Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/6791#discussion_r33086363
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala ---
@@ -465,6 +465,39 @@ private[python] class PythonMLLibAPI extends
Serializable {
}
/**
+ * Java stub for Python mllib LDA.run()
+ */
+ def trainLDAModel(
+ data: JavaRDD[java.util.List[Any]],
+ k: Int,
+ maxIterations: Int,
+ docConcentration: Double,
+ topicConcentration: Double,
+ seed: java.lang.Long,
+ checkpointInterval: Int,
+ optimizer: String): LDAModel = {
+ val algo = new LDA()
+ .setK(k)
+ .setMaxIterations(maxIterations)
+ .setDocConcentration(docConcentration)
+ .setTopicConcentration(topicConcentration)
+ .setCheckpointInterval(checkpointInterval)
+ .setOptimizer(optimizer)
+
+ if (seed != null) algo.setSeed(seed)
+
+ val documents = data.rdd.map(_.asScala.toArray).map { r =>
+ r(0).getClass.getSimpleName match {
--- End diff --
r(0) match {
case i: java.lang.Integer => i.toLong
case l: java.lang.Long => l
}
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
