changes from PR
Project: http://git-wip-us.apache.org/repos/asf/incubator-spark/repo Commit: http://git-wip-us.apache.org/repos/asf/incubator-spark/commit/d28bf418 Tree: http://git-wip-us.apache.org/repos/asf/incubator-spark/tree/d28bf418 Diff: http://git-wip-us.apache.org/repos/asf/incubator-spark/diff/d28bf418 Branch: refs/heads/master Commit: d28bf4182758f08862d5838c918756801a9d7327 Parents: 845e568 Author: Reza Zadeh <riz...@gmail.com> Authored: Fri Jan 17 13:39:40 2014 -0800 Committer: Reza Zadeh <riz...@gmail.com> Committed: Fri Jan 17 13:39:40 2014 -0800 ---------------------------------------------------------------------- docs/mllib-guide.md | 5 +- .../org/apache/spark/examples/SparkSVD.scala | 59 -------------------- .../apache/spark/examples/mllib/SparkSVD.scala | 59 ++++++++++++++++++++ 3 files changed, 62 insertions(+), 61 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/incubator-spark/blob/d28bf418/docs/mllib-guide.md ---------------------------------------------------------------------- diff --git a/docs/mllib-guide.md b/docs/mllib-guide.md index a140ecb..26350ce 100644 --- a/docs/mllib-guide.md +++ b/docs/mllib-guide.md @@ -445,11 +445,12 @@ Given an *m x n* matrix *A*, we can compute matrices *U, S, V* such that *A = U * S * V^T* -There is no restriction on m, but we require n^2 doubles to fit in memory. +There is no restriction on m, but we require n^2 doubles to +fit in memory locally on one machine. Further, n should be less than m. The decomposition is computed by first computing *A^TA = V S^2 V^T*, -computing svd locally on that (since n x n is small), +computing SVD locally on that (since n x n is small), from which we recover S and V. Then we compute U via easy matrix multiplication as *U = A * V * S^-1* http://git-wip-us.apache.org/repos/asf/incubator-spark/blob/d28bf418/examples/src/main/scala/org/apache/spark/examples/SparkSVD.scala ---------------------------------------------------------------------- diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkSVD.scala b/examples/src/main/scala/org/apache/spark/examples/SparkSVD.scala deleted file mode 100644 index ce7c1c4..0000000 --- a/examples/src/main/scala/org/apache/spark/examples/SparkSVD.scala +++ /dev/null @@ -1,59 +0,0 @@ -/* - * 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 - -import org.apache.spark.SparkContext -import org.apache.spark.mllib.linalg.SVD -import org.apache.spark.mllib.linalg.MatrixEntry -import org.apache.spark.mllib.linalg.SparseMatrix - -/** - * Compute SVD of an example matrix - * Input file should be comma separated, 1 indexed of the form - * i,j,value - * Where i is the column, j the row, and value is the matrix entry - * - * For example input file, see: - * mllib/data/als/test.data (example is 4 x 4) - */ -object SparkSVD { - def main(args: Array[String]) { - if (args.length != 4) { - System.err.println("Usage: SparkSVD <master> <file> m n") - System.exit(1) - } - val sc = new SparkContext(args(0), "SVD", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) - - // Load and parse the data file - val data = sc.textFile(args(1)).map { line => - val parts = line.split(',') - MatrixEntry(parts(0).toInt, parts(1).toInt, parts(2).toDouble) - } - val m = args(2).toInt - val n = args(3).toInt - - // recover largest singular vector - val decomposed = SVD.sparseSVD(SparseMatrix(data, m, n), 1) - val u = decomposed.U.data - val s = decomposed.S.data - val v = decomposed.V.data - - println("singular values = " + s.toArray.mkString) - } -} http://git-wip-us.apache.org/repos/asf/incubator-spark/blob/d28bf418/examples/src/main/scala/org/apache/spark/examples/mllib/SparkSVD.scala ---------------------------------------------------------------------- diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/SparkSVD.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/SparkSVD.scala new file mode 100644 index 0000000..50e5f5b --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/SparkSVD.scala @@ -0,0 +1,59 @@ +/* + * 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 org.apache.spark.SparkContext +import org.apache.spark.mllib.linalg.SVD +import org.apache.spark.mllib.linalg.MatrixEntry +import org.apache.spark.mllib.linalg.SparseMatrix + +/** + * Compute SVD of an example matrix + * Input file should be comma separated, 1 indexed of the form + * i,j,value + * Where i is the column, j the row, and value is the matrix entry + * + * For example input file, see: + * mllib/data/als/test.data (example is 4 x 4) + */ +object SparkSVD { + def main(args: Array[String]) { + if (args.length != 4) { + System.err.println("Usage: SparkSVD <master> <file> m n") + System.exit(1) + } + val sc = new SparkContext(args(0), "SVD", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + + // Load and parse the data file + val data = sc.textFile(args(1)).map { line => + val parts = line.split(',') + MatrixEntry(parts(0).toInt, parts(1).toInt, parts(2).toDouble) + } + val m = args(2).toInt + val n = args(3).toInt + + // recover largest singular vector + val decomposed = SVD.sparseSVD(SparseMatrix(data, m, n), 1) + val u = decomposed.U.data + val s = decomposed.S.data + val v = decomposed.V.data + + println("singular values = " + s.toArray.mkString) + } +}
