[SPARK-11468][SPARKR] add stddev/variance agg functions for Column

R/pkg/NAMESPACE

@@ -152,6 +152,7 @@ exportMethods("%in%",
               "isNaN",
               "isNotNull",
               "isNull",
+              "kurtosis",
               "lag",
               "last",
               "last_day",
@@ -204,12 +205,17 @@ exportMethods("%in%",
               "shiftLeft",
               "shiftRight",
               "shiftRightUnsigned",
+              "sd",
               "sign",
               "signum",
               "sin",
               "sinh",
               "size",
+              "skewness",
               "soundex",
+              "stddev",
+              "stddev_pop",
+              "stddev_samp",
               "sqrt",
               "startsWith",
               "substr",
@@ -228,6 +234,10 @@ exportMethods("%in%",
               "unhex",
               "unix_timestamp",
               "upper",
+              "var",
+              "variance",
+              "var_pop",
+              "var_samp",
               "weekofyear",
               "when",
               "year")

R/pkg/R/functions.R

@@ -520,6 +520,22 @@ setMethod("isNaN",
             column(jc)
           })
 
+#' kurtosis
+#'
+#' Aggregate function: returns the kurtosis of the values in a group.
+#'
+#' @rdname kurtosis
+#' @name kurtosis
+#' @family agg_funcs
+#' @export
+#' @examples \dontrun{kurtosis(df$c)}
+setMethod("kurtosis",
+          signature(x = "Column"),
+          function(x) {
+            jc <- callJStatic("org.apache.spark.sql.functions", "kurtosis", x@jc)
+            column(jc)
+          })
+
 #' last
 #'
 #' Aggregate function: returns the last value in a group.
@@ -861,6 +877,28 @@ setMethod("rtrim",
             column(jc)
           })
 
+#' sd
+#'
+#' Aggregate function: alias for \link{stddev_samp}
+#'
+#' @rdname sd
+#' @name sd
+#' @family agg_funcs
+#' @seealso \link{stddev_pop}, \link{stddev_samp}
+#' @export
+#' @examples
+#'\dontrun{
+#'stddev(df$c)
+#'select(df, stddev(df$age))
+#'agg(df, sd(df$age))
+#'}
+setMethod("sd",
+          signature(x = "Column"),
+          function(x, na.rm = FALSE) {
+            # In R, sample standard deviation is calculated with the sd() function.
+            stddev_samp(x)
+          })
+
 #' second
 #'
 #' Extracts the seconds as an integer from a given date/timestamp/string.
@@ -958,6 +996,22 @@ setMethod("size",
             column(jc)
           })
 
+#' skewness
+#'
+#' Aggregate function: returns the skewness of the values in a group.
+#'
+#' @rdname skewness
+#' @name skewness
+#' @family agg_funcs
+#' @export
+#' @examples \dontrun{skewness(df$c)}
+setMethod("skewness",
+          signature(x = "Column"),
+          function(x) {
+            jc <- callJStatic("org.apache.spark.sql.functions", "skewness", x@jc)
+            column(jc)
+          })
+
 #' soundex
 #'
 #' Return the soundex code for the specified expression.
@@ -974,6 +1028,49 @@ setMethod("soundex",
             column(jc)
           })
 
+#' @rdname sd
+#' @name stddev
+setMethod("stddev",
+          signature(x = "Column"),
+          function(x) {
+            jc <- callJStatic("org.apache.spark.sql.functions", "stddev", x@jc)
+            column(jc)
+          })
+
+#' stddev_pop
+#'
+#' Aggregate function: returns the population standard deviation of the expression in a group.
+#'
+#' @rdname stddev_pop
+#' @name stddev_pop
+#' @family agg_funcs
+#' @seealso \link{sd}, \link{stddev_samp}
+#' @export
+#' @examples \dontrun{stddev_pop(df$c)}
+setMethod("stddev_pop",
+          signature(x = "Column"),
+          function(x) {
+            jc <- callJStatic("org.apache.spark.sql.functions", "stddev_pop", x@jc)
+            column(jc)
+          })
+
+#' stddev_samp
+#'
+#' Aggregate function: returns the unbiased sample standard deviation of the expression in a group.
+#'
+#' @rdname stddev_samp
+#' @name stddev_samp
+#' @family agg_funcs
+#' @seealso \link{stddev_pop}, \link{sd}
+#' @export
+#' @examples \dontrun{stddev_samp(df$c)}
+setMethod("stddev_samp",
+          signature(x = "Column"),
+          function(x) {
+            jc <- callJStatic("org.apache.spark.sql.functions", "stddev_samp", x@jc)
+            column(jc)
+          })
+
 #' sqrt
 #'
 #' Computes the square root of the specified float value.
@@ -1168,6 +1265,71 @@ setMethod("upper",
             column(jc)
           })
 
+#' var
+#'
+#' Aggregate function: alias for \link{var_samp}.
+#'
+#' @rdname var
+#' @name var
+#' @family agg_funcs
+#' @seealso \link{var_pop}, \link{var_samp}
+#' @export
+#' @examples
+#'\dontrun{
+#'variance(df$c)
+#'select(df, var_pop(df$age))
+#'agg(df, var(df$age))
+#'}
+setMethod("var",
+          signature(x = "Column"),
+          function(x, y = NULL, na.rm = FALSE, use) {
+            # In R, sample variance is calculated with the var() function.
+            var_samp(x)
+          })
+
+#' @rdname var
+#' @name variance
+setMethod("variance",
+          signature(x = "Column"),
+          function(x) {
+            jc <- callJStatic("org.apache.spark.sql.functions", "variance", x@jc)
+            column(jc)
+          })
+
+#' var_pop
+#'
+#' Aggregate function: returns the population variance of the values in a group.
+#'
+#' @rdname var_pop
+#' @name var_pop
+#' @family agg_funcs
+#' @seealso \link{var}, \link{var_samp}
+#' @export
+#' @examples \dontrun{var_pop(df$c)}
+setMethod("var_pop",
+          signature(x = "Column"),
+          function(x) {
+            jc <- callJStatic("org.apache.spark.sql.functions", "var_pop", x@jc)
+            column(jc)
+          })
+
+#' var_samp
+#'
+#' Aggregate function: returns the unbiased variance of the values in a group.
+#'
+#' @rdname var_samp
+#' @name var_samp
+#' @family agg_funcs
+#' @seealso \link{var_pop}, \link{var}
+#' @export
+#' @examples \dontrun{var_samp(df$c)}
+setMethod("var_samp",
+          signature(x = "Column"),
+          function(x) {
+            jc <- callJStatic("org.apache.spark.sql.functions", "var_samp", x@jc)
+            column(jc)
+          })
+
 #' weekofyear
 #'
 #' Extracts the week number as an integer from a given date/timestamp/string.
@@ -2020,10 +2182,10 @@ setMethod("ifelse",
 #'
 #' Window function: returns the cumulative distribution of values within a window partition,
 #' i.e. the fraction of rows that are below the current row.
-#' 
+#'
 #'   N = total number of rows in the partition
 #'   cumeDist(x) = number of values before (and including) x / N
-#'   
+#'
 #' This is equivalent to the CUME_DIST function in SQL.
 #'
 #' @rdname cumeDist
@@ -2039,13 +2201,13 @@ setMethod("cumeDist",
           })
 
 #' denseRank
-#' 
+#'
 #' Window function: returns the rank of rows within a window partition, without any gaps.
 #' The difference between rank and denseRank is that denseRank leaves no gaps in ranking
 #' sequence when there are ties. That is, if you were ranking a competition using denseRank
 #' and had three people tie for second place, you would say that all three were in second
 #' place and that the next person came in third.
-#' 
+#'
 #' This is equivalent to the DENSE_RANK function in SQL.
 #'
 #' @rdname denseRank
@@ -2065,7 +2227,7 @@ setMethod("denseRank",
 #' Window function: returns the value that is `offset` rows before the current row, and
 #' `defaultValue` if there is less than `offset` rows before the current row. For example,
 #' an `offset` of one will return the previous row at any given point in the window partition.
-#' 
+#'
 #' This is equivalent to the LAG function in SQL.
 #'
 #' @rdname lag
@@ -2092,7 +2254,7 @@ setMethod("lag",
 #' Window function: returns the value that is `offset` rows after the current row, and
 #' `null` if there is less than `offset` rows after the current row. For example,
 #' an `offset` of one will return the next row at any given point in the window partition.
-#' 
+#'
 #' This is equivalent to the LEAD function in SQL.
 #'
 #' @rdname lead
@@ -2119,7 +2281,7 @@ setMethod("lead",
 #' Window function: returns the ntile group id (from 1 to `n` inclusive) in an ordered window
 #' partition. Fow example, if `n` is 4, the first quarter of the rows will get value 1, the second
 #' quarter will get 2, the third quarter will get 3, and the last quarter will get 4.
-#' 
+#'
 #' This is equivalent to the NTILE function in SQL.
 #'
 #' @rdname ntile
@@ -2137,9 +2299,9 @@ setMethod("ntile",
 #' percentRank
 #'
 #' Window function: returns the relative rank (i.e. percentile) of rows within a window partition.
-#' 
+#'
 #' This is computed by:
-#' 
+#'
 #'   (rank of row in its partition - 1) / (number of rows in the partition - 1)
 #'
 #' This is equivalent to the PERCENT_RANK function in SQL.
@@ -2159,12 +2321,12 @@ setMethod("percentRank",
 #' rank
 #'
 #' Window function: returns the rank of rows within a window partition.
-#' 
+#'
 #' The difference between rank and denseRank is that denseRank leaves no gaps in ranking
 #' sequence when there are ties. That is, if you were ranking a competition using denseRank
 #' and had three people tie for second place, you would say that all three were in second
 #' place and that the next person came in third.
-#' 
+#'
 #' This is equivalent to the RANK function in SQL.
 #'
 #' @rdname rank
@@ -2189,7 +2351,7 @@ setMethod("rank",
 #' rowNumber
 #'
 #' Window function: returns a sequential number starting at 1 within a window partition.
-#' 
+#'
 #' This is equivalent to the ROW_NUMBER function in SQL.
 #'
 #' @rdname rowNumber

R/pkg/R/generics.R

@@ -798,6 +798,10 @@ setGeneric("instr", function(y, x) { standardGeneric("instr") })
 #' @export
 setGeneric("isNaN", function(x) { standardGeneric("isNaN") })
 
+#' @rdname kurtosis
+#' @export
+setGeneric("kurtosis", function(x) { standardGeneric("kurtosis") })
+
 #' @rdname lag
 #' @export
 setGeneric("lag", function(x, offset, defaultValue = NULL) { standardGeneric("lag") })
@@ -935,6 +939,10 @@ setGeneric("rpad", function(x, len, pad) { standardGeneric("rpad") })
 #' @export
 setGeneric("rtrim", function(x) { standardGeneric("rtrim") })
 
+#' @rdname sd
+#' @export
+setGeneric("sd", function(x, na.rm = FALSE) { standardGeneric("sd") })
+
 #' @rdname second
 #' @export
 setGeneric("second", function(x) { standardGeneric("second") })
@@ -967,10 +975,26 @@ setGeneric("signum", function(x) { standardGeneric("signum") })
 #' @export
 setGeneric("size", function(x) { standardGeneric("size") })
 
+#' @rdname skewness
+#' @export
+setGeneric("skewness", function(x) { standardGeneric("skewness") })
+
 #' @rdname soundex
 #' @export
 setGeneric("soundex", function(x) { standardGeneric("soundex") })
 
+#' @rdname sd
+#' @export
+setGeneric("stddev", function(x) { standardGeneric("stddev") })
+
+#' @rdname stddev_pop
+#' @export
+setGeneric("stddev_pop", function(x) { standardGeneric("stddev_pop") })
+
+#' @rdname stddev_samp
+#' @export
+setGeneric("stddev_samp", function(x) { standardGeneric("stddev_samp") })
+
 #' @rdname substring_index
 #' @export
 setGeneric("substring_index", function(x, delim, count) { standardGeneric("substring_index") })
@@ -1019,6 +1043,22 @@ setGeneric("unix_timestamp", function(x, format) { standardGeneric("unix_timesta
 #' @export
 setGeneric("upper", function(x) { standardGeneric("upper") })
 
+#' @rdname var
+#' @export
+setGeneric("var", function(x, y = NULL, na.rm = FALSE, use) { standardGeneric("var") })
+
+#' @rdname var
+#' @export
+setGeneric("variance", function(x) { standardGeneric("variance") })
+
+#' @rdname var_pop
+#' @export
+setGeneric("var_pop", function(x) { standardGeneric("var_pop") })
+
+#' @rdname var_samp
+#' @export
+setGeneric("var_samp", function(x) { standardGeneric("var_samp") })
+
 #' @rdname weekofyear
 #' @export
 setGeneric("weekofyear", function(x) { standardGeneric("weekofyear") })