srowen commented on a change in pull request #30548:
URL: https://github.com/apache/spark/pull/30548#discussion_r536781521
##########
File path: mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
##########
@@ -285,27 +285,33 @@ class Word2VecModel private[ml] (
@Since("2.0.0")
override def transform(dataset: Dataset[_]): DataFrame = {
val outputSchema = transformSchema(dataset.schema, logging = true)
- val vectors = wordVectors.getVectors
- .mapValues(vv => Vectors.dense(vv.map(_.toDouble)))
- .map(identity).toMap // mapValues doesn't return a serializable map
(SI-7005)
- val bVectors = dataset.sparkSession.sparkContext.broadcast(vectors)
- val d = $(vectorSize)
- val emptyVec = Vectors.sparse(d, Array.emptyIntArray,
Array.emptyDoubleArray)
- val word2Vec = udf { sentence: Seq[String] =>
+
+ val bcModel = dataset.sparkSession.sparkContext.broadcast(this.wordVectors)
Review comment:
Looks good but i'd back out this part of the change
----------------------------------------------------------------
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]
