RC 1.4.3

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: dials
 Title: Tools for Creating Tuning Parameter Values
-Version: 1.4.2.9001
+Version: 1.4.3
 Authors@R: c(
     person("Max", "Kuhn", , "max@posit.co", role = "aut"),
     person("Hannah", "Frick", , "hannah@posit.co", role = c("aut", "cre")),

NEWS.md

@@ -1,21 +1,25 @@
-# dials (development version)
+# dials 1.4.3
+
+## New parameters
 
 * `ordinal_link()` and `odds_link()` are two new parameters for the new `ordinal_reg()` models in parsnip (@corybrunson, #435).
 
-* A bug was fixed where some space-filling designs did not respect the `original` argument (#409).
+* `num_estimators()`, `softmax_temperature()`, `balance_probabilities()`, `average_before_softmax()`, and `training_set_limit()` are new parameters for the `tab_pfn()` model in parsnip (#412).
+
+## Other changes
 
-* Parameters were added for the `tab_pfn` model: `num_estimators()`, `softmax_temperature()`, `balance_probabilities()`, `average_before_softmax()`, and `training_set_limit()`.
+* `grid_space_filling()` now also respects the `original` argument when pre-made designs are available (#409).
 
 * `parameters()` and the `grid_*()` functions give more information in the error message when non-parameter objects are passed in (#437, #438).
 
-* Improved several type-checking error messages to include the actual type of the input (#423).
-
 * `encode_unit()` now provides a helpful error when `x` is not a parameter object (#430).
 
 * `value_validate()`, `value_transform()`, `value_inverse()`, and `value_set()` now produce more informative error messages when values contain unknowns (#445).
 
 * `value_validate()`, `encode_unit()`, `get_p()`, `get_log_p()`, `get_n()`, `get_n_frac()`, `get_n_frac_range()`, and `get_batch_sizes()` now enforce empty dots (#439).
 
+* Several further type-checking error messages now include the actual type of the input (#423).
+
 
 # dials 1.4.2
 

vignettes/dials.Rmd

@@ -30,7 +30,7 @@ In any case, some information is needed to create a grid or to validate whether
 
  * Create an easy to use framework for describing and querying tuning parameters. This can include getting sequences or random tuning values, validating current values, transforming parameters, and other tasks.
  * Standardize the names of different parameters. Different packages in R use different argument names for the same quantities. `dials` proposes some standardized names so that the user doesn't need to memorize the syntactical minutiae of every package. 
- * Work with the other [tidymodels](https://www.tidymodels.org) packages for modeling and machine learning using [tidyverse](https://www.tidyverse.org/) principles.
+ * Work with the other [tidymodels](https://www.tidymodels.org) packages for modeling and machine learning using [tidyverse](https://tidyverse.org/) principles.
 
 
 ## Parameter Objects