3c004a4145
* `XGDMatrixGetQuantileCut` * `XGDMatrixNumNonMissing` * `XGDMatrixGetDataAsCSR` --------- Co-authored-by: Jiaming Yuan <jm.yuan@outlook.com>
59 lines
2.0 KiB
R
59 lines
2.0 KiB
R
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/xgb.DMatrix.R
|
|
\name{xgb.get.DMatrix.qcut}
|
|
\alias{xgb.get.DMatrix.qcut}
|
|
\title{Get Quantile Cuts from DMatrix}
|
|
\usage{
|
|
xgb.get.DMatrix.qcut(dmat, output = c("list", "arrays"))
|
|
}
|
|
\arguments{
|
|
\item{dmat}{An \code{xgb.DMatrix} object, as returned by \link{xgb.DMatrix}.}
|
|
|
|
\item{output}{Output format for the quantile cuts. Possible options are:\itemize{
|
|
\item \code{"list"} will return the output as a list with one entry per column, where
|
|
each column will have a numeric vector with the cuts. The list will be named if
|
|
\code{dmat} has column names assigned to it.
|
|
\item \code{"arrays"} will return a list with entries \code{indptr} (base-0 indexing) and
|
|
\code{data}. Here, the cuts for column 'i' are obtained by slicing 'data' from entries
|
|
\code{indptr[i]+1} to \code{indptr[i+1]}.
|
|
}}
|
|
}
|
|
\value{
|
|
The quantile cuts, in the format specified by parameter \code{output}.
|
|
}
|
|
\description{
|
|
Get the quantile cuts (a.k.a. borders) from an \code{xgb.DMatrix}
|
|
that has been quantized for the histogram method (\code{tree_method="hist"}).
|
|
|
|
These cuts are used in order to assign observations to bins - i.e. these are ordered
|
|
boundaries which are used to determine assignment condition \verb{border_low < x < border_high}.
|
|
As such, the first and last bin will be outside of the range of the data, so as to include
|
|
all of the observations there.
|
|
|
|
If a given column has 'n' bins, then there will be 'n+1' cuts / borders for that column,
|
|
which will be output in sorted order from lowest to highest.
|
|
|
|
Different columns can have different numbers of bins according to their range.
|
|
}
|
|
\examples{
|
|
library(xgboost)
|
|
data(mtcars)
|
|
y <- mtcars$mpg
|
|
x <- as.matrix(mtcars[, -1])
|
|
dm <- xgb.DMatrix(x, label = y, nthread = 1)
|
|
|
|
# DMatrix is not quantized right away, but will be once a hist model is generated
|
|
model <- xgb.train(
|
|
data = dm,
|
|
params = list(
|
|
tree_method = "hist",
|
|
max_bin = 8,
|
|
nthread = 1
|
|
),
|
|
nrounds = 3
|
|
)
|
|
|
|
# Now can get the quantile cuts
|
|
xgb.get.DMatrix.qcut(dm)
|
|
}
|