examples/mllib/JavaSVDExample.java

0001 /*
0002  * Licensed to the Apache Software Foundation (ASF) under one or more
0003  * contributor license agreements.  See the NOTICE file distributed with
0004  * this work for additional information regarding copyright ownership.
0005  * The ASF licenses this file to You under the Apache License, Version 2.0
0006  * (the "License"); you may not use this file except in compliance with
0007  * the License.  You may obtain a copy of the License at
0008  *
0009  *    http://www.apache.org/licenses/LICENSE-2.0
0010  *
0011  * Unless required by applicable law or agreed to in writing, software
0012  * distributed under the License is distributed on an "AS IS" BASIS,
0013  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014  * See the License for the specific language governing permissions and
0015  * limitations under the License.
0016  */
0017
0018 package org.apache.spark.examples.mllib;
0019
0020 // $example on$
0021 import java.util.Arrays;
0022 import java.util.List;
0023 // $example off$
0024
0025 import org.apache.spark.SparkConf;
0026 import org.apache.spark.SparkContext;
0027 // $example on$
0028 import org.apache.spark.api.java.JavaRDD;
0029 import org.apache.spark.api.java.JavaSparkContext;
0030 import org.apache.spark.mllib.linalg.Matrix;
0031 import org.apache.spark.mllib.linalg.SingularValueDecomposition;
0032 import org.apache.spark.mllib.linalg.Vector;
0033 import org.apache.spark.mllib.linalg.Vectors;
0034 import org.apache.spark.mllib.linalg.distributed.RowMatrix;
0035 // $example off$
0036
0037 /**
0038  * Example for SingularValueDecomposition.
0039  */
0040 public class JavaSVDExample {
0041   public static void main(String[] args) {
0042     SparkConf conf = new SparkConf().setAppName("SVD Example");
0043     SparkContext sc = new SparkContext(conf);
0044     JavaSparkContext jsc = JavaSparkContext.fromSparkContext(sc);
0045
0046     // $example on$
0047     List<Vector> data = Arrays.asList(
0048             Vectors.sparse(5, new int[] {1, 3}, new double[] {1.0, 7.0}),
0049             Vectors.dense(2.0, 0.0, 3.0, 4.0, 5.0),
0050             Vectors.dense(4.0, 0.0, 0.0, 6.0, 7.0)
0051     );
0052
0053     JavaRDD<Vector> rows = jsc.parallelize(data);
0054
0055     // Create a RowMatrix from JavaRDD<Vector>.
0056     RowMatrix mat = new RowMatrix(rows.rdd());
0057
0058     // Compute the top 5 singular values and corresponding singular vectors.
0059     SingularValueDecomposition<RowMatrix, Matrix> svd = mat.computeSVD(5, true, 1.0E-9d);
0060     RowMatrix U = svd.U();  // The U factor is a RowMatrix.
0061     Vector s = svd.s();     // The singular values are stored in a local dense vector.
0062     Matrix V = svd.V();     // The V factor is a local dense matrix.
0063     // $example off$
0064     Vector[] collectPartitions = (Vector[]) U.rows().collect();
0065     System.out.println("U factor is:");
0066     for (Vector vector : collectPartitions) {
0067       System.out.println("\t" + vector);
0068     }
0069     System.out.println("Singular values are: " + s);
0070     System.out.println("V factor is:\n" + V);
0071
0072     jsc.stop();
0073   }
0074 }