diff options
author | MechCoder <manojkumarsivaraj334@gmail.com> | 2015-02-10 14:05:55 -0800 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-02-10 14:05:55 -0800 |
commit | fd2c032f95bbee342ca539df9e44927482981659 (patch) | |
tree | d62c6a533c9ae2d06c8d8888d5197f481955969f /mllib/src/test | |
parent | f98707c043f1be9569ec774796edb783132773a8 (diff) | |
download | spark-fd2c032f95bbee342ca539df9e44927482981659.tar.gz spark-fd2c032f95bbee342ca539df9e44927482981659.tar.bz2 spark-fd2c032f95bbee342ca539df9e44927482981659.zip |
[SPARK-5021] [MLlib] Gaussian Mixture now supports Sparse Input
Following discussion in the Jira.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes #4459 from MechCoder/sparse_gmm and squashes the following commits:
1b18dab [MechCoder] Rewrite syr for sparse matrices
e579041 [MechCoder] Add test for covariance matrix
5cb370b [MechCoder] Separate tests for sparse data
5e096bd [MechCoder] Alphabetize and correct error message
e180f4c [MechCoder] [SPARK-5021] Gaussian Mixture now supports Sparse Input
Diffstat (limited to 'mllib/src/test')
-rw-r--r-- | mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala | 66 | ||||
-rw-r--r-- | mllib/src/test/scala/org/apache/spark/mllib/linalg/BLASSuite.scala | 8 |
2 files changed, 70 insertions, 4 deletions
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala index c2cd56ea40..1b46a4012d 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala @@ -31,7 +31,7 @@ class GaussianMixtureSuite extends FunSuite with MLlibTestSparkContext { Vectors.dense(5.0, 10.0), Vectors.dense(4.0, 11.0) )) - + // expectations val Ew = 1.0 val Emu = Vectors.dense(5.0, 10.0) @@ -44,6 +44,7 @@ class GaussianMixtureSuite extends FunSuite with MLlibTestSparkContext { assert(gmm.gaussians(0).mu ~== Emu absTol 1E-5) assert(gmm.gaussians(0).sigma ~== Esigma absTol 1E-5) } + } test("two clusters") { @@ -54,7 +55,7 @@ class GaussianMixtureSuite extends FunSuite with MLlibTestSparkContext { Vectors.dense( 5.7048), Vectors.dense( 4.6567), Vectors.dense( 5.5026), Vectors.dense( 4.5605), Vectors.dense( 5.2043), Vectors.dense( 6.2734) )) - + // we set an initial gaussian to induce expected results val initialGmm = new GaussianMixtureModel( Array(0.5, 0.5), @@ -63,7 +64,7 @@ class GaussianMixtureSuite extends FunSuite with MLlibTestSparkContext { new MultivariateGaussian(Vectors.dense(1.0), Matrices.dense(1, 1, Array(1.0))) ) ) - + val Ew = Array(1.0 / 3.0, 2.0 / 3.0) val Emu = Array(Vectors.dense(-4.3673), Vectors.dense(5.1604)) val Esigma = Array(Matrices.dense(1, 1, Array(1.1098)), Matrices.dense(1, 1, Array(0.86644))) @@ -72,7 +73,7 @@ class GaussianMixtureSuite extends FunSuite with MLlibTestSparkContext { .setK(2) .setInitialModel(initialGmm) .run(data) - + assert(gmm.weights(0) ~== Ew(0) absTol 1E-3) assert(gmm.weights(1) ~== Ew(1) absTol 1E-3) assert(gmm.gaussians(0).mu ~== Emu(0) absTol 1E-3) @@ -80,4 +81,61 @@ class GaussianMixtureSuite extends FunSuite with MLlibTestSparkContext { assert(gmm.gaussians(0).sigma ~== Esigma(0) absTol 1E-3) assert(gmm.gaussians(1).sigma ~== Esigma(1) absTol 1E-3) } + + test("single cluster with sparse data") { + val data = sc.parallelize(Array( + Vectors.sparse(3, Array(0, 2), Array(4.0, 2.0)), + Vectors.sparse(3, Array(0, 2), Array(2.0, 4.0)), + Vectors.sparse(3, Array(1), Array(6.0)) + )) + + val Ew = 1.0 + val Emu = Vectors.dense(2.0, 2.0, 2.0) + val Esigma = Matrices.dense(3, 3, + Array(8.0 / 3.0, -4.0, 4.0 / 3.0, -4.0, 8.0, -4.0, 4.0 / 3.0, -4.0, 8.0 / 3.0) + ) + + val seeds = Array(42, 1994, 27, 11, 0) + seeds.foreach { seed => + val gmm = new GaussianMixture().setK(1).setSeed(seed).run(data) + assert(gmm.weights(0) ~== Ew absTol 1E-5) + assert(gmm.gaussians(0).mu ~== Emu absTol 1E-5) + assert(gmm.gaussians(0).sigma ~== Esigma absTol 1E-5) + } + } + + test("two clusters with sparse data") { + val data = sc.parallelize(Array( + Vectors.dense(-5.1971), Vectors.dense(-2.5359), Vectors.dense(-3.8220), + Vectors.dense(-5.2211), Vectors.dense(-5.0602), Vectors.dense( 4.7118), + Vectors.dense( 6.8989), Vectors.dense( 3.4592), Vectors.dense( 4.6322), + Vectors.dense( 5.7048), Vectors.dense( 4.6567), Vectors.dense( 5.5026), + Vectors.dense( 4.5605), Vectors.dense( 5.2043), Vectors.dense( 6.2734) + )) + + val sparseData = data.map(point => Vectors.sparse(1, Array(0), point.toArray)) + // we set an initial gaussian to induce expected results + val initialGmm = new GaussianMixtureModel( + Array(0.5, 0.5), + Array( + new MultivariateGaussian(Vectors.dense(-1.0), Matrices.dense(1, 1, Array(1.0))), + new MultivariateGaussian(Vectors.dense(1.0), Matrices.dense(1, 1, Array(1.0))) + ) + ) + val Ew = Array(1.0 / 3.0, 2.0 / 3.0) + val Emu = Array(Vectors.dense(-4.3673), Vectors.dense(5.1604)) + val Esigma = Array(Matrices.dense(1, 1, Array(1.1098)), Matrices.dense(1, 1, Array(0.86644))) + + val sparseGMM = new GaussianMixture() + .setK(2) + .setInitialModel(initialGmm) + .run(data) + + assert(sparseGMM.weights(0) ~== Ew(0) absTol 1E-3) + assert(sparseGMM.weights(1) ~== Ew(1) absTol 1E-3) + assert(sparseGMM.gaussians(0).mu ~== Emu(0) absTol 1E-3) + assert(sparseGMM.gaussians(1).mu ~== Emu(1) absTol 1E-3) + assert(sparseGMM.gaussians(0).sigma ~== Esigma(0) absTol 1E-3) + assert(sparseGMM.gaussians(1).sigma ~== Esigma(1) absTol 1E-3) + } } diff --git a/mllib/src/test/scala/org/apache/spark/mllib/linalg/BLASSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/linalg/BLASSuite.scala index b0b78acd6d..002cb25386 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/linalg/BLASSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/linalg/BLASSuite.scala @@ -166,6 +166,14 @@ class BLASSuite extends FunSuite { syr(alpha, y, dA) } } + + val xSparse = new SparseVector(4, Array(0, 2, 3), Array(1.0, 3.0, 4.0)) + val dD = new DenseMatrix(4, 4, + Array(0.0, 1.2, 2.2, 3.1, 1.2, 3.2, 5.3, 4.6, 2.2, 5.3, 1.8, 3.0, 3.1, 4.6, 3.0, 0.8)) + syr(0.1, xSparse, dD) + val expectedSparse = new DenseMatrix(4, 4, + Array(0.1, 1.2, 2.5, 3.5, 1.2, 3.2, 5.3, 4.6, 2.5, 5.3, 2.7, 4.2, 3.5, 4.6, 4.2, 2.4)) + assert(dD ~== expectedSparse absTol 1e-15) } test("gemm") { |