[SPARK-8364] [SPARKR] Add crosstab to SparkR DataFrames

Add `crosstab` to SparkR DataFrames, which takes two column names and returns a local R data.frame. This is similar to `table` in R. However, `table` in SparkR is used for loading SQL tables as DataFrames. The return type is data.frame instead table for `crosstab` to be compatible with Scala/Python.

I couldn't run R tests successfully on my local. Many unit tests failed. So let's try Jenkins.

Author: Xiangrui Meng <meng@databricks.com>

Closes #7318 from mengxr/SPARK-8364 and squashes the following commits:

d75e894 [Xiangrui Meng] fix tests
53f6ddd [Xiangrui Meng] fix tests
f1348d6 [Xiangrui Meng] update test
47cb088 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-8364
5621262 [Xiangrui Meng] first version without test

R/pkg/NAMESPACE

@@ -26,6 +26,7 @@ exportMethods("arrange",
               "collect",
               "columns",
               "count",
+              "crosstab",
               "describe",
               "distinct",
               "dropna",

R/pkg/R/DataFrame.R

@@ -1554,3 +1554,31 @@ setMethod("fillna",
             }
             dataFrame(sdf)
           })
+
+#' crosstab
+#'
+#' 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.
+#'
+#' @param col1 name of the first column. Distinct items will make the first item of each row.
+#' @param col2 name of the second column. Distinct items will make the column names of the output.
+#' @return a local R data.frame representing the contingency table. The first column of each row
+#'         will be the distinct values of `col1` and the column names will be the distinct values
+#'         of `col2`. The name of the first column will be `$col1_$col2`. Pairs that have no
+#'         occurrences will have `null` as their counts.
+#'
+#' @rdname statfunctions
+#' @export
+#' @examples
+#' \dontrun{
+#' df <- jsonFile(sqlCtx, "/path/to/file.json")
+#' ct = crosstab(df, "title", "gender")
+#' }
+setMethod("crosstab",
+          signature(x = "DataFrame", col1 = "character", col2 = "character"),
+          function(x, col1, col2) {
+            statFunctions <- callJMethod(x@sdf, "stat")
+            sct <- callJMethod(statFunctions, "crosstab", col1, col2)
+            collect(dataFrame(sct))
+          })

R/pkg/R/generics.R

@@ -59,6 +59,10 @@ setGeneric("count", function(x) { standardGeneric("count") })
 # @export
 setGeneric("countByValue", function(x) { standardGeneric("countByValue") })
 
+# @rdname statfunctions
+# @export
+setGeneric("crosstab", function(x, col1, col2) { standardGeneric("crosstab") })
+
 # @rdname distinct
 # @export
 setGeneric("distinct", function(x, numPartitions = 1) { standardGeneric("distinct") })

R/pkg/inst/tests/test_sparkSQL.R

@@ -987,6 +987,19 @@ test_that("fillna() on a DataFrame", {
   expect_identical(expected, actual)
 })
 
+test_that("crosstab() on a DataFrame", {
+  rdd <- lapply(parallelize(sc, 0:3), function(x) {
+    list(paste0("a", x %% 3), paste0("b", x %% 2))
+  })
+  df <- toDF(rdd, list("a", "b"))
+  ct <- crosstab(df, "a", "b")
+  ordered <- ct[order(ct$a_b),]
+  row.names(ordered) <- NULL
+  expected <- data.frame("a_b" = c("a0", "a1", "a2"), "b0" = c(1, 0, 1), "b1" = c(1, 1, 0),
+                         stringsAsFactors = FALSE, row.names = NULL)
+  expect_identical(expected, ordered)
+})
+
 unlink(parquetPath)
 unlink(jsonPath)
 unlink(jsonPathNa)