lightgbm-org--lightgbm
wehub-resource-sync
83 行
3.1 KiB
R
83 行
3.1 KiB
R
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/lgb.Dataset.R
|
|
\name{lgb.Dataset}
|
|
\alias{lgb.Dataset}
|
|
\title{Construct \code{lgb.Dataset} object}
|
|
\usage{
|
|
lgb.Dataset(
|
|
data,
|
|
params = list(),
|
|
reference = NULL,
|
|
colnames = NULL,
|
|
categorical_feature = NULL,
|
|
free_raw_data = TRUE,
|
|
label = NULL,
|
|
weight = NULL,
|
|
group = NULL,
|
|
init_score = NULL
|
|
)
|
|
}
|
|
\arguments{
|
|
\item{data}{a \code{matrix} object, a \code{dgCMatrix} object,
|
|
a character representing a path to a text file (CSV, TSV, or LibSVM),
|
|
or a character representing a path to a binary \code{lgb.Dataset} file}
|
|
|
|
\item{params}{a list of parameters. See
|
|
\href{https://lightgbm.readthedocs.io/en/latest/Parameters.html#dataset-parameters}{
|
|
The "Dataset Parameters" section of the documentation} for a list of parameters
|
|
and valid values.}
|
|
|
|
\item{reference}{reference dataset. When LightGBM creates a Dataset, it does some preprocessing like binning
|
|
continuous features into histograms. If you want to apply the same bin boundaries from an existing
|
|
dataset to new \code{data}, pass that existing Dataset to this argument.}
|
|
|
|
\item{colnames}{names of columns}
|
|
|
|
\item{categorical_feature}{categorical features. This can either be a character vector of feature
|
|
names or an integer vector with the indices of the features (e.g.
|
|
\code{c(1L, 10L)} to say "the first and tenth columns").}
|
|
|
|
\item{free_raw_data}{LightGBM constructs its data format, called a "Dataset", from tabular data.
|
|
By default, that Dataset object on the R side does not keep a copy of the raw data.
|
|
This reduces LightGBM's memory consumption, but it means that the Dataset object
|
|
cannot be changed after it has been constructed. If you'd prefer to be able to
|
|
change the Dataset object after construction, set \code{free_raw_data = FALSE}.}
|
|
|
|
\item{label}{vector of labels to use as the target variable}
|
|
|
|
\item{weight}{numeric vector of sample weights}
|
|
|
|
\item{group}{used for learning-to-rank tasks. An integer vector describing how to
|
|
group rows together as ordered results from the same set of candidate results
|
|
to be ranked. For example, if you have a 100-document dataset with
|
|
\code{group = c(10, 20, 40, 10, 10, 10)}, that means that you have 6 groups,
|
|
where the first 10 records are in the first group, records 11-30 are in the
|
|
second group, etc.}
|
|
|
|
\item{init_score}{initial score is the base prediction lightgbm will boost from}
|
|
}
|
|
\value{
|
|
constructed dataset
|
|
}
|
|
\description{
|
|
LightGBM does not train on raw data.
|
|
It discretizes continuous features into histogram bins, tries to
|
|
combine categorical features, and automatically handles missing and
|
|
|
|
The \code{Dataset} class handles that preprocessing, and holds that
|
|
alternative representation of the input data.
|
|
}
|
|
\examples{
|
|
\donttest{
|
|
\dontshow{setLGBMthreads(2L)}
|
|
\dontshow{data.table::setDTthreads(1L)}
|
|
data(agaricus.train, package = "lightgbm")
|
|
train <- agaricus.train
|
|
dtrain <- lgb.Dataset(train$data, label = train$label)
|
|
data_file <- tempfile(fileext = ".data")
|
|
lgb.Dataset.save(dtrain, data_file)
|
|
dtrain <- lgb.Dataset(data_file)
|
|
lgb.Dataset.construct(dtrain)
|
|
}
|
|
}
|