merge pr #718: document elastic net regularization via mixture

Author: simonpcouch

R/linear_reg.R

@@ -17,10 +17,14 @@
 #'  model is `"lm"`.
 #' @param penalty A non-negative number representing the total
 #'  amount of regularization (specific engines only).
-#' @param mixture A number between zero and one (inclusive) that is the
-#'  proportion of L1 regularization (i.e. lasso) in the model. When
-#'  `mixture = 1`, it is a pure lasso model while `mixture = 0` indicates that
-#'  ridge regression is being used (specific engines only).
+#' @param mixture A number between zero and one (inclusive) denoting the
+#'  proportion of L1 regularization (i.e. lasso) in the model.
+#'
+#'  * `mixture = 1` specifies a pure lasso model,
+#'  * `mixture = 0`  specifies a ridge regression model, and
+#'  * `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
+#'
+#'  Available for specific engines only.
 #'
 #' @template spec-details
 #'

R/logistic_reg.R

@@ -20,11 +20,15 @@
 #'  For `keras` models, this corresponds to purely L2 regularization
 #'  (aka weight decay) while the other models can be either or a combination
 #'  of L1 and L2 (depending on the value of `mixture`).
-#' @param mixture A number between zero and one (inclusive) that is the
-#'  proportion of L1 regularization (i.e. lasso) in the model. When
-#'  `mixture = 1`, it is a pure lasso model while `mixture = 0` indicates that
-#'  ridge regression is being used. (specific engines only).
-#'  For `LiblineaR` models, `mixture` must be exactly 0 or 1 only.
+#' @param mixture A number between zero and one (inclusive) giving the
+#'  proportion of L1 regularization (i.e. lasso) in the model.
+#'
+#'  * `mixture = 1` specifies a pure lasso model,
+#'  * `mixture = 0`  specifies a ridge regression model, and
+#'  * `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
+#'
+#'  Available for specific engines only. For `LiblineaR` models, `mixture` must
+#'  be exactly 1 or 0 only.
 #'
 #' @template spec-details
 #'

R/multinom_reg.R

@@ -21,10 +21,14 @@
 #'  For `keras` models, this corresponds to purely L2 regularization
 #'  (aka weight decay) while the other models can be a combination
 #'  of L1 and L2 (depending on the value of `mixture`).
-#' @param mixture A number between zero and one (inclusive) that is the
-#'  proportion of L1 regularization (i.e. lasso) in the model. When
-#'  `mixture = 1`, it is a pure lasso model while `mixture = 0` indicates that
-#'  ridge regression is being used. (specific engines only).
+#' @param mixture A number between zero and one (inclusive) giving the
+#'  proportion of L1 regularization (i.e. lasso) in the model.
+#'
+#'  * `mixture = 1` specifies a pure lasso model,
+#'  * `mixture = 0`  specifies a ridge regression model, and
+#'  * `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
+#'
+#'  Available for specific engines only.
 #'
 #' @template spec-details
 #'

R/poisson_reg.R

@@ -15,10 +15,14 @@
 #'  The only possible value for this model is "regression".
 #' @param penalty A non-negative number representing the total
 #'  amount of regularization (`glmnet` only).
-#' @param mixture A number between zero and one (inclusive) that is the
-#'  proportion of L1 regularization (i.e. lasso) in the model. When
-#'  `mixture = 1`, it is a pure lasso model while `mixture = 0` indicates that
-#'  ridge regression is being used. (`glmnet` and `spark` only).
+#' @param mixture A number between zero and one (inclusive) giving the
+#'  proportion of L1 regularization (i.e. lasso) in the model.
+#'
+#'  * `mixture = 1` specifies a pure lasso model,
+#'  * `mixture = 0`  specifies a ridge regression model, and
+#'  * `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
+#'
+#'  Available for `glmnet` and `spark` only.
 #'
 #' @template spec-details
 #'

man/linear_reg.Rd

@@ -22,9 +22,11 @@ This model has `r nrow(param)` tuning parameters:
 param$item
 ```
 
-For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). 
+For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). As for `mixture`:
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package
 

man/logistic_reg.Rd

@@ -13,9 +13,11 @@ This model has 2 tuning parameters:
 
 - `mixture`: Proportion of Lasso Penalty (type: double, default: 0.0)
 
-For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). 
+For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). As for `mixture`:
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package
 

man/multinom_reg.Rd

@@ -22,9 +22,11 @@ This model has `r nrow(param)` tuning parameters:
 param$item
 ```
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details]. As for `mixture`:
 
-The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details].
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package
 

man/parsnip_update.Rd

@@ -13,9 +13,11 @@ This model has 2 tuning parameters:
 
 - `mixture`: Proportion of Lasso Penalty (type: double, default: 1.0)
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details]. As for `mixture`:
 
-The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details].
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package
 

man/poisson_reg.Rd

@@ -22,9 +22,11 @@ This model has `r nrow(param)` tuning parameters:
 param$item
 ```
 
-For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). 
+For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). As for `mixture`:
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package
 

man/proportional_hazards.Rd

@@ -13,9 +13,11 @@ This model has 2 tuning parameters:
 
 - `mixture`: Proportion of Lasso Penalty (type: double, default: 0.0)
 
-For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). 
+For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). As for `mixture`:
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package
 

man/rmd/linear_reg_spark.Rmd

@@ -22,9 +22,11 @@ This model has `r nrow(param)` tuning parameters:
 param$item
 ```
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details]. As for `mixture`:
 
-The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details].
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package
 

man/rmd/linear_reg_spark.md

@@ -13,9 +13,11 @@ This model has 2 tuning parameters:
 
 - `mixture`: Proportion of Lasso Penalty (type: double, default: 1.0)
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details]. As for `mixture`:
 
-The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details].
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package
 

man/rmd/logistic_reg_glmnet.Rmd

@@ -22,9 +22,11 @@ This model has `r nrow(param)` tuning parameters:
 param$item
 ```
 
-For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). 
+For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). As for `mixture`:
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package
 

man/rmd/logistic_reg_glmnet.md

@@ -13,9 +13,11 @@ This model has 2 tuning parameters:
 
 - `mixture`: Proportion of Lasso Penalty (type: double, default: 0.0)
 
-For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). 
+For `penalty`, the amount of regularization includes both the L1 penalty (i.e., lasso) and the L2 penalty (i.e., ridge or weight decay). As for `mixture`:
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package
 

man/rmd/logistic_reg_spark.Rmd

@@ -22,9 +22,11 @@ This model has `r nrow(param)` tuning parameters:
 param$item
 ```
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details]. As for `mixture`:
 
-The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details].
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package
 

man/rmd/logistic_reg_spark.md

@@ -13,9 +13,11 @@ This model has 2 tuning parameters:
 
 - `mixture`: Proportion of Lasso Penalty (type: double, default: 1.0)
 
-A value of `mixture = 1` corresponds to a pure lasso model, while `mixture = 0` indicates ridge regression.
+The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details]. As for `mixture`:
 
-The `penalty` parameter has no default and requires a single numeric value. For more details about this, and the `glmnet` model in general, see [glmnet-details].
+* `mixture = 1` specifies a pure lasso model,
+* `mixture = 0`  specifies a ridge regression model, and
+* `0 < mixture < 1` specifies an elastic net model, interpolating lasso and ridge.
 
 ## Translation from parsnip to the original package