Github user NarineK commented on a diff in the pull request: https://github.com/apache/spark/pull/12836#discussion_r66732763 --- Diff: R/pkg/R/group.R --- @@ -142,3 +142,58 @@ createMethods <- function() { } createMethods() + +#' gapply +#' +#' Applies a R function to each group in the input GroupedData +#' +#' @param x a GroupedData +#' @param func A function to be applied to each group partition specified by GroupedData. +#' The function `func` takes as argument a key - grouping columns and +#' a data frame - a local R data.frame. +#' The output of `func` is a local R data.frame. +#' @param schema The schema of the resulting SparkDataFrame after the function is applied. +#' It must match the output of func. +#' @return a SparkDataFrame +#' @rdname gapply +#' @name gapply +#' @examples +#' \dontrun{ +#' Computes the arithmetic mean of the second column by grouping +#' on the first and third columns. Output the grouping values and the average. +#' +#' df <- createDataFrame ( +#' list(list(1L, 1, "1", 0.1), list(1L, 2, "1", 0.2), list(3L, 3, "3", 0.3)), +#' c("a", "b", "c", "d")) +#' +#' schema <- structType(structField("a", "integer"), structField("c", "string"), +#' structField("avg", "double")) +#' df1 <- gapply( +#' df, +#' list("a", "c"), +#' function(key, x) { +#' y <- data.frame(key, mean(x$b), stringsAsFactors = FALSE) +#' }, +#' schema) +#' collect(df1) +#' +#' Result +#' ------ +#' a c avg +#' 3 3 3.0 +#' 1 1 1.5 +#' } +setMethod("gapply", + signature(x = "GroupedData"), + function(x, func, schema) { + packageNamesArr <- serialize(.sparkREnv[[".packages"]], + connection = NULL) + broadcastArr <- lapply(ls(.broadcastNames), + function(name) { get(name, .broadcastNames) }) + sdf <- callJMethod(x@sgd, "flatMapGroupsInR", + serialize(cleanClosure(func), connection = NULL), + packageNamesArr, + broadcastArr, + if (is.null(schema)) { schema } else { schema$jobj }) --- End diff -- Thnx, I set an assertion. we cannot do it exactly like dapply by forcing with schema because gapply for GroupedData is slightly different from DataFrame's gapply.
--- 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