Added "Predict type" section to each model type documentation.

man/rmd/.gitignore

@@ -0,0 +1,2 @@
+/.quarto/
+**/*.quarto_ipynb

man/rmd/C5_rules_C5.0.Rmd

@@ -60,6 +60,16 @@ C5_rules(
 #| child: template-uses-case-weights.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("C5_rules_predict") |>
+  dplyr::select(mode, type)
+
+```
+
 ## Saving fitted model objects
 
 ```{r}

man/rmd/auto_ml_h2o.Rmd

@@ -23,9 +23,12 @@ Engine arguments of interest
 
 ```{r}
 #| label: h2o-reg
-auto_ml() |>  
-  set_engine("h2o") |> 
-  set_mode("regression") |> 
+
+library(agua)
+
+auto_ml() |>
+  set_engine("h2o") |>
+  set_mode("regression") |>
   translate()
 ```
 
@@ -52,6 +55,16 @@ auto_ml() |>
 #| child: template-h2o-init.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("auto_ml_predict") |>
+  dplyr::select(mode, type)
+
+```
+
 ## Saving fitted model objects
 
 ```{r}

man/rmd/bag_mars_earth.Rmd

@@ -75,6 +75,16 @@ bag_mars(
 
 Note that the `earth` package documentation has: "In the current implementation, _building models with weights can be slow_."
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("bag_mars_predict") |>
+  dplyr::select(mode, type)
+
+```
+
 ## References
 
  - Breiman, L. 1996. "Bagging predictors". Machine Learning. 24 (2): 123-140

man/rmd/bag_mlp_nnet.Rmd

@@ -78,6 +78,16 @@ bag_mlp(penalty = double(1), hidden_units = integer(1)) |>
 #| child: template-no-case-weights.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("bag_mlp_predict") |>
+  dplyr::select(mode, type)
+
+```
+
 
 ## References
 

man/rmd/bag_tree_C5.0.Rmd

@@ -56,6 +56,16 @@ bag_tree(min_n = integer()) |>
 #| child: template-uses-case-weights.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("bag_mars_predict") |>
+  dplyr::filter(engine == "C5.0") |>
+  dplyr::select(mode, type)
+
+```
 
 ## References
 

man/rmd/bag_tree_rpart.Rmd

@@ -89,6 +89,17 @@ bag_tree(tree_depth = integer(1), min_n = integer(1), cost_complexity = double(1
 #| child: template-uses-case-weights.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("bag_mars_predict") |>
+  dplyr::filter(engine == "rpart") |>
+  dplyr::select(mode, type)
+
+```
+
 ## Other details
 
 ```{r}

man/rmd/bart_dbarts.Rmd

@@ -93,6 +93,15 @@ parsnip::bart(
 
 [dbarts::bart()] will also convert the factors to indicators if the user does not create them first. 
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("bart_predict") |>
+  dplyr::select(mode, type)
+
+```
 
 ## References
 

man/rmd/boost_tree_C5.0.Rmd

@@ -56,6 +56,17 @@ boost_tree(trees = integer(), min_n = integer(), sample_size = numeric()) |>
 #| child: template-uses-case-weights.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("boost_tree_predict") |>
+  dplyr::filter(engine == "C5.0") |>
+  dplyr::select(mode, type)
+
+```
+
 ## Saving fitted model objects
 
 ```{r}

man/rmd/boost_tree_h2o.Rmd

@@ -82,6 +82,17 @@ Non-numeric predictors (i.e., factors) are internally converted to numeric. In t
 #| child: template-mtry-prop.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("boost_tree_predict") |>
+  dplyr::filter(stringr::(str_starts(engine, "h2o"))) |>
+  dplyr::select(mode, type)
+
+```
+
 ## Initializing h2o 
 
 ```{r}

man/rmd/boost_tree_lightgbm.Rmd

@@ -85,6 +85,17 @@ Non-numeric predictors (i.e., factors) are internally converted to numeric. In t
 #| child: template-mtry-prop.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("boost_tree_predict") |>
+  dplyr::filter(engine == "lightgbm") |>
+  dplyr::select(mode, type)
+
+```
+
 ### Bagging
 
 The `sample_size` argument is translated to the `bagging_fraction` parameter in the `param` argument of `lgb.train`. The argument is interpreted by lightgbm as a _proportion_ rather than a count, so bonsai internally reparameterizes the `sample_size` argument with [dials::sample_prop()] during tuning. 

man/rmd/boost_tree_mboost.Rmd

@@ -54,6 +54,17 @@ boost_tree() |>
 #| child: template-tree-split-factors.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("boost_tree_predict") |>
+  dplyr::filter(engine == "mboost") |>
+  dplyr::select(mode, type)
+
+```
+
 ## Other details
 
 ```{r}

man/rmd/boost_tree_spark.Rmd

@@ -73,6 +73,17 @@ boost_tree(
 
 Note that, for spark engines, the `case_weight` argument value should be a character string to specify the column with the numeric case weights. 
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("boost_tree_predict") |>
+  dplyr::filter(engine == "spark") |>
+  dplyr::select(mode, type)
+
+```
+
 ## Other details
 
 ```{r}

man/rmd/boost_tree_xgboost.Rmd

@@ -75,6 +75,17 @@ For classification, non-numeric outcomes (i.e., factors) are internally converte
 #| child: template-uses-case-weights.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("boost_tree_predict") |>
+  dplyr::filter(engine == "xgboost") |>
+  dplyr::select(mode, type)
+
+```
+
 ## Sparse Data
 
 ```{r}

man/rmd/cubist_rules_Cubist.Rmd

@@ -54,6 +54,16 @@ cubist_rules(
 #| child: template-tree-split-factors.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("cubist_rules_predict") |>
+  dplyr::select(mode, type)
+
+```
+
 ## References
 
  - Quinlan R (1992). "Learning with Continuous Classes." Proceedings of the 5th Australian Joint Conference On Artificial Intelligence, pp. 343-348.

man/rmd/decision_tree_C5.0.Rmd

@@ -54,6 +54,17 @@ decision_tree(min_n = integer()) |>
 #| child: template-uses-case-weights.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("decision_tree_predict") |>
+  dplyr::filter(engine == "C5.0") |>
+  dplyr::select(mode, type)
+
+```
+
 ## Saving fitted model objects
 
 ```{r}

man/rmd/decision_tree_partykit.Rmd

@@ -89,6 +89,17 @@ decision_tree(tree_depth = integer(1), min_n = integer(1)) |>
 #| child: template-tree-split-factors.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("decision_tree_predict") |>
+  dplyr::filter(engine == "partykit") |>
+  dplyr::select(mode, type)
+
+```
+
 ## Other details
 
 ```{r}

man/rmd/decision_tree_rpart.Rmd

@@ -82,6 +82,17 @@ decision_tree(
 #| child: template-uses-case-weights.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("decision_tree_predict") |>
+  dplyr::filter(engine == "rpart") |>
+  dplyr::select(mode, type)
+
+```
+
 ## Other details
 
 ```{r}

man/rmd/decision_tree_spark.Rmd

@@ -65,6 +65,17 @@ decision_tree(tree_depth = integer(1), min_n = integer(1)) |>
 
 Note that, for spark engines, the `case_weight` argument value should be a character string to specify the column with the numeric case weights. 
 
+
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("decision_tree_predict") |>
+  dplyr::filter(engine == "spark") |>
+  dplyr::select(mode, type)
+
+```
 ## Other details
 
 ```{r}

man/rmd/discrim_flexible_earth.Rmd

@@ -59,6 +59,16 @@ discrim_flexible(
 #| child: template-uses-case-weights.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("discrim_flexible_predict") |>
+  dplyr::select(mode, type)
+
+```
+
 ## References
 
  - Hastie, Tibshirani & Buja (1994) Flexible Discriminant Analysis by Optimal 

man/rmd/discrim_linear_MASS.Rmd

@@ -38,6 +38,17 @@ discrim_linear() |>
 #| child: template-no-case-weights.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("discrim_linear_predict") |>
+  dplyr::filter(engine == "MASS") |>
+  dplyr::select(mode, type)
+
+```
+
 ## References
 
  - Kuhn, M, and K Johnson. 2013. _Applied Predictive Modeling_. Springer.

man/rmd/discrim_linear_mda.Rmd

@@ -59,6 +59,17 @@ discrim_linear(penalty = numeric(0)) |>
 #| child: template-uses-case-weights.Rmd
 ```
 
+## Prediction types
+
+```{r}
+#| label: predict-types
+
+parsnip:::get_from_env("discrim_linear_predict") |>
+  dplyr::filter(engine == "mda") |>
+  dplyr::select(mode, type)
+
+```
+
 ## References
 
  - Hastie, Tibshirani & Buja (1994) Flexible Discriminant Analysis by Optimal