From a5257048d74359c3fa7810009be1d60d370e2896 Mon Sep 17 00:00:00 2001
From: Liu Xiang <lxmtlab@gmail.com>
Date: Thu, 11 Feb 2016 17:28:37 -0800
Subject: [PATCH] [SPARK-12765][ML][COUNTVECTORIZER] fix
CountVectorizer.transform's lost transformSchema
https://issues.apache.org/jira/browse/SPARK-12765
Author: Liu Xiang <lxmtlab@gmail.com>
Closes #10720 from sloth2012/sloth.
---
.../main/scala/org/apache/spark/ml/feature/CountVectorizer.scala | 1 +
1 file changed, 1 insertion(+)
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))
--
GitLab