Repository: spark Updated Branches: refs/heads/master 2d6919bea -> 57746295e
[SPARK-16109][SPARKR][DOC] R more doc fixes ## What changes were proposed in this pull request? Found these issues while reviewing for SPARK-16090 ## How was this patch tested? roxygen2 doc gen, checked output html Author: Felix Cheung <felixcheun...@hotmail.com> Closes #13803 from felixcheung/rdocrd. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/57746295 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/57746295 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/57746295 Branch: refs/heads/master Commit: 57746295e6fb705f8393a00ab1cc570ddb7da44e Parents: 2d6919b Author: Felix Cheung <felixcheun...@hotmail.com> Authored: Tue Jun 21 11:01:42 2016 -0700 Committer: Shivaram Venkataraman <shiva...@cs.berkeley.edu> Committed: Tue Jun 21 11:01:42 2016 -0700 ---------------------------------------------------------------------- R/pkg/R/DataFrame.R | 7 +++++-- R/pkg/R/functions.R | 4 +++- R/pkg/R/generics.R | 8 ++++---- R/pkg/R/schema.R | 7 +++++-- R/pkg/R/stats.R | 37 +++++++++++++++++++++++-------------- 5 files changed, 40 insertions(+), 23 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/57746295/R/pkg/R/DataFrame.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R index a8ade1a..ed0bb85 100644 --- a/R/pkg/R/DataFrame.R +++ b/R/pkg/R/DataFrame.R @@ -59,6 +59,7 @@ setMethod("initialize", "SparkDataFrame", function(.Object, sdf, isCached) { #' @export #' @param sdf A Java object reference to the backing Scala DataFrame #' @param isCached TRUE if the SparkDataFrame is cached +#' @noRd dataFrame <- function(sdf, isCached = FALSE) { new("SparkDataFrame", sdf, isCached) } @@ -119,7 +120,7 @@ setMethod("schema", #' Print the logical and physical Catalyst plans to the console for debugging. #' #' @param x A SparkDataFrame -#' @param extended Logical. If extended is False, explain() only prints the physical plan. +#' @param extended Logical. If extended is FALSE, explain() only prints the physical plan. #' @family SparkDataFrame functions #' @rdname explain #' @name explain @@ -175,6 +176,8 @@ setMethod("isLocal", #' #' @param x 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 +#' truncated and all cells will be aligned right #' #' @family SparkDataFrame functions #' @rdname showDF @@ -1854,7 +1857,7 @@ setMethod("withColumnRenamed", select(x, cols) }) -#' @param newColPair A named pair of the form new_column_name = existing_column +#' @param ... A named pair of the form new_column_name = existing_column #' @rdname rename #' @name rename #' @export http://git-wip-us.apache.org/repos/asf/spark/blob/57746295/R/pkg/R/functions.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/functions.R b/R/pkg/R/functions.R index 6e0009f..09e5afa 100644 --- a/R/pkg/R/functions.R +++ b/R/pkg/R/functions.R @@ -1777,7 +1777,7 @@ setMethod("months_between", signature(y = "Column"), #' nanvl #' #' Returns col1 if it is not NaN, or col2 if col1 is NaN. -#' hhBoth inputs should be floating point columns (DoubleType or FloatType). +#' Both inputs should be floating point columns (DoubleType or FloatType). #' #' @rdname nanvl #' @name nanvl @@ -2008,6 +2008,8 @@ setMethod("from_utc_timestamp", signature(y = "Column", x = "character"), #' NOTE: The position is not zero based, but 1 based index, returns 0 if substr #' could not be found in str. #' +#' @param y column to check +#' @param x substring to check #' @family string_funcs #' @rdname instr #' @name instr http://git-wip-us.apache.org/repos/asf/spark/blob/57746295/R/pkg/R/generics.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/generics.R b/R/pkg/R/generics.R index 43395aa..7b08a8e 100644 --- a/R/pkg/R/generics.R +++ b/R/pkg/R/generics.R @@ -59,15 +59,15 @@ setGeneric("count", function(x) { standardGeneric("count") }) # @export setGeneric("countByValue", function(x) { standardGeneric("countByValue") }) -# @rdname statfunctions +# @rdname crosstab # @export setGeneric("crosstab", function(x, col1, col2) { standardGeneric("crosstab") }) -# @rdname statfunctions +# @rdname freqItems # @export setGeneric("freqItems", function(x, cols, support = 0.01) { standardGeneric("freqItems") }) -# @rdname statfunctions +# @rdname approxQuantile # @export setGeneric("approxQuantile", function(x, col, probabilities, relativeError) { @@ -575,7 +575,7 @@ setGeneric("sample", setGeneric("sample_frac", function(x, withReplacement, fraction, seed) { standardGeneric("sample_frac") }) -#' @rdname statfunctions +#' @rdname sampleBy #' @export setGeneric("sampleBy", function(x, col, fractions, seed) { standardGeneric("sampleBy") }) http://git-wip-us.apache.org/repos/asf/spark/blob/57746295/R/pkg/R/schema.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/schema.R b/R/pkg/R/schema.R index fb23c78..a91e998 100644 --- a/R/pkg/R/schema.R +++ b/R/pkg/R/schema.R @@ -86,9 +86,8 @@ print.structType <- function(x, ...) { #' Create a structField object that contains the metadata for a single field in a schema. #' #' @param x The name of the field -#' @param type The data type of the field -#' @param nullable A logical vector indicating whether or not the field is nullable #' @return a structField object +#' @rdname structField #' @export #' @examples #'\dontrun{ @@ -176,6 +175,10 @@ checkType <- function(type) { stop(paste("Unsupported type for SparkDataframe:", type)) } +#' @param type The data type of the field +#' @param nullable A logical vector indicating whether or not the field is nullable +#' @rdname structField +#' @export structField.character <- function(x, type, nullable = TRUE) { if (class(x) != "character") { stop("Field name must be a string.") http://git-wip-us.apache.org/repos/asf/spark/blob/57746295/R/pkg/R/stats.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/stats.R b/R/pkg/R/stats.R index e40b177..c92352e 100644 --- a/R/pkg/R/stats.R +++ b/R/pkg/R/stats.R @@ -19,10 +19,9 @@ setOldClass("jobj") -#' @title SparkDataFrame statistic functions - -#' @description -#' crosstab - Computes a pair-wise frequency table of the given columns. Also known as a contingency +#' Computes a pair-wise frequency table of the given columns +#' +#' Computes a pair-wise frequency table of the given columns. Also known as a contingency #' table. The number of distinct values for each column should be less than 1e4. At most 1e6 #' non-zero pair frequencies will be returned. #' @@ -33,8 +32,9 @@ setOldClass("jobj") #' of `col2`. The name of the first column will be `$col1_$col2`. Pairs that have no #' occurrences will have zero as their counts. #' -#' @rdname statfunctions +#' @rdname crosstab #' @name crosstab +#' @family stat functions #' @export #' @examples #' \dontrun{ @@ -59,6 +59,7 @@ setMethod("crosstab", #' #' @rdname cov #' @name cov +#' @family stat functions #' @export #' @examples #'\dontrun{ @@ -87,6 +88,7 @@ setMethod("cov", #' #' @rdname corr #' @name corr +#' @family stat functions #' @export #' @examples #'\dontrun{ @@ -103,8 +105,10 @@ setMethod("corr", callJMethod(statFunctions, "corr", col1, col2, method) }) -#' @description -#' freqItems - Finding frequent items for columns, possibly with false positives. + +#' Finding frequent items for columns, possibly with false positives +#' +#' Finding frequent items for columns, possibly with false positives. #' Using the frequent element count algorithm described in #' \url{http://dx.doi.org/10.1145/762471.762473}, proposed by Karp, Schenker, and Papadimitriou. #' @@ -114,8 +118,9 @@ setMethod("corr", #' Should be greater than 1e-4. Default support = 0.01. #' @return a local R data.frame with the frequent items in each column #' -#' @rdname statfunctions +#' @rdname freqItems #' @name freqItems +#' @family stat functions #' @export #' @examples #' \dontrun{ @@ -130,8 +135,9 @@ setMethod("freqItems", signature(x = "SparkDataFrame", cols = "character"), collect(dataFrame(sct)) }) -#' @description -#' approxQuantile - Calculates the approximate quantiles of a numerical column of a SparkDataFrame. +#' Calculates the approximate quantiles of a numerical column of a SparkDataFrame +#' +#' Calculates the approximate quantiles of a numerical column of a SparkDataFrame. #' The result of this algorithm has the following deterministic bound: #' If the SparkDataFrame has N elements and if we request the quantile at probability `p` up to #' error `err`, then the algorithm will return a sample `x` from the SparkDataFrame so that the @@ -150,8 +156,9 @@ setMethod("freqItems", signature(x = "SparkDataFrame", cols = "character"), #' Note that values greater than 1 are accepted but give the same result as 1. #' @return The approximate quantiles at the given probabilities. #' -#' @rdname statfunctions +#' @rdname approxQuantile #' @name approxQuantile +#' @family stat functions #' @export #' @examples #' \dontrun{ @@ -168,8 +175,9 @@ setMethod("approxQuantile", as.list(probabilities), relativeError) }) -#' @description -#' sampleBy - Returns a stratified sample without replacement based on the fraction given on each +#' Returns a stratified sample without replacement +#' +#' Returns a stratified sample without replacement based on the fraction given on each #' stratum. #' #' @param x A SparkDataFrame @@ -179,8 +187,9 @@ setMethod("approxQuantile", #' @param seed random seed #' @return A new SparkDataFrame that represents the stratified sample #' -#' @rdname statfunctions +#' @rdname sampleBy #' @name sampleBy +#' @family stat functions #' @export #' @examples #'\dontrun{ --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
