[SPARK-16508][SparkR] Fix CRAN undocumented/duplicated arguments warnings.

R/pkg/R/DataFrame.R

@@ -932,7 +932,7 @@ setMethod("sample_frac",
 #' @param x a SparkDataFrame.
 #' @family SparkDataFrame functions
 #' @rdname nrow
-#' @name count
+#' @name nrow
 #' @aliases count,SparkDataFrame-method
 #' @export
 #' @examples
@@ -1214,9 +1214,9 @@ setMethod("toRDD",
 #'
 #' Groups the SparkDataFrame using the specified columns, so we can run aggregation on them.
 #'
-#' @param x a SparkDataFrame
+#' @param x a SparkDataFrame.
 #' @param ... variable(s) (character names(s) or Column(s)) to group on.
-#' @return a GroupedData
+#' @return A GroupedData.
 #' @family SparkDataFrame functions
 #' @aliases groupBy,SparkDataFrame-method
 #' @rdname groupBy
@@ -3037,8 +3037,8 @@ setMethod("str",
 #' This is a no-op if schema doesn't contain column name(s).
 #'
 #' @param x a SparkDataFrame.
-#' @param ... further arguments to be passed to or from other methods.
 #' @param col a character vector of column names or a Column.
+#' @param ... further arguments to be passed to or from other methods.
 #' @return A SparkDataFrame.
 #'
 #' @family SparkDataFrame functions
@@ -3058,7 +3058,7 @@ setMethod("str",
 #' @note drop since 2.0.0
 setMethod("drop",
           signature(x = "SparkDataFrame"),
-          function(x, col) {
+          function(x, col, ...) {
             stopifnot(class(col) == "character" || class(col) == "Column")
 
             if (class(col) == "Column") {
@@ -3218,11 +3218,11 @@ setMethod("histogram",
 #'         and to not change the existing data.
 #' }
 #'
-#' @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 x s SparkDataFrame.
+#' @param url JDBC database url of the form `jdbc:subprotocol:subname`.
+#' @param tableName yhe name of the table in the external database.
+#' @param mode one of 'append', 'overwrite', 'error', 'ignore' save mode (it is 'error' by default).
 #' @param ... additional JDBC database connection properties.
-#' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode (it is 'error' by default)
 #' @family SparkDataFrame functions
 #' @rdname write.jdbc
 #' @name write.jdbc

R/pkg/R/SQLContext.R

@@ -730,7 +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 external data source specific named propertie(s).
+#' @param ... additional external data source specific named properties.
 #' @return SparkDataFrame
 #' @rdname read.df
 #' @name read.df

R/pkg/R/WindowSpec.R

@@ -55,7 +55,7 @@ setMethod("show", "WindowSpec",
 #' Defines the partitioning columns in a WindowSpec.
 #'
 #' @param x a WindowSpec.
-#' @param col a column to partition on (desribed by the name or Column object).
+#' @param col a column to partition on (desribed by the name or Column).
 #' @param ... additional column(s) to partition on.
 #' @return A WindowSpec.
 #' @rdname partitionBy
@@ -88,7 +88,7 @@ setMethod("partitionBy",
 #'
 #' Defines the ordering columns in a WindowSpec.
 #' @param x a WindowSpec
-#' @param col a character or Column object indicating an ordering column
+#' @param col a character or Column indicating an ordering column
 #' @param ... additional sorting fields
 #' @return A WindowSpec.
 #' @name orderBy
@@ -194,7 +194,7 @@ setMethod("rangeBetween",
 #'
 #' Define a windowing column.
 #'
-#' @param x a Column object, usually one returned by window function(s).
+#' @param x a Column, usually one returned by window function(s).
 #' @param window a WindowSpec object. Can be created by `windowPartitionBy` or
 #'        `windowOrderBy` and configured by other WindowSpec methods.
 #' @rdname over

R/pkg/R/column.R

@@ -163,7 +163,7 @@ setMethod("alias",
 #' @family colum_func
 #' @aliases substr,Column-method
 #'
-#' @param x a Column object.
+#' @param x a Column.
 #' @param start starting position.
 #' @param stop ending position.
 #' @note substr since 1.4.0
@@ -220,7 +220,7 @@ setMethod("endsWith", signature(x = "Column"),
 #' @family colum_func
 #' @aliases between,Column-method
 #'
-#' @param x a Column object
+#' @param x a Column
 #' @param bounds lower and upper bounds
 #' @note between since 1.5.0
 setMethod("between", signature(x = "Column"),
@@ -235,7 +235,7 @@ setMethod("between", signature(x = "Column"),
 
 #' Casts the column to a different data type.
 #'
-#' @param x a Column object.
+#' @param x a Column.
 #' @param dataType a character object describing the target data type.
 #'        See
 #'        \href{https://spark.apache.org/docs/latest/sparkr.html#data-type-mapping-between-r-and-spark}{

R/pkg/R/functions.R

@@ -316,7 +316,7 @@ setMethod("column",
 #'
 #' Computes the Pearson Correlation Coefficient for two Columns.
 #'
-#' @param col2 a (second) Column object.
+#' @param col2 a (second) Column.
 #'
 #' @rdname corr
 #' @name corr
@@ -357,8 +357,8 @@ setMethod("cov", signature(x = "characterOrColumn"),
 
 #' @rdname cov
 #'
-#' @param col1 the first Column object.
-#' @param col2 the second Column object.
+#' @param col1 the first Column.
+#' @param col2 the second Column.
 #' @name covar_samp
 #' @aliases covar_samp,characterOrColumn,characterOrColumn-method
 #' @note covar_samp since 2.0.0
@@ -446,8 +446,8 @@ setMethod("cosh",
 #'
 #' Returns the number of items in a group. This is a column aggregate function.
 #'
-#' @rdname n
-#' @name n
+#' @rdname count
+#' @name count
 #' @family agg_funcs
 #' @aliases count,Column-method
 #' @export
@@ -1270,14 +1270,14 @@ setMethod("round",
 
 #' bround
 #'
-#' Returns the value of the column `e` rounded to `scale` decimal places using HALF_EVEN rounding
-#' mode if `scale` >= 0 or at integer part when `scale` < 0.
+#' Returns the value of the column \code{e} rounded to \code{scale} decimal places using HALF_EVEN rounding
+#' mode if \code{scale} >= 0 or at integer part when \code{scale} < 0.
 #' Also known as Gaussian rounding or bankers' rounding that rounds to the nearest even number.
 #' bround(2.5, 0) = 2, bround(3.5, 0) = 4.
 #'
 #' @param x Column to compute on.
 #' @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
+#'        the nearest even number when \code{scale} = 0, and \code{scale} digits to the left
 #'        of the decimal point when \code{scale} < 0.
 #' @param ... further arguments to be passed to or from other methods.
 #' @rdname bround
@@ -2276,8 +2276,7 @@ setMethod("n_distinct", signature(x = "Column"),
             countDistinct(x, ...)
           })
 
-#' @param x a Column.
-#' @rdname n
+#' @rdname count
 #' @name n
 #' @aliases n,Column-method
 #' @export
@@ -2655,7 +2654,7 @@ setMethod("expr", signature(x = "character"),
 #' Formats the arguments in printf-style and returns the result as a string column.
 #'
 #' @param format a character object of format strings.
-#' @param x a Column object.
+#' @param x a Column.
 #' @param ... additional Column(s).
 #' @family string_funcs
 #' @rdname format_string

R/pkg/R/generics.R

@@ -432,7 +432,8 @@ setGeneric("coltypes<-", function(x, value) { standardGeneric("coltypes<-") })
 #' @export
 setGeneric("columns", function(x) {standardGeneric("columns") })
 
-#' @rdname nrow
+#' @param x a GroupedData or Column.
+#' @rdname count
 #' @export
 setGeneric("count", function(x) { standardGeneric("count") })
 
@@ -1071,7 +1072,7 @@ setGeneric("month", function(x) { standardGeneric("month") })
 #' @export
 setGeneric("months_between", function(y, x) { standardGeneric("months_between") })
 
-#' @rdname n
+#' @rdname count
 #' @export
 setGeneric("n", function(x) { standardGeneric("n") })
 
@@ -1303,6 +1304,10 @@ setGeneric("year", function(x) { standardGeneric("year") })
 #' @export
 setGeneric("spark.glm", function(data, formula, ...) { standardGeneric("spark.glm") })
 
+#' @param x,y For \code{glm}: logical values indicating whether the response vector
+#'          and model matrix used in the fitting process should be returned as
+#'          components of the returned value.
+#' @inheritParams stats::glm
 #' @rdname glm
 #' @export
 setGeneric("glm")

R/pkg/R/group.R

@@ -59,7 +59,6 @@ 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.
 #' @rdname count
 #' @aliases count,GroupedData-method

R/pkg/R/mllib.R

@@ -173,7 +173,7 @@ setMethod("spark.glm", signature(data = "SparkDataFrame", formula = "formula"),
 #' Fits a generalized linear model, similarly to R's glm().
 #' @param formula a symbolic description of the model to be fitted. Currently only a few formula
 #'                operators are supported, including '~', '.', ':', '+', and '-'.
-#' @param data SparkDataFrame for training.
+#' @param data a SparkDataFrame or R's glm data for training.
 #' @param family a description of the error distribution and link function to be used in the model.
 #'               This can be a character string naming a family function, a family function or
 #'               the result of a call to a family function. Refer R family at
@@ -508,10 +508,10 @@ setMethod("summary", signature(object = "IsotonicRegressionModel"),
 #' @param formula a symbolic description of the model to be fitted. Currently only a few formula
 #'                operators are supported, including '~', '.', ':', '+', and '-'.
 #'                Note that the response variable of formula is empty in spark.kmeans.
-#' @param ... additional argument(s) passed to the method.
 #' @param k number of centers.
 #' @param maxIter maximum iteration number.
 #' @param initMode the initialization algorithm choosen to fit the model.
+#' @param ... additional argument(s) passed to the method.
 #' @return \code{spark.kmeans} returns a fitted k-means model.
 #' @rdname spark.kmeans
 #' @aliases spark.kmeans,SparkDataFrame,formula-method
@@ -628,8 +628,8 @@ 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 argument(s) passed to the method. Currently only \code{smoothing}.
 #' @return \code{spark.naiveBayes} returns a fitted naive Bayes model.
 #' @rdname spark.naiveBayes
 #' @aliases spark.naiveBayes,SparkDataFrame,formula-method
@@ -657,7 +657,7 @@ 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)