Github user MLnick commented on a diff in the pull request:
https://github.com/apache/spark/pull/10152#discussion_r47875988
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala ---
@@ -281,17 +295,28 @@ class Word2Vec extends Serializable with Logging {
val expTable = sc.broadcast(createExpTable())
val bcVocab = sc.broadcast(vocab)
val bcVocabHash = sc.broadcast(vocabHash)
-
- val sentences: RDD[Array[Int]] = words.mapPartitions { iter =>
+ // each partition is a collection of sentences, will be translated
into arrays of Index integer
+ val sentences: RDD[Array[Int]] = dataset.mapPartitions { sentenceIter
=>
new Iterator[Array[Int]] {
- def hasNext: Boolean = iter.hasNext
+ var wordIter: Iterator[String] = null
+
+ def hasNext: Boolean = sentenceIter.hasNext || (wordIter != null
&& wordIter.hasNext)
def next(): Array[Int] = {
val sentence = ArrayBuilder.make[Int]
var sentenceLength = 0
- while (iter.hasNext && sentenceLength < MAX_SENTENCE_LENGTH) {
- val word = bcVocabHash.value.get(iter.next())
- word match {
+ // do translation of each word into its index in the vocabulary,
+ // do cutting only when the sentence is larger than
maxSentenceLength
+ if ((wordIter == null || !wordIter.hasNext) &&
sentenceIter.hasNext) {
+ do {
--- End diff --
ok, fair enough
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
