swh:1:snp:0f920b1e114986636ba2e45b5c1a83473fb6cf12
Raw File
Tip revision: 893e2d90fd8569e5f0295334c9a1844e95d7911b authored by Piotr Romanski on 11 April 2009, 00:00:00 UTC
version 0.18
Tip revision: 893e2d9
hill.climbing.search.Rd
\name{hill.climbing.search}
\alias{hill.climbing.search}
\title{ Hill climbing search }
\description{
  The algorithm for searching atrribute subset space.
}
\usage{
hill.climbing.search(attributes, eval.fun)
}
\arguments{
  \item{attributes}{ a character vector of all attributes to search in }
  \item{eval.fun}{ a function taking as first parameter a character vector of all attributes and returning a numeric indicating how important a given subset is }
}
\details{
  The algorithm starts with a random attribute set. Then it evaluates all its neighbours and chooses the best one. It might be susceptible to local maximum.
}
\value{
  A character vector of selected attributes.
}
\author{ Piotr Romanski }
\seealso{ \code{\link{forward.search}}, \code{\link{backward.search}}, \code{\link{best.first.search}}, \code{\link{exhaustive.search}} }
\examples{
  library(rpart)
  data(iris)
  
  evaluator <- function(subset) {
    #k-fold cross validation
    k <- 5
    splits <- runif(nrow(iris))
    results = sapply(1:k, function(i) {
      test.idx <- (splits >= (i - 1) / k) & (splits < i / k)
      train.idx <- !test.idx
      test <- iris[test.idx, , drop=FALSE]
      train <- iris[train.idx, , drop=FALSE]
      tree <- rpart(as.simple.formula(subset, "Species"), train)
      error.rate = sum(test$Species != predict(tree, test, type="c")) / nrow(test)
      return(1 - error.rate)
    })
    print(subset)
    print(mean(results))
    return(mean(results))
  }
  
  subset <- hill.climbing.search(names(iris)[-5], evaluator)
  f <- as.simple.formula(subset, "Species")
  print(f)

  
}
back to top