diff options
Diffstat (limited to 'examples')
-rw-r--r-- | examples/src/main/java/org/apache/spark/examples/mllib/JavaLDAExample.java | 75 |
1 files changed, 75 insertions, 0 deletions
diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaLDAExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaLDAExample.java new file mode 100644 index 0000000000..f394ff2084 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaLDAExample.java @@ -0,0 +1,75 @@ +/* + * 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; + +import scala.Tuple2; + +import org.apache.spark.api.java.*; +import org.apache.spark.api.java.function.Function; +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; +import org.apache.spark.SparkConf; + +public class JavaLDAExample { + public static void main(String[] args) { + SparkConf conf = new SparkConf().setAppName("LDA Example"); + JavaSparkContext sc = new JavaSparkContext(conf); + + // Load and parse the data + String path = "data/mllib/sample_lda_data.txt"; + JavaRDD<String> data = sc.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 + DistributedLDAModel 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++) { + System.out.print("Topic " + topic + ":"); + for (int word = 0; word < ldaModel.vocabSize(); word++) { + System.out.print(" " + topics.apply(word, topic)); + } + System.out.println(); + } + } +} |