HyukjinKwon commented on a change in pull request #23760: [SPARK-26762][SQL][R]
Arrow optimization for conversion from Spark DataFrame to R DataFrame
URL: https://github.com/apache/spark/pull/23760#discussion_r255798391
##########
File path: R/pkg/R/DataFrame.R
##########
@@ -1177,11 +1177,62 @@ setMethod("dim",
setMethod("collect",
signature(x = "SparkDataFrame"),
function(x, stringsAsFactors = FALSE) {
+ useArrow <- FALSE
+ arrowEnabled <-
sparkR.conf("spark.sql.execution.arrow.enabled")[[1]] == "true"
+ if (arrowEnabled) {
+ useArrow <- tryCatch({
+ # Currenty Arrow optimization does not support raw for now.
+ # Also, it does not support explicit float type set by users.
+ if (inherits(schema(x), "structType")) {
+ if (any(sapply(schema(x)$fields(),
+ function(x) x$dataType.toString() ==
"FloatType"))) {
+ stop(paste0("Arrow optimization in the conversion from
Spark DataFrame to R ",
+ "DataFrame does not support FloatType yet."))
+ }
+ if (any(sapply(schema(x)$fields(),
+ function(x) x$dataType.toString() ==
"BinaryType"))) {
+ stop(paste0("Arrow optimization in the conversion from
Spark DataFrame to R ",
+ "DataFrame does not support BinaryType yet."))
+ }
+ }
+ TRUE
+ },
+ error = function(e) {
+ warning(paste0("The conversion from Spark DataFrame to R
DataFrame was attempted ",
+ "with Arrow optimization because ",
+ "'spark.sql.execution.arrow.enabled' is set to
true; however, ",
+ "failed, attempting non-optimization. Reason: ",
+ e))
+ FALSE
+ })
+ }
+
dtypes <- dtypes(x)
ncol <- length(dtypes)
if (ncol <= 0) {
# empty data.frame with 0 columns and 0 rows
data.frame()
+ } else if (useArrow) {
+ # This is a hack to avoid CRAN check. Arrow is not uploaded into
CRAN now.
+ # See ARROW-3204.
+ requireNamespace1 <- requireNamespace
Review comment:
cc @felixcheung, I promise I will get rid of this as soon as Arrow is
available on CRAN (hopefully before Spark 3.0)
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
