Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/5748#discussion_r35392037
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala ---
@@ -548,6 +545,24 @@ class Word2VecModel private[spark] (
@Experimental
object Word2VecModel extends Loader[Word2VecModel] {
+ private def buildWordIndex(model: Map[String, Array[Float]]):
Map[String, Int] = {
+ model.keys.zipWithIndex.toMap
+ }
+
+ private def buildWordVectors(model: Map[String, Array[Float]]):
Array[Float] = {
+ require(!model.isEmpty, "Word2VecMap should be non-empty")
+ val (vectorSize, numWords) = (model.head._2.size, model.size)
+ val wordList = model.keys.toArray
+ val wordVectors = new Array[Float](vectorSize * numWords)
+ var i = 0
+ while (i < numWords) {
+ val vec = model.get(wordList(i)).get
--- End diff --
style: Use ```model(wordList(i))``` rather than "get"
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
