ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[SPARK-11294][SPARKR] Improve R doc for read.df, write.df, saveAsTable

Browse source 
Add examples for read.df, write.df; fix grouping for read.df, loadDF; fix formatting and text truncation for write.df, saveAsTable.

Several text issues:
![image](https://cloud.githubusercontent.com/assets/8969467/10708590/1303a44e-79c3-11e5-854f-3a2e16854cd7.png)
- text collapsed into a single paragraph
- text truncated at 2 places, eg. "overwrite: Existing data is expected to be overwritten by the contents of error:"

shivaram

Author: felixcheung <felixcheung_m@hotmail.com>

Closes #9261 from felixcheung/rdocreadwritedf.
This commit is contained in:
felixcheung 2015-10-23 21:42:00 -07:00 committed by Shivaram Venkataraman
parent 2462dbcce8
commit 5e45812501
2 changed files with 24 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
R/pkg/R/DataFrame.R
View file

@ -1572,18 +1572,17 @@ setMethod("except",
#' spark.sql.sources.default will be used.
#'
#' Additionally, mode is used to specify the behavior of the save operation when
#' data already exists in the data source. There are four modes:
#' append: Contents of this DataFrame are expected to be appended to existing data.
#' overwrite: Existing data is expected to be overwritten by the contents of
# this DataFrame.
#' error: An exception is expected to be thrown.
#' data already exists in the data source. There are four modes: \cr
#' append: Contents of this DataFrame are expected to be appended to existing data. \cr
#' overwrite: Existing data is expected to be overwritten by the contents of this DataFrame. \cr
#' error: An exception is expected to be thrown. \cr
#' ignore: The save operation is expected to not save the contents of the DataFrame
# and to not change the existing data.
#' and to not change the existing data. \cr
#'
#' @param df A SparkSQL DataFrame
#' @param path A name for the table
#' @param source A name for external data source
#' @param mode One of 'append', 'overwrite', 'error', 'ignore'
#' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode
#'
#' @rdname write.df
#' @name write.df
@ -1596,6 +1595,7 @@ setMethod("except",
#' path <- "path/to/file.json"
#' df <- jsonFile(sqlContext, path)
#' write.df(df, "myfile", "parquet", "overwrite")
#' saveDF(df, parquetPath2, "parquet", mode = saveMode, mergeSchema = mergeSchema)
#' }
setMethod("write.df",
signature(df = "DataFrame", path = "character"),
@ -1637,18 +1637,17 @@ setMethod("saveDF",
#' spark.sql.sources.default will be used.
#'
#' Additionally, mode is used to specify the behavior of the save operation when
#' data already exists in the data source. There are four modes:
#' append: Contents of this DataFrame are expected to be appended to existing data.
#' overwrite: Existing data is expected to be overwritten by the contents of
# this DataFrame.
#' error: An exception is expected to be thrown.
#' data already exists in the data source. There are four modes: \cr
#' append: Contents of this DataFrame are expected to be appended to existing data. \cr
#' overwrite: Existing data is expected to be overwritten by the contents of this DataFrame. \cr
#' error: An exception is expected to be thrown. \cr
#' ignore: The save operation is expected to not save the contents of the DataFrame
# and to not change the existing data.
#' and to not change the existing data. \cr
#'
#' @param df A SparkSQL DataFrame
#' @param tableName A name for the table
#' @param source A name for external data source
#' @param mode One of 'append', 'overwrite', 'error', 'ignore'
#' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode
#'
#' @rdname saveAsTable
#' @name saveAsTable

16
R/pkg/R/SQLContext.R
View file

@ -452,14 +452,21 @@ dropTempTable <- function(sqlContext, tableName) {
#'
#' @param sqlContext SQLContext to use
#' @param path The path of files to load
#' @param source the name of external data source
#' @param source The name of external data source
#' @param schema The data schema defined in structType
#' @return DataFrame
#' @rdname read.df
#' @name read.df
#' @export
#' @examples
#'\dontrun{
#' sc <- sparkR.init()
#' sqlContext <- sparkRSQL.init(sc)
#' df <- read.df(sqlContext, "path/to/file.json", source = "json")
#' df1 <- read.df(sqlContext, "path/to/file.json", source = "json")
#' schema <- structType(structField("name", "string"),
#' structField("info", "map<string,double>"))
#' df2 <- read.df(sqlContext, mapTypeJsonPath, "json", schema)
#' df3 <- loadDF(sqlContext, "data/test_table", "parquet", mergeSchema = "true")
#' }
read.df <- function(sqlContext, path = NULL, source = NULL, schema = NULL, ...) {
@ -482,9 +489,8 @@ read.df <- function(sqlContext, path = NULL, source = NULL, schema = NULL, ...)
dataFrame(sdf)
}
#' @aliases loadDF
#' @export
#' @rdname read.df
#' @name loadDF
loadDF <- function(sqlContext, path = NULL, source = NULL, schema = NULL, ...) {
read.df(sqlContext, path, source, schema, ...)
}