diff options
-rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/mllib/LDAExample.scala | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/LDAExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/LDAExample.scala index 7e50b122e6..b923e627f2 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/LDAExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/LDAExample.scala @@ -24,8 +24,9 @@ import scopt.OptionParser import org.apache.spark.{SparkConf, SparkContext} import org.apache.spark.ml.Pipeline import org.apache.spark.ml.feature.{CountVectorizer, CountVectorizerModel, RegexTokenizer, StopWordsRemover} +import org.apache.spark.ml.linalg.{Vector => MLVector} import org.apache.spark.mllib.clustering.{DistributedLDAModel, EMLDAOptimizer, LDA, OnlineLDAOptimizer} -import org.apache.spark.mllib.linalg.Vector +import org.apache.spark.mllib.linalg.{Vector, Vectors} import org.apache.spark.rdd.RDD import org.apache.spark.sql.{Row, SparkSession} @@ -223,7 +224,7 @@ object LDAExample { val documents = model.transform(df) .select("features") .rdd - .map { case Row(features: Vector) => features } + .map { case Row(features: MLVector) => Vectors.fromML(features) } .zipWithIndex() .map(_.swap) |