Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/4233#discussion_r23910101
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
---
@@ -68,6 +79,65 @@ class LogisticRegressionModel (
case None => score
}
}
+
+ override def save(sc: SparkContext, path: String): Unit = {
+ val sqlContext = new SQLContext(sc)
+ import sqlContext._
+
+ // Create JSON metadata.
+ val metadata = LogisticRegressionModel.Metadata(
+ clazz = this.getClass.getName, version = Exportable.latestVersion)
+ val metadataRDD: DataFrame = sc.parallelize(Seq(metadata))
+ metadataRDD.toJSON.saveAsTextFile(path + "/metadata")
+ // Create Parquet data.
+ val data = LogisticRegressionModel.Data(weights, intercept, threshold)
+ val dataRDD: DataFrame = sc.parallelize(Seq(data))
+ dataRDD.saveAsParquetFile(path + "/data")
+ }
+}
+
+object LogisticRegressionModel extends Importable[LogisticRegressionModel]
{
+
+ private case class Metadata(clazz: String, version: String)
+
+ private case class Data(weights: Vector, intercept: Double, threshold:
Option[Double])
+
+ override def load(sc: SparkContext, path: String):
LogisticRegressionModel = {
+ val sqlContext = new SQLContext(sc)
+ import sqlContext._
+
+ // Load JSON metadata.
+ val metadataRDD = sqlContext.jsonFile(path + "/metadata")
--- End diff --
(I guess these are conflicting since using DataFrame and toJSON will mean 1
record per text file line, but that's OK with me.)
---
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]
