diff options
Diffstat (limited to 'R/pkg/R/DataFrame.R')
-rw-r--r-- | R/pkg/R/DataFrame.R | 105 |
1 files changed, 97 insertions, 8 deletions
diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R index 87a2c66ffd..df5bc81371 100644 --- a/R/pkg/R/DataFrame.R +++ b/R/pkg/R/DataFrame.R @@ -23,15 +23,23 @@ NULL setOldClass("jobj") #' @title S4 class that represents a DataFrame -#' @description DataFrames can be created using functions like -#' \code{jsonFile}, \code{table} etc. +#' @description DataFrames can be created using functions like \link{createDataFrame}, +#' \link{jsonFile}, \link{table} etc. +#' @family dataframe_funcs #' @rdname DataFrame -#' @seealso jsonFile, table #' @docType class #' #' @slot env An R environment that stores bookkeeping states of the DataFrame #' @slot sdf A Java object reference to the backing Scala DataFrame +#' @seealso \link{createDataFrame}, \link{jsonFile}, \link{table} +#' @seealso \url{https://spark.apache.org/docs/latest/sparkr.html#sparkr-dataframes} #' @export +#' @examples +#'\dontrun{ +#' sc <- sparkR.init() +#' sqlContext <- sparkRSQL.init(sc) +#' df <- createDataFrame(sqlContext, faithful) +#'} setClass("DataFrame", slots = list(env = "environment", sdf = "jobj")) @@ -46,7 +54,6 @@ setMethod("initialize", "DataFrame", function(.Object, sdf, isCached) { #' @rdname DataFrame #' @export -#' #' @param sdf A Java object reference to the backing Scala DataFrame #' @param isCached TRUE if the dataFrame is cached dataFrame <- function(sdf, isCached = FALSE) { @@ -61,6 +68,7 @@ dataFrame <- function(sdf, isCached = FALSE) { #' #' @param x A SparkSQL DataFrame #' +#' @family dataframe_funcs #' @rdname printSchema #' @name printSchema #' @export @@ -85,6 +93,7 @@ setMethod("printSchema", #' #' @param x A SparkSQL DataFrame #' +#' @family dataframe_funcs #' @rdname schema #' @name schema #' @export @@ -108,6 +117,7 @@ setMethod("schema", #' #' @param x A SparkSQL DataFrame #' @param extended Logical. If extended is False, explain() only prints the physical plan. +#' @family dataframe_funcs #' @rdname explain #' @name explain #' @export @@ -138,6 +148,7 @@ setMethod("explain", #' #' @param x A SparkSQL DataFrame #' +#' @family dataframe_funcs #' @rdname isLocal #' @name isLocal #' @export @@ -162,6 +173,7 @@ setMethod("isLocal", #' @param x A SparkSQL DataFrame #' @param numRows The number of rows to print. Defaults to 20. #' +#' @family dataframe_funcs #' @rdname showDF #' @name showDF #' @export @@ -186,6 +198,7 @@ setMethod("showDF", #' #' @param x A SparkSQL DataFrame #' +#' @family dataframe_funcs #' @rdname show #' @name show #' @export @@ -212,6 +225,7 @@ setMethod("show", "DataFrame", #' #' @param x A SparkSQL DataFrame #' +#' @family dataframe_funcs #' @rdname dtypes #' @name dtypes #' @export @@ -237,6 +251,7 @@ setMethod("dtypes", #' #' @param x A SparkSQL DataFrame #' +#' @family dataframe_funcs #' @rdname columns #' @name columns #' @aliases names @@ -257,6 +272,7 @@ setMethod("columns", }) }) +#' @family dataframe_funcs #' @rdname columns #' @name names setMethod("names", @@ -265,6 +281,7 @@ setMethod("names", columns(x) }) +#' @family dataframe_funcs #' @rdname columns #' @name names<- setMethod("names<-", @@ -283,6 +300,7 @@ setMethod("names<-", #' @param x A SparkSQL DataFrame #' @param tableName A character vector containing the name of the table #' +#' @family dataframe_funcs #' @rdname registerTempTable #' @name registerTempTable #' @export @@ -310,6 +328,7 @@ setMethod("registerTempTable", #' @param overwrite A logical argument indicating whether or not to overwrite #' the existing rows in the table. #' +#' @family dataframe_funcs #' @rdname insertInto #' @name insertInto #' @export @@ -334,6 +353,7 @@ setMethod("insertInto", #' #' @param x A SparkSQL DataFrame #' +#' @family dataframe_funcs #' @rdname cache #' @name cache #' @export @@ -360,6 +380,8 @@ setMethod("cache", #' \url{http://spark.apache.org/docs/latest/programming-guide.html#rdd-persistence}. #' #' @param x The DataFrame to persist +#' +#' @family dataframe_funcs #' @rdname persist #' @name persist #' @export @@ -386,6 +408,8 @@ setMethod("persist", #' #' @param x The DataFrame to unpersist #' @param blocking Whether to block until all blocks are deleted +#' +#' @family dataframe_funcs #' @rdname unpersist-methods #' @name unpersist #' @export @@ -412,6 +436,8 @@ setMethod("unpersist", #' #' @param x A SparkSQL DataFrame #' @param numPartitions The number of partitions to use. +#' +#' @family dataframe_funcs #' @rdname repartition #' @name repartition #' @export @@ -435,8 +461,10 @@ setMethod("repartition", # Convert the rows of a DataFrame into JSON objects and return an RDD where # each element contains a JSON string. # -#@param x A SparkSQL DataFrame +# @param x A SparkSQL DataFrame # @return A StringRRDD of JSON objects +# +# @family dataframe_funcs # @rdname tojson # @export # @examples @@ -462,6 +490,8 @@ setMethod("toJSON", #' #' @param x A SparkSQL DataFrame #' @param path The directory where the file is saved +#' +#' @family dataframe_funcs #' @rdname saveAsParquetFile #' @name saveAsParquetFile #' @export @@ -484,6 +514,8 @@ setMethod("saveAsParquetFile", #' Return a new DataFrame containing the distinct rows in this DataFrame. #' #' @param x A SparkSQL DataFrame +#' +#' @family dataframe_funcs #' @rdname distinct #' @name distinct #' @export @@ -506,6 +538,7 @@ setMethod("distinct", # #' @description Returns a new DataFrame containing distinct rows in this DataFrame #' +#' @family dataframe_funcs #' @rdname unique #' @name unique #' @aliases distinct @@ -522,6 +555,8 @@ setMethod("unique", #' @param x A SparkSQL DataFrame #' @param withReplacement Sampling with replacement or not #' @param fraction The (rough) sample target fraction +#' +#' @family dataframe_funcs #' @rdname sample #' @aliases sample_frac #' @export @@ -545,6 +580,7 @@ setMethod("sample", dataFrame(sdf) }) +#' @family dataframe_funcs #' @rdname sample #' @name sample_frac setMethod("sample_frac", @@ -560,6 +596,7 @@ setMethod("sample_frac", #' #' @param x A SparkSQL DataFrame #' +#' @family dataframe_funcs #' @rdname count #' @name count #' @aliases nrow @@ -583,6 +620,7 @@ setMethod("count", #' #' @name nrow #' +#' @family dataframe_funcs #' @rdname nrow #' @aliases count setMethod("nrow", @@ -595,6 +633,7 @@ setMethod("nrow", #' #' @param x a SparkSQL DataFrame #' +#' @family dataframe_funcs #' @rdname ncol #' @name ncol #' @export @@ -615,6 +654,7 @@ setMethod("ncol", #' Returns the dimentions (number of rows and columns) of a DataFrame #' @param x a SparkSQL DataFrame #' +#' @family dataframe_funcs #' @rdname dim #' @name dim #' @export @@ -637,6 +677,8 @@ setMethod("dim", #' @param x A SparkSQL DataFrame #' @param stringsAsFactors (Optional) A logical indicating whether or not string columns #' should be converted to factors. FALSE by default. +#' +#' @family dataframe_funcs #' @rdname collect #' @name collect #' @export @@ -704,6 +746,7 @@ setMethod("collect", #' @param num The number of rows to return #' @return A new DataFrame containing the number of rows specified. #' +#' @family dataframe_funcs #' @rdname limit #' @name limit #' @export @@ -724,6 +767,7 @@ setMethod("limit", #' Take the first NUM rows of a DataFrame and return a the results as a data.frame #' +#' @family dataframe_funcs #' @rdname take #' @name take #' @export @@ -752,6 +796,7 @@ setMethod("take", #' @param num The number of rows to return. Default is 6. #' @return A data.frame #' +#' @family dataframe_funcs #' @rdname head #' @name head #' @export @@ -774,6 +819,7 @@ setMethod("head", #' #' @param x A SparkSQL DataFrame #' +#' @family dataframe_funcs #' @rdname first #' @name first #' @export @@ -797,6 +843,7 @@ setMethod("first", # # @param x A Spark DataFrame # +# @family dataframe_funcs # @rdname DataFrame # @export # @examples @@ -827,6 +874,7 @@ setMethod("toRDD", #' @return a GroupedData #' @seealso GroupedData #' @aliases group_by +#' @family dataframe_funcs #' @rdname groupBy #' @name groupBy #' @export @@ -851,6 +899,7 @@ setMethod("groupBy", groupedData(sgd) }) +#' @family dataframe_funcs #' @rdname groupBy #' @name group_by setMethod("group_by", @@ -864,6 +913,7 @@ setMethod("group_by", #' Compute aggregates by specifying a list of columns #' #' @param x a DataFrame +#' @family dataframe_funcs #' @rdname agg #' @name agg #' @aliases summarize @@ -874,6 +924,7 @@ setMethod("agg", agg(groupBy(x), ...) }) +#' @family dataframe_funcs #' @rdname agg #' @name summarize setMethod("summarize", @@ -889,6 +940,7 @@ setMethod("summarize", # the requested map function. # ################################################################################### +# @family dataframe_funcs # @rdname lapply setMethod("lapply", signature(X = "DataFrame", FUN = "function"), @@ -897,6 +949,7 @@ setMethod("lapply", lapply(rdd, FUN) }) +# @family dataframe_funcs # @rdname lapply setMethod("map", signature(X = "DataFrame", FUN = "function"), @@ -904,6 +957,7 @@ setMethod("map", lapply(X, FUN) }) +# @family dataframe_funcs # @rdname flatMap setMethod("flatMap", signature(X = "DataFrame", FUN = "function"), @@ -911,7 +965,7 @@ setMethod("flatMap", rdd <- toRDD(X) flatMap(rdd, FUN) }) - +# @family dataframe_funcs # @rdname lapplyPartition setMethod("lapplyPartition", signature(X = "DataFrame", FUN = "function"), @@ -920,6 +974,7 @@ setMethod("lapplyPartition", lapplyPartition(rdd, FUN) }) +# @family dataframe_funcs # @rdname lapplyPartition setMethod("mapPartitions", signature(X = "DataFrame", FUN = "function"), @@ -927,6 +982,7 @@ setMethod("mapPartitions", lapplyPartition(X, FUN) }) +# @family dataframe_funcs # @rdname foreach setMethod("foreach", signature(x = "DataFrame", func = "function"), @@ -935,6 +991,7 @@ setMethod("foreach", foreach(rdd, func) }) +# @family dataframe_funcs # @rdname foreach setMethod("foreachPartition", signature(x = "DataFrame", func = "function"), @@ -1034,6 +1091,7 @@ setMethod("[", signature(x = "DataFrame", i = "Column"), #' @param select expression for the single Column or a list of columns to select from the DataFrame #' @return A new DataFrame containing only the rows that meet the condition with selected columns #' @export +#' @family dataframe_funcs #' @rdname subset #' @name subset #' @aliases [ @@ -1064,6 +1122,7 @@ setMethod("subset", signature(x = "DataFrame"), #' @param col A list of columns or single Column or name #' @return A new DataFrame with selected columns #' @export +#' @family dataframe_funcs #' @rdname select #' @name select #' @family subsetting functions @@ -1091,6 +1150,7 @@ setMethod("select", signature(x = "DataFrame", col = "character"), } }) +#' @family dataframe_funcs #' @rdname select #' @export setMethod("select", signature(x = "DataFrame", col = "Column"), @@ -1102,6 +1162,7 @@ setMethod("select", signature(x = "DataFrame", col = "Column"), dataFrame(sdf) }) +#' @family dataframe_funcs #' @rdname select #' @export setMethod("select", @@ -1126,6 +1187,7 @@ setMethod("select", #' @param expr A string containing a SQL expression #' @param ... Additional expressions #' @return A DataFrame +#' @family dataframe_funcs #' @rdname selectExpr #' @name selectExpr #' @export @@ -1153,6 +1215,7 @@ setMethod("selectExpr", #' @param colName A string containing the name of the new column. #' @param col A Column expression. #' @return A DataFrame with the new column added. +#' @family dataframe_funcs #' @rdname withColumn #' @name withColumn #' @aliases mutate transform @@ -1178,6 +1241,7 @@ setMethod("withColumn", #' @param .data A DataFrame #' @param col a named argument of the form name = col #' @return A new DataFrame with the new columns added. +#' @family dataframe_funcs #' @rdname withColumn #' @name mutate #' @aliases withColumn transform @@ -1211,6 +1275,7 @@ setMethod("mutate", }) #' @export +#' @family dataframe_funcs #' @rdname withColumn #' @name transform #' @aliases withColumn mutate @@ -1228,6 +1293,7 @@ setMethod("transform", #' @param existingCol The name of the column you want to change. #' @param newCol The new column name. #' @return A DataFrame with the column name changed. +#' @family dataframe_funcs #' @rdname withColumnRenamed #' @name withColumnRenamed #' @export @@ -1259,6 +1325,7 @@ setMethod("withColumnRenamed", #' @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_funcs #' @rdname withColumnRenamed #' @name rename #' @aliases withColumnRenamed @@ -1303,6 +1370,7 @@ setClassUnion("characterOrColumn", c("character", "Column")) #' @param decreasing A logical argument indicating sorting order for columns when #' a character vector is specified for col #' @return A DataFrame where all elements are sorted. +#' @family dataframe_funcs #' @rdname arrange #' @name arrange #' @aliases orderby @@ -1329,6 +1397,7 @@ setMethod("arrange", dataFrame(sdf) }) +#' @family dataframe_funcs #' @rdname arrange #' @export setMethod("arrange", @@ -1360,6 +1429,7 @@ setMethod("arrange", do.call("arrange", c(x, jcols)) }) +#' @family dataframe_funcs #' @rdname arrange #' @name orderby setMethod("orderBy", @@ -1376,6 +1446,7 @@ setMethod("orderBy", #' @param condition The condition to filter on. This may either be a Column expression #' or a string containing a SQL statement #' @return A DataFrame containing only the rows that meet the condition. +#' @family dataframe_funcs #' @rdname filter #' @name filter #' @family subsetting functions @@ -1399,6 +1470,7 @@ setMethod("filter", dataFrame(sdf) }) +#' @family dataframe_funcs #' @rdname filter #' @name where setMethod("where", @@ -1419,6 +1491,7 @@ setMethod("where", #' 'inner', 'outer', 'full', 'fullouter', leftouter', 'left_outer', 'left', #' 'right_outer', 'rightouter', 'right', and 'leftsemi'. The default joinType is "inner". #' @return A DataFrame containing the result of the join operation. +#' @family dataframe_funcs #' @rdname join #' @name join #' @export @@ -1477,6 +1550,7 @@ setMethod("join", #' be returned. If all.x is set to FALSE and all.y is set to TRUE, a right #' outer join will be returned. If all.x and all.y are set to TRUE, a full #' outer join will be returned. +#' @family dataframe_funcs #' @rdname merge #' @export #' @examples @@ -1608,6 +1682,7 @@ generateAliasesForIntersectedCols <- function (x, intersectedColNames, suffix) { #' @param x A Spark DataFrame #' @param y A Spark DataFrame #' @return A DataFrame containing the result of the union. +#' @family dataframe_funcs #' @rdname unionAll #' @name unionAll #' @export @@ -1627,9 +1702,10 @@ setMethod("unionAll", }) #' @title Union two or more DataFrames -# +#' #' @description Returns a new DataFrame containing rows of all parameters. -# +#' +#' @family dataframe_funcs #' @rdname rbind #' @name rbind #' @aliases unionAll @@ -1651,6 +1727,7 @@ setMethod("rbind", #' @param x A Spark DataFrame #' @param y A Spark DataFrame #' @return A DataFrame containing the result of the intersect. +#' @family dataframe_funcs #' @rdname intersect #' @name intersect #' @export @@ -1677,6 +1754,7 @@ setMethod("intersect", #' @param x A Spark DataFrame #' @param y A Spark DataFrame #' @return A DataFrame containing the result of the except operation. +#' @family dataframe_funcs #' @rdname except #' @name except #' @export @@ -1716,6 +1794,7 @@ setMethod("except", #' @param source A name for external data source #' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode #' +#' @family dataframe_funcs #' @rdname write.df #' @name write.df #' @aliases saveDF @@ -1751,6 +1830,7 @@ setMethod("write.df", callJMethod(df@sdf, "save", source, jmode, options) }) +#' @family dataframe_funcs #' @rdname write.df #' @name saveDF #' @export @@ -1781,6 +1861,7 @@ setMethod("saveDF", #' @param source A name for external data source #' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode #' +#' @family dataframe_funcs #' @rdname saveAsTable #' @name saveAsTable #' @export @@ -1821,6 +1902,7 @@ setMethod("saveAsTable", #' @param col A string of name #' @param ... Additional expressions #' @return A DataFrame +#' @family dataframe_funcs #' @rdname describe #' @name describe #' @aliases summary @@ -1843,6 +1925,7 @@ setMethod("describe", dataFrame(sdf) }) +#' @family dataframe_funcs #' @rdname describe #' @name describe setMethod("describe", @@ -1857,6 +1940,7 @@ setMethod("describe", #' #' @description Computes statistics for numeric columns of the DataFrame #' +#' @family dataframe_funcs #' @rdname summary #' @name summary setMethod("summary", @@ -1881,6 +1965,7 @@ setMethod("summary", #' @param cols Optional list of column names to consider. #' @return A DataFrame #' +#' @family dataframe_funcs #' @rdname nafunctions #' @name dropna #' @aliases na.omit @@ -1910,6 +1995,7 @@ setMethod("dropna", dataFrame(sdf) }) +#' @family dataframe_funcs #' @rdname nafunctions #' @name na.omit #' @export @@ -1937,6 +2023,7 @@ setMethod("na.omit", #' column is simply ignored. #' @return A DataFrame #' +#' @family dataframe_funcs #' @rdname nafunctions #' @name fillna #' @export @@ -2000,6 +2087,7 @@ setMethod("fillna", #' @title Download data from a DataFrame into a data.frame #' @param x a DataFrame #' @return a data.frame +#' @family dataframe_funcs #' @rdname as.data.frame #' @examples \dontrun{ #' @@ -2020,6 +2108,7 @@ setMethod("as.data.frame", #' the DataFrame is searched by R when evaluating a variable, so columns in #' the DataFrame can be accessed by simply giving their names. #' +#' @family dataframe_funcs #' @rdname attach #' @title Attach DataFrame to R search path #' @param what (DataFrame) The DataFrame to attach |