aboutsummaryrefslogtreecommitdiff
path: root/mllib/src/test/java
diff options
context:
space:
mode:
authorFeynman Liang <fliang@databricks.com>2015-07-29 16:20:20 -0700
committerJoseph K. Bradley <joseph@databricks.com>2015-07-29 16:20:20 -0700
commit2cc212d56a1d50fe68d5816f71b27803de1f6389 (patch)
tree57246612d422ea82e592c4079fe43f16e9bdfb84 /mllib/src/test/java
parent1b0099fc62d02ff6216a76fbfe17a4ec5b2f3536 (diff)
downloadspark-2cc212d56a1d50fe68d5816f71b27803de1f6389.tar.gz
spark-2cc212d56a1d50fe68d5816f71b27803de1f6389.tar.bz2
spark-2cc212d56a1d50fe68d5816f71b27803de1f6389.zip
[SPARK-6793] [MLLIB] OnlineLDAOptimizer LDA perplexity
Implements `logPerplexity` in `OnlineLDAOptimizer`. Also refactors inference code into companion object to enable future reuse (e.g. `predict` method). Author: Feynman Liang <fliang@databricks.com> Closes #7705 from feynmanliang/SPARK-6793-perplexity and squashes the following commits: 6da2c99 [Feynman Liang] Remove get* from LDAModel public API 8381da6 [Feynman Liang] Code review comments 17f7000 [Feynman Liang] Documentation typo fixes 2f452a4 [Feynman Liang] Remove auxillary DistributedLDAModel constructor a275914 [Feynman Liang] Prevent empty counts calls to variationalInference 06d02d9 [Feynman Liang] Remove deprecated LocalLDAModel constructor afecb46 [Feynman Liang] Fix regression bug in sstats accumulator 5a327a0 [Feynman Liang] Code review quick fixes 998c03e [Feynman Liang] Fix style 1cbb67d [Feynman Liang] Fix access modifier bug 4362daa [Feynman Liang] Organize imports 4f171f7 [Feynman Liang] Fix indendation 2f049ce [Feynman Liang] Fix failing save/load tests 7415e96 [Feynman Liang] Pick changes from big PR 11e7c33 [Feynman Liang] Merge remote-tracking branch 'apache/master' into SPARK-6793-perplexity f8adc48 [Feynman Liang] Add logPerplexity, refactor variationalBound into a method cd521d6 [Feynman Liang] Refactor methods into companion class 7f62a55 [Feynman Liang] --amend c62cb1e [Feynman Liang] Outer product for stats, revert Range slicing aead650 [Feynman Liang] Range slice, in-place update, reduce transposes
Diffstat (limited to 'mllib/src/test/java')
-rw-r--r--mllib/src/test/java/org/apache/spark/mllib/clustering/JavaLDASuite.java6
1 files changed, 5 insertions, 1 deletions
diff --git a/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaLDASuite.java b/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaLDASuite.java
index b48f190f59..d272a42c85 100644
--- a/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaLDASuite.java
+++ b/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaLDASuite.java
@@ -19,6 +19,7 @@ package org.apache.spark.mllib.clustering;
import java.io.Serializable;
import java.util.ArrayList;
+import java.util.Arrays;
import scala.Tuple2;
@@ -59,7 +60,10 @@ public class JavaLDASuite implements Serializable {
@Test
public void localLDAModel() {
- LocalLDAModel model = new LocalLDAModel(LDASuite$.MODULE$.tinyTopics());
+ Matrix topics = LDASuite$.MODULE$.tinyTopics();
+ double[] topicConcentration = new double[topics.numRows()];
+ Arrays.fill(topicConcentration, 1.0D / topics.numRows());
+ LocalLDAModel model = new LocalLDAModel(topics, Vectors.dense(topicConcentration), 1D, 100D);
// Check: basic parameters
assertEquals(model.k(), tinyK);