zhengruifeng commented on a change in pull request #30548:
URL: https://github.com/apache/spark/pull/30548#discussion_r534612019
##########
File path: mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
##########
@@ -278,34 +279,45 @@ class Word2VecModel private[ml] (
@Since("1.4.0")
def setOutputCol(value: String): this.type = set(outputCol, value)
+ private var bcModel: Broadcast[Word2VecModel] = _
+
/**
* Transform a sentence column to a vector column to represent the whole
sentence. The transform
* is performed by averaging all word vectors it contains.
*/
@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] =>
+
+ if (bcModel == null) {
+ bcModel = dataset.sparkSession.sparkContext.broadcast(this)
Review comment:
yes, there are two `wordVectors`...
----------------------------------------------------------------
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]
