init

init

init

init

init

init

init

init

init

init

init

use nativeBLAS for dense input

add py

refactor

refactor

refactor

nit

revert BLAS.ger

revert BLAS.ger

revert BLAS.ger

nit

nit

simplify

Author: zhengruifeng

mllib-local/src/main/scala/org/apache/spark/ml/linalg/BLAS.scala

@@ -271,7 +271,7 @@ private[spark] object BLAS extends Serializable {
   }
 
   /**
-   * Adds alpha * x * x.t to a matrix in-place. This is the same as BLAS's ?SPR.
+   * Adds alpha * v * v.t to a matrix in-place. This is the same as BLAS's ?SPR.
    *
    * @param U the upper triangular part of the matrix packed in an array (column major)
    */

mllib-local/src/main/scala/org/apache/spark/ml/stat/distribution/MultivariateGaussian.scala

@@ -55,7 +55,7 @@ class MultivariateGaussian @Since("2.0.0") (
    */
   @transient private lazy val tuple = {
     val (rootSigmaInv, u) = calculateCovarianceConstants
-    val rootSigmaInvMat = Matrices.fromBreeze(rootSigmaInv)
+    val rootSigmaInvMat = Matrices.fromBreeze(rootSigmaInv).toDense
     val rootSigmaInvMulMu = rootSigmaInvMat.multiply(mean)
     (rootSigmaInvMat, u, rootSigmaInvMulMu)
   }
@@ -81,6 +81,43 @@ class MultivariateGaussian @Since("2.0.0") (
     u - 0.5 * BLAS.dot(v, v)
   }
 
+  private[ml] def pdf(X: Matrix): Vector = {
+    val m = X.numRows
+    val n = X.numCols
+    val mat = new DenseMatrix(m, n, Array.ofDim[Double](m * n))
+    pdf(X, mat)
+  }
+
+  private[ml] def pdf(X: Matrix, mat: DenseMatrix): Vector = {
+    require(!mat.isTransposed)
+    val localU = u
+    val localRootSigmaInvMat = rootSigmaInvMat
+    val localRootSigmaInvMulMu = rootSigmaInvMulMu.toArray
+
+    BLAS.gemm(1.0, X, localRootSigmaInvMat.transpose, 0.0, mat)
+    val arr = mat.values
+    val m = mat.numRows
+    val n = mat.numCols
+
+    val pdfArr = Array.ofDim[Double](m)
+    var i = 0
+    while (i < m) {
+      var squaredSum = 0.0
+      var index = i
+      var j = 0
+      while (j < n) {
+        val d = arr(index) - localRootSigmaInvMulMu(j)
+        squaredSum += d * d
+        index += m
+        j += 1
+      }
+      pdfArr(i) = math.exp(localU - 0.5 * squaredSum)
+      i += 1
+    }
+
+    Vectors.dense(pdfArr)
+  }
+
   /**
    * Calculate distribution dependent components used for the density function:
    *    pdf(x) = (2*pi)^(-k/2)^ * det(sigma)^(-1/2)^ * exp((-1/2) * (x-mu).t * inv(sigma) * (x-mu))

mllib-local/src/test/scala/org/apache/spark/ml/stat/distribution/MultivariateGaussianSuite.scala

@@ -27,6 +27,7 @@ class MultivariateGaussianSuite extends SparkMLFunSuite {
   test("univariate") {
     val x1 = Vectors.dense(0.0)
     val x2 = Vectors.dense(1.5)
+    val mat = Matrices.fromVectors(Seq(x1, x2))
 
     val mu = Vectors.dense(0.0)
     val sigma1 = Matrices.dense(1, 1, Array(1.0))
@@ -35,18 +36,21 @@ class MultivariateGaussianSuite extends SparkMLFunSuite {
     assert(dist1.logpdf(x2) ~== -2.0439385332046727 absTol 1E-5)
     assert(dist1.pdf(x1) ~== 0.39894 absTol 1E-5)
     assert(dist1.pdf(x2) ~== 0.12952 absTol 1E-5)
+    assert(dist1.pdf(mat) ~== Vectors.dense(0.39894, 0.12952) absTol 1E-5)
 
     val sigma2 = Matrices.dense(1, 1, Array(4.0))
     val dist2 = new MultivariateGaussian(mu, sigma2)
     assert(dist2.logpdf(x1) ~== -1.612085713764618 absTol 1E-5)
     assert(dist2.logpdf(x2) ~== -1.893335713764618 absTol 1E-5)
     assert(dist2.pdf(x1) ~== 0.19947 absTol 1E-5)
     assert(dist2.pdf(x2) ~== 0.15057 absTol 1E-5)
+    assert(dist2.pdf(mat) ~== Vectors.dense(0.19947, 0.15057) absTol 1E-5)
   }
 
   test("multivariate") {
     val x1 = Vectors.dense(0.0, 0.0)
     val x2 = Vectors.dense(1.0, 1.0)
+    val mat = Matrices.fromVectors(Seq(x1, x2))
 
     val mu = Vectors.dense(0.0, 0.0)
     val sigma1 = Matrices.dense(2, 2, Array(1.0, 0.0, 0.0, 1.0))
@@ -55,28 +59,33 @@ class MultivariateGaussianSuite extends SparkMLFunSuite {
     assert(dist1.logpdf(x2) ~== -2.8378770664093453 absTol 1E-5)
     assert(dist1.pdf(x1) ~== 0.15915 absTol 1E-5)
     assert(dist1.pdf(x2) ~== 0.05855 absTol 1E-5)
+    assert(dist1.pdf(mat) ~== Vectors.dense(0.15915, 0.05855) absTol 1E-5)
 
     val sigma2 = Matrices.dense(2, 2, Array(4.0, -1.0, -1.0, 2.0))
     val dist2 = new MultivariateGaussian(mu, sigma2)
     assert(dist2.logpdf(x1) ~== -2.810832140937002 absTol 1E-5)
     assert(dist2.logpdf(x2) ~== -3.3822607123655732 absTol 1E-5)
     assert(dist2.pdf(x1) ~== 0.060155 absTol 1E-5)
     assert(dist2.pdf(x2) ~== 0.033971 absTol 1E-5)
+    assert(dist2.pdf(mat) ~== Vectors.dense(0.060155, 0.033971) absTol 1E-5)
   }
 
   test("multivariate degenerate") {
     val x1 = Vectors.dense(0.0, 0.0)
     val x2 = Vectors.dense(1.0, 1.0)
+    val mat = Matrices.fromVectors(Seq(x1, x2))
 
     val mu = Vectors.dense(0.0, 0.0)
     val sigma = Matrices.dense(2, 2, Array(1.0, 1.0, 1.0, 1.0))
     val dist = new MultivariateGaussian(mu, sigma)
     assert(dist.pdf(x1) ~== 0.11254 absTol 1E-5)
     assert(dist.pdf(x2) ~== 0.068259 absTol 1E-5)
+    assert(dist.pdf(mat) ~== Vectors.dense(0.11254, 0.068259) absTol 1E-5)
   }
 
   test("SPARK-11302") {
     val x = Vectors.dense(629, 640, 1.7188, 618.19)
+    val mat = Matrices.fromVectors(Seq(x))
     val mu = Vectors.dense(
       1055.3910505836575, 1070.489299610895, 1.39020554474708, 1040.5907503867697)
     val sigma = Matrices.dense(4, 4, Array(
@@ -87,5 +96,6 @@ class MultivariateGaussianSuite extends SparkMLFunSuite {
     val dist = new MultivariateGaussian(mu, sigma)
     // Agrees with R's dmvnorm: 7.154782e-05
     assert(dist.pdf(x) ~== 7.154782224045512E-5 absTol 1E-9)
+    assert(dist.pdf(mat) ~== Vectors.dense(7.154782224045512E-5) absTol 1E-5)
   }
 }