Repository: spark Updated Branches: refs/heads/master 03ba56d78 -> a6239d587
[SPARK-11756][SPARKR] Fix use of aliases - SparkR can not output help information for SparkR:::summary correctly Fix use of aliases and changes uses of rdname and seealso `aliases` is the hint for `?` - it should not be linked to some other name - those should be seealso https://cran.r-project.org/web/packages/roxygen2/vignettes/rd.html Clean up usage on family, as multiple use of family with the same rdname is causing duplicated See Also html blocks (like http://spark.apache.org/docs/latest/api/R/count.html) Also changing some rdname for dplyr-like variant for better R user visibility in R doc, eg. rbind, summary, mutate, summarize shivaram yanboliang Author: felixcheung <felixcheun...@hotmail.com> Closes #9750 from felixcheung/rdocaliases. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/a6239d58 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/a6239d58 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/a6239d58 Branch: refs/heads/master Commit: a6239d587c638691f52eca3eee905c53fbf35a12 Parents: 03ba56d Author: felixcheung <felixcheun...@hotmail.com> Authored: Fri Nov 20 15:10:55 2015 -0800 Committer: Shivaram Venkataraman <shiva...@cs.berkeley.edu> Committed: Fri Nov 20 15:10:55 2015 -0800 ---------------------------------------------------------------------- R/pkg/R/DataFrame.R | 96 ++++++++++++------------------------------------ R/pkg/R/broadcast.R | 1 - R/pkg/R/generics.R | 12 +++--- R/pkg/R/group.R | 12 +++--- 4 files changed, 37 insertions(+), 84 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/a6239d58/R/pkg/R/DataFrame.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R index 06b0108..8a13e7a 100644 --- a/R/pkg/R/DataFrame.R +++ b/R/pkg/R/DataFrame.R @@ -254,7 +254,6 @@ setMethod("dtypes", #' @family DataFrame functions #' @rdname columns #' @name columns -#' @aliases names #' @export #' @examples #'\dontrun{ @@ -272,7 +271,6 @@ setMethod("columns", }) }) -#' @family DataFrame functions #' @rdname columns #' @name names setMethod("names", @@ -281,7 +279,6 @@ setMethod("names", columns(x) }) -#' @family DataFrame functions #' @rdname columns #' @name names<- setMethod("names<-", @@ -533,14 +530,8 @@ setMethod("distinct", dataFrame(sdf) }) -#' @title Distinct rows in a DataFrame -# -#' @description Returns a new DataFrame containing distinct rows in this DataFrame -#' -#' @family DataFrame functions -#' @rdname unique +#' @rdname distinct #' @name unique -#' @aliases distinct setMethod("unique", signature(x = "DataFrame"), function(x) { @@ -557,7 +548,7 @@ setMethod("unique", #' #' @family DataFrame functions #' @rdname sample -#' @aliases sample_frac +#' @name sample #' @export #' @examples #'\dontrun{ @@ -579,7 +570,6 @@ setMethod("sample", dataFrame(sdf) }) -#' @family DataFrame functions #' @rdname sample #' @name sample_frac setMethod("sample_frac", @@ -589,16 +579,15 @@ setMethod("sample_frac", sample(x, withReplacement, fraction) }) -#' Count +#' nrow #' #' Returns the number of rows in a DataFrame #' #' @param x A SparkSQL DataFrame #' #' @family DataFrame functions -#' @rdname count +#' @rdname nrow #' @name count -#' @aliases nrow #' @export #' @examples #'\dontrun{ @@ -614,14 +603,8 @@ setMethod("count", callJMethod(x@sdf, "count") }) -#' @title Number of rows for a DataFrame -#' @description Returns number of rows in a DataFrames -#' #' @name nrow -#' -#' @family DataFrame functions #' @rdname nrow -#' @aliases count setMethod("nrow", signature(x = "DataFrame"), function(x) { @@ -870,7 +853,6 @@ setMethod("toRDD", #' @param x a DataFrame #' @return a GroupedData #' @seealso GroupedData -#' @aliases group_by #' @family DataFrame functions #' @rdname groupBy #' @name groupBy @@ -896,7 +878,6 @@ setMethod("groupBy", groupedData(sgd) }) -#' @family DataFrame functions #' @rdname groupBy #' @name group_by setMethod("group_by", @@ -913,7 +894,6 @@ setMethod("group_by", #' @family DataFrame functions #' @rdname agg #' @name agg -#' @aliases summarize #' @export setMethod("agg", signature(x = "DataFrame"), @@ -921,7 +901,6 @@ setMethod("agg", agg(groupBy(x), ...) }) -#' @family DataFrame functions #' @rdname agg #' @name summarize setMethod("summarize", @@ -1092,7 +1071,6 @@ setMethod("[", signature(x = "DataFrame", i = "Column"), #' @family DataFrame functions #' @rdname subset #' @name subset -#' @aliases [ #' @family subsetting functions #' @examples #' \dontrun{ @@ -1216,7 +1194,7 @@ setMethod("selectExpr", #' @family DataFrame functions #' @rdname withColumn #' @name withColumn -#' @aliases mutate transform +#' @seealso \link{rename} \link{mutate} #' @export #' @examples #'\dontrun{ @@ -1231,7 +1209,6 @@ setMethod("withColumn", function(x, colName, col) { select(x, x$"*", alias(col, colName)) }) - #' Mutate #' #' Return a new DataFrame with the specified columns added. @@ -1240,9 +1217,9 @@ setMethod("withColumn", #' @param col a named argument of the form name = col #' @return A new DataFrame with the new columns added. #' @family DataFrame functions -#' @rdname withColumn +#' @rdname mutate #' @name mutate -#' @aliases withColumn transform +#' @seealso \link{rename} \link{withColumn} #' @export #' @examples #'\dontrun{ @@ -1273,17 +1250,15 @@ setMethod("mutate", }) #' @export -#' @family DataFrame functions -#' @rdname withColumn +#' @rdname mutate #' @name transform -#' @aliases withColumn mutate setMethod("transform", signature(`_data` = "DataFrame"), function(`_data`, ...) { mutate(`_data`, ...) }) -#' WithColumnRenamed +#' rename #' #' Rename an existing column in a DataFrame. #' @@ -1292,8 +1267,9 @@ setMethod("transform", #' @param newCol The new column name. #' @return A DataFrame with the column name changed. #' @family DataFrame functions -#' @rdname withColumnRenamed +#' @rdname rename #' @name withColumnRenamed +#' @seealso \link{mutate} #' @export #' @examples #'\dontrun{ @@ -1316,17 +1292,9 @@ setMethod("withColumnRenamed", select(x, cols) }) -#' Rename -#' -#' Rename an existing column in a DataFrame. -#' -#' @param x A DataFrame -#' @param newCol A named pair of the form new_column_name = existing_column -#' @return A DataFrame with the column name changed. -#' @family DataFrame functions -#' @rdname withColumnRenamed +#' @param newColPair A named pair of the form new_column_name = existing_column +#' @rdname rename #' @name rename -#' @aliases withColumnRenamed #' @export #' @examples #'\dontrun{ @@ -1371,7 +1339,6 @@ setClassUnion("characterOrColumn", c("character", "Column")) #' @family DataFrame functions #' @rdname arrange #' @name arrange -#' @aliases orderby #' @export #' @examples #'\dontrun{ @@ -1395,8 +1362,8 @@ setMethod("arrange", dataFrame(sdf) }) -#' @family DataFrame functions #' @rdname arrange +#' @name arrange #' @export setMethod("arrange", signature(x = "DataFrame", col = "character"), @@ -1427,9 +1394,9 @@ setMethod("arrange", do.call("arrange", c(x, jcols)) }) -#' @family DataFrame functions #' @rdname arrange -#' @name orderby +#' @name orderBy +#' @export setMethod("orderBy", signature(x = "DataFrame", col = "characterOrColumn"), function(x, col) { @@ -1492,6 +1459,7 @@ setMethod("where", #' @family DataFrame functions #' @rdname join #' @name join +#' @seealso \link{merge} #' @export #' @examples #'\dontrun{ @@ -1528,9 +1496,7 @@ setMethod("join", dataFrame(sdf) }) -#' #' @name merge -#' @aliases join #' @title Merges two data frames #' @param x the first data frame to be joined #' @param y the second data frame to be joined @@ -1550,6 +1516,7 @@ setMethod("join", #' outer join will be returned. #' @family DataFrame functions #' @rdname merge +#' @seealso \link{join} #' @export #' @examples #'\dontrun{ @@ -1671,7 +1638,7 @@ generateAliasesForIntersectedCols <- function (x, intersectedColNames, suffix) { cols } -#' UnionAll +#' rbind #' #' Return a new DataFrame containing the union of rows in this DataFrame #' and another DataFrame. This is equivalent to `UNION ALL` in SQL. @@ -1681,7 +1648,7 @@ generateAliasesForIntersectedCols <- function (x, intersectedColNames, suffix) { #' @param y A Spark DataFrame #' @return A DataFrame containing the result of the union. #' @family DataFrame functions -#' @rdname unionAll +#' @rdname rbind #' @name unionAll #' @export #' @examples @@ -1700,13 +1667,11 @@ setMethod("unionAll", }) #' @title Union two or more DataFrames -#' #' @description Returns a new DataFrame containing rows of all parameters. #' -#' @family DataFrame functions #' @rdname rbind #' @name rbind -#' @aliases unionAll +#' @export setMethod("rbind", signature(... = "DataFrame"), function(x, ..., deparse.level = 1) { @@ -1795,7 +1760,6 @@ setMethod("except", #' @family DataFrame functions #' @rdname write.df #' @name write.df -#' @aliases saveDF #' @export #' @examples #'\dontrun{ @@ -1828,7 +1792,6 @@ setMethod("write.df", callJMethod(df@sdf, "save", source, jmode, options) }) -#' @family DataFrame functions #' @rdname write.df #' @name saveDF #' @export @@ -1891,7 +1854,7 @@ setMethod("saveAsTable", callJMethod(df@sdf, "saveAsTable", tableName, source, jmode, options) }) -#' describe +#' summary #' #' Computes statistics for numeric columns. #' If no columns are given, this function computes statistics for all numerical columns. @@ -1901,9 +1864,8 @@ setMethod("saveAsTable", #' @param ... Additional expressions #' @return A DataFrame #' @family DataFrame functions -#' @rdname describe +#' @rdname summary #' @name describe -#' @aliases summary #' @export #' @examples #'\dontrun{ @@ -1923,8 +1885,7 @@ setMethod("describe", dataFrame(sdf) }) -#' @family DataFrame functions -#' @rdname describe +#' @rdname summary #' @name describe setMethod("describe", signature(x = "DataFrame"), @@ -1934,11 +1895,6 @@ setMethod("describe", dataFrame(sdf) }) -#' @title Summary -#' -#' @description Computes statistics for numeric columns of the DataFrame -#' -#' @family DataFrame functions #' @rdname summary #' @name summary setMethod("summary", @@ -1966,7 +1922,6 @@ setMethod("summary", #' @family DataFrame functions #' @rdname nafunctions #' @name dropna -#' @aliases na.omit #' @export #' @examples #'\dontrun{ @@ -1993,7 +1948,6 @@ setMethod("dropna", dataFrame(sdf) }) -#' @family DataFrame functions #' @rdname nafunctions #' @name na.omit #' @export @@ -2019,9 +1973,7 @@ setMethod("na.omit", #' type are ignored. For example, if value is a character, and #' subset contains a non-character column, then the non-character #' column is simply ignored. -#' @return A DataFrame #' -#' @family DataFrame functions #' @rdname nafunctions #' @name fillna #' @export http://git-wip-us.apache.org/repos/asf/spark/blob/a6239d58/R/pkg/R/broadcast.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/broadcast.R b/R/pkg/R/broadcast.R index 2403925..38f0eed 100644 --- a/R/pkg/R/broadcast.R +++ b/R/pkg/R/broadcast.R @@ -51,7 +51,6 @@ Broadcast <- function(id, value, jBroadcastRef, objName) { # # @param bcast The broadcast variable to get # @rdname broadcast -# @aliases value,Broadcast-method setMethod("value", signature(bcast = "Broadcast"), function(bcast) { http://git-wip-us.apache.org/repos/asf/spark/blob/a6239d58/R/pkg/R/generics.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/generics.R b/R/pkg/R/generics.R index 71004a0..1b3f10e 100644 --- a/R/pkg/R/generics.R +++ b/R/pkg/R/generics.R @@ -397,7 +397,7 @@ setGeneric("cov", function(x, col1, col2) {standardGeneric("cov") }) #' @export setGeneric("corr", function(x, col1, col2, method = "pearson") {standardGeneric("corr") }) -#' @rdname describe +#' @rdname summary #' @export setGeneric("describe", function(x, col, ...) { standardGeneric("describe") }) @@ -459,11 +459,11 @@ setGeneric("isLocal", function(x) { standardGeneric("isLocal") }) #' @export setGeneric("limit", function(x, num) {standardGeneric("limit") }) -#' rdname merge +#' @rdname merge #' @export setGeneric("merge") -#' @rdname withColumn +#' @rdname mutate #' @export setGeneric("mutate", function(.data, ...) {standardGeneric("mutate") }) @@ -475,7 +475,7 @@ setGeneric("orderBy", function(x, col) { standardGeneric("orderBy") }) #' @export setGeneric("printSchema", function(x) { standardGeneric("printSchema") }) -#' @rdname withColumnRenamed +#' @rdname rename #' @export setGeneric("rename", function(x, ...) { standardGeneric("rename") }) @@ -553,7 +553,7 @@ setGeneric("toJSON", function(x) { standardGeneric("toJSON") }) setGeneric("toRDD", function(x) { standardGeneric("toRDD") }) -#' @rdname unionAll +#' @rdname rbind #' @export setGeneric("unionAll", function(x, y) { standardGeneric("unionAll") }) @@ -565,7 +565,7 @@ setGeneric("where", function(x, condition) { standardGeneric("where") }) #' @export setGeneric("withColumn", function(x, colName, col) { standardGeneric("withColumn") }) -#' @rdname withColumnRenamed +#' @rdname rename #' @export setGeneric("withColumnRenamed", function(x, existingCol, newCol) { standardGeneric("withColumnRenamed") }) http://git-wip-us.apache.org/repos/asf/spark/blob/a6239d58/R/pkg/R/group.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/group.R b/R/pkg/R/group.R index e5f702f..23b49ae 100644 --- a/R/pkg/R/group.R +++ b/R/pkg/R/group.R @@ -68,7 +68,7 @@ setMethod("count", dataFrame(callJMethod(x@sgd, "count")) }) -#' Agg +#' summarize #' #' Aggregates on the entire DataFrame without groups. #' The resulting DataFrame will also contain the grouping columns. @@ -78,12 +78,14 @@ setMethod("count", #' #' @param x a GroupedData #' @return a DataFrame -#' @rdname agg +#' @rdname summarize +#' @name agg #' @family agg_funcs #' @examples #' \dontrun{ #' df2 <- agg(df, age = "sum") # new column name will be created as 'SUM(age#0)' -#' df2 <- agg(df, ageSum = sum(df$age)) # Creates a new column named ageSum +#' df3 <- agg(df, ageSum = sum(df$age)) # Creates a new column named ageSum +#' df4 <- summarize(df, ageSum = max(df$age)) #' } setMethod("agg", signature(x = "GroupedData"), @@ -110,8 +112,8 @@ setMethod("agg", dataFrame(sdf) }) -#' @rdname agg -#' @aliases agg +#' @rdname summarize +#' @name summarize setMethod("summarize", signature(x = "GroupedData"), function(x, ...) { --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
