r package #infer from #tidymodels to perform a repeated-measures ANOVA? I would like to compare the grades of students (response) that took a series of 9 quizzes (repeated-measure) and belonged to one of 3 treatment groups (explanatory).

Pull a formula from a recipe in R, sure thing!

#DataPreprocessing #DataRecipes #RProgramming #DataScience #FormulaFunction #r #rstats #technology #innovation #opensource #opensourcesoftware #opensourcecommunity #recipes #tidymodels #formula

Post: https://www.spsanderson.com/steveondata/posts/2023-06-14/

Starting to mix #tidymodels with #targets for the first time in #rstats... I'm interested to hear tips from anyone who's trodden this path before.

It seems that the tidymodels idea of making a large specification which is evaluated late in one large computation is kind of at odds with the value targets brings to caching intermediate steps?

May posit::glimpse() newsletter

https://posit.co/blog/posit-glimpse-newsletter-06/

💬AI chat apps with Shiny
🎉Quarto 1.3 release
✨Shiny on Hugging Face
🌳RStudio on Amazon SageMaker
🌞Join us for posit::conf()
🙌Updates for gt, pins, #tidymodels, Connect & more!

#huggingface #tidyverse #rstats #ai #shiny #pydata #python

All the #tidymodels you could want to read about!
(from the last three months)

📦 24 CRAN releases of tidymodels packages
❎ More informative errors
🏃‍♀️Things are getting faster

Tidymodels Q1 Roundup blog post from @emilhvitfeldt

https://www.tidyverse.org/blog/2023/04/tidymodels-2023-q1/

#RStats

After a cascade of new #rstats package versions, we also have a new version of the #tidymodels meta-package out today:

https://tidymodels.tidymodels.org

Are you interested in building machine learning models in R, but not sure where to start? Look no further than the tidymodels package! In this post, we'll break down a simple code example that demonstrates how to build a linear regression model using tidymodels.

Post: https://www.spsanderson.com/steveondata/posts/rtip-2023-05-01/

#tidymodels #tidyverse #r #rstats #datamodeling #datascientist #workflows #parsnip #extract #opensource

The #tidymodels team has been busy this quarter with 24 new #rstats CRAN releases!
This Q1 roundup blog post highlights some new changes regarding errors and performance
https://www.tidyverse.org/blog/2023/04/tidymodels-2023-q1/

Here is post Part 3 for the tidyAML shiny app. I have added funcitonality for selecting a parsnip function. When I say parsnip function what I mean is something like linear_reg()

Post: https://www.spsanderson.com/steveondata/posts/rtip-2023-04-27/

#tidymodels #tidyaml #r #rstats #parsnip #tidy #opensource #shiny #opensourcesoftware #software #technology #innovation #regresion #linear #bonsai #ranger #randomforest #gee #lm

Made some updates to yesterdays shiny app building models with tidyAML

Post: https://www.spsanderson.com/steveondata/posts/rtip-2023-04-26/

#tidymodels #parsnip #tidyaml #aml #ml #reactable #shiny #r #rstats #opensource #opensourcesoftware #opensourcecommunity #technology #innovation #data #datascientist #machinelearning

Introducing tidyAML Model Builder, a new Shiny app

✅ User-friendly interface
✅ Automated data normalization
✅ Fast model building
✅ Interactive model inspection

#machinelearning #datascience #tidyverse #Rstats #r #tidymodels #tidy #shiny #building #technology #innovation #blogpost #github #code #opensource #opensourcecommunity

Post: https://www.spsanderson.com/steveondata/posts/rtip-2023-04-25/

tidyAML: https://www.spsanderson.com/tidyAML/

We’re back with our newsletter!

https://posit.co/blog/posit-glimpse-newsletter-05/

posit::glimpse() is the same glimpse of our tools and how to use them, but now with our new name.

In this edition: Learn how to position text and images in Shiny apps, work on your data science compositions in Quarto, transpose data with tidyverse, & work with teams in R and Python.

We posit you’ll find something useful, and positive you’ll learn something new!

#rstats #python #quartopub #tidyverse #tidymodels

Sometimes we want to look at a #bootstrapping #model and we can easily achieve this in #r even in #timeseries #modeling with the #forecast #package

In this post I used the AirPassengers dataset and used the auto.arima() function to bootstrap models, then I wanted to take a look at the residuals.

This is not comprehensive but sheds some light on how to do this outside of the #tidymodels #framework

Post: https://lnkd.in/gwjMfezH

#rstats #r #arima #opensource #software #autoarima

#RStats issues I'm struggling with that seem impossible to Google: Building a {brms} model within the {tidymodels} framework using {bayesian}.

The formula is inherently too complex (including splines and random effects) for the typical tidymodels workflow that involves recipes &c., so it must be added in at a later step. Two things:

1. Complex {brms} multivariate formulas seem to not be possible using {tidymodels}. E.g., literally multivariate or including phi after my formula via brms::bf(). It simply errors. :( This may just need some tweaking of {bayesian}'s scripts or waiting for an update since it's still fairly young.

2. Using {mgcv} random effect syntax like s(cat1, cat2, bs = "re") seems to not pick up as random effects in the model...I think? And I have never figured out if this is creating hierarchical random effects or not -- or if multilevel random effects just aren't possible in this syntax(?).

3. Using {lme4} random effect like (1 | cat1 / cat2) to ensure the hierarchy is preserved *does* retain random effects I can pull out of the model later using `ranef`, but for some absurd reason I cannot run this model through cross-validation or a myriad of other steps later because it seems to force-create a complex web of interacting factor levels that don't exist. E.g., if my random effects are '(1 | realm / biome)', this eventually fails because it'll look for tundra biome types in Africa for some absurd reason.*

Noticed this while trying to solve *separate* issues within broom.mixed:::tidy.brmsfit() -- that it seems to delete the names of all the fixed effects and return them as 'NULL' character strings (???), and its reliance on 'ranef' means it doesn't find the random effects using {mgcv} syntax.

That's my rambling mess of an essay for the day. Not sure how many of these are real issues or me simply not understanding how these packages differ or wot.

#brms #mgcv #tidymodels

* Almost wondering if this might even be a separate {tidymodels} issue right now. Every recipe no matter what seems to factor every single character column regardless of how the recipe is built. Hmmmm.

Has someone experienced this same trouble installing bonsai? #tidymodels #rstats
https://stackoverflow.com/questions/75817180/bonsai-r-package-installation-problem-in-windows

Discover what makes posit::conf(2023) special from four organizers' perspectives.
https://posit.co/blog/posit-2023-through-our-eyes/

#positconf2023 #rstats #pydata #tidyverse #tidymodels #vetiver #rmarkdown #RShiny #quarto

With R's Infer library, one can test point hypotheses, such as "the work week has 40 hours".

I think this is a great improvement on testing point null hypotheses of no difference, which we know a priori to be false.

https://infer.netlify.app/

#rstats #statistics part of #tidymodels and #tidydata

🚀 Benchmarking autoML: https://arxiv.org/pdf/2207.12560.pdf

🚀 {agua}: https://agua.tidymodels.org (H2O in #tidymodels)

🚀 H2O Wave: https://wave.h2o.ai/docs/getting-started (a software stack to build browser-based applications; if some Python developers love to contribute - feel free to reach out to Erin)

🚀 ... And more resources are in the screenshot 🤗