Github user dongjoon-hyun commented on a diff in the pull request: https://github.com/apache/spark/pull/13721#discussion_r67443885 --- Diff: R/pkg/R/DataFrame.R --- @@ -2884,3 +2884,38 @@ setMethod("write.jdbc", write <- callJMethod(write, "mode", jmode) invisible(callJMethod(write, "jdbc", url, tableName, jprops)) }) + +#' randomSplit +#' +#' Return randomly split RDDs with the provided weights. +#' +#' @param x A SparkDataFrame +#' @param weights a vector of weights for splits, will be normalized if they don't sum to 1 +#' @param seed Randomness seed value +#' +#' @family SparkDataFrame functions +#' @rdname randomSplit +#' @name randomSplit +#' @export +#' @examples +#'\dontrun{ +#' sc <- sparkR.init() +#' sqlContext <- sparkRSQL.init(sc) +#' df <- createDataFrame(data.frame(id = 1:1000)) +#' df_list <- randomSplit(df, c(2, 3, 5), 0) +#' sapply(df_list, count) +#'} +setMethod("randomSplit", + signature(x = "SparkDataFrame", weights = "numeric"), + function(x, weights, seed) { + if (!all(sapply(weights, function(c) { c >= 0 }))) { + stop("all weight values should not be negative") --- End diff -- I think it's allowable for some usecases.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org