Skip to content

GitLab

Commit 6bb61ea3 authored by James Lamb's avatar James Lamb Committed by Guolin Ke
Browse files

Fixed misc CRAN issues (#1260) 

* Fixed misc CRAN issues

* Added additional details to R-package DESCRIPTION
parent ebb07f01
Hide whitespace changes
Inline Side-by-side
Showing with 344 additions and 310 deletions
R-package/.Rbuildignore 0 → 100644
View file @ 6bb61ea3
^build_package.R$
R-package/DESCRIPTION
View file @ 6bb61ea3
......@@ -5,13 +5,16 @@ Version: 2.1.0
Date: 2018-01-25
Author: Guolin Ke <guolin.ke@microsoft.com>
Maintainer: Guolin Ke <guolin.ke@microsoft.com>
Description: LightGBM is a gradient boosting framework that uses tree based learning algorithms.
Description: Tree based algorithms can be improved by introducing boosting frameworks. LightGBM is one such framework, and this package offers an R interface to work with it.
It is designed to be distributed and efficient with the following advantages:
1. Faster training speed and higher efficiency.
2. Lower memory usage.
3. Better accuracy.
4. Parallel learning supported.
5. Capable of handling large-scale data.
In recognition of these advantages, LightGBM has being widely-used in many winning solutions of machine learning competitions.
Comparison experiments on public datasets suggest that LightGBM can outperform existing boosting frameworks on both efficiency and accuracy, with significantly lower memory consumption. In addition, parallel experiments suggest that in certain circumstances, LightGBM can achieve a linear speed-up in training time by using multiple machines.
License: MIT + file LICENSE
URL: https://github.com/Microsoft/LightGBM
BugReports: https://github.com/Microsoft/LightGBM/issues
......@@ -30,6 +33,7 @@ Depends:
R (>= 3.0),
R6 (>= 2.0)
Imports:
graphics,
methods,
Matrix (>= 1.1-0),
data.table (>= 1.9.6),
......
R-package/NAMESPACE
View file @ 6bb61ea3
......@@ -38,6 +38,9 @@ export(slice)
import(methods)
importFrom(R6,R6Class)
importFrom(data.table,":=")
importFrom(data.table,set)
importFrom(graphics,barplot)
importFrom(graphics,par)
importFrom(magrittr,"%>%")
importFrom(magrittr,"%T>%")
useDynLib(lib_lightgbm)
R-package/R/lgb.Booster.R
View file @ 6bb61ea3
......@@ -619,7 +619,8 @@ Booster <- R6Class(
#' @param header only used for prediction for text file. True if text file has header
#' @param reshape whether to reshape the vector of predictions to a matrix form when there are several
#' prediction outputs per case.
#' @param ... Additional named arguments passed to the \code{predict()} method of
#' the \code{lgb.Booster} object passed to \code{object}.
#' @return
#' For regression or binary classification, it returns a vector of length \code{nrows(data)}.
#' For multiclass classification, either a \code{num_class * nrows(data)} vector or
......
R-package/R/lgb.cv.R
View file @ 6bb61ea3
......@@ -16,10 +16,8 @@ CVBooster <- R6Class(
)
)
#' Main CV logic for LightGBM
#'
#' Main CV logic for LightGBM
#'
#' @title Main CV logic for LightGBM
#' @name lgb.cv
#' @param params List of parameters
#' @param data a \code{lgb.Dataset} object, used for CV
#' @param nrounds number of CV rounds
......
R-package/R/lgb.model.dt.tree.R
View file @ 6bb61ea3
......@@ -3,6 +3,8 @@
#' Parse a LightGBM model json dump into a \code{data.table} structure.
#'
#' @param model object of class \code{lgb.Booster}
#' @param num_iteration number of iterations you want to predict with. NULL or
#' <= 0 means use best iteration
#'
#' @return
#' A \code{data.table} with detailed information about model trees' nodes and leafs.
......
R-package/R/lgb.plot.importance.R
View file @ 6bb61ea3
......@@ -31,7 +31,7 @@
#' tree_imp <- lgb.importance(model, percentage = TRUE)
#' lgb.plot.importance(tree_imp, top_n = 10, measure = "Gain")
#' }
#'
#' @importFrom graphics barplot par
#' @export
lgb.plot.importance <- function(tree_imp,
top_n = 10,
......@@ -54,22 +54,24 @@ lgb.plot.importance <- function(tree_imp,
}
# Refresh plot
op <- par(no.readonly = TRUE)
on.exit(par(op))
op <- graphics::par(no.readonly = TRUE)
on.exit(graphics::par(op))
# Do some magic plotting
par(mar = op$mar %>% magrittr::inset(., 2, left_margin))
graphics::par(mar = op$mar %>% magrittr::inset(., 2, left_margin))
# Do plot
tree_imp[.N:1,
barplot(height = get(measure),
names.arg = Feature,
horiz = TRUE,
border = NA,
main = "Feature Importance",
xlab = measure,
cex.names = cex,
las = 1)]
graphics::barplot(
height = get(measure),
names.arg = Feature,
horiz = TRUE,
border = NA,
main = "Feature Importance",
xlab = measure,
cex.names = cex,
las = 1
)]
# Return invisibly
invisible(tree_imp)
......
R-package/R/lgb.plot.interpretation.R
View file @ 6bb61ea3
......@@ -36,7 +36,7 @@
#' tree_interpretation <- lgb.interprete(model, test$data, 1:5)
#' lgb.plot.interpretation(tree_interpretation[[1]], top_n = 10)
#' }
#'
#' @importFrom graphics barplot par
#' @export
lgb.plot.interpretation <- function(tree_interpretation_dt,
top_n = 10,
......@@ -48,11 +48,11 @@ lgb.plot.interpretation <- function(tree_interpretation_dt,
num_class <- ncol(tree_interpretation_dt) - 1
# Refresh plot
op <- par(no.readonly = TRUE)
on.exit(par(op))
op <- graphics::par(no.readonly = TRUE)
on.exit(graphics::par(op))
# Do some magic plotting
par(mar = op$mar %>% magrittr::inset(., 1:3, c(3, left_margin, 2)))
graphics::par(mar = op$mar %>% magrittr::inset(., 1:3, c(3, left_margin, 2)))
# Check for number of classes
if (num_class == 1) {
......@@ -70,7 +70,7 @@ lgb.plot.interpretation <- function(tree_interpretation_dt,
ncol = cols, nrow = ceiling(num_class / cols))
# Shape output
par(mfcol = c(nrow(layout_mat), ncol(layout_mat)))
graphics::par(mfcol = c(nrow(layout_mat), ncol(layout_mat)))
# Loop throughout all classes
for (i in seq_len(num_class)) {
......@@ -102,14 +102,16 @@ multiple.tree.plot.interpretation <- function(tree_interpretation,
# Do plot
tree_interpretation[.N:1,
barplot(height = Contribution,
names.arg = Feature,
horiz = TRUE,
col = ifelse(Contribution > 0, "firebrick", "steelblue"),
border = NA,
main = title,
cex.names = cex,
las = 1)]
graphics::barplot(
height = Contribution,
names.arg = Feature,
horiz = TRUE,
col = ifelse(Contribution > 0, "firebrick", "steelblue"),
border = NA,
main = title,
cex.names = cex,
las = 1
)]
# Return invisibly
invisible(NULL)
......
R-package/R/lgb.train.R
View file @ 6bb61ea3
#' Main training logic for LightGBM
#'
#' @title Main training logic for LightGBM
#' @name lgb.train
#' @param params List of parameters
#' @param data a \code{lgb.Dataset} object, used for training
#' @param nrounds number of training rounds
......
R-package/R/lgb.unloader.R
View file @ 6bb61ea3
......@@ -2,7 +2,7 @@
#'
#' Attempts to unload LightGBM packages so you can remove objects cleanly without having to restart R. This is useful for instance if an object becomes stuck for no apparent reason and you do not want to restart R to fix the lost object.
#'
#' @param restart Whether to reload \code{LightGBM} immediately after detaching from R. Defaults to \code{TRUE} which means automatically reload \code{LightGBM} once unloading is performed.
#' @param restore Whether to reload \code{LightGBM} immediately after detaching from R. Defaults to \code{TRUE} which means automatically reload \code{LightGBM} once unloading is performed.
#' @param wipe Whether to wipe all \code{lgb.Dataset} and \code{lgb.Booster} from the global environment. Defaults to \code{FALSE} which means to not remove them.
#' @param envir The environment to perform wiping on if \code{wipe == TRUE}. Defaults to \code{.GlobalEnv} which is the global environment.
#'
......
R-package/R/lightgbm.R
View file @ 6bb61ea3
......@@ -122,5 +122,28 @@ NULL
# Various imports
#' @import methods
#' @importFrom R6 R6Class
#' @useDynLib lightgbm
#' @useDynLib lib_lightgbm
NULL
# Suppress false positive warnings from R CMD CHECK about
# "unrecognized global variable"
globalVariables(c(
"."
, ".N"
, ".SD"
, "Contribution"
, "Cover"
, "Feature"
, "Frequency"
, "Gain"
, "internal_count"
, "internal_value"
, "leaf_index"
, "leaf_parent"
, "leaf_value"
, "node_parent"
, "split_feature"
, "split_gain"
, "split_index"
, "tree_index"
))
R-package/man/lgb.model.dt.tree.Rd
View file @ 6bb61ea3
......@@ -8,6 +8,9 @@ lgb.model.dt.tree(model, num_iteration = NULL)
}
\arguments{
\item{model}{object of class \code{lgb.Booster}}
\item{num_iteration}{number of iterations you want to predict with. NULL or
<= 0 means use best iteration}
}
\value{
A \code{data.table} with detailed information about model trees' nodes and leafs.
......@@ -25,6 +28,7 @@ The columns of the \code{data.table} are:
\item \code{split_gain}: Split gain of a node
\item \code{threshold}: Spliting threshold value of a node
\item \code{decision_type}: Decision type of a node
\item \code{default_left}: Determine how to handle NA value, TRUE -> Left, FALSE -> Right
\item \code{internal_value}: Node value
\item \code{internal_count}: The number of observation collected by a node
\item \code{leaf_value}: Leaf value
......
R-package/man/lgb.plot.importance.Rd
View file @ 6bb61ea3
......@@ -44,5 +44,4 @@ model <- lgb.train(params, dtrain, 20)
tree_imp <- lgb.importance(model, percentage = TRUE)
lgb.plot.importance(tree_imp, top_n = 10, measure = "Gain")
}
}
R-package/man/lgb.plot.interpretation.Rd
View file @ 6bb61ea3
......@@ -49,5 +49,4 @@ model <- lgb.train(params, dtrain, 20)
tree_interpretation <- lgb.interprete(model, test$data, 1:5)
lgb.plot.interpretation(tree_interpretation[[1]], top_n = 10)
}
}
R-package/man/lgb.prepare.Rd
View file @ 6bb61ea3
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/lgb.prepare.R
\name{lgb.prepare}
\alias{lgb.prepare}
\title{Data preparator for LightGBM datasets (numeric)}
\usage{
lgb.prepare(data)
}
\arguments{
\item{data}{A data.frame or data.table to prepare.}
}
\value{
The cleaned dataset. It must be converted to a matrix format (\code{as.matrix}) for input in lgb.Dataset.
}
\description{
Attempts to prepare a clean dataset to prepare to put in a lgb.Dataset. Factors and characters are converted to numeric without integers. Please use \code{lgb.prepare_rules} if you want to apply this transformation to other datasets.
}
\examples{
\dontrun{
library(lightgbm)
data(iris)
str(iris)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
str(lgb.prepare(data = iris)) # Convert all factors/chars to numeric
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : num 1 1 1 1 1 1 1 1 1 1 ...
# When lightgbm package is installed, and you do not want to load it
# You can still use the function!
lgb.unloader()
str(lightgbm::lgb.prepare(data = iris))
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : num 1 1 1 1 1 1 1 1 1 1 ...
}
}
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/lgb.prepare.R
\name{lgb.prepare}
\alias{lgb.prepare}
\title{Data preparator for LightGBM datasets (numeric)}
\usage{
lgb.prepare(data)
}
\arguments{
\item{data}{A data.frame or data.table to prepare.}
}
\value{
The cleaned dataset. It must be converted to a matrix format (\code{as.matrix}) for input in lgb.Dataset.
}
\description{
Attempts to prepare a clean dataset to prepare to put in a lgb.Dataset. Factors and characters are converted to numeric without integers. Please use \code{lgb.prepare_rules} if you want to apply this transformation to other datasets.
}
\examples{
\dontrun{
library(lightgbm)
data(iris)
str(iris)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
str(lgb.prepare(data = iris)) # Convert all factors/chars to numeric
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : num 1 1 1 1 1 1 1 1 1 1 ...
# When lightgbm package is installed, and you do not want to load it
# You can still use the function!
lgb.unloader()
str(lightgbm::lgb.prepare(data = iris))
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : num 1 1 1 1 1 1 1 1 1 1 ...
}
}
R-package/man/lgb.prepare2.Rd
View file @ 6bb61ea3
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/lgb.prepare2.R
\name{lgb.prepare2}
\alias{lgb.prepare2}
\title{Data preparator for LightGBM datasets (integer)}
\usage{
lgb.prepare2(data)
}
\arguments{
\item{data}{A data.frame or data.table to prepare.}
}
\value{
The cleaned dataset. It must be converted to a matrix format (\code{as.matrix}) for input in lgb.Dataset.
}
\description{
Attempts to prepare a clean dataset to prepare to put in a lgb.Dataset. Factors and characters are converted to numeric (specifically: integer). Please use \code{lgb.prepare_rules2} if you want to apply this transformation to other datasets. 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{
\dontrun{
library(lightgbm)
data(iris)
str(iris)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
str(lgb.prepare2(data = iris)) # Convert all factors/chars to integer
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : int 1 1 1 1 1 1 1 1 1 1 ...
# When lightgbm package is installed, and you do not want to load it
# You can still use the function!
lgb.unloader()
str(lightgbm::lgb.prepare2(data = iris))
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : int 1 1 1 1 1 1 1 1 1 1 ...
}
}
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/lgb.prepare2.R
\name{lgb.prepare2}
\alias{lgb.prepare2}
\title{Data preparator for LightGBM datasets (integer)}
\usage{
lgb.prepare2(data)
}
\arguments{
\item{data}{A data.frame or data.table to prepare.}
}
\value{
The cleaned dataset. It must be converted to a matrix format (\code{as.matrix}) for input in lgb.Dataset.
}
\description{
Attempts to prepare a clean dataset to prepare to put in a lgb.Dataset. Factors and characters are converted to numeric (specifically: integer). Please use \code{lgb.prepare_rules2} if you want to apply this transformation to other datasets. 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{
\dontrun{
library(lightgbm)
data(iris)
str(iris)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
str(lgb.prepare2(data = iris)) # Convert all factors/chars to integer
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : int 1 1 1 1 1 1 1 1 1 1 ...
# When lightgbm package is installed, and you do not want to load it
# You can still use the function!
lgb.unloader()
str(lightgbm::lgb.prepare2(data = iris))
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : int 1 1 1 1 1 1 1 1 1 1 ...
}
}
R-package/man/lgb.prepare_rules.Rd
View file @ 6bb61ea3
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/lgb.prepare_rules.R
\name{lgb.prepare_rules}
\alias{lgb.prepare_rules}
\title{Data preparator for LightGBM datasets with rules (numeric)}
\usage{
lgb.prepare_rules(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 lgb.Dataset.
}
\description{
Attempts to prepare a clean dataset to prepare to put in a lgb.Dataset. Factors and characters are converted to numeric. In addition, keeps rules created so you can convert other datasets using this converter.
}
\examples{
\dontrun{
library(lightgbm)
data(iris)
str(iris)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
new_iris <- lgb.prepare_rules(data = iris) # Autoconverter
str(new_iris$data)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : num 1 1 1 1 1 1 1 1 1 1 ...
data(iris) # Erase iris dataset
iris$Species[1] <- "NEW FACTOR" # Introduce junk factor (NA)
# Warning message:
# In `[<-.factor`(`*tmp*`, 1, value = c(NA, 1L, 1L, 1L, 1L, 1L, 1L, :
# invalid factor level, NA generated
# Use conversion using known rules
# Unknown factors become 0, excellent for sparse datasets
newer_iris <- lgb.prepare_rules(data = iris, rules = new_iris$rules)
# Unknown factor is now zero, perfect for sparse datasets
newer_iris$data[1, ] # Species became 0 as it is an unknown factor
# Sepal.Length Sepal.Width Petal.Length Petal.Width Species
# 1 5.1 3.5 1.4 0.2 0
newer_iris$data[1, 5] <- 1 # Put back real initial value
# Is the newly created dataset equal? YES!
all.equal(new_iris$data, newer_iris$data)
# [1] TRUE
# Can we test our own rules?
data(iris) # Erase iris dataset
# We remapped values differently
personal_rules <- list(Species = c("setosa" = 3,
"versicolor" = 2,
"virginica" = 1))
newest_iris <- lgb.prepare_rules(data = iris, rules = personal_rules)
str(newest_iris$data) # SUCCESS!
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : num 3 3 3 3 3 3 3 3 3 3 ...
}
}
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/lgb.prepare_rules.R
\name{lgb.prepare_rules}
\alias{lgb.prepare_rules}
\title{Data preparator for LightGBM datasets with rules (numeric)}
\usage{
lgb.prepare_rules(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 lgb.Dataset.
}
\description{
Attempts to prepare a clean dataset to prepare to put in a lgb.Dataset. Factors and characters are converted to numeric. In addition, keeps rules created so you can convert other datasets using this converter.
}
\examples{
\dontrun{
library(lightgbm)
data(iris)
str(iris)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
new_iris <- lgb.prepare_rules(data = iris) # Autoconverter
str(new_iris$data)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : num 1 1 1 1 1 1 1 1 1 1 ...
data(iris) # Erase iris dataset
iris$Species[1] <- "NEW FACTOR" # Introduce junk factor (NA)
# Warning message:
# In `[<-.factor`(`*tmp*`, 1, value = c(NA, 1L, 1L, 1L, 1L, 1L, 1L, :
# invalid factor level, NA generated
# Use conversion using known rules
# Unknown factors become 0, excellent for sparse datasets
newer_iris <- lgb.prepare_rules(data = iris, rules = new_iris$rules)
# Unknown factor is now zero, perfect for sparse datasets
newer_iris$data[1, ] # Species became 0 as it is an unknown factor
# Sepal.Length Sepal.Width Petal.Length Petal.Width Species
# 1 5.1 3.5 1.4 0.2 0
newer_iris$data[1, 5] <- 1 # Put back real initial value
# Is the newly created dataset equal? YES!
all.equal(new_iris$data, newer_iris$data)
# [1] TRUE
# Can we test our own rules?
data(iris) # Erase iris dataset
# We remapped values differently
personal_rules <- list(Species = c("setosa" = 3,
"versicolor" = 2,
"virginica" = 1))
newest_iris <- lgb.prepare_rules(data = iris, rules = personal_rules)
str(newest_iris$data) # SUCCESS!
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : num 3 3 3 3 3 3 3 3 3 3 ...
}
}
R-package/man/lgb.prepare_rules2.Rd
View file @ 6bb61ea3
% 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 lgb.Dataset.
}
\description{
Attempts to prepare a clean dataset to prepare to put in a 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{
\dontrun{
library(lightgbm)
data(iris)
str(iris)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
new_iris <- lgb.prepare_rules2(data = iris) # Autoconverter
str(new_iris$data)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : int 1 1 1 1 1 1 1 1 1 1 ...
data(iris) # Erase iris dataset
iris$Species[1] <- "NEW FACTOR" # Introduce junk factor (NA)
# Warning message:
# In `[<-.factor`(`*tmp*`, 1, value = c(NA, 1L, 1L, 1L, 1L, 1L, 1L, :
# invalid factor level, NA generated
# Use conversion using known rules
# Unknown factors become 0, excellent for sparse datasets
newer_iris <- lgb.prepare_rules2(data = iris, rules = new_iris$rules)
# Unknown factor is now zero, perfect for sparse datasets
newer_iris$data[1, ] # Species became 0 as it is an unknown factor
# Sepal.Length Sepal.Width Petal.Length Petal.Width Species
# 1 5.1 3.5 1.4 0.2 0
newer_iris$data[1, 5] <- 1 # Put back real initial value
# Is the newly created dataset equal? YES!
all.equal(new_iris$data, newer_iris$data)
# [1] TRUE
# 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!
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : int 3 3 3 3 3 3 3 3 3 3 ...
}
}
% 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 lgb.Dataset.
}
\description{
Attempts to prepare a clean dataset to prepare to put in a 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{
\dontrun{
library(lightgbm)
data(iris)
str(iris)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
new_iris <- lgb.prepare_rules2(data = iris) # Autoconverter
str(new_iris$data)
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : int 1 1 1 1 1 1 1 1 1 1 ...
data(iris) # Erase iris dataset
iris$Species[1] <- "NEW FACTOR" # Introduce junk factor (NA)
# Warning message:
# In `[<-.factor`(`*tmp*`, 1, value = c(NA, 1L, 1L, 1L, 1L, 1L, 1L, :
# invalid factor level, NA generated
# Use conversion using known rules
# Unknown factors become 0, excellent for sparse datasets
newer_iris <- lgb.prepare_rules2(data = iris, rules = new_iris$rules)
# Unknown factor is now zero, perfect for sparse datasets
newer_iris$data[1, ] # Species became 0 as it is an unknown factor
# Sepal.Length Sepal.Width Petal.Length Petal.Width Species
# 1 5.1 3.5 1.4 0.2 0
newer_iris$data[1, 5] <- 1 # Put back real initial value
# Is the newly created dataset equal? YES!
all.equal(new_iris$data, newer_iris$data)
# [1] TRUE
# 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!
# 'data.frame': 150 obs. of 5 variables:
# $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
# $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
# $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
# $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
# $ Species : int 3 3 3 3 3 3 3 3 3 3 ...
}
}
R-package/man/lgb.train.Rd
View file @ 6bb61ea3
......@@ -75,7 +75,7 @@ If early stopping occurs, the model will have 'best_iter' field}
\item{callbacks}{list of callback functions
List of callback functions that are applied at each iteration.}
\item{...}{other parameters, see parameters.md for more informations}
\item{...}{other parameters, see Parameters.rst for more informations}
\item{valids}{a list of \code{lgb.Dataset} objects, used for validation}
......@@ -135,7 +135,7 @@ If early stopping occurs, the model will have 'best_iter' field}
\item{callbacks}{list of callback functions
List of callback functions that are applied at each iteration.}
\item{...}{other parameters, see parameters.md for more informations}
\item{...}{other parameters, see Parameters.rst for more informations}
}
\value{
a trained model \code{lgb.CVBooster}.
......@@ -143,10 +143,6 @@ a trained model \code{lgb.CVBooster}.
a trained booster model \code{lgb.Booster}.
}
\description{
Main CV logic for LightGBM
Main training logic for LightGBM
Simple interface for training an lightgbm model.
Its documentation is combined with lgb.train.
}
......
R-package/man/lgb.unloader.Rd
View file @ 6bb61ea3
......@@ -7,11 +7,11 @@
lgb.unloader(restore = TRUE, wipe = FALSE, envir = .GlobalEnv)
}
\arguments{
\item{restore}{Whether to reload \code{LightGBM} immediately after detaching from R. Defaults to \code{TRUE} which means automatically reload \code{LightGBM} once unloading is performed.}
\item{wipe}{Whether to wipe all \code{lgb.Dataset} and \code{lgb.Booster} from the global environment. Defaults to \code{FALSE} which means to not remove them.}
\item{envir}{The environment to perform wiping on if \code{wipe == TRUE}. Defaults to \code{.GlobalEnv} which is the global environment.}
\item{restart}{Whether to reload \code{LightGBM} immediately after detaching from R. Defaults to \code{TRUE} which means automatically reload \code{LightGBM} once unloading is performed.}
}
\value{
NULL invisibly.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment