Github user srowen commented on a diff in the pull request: https://github.com/apache/spark/pull/16607#discussion_r96307444 --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala --- @@ -320,14 +341,29 @@ object Word2VecModel extends MLReadable[Word2VecModel] { private val className = classOf[Word2VecModel].getName override def load(path: String): Word2VecModel = { + val spark = sparkSession + import spark.implicits._ + val metadata = DefaultParamsReader.loadMetadata(path, sc, className) + val dataPath = new Path(path, "data").toString - val data = sparkSession.read.parquet(dataPath) - .select("wordIndex", "wordVectors") - .head() - val wordIndex = data.getAs[Map[String, Int]](0) - val wordVectors = data.getAs[Seq[Float]](1).toArray - val oldModel = new feature.Word2VecModel(wordIndex, wordVectors) + val rawData = spark.read.parquet(dataPath) + + val oldModel = if (rawData.columns.contains("wordIndex")) { + val data = rawData + .select("wordIndex", "wordVectors") + .head() + val wordIndex = data.getAs[Map[String, Int]](0) + val wordVectors = data.getAs[Seq[Float]](1).toArray + new feature.Word2VecModel(wordIndex, wordVectors) + } else { + val wordVectorsMap: Map[String, Array[Float]] = rawData.as[Data] --- End diff -- Type isn't needed here, nor in general on locals
--- 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