Work/wCBA.R

In ianjjohnson/arulesCBA: Classification Based on Association Rules

#' Classification Based on Association Rules
#'
#' Build a classifier using a naive rule-weighting algorithm.  The algorithm is
#' currently in development, and is not yet formally documented.
#'
#' Mines association rules on input data and creates a weighted-vote classifier
#' where a rules weight is the product of its support and confidence.  Default
#' class is set to the most common class in the training data.
#'
#' @aliases wCBA wcba
#' @param formula A symbolic description of the model to be fitted. Has to be
#' of form \code{class ~ .}. The class is the variable name (part of the item
#' label before \code{=}).
#' @param data A data.frame containing the training data.
#' @param parameter,control Optional parameter and control lists for apriori.
#' @param sort.parameter Ordered vector of arules interest measures (as
#' characters) which are used to sort rules in preprocessing.
#' @param lhs.support Logical variable, which, when set to default value of
#' True, indicates that LHS support should be used for rule mining.
#' @param class.weights Weights that should be assigned to the rows of each
#' class (ordered by appearance in levels(classColumn))
#' @param disc.method Discretization method for factorizing numeric input
#' (default: \code{"mdlp"}). See \code{\link{discretizeDF.supervised}} for more
#' supervised discretization methods.
#' @param verbose Optional logical flag to allow verbose execution, where
#' additional intermediary execution information is printed at runtime.
#' @param ... Additional parameters are added to the apriori parameters (e.g.,
#' support and confidence).
#' @return Returns an object of class \code{CBA} representing the trained
#' classifier with fields: \item{rules}{the classifier rule base.}
#' \item{default}{default class label.} \item{levels}{levels of the class
#' variable.}
#' @author Ian Johnson
#' @seealso \code{\link{predict.CBA}}, \code{\link{CBA.object}},
#' \code{\link[arules]{apriori}},
#' @examples
#'
#' data("iris")
#'
#' classifier <- wCBA(Species ~ ., data = iris, supp = 0.05, conf = 0.9)
#' classifier
#'
#' predict(classifier, head(iris))
#'
wCBA <- function(formula, data,
  parameter = NULL, control = NULL, sort.parameter = NULL, lhs.support=FALSE, class.weights=NULL,
	disc.method = "mdlp", verbose=FALSE, ...){

    return(CBA.internal(formula, data, method="weighted", verbose = verbose,
      parameter = parameter, control = control, sort.parameter = sort.parameter,
      lhs.support = lhs.support, disc.method=disc.method, ...))

}