merge upstream

Merge branch 'main' into spark-1045

# Conflicts:
#	NEWS.md

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: parsnip
 Title: A Common API to Modeling and Analysis Functions
-Version: 1.1.1.9003
+Version: 1.1.1.9007
 Authors@R: c(
     person("Max", "Kuhn", , "[email protected]", role = c("aut", "cre")),
     person("Davis", "Vaughan", , "[email protected]", role = "aut"),
@@ -76,4 +76,4 @@ Config/testthat/edition: 3
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.3.9000
+RoxygenNote: 7.2.3

NAMESPACE

@@ -2,7 +2,6 @@
 
 S3method(.censoring_weights_graf,default)
 S3method(.censoring_weights_graf,model_fit)
-S3method(.censoring_weights_graf,workflow)
 S3method(augment,model_fit)
 S3method(autoplot,glmnet)
 S3method(autoplot,model_fit)
@@ -179,6 +178,7 @@ export(bag_tree)
 export(bart)
 export(bartMachine_interval_calc)
 export(boost_tree)
+export(case_weights_allowed)
 export(cforest_train)
 export(check_empty_ellipse)
 export(check_final_param)

NEWS.md

@@ -2,6 +2,8 @@
 
 * Fixed bug in fitting some model types with the `"spark"` engine (#1045).
 
+* `.filter_eval_time()` was moved to the survival standalone file. 
+
 * Improved errors and documentation related to special terms in formulas. See `?model_formula` to learn more. (#770, #1014)
 
 * Improved errors in cases where the outcome column is mis-specified. (#1003)
@@ -12,6 +14,10 @@
 
 * When computing censoring weights, the resulting vectors are no longer named (#1023).
 
+* Fixed a bug in the integration with workflows where using a model formula with a formula preprocessor could result in a double intercept (#1033).
+
+* The `predict()` method for `censoring_model_reverse_km` objects now checks that `...` are empty (#1029).
+
 # parsnip 1.1.1
 
 * Fixed bug where prediction on rank deficient `lm()` models produced `.pred_res` instead of `.pred`. (#985)

R/bag_tree.R

@@ -10,6 +10,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
+#' @inheritParams boost_tree
 #' @inheritParams decision_tree
 #' @param class_cost A non-negative scalar for a class cost (where a cost of 1
 #' means no extra cost). This is useful for when the first level of the outcome

R/bart.R

@@ -11,6 +11,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
+#' @inheritParams nearest_neighbor
 #' @inheritParams boost_tree
 #' @param prior_terminal_node_coef A coefficient for the prior probability that
 #' a node is a terminal node. Values are usually between 0 and one with

R/boost_tree.R

@@ -15,8 +15,8 @@
 #' \url{https://www.tidymodels.org/}.
 #'
 #' @param mode A single character string for the prediction outcome mode.
-#'  Possible values for this model are "unknown", "regression", or
-#'  "classification".
+#'  Possible values for this model are "unknown", "regression",
+#'  "classification", or "censored regression".
 #' @param engine A single character string specifying what computational engine
 #'  to use for fitting.
 #' @param mtry A number for the number (or proportion) of predictors that will

R/c5_rules.R

@@ -13,7 +13,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @param mode A single character string for the type of model.
 #'  The only possible value for this model is "classification".
 #' @param trees A non-negative integer (no greater than 100) for the number

R/case_weights.R

@@ -67,6 +67,17 @@ patch_formula_environment_with_case_weights <- function(formula,
 
 # ------------------------------------------------------------------------------
 
+#' Determine if case weights are used
+#'
+#' Not all modeling engines can incorporate case weights into their
+#' calculations. This function can determine whether they can be used.
+#'
+#' @param spec A parsnip model specification.
+#' @return A single logical.
+#' @examples
+#' case_weights_allowed(linear_reg())
+#' case_weights_allowed(linear_reg(engine = "keras"))
+#' @export
 case_weights_allowed <- function(spec) {
   mod_type <- class(spec)[1]
   mod_eng <- spec$engine

R/convert_data.R

@@ -45,6 +45,10 @@
     rlang::abort("`composition` should be either 'data.frame' or 'matrix'.")
   }
 
+  if (remove_intercept) {
+    data <- data[, colnames(data) != "(Intercept)", drop = FALSE]
+  }
+
   ## Assemble model.frame call from call arguments
   mf_call <- quote(model.frame(formula, data))
   mf_call$na.action <- match.call()$na.action # TODO this should work better

R/cubist_rules.R

@@ -10,7 +10,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @param mode A single character string for the type of model.
 #'  The only possible value for this model is "regression".
 #' @param committees A non-negative integer (no greater than 100) for the number

R/discrim_flexible.R

@@ -11,7 +11,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @inheritParams discrim_linear
 #' @param num_terms The number of features that will be retained in the
 #'    final model, including the intercept.

R/discrim_linear.R

@@ -13,7 +13,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @param mode A single character string for the type of model. The only
 #'  possible value for this model is "classification".
 #' @param penalty An non-negative number representing the amount of

R/discrim_quad.R

@@ -13,7 +13,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @param mode A single character string for the type of model. The only
 #'  possible value for this model is "classification".
 #' @param regularization_method A character string for the type of regularized

R/discrim_regularized.R

@@ -13,7 +13,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @inheritParams discrim_linear
 #' @param frac_common_cov,frac_identity Numeric values between zero and one.
 #'

R/fit_helpers.R

@@ -8,6 +8,15 @@ form_form <-
 
     if (inherits(env$data, "data.frame")) {
       check_outcome(eval_tidy(rlang::f_lhs(env$formula), env$data), object)
+
+      encoding_info <-
+        get_encoding(class(object)[1]) %>%
+        dplyr::filter(mode == object$mode, engine == object$engine)
+
+      remove_intercept <- encoding_info %>% dplyr::pull(remove_intercept)
+      if (remove_intercept) {
+        env$data <- env$data[, colnames(env$data) != "(Intercept)", drop = FALSE]
+      }
     }
 
     # prob rewrite this as simple subset/levels

R/gen_additive_mod.R

@@ -10,7 +10,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @param select_features `TRUE` or `FALSE.` If `TRUE`, the model has the
 #'  ability to eliminate a predictor (via penalization). Increasing
 #'  `adjust_deg_free` will increase the likelihood of removing predictors.

R/mars.R

@@ -12,7 +12,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @param num_terms The number of features that will be retained in the
 #'    final model, including the intercept.
 #' @param prod_degree The highest possible interaction degree.

R/mlp.R

@@ -10,6 +10,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
+#' @inheritParams nearest_neighbor
 #' @inheritParams boost_tree
 #' @param hidden_units An integer for the number of units in the hidden model.
 #' @param penalty A non-negative numeric value for the amount of weight

R/naive_Bayes.R

@@ -11,7 +11,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @inheritParams discrim_linear
 #' @param smoothness An non-negative number representing the the relative
 #'  smoothness of the class boundary. Smaller examples result in model flexible

R/nearest_neighbor.R

@@ -11,7 +11,11 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @param mode A single character string for the prediction outcome mode.
+#'  Possible values for this model are "unknown", "regression", or
+#'  "classification".
+#' @param engine A single character string specifying what computational engine
+#'  to use for fitting.
 #' @param neighbors A single integer for the number of neighbors
 #' to consider (often called `k`). For \pkg{kknn}, a value of 5
 #' is used if `neighbors` is not specified.

R/pls.R

@@ -10,7 +10,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @param predictor_prop The maximum proportion of original predictors that can
 #'  have _non-zero_ coefficients for each PLS component (via regularization).
 #'  This value is used for all PLS components for X.

R/poisson_reg.R

@@ -10,7 +10,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @param mode A single character string for the type of model.
 #'  The only possible value for this model is "regression".
 #' @param penalty A non-negative number representing the total

R/proportional_hazards.R

@@ -10,7 +10,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
-#' @inheritParams boost_tree
+#' @inheritParams nearest_neighbor
 #' @inheritParams linear_reg
 #' @param mode A single character string for the prediction outcome mode.
 #'  The only possible value for this model is "censored regression".

R/rule_fit.R

@@ -10,6 +10,7 @@
 #' More information on how \pkg{parsnip} is used for modeling is at
 #' \url{https://www.tidymodels.org/}.
 #'
+#' @inheritParams nearest_neighbor
 #' @inheritParams boost_tree
 #' @param penalty L1 regularization parameter.
 #' @details