Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/20146#discussion_r183619017
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala ---
@@ -130,21 +159,57 @@ class StringIndexer @Since("1.4.0") (
@Since("1.4.0")
def setOutputCol(value: String): this.type = set(outputCol, value)
+ /** @group setParam */
+ @Since("2.4.0")
+ def setInputCols(value: Array[String]): this.type = set(inputCols, value)
+
+ /** @group setParam */
+ @Since("2.4.0")
+ def setOutputCols(value: Array[String]): this.type = set(outputCols,
value)
+
+ private def countByValue(
+ dataset: Dataset[_],
+ inputCols: Array[String]): Array[OpenHashMap[String, Long]] = {
+
+ val aggregator = new StringIndexerAggregator(inputCols.length)
--- End diff --
Use SQL `Aggregator` now.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
