[R-package] remove Dataset `setinfo()` (#4854)

* [R-package] remove Dataset setinfo()

* revert unintended docs changes

* fix examples

* revert FAQ changes

* empty commit

R-package/NAMESPACE

@@ -8,7 +8,6 @@ S3method(getinfo,lgb.Dataset)
 S3method(predict,lgb.Booster)
 S3method(print,lgb.Booster)
 S3method(set_field,lgb.Dataset)
-S3method(setinfo,lgb.Dataset)
 S3method(slice,lgb.Dataset)
 S3method(summary,lgb.Booster)
 export(get_field)
@@ -39,7 +38,6 @@ export(lightgbm)
 export(readRDS.lgb.Booster)
 export(saveRDS.lgb.Booster)
 export(set_field)
-export(setinfo)
 export(slice)
 import(methods)
 importFrom(Matrix,Matrix)

R-package/R/lgb.Dataset.R

@@ -529,19 +529,6 @@ Dataset <- R6::R6Class(
 
     },
 
-    setinfo = function(name, info) {
-      warning(paste0(
-        "Dataset$setinfo() is deprecated and will be removed in a future release. "
-        , "Use Dataset$set_field() instead."
-      ))
-      return(
-        self$set_field(
-          field_name = name
-          , data = info
-        )
-      )
-    },
-
     set_field = function(field_name, data) {
 
       # Check if attribute key is in the known attribute list
@@ -1200,7 +1187,7 @@ slice.lgb.Dataset <- function(dataset, idxset, ...) {
 #' lgb.Dataset.construct(dtrain)
 #'
 #' labels <- lightgbm::getinfo(dtrain, "label")
-#' lightgbm::setinfo(dtrain, "label", 1 - labels)
+#' lightgbm::set_field(dtrain, "label", 1 - labels)
 #'
 #' labels2 <- lightgbm::getinfo(dtrain, "label")
 #' stopifnot(all(labels2 == 1 - labels))
@@ -1234,69 +1221,6 @@ getinfo.lgb.Dataset <- function(dataset, name, ...) {
 
 }
 
-#' @name setinfo
-#' @title Set information of an \code{lgb.Dataset} object
-#' @description Set one attribute of a \code{lgb.Dataset}
-#' @param dataset Object of class \code{lgb.Dataset}
-#' @param name the name of the field to get
-#' @param info the specific field of information to set
-#' @param ... other parameters (ignored)
-#' @return the dataset you passed in
-#'
-#' @details
-#' The \code{name} field can be one of the following:
-#'
-#' \itemize{
-#'     \item{\code{label}: vector of labels to use as the target variable}
-#'     \item{\code{weight}: to do a weight rescale}
-#'     \item{\code{init_score}: initial score is the base prediction lightgbm will boost from}
-#'     \item{\code{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.}
-#' }
-#'
-#' @examples
-#' \donttest{
-#' data(agaricus.train, package = "lightgbm")
-#' train <- agaricus.train
-#' dtrain <- lgb.Dataset(train$data, label = train$label)
-#' lgb.Dataset.construct(dtrain)
-#'
-#' labels <- lightgbm::getinfo(dtrain, "label")
-#' lightgbm::setinfo(dtrain, "label", 1 - labels)
-#'
-#' labels2 <- lightgbm::getinfo(dtrain, "label")
-#' stopifnot(all.equal(labels2, 1 - labels))
-#' }
-#' @export
-setinfo <- function(dataset, ...) {
-  UseMethod("setinfo")
-}
-
-#' @rdname setinfo
-#' @export
-setinfo.lgb.Dataset <- function(dataset, name, info, ...) {
-
-  warning("Calling setinfo() on a lgb.Dataset is deprecated. Use set_field() instead.")
-
-  additional_args <- list(...)
-  if (length(additional_args) > 0L) {
-    warning(paste0(
-      "setinfo.lgb.Dataset: Found the following passed through '...': "
-      , paste(names(additional_args), collapse = ", ")
-      , ". These are ignored. In future releases of lightgbm, this warning will become an error. "
-      , "See ?setinfo.lgb.Dataset for documentation on how to call this function."
-    ))
-  }
-
-  if (!lgb.is.Dataset(x = dataset)) {
-    stop("setinfo.lgb.Dataset: input dataset should be an lgb.Dataset object")
-  }
-
-  return(invisible(dataset$set_field(field_name = name, data = info)))
-}
 
 #' @name get_field
 #' @title Get one attribute of a \code{lgb.Dataset}

R-package/man/getinfo.Rd

@@ -44,7 +44,7 @@ dtrain <- lgb.Dataset(train$data, label = train$label)
 lgb.Dataset.construct(dtrain)
 
 labels <- lightgbm::getinfo(dtrain, "label")
-lightgbm::setinfo(dtrain, "label", 1 - labels)
+lightgbm::set_field(dtrain, "label", 1 - labels)
 
 labels2 <- lightgbm::getinfo(dtrain, "label")
 stopifnot(all(labels2 == 1 - labels))

R-package/man/setinfo.Rd

-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/lgb.Dataset.R
-\name{setinfo}
-\alias{setinfo}
-\alias{setinfo.lgb.Dataset}
-\title{Set information of an \code{lgb.Dataset} object}
-\usage{
-setinfo(dataset, ...)
-
-\method{setinfo}{lgb.Dataset}(dataset, name, info, ...)
-}
-\arguments{
-\item{dataset}{Object of class \code{lgb.Dataset}}
-
-\item{...}{other parameters (ignored)}
-
-\item{name}{the name of the field to get}
-
-\item{info}{the specific field of information to set}
-}
-\value{
-the dataset you passed in
-}
-\description{
-Set one attribute of a \code{lgb.Dataset}
-}
-\details{
-The \code{name} field can be one of the following:
-
-\itemize{
-    \item{\code{label}: vector of labels to use as the target variable}
-    \item{\code{weight}: to do a weight rescale}
-    \item{\code{init_score}: initial score is the base prediction lightgbm will boost from}
-    \item{\code{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.}
-}
-}
-\examples{
-\donttest{
-data(agaricus.train, package = "lightgbm")
-train <- agaricus.train
-dtrain <- lgb.Dataset(train$data, label = train$label)
-lgb.Dataset.construct(dtrain)
-
-labels <- lightgbm::getinfo(dtrain, "label")
-lightgbm::setinfo(dtrain, "label", 1 - labels)
-
-labels2 <- lightgbm::getinfo(dtrain, "label")
-stopifnot(all.equal(labels2, 1 - labels))
-}
-}

R-package/tests/testthat/test_dataset.R

@@ -27,11 +27,11 @@ test_that("lgb.Dataset: basic construction, saving, loading", {
   expect_equal(get_field(dtest1, "label"), get_field(dtest3, "label"))
 })
 
-test_that("lgb.Dataset: getinfo & setinfo", {
+test_that("lgb.Dataset: getinfo", {
   dtest <- lgb.Dataset(test_data)
   dtest$construct()
 
-  setinfo(dtest, "label", test_label)
+  set_field(dtest, "label", test_label)
   labels <- getinfo(dtest, "label")
   expect_equal(test_label, getinfo(dtest, "label"))
 
@@ -39,7 +39,7 @@ test_that("lgb.Dataset: getinfo & setinfo", {
   expect_true(length(getinfo(dtest, "init_score")) == 0L)
 
   # any other label should error
-  expect_error(setinfo(dtest, "asdf", test_label))
+  expect_error(set_field(dtest, "asdf", test_label))
 })
 
 test_that("lgb.Dataset: get_field & set_field", {
@@ -259,19 +259,6 @@ test_that("cpp errors should be raised as proper R errors", {
   }, regexp = "Initial score size doesn't match data size")
 })
 
-test_that("lgb.Dataset$setinfo() should convert 'group' to integer", {
-  ds <- lgb.Dataset(
-    data = matrix(rnorm(100L), nrow = 50L, ncol = 2L)
-    , label = sample(c(0L, 1L), size = 50L, replace = TRUE)
-  )
-  ds$construct()
-  current_group <- ds$getinfo("group")
-  expect_null(current_group)
-  group_as_numeric <- rep(25.0, 2L)
-  ds$setinfo("group", group_as_numeric)
-  expect_identical(ds$getinfo("group"), as.integer(group_as_numeric))
-})
-
 test_that("lgb.Dataset$set_field() should convert 'group' to integer", {
   ds <- lgb.Dataset(
     data = matrix(rnorm(100L), nrow = 50L, ncol = 2L)

docs/FAQ.rst

@@ -230,8 +230,11 @@ This is a known issue: `Microsoft/LightGBM#698 <https://github.com/microsoft/Lig
 2. I used ``setinfo()``, tried to print my ``lgb.Dataset``, and now the R console froze!
 ----------------------------------------------------------------------------------------
 
-Avoid printing the ``lgb.Dataset`` after using ``setinfo``.
-This is a known bug: `Microsoft/LightGBM#539 <https://github.com/microsoft/LightGBM/issues/539>`__.
+As of at least LightGBM v3.3.0, this issue has been resolved and printing a ``Dataset`` object does not cause the console to freeze.
+
+In older versions, avoid printing the ``Dataset`` after calling ``setinfo()``.
+
+As of LightGBM v4.0.0, ``setinfo()`` has been replaced by a new method, ``set_field()``.
 
 3. ``error in data.table::data.table()...argument 2 is NULL``
 -------------------------------------------------------------