Github user felixcheung commented on a diff in the pull request:
https://github.com/apache/spark/pull/22107#discussion_r210488890
--- Diff: R/pkg/R/DataFrame.R ---
@@ -2876,6 +2905,37 @@ setMethod("except",
dataFrame(excepted)
})
+#' exceptAll
+#'
+#' Return a new SparkDataFrame containing rows in this SparkDataFrame
+#' but not in another SparkDataFrame while preserving the duplicates.
+#' This is equivalent to \code{EXCEPT ALL} in SQL. Also as standard in
+#' SQL, this function resolves columns by position (not by name).
+#'
+#' @param x a SparkDataFrame.
+#' @param y a SparkDataFrame.
+#' @return A SparkDataFrame containing the result of the except all
operation.
+#' @family SparkDataFrame functions
+#' @aliases exceptAll,SparkDataFrame,SparkDataFrame-method
+#' @rdname exceptAll
+#' @name exceptAll
+#' @examples
+#'\dontrun{
+#' sparkR.session()
+#' df1 <- read.json(path)
+#' df2 <- read.json(path2)
+#' exceptAllDF <- exceptAll(df1, df2)
+#' }
+#' @rdname exceptAll
+#' @note exceptAll since 2.4.0
+setMethod("exceptAll",
+ signature(x = "SparkDataFrame", y = "SparkDataFrame"),
+ function(x, y) {
+ excepted <- callJMethod(x@sdf, "exceptAll", y@sdf)
+ dataFrame(excepted)
+ })
+
--- End diff --
nit: remove one of the two empty lines
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
