Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/4233#discussion_r24054690
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala ---
@@ -65,6 +67,70 @@ class NaiveBayesModel private[mllib] (
override def predict(testData: Vector): Double = {
labels(brzArgmax(brzPi + brzTheta * testData.toBreeze))
}
+
+ override def save(sc: SparkContext, path: String): Unit = {
+ val sqlContext = new SQLContext(sc)
+ import sqlContext._
+
+ // Create JSON metadata.
+ val metadataRDD =
+ sc.parallelize(Seq((this.getClass.getName,
formatVersion))).toDataFrame("class", "version")
+ metadataRDD.toJSON.repartition(1).saveAsTextFile(path + "/metadata")
+
+ // Create Parquet data.
+ val data = NaiveBayesModel.Data(labels, pi, theta)
+ val dataRDD: DataFrame = sc.parallelize(Seq(data))
+ dataRDD.repartition(1).saveAsParquetFile(path + "/data")
+ }
+
+ override protected def formatVersion: String =
NaiveBayesModel.formatVersion
+
+}
+
+object NaiveBayesModel extends Importable[NaiveBayesModel] {
+
+ /** Model data for model import/export */
+ private case class Data(labels: Array[Double], pi: Array[Double], theta:
Array[Array[Double]])
--- End diff --
Good point
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
