brms_rstan: windows testing, index, author

Author: falkmielke

content/tutorials/r_brms/brms_eng/workshop_1_mcmc_en_brms_eng.Rmd

@@ -36,6 +36,7 @@ library(tidybayes) # wrangling and visualising Bayesian models
 # Conflicten tussen packages
 conflicted::conflicts_prefer(dplyr::filter)
 conflicted::conflicts_prefer(dplyr::lag)
+conflicted::conflicts_prefer(tidyr::extract)
 conflicted::conflicts_prefer(brms::ar)
 conflicted::conflicts_prefer(brms::dstudent_t)
 conflicted::conflicts_prefer(brms::pstudent_t)
@@ -716,7 +717,7 @@ as_draws_df(fit_normal1, variable = parameters) %>%
   pivot_longer(cols = starts_with(parameters), names_to = "name",
                values_to = "value") %>%
   # split columns names at the last underscore
-  extract(name, into = c("parameter", "statistic"), "(.*)_([^_]+)$") %>%
+  tidyr::extract(name, into = c("parameter", "statistic"), "(.*)_([^_]+)$") %>%
   ggplot(aes(y = value, x = .iteration, colour = factor(.chain))) +
     geom_line(aes(linetype = statistic), linewidth = 0.8) +
     facet_wrap(~parameter, nrow = 3, scales = "free")
@@ -1087,10 +1088,12 @@ conflicted::conflicts_prefer(brms::loo)
 
 ### Model Definition
 RMarkdown can handle `stan` code chunks, though more general model definition is outsourced to a separate "*.stan" file.
+Alternatively, you can define your model in a big text block, as shown below.
 The simple poisson model resembles [one of the `stan`-dard examples](https://mc-stan.org/docs/stan-users-guide/posterior-prediction.html#posterior-prediction-for-regressions), which you can refer to for all further details and more.
 
 
-```{stan, output.var="stan_poisson_model", class.source='fold-show'}
+```{r stan_poisson_simple, eval=TRUE, output.var="", class.source='fold-show'}
+stan_poisson_model_code = '
 data {
   int<lower=1> N;                   // sample size
   vector[N] habitat_obs;            // habitat
@@ -1112,7 +1115,7 @@ model {
 
 }
 
-
+'
 ```
 
 
@@ -1123,9 +1126,10 @@ Yet note how even Stan is not without convenience functions: we can use the `poi
 
 When working outside RStudio/RMarkdown, you might prefer loading the model from a file:
 
-```{r stan_load_model, eval=FALSE, class.source='fold-show'}
+```{r stan_load_model, eval=TRUE, class.source='fold-show'}
 stan_poisson_model <- stan_model(
-  file = "./poisson_model.stan",
+  # file = "./poisson_model.stan",
+  model_code = stan_poisson_model_code, 
   model_name = "stan poisson model"
   )
 ```

content/tutorials/r_brms/brms_nl/workshop_1_mcmc_en_brms.Rmd

@@ -35,6 +35,7 @@ library(tidybayes) # nabewerking en visualisatie van Bayesiaanse modellen
 # Conflicten tussen packages
 conflicted::conflicts_prefer(dplyr::filter)
 conflicted::conflicts_prefer(dplyr::lag)
+conflicted::conflicts_prefer(tidyr::extract)
 conflicted::conflicts_prefer(brms::ar)
 conflicted::conflicts_prefer(brms::dstudent_t)
 conflicted::conflicts_prefer(brms::pstudent_t)
@@ -705,7 +706,7 @@ as_draws_df(fit_normal1, variable = parameters) %>%
   pivot_longer(cols = starts_with(parameters), names_to = "name",
                values_to = "value") %>%
   # splits naam kolom op bij laatste underscore
-  extract(name, into = c("parameter", "statistiek"), "(.*)_([^_]+)$") %>%
+  tidyr::extract(name, into = c("parameter", "statistiek"), "(.*)_([^_]+)$") %>%
   ggplot(aes(y = value, x = .iteration, colour = factor(.chain))) +
     geom_line(aes(linetype = statistiek), linewidth = 0.8) +
     facet_wrap(~parameter, nrow = 3, scales = "free")
@@ -1079,9 +1080,12 @@ conflicted::conflicts_prefer(brms::loo)
 The simple poisson model resembles [one of the `stan`dard examples](https://mc-stan.org/docs/stan-users-guide/posterior-prediction.html#posterior-prediction-for-regressions), which you can refer to for all further details and more.
 
 RMarkdown kan `stan`-chunks verwerken, hoewel de algemenere modeldefinitie is uitbesteed aan een apart "*.stan"-bestand.
+Alternatief kan je je model ook als grote tekstblok definiëren, zoals hieronder te zien.
 Het eenvoudige poissonmodel lijkt op [een van de `stan`-daardvoorbeelden](https://mc-stan.org/docs/stan-users-guide/posterior-prediction.html#posterior-prediction-for-regressions), waarnaar u terecht kunt voor verdere details en meer.
 
-```{stan, output.var="stan_poisson_model", class.source='fold-show'}
+
+```{r stan_poisson_simple, eval=TRUE, output.var="", class.source='fold-show'}
+stan_poisson_model_code = '
 data {
   int<lower=1> N;                   // sample size
   vector[N] habitat_obs;            // habitat
@@ -1103,19 +1107,21 @@ model {
 
 }
 
-
+'
 ```
 
 
+
 Zie dit als een "kijkje achter de schermen"!
 Je moet expliciet de modelstructuur, priors en zelfs de gegevenstypen van invoervariabelen definiëren.
 Maar let op hoe zelfs Stan niet zonder handige functies is: we kunnen de `poisson_log` posterior gebruiken om de $log(\lambda )$ te modelleren.
 
 Als je buiten RStudio/RMarkdown werkt, kun je het model het beste laden vanuit een bestand:
 
-```{r stan_load_model, eval=FALSE, class.source='fold-show'}
+```{r stan_load_model, eval=TRUE, class.source='fold-show'}
 stan_poisson_model <- stan_model(
-  file = "./poisson_model.stan",
+  # file = "./poisson_model.stan",
+  model_code = stan_poisson_model_code, 
   model_name = "stan poisson model"
   )
 ```

content/tutorials/r_brms/index.md

@@ -1,15 +1,17 @@
 ---
 title: "Tutorial Bayesian statistics with brms"
 description: "This tutorial starts with a theoretical overview of bayesian statistics and the MCMC algorithm. Next, we fit, check, and analyse Bayesian models with the brms package."
-author: [raisacarmen, wardlangeraert, toonvandaele]
+author: [raisacarmen, wardlangeraert, toonvandaele, falkmielke]
 date: 2024-01-02
 categories: ["r", "statistics"]
-tags: ["generalized linear regression", "brms", "r", "mixed models"]
+tags: ["generalized linear regression", "brms", "r", "mixed models", "stan"]
 ---
 
 In the fall of 2023, a tutorial on Bayesian statistics with the [**brms**](https://paul-buerkner.github.io/brms/) packages was organised at INBO.
 Before you start the tutorial, please follow the instructions in [this R script](https://github.com/inbo/tutorials/blob/master/content/tutorials/r_brms/brms_eng/install_packages.R) to install brms properly.
+For more advanced use cases, we added an example of how to directly use [**stan**](https://mc-stan.org) via the `rstan` package.
 All course material can be found in Dutch and English on the following pages:
 
 - The [English tutorial](../../html/workshop_1_mcmc_en_brms_eng.html) with all [course material](https://github.com/inbo/tutorials/tree/master/content/tutorials/r_brms/brms_eng) to test the examples yourself.
 - The [Dutch tutorial](../../html/workshop_1_mcmc_en_brms.html) with all [course material](https://github.com/inbo/tutorials/tree/master/content/tutorials/r_brms/brms_nl) to test the examples yourself.
+

data/authors/falkmielke.toml

@@ -0,0 +1,13 @@
+id = "falkmielke"
+
+[email]
+username = ""
+host = ""
+
+[name]
+display = "Falk Mielke"
+
+[social]
+email = ""
+facebook  = ""
+twitter = ""