lgb.prepare_rules2.Rd

% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/lgb.prepare_rules2.R
\name{lgb.prepare_rules2}
\alias{lgb.prepare_rules2}
\title{Data preparator for LightGBM datasets with rules (integer)}
\usage{
lgb.prepare_rules2(data, rules = NULL)
}
\arguments{
\item{data}{A data.frame or data.table to prepare.}

\item{rules}{A set of rules from the data preparator, if already used.}
}
\value{
A list with the cleaned dataset (\code{data}) and the rules (\code{rules}).
        The data must be converted to a matrix format (\code{as.matrix}) for input in
        \code{lgb.Dataset}.
}
\description{
Attempts to prepare a clean dataset to prepare to put in a \code{lgb.Dataset}.
             Factors and characters are converted to numeric (specifically: integer).
             In addition, keeps rules created so you can convert other datasets using this converter.
             This is useful if you have a specific need for integer dataset instead of numeric dataset.
             Note that there are programs which do not support integer-only input.
             Consider this as a half memory technique which is dangerous, especially for LightGBM.
}
\examples{
library(lightgbm)
data(iris)

str(iris)

new_iris <- lgb.prepare_rules2(data = iris) # Autoconverter
str(new_iris$data)

data(iris) # Erase iris dataset
iris$Species[1L] <- "NEW FACTOR" # Introduce junk factor (NA)

# Use conversion using known rules
# Unknown factors become 0, excellent for sparse datasets
newer_iris <- lgb.prepare_rules2(data = iris, rules = new_iris$rules)

# Unknown factor is now zero, perfect for sparse datasets
newer_iris$data[1L, ] # Species became 0 as it is an unknown factor

newer_iris$data[1L, 5L] <- 1.0 # Put back real initial value

# Is the newly created dataset equal? YES!
all.equal(new_iris$data, newer_iris$data)

# Can we test our own rules?
data(iris) # Erase iris dataset

# We remapped values differently
personal_rules <- list(
  Species = c(
    "setosa" = 3L
    , "versicolor" = 2L
    , "virginica" = 1L
  )
)
newest_iris <- lgb.prepare_rules2(data = iris, rules = personal_rules)
str(newest_iris$data) # SUCCESS!

}