Hi!

I just wanted to contribute with this simple function to extract explained variance

extract_explained_variace <- function(pca_recipe, n_comp = NULL) {
if (!tune::is_recipe(pca_recipe)) {
stop("Input must be a recipe.")
} else {
pca_result <- pca_recipe %>%
prep() %>%
pluck("steps", 2, "res", "sdev") %>%
tibble(sdev = .) %>%
mutate(var_expl = round((sdev^2 / sum(sdev^2)) * 100, 3), .keep = "unused") %>%
rownames_to_column("PC") %>%
mutate(PC = paste0("PC", row_number()),
PC = factor(PC, levels = unique(PC)))
if (!is.null(n_comp)) {
pca_result <- pca_result %>%
slice(1:n_comp)
}
return(pca_result)
}
}

Thanks a lot for the amazing work done with tidymodels!

Best wishes!

The problem

When I run learnr::run_tutorial("pca_recipes", package = "learntidymodels"), I get the error:

Quitting from lines 13-80 (pca_recipes.Rmd) 
Error: package or namespace load failed for 'gradethis':
 .onLoad failed in loadNamespace() for 'gradethis', details:
  call: (function (exercise.cap = "Code", exercise.eval = FALSE, exercise.timelimit = 30, 
  error: unused argument (exercise.error.check.code = "gradethis_error_checker()")

Versions:

R itself is 4.0.4
{learnr} is 0.10.1
{learntidymodels} is 0.0.0.9001

I don't believe that the munging we have here in the learntidymodels package to order bars works anymore:

library(learntidymodels)
#> Loading required package: tidyverse
#> Loading required package: tidymodels
#> Registered S3 method overwritten by 'tune':
#>   method                   from   
#>   required_pkgs.model_spec parsnip
library(tidymodels)
library(ggplot2)

data("cells", package = "modeldata")

cell_pca <-
   recipe(class ~ ., data = cells %>% dplyr::select(-case)) %>%
   step_center(all_predictors()) %>%
   step_scale(all_predictors()) %>%
   step_pca(all_predictors())

cell_pca <- prep(cell_pca)

plot_top_loadings(cell_pca, grepl("ch_1", terms) & component_number <= 4, n = 10)

^{Created on 2021-08-25 by the reprex package (v2.0.1)}

I do have different versions of this type of functionality in tidytext, if we want to use that instead, but tidytext seems like a heavy and ridiculous dependency for this.

The master branch of this repository will soon be renamed to main, as part of a coordinated change across several GitHub organizations (including, but not limited to: tidyverse, r-lib, tidymodels, and sol-eng). We anticipate this will happen by the end of September 2021.

That will be preceded by a release of the usethis package, which will gain some functionality around detecting and adapting to a renamed default branch. There will also be a blog post at the time of this master --> main change.

The purpose of this issue is to:

• Help us firm up the list of targetted repositories
• Make sure all maintainers are aware of what's coming
• Give us an issue to close when the job is done
• Give us a place to put advice for collaborators re: how to adapt

message id: euphoric_snowdog