Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/10152#discussion_r52722467 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala --- @@ -289,24 +301,20 @@ 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 => - new Iterator[Array[Int]] { - def hasNext: Boolean = iter.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 { - case Some(w) => - sentence += w - sentenceLength += 1 - case None => - } + // each partition is a collection of sentences, + // will be translated into arrays of Index integer + val sentences: RDD[Array[Int]] = dataset.mapPartitions { sentenceIter => + // Each sentence will map to 0 or more Array[Int] + sentenceIter.flatMap { sentence => { + // Sentence of words, some of which map to a word index + val wordIndexes = sentence.flatMap(bcVocabHash.value.get) + if (wordIndexes.nonEmpty) { + // break wordIndexes into trunks of maxSentenceLength when has more + val sentenceSplit = wordIndexes.grouped(maxSentenceLength) + sentenceSplit.map(_.toArray) --- End diff -- `sentenceSplit` should be an `Iterator[Array[Int]]`. So this line might be unnecessary.
--- 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