From aa6564f37f1d8de77c3b7bfa885000252efffea6 Mon Sep 17 00:00:00 2001 From: Yuhao Yang Date: Thu, 30 Jun 2016 19:34:51 -0700 Subject: [SPARK-14608][ML] transformSchema needs better documentation ## What changes were proposed in this pull request? jira: https://issues.apache.org/jira/browse/SPARK-14608 PipelineStage.transformSchema currently has minimal documentation. It should have more to explain it can: check schema check parameter interactions ## How was this patch tested? unit test Author: Yuhao Yang Author: Yuhao Yang Closes #12384 from hhbyyh/transformSchemaDoc. --- mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'mllib/src') diff --git a/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala b/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala index 25e56d70c2..a1d08b3a6e 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala @@ -44,7 +44,10 @@ abstract class PipelineStage extends Params with Logging { /** * :: DeveloperApi :: * - * Derives the output schema from the input schema. + * Check transform validity and derive the output schema from the input schema. + * + * Typical implementation should first conduct verification on schema change and parameter + * validity, including complex parameter interaction checks. */ @DeveloperApi def transformSchema(schema: StructType): StructType -- cgit v1.2.3