aboutsummaryrefslogtreecommitdiff
path: root/R/pkg/R/functions.R
diff options
context:
space:
mode:
authorzero323 <zero323@users.noreply.github.com>2017-04-21 12:06:21 -0700
committerFelix Cheung <felixcheung@apache.org>2017-04-21 12:06:21 -0700
commitfd648bff63f91a30810910dfc5664eea0ff5e6f9 (patch)
treef00aacc693efa151d857684b3cb0907ce74fd775 /R/pkg/R/functions.R
parenteb00378f0eed6afbf328ae6cd541cc202d14c1f0 (diff)
downloadspark-fd648bff63f91a30810910dfc5664eea0ff5e6f9.tar.gz
spark-fd648bff63f91a30810910dfc5664eea0ff5e6f9.tar.bz2
spark-fd648bff63f91a30810910dfc5664eea0ff5e6f9.zip
[SPARK-20371][R] Add wrappers for collect_list and collect_set
## What changes were proposed in this pull request? Adds wrappers for `collect_list` and `collect_set`. ## How was this patch tested? Unit tests, `check-cran.sh` Author: zero323 <zero323@users.noreply.github.com> Closes #17672 from zero323/SPARK-20371.
Diffstat (limited to 'R/pkg/R/functions.R')
-rw-r--r--R/pkg/R/functions.R40
1 files changed, 40 insertions, 0 deletions
diff --git a/R/pkg/R/functions.R b/R/pkg/R/functions.R
index f854df11e5..e7decb9186 100644
--- a/R/pkg/R/functions.R
+++ b/R/pkg/R/functions.R
@@ -3705,3 +3705,43 @@ setMethod("create_map",
jc <- callJStatic("org.apache.spark.sql.functions", "map", jcols)
column(jc)
})
+
+#' collect_list
+#'
+#' Creates a list of objects with duplicates.
+#'
+#' @param x Column to compute on
+#'
+#' @rdname collect_list
+#' @name collect_list
+#' @family agg_funcs
+#' @aliases collect_list,Column-method
+#' @export
+#' @examples \dontrun{collect_list(df$x)}
+#' @note collect_list since 2.3.0
+setMethod("collect_list",
+ signature(x = "Column"),
+ function(x) {
+ jc <- callJStatic("org.apache.spark.sql.functions", "collect_list", x@jc)
+ column(jc)
+ })
+
+#' collect_set
+#'
+#' Creates a list of objects with duplicate elements eliminated.
+#'
+#' @param x Column to compute on
+#'
+#' @rdname collect_set
+#' @name collect_set
+#' @family agg_funcs
+#' @aliases collect_set,Column-method
+#' @export
+#' @examples \dontrun{collect_set(df$x)}
+#' @note collect_set since 2.3.0
+setMethod("collect_set",
+ signature(x = "Column"),
+ function(x) {
+ jc <- callJStatic("org.apache.spark.sql.functions", "collect_set", x@jc)
+ column(jc)
+ })