[SPARKR][DOCS] R code doc cleanup

## What changes were proposed in this pull request?

I ran a full pass from A to Z and fixed the obvious duplications, improper grouping etc.

There are still more doc issues to be cleaned up.

## How was this patch tested?

manual tests

Author: Felix Cheung <[email protected]>

Closes #13798 from felixcheung/rdocseealso.

Author: felixcheung

R/pkg/R/DataFrame.R

@@ -463,6 +463,7 @@ setMethod("createOrReplaceTempView",
           })
 
 #' (Deprecated) Register Temporary Table
+#'
 #' Registers a SparkDataFrame as a Temporary Table in the SQLContext
 #' @param x A SparkDataFrame
 #' @param tableName A character vector containing the name of the table
@@ -606,10 +607,10 @@ setMethod("unpersist",
 #'
 #' The following options for repartition are possible:
 #' \itemize{
-#'  \item{"Option 1"} {Return a new SparkDataFrame partitioned by
+#'  \item{1.} {Return a new SparkDataFrame partitioned by
 #'                      the given columns into `numPartitions`.}
-#'  \item{"Option 2"} {Return a new SparkDataFrame that has exactly `numPartitions`.}
-#'  \item{"Option 3"} {Return a new SparkDataFrame partitioned by the given column(s),
+#'  \item{2.} {Return a new SparkDataFrame that has exactly `numPartitions`.}
+#'  \item{3.} {Return a new SparkDataFrame partitioned by the given column(s),
 #'                      using `spark.sql.shuffle.partitions` as number of partitions.}
 #'}
 #' @param x A SparkDataFrame
@@ -1053,7 +1054,7 @@ setMethod("limit",
             dataFrame(res)
           })
 
-#' Take the first NUM rows of a SparkDataFrame and return a the results as a data.frame
+#' Take the first NUM rows of a SparkDataFrame and return a the results as a R data.frame
 #'
 #' @family SparkDataFrame functions
 #' @rdname take
@@ -1076,7 +1077,7 @@ setMethod("take",
 
 #' Head
 #'
-#' Return the first NUM rows of a SparkDataFrame as a data.frame. If NUM is NULL,
+#' Return the first NUM rows of a SparkDataFrame as a R data.frame. If NUM is NULL,
 #' then head() returns the first 6 rows in keeping with the current data.frame
 #' convention in R.
 #'
@@ -1157,7 +1158,6 @@ setMethod("toRDD",
 #'
 #' @param x a SparkDataFrame
 #' @return a GroupedData
-#' @seealso GroupedData
 #' @family SparkDataFrame functions
 #' @rdname groupBy
 #' @name groupBy
@@ -1242,9 +1242,9 @@ dapplyInternal <- function(x, func, schema) {
 #'
 #' @param x A SparkDataFrame
 #' @param func A function to be applied to each partition of the SparkDataFrame.
-#'             func should have only one parameter, to which a data.frame corresponds
+#'             func should have only one parameter, to which a R data.frame corresponds
 #'             to each partition will be passed.
-#'             The output of func should be a data.frame.
+#'             The output of func should be a R data.frame.
 #' @param schema The schema of the resulting SparkDataFrame after the function is applied.
 #'               It must match the output of func.
 #' @family SparkDataFrame functions
@@ -1291,9 +1291,9 @@ setMethod("dapply",
 #'
 #' @param x A SparkDataFrame
 #' @param func A function to be applied to each partition of the SparkDataFrame.
-#'             func should have only one parameter, to which a data.frame corresponds
+#'             func should have only one parameter, to which a R data.frame corresponds
 #'             to each partition will be passed.
-#'             The output of func should be a data.frame.
+#'             The output of func should be a R data.frame.
 #' @family SparkDataFrame functions
 #' @rdname dapplyCollect
 #' @name dapplyCollect
@@ -1641,7 +1641,6 @@ setMethod("select", signature(x = "SparkDataFrame", col = "character"),
             }
           })
 
-#' @family SparkDataFrame functions
 #' @rdname select
 #' @export
 #' @note select(SparkDataFrame, Column) since 1.4.0
@@ -1654,7 +1653,6 @@ setMethod("select", signature(x = "SparkDataFrame", col = "Column"),
             dataFrame(sdf)
           })
 
-#' @family SparkDataFrame functions
 #' @rdname select
 #' @export
 #' @note select(SparkDataFrame, list) since 1.4.0
@@ -2001,7 +1999,6 @@ setMethod("filter",
             dataFrame(sdf)
           })
 
-#' @family SparkDataFrame functions
 #' @rdname filter
 #' @name where
 #' @note where since 1.4.0
@@ -2222,11 +2219,13 @@ setMethod("merge",
             joinRes
           })
 
+#' Creates a list of columns by replacing the intersected ones with aliases
+#'
 #' Creates a list of columns by replacing the intersected ones with aliases.
 #' The name of the alias column is formed by concatanating the original column name and a suffix.
 #'
-#' @param x a SparkDataFrame on which the
-#' @param intersectedColNames a list of intersected column names
+#' @param x a SparkDataFrame
+#' @param intersectedColNames a list of intersected column names of the SparkDataFrame
 #' @param suffix a suffix for the column name
 #' @return list of columns
 #'
@@ -2513,9 +2512,9 @@ setMethod("summary",
           })
 
 
-#' dropna
+#' A set of SparkDataFrame functions working with NA values
 #'
-#' Returns a new SparkDataFrame omitting rows with null values.
+#' dropna, na.omit - Returns a new SparkDataFrame omitting rows with null values.
 #'
 #' @param x A SparkDataFrame.
 #' @param how "any" or "all".
@@ -2567,9 +2566,7 @@ setMethod("na.omit",
             dropna(object, how, minNonNulls, cols)
           })
 
-#' fillna
-#'
-#' Replace null values.
+#' fillna - Replace null values.
 #'
 #' @param x A SparkDataFrame.
 #' @param value Value to replace null values with.
@@ -2640,7 +2637,7 @@ setMethod("fillna",
             dataFrame(sdf)
           })
 
-#' Download data from a SparkDataFrame into a data.frame
+#' Download data from a SparkDataFrame into a R data.frame
 #'
 #' This function downloads the contents of a SparkDataFrame into an R's data.frame.
 #' Since data.frames are held in memory, ensure that you have enough memory

R/pkg/R/SQLContext.R

@@ -67,7 +67,7 @@ dispatchFunc <- function(newFuncSig, x, ...) {
 }
 
 #' return the SparkSession
-#' @note getSparkSession since 2.0.0
+#' @noRd
 getSparkSession <- function() {
   if (exists(".sparkRsession", envir = .sparkREnv)) {
     get(".sparkRsession", envir = .sparkREnv)
@@ -77,7 +77,7 @@ getSparkSession <- function() {
 }
 
 #' infer the SQL type
-#' @note infer_type since 1.4.0
+#' @noRd
 infer_type <- function(x) {
   if (is.null(x)) {
     stop("can not infer type from NULL")
@@ -451,7 +451,7 @@ sql <- function(x, ...) {
 #' Create a SparkDataFrame from a SparkSQL Table
 #'
 #' Returns the specified Table as a SparkDataFrame.  The Table must have already been registered
-#' in the SQLContext.
+#' in the SparkSession.
 #'
 #' @param tableName The SparkSQL Table to convert to a SparkDataFrame.
 #' @return SparkDataFrame

R/pkg/R/column.R

@@ -34,6 +34,11 @@ setOldClass("jobj")
 setClass("Column",
          slots = list(jc = "jobj"))
 
+#' A set of operations working with SparkDataFrame columns
+#' @rdname columnfunctions
+#' @name columnfunctions
+NULL
+
 setMethod("initialize", "Column", function(.Object, jc) {
   .Object@jc <- jc
   .Object
@@ -47,6 +52,7 @@ setMethod("column",
 
 #' @rdname show
 #' @name show
+#' @export
 #' @note show(Column) since 1.4.0
 setMethod("show", "Column",
           function(object) {

R/pkg/R/context.R

@@ -225,9 +225,10 @@ setCheckpointDir <- function(sc, dirName) {
   invisible(callJMethod(sc, "setCheckpointDir", suppressWarnings(normalizePath(dirName))))
 }
 
-#' Run a function over a list of elements, distributing the computations with Spark.
+#' Run a function over a list of elements, distributing the computations with Spark
 #'
-#' Applies a function in a manner that is similar to doParallel or lapply to elements of a list.
+#' Run a function over a list of elements, distributing the computations with Spark. Applies a
+#' function in a manner that is similar to doParallel or lapply to elements of a list.
 #' The computations are distributed using Spark. It is conceptually the same as the following code:
 #'   lapply(list, func)
 #'

R/pkg/R/functions.R

@@ -77,13 +77,14 @@ setMethod("acos",
             column(jc)
           })
 
-#' approxCountDistinct
+#' Returns the approximate number of distinct items in a group
 #'
-#' Aggregate function: returns the approximate number of distinct items in a group.
+#' Returns the approximate number of distinct items in a group. This is a column
+#' aggregate function.
 #'
 #' @rdname approxCountDistinct
 #' @name approxCountDistinct
-#' @family agg_funcs
+#' @return the approximate number of distinct items in a group.
 #' @export
 #' @examples \dontrun{approxCountDistinct(df$c)}
 #' @note approxCountDistinct(Column) since 1.4.0
@@ -234,7 +235,7 @@ setMethod("cbrt",
             column(jc)
           })
 
-#' ceil
+#' Computes the ceiling of the given value
 #'
 #' Computes the ceiling of the given value.
 #'
@@ -254,15 +255,16 @@ setMethod("ceil",
 #' Though scala functions has "col" function, we don't expose it in SparkR
 #' because we don't want to conflict with the "col" function in the R base
 #' package and we also have "column" function exported which is an alias of "col".
+#' @noRd
 col <- function(x) {
   column(callJStatic("org.apache.spark.sql.functions", "col", x))
 }
 
-#' column
+#' Returns a Column based on the given column name
 #'
 #' Returns a Column based on the given column name.
 #'
-#' @rdname col
+#' @rdname column
 #' @name column
 #' @family normal_funcs
 #' @export
@@ -385,9 +387,9 @@ setMethod("cosh",
             column(jc)
           })
 
-#' count
+#' Returns the number of items in a group
 #'
-#' Aggregate function: returns the number of items in a group.
+#' Returns the number of items in a group. This is a column aggregate function.
 #'
 #' @rdname count
 #' @name count
@@ -1193,7 +1195,7 @@ setMethod("sha1",
 #'
 #' Computes the signum of the given value.
 #'
-#' @rdname signum
+#' @rdname sign
 #' @name signum
 #' @family math_funcs
 #' @export
@@ -1717,7 +1719,7 @@ setMethod("datediff", signature(y = "Column"),
 
 #' hypot
 #'
-#' Computes `sqrt(a^2^ + b^2^)` without intermediate overflow or underflow.
+#' Computes "sqrt(a^2 + b^2)" without intermediate overflow or underflow.
 #'
 #' @rdname hypot
 #' @name hypot
@@ -1813,12 +1815,8 @@ setMethod("pmod", signature(y = "Column"),
           })
 
 
-#' Approx Count Distinct
-#'
-#' @family agg_funcs
 #' @rdname approxCountDistinct
 #' @name approxCountDistinct
-#' @return the approximate number of distinct items in a group.
 #' @export
 #' @examples \dontrun{approxCountDistinct(df$c, 0.02)}
 #' @note approxCountDistinct(Column, numeric) since 1.4.0
@@ -1918,10 +1916,6 @@ setMethod("least",
             column(jc)
           })
 
-#' ceiling
-#'
-#' Computes the ceiling of the given value.
-#'
 #' @rdname ceil
 #' @name ceiling
 #' @export
@@ -1933,11 +1927,7 @@ setMethod("ceiling",
             ceil(x)
           })
 
-#' sign
-#'
-#' Computes the signum of the given value.
-#'
-#' @rdname signum
+#' @rdname sign
 #' @name sign
 #' @export
 #' @examples \dontrun{sign(df$c)}
@@ -1961,10 +1951,6 @@ setMethod("n_distinct", signature(x = "Column"),
             countDistinct(x, ...)
           })
 
-#' n
-#'
-#' Aggregate function: returns the number of items in a group.
-#'
 #' @rdname count
 #' @name n
 #' @export