Github user felixcheung commented on a diff in the pull request:
https://github.com/apache/spark/pull/9613#discussion_r44735133
--- Diff: R/pkg/R/DataFrame.R ---
@@ -2200,4 +2200,107 @@ setMethod("coltypes",
rTypes[naIndices] <- types[naIndices]
rTypes
- })
\ No newline at end of file
+ })
+
+#' Display the structure of a DataFrame, including column names, column
types, as well as a
+#' a small sample of rows.
+#' @name str
+#' @title Compactly display the structure of a dataset
+#' @rdname str_data_frame
+#' @family dataframe_funcs
+#' @param x a DataFrame
+#' @examples \dontrun{
+#'
+#' # Create a DataFrame from the Iris dataset
+#' irisDF <- createDataFrame(sqlContext, iris)
+#'
+#' # Show the structure of the DataFrame
+#' str(irisDF)
+#'
+#' }
+setMethod("str", signature="DataFrame", definition=
+ function(object) {
+
+ # A synonym for easily concatenating strings
+ "%++%" <- function(x, y) {
+ paste(x, y, sep = "")
+ }
+
+ # TODO: These could be made global parameters, though in R
it's not the case
+ DEFAULT_HEAD_ROWS <- 6
+ MAX_CHAR_PER_ROW <- 120
+ MAX_COLS <- 100
+
+ # Get the column names and types of the DataFrame
+ names <- names(object)
+ types <- coltypes(object)
+
+ # Get the number of rows.
+ # TODO: Ideally, this should be cached
+ cachedCount <- nrow(object)
+
+ # Get the first elements of the dataset. Limit number of
columns accordingly
+ dataFrame <- if (ncol(object) > MAX_COLS) {
+ head(object[, c(1:MAX_COLS)],
DEFAULT_HEAD_ROWS)
+ } else {
+ head(object, DEFAULT_HEAD_ROWS)
+ }
+
+ # The number of observations will be displayed only if the
number
+ # of rows of the dataset has already been cached.
+ if (!is.null(cachedCount)) {
+ cat("'" %++% class(object) %++% "': " %++% cachedCount
%++% " obs. of " %++%
+ length(names) %++% " variables:\n")
+ } else {
+ cat("'" %++% class(object) %++% "': " %++% length(names)
%++% " variables:\n")
+ }
+
+ # Whether the ... should be printed at the end of each row
+ ellipsis <- FALSE
+
+ # Add ellipsis (i.e., "...") if there are more rows than
shown
+ if (!is.null(cachedCount)) {
+ if (nrow(object) > DEFAULT_HEAD_ROWS) {
+ ellipsis <- TRUE
+ }
+ }
+
+ if (nrow(dataFrame) > 0) {
+ for (i in 1 : ncol(dataFrame)) {
+ firstElements <- ""
+
+ # Get the first elements for each column
+ if (types[i] == "chr") {
--- End diff --
`types` is from calling `dtypes` above right, how do we get "chr" from that?
---
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]
