aboutsummaryrefslogtreecommitdiff
path: root/R/pkg/R/DataFrame.R
diff options
context:
space:
mode:
Diffstat (limited to 'R/pkg/R/DataFrame.R')
-rw-r--r--R/pkg/R/DataFrame.R33
1 files changed, 1 insertions, 32 deletions
diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R
index 14aea923fc..85db3a5ed3 100644
--- a/R/pkg/R/DataFrame.R
+++ b/R/pkg/R/DataFrame.R
@@ -1828,36 +1828,6 @@ 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 zero as their counts.
-#'
-#' @rdname statfunctions
-#' @name crosstab
-#' @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))
- })
-
-
#' This function downloads the contents of a DataFrame into an R's data.frame.
#' Since data.frames are held in memory, ensure that you have enough memory
#' in your system to accommodate the contents.
@@ -1879,5 +1849,4 @@ setMethod("as.data.frame",
stop(paste("Unused argument(s): ", paste(list(...), collapse=", ")))
}
collect(x)
- }
-)
+ })