From ceba8d9ecf6e9831463fa4070e56a504a93a7740 Mon Sep 17 00:00:00 2001 From: chen-lin Date: Wed, 7 Jun 2017 16:03:46 +0800 Subject: [PATCH 1/2] [SPARK-21005] Fix VectorIndexerModel does not prepare output column field correctly --- .../scala/org/apache/spark/ml/feature/VectorIndexer.scala | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala index d371da762c55..c420db5ed6cc 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala @@ -414,7 +414,11 @@ class VectorIndexerModel private[ml] ( featAttr } case (origAttr: Attribute, featAttr: NumericAttribute) => - origAttr.withIndex(featAttr.index.get) + if (origAttr.name.nonEmpty) { + featAttr.withName(origAttr.name.get) + } else { + featAttr + } case (origAttr: Attribute, _) => origAttr } From e1cae98ea16c15fe8a2af0537333dc155138b870 Mon Sep 17 00:00:00 2001 From: hibayesian Date: Wed, 7 Jun 2017 16:03:46 +0800 Subject: [PATCH 2/2] [SPARK-21005] Fix VectorIndexerModel does not prepare output column field correctly --- .../scala/org/apache/spark/ml/feature/VectorIndexer.scala | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala index d371da762c55..c420db5ed6cc 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala @@ -414,7 +414,11 @@ class VectorIndexerModel private[ml] ( featAttr } case (origAttr: Attribute, featAttr: NumericAttribute) => - origAttr.withIndex(featAttr.index.get) + if (origAttr.name.nonEmpty) { + featAttr.withName(origAttr.name.get) + } else { + featAttr + } case (origAttr: Attribute, _) => origAttr }