diff options
Diffstat (limited to 'mllib')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala index 10dcda2382..d5cb05f29b 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala @@ -210,6 +210,7 @@ class CountVectorizerModel(override val uid: String, val vocabulary: Array[Strin private var broadcastDict: Option[Broadcast[Map[String, Int]]] = None override def transform(dataset: DataFrame): DataFrame = { + transformSchema(dataset.schema, logging = true) if (broadcastDict.isEmpty) { val dict = vocabulary.zipWithIndex.toMap broadcastDict = Some(dataset.sqlContext.sparkContext.broadcast(dict)) |