More fixes of the docs.

R/pkg/R/DataFrame.R

@@ -177,7 +177,7 @@ setMethod("isLocal",
 #' Print the first numRows rows of a SparkDataFrame
 #'
 #' @param numRows the number of rows to print. Defaults to 20.
-#' @param truncate whether truncate long strings. If true, strings more than 20 characters will be
+#' @param truncate whether truncate long strings. If \code{TRUE}, strings more than 20 characters will be
 #'    truncated. However, if set greater than zero, truncates strings longer than `truncate`
 #'    characters and all cells will be aligned right.
 #' @family SparkDataFrame functions
@@ -916,6 +916,7 @@ setMethod("sample_frac",
 
 #' Returns the number of rows in a SparkDataFrame
 #'
+#' @param x a SparkDataFrame.
 #' @family SparkDataFrame functions
 #' @rdname nrow
 #' @name count
@@ -2847,7 +2848,7 @@ setMethod("fillna",
 #' @param x a SparkDataFrame.
 #' @param row.names NULL or a character vector giving the row names for the data frame.
 #' @param optional If `TRUE`, converting column names is optional.
-#' @param ... additional arguments passed to the method.
+#' @param ... additional arguments to pass to base::as.data.frame.
 #' @return A data.frame.
 #' @family SparkDataFrame functions
 #' @aliases as.data.frame,SparkDataFrame-method
@@ -3050,7 +3051,7 @@ setMethod("drop",
 #'
 #' @name histogram
 #' @param nbins the number of bins (optional). Default value is 10.
-#' @param col the column (described by character or Column object) to build the histogram from.
+#' @param col the column as Character string or a Column to build the histogram from.
 #' @param df the SparkDataFrame containing the Column to build the histogram from.
 #' @return a data.frame with the histogram statistics, i.e., counts and centroids.
 #' @rdname histogram
@@ -3185,7 +3186,7 @@ setMethod("histogram",
 #' @param x A SparkDataFrame
 #' @param url JDBC database url of the form `jdbc:subprotocol:subname`
 #' @param tableName The name of the table in the external database
-#' @param ... additional argument(s) passed to the method
+#' @param ... additional JDBC database connection propertie(s).
 #' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode (it is 'error' by default)
 #' @family SparkDataFrame functions
 #' @rdname write.jdbc

R/pkg/R/SQLContext.R

@@ -260,12 +260,13 @@ createDataFrame <- function(x, ...) {
   dispatchFunc("createDataFrame(data, schema = NULL)", x, ...)
 }
 
+#' @param samplingRatio Currently not used.
 #' @rdname createDataFrame
 #' @aliases createDataFrame
 #' @export
 #' @method as.DataFrame default
 #' @note as.DataFrame since 1.6.0
-as.DataFrame.default <- function(data, schema = NULL) {
+as.DataFrame.default <- function(data, schema = NULL, samplingRatio = 1.0) {
   createDataFrame(data, schema)
 }
 
@@ -729,7 +730,7 @@ dropTempView <- function(viewName) {
 #' @param source The name of external data source
 #' @param schema The data schema defined in structType
 #' @param na.strings Default string value for NA when source is "csv"
-#' @param ... additional argument(s) passed to the method.
+#' @param ... additional external data source specific named propertie(s).
 #' @return SparkDataFrame
 #' @rdname read.df
 #' @name read.df
@@ -844,7 +845,7 @@ createExternalTable <- function(x, ...) {
 #'                      clause expressions used to split the column `partitionColumn` evenly.
 #'                      This defaults to SparkContext.defaultParallelism when unset.
 #' @param predicates a list of conditions in the where clause; each one defines one partition
-#' @param ... additional argument(s) passed to the method.
+#' @param ... additional JDBC database connection named propertie(s).
 #' @return SparkDataFrame
 #' @rdname read.jdbc
 #' @name read.jdbc

R/pkg/R/functions.R

@@ -445,8 +445,8 @@ setMethod("cosh",
 #'
 #' Returns the number of items in a group. This is a column aggregate function.
 #'
-#' @rdname nrow
-#' @name count
+#' @rdname n
+#' @name n
 #' @family agg_funcs
 #' @aliases count,Column-method
 #' @export
@@ -1272,9 +1272,9 @@ setMethod("round",
 #' bround(2.5, 0) = 2, bround(3.5, 0) = 4.
 #'
 #' @param x Column to compute on.
-#' @param scale round to `scale` digits to the right of the decimal point when `scale` > 0,
-#'        the nearest even number when `scale` = 0, and `scale` digits to the left
-#'        of the decimal point when `scale` <= 0.
+#' @param scale round to \code{scale} digits to the right of the decimal point when \code{scale} > 0,
+#'        the nearest even number when \code{scale} = 0, and `scale` digits to the left
+#'        of the decimal point when \code{scale} < 0.
 #' @rdname bround
 #' @name bround
 #' @family math_funcs
@@ -1557,7 +1557,7 @@ setMethod("stddev_samp",
 #' Creates a new struct column that composes multiple input columns.
 #'
 #' @param x a column to compute on.
-#' @param ... additional column(s) to be included.
+#' @param ... optional column(s) to be included.
 #'
 #' @rdname struct
 #' @name struct
@@ -2269,8 +2269,8 @@ setMethod("n_distinct", signature(x = "Column"),
             countDistinct(x, ...)
           })
 
-#' @rdname nrow
-#'
+#' @param x a Column.
+#' @rdname n
 #' @name n
 #' @aliases n,Column-method
 #' @export
@@ -2649,7 +2649,7 @@ setMethod("expr", signature(x = "character"),
 #'
 #' @param format a character object of format strings.
 #' @param x a Column object.
-#' @param ... additional columns.
+#' @param ... additional Column(s).
 #' @family string_funcs
 #' @rdname format_string
 #' @name format_string
@@ -3034,8 +3034,8 @@ setMethod("when", signature(condition = "Column", value = "ANY"),
 #' Otherwise \code{no} is returned for unmatched conditions.
 #'
 #' @param test a Column expression that describes the condition.
-#' @param yes return values for true elements of test.
-#' @param no return values for false elements of test.
+#' @param yes return values for \code{TRUE} elements of test.
+#' @param no return values for \code{FALSE} elements of test.
 #' @family normal_funcs
 #' @rdname ifelse
 #' @name ifelse

R/pkg/R/generics.R

@@ -51,7 +51,7 @@ setGeneric("collectPartition",
              standardGeneric("collectPartition")
            })
 
-# @rdname nrow
+# @rdname count
 # @export
 setGeneric("count", function(x) { standardGeneric("count") })
 
@@ -1059,8 +1059,7 @@ setGeneric("month", function(x) { standardGeneric("month") })
 #' @export
 setGeneric("months_between", function(y, x) { standardGeneric("months_between") })
 
-#' @param x a SparkDataFrame or a Column object.
-#' @rdname nrow
+#' @rdname n
 #' @export
 setGeneric("n", function(x) { standardGeneric("n") })
 
@@ -1315,7 +1314,7 @@ setGeneric("spark.naiveBayes", function(data, formula, ...) { standardGeneric("s
 
 #' @rdname spark.survreg
 #' @export
-setGeneric("spark.survreg", function(data, formula, ...) { standardGeneric("spark.survreg") })
+setGeneric("spark.survreg", function(data, formula) { standardGeneric("spark.survreg") })
 
 #' @rdname write.ml
 #' @export

R/pkg/R/group.R

@@ -59,8 +59,8 @@ setMethod("show", "GroupedData",
 #' Count the number of rows for each group.
 #' The resulting SparkDataFrame will also contain the grouping columns.
 #'
-#' @param x a GroupedData
-#' @return a SparkDataFrame
+#' @param x a GroupedData.
+#' @return A SparkDataFrame.
 #' @rdname count
 #' @aliases count,GroupedData-method
 #' @export

R/pkg/R/mllib.R

@@ -354,8 +354,8 @@ setMethod("spark.kmeans", signature(data = "SparkDataFrame", formula = "formula"
 #' Note: A saved-loaded model does not support this method.
 #'
 #' @param object a fitted k-means model.
-#' @param method type of fitted results, `"centers"` for cluster centers
-#'        or `"classes"` for assigned classes.
+#' @param method type of fitted results, \code{"centers"} for cluster centers
+#'        or \code{"classes"} for assigned classes.
 #' @param ... additional argument(s) passed to the method.
 #' @return \code{fitted} returns a SparkDataFrame containing fitted values.
 #' @rdname fitted
@@ -428,8 +428,8 @@ setMethod("predict", signature(object = "KMeansModel"),
 #' @param data a \code{SparkDataFrame} of observations and labels for model fitting.
 #' @param formula a symbolic description of the model to be fitted. Currently only a few formula
 #'               operators are supported, including '~', '.', ':', '+', and '-'.
+#' @param ... additional argument(s) passed to the method. Currently only \code{smoothing}.
 #' @param smoothing smoothing parameter.
-#' @param ... additional parameter(s) passed to the method.
 #' @return \code{spark.naiveBayes} returns a fitted naive Bayes model.
 #' @rdname spark.naiveBayes
 #' @aliases spark.naiveBayes,SparkDataFrame,formula-method
@@ -457,7 +457,7 @@ setMethod("predict", signature(object = "KMeansModel"),
 #' }
 #' @note spark.naiveBayes since 2.0.0
 setMethod("spark.naiveBayes", signature(data = "SparkDataFrame", formula = "formula"),
-          function(data, formula, smoothing = 1.0, ...) {
+          function(data, formula, smoothing = 1.0) {
             formula <- paste(deparse(formula), collapse = "")
             jobj <- callJStatic("org.apache.spark.ml.r.NaiveBayesWrapper", "fit",
             formula, data@sdf, smoothing)
@@ -577,8 +577,7 @@ read.ml <- function(path) {
 #' @param data a SparkDataFrame for training.
 #' @param formula a symbolic description of the model to be fitted. Currently only a few formula
 #'                operators are supported, including '~', ':', '+', and '-'.
-#'                Note that operator '.' is not supported currently
-#' @param ... additional argument(s) passed to the method.
+#'                Note that operator '.' is not supported currently.
 #' @return \code{spark.survreg} returns a fitted AFT survival regression model.
 #' @rdname spark.survreg
 #' @seealso survival: \url{https://cran.r-project.org/web/packages/survival/}
@@ -603,7 +602,7 @@ read.ml <- function(path) {
 #' }
 #' @note spark.survreg since 2.0.0
 setMethod("spark.survreg", signature(data = "SparkDataFrame", formula = "formula"),
-          function(data, formula, ...) {
+          function(data, formula) {
             formula <- paste(deparse(formula), collapse = "")
             jobj <- callJStatic("org.apache.spark.ml.r.AFTSurvivalRegressionWrapper",
                                 "fit", formula, data@sdf)

R/pkg/R/sparkR.R

@@ -320,15 +320,15 @@ sparkRHive.init <- function(jsc = NULL) {
 #' For details on how to initialize and use SparkR, refer to SparkR programming guide at
 #' \url{http://spark.apache.org/docs/latest/sparkr.html#starting-up-sparksession}.
 #'
-#' @param master The Spark master URL
-#' @param appName Application name to register with cluster manager
-#' @param sparkHome Spark Home directory
-#' @param sparkConfig Named list of Spark configuration to set on worker nodes
-#' @param sparkJars Character vector of jar files to pass to the worker nodes
-#' @param sparkPackages Character vector of packages from spark-packages.org
-#' @param enableHiveSupport Enable support for Hive, fallback if not built with Hive support; once
+#' @param master the Spark master URL.
+#' @param appName application name to register with cluster manager.
+#' @param sparkHome Spark Home directory.
+#' @param sparkConfig named list of Spark configuration to set on worker nodes.
+#' @param sparkJars character vector of jar files to pass to the worker nodes.
+#' @param sparkPackages character vector of packages from spark-packages.org
+#' @param enableHiveSupport enable support for Hive, fallback if not built with Hive support; once
 #'        set, this cannot be turned off on an existing session
-#' @param ... additional parameters passed to the method
+#' @param ... named Spark properties passed to the method.
 #' @export
 #' @examples
 #'\dontrun{