viirya commented on a change in pull request #20146: [SPARK-11215][ML] Add
multiple columns support to StringIndexer
URL: https://github.com/apache/spark/pull/20146#discussion_r243734787
##########
File path: mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
##########
@@ -130,21 +165,69 @@ class StringIndexer @Since("1.4.0") (
@Since("1.4.0")
def setOutputCol(value: String): this.type = set(outputCol, value)
+ /** @group setParam */
+ @Since("3.0.0")
+ def setInputCols(value: Array[String]): this.type = set(inputCols, value)
+
+ /** @group setParam */
+ @Since("3.0.0")
+ 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)
+ implicit val encoder = Encoders.kryo[Array[OpenHashMap[String, Long]]]
+
+ dataset.select(inputCols.map(col(_).cast(StringType)): _*)
+ .toDF
+ .groupBy().agg(aggregator.toColumn)
+ .as[Array[OpenHashMap[String, Long]]]
+ .collect()(0)
+ }
+
@Since("2.0.0")
override def fit(dataset: Dataset[_]): StringIndexerModel = {
transformSchema(dataset.schema, logging = true)
- val values = dataset.na.drop(Array($(inputCol)))
- .select(col($(inputCol)).cast(StringType))
- .rdd.map(_.getString(0))
- val labels = $(stringOrderType) match {
- case StringIndexer.frequencyDesc =>
values.countByValue().toSeq.sortBy(-_._2)
- .map(_._1).toArray
- case StringIndexer.frequencyAsc =>
values.countByValue().toSeq.sortBy(_._2)
- .map(_._1).toArray
- case StringIndexer.alphabetDesc => values.distinct.collect.sortWith(_ >
_)
- case StringIndexer.alphabetAsc => values.distinct.collect.sortWith(_ < _)
- }
- copyValues(new StringIndexerModel(uid, labels).setParent(this))
+
+ val (inputCols, _) = getInOutCols()
+
+ val filteredDF = dataset.na.drop(inputCols)
Review comment:
Now I handle null and NaN values in `StringIndexerAggregator`.
----------------------------------------------------------------
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]
