diff options
author | hqzizania <qian.huang@intel.com> | 2015-05-08 11:25:04 -0700 |
---|---|---|
committer | Shivaram Venkataraman <shivaram@cs.berkeley.edu> | 2015-05-08 11:25:04 -0700 |
commit | 008a60dd371e76819d8e08ab638cac7b3a48c9fc (patch) | |
tree | 88293a2d57c6bade201b7bdb3b1ebf0b13fdffcc /R/pkg/R/context.R | |
parent | 65afd3ce8b8a0b00f4ea8294eac14b72e964872d (diff) | |
download | spark-008a60dd371e76819d8e08ab638cac7b3a48c9fc.tar.gz spark-008a60dd371e76819d8e08ab638cac7b3a48c9fc.tar.bz2 spark-008a60dd371e76819d8e08ab638cac7b3a48c9fc.zip |
[SPARK-6824] Fill the docs for DataFrame API in SparkR
This patch also removes the RDD docs from being built as a part of roxygen just by the method to delete
" ' '" of " \#' ".
Author: hqzizania <qian.huang@intel.com>
Author: qhuang <qian.huang@intel.com>
Closes #5969 from hqzizania/R1 and squashes the following commits:
6d27696 [qhuang] fixes in NAMESPACE
eb4b095 [qhuang] remove more docs
6394579 [qhuang] remove RDD docs in generics.R
6813860 [hqzizania] Fill the docs for DataFrame API in SparkR
857220f [hqzizania] remove the pairRDD docs from being built as a part of roxygen
c045d64 [hqzizania] remove the RDD docs from being built as a part of roxygen
Diffstat (limited to 'R/pkg/R/context.R')
-rw-r--r-- | R/pkg/R/context.R | 240 |
1 files changed, 120 insertions, 120 deletions
diff --git a/R/pkg/R/context.R b/R/pkg/R/context.R index b4845b6948..43be9c904f 100644 --- a/R/pkg/R/context.R +++ b/R/pkg/R/context.R @@ -25,27 +25,27 @@ getMinPartitions <- function(sc, minPartitions) { as.integer(minPartitions) } -#' Create an RDD from a text file. -#' -#' This function reads a text file from HDFS, a local file system (available on all -#' nodes), or any Hadoop-supported file system URI, and creates an -#' RDD of strings from it. -#' -#' @param sc SparkContext to use -#' @param path Path of file to read. A vector of multiple paths is allowed. -#' @param minPartitions Minimum number of partitions to be created. If NULL, the default -#' value is chosen based on available parallelism. -#' @return RDD where each item is of type \code{character} -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' lines <- textFile(sc, "myfile.txt") -#'} +# Create an RDD from a text file. +# +# This function reads a text file from HDFS, a local file system (available on all +# nodes), or any Hadoop-supported file system URI, and creates an +# RDD of strings from it. +# +# @param sc SparkContext to use +# @param path Path of file to read. A vector of multiple paths is allowed. +# @param minPartitions Minimum number of partitions to be created. If NULL, the default +# value is chosen based on available parallelism. +# @return RDD where each item is of type \code{character} +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# lines <- textFile(sc, "myfile.txt") +#} textFile <- function(sc, path, minPartitions = NULL) { # Allow the user to have a more flexible definiton of the text file path path <- suppressWarnings(normalizePath(path)) - #' Convert a string vector of paths to a string containing comma separated paths + # Convert a string vector of paths to a string containing comma separated paths path <- paste(path, collapse = ",") jrdd <- callJMethod(sc, "textFile", path, getMinPartitions(sc, minPartitions)) @@ -53,27 +53,27 @@ textFile <- function(sc, path, minPartitions = NULL) { RDD(jrdd, "string") } -#' Load an RDD saved as a SequenceFile containing serialized objects. -#' -#' The file to be loaded should be one that was previously generated by calling -#' saveAsObjectFile() of the RDD class. -#' -#' @param sc SparkContext to use -#' @param path Path of file to read. A vector of multiple paths is allowed. -#' @param minPartitions Minimum number of partitions to be created. If NULL, the default -#' value is chosen based on available parallelism. -#' @return RDD containing serialized R objects. -#' @seealso saveAsObjectFile -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- objectFile(sc, "myfile") -#'} +# Load an RDD saved as a SequenceFile containing serialized objects. +# +# The file to be loaded should be one that was previously generated by calling +# saveAsObjectFile() of the RDD class. +# +# @param sc SparkContext to use +# @param path Path of file to read. A vector of multiple paths is allowed. +# @param minPartitions Minimum number of partitions to be created. If NULL, the default +# value is chosen based on available parallelism. +# @return RDD containing serialized R objects. +# @seealso saveAsObjectFile +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- objectFile(sc, "myfile") +#} objectFile <- function(sc, path, minPartitions = NULL) { # Allow the user to have a more flexible definiton of the text file path path <- suppressWarnings(normalizePath(path)) - #' Convert a string vector of paths to a string containing comma separated paths + # Convert a string vector of paths to a string containing comma separated paths path <- paste(path, collapse = ",") jrdd <- callJMethod(sc, "objectFile", path, getMinPartitions(sc, minPartitions)) @@ -81,24 +81,24 @@ objectFile <- function(sc, path, minPartitions = NULL) { RDD(jrdd, "byte") } -#' Create an RDD from a homogeneous list or vector. -#' -#' This function creates an RDD from a local homogeneous list in R. The elements -#' in the list are split into \code{numSlices} slices and distributed to nodes -#' in the cluster. -#' -#' @param sc SparkContext to use -#' @param coll collection to parallelize -#' @param numSlices number of partitions to create in the RDD -#' @return an RDD created from this collection -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:10, 2) -#' # The RDD should contain 10 elements -#' length(rdd) -#'} +# Create an RDD from a homogeneous list or vector. +# +# This function creates an RDD from a local homogeneous list in R. The elements +# in the list are split into \code{numSlices} slices and distributed to nodes +# in the cluster. +# +# @param sc SparkContext to use +# @param coll collection to parallelize +# @param numSlices number of partitions to create in the RDD +# @return an RDD created from this collection +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:10, 2) +# # The RDD should contain 10 elements +# length(rdd) +#} parallelize <- function(sc, coll, numSlices = 1) { # TODO: bound/safeguard numSlices # TODO: unit tests for if the split works for all primitives @@ -133,33 +133,33 @@ parallelize <- function(sc, coll, numSlices = 1) { RDD(jrdd, "byte") } -#' Include this specified package on all workers -#' -#' This function can be used to include a package on all workers before the -#' user's code is executed. This is useful in scenarios where other R package -#' functions are used in a function passed to functions like \code{lapply}. -#' NOTE: The package is assumed to be installed on every node in the Spark -#' cluster. -#' -#' @param sc SparkContext to use -#' @param pkg Package name -#' -#' @export -#' @examples -#'\dontrun{ -#' library(Matrix) -#' -#' sc <- sparkR.init() -#' # Include the matrix library we will be using -#' includePackage(sc, Matrix) -#' -#' generateSparse <- function(x) { -#' sparseMatrix(i=c(1, 2, 3), j=c(1, 2, 3), x=c(1, 2, 3)) -#' } -#' -#' rdd <- lapplyPartition(parallelize(sc, 1:2, 2L), generateSparse) -#' collect(rdd) -#'} +# Include this specified package on all workers +# +# This function can be used to include a package on all workers before the +# user's code is executed. This is useful in scenarios where other R package +# functions are used in a function passed to functions like \code{lapply}. +# NOTE: The package is assumed to be installed on every node in the Spark +# cluster. +# +# @param sc SparkContext to use +# @param pkg Package name +# +# @export +# @examples +#\dontrun{ +# library(Matrix) +# +# sc <- sparkR.init() +# # Include the matrix library we will be using +# includePackage(sc, Matrix) +# +# generateSparse <- function(x) { +# sparseMatrix(i=c(1, 2, 3), j=c(1, 2, 3), x=c(1, 2, 3)) +# } +# +# rdd <- lapplyPartition(parallelize(sc, 1:2, 2L), generateSparse) +# collect(rdd) +#} includePackage <- function(sc, pkg) { pkg <- as.character(substitute(pkg)) if (exists(".packages", .sparkREnv)) { @@ -171,30 +171,30 @@ includePackage <- function(sc, pkg) { .sparkREnv$.packages <- packages } -#' @title Broadcast a variable to all workers -#' -#' @description -#' Broadcast a read-only variable to the cluster, returning a \code{Broadcast} -#' object for reading it in distributed functions. -#' -#' @param sc Spark Context to use -#' @param object Object to be broadcast -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' rdd <- parallelize(sc, 1:2, 2L) -#' -#' # Large Matrix object that we want to broadcast -#' randomMat <- matrix(nrow=100, ncol=10, data=rnorm(1000)) -#' randomMatBr <- broadcast(sc, randomMat) -#' -#' # Use the broadcast variable inside the function -#' useBroadcast <- function(x) { -#' sum(value(randomMatBr) * x) -#' } -#' sumRDD <- lapply(rdd, useBroadcast) -#'} +# @title Broadcast a variable to all workers +# +# @description +# Broadcast a read-only variable to the cluster, returning a \code{Broadcast} +# object for reading it in distributed functions. +# +# @param sc Spark Context to use +# @param object Object to be broadcast +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# rdd <- parallelize(sc, 1:2, 2L) +# +# # Large Matrix object that we want to broadcast +# randomMat <- matrix(nrow=100, ncol=10, data=rnorm(1000)) +# randomMatBr <- broadcast(sc, randomMat) +# +# # Use the broadcast variable inside the function +# useBroadcast <- function(x) { +# sum(value(randomMatBr) * x) +# } +# sumRDD <- lapply(rdd, useBroadcast) +#} broadcast <- function(sc, object) { objName <- as.character(substitute(object)) serializedObj <- serialize(object, connection = NULL) @@ -205,21 +205,21 @@ broadcast <- function(sc, object) { Broadcast(id, object, jBroadcast, objName) } -#' @title Set the checkpoint directory -#' -#' Set the directory under which RDDs are going to be checkpointed. The -#' directory must be a HDFS path if running on a cluster. -#' -#' @param sc Spark Context to use -#' @param dirName Directory path -#' @export -#' @examples -#'\dontrun{ -#' sc <- sparkR.init() -#' setCheckpointDir(sc, "~/checkpoint") -#' rdd <- parallelize(sc, 1:2, 2L) -#' checkpoint(rdd) -#'} +# @title Set the checkpoint directory +# +# Set the directory under which RDDs are going to be checkpointed. The +# directory must be a HDFS path if running on a cluster. +# +# @param sc Spark Context to use +# @param dirName Directory path +# @export +# @examples +#\dontrun{ +# sc <- sparkR.init() +# setCheckpointDir(sc, "~/checkpoint") +# rdd <- parallelize(sc, 1:2, 2L) +# checkpoint(rdd) +#} setCheckpointDir <- function(sc, dirName) { invisible(callJMethod(sc, "setCheckpointDir", suppressWarnings(normalizePath(dirName)))) } |