add documentation for datasets

This commit is contained in:
hetong 2014-09-06 19:02:23 -07:00
parent 99b7ead5ad
commit e04b6aaec5
3 changed files with 89 additions and 1 deletions

View File

@ -53,3 +53,58 @@ xgboost <- function(data = NULL, label = NULL, params = list(), nrounds,
return(bst)
}
#' Training part from Mushroom Data Set
#'
#' This data set is originally from the Mushroom data set,
#' UCI Machine Learning Repository.
#'
#' This data set includes the following fields:
#'
#' \itemize{
#' \item \code{label} the label for each record
#' \item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 127 rows.
#' }
#'
#'#' @references
#' https://archive.ics.uci.edu/ml/datasets/Mushroom
#'
#' Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository
#' [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
#' School of Information and Computer Science.
#'
#' @docType data
#' @keywords datasets
#' @name agaricus.train
#' @usage data(agaricus.train)
#' @format A list containing a label vector, and a dgCMatrix object with 6513
#' rows and 127 variables
NULL
#' Test part from Mushroom Data Set
#'
#' This data set is originally from the Mushroom data set,
#' UCI Machine Learning Repository.
#'
#' This data set includes the following fields:
#'
#' \itemize{
#' \item \code{label} the label for each record
#' \item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 127 rows.
#' }
#'
#' @references
#' https://archive.ics.uci.edu/ml/datasets/Mushroom
#'
#' Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository
#' [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
#' School of Information and Computer Science.
#'
#' @docType data
#' @keywords datasets
#' @name agaricus.test
#' @usage data(agaricus.test)
#' @format A list containing a label vector, and a dgCMatrix object with 1611
#' rows and 127 variables
NULL

View File

@ -0,0 +1,33 @@
% Generated by roxygen2 (4.0.1): do not edit by hand
\docType{data}
\name{agaricus.train}
\alias{agaricus.train}
\title{Training part from Mushroom Data Set}
\format{A list containing a label vector, and a dgCMatrix object with 6513
rows and 127 variables}
\usage{
data(agaricus.train)
}
\description{
This data set is originally from the Mushroom data set,
UCI Machine Learning Repository.
}
\details{
This data set includes the following fields:
\itemize{
\item \code{label} the label for each record
\item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 127 rows.
}
#'
}
\references{
https://archive.ics.uci.edu/ml/datasets/Mushroom
Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository
[http://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
School of Information and Computer Science.
}
\keyword{datasets}

View File

@ -30,7 +30,7 @@ xgb.cv(params = list(), data, nrounds, nfold, label = NULL, showsd = TRUE,
\item{label}{option field, when data is Matrix}
\item{showd}{boolean, whether show standard deviation of cross validation}
\item{showsd}{boolean, whether show standard deviation of cross validation}
\item{metrics,}{list of evaluation metrics to be used in corss validation,
when it is not specified, the evaluation metric is chosen according to objective function.