Github user olarayej commented on a diff in the pull request: https://github.com/apache/spark/pull/11569#discussion_r57349827 --- Diff: R/pkg/R/functions.R --- @@ -2638,3 +2638,81 @@ 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). The default 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. +#' @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, it would be very easy to +#' # render the histogram using R's visualization packages such as ggplot2. +#' +#' } +setMethod("histogram", + signature(df = "DataFrame"), + function(df, colname, nbins = 10) { + # Validate nbins + if (nbins < 2) { + stop("The number of bins must be a positive integer number greater than 1.") --- End diff -- Done!
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org