zhengruifeng commented on code in PR #47904:
URL: https://github.com/apache/spark/pull/47904#discussion_r1735745727
##########
mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala:
##########
@@ -197,53 +196,43 @@ class StringIndexer @Since("1.4.0") (
}
}
- private def countByValue(
- dataset: Dataset[_],
- inputCols: Array[String]): Array[OpenHashMap[String, Long]] = {
+ private def sortByFreq(dataset: Dataset[_], ascending: Boolean):
Array[Array[String]] = {
+ val (inputCols, _) = getInOutCols()
val selectedCols = getSelectedCols(dataset, inputCols.toImmutableArraySeq)
- val results = Array.fill(selectedCols.size)(new OpenHashMap[String,
Long]())
+ val numCols = inputCols.length
+
+ // In the case of equal frequency, always sorts strings by alphabet
(ascending).
+ val countCol = if (ascending) count(lit(1)) else negate(count(lit(1)))
+
+ val result = Array.fill(numCols)(Array.empty[String])
dataset.select(posexplode(array(selectedCols: _*)).as(Seq("index",
"value")))
.where(col("value").isNotNull)
.groupBy("index", "value")
- .agg(count(lit(1)).as("count"))
+ .agg(countCol.as("count"))
.groupBy("index")
- .agg(collect_list(struct("value", "count")))
+ .agg(collect_list(struct("count", "value")).alias("array"))
+ .repartition(8, col("index"))
Review Comment:
to be consistent with original parallelism:
```
ThreadUtils.parmap(orgStrings, "sortingStringLabels", 8) { counts =>
counts.toSeq.sortWith(sortFunc).map(_._1).toArray
}.toArray
```
on second thought, I think we can remove it
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
