Github user sun-rui commented on a diff in the pull request:
https://github.com/apache/spark/pull/12836#discussion_r62602345
--- Diff: R/pkg/R/DataFrame.R ---
@@ -1187,6 +1187,95 @@ setMethod("dapply",
dataFrame(sdf)
})
+#' gapply
+#'
+#' Apply a function to each group of a DataFrame. The group is defined by
an input
+#' grouping column.
+#' Currently only one grouping column is allowed. Support for multiple
columns will
+#' be added later.
+#'
+#' @param x A SparkDataFrame
+#' @param func A function to be applied to each group partition specified
by grouping
+#' column of the SparkDataFrame.
+#' The output of func is a local R data.frame.
+#' @param schema The schema of the resulting SparkDataFrame after the
function is applied.
+#' It must match the output of func.
+#' @family SparkDataFrame functions
+#' @rdname gapply
+#' @name gapply
+#' @export
+#' @examples
+#'
+#' \dontrun{
+#'
+#' Computes the arithmetic mean of the second column by grouping
+#' on the first column. Output the grouping value and the average.
+#'
+#' df <- createDataFrame (
+#' sqlContext,
+#' list(list(1L, 1, "1", 0.1), list(1L, 2, "2", 0.2), list(3L, 3, "3",
0.3)),
+#' c("a", "b", "c", "d"))
+#'
+#' schema <- structType(structField("a", "integer"), structField("avg",
"double"))
+#' df1 <- gapply(
+#' df,
+#' function(x) {
+#' y <- (data.frame(x$a[1], mean(x$b)))
+#' },
+#' schema, df$"a")
+#' collect(df1)
+#'
+#' Result
+#' ------
+#' a avg
+#' 1 1.5
+#' 3 3.0
+#'
+#' Fits linear models on iris dataset by grouping on the 'Species' column
and
+#' using 'Sepal_Length' as a target variable, 'Sepal_Width', 'Petal_Length'
+#' and 'Petal_Width' as training features.
+#'
+#' df <- createDataFrame (sqlContext, iris)
+#' schema <- structType(structField("(Intercept)", "double"),
+#' structField("Sepal_Width", "double"),structField("Petal_Length",
"double"),
+#' structField("Petal_Width", "double"))
+#' df1 <- gapply(
+#' df,
+#' function(x) {
+#' m <- suppressWarnings(lm(Sepal_Length ~
+#' Sepal_Width + Petal_Length + Petal_Width, x))
+#' data.frame(t(coef(m)))
+#' }, schema, "Species")
+#' collect(df1)
+#'
+#'Result
+#'---------
+#' Model (Intercept) Sepal_Width Petal_Length Petal_Width
+#' 1 0.699883 0.3303370 0.9455356 -0.1697527
+#' 2 1.895540 0.3868576 0.9083370 -0.6792238
+#' 3 2.351890 0.6548350 0.2375602 0.2521257
+#'
+#'}
+setMethod("gapply",
+ signature(x = "SparkDataFrame", func = "function", schema =
"structType",
+ col = "characterOrColumn"),
--- End diff --
it is more natural to adjust the parameter order: x, col, func, schema. col
is a vector that can support mulitple strings or Columns.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
