Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/7307#discussion_r35056040
--- Diff:
mllib/src/test/scala/org/apache/spark/mllib/clustering/LDASuite.scala ---
@@ -217,6 +233,56 @@ class LDASuite extends SparkFunSuite with
MLlibTestSparkContext {
}
}
+ test("OnlineLDAOptimizer with asymmetric prior") {
+ def toydata: Array[(Long, Vector)] = Array(
+ Vectors.sparse(6, Array(0, 1), Array(1, 1)),
+ Vectors.sparse(6, Array(1, 2), Array(1, 1)),
+ Vectors.sparse(6, Array(0, 2), Array(1, 1)),
+ Vectors.sparse(6, Array(3, 4), Array(1, 1)),
+ Vectors.sparse(6, Array(3, 5), Array(1, 1)),
+ Vectors.sparse(6, Array(4, 5), Array(1, 1))
+ ).zipWithIndex.map { case (wordCounts, docId) => (docId.toLong,
wordCounts) }
+
+ val docs = sc.parallelize(toydata)
+ val op = new
OnlineLDAOptimizer().setMiniBatchFraction(1).setTau0(1024).setKappa(0.51)
+ .setGammaShape(1e10)
+ val lda = new LDA().setK(2)
+ .setDocConcentration(Vectors.dense(0.00001, 0.1))
+ .setTopicConcentration(0.01)
+ .setMaxIterations(100)
+ .setOptimizer(op)
+ .setSeed(12345)
+
+ val ldaModel = lda.run(docs)
+ val topicIndices = ldaModel.describeTopics(maxTermsPerTopic = 10)
+ val topics = topicIndices.map { case (terms, termWeights) =>
+ terms.zip(termWeights)
+ }
+
+ /* Verify results with Python:
--- End diff --
Nice
---
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]
