From 2ad4837cfa66fcedc96b0819a8c2f4c3d70b0aaa Mon Sep 17 00:00:00 2001
From: Xiangrui Meng <meng@databricks.com>
Date: Wed, 20 May 2015 12:50:06 -0700
Subject: [PATCH] [SPARK-7537] [MLLIB] spark.mllib API updates
Minor updates to the spark.mllib APIs:
1. Add `DeveloperApi` to `PMMLExportable` and add `Experimental` to `toPMML` methods.
2. Mention `RankingMetrics.of` in the `RankingMetrics` constructor.
Author: Xiangrui Meng <meng@databricks.com>
Closes #6280 from mengxr/SPARK-7537 and squashes the following commits:
1bd2583 [Xiangrui Meng] organize imports
94afa7a [Xiangrui Meng] mark all toPMML methods experimental
4c40da1 [Xiangrui Meng] mention the factory method for RankingMetrics for Java users
88c62d0 [Xiangrui Meng] add DeveloperApi to PMMLExportable
---
.../spark/mllib/evaluation/RankingMetrics.scala | 2 ++
.../org/apache/spark/mllib/pmml/PMMLExportable.scala | 11 +++++++++++
2 files changed, 13 insertions(+)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RankingMetrics.scala b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RankingMetrics.scala
index b9b54b93c2..5b5a2a1450 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RankingMetrics.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RankingMetrics.scala
@@ -31,6 +31,8 @@ import org.apache.spark.rdd.RDD
* ::Experimental::
* Evaluator for ranking algorithms.
*
+ * Java users should use [[RankingMetrics$.of]] to create a [[RankingMetrics]] instance.
+ *
* @param predictionAndLabels an RDD of (predicted ranking, ground truth set) pairs.
*/
@Experimental
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/pmml/PMMLExportable.scala b/mllib/src/main/scala/org/apache/spark/mllib/pmml/PMMLExportable.scala
index 354e90f3ee..5e882d4ebb 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/pmml/PMMLExportable.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/pmml/PMMLExportable.scala
@@ -23,13 +23,16 @@ import javax.xml.transform.stream.StreamResult
import org.jpmml.model.JAXBUtil
import org.apache.spark.SparkContext
+import org.apache.spark.annotation.{DeveloperApi, Experimental}
import org.apache.spark.mllib.pmml.export.PMMLModelExportFactory
/**
+ * :: DeveloperApi ::
* Export model to the PMML format
* Predictive Model Markup Language (PMML) is an XML-based file format
* developed by the Data Mining Group (www.dmg.org).
*/
+@DeveloperApi
trait PMMLExportable {
/**
@@ -41,30 +44,38 @@ trait PMMLExportable {
}
/**
+ * :: Experimental ::
* Export the model to a local file in PMML format
*/
+ @Experimental
def toPMML(localPath: String): Unit = {
toPMML(new StreamResult(new File(localPath)))
}
/**
+ * :: Experimental ::
* Export the model to a directory on a distributed file system in PMML format
*/
+ @Experimental
def toPMML(sc: SparkContext, path: String): Unit = {
val pmml = toPMML()
sc.parallelize(Array(pmml), 1).saveAsTextFile(path)
}
/**
+ * :: Experimental ::
* Export the model to the OutputStream in PMML format
*/
+ @Experimental
def toPMML(outputStream: OutputStream): Unit = {
toPMML(new StreamResult(outputStream))
}
/**
+ * :: Experimental ::
* Export the model to a String in PMML format
*/
+ @Experimental
def toPMML(): String = {
val writer = new StringWriter
toPMML(new StreamResult(writer))
--
GitLab