Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/19876#discussion_r156370588
--- Diff: mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala ---
@@ -85,12 +87,55 @@ private[util] sealed trait BaseReadWrite {
protected final def sc: SparkContext = sparkSession.sparkContext
}
+/**
+ * ML export formats for should implement this trait so that users can
specify a shortname rather
+ * than the fully qualified class name of the exporter.
+ *
+ * A new instance of this class will be instantiated each time a DDL call
is made.
+ *
+ * @since 2.3.0
+ */
[email protected]
+trait MLFormatRegister {
+ /**
+ * The string that represents the format that this data source provider
uses. This is
+ * overridden by children to provide a nice alias for the data source.
For example:
+ *
+ * {{{
+ * override def shortName(): String =
+ * "pmml+org.apache.spark.ml.regression.LinearRegressionModel"
+ * }}}
+ * Indicates that this format is capable of saving Spark's own
LinearRegressionModel in pmml.
+ *
+ * Format discovery is done using a ServiceLoader so make sure to list
your format in
+ * META-INF/services.
+ * @since 2.3.0
+ */
+ def shortName(): String
+}
+
+/**
+ * Implemented by objects that provide ML exportability.
+ *
+ * A new instance of this class will be instantiated each time a DDL call
is made.
+ *
+ * @since 2.3.0
+ */
[email protected]
+trait MLWriterFormat {
+ /**
+ * Function write the provided pipeline stage out.
+ */
+ def write(path: String, session: SparkSession, optionMap:
mutable.Map[String, String],
+ stage: PipelineStage)
--- End diff --
return type?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
