diff options
Diffstat (limited to 'R/pkg/R/SQLContext.R')
-rw-r--r-- | R/pkg/R/SQLContext.R | 66 |
1 files changed, 32 insertions, 34 deletions
diff --git a/R/pkg/R/SQLContext.R b/R/pkg/R/SQLContext.R index 1bf025cce4..fd013fdb30 100644 --- a/R/pkg/R/SQLContext.R +++ b/R/pkg/R/SQLContext.R @@ -144,7 +144,6 @@ createDataFrame <- function(sqlContext, data, schema = NULL, samplingRatio = 1.0 } stopifnot(class(schema) == "structType") - # schemaString <- tojson(schema) jrdd <- getJRDD(lapply(rdd, function(x) x), "row") srdd <- callJMethod(jrdd, "rdd") @@ -160,22 +159,21 @@ as.DataFrame <- function(sqlContext, data, schema = NULL, samplingRatio = 1.0) { createDataFrame(sqlContext, data, schema, samplingRatio) } -# toDF -# -# Converts an RDD to a DataFrame by infer the types. -# -# @param x An RDD -# -# @rdname DataFrame -# @export -# @examples -#\dontrun{ -# sc <- sparkR.init() -# sqlContext <- sparkRSQL.init(sc) -# rdd <- lapply(parallelize(sc, 1:10), function(x) list(a=x, b=as.character(x))) -# df <- toDF(rdd) -# } - +#' toDF +#' +#' Converts an RDD to a DataFrame by infer the types. +#' +#' @param x An RDD +#' +#' @rdname DataFrame +#' @noRd +#' @examples +#'\dontrun{ +#' sc <- sparkR.init() +#' sqlContext <- sparkRSQL.init(sc) +#' rdd <- lapply(parallelize(sc, 1:10), function(x) list(a=x, b=as.character(x))) +#' df <- toDF(rdd) +#'} setGeneric("toDF", function(x, ...) { standardGeneric("toDF") }) setMethod("toDF", signature(x = "RDD"), @@ -217,23 +215,23 @@ jsonFile <- function(sqlContext, path) { } -# JSON RDD -# -# Loads an RDD storing one JSON object per string as a DataFrame. -# -# @param sqlContext SQLContext to use -# @param rdd An RDD of JSON string -# @param schema A StructType object to use as schema -# @param samplingRatio The ratio of simpling used to infer the schema -# @return A DataFrame -# @export -# @examples -#\dontrun{ -# sc <- sparkR.init() -# sqlContext <- sparkRSQL.init(sc) -# rdd <- texFile(sc, "path/to/json") -# df <- jsonRDD(sqlContext, rdd) -# } +#' JSON RDD +#' +#' Loads an RDD storing one JSON object per string as a DataFrame. +#' +#' @param sqlContext SQLContext to use +#' @param rdd An RDD of JSON string +#' @param schema A StructType object to use as schema +#' @param samplingRatio The ratio of simpling used to infer the schema +#' @return A DataFrame +#' @noRd +#' @examples +#'\dontrun{ +#' sc <- sparkR.init() +#' sqlContext <- sparkRSQL.init(sc) +#' rdd <- texFile(sc, "path/to/json") +#' df <- jsonRDD(sqlContext, rdd) +#'} # TODO: support schema jsonRDD <- function(sqlContext, rdd, schema = NULL, samplingRatio = 1.0) { |