Merge pull request apache#149 from hqzizania/master

[SPARKR-170] Update reduceByKey, groupByKey, combineByKey, partitionBy documentation in RDD.R

Author: shivaram

pkg/R/RDD.R

@@ -1244,12 +1244,12 @@ setMethod("flatMapValues",
 
 #' Partition an RDD by key
 #'
-#' This function operates on RDDs where every element is of the form list(K, V).
+#' This function operates on RDDs where every element is of the form list(K, V) or c(K, V).
 #' For each element of this RDD, the partitioner is used to compute a hash
 #' function and the RDD is partitioned using this hash value.
 #'
 #' @param rdd The RDD to partition. Should be an RDD where each element is
-#'             list(K, V).
+#'             list(K, V) or c(K, V).
 #' @param numPartitions Number of partitions to create.
 #' @param ... Other optional arguments to partitionBy.
 #'
@@ -1261,10 +1261,10 @@ setMethod("flatMapValues",
 #' @examples
 #'\dontrun{
 #' sc <- sparkR.init()
-#' pairs <- list(c(1, 2), c(1.1, 3), c(1, 4))
+#' pairs <- list(list(1, 2), list(1.1, 3), list(1, 4))
 #' rdd <- parallelize(sc, pairs)
 #' parts <- partitionBy(rdd, 2L)
-#' collectPartition(parts, 0L) # First partition should contain c(1,2) and c(1,3)
+#' collectPartition(parts, 0L) # First partition should contain list(1, 2) and list(1, 4)
 #'}
 setGeneric("partitionBy",
            function(rdd, numPartitions, ...) {
@@ -1325,11 +1325,11 @@ setMethod("partitionBy",
 
 #' Group values by key
 #'
-#' This function operates on RDDs where every element is of the form list(K, V).
+#' This function operates on RDDs where every element is of the form list(K, V) or c(K, V).
 #' and group values for each key in the RDD into a single sequence.
 #'
 #' @param rdd The RDD to group. Should be an RDD where each element is
-#'             list(K, V).
+#'             list(K, V) or c(K, V).
 #' @param numPartitions Number of partitions to create.
 #' @return An RDD where each element is list(K, list(V))
 #' @seealso reduceByKey
@@ -1338,7 +1338,7 @@ setMethod("partitionBy",
 #' @examples
 #'\dontrun{
 #' sc <- sparkR.init()
-#' pairs <- list(c(1, 2), c(1.1, 3), c(1, 4))
+#' pairs <- list(list(1, 2), list(1.1, 3), list(1, 4))
 #' rdd <- parallelize(sc, pairs)
 #' parts <- groupByKey(rdd, 2L)
 #' grouped <- collect(parts)
@@ -1384,11 +1384,11 @@ setMethod("groupByKey",
 
 #' Merge values by key
 #'
-#' This function operates on RDDs where every element is of the form list(K, V).
+#' This function operates on RDDs where every element is of the form list(K, V) or c(K, V).
 #' and merges the values for each key using an associative reduce function.
 #'
 #' @param rdd The RDD to reduce by key. Should be an RDD where each element is
-#'             list(K, V).
+#'             list(K, V) or c(K, V).
 #' @param combineFunc The associative reduce function to use.
 #' @param numPartitions Number of partitions to create.
 #' @return An RDD where each element is list(K, V') where V' is the merged
@@ -1399,7 +1399,7 @@ setMethod("groupByKey",
 #' @examples
 #'\dontrun{
 #' sc <- sparkR.init()
-#' pairs <- list(c(1, 2), c(1.1, 3), c(1, 4))
+#' pairs <- list(list(1, 2), list(1.1, 3), list(1, 4))
 #' rdd <- parallelize(sc, pairs)
 #' parts <- reduceByKey(rdd, "+", 2L)
 #' reduced <- collect(parts)
@@ -1456,7 +1456,7 @@ setMethod("reduceByKey",
 #' }
 #'
 #' @param rdd The RDD to combine. Should be an RDD where each element is
-#'             list(K, V).
+#'             list(K, V) or c(K, V).
 #' @param createCombiner Create a combiner (C) given a value (V)
 #' @param mergeValue Merge the given value (V) with an existing combiner (C)
 #' @param mergeCombiners Merge two combiners and return a new combiner
@@ -1469,7 +1469,7 @@ setMethod("reduceByKey",
 #' @examples
 #'\dontrun{
 #' sc <- sparkR.init()
-#' pairs <- list(c(1, 2), c(1.1, 3), c(1, 4))
+#' pairs <- list(list(1, 2), list(1.1, 3), list(1, 4))
 #' rdd <- parallelize(sc, pairs)
 #' parts <- combineByKey(rdd, function(x) { x }, "+", "+", 2L)
 #' combined <- collect(parts)

pkg/man/combineByKey.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.2): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/RDD.R
 \docType{methods}
 \name{combineByKey}
 \alias{combineByKey}
@@ -12,7 +13,7 @@ combineByKey(rdd, createCombiner, mergeValue, mergeCombiners, numPartitions)
 }
 \arguments{
 \item{rdd}{The RDD to combine. Should be an RDD where each element is
-list(K, V).}
+list(K, V) or c(K, V).}
 
 \item{createCombiner}{Create a combiner (C) given a value (V)}
 
@@ -41,7 +42,7 @@ Users provide three functions:
 \examples{
 \dontrun{
 sc <- sparkR.init()
-pairs <- list(c(1, 2), c(1.1, 3), c(1, 4))
+pairs <- list(list(1, 2), list(1.1, 3), list(1, 4))
 rdd <- parallelize(sc, pairs)
 parts <- combineByKey(rdd, function(x) { x }, "+", "+", 2L)
 combined <- collect(parts)

pkg/man/groupByKey.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.2): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/RDD.R
 \docType{methods}
 \name{groupByKey}
 \alias{groupByKey}
@@ -11,21 +12,21 @@ groupByKey(rdd, numPartitions)
 }
 \arguments{
 \item{rdd}{The RDD to group. Should be an RDD where each element is
-list(K, V).}
+list(K, V) or c(K, V).}
 
 \item{numPartitions}{Number of partitions to create.}
 }
 \value{
 An RDD where each element is list(K, list(V))
 }
 \description{
-This function operates on RDDs where every element is of the form list(K, V).
+This function operates on RDDs where every element is of the form list(K, V) or c(K, V).
 and group values for each key in the RDD into a single sequence.
 }
 \examples{
 \dontrun{
 sc <- sparkR.init()
-pairs <- list(c(1, 2), c(1.1, 3), c(1, 4))
+pairs <- list(list(1, 2), list(1.1, 3), list(1, 4))
 rdd <- parallelize(sc, pairs)
 parts <- groupByKey(rdd, 2L)
 grouped <- collect(parts)

pkg/man/partitionBy.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.2): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/RDD.R
 \docType{methods}
 \name{partitionBy}
 \alias{partitionBy}
@@ -12,7 +13,7 @@ partitionBy(rdd, numPartitions, ...)
 }
 \arguments{
 \item{rdd}{The RDD to partition. Should be an RDD where each element is
-list(K, V).}
+list(K, V) or c(K, V).}
 
 \item{numPartitions}{Number of partitions to create.}
 
@@ -25,17 +26,17 @@ function if not provided}
 An RDD partitioned using the specified partitioner.
 }
 \description{
-This function operates on RDDs where every element is of the form list(K, V).
+This function operates on RDDs where every element is of the form list(K, V) or c(K, V).
 For each element of this RDD, the partitioner is used to compute a hash
 function and the RDD is partitioned using this hash value.
 }
 \examples{
 \dontrun{
 sc <- sparkR.init()
-pairs <- list(c(1, 2), c(1.1, 3), c(1, 4))
+pairs <- list(list(1, 2), list(1.1, 3), list(1, 4))
 rdd <- parallelize(sc, pairs)
 parts <- partitionBy(rdd, 2L)
-collectPartition(parts, 0L) # First partition should contain c(1,2) and c(1,3)
+collectPartition(parts, 0L) # First partition should contain list(1, 2) and list(1, 4)
 }
 }
 

pkg/man/reduceByKey.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.2): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/RDD.R
 \docType{methods}
 \name{reduceByKey}
 \alias{reduceByKey}
@@ -12,7 +13,7 @@ reduceByKey(rdd, combineFunc, numPartitions)
 }
 \arguments{
 \item{rdd}{The RDD to reduce by key. Should be an RDD where each element is
-list(K, V).}
+list(K, V) or c(K, V).}
 
 \item{combineFunc}{The associative reduce function to use.}
 
@@ -23,13 +24,13 @@ An RDD where each element is list(K, V') where V' is the merged
         value
 }
 \description{
-This function operates on RDDs where every element is of the form list(K, V).
+This function operates on RDDs where every element is of the form list(K, V) or c(K, V).
 and merges the values for each key using an associative reduce function.
 }
 \examples{
 \dontrun{
 sc <- sparkR.init()
-pairs <- list(c(1, 2), c(1.1, 3), c(1, 4))
+pairs <- list(list(1, 2), list(1.1, 3), list(1, 4))
 rdd <- parallelize(sc, pairs)
 parts <- reduceByKey(rdd, "+", 2L)
 reduced <- collect(parts)