Differences

This shows you the differences between two versions of the page.

--- programming_languages:r:parameter_description [2017/03/19 17:38] – phreazer
+++ programming_languages:r:parameter_description [2017/03/26 18:26] (current) – [dtw] phreazer
@@ Line 4: / Line 4: @@
 Issues:
-  * Documenting the possible entries is not easy, because a single model description already contains a lot of information. When many models must be described in help, the help page of the function becomes to large (in particular the parameter description part).
+  * Documenting the possible entries is not easy, because a single model description already contains a lot of information. When many models must be described in help, the help page of the function becomes too large (in particular the parameter description part).
   * The model description itself should be structured.
@@ Line 10: / Line 10: @@
 How is this problem solved by different popular packages?
+===== caret =====
+==== train method ====
+  method: a string specifying which classification or regression model
+          to use. Possible values are found using
+          ‘names(getModelInfo())’. See <URL:
+          http://topepo.github.io/caret/bytag.html>. A list of
+          functions can also be passed for a custom model function. See
+          <URL: http://topepo.github.io/caret/custom_models.html> for
+          details.
+  preProcess: a string vector that defines a pre-processing of the
+          predictor data. Current possibilities are "BoxCox",
+          "YeoJohnson", "expoTrans", "center", "scale", "range",
+          "knnImpute", "bagImpute", "medianImpute", "pca", "ica" and
+          "spatialSign". The default is no pre-processing. See
+          ‘preProcess’ and ‘trainControl’ on the procedures and how to
+          adjust them. Pre-processing code is only designed to work
+          when ‘x’ is a simple matrix or data frame.
+getModelInfo shows infos about models and packages that are accessible via ‘train’
+  Usage:
+     modelLookup(model = NULL)
+     checkInstall(pkg)
+     getModelInfo(model = NULL, regex = TRUE, ...)
+     ‘modelLookup’ is good for getting information related to the
+     tuning parameters for a model. ‘getModelInfo’ will return all the
+     functions and metadata associated with a model. Both of these
+     functions will only search within the models bundled in this
+     package.
+  Value:
+   ‘modelLookup’ produces a data frame with columns
+   model: a character string for the model code
+   parameter : the tuning parameter name
+   label : a tuning parameter label (used in plots)
+   forReg : a logical; can the model be used for regression?
+   forClass : a logical; can the model be used for classification?
+   probModel : a logical; does the model produce class probabilities?
+     ‘getModelInfo’ returns a list containing one or more lists of the
+     standard model information.
+Returned info from getModelInfo is a rather cryptic list.
+preProcess is a function which has it's own different method types. The methods are explained in the details section of the perProcess help page.
+trainControl is also a function, where different possible values for methods are listed, but not explained. Only hints which methods should be used under which circumstances.
+===== proxy =====
+  # summary of available distance measures
+  summary(pr_DB)
+  # particular info about one distance measure
+  pr_DB$get_entry("Jaccard")
+===== dtw =====
+  # directly print stepPattern (it's a class)
+  print(symmetric2)
+===== arules =====
+  object of class APparameter or named list.