Max Kuhn
Max Kuhn
Adds some clarification and benchmark results to the parallel processing vignette. Once this is merged (and pkdown finishes), I'll never the version number to the dev value and commit to...
Tests were previously in `test-censored-reg.R`, `test-eval-time-args.R`, and `test-metric-args.R`. Moving them here will allow us to remove censored from being in Suggests for tune.
A helper file (and example) for caching expensive objects. This will enable us to have smaller `test_that({})` chunks with a smaller scope. - `is_object_available()` see if the object is cached....
When running knitr, a lot of messages are sent to the log file: ``` processing file: initial-data-splitting.qmd |...................................... | 80% [fig-ames-splitting] Inverted geom defaults of fill and color/colour. To change...
``` r ggdark::dark_theme_grey() #> Error in if (geoms_are_dark || force_geom_invert) {: missing value where TRUE/FALSE needed ``` Created on 2024-06-29 with [reprex v2.1.0](https://reprex.tidyverse.org) or maybe add ggplot2 as depends since...
I want to add some constraints to parameter sets to filter out some grid points based on user-defined constraints: - `mtry`
Maybe using [Poisson glms with an offset](https://github.com/topepo/caret/issues/861) with `rsample` and so on.
From [this post](https://community.rstudio.com/t/how-to-specify-a-column-to-be-unaffected-in-recipes/23056/6). ``` r library(dplyr, warn.conflicts = FALSE) library(recipes, warn.conflicts = FALSE) data % step_scale(pred1, pred2) %>% step_medianimpute(all_predictors()) rec_trained #> 1 -1.66 0.155 -0.484 0 1 #> 2 -0.0917...
If they can be used on future data. See [issue 15 from that package](https://github.com/markvanderloo/simputation/issues/15).
Same as tidymodels/tune#912 ``` r library(tidymodels) library(finetune) ``` ``` r set.seed(6735) folds % step_spline_natural(wt, deg_free = tune("wt")) lin_mod % set_engine("lm") spline_wflow passed: '' #> Optimizing rmse #> Initial best: 2.64170...