Github user olarayej commented on a diff in the pull request:
https://github.com/apache/spark/pull/11569#discussion_r60452619
--- Diff: R/pkg/R/functions.R ---
@@ -2638,3 +2638,100 @@ setMethod("sort_array",
jc <- callJStatic("org.apache.spark.sql.functions",
"sort_array", x@jc, asc)
column(jc)
})
+
+#' This function computes a histogram for a given SparkR Column.
+#'
+#' @name histogram
+#' @title Histogram
+#' @param nbins the number of bins (optional). Default value is 10.
+#' @param df the DataFrame containing the Column to build the histogram
from.
+#' @param colname the name of the column to build the histogram from.
+#' @return a data.frame with the histogram statistics, i.e., counts and
centroids.
+#' @rdname histogram
+#' @family agg_funcs
+#' @export
+#' @examples
+#' \dontrun{
+#' # Create a DataFrame from the Iris dataset
+#' irisDF <- createDataFrame(sqlContext, iris)
+#'
+#' # Compute histogram statistics
+#' histData <- histogram(df, "colname"Sepal_Length", nbins = 12)
+#'
+#' # Once SparkR has computed the histogram statistics, the histogram can
be
+#' # rendered using the ggplot2 library:
+#'
+#' require(ggplot2)
+#' plot <- ggplot(histStats, aes(x = centroids, y = counts))
+#' plot <- plot + geom_histogram(data = histStats, stat = "identity",
binwidth = 100)
+#' plot <- plot + xlab("Sepal_Length") + ylab("Frequency")
+#' }
+setMethod("histogram",
+ signature(df = "DataFrame", col = "characterOrColumn"),
+ function(df, col, nbins = 10) {
+ # Validate nbins
+ if (nbins < 2) {
+ stop("The number of bins must be a positive integer number
greater than 1.")
+ }
+
+ # Round nbins to the smallest integer
+ nbins <- floor(nbins)
+
+ # Validate col
+ if (is.null(col)) {
+ stop("col must be specified.")
+ }
+
+ colname <- col
+ x <- if (class(col) == "character") {
+ if (!colname %in% names(df)) {
+ stop("Specified colname does not belong to the given
DataFrame.")
+ }
+
+ # Filter NA values in the target column
+ df <- na.omit(df[, colname])
+
+ # TODO: This will be when improved SPARK-9325 or SPARK-13436
are fixed
+ eval(parse(text = paste0("df$", colname)))
+ } else if (class(col) == "Column") {
+ # Append the given column to the dataset
+ df$x <- col
+ colname <- "x"
+ col
+ }
+
+ stats <- collect(describe(df[, colname]))
+ min <- as.numeric(stats[4, 2])
+ max <- as.numeric(stats[5, 2])
+
+ # Normalize the data
+ xnorm <- (x - min) / (max - min)
+
+ # Round the data to 4 significant digits. This is to avoid
rounding issues.
+ xnorm <- cast(xnorm * 10000, "integer") / 10000.0
+
+ # Since min = 0, max = 1 (data is already normalized)
+ normBinSize <- 1 / nbins
+ binsize <- (max - min) / nbins
+ approxBins <- xnorm / normBinSize
+
+ # Adjust values that are equal to the upper bound of each bin
+ bins <- cast(approxBins -
+ ifelse(approxBins == cast(approxBins, "integer")
& x != min, 1, 0),
+ "integer")
+
+ df$bins <- bins
--- End diff --
@felixcheung I need to remove NA values from Column `x` too, since `x`
could be an arbitrary Column expression. Therefore, the `na.omit() `invocation
should go afterwards
---
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]
