Github user yinxusen commented on a diff in the pull request:
https://github.com/apache/spark/pull/11116#discussion_r53395058
--- Diff:
examples/src/main/java/org/apache/spark/examples/mllib/JavaLatentDirichletAllocationExample.java
---
@@ -0,0 +1,87 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.examples.mllib;
+
+// $example on$
+import scala.Tuple2;
+
+import org.apache.spark.api.java.*;
+import org.apache.spark.api.java.function.Function;
+import org.apache.spark.mllib.clustering.LDAModel;
+import org.apache.spark.mllib.clustering.DistributedLDAModel;
+import org.apache.spark.mllib.clustering.LDA;
+import org.apache.spark.mllib.linalg.Matrix;
+import org.apache.spark.mllib.linalg.Vector;
+import org.apache.spark.mllib.linalg.Vectors;
+// $example off$
+
+import org.apache.spark.SparkConf;
+
+public class JavaLatentDirichletAllocationExample {
+ public static void main(String[] args) {
+
+ SparkConf conf = new
SparkConf().setAppName("JavaKLatentDirichletAllocationExample");
+ JavaSparkContext jsc = new JavaSparkContext(conf);
+
+ // $example on$
+ // Load and parse the data
+ String path = "data/mllib/sample_lda_data.txt";
+ JavaRDD<String> data = jsc.textFile(path);
+ JavaRDD<Vector> parsedData = data.map(
+ new Function<String, Vector>() {
+ public Vector call(String s) {
+ String[] sarray = s.trim().split(" ");
+ double[] values = new double[sarray.length];
+ for (int i = 0; i < sarray.length; i++)
+ values[i] = Double.parseDouble(sarray[i]);
+ return Vectors.dense(values);
+ }
+ }
+ );
+ // Index documents with unique IDs
+ JavaPairRDD<Long, Vector> corpus =
JavaPairRDD.fromJavaRDD(parsedData.zipWithIndex().map(
+ new Function<Tuple2<Vector, Long>, Tuple2<Long, Vector>>() {
+ public Tuple2<Long, Vector> call(Tuple2<Vector, Long>
doc_id) {
+ return doc_id.swap();
+ }
+ }
+ ));
+ corpus.cache();
+
+ // Cluster the documents into three topics using LDA
+ LDAModel ldaModel = new LDA().setK(3).run(corpus);
+
+ // Output topics. Each is a distribution over words (matching word
count vectors)
+ System.out.println("Learned topics (as distributions over vocab of " +
ldaModel.vocabSize()
+ + " words):");
+ Matrix topics = ldaModel.topicsMatrix();
+ for (int topic = 0; topic < 3; topic++) {
--- End diff --
Same for the for-block:
```Java
for (int topic = 0; topic < 3; topic++) {
System.out.print("Topic " + topic + ":");
for (int word = 0; word < ldaModel.vocabSize(); word++) {
System.out.print(" " + topics.apply(word, topic));
}
System.out.println();
}
```
---
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
