srowen commented on a change in pull request #29852:
URL: https://github.com/apache/spark/pull/29852#discussion_r494390254
##########
File path: mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala
##########
@@ -91,20 +90,13 @@ class HashingTF @Since("3.0.0") private[ml] (
@Since("2.0.0")
override def transform(dataset: Dataset[_]): DataFrame = {
val outputSchema = transformSchema(dataset.schema)
- val localNumFeatures = $(numFeatures)
- val localBinary = $(binary)
+ val n = $(numFeatures)
+ val updateFunc = if ($(binary)) (v: Double) => 1.0 else (v: Double) => v +
1.0
val hashUDF = udf { terms: Seq[_] =>
- val termFrequencies = mutable.HashMap.empty[Int,
Double].withDefaultValue(0.0)
- terms.foreach { term =>
- val i = indexOf(term)
- if (localBinary) {
- termFrequencies(i) = 1.0
- } else {
- termFrequencies(i) += 1.0
- }
- }
- Vectors.sparse(localNumFeatures, termFrequencies.toSeq)
+ val map = new OpenHashMap[Int, Double]()
Review comment:
This seems fine but is it faster than Scala's Map? the comment refers to
the Java HashMap.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
