0052b193cf
Fix @export tag in each R file (for Roxygen 5, otherwise it doesn't work anymore) Regerate Roxygen doc
84 lines
3.2 KiB
R
84 lines
3.2 KiB
R
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/xgboost.R
|
|
\name{xgboost}
|
|
\alias{xgboost}
|
|
\title{eXtreme Gradient Boosting (Tree) library}
|
|
\usage{
|
|
xgboost(data = NULL, label = NULL, missing = NA, weight = NULL,
|
|
params = list(), nrounds, verbose = 1, print.every.n = 1L,
|
|
early.stop.round = NULL, maximize = NULL, save_period = 0,
|
|
save_name = "xgboost.model", ...)
|
|
}
|
|
\arguments{
|
|
\item{data}{takes \code{matrix}, \code{dgCMatrix}, local data file or
|
|
\code{xgb.DMatrix}.}
|
|
|
|
\item{label}{the response variable. User should not set this field,
|
|
if data is local data file or \code{xgb.DMatrix}.}
|
|
|
|
\item{missing}{Missing is only used when input is dense matrix, pick a float
|
|
value that represents missing value. Sometimes a data use 0 or other extreme value to represents missing values.}
|
|
|
|
\item{weight}{a vector indicating the weight for each row of the input.}
|
|
|
|
\item{params}{the list of parameters.
|
|
|
|
Commonly used ones are:
|
|
\itemize{
|
|
\item \code{objective} objective function, common ones are
|
|
\itemize{
|
|
\item \code{reg:linear} linear regression
|
|
\item \code{binary:logistic} logistic regression for classification
|
|
}
|
|
\item \code{eta} step size of each boosting step
|
|
\item \code{max.depth} maximum depth of the tree
|
|
\item \code{nthread} number of thread used in training, if not set, all threads are used
|
|
}
|
|
|
|
Look at \code{\link{xgb.train}} for a more complete list of parameters or \url{https://github.com/dmlc/xgboost/wiki/Parameters} for the full list.
|
|
|
|
See also \code{demo/} for walkthrough example in R.}
|
|
|
|
\item{nrounds}{the max number of iterations}
|
|
|
|
\item{verbose}{If 0, xgboost will stay silent. If 1, xgboost will print
|
|
information of performance. If 2, xgboost will print information of both
|
|
performance and construction progress information}
|
|
|
|
\item{print.every.n}{Print every N progress messages when \code{verbose>0}. Default is 1 which means all messages are printed.}
|
|
|
|
\item{early.stop.round}{If \code{NULL}, the early stopping function is not triggered.
|
|
If set to an integer \code{k}, training with a validation set will stop if the performance
|
|
keeps getting worse consecutively for \code{k} rounds.}
|
|
|
|
\item{maximize}{If \code{feval} and \code{early.stop.round} are set, then \code{maximize} must be set as well.
|
|
\code{maximize=TRUE} means the larger the evaluation score the better.}
|
|
|
|
\item{save_period}{save the model to the disk in every \code{save_period} rounds, 0 means no such action.}
|
|
|
|
\item{save_name}{the name or path for periodically saved model file.}
|
|
|
|
\item{...}{other parameters to pass to \code{params}.}
|
|
}
|
|
\description{
|
|
A simple interface for training xgboost model. Look at \code{\link{xgb.train}} function for a more advanced interface.
|
|
}
|
|
\details{
|
|
This is the modeling function for Xgboost.
|
|
|
|
Parallelization is automatically enabled if \code{OpenMP} is present.
|
|
|
|
Number of threads can also be manually specified via \code{nthread} parameter.
|
|
}
|
|
\examples{
|
|
data(agaricus.train, package='xgboost')
|
|
data(agaricus.test, package='xgboost')
|
|
train <- agaricus.train
|
|
test <- agaricus.test
|
|
bst <- xgboost(data = train$data, label = train$label, max.depth = 2,
|
|
eta = 1, nthread = 2, nround = 2, objective = "binary:logistic")
|
|
pred <- predict(bst, test$data)
|
|
|
|
}
|
|
|