diff options
| author | Earthson Lu <Earthson.Lu@gmail.com> | 2016-02-11 18:31:46 -0800 |
|---|---|---|
| committer | Xiangrui Meng <meng@databricks.com> | 2016-02-11 18:31:46 -0800 |
| commit | 5f1c359069545e75dfe83757c67a4be80428d342 (patch) | |
| tree | 09f731a43f4535d6542b975df7ab0f595c9aca70 /mllib | |
| parent | 8121a4b1cb4d7efa84a5e9e8e16d6656cdb79b85 (diff) | |
| download | spark-5f1c359069545e75dfe83757c67a4be80428d342.tar.gz spark-5f1c359069545e75dfe83757c67a4be80428d342.tar.bz2 spark-5f1c359069545e75dfe83757c67a4be80428d342.zip | |
[SPARK-12746][ML] ArrayType(_, true) should also accept ArrayType(_, false)
https://issues.apache.org/jira/browse/SPARK-12746
Author: Earthson Lu <Earthson.Lu@gmail.com>
Closes #10697 from Earthson/SPARK-12746.
Diffstat (limited to 'mllib')
| -rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala | 3 |
1 files changed, 2 insertions, 1 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 d5cb05f29b..a6dfe58e56 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 @@ -71,7 +71,8 @@ private[feature] trait CountVectorizerParams extends Params with HasInputCol wit /** Validates and transforms the input schema. */ protected def validateAndTransformSchema(schema: StructType): StructType = { validateParams() - SchemaUtils.checkColumnType(schema, $(inputCol), new ArrayType(StringType, true)) + val typeCandidates = List(new ArrayType(StringType, true), new ArrayType(StringType, false)) + SchemaUtils.checkColumnTypes(schema, $(inputCol), typeCandidates) SchemaUtils.appendColumn(schema, $(outputCol), new VectorUDT) } |