From b73defdd790cb823a4f9958ca89cec06fd198051 Mon Sep 17 00:00:00 2001
From: Felix Cheung <felixcheung_m@hotmail.com>
Date: Mon, 25 Jul 2016 11:25:41 -0700
Subject: [PATCH] [SPARKR][DOCS] fix broken url in doc
## What changes were proposed in this pull request?
Fix broken url, also,
sparkR.session.stop doc page should have it in the header, instead of saying "sparkR.stop"
Data type section is in the middle of a list of gapply/gapplyCollect subsections:
## How was this patch tested?
manual test
Author: Felix Cheung <felixcheung_m@hotmail.com>
Closes #14329 from felixcheung/rdoclinkfix.
---
R/pkg/R/DataFrame.R | 2 +-
R/pkg/R/sparkR.R | 16 +++----
docs/sparkr.md | 107 ++++++++++++++++++++++----------------------
3 files changed, 62 insertions(+), 63 deletions(-)
diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R
index 2e99aa026d..a4733313ed 100644
--- a/R/pkg/R/DataFrame.R
+++ b/R/pkg/R/DataFrame.R
@@ -35,7 +35,7 @@ setOldClass("structType")
#' @slot env An R environment that stores bookkeeping states of the SparkDataFrame
#' @slot sdf A Java object reference to the backing Scala DataFrame
#' @seealso \link{createDataFrame}, \link{read.json}, \link{table}
-#' @seealso \url{https://spark.apache.org/docs/latest/sparkr.html#sparkdataframe}
+#' @seealso \url{https://spark.apache.org/docs/latest/sparkr.html#sparkr-dataframes}
#' @export
#' @examples
#'\dontrun{
diff --git a/R/pkg/R/sparkR.R b/R/pkg/R/sparkR.R
index ff5297ffd5..524f7c4a26 100644
--- a/R/pkg/R/sparkR.R
+++ b/R/pkg/R/sparkR.R
@@ -28,14 +28,6 @@ connExists <- function(env) {
})
}
-#' @rdname sparkR.session.stop
-#' @name sparkR.stop
-#' @export
-#' @note sparkR.stop since 1.4.0
-sparkR.stop <- function() {
- sparkR.session.stop()
-}
-
#' Stop the Spark Session and Spark Context
#'
#' Stop the Spark Session and Spark Context.
@@ -90,6 +82,14 @@ sparkR.session.stop <- function() {
clearJobjs()
}
+#' @rdname sparkR.session.stop
+#' @name sparkR.stop
+#' @export
+#' @note sparkR.stop since 1.4.0
+sparkR.stop <- function() {
+ sparkR.session.stop()
+}
+
#' (Deprecated) Initialize a new Spark Context
#'
#' This function initializes a new SparkContext.
diff --git a/docs/sparkr.md b/docs/sparkr.md
index dfa5278ef8..4bbc362c52 100644
--- a/docs/sparkr.md
+++ b/docs/sparkr.md
@@ -322,8 +322,59 @@ head(ldf, 3)
Apply a function to each group of a `SparkDataFrame`. The function is to be applied to each group of the `SparkDataFrame` and should have only two parameters: grouping key and R `data.frame` corresponding to
that key. The groups are chosen from `SparkDataFrame`s column(s).
The output of function should be a `data.frame`. Schema specifies the row format of the resulting
-`SparkDataFrame`. It must represent R function's output schema on the basis of Spark data types. The column names of the returned `data.frame` are set by user. Below is the data type mapping between R
-and Spark.
+`SparkDataFrame`. It must represent R function's output schema on the basis of Spark [data types](#data-type-mapping-between-r-and-spark). The column names of the returned `data.frame` are set by user.
+
+<div data-lang="r" markdown="1">
+{% highlight r %}
+
+# Determine six waiting times with the largest eruption time in minutes.
+schema <- structType(structField("waiting", "double"), structField("max_eruption", "double"))
+result <- gapply(
+ df,
+ "waiting",
+ function(key, x) {
+ y <- data.frame(key, max(x$eruptions))
+ },
+ schema)
+head(collect(arrange(result, "max_eruption", decreasing = TRUE)))
+
+## waiting max_eruption
+##1 64 5.100
+##2 69 5.067
+##3 71 5.033
+##4 87 5.000
+##5 63 4.933
+##6 89 4.900
+{% endhighlight %}
+</div>
+
+##### gapplyCollect
+Like `gapply`, applies a function to each partition of a `SparkDataFrame` and collect the result back to R data.frame. The output of the function should be a `data.frame`. But, the schema is not required to be passed. Note that `gapplyCollect` can fail if the output of UDF run on all the partition cannot be pulled to the driver and fit in driver memory.
+
+<div data-lang="r" markdown="1">
+{% highlight r %}
+
+# Determine six waiting times with the largest eruption time in minutes.
+result <- gapplyCollect(
+ df,
+ "waiting",
+ function(key, x) {
+ y <- data.frame(key, max(x$eruptions))
+ colnames(y) <- c("waiting", "max_eruption")
+ y
+ })
+head(result[order(result$max_eruption, decreasing = TRUE), ])
+
+## waiting max_eruption
+##1 64 5.100
+##2 69 5.067
+##3 71 5.033
+##4 87 5.000
+##5 63 4.933
+##6 89 4.900
+
+{% endhighlight %}
+</div>
#### Data type mapping between R and Spark
<table class="table">
@@ -394,58 +445,6 @@ and Spark.
</tr>
</table>
-<div data-lang="r" markdown="1">
-{% highlight r %}
-
-# Determine six waiting times with the largest eruption time in minutes.
-schema <- structType(structField("waiting", "double"), structField("max_eruption", "double"))
-result <- gapply(
- df,
- "waiting",
- function(key, x) {
- y <- data.frame(key, max(x$eruptions))
- },
- schema)
-head(collect(arrange(result, "max_eruption", decreasing = TRUE)))
-
-## waiting max_eruption
-##1 64 5.100
-##2 69 5.067
-##3 71 5.033
-##4 87 5.000
-##5 63 4.933
-##6 89 4.900
-{% endhighlight %}
-</div>
-
-##### gapplyCollect
-Like `gapply`, applies a function to each partition of a `SparkDataFrame` and collect the result back to R data.frame. The output of the function should be a `data.frame`. But, the schema is not required to be passed. Note that `gapplyCollect` can fail if the output of UDF run on all the partition cannot be pulled to the driver and fit in driver memory.
-
-<div data-lang="r" markdown="1">
-{% highlight r %}
-
-# Determine six waiting times with the largest eruption time in minutes.
-result <- gapplyCollect(
- df,
- "waiting",
- function(key, x) {
- y <- data.frame(key, max(x$eruptions))
- colnames(y) <- c("waiting", "max_eruption")
- y
- })
-head(result[order(result$max_eruption, decreasing = TRUE), ])
-
-## waiting max_eruption
-##1 64 5.100
-##2 69 5.067
-##3 71 5.033
-##4 87 5.000
-##5 63 4.933
-##6 89 4.900
-
-{% endhighlight %}
-</div>
-
#### Run local R functions distributed using `spark.lapply`
##### spark.lapply
--
GitLab