aboutsummaryrefslogtreecommitdiff
path: root/mllib-local
diff options
context:
space:
mode:
authorDB Tsai <dbt@netflix.com>2016-05-27 14:02:39 -0700
committerJoseph K. Bradley <joseph@databricks.com>2016-05-27 14:02:39 -0700
commit21b2605dc4900894ea7a911e039781ecc2a18c14 (patch)
tree033e2083e4db2951acb9a76d14a0b530ad412f69 /mllib-local
parent130b8d07b8eb08f2ad522081a95032b90247094d (diff)
downloadspark-21b2605dc4900894ea7a911e039781ecc2a18c14.tar.gz
spark-21b2605dc4900894ea7a911e039781ecc2a18c14.tar.bz2
spark-21b2605dc4900894ea7a911e039781ecc2a18c14.zip
[SPARK-15413][ML][MLLIB] Change `toBreeze` to `asBreeze` in Vector and Matrix
## What changes were proposed in this pull request? We're using `asML` to convert the mllib vector/matrix to ml vector/matrix now. Using `as` is more correct given that this conversion actually shares the same underline data structure. As a result, in this PR, `toBreeze` will be changed to `asBreeze`. This is a private API, as a result, it will not affect any user's application. ## How was this patch tested? unit tests Author: DB Tsai <dbt@netflix.com> Closes #13198 from dbtsai/minor.
Diffstat (limited to 'mllib-local')
-rw-r--r--mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala16
-rw-r--r--mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala8
-rw-r--r--mllib-local/src/main/scala/org/apache/spark/ml/stat/distribution/MultivariateGaussian.scala8
-rw-r--r--mllib-local/src/test/scala/org/apache/spark/ml/linalg/BreezeMatrixConversionSuite.scala4
-rw-r--r--mllib-local/src/test/scala/org/apache/spark/ml/linalg/BreezeVectorConversionSuite.scala4
-rw-r--r--mllib-local/src/test/scala/org/apache/spark/ml/linalg/MatricesSuite.scala14
-rw-r--r--mllib-local/src/test/scala/org/apache/spark/ml/linalg/VectorsSuite.scala2
7 files changed, 28 insertions, 28 deletions
diff --git a/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala b/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala
index a47526d36f..0ea687bbcc 100644
--- a/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala
+++ b/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala
@@ -69,7 +69,7 @@ sealed trait Matrix extends Serializable {
def rowIter: Iterator[Vector] = this.transpose.colIter
/** Converts to a breeze matrix. */
- private[ml] def toBreeze: BM[Double]
+ private[ml] def asBreeze: BM[Double]
/** Gets the (i, j)-th element. */
@Since("2.0.0")
@@ -112,11 +112,11 @@ sealed trait Matrix extends Serializable {
}
/** A human readable representation of the matrix */
- override def toString: String = toBreeze.toString()
+ override def toString: String = asBreeze.toString()
/** A human readable representation of the matrix with maximum lines and width */
@Since("2.0.0")
- def toString(maxLines: Int, maxLineWidth: Int): String = toBreeze.toString(maxLines, maxLineWidth)
+ def toString(maxLines: Int, maxLineWidth: Int): String = asBreeze.toString(maxLines, maxLineWidth)
/**
* Map the values of this matrix using a function. Generates a new matrix. Performs the
@@ -202,7 +202,7 @@ class DenseMatrix @Since("2.0.0") (
this(numRows, numCols, values, false)
override def equals(o: Any): Boolean = o match {
- case m: Matrix => toBreeze == m.toBreeze
+ case m: Matrix => asBreeze == m.asBreeze
case _ => false
}
@@ -210,7 +210,7 @@ class DenseMatrix @Since("2.0.0") (
Seq(numRows, numCols, toArray).##
}
- private[ml] def toBreeze: BM[Double] = {
+ private[ml] def asBreeze: BM[Double] = {
if (!isTransposed) {
new BDM[Double](numRows, numCols, values)
} else {
@@ -488,14 +488,14 @@ class SparseMatrix @Since("2.0.0") (
rowIndices: Array[Int],
values: Array[Double]) = this(numRows, numCols, colPtrs, rowIndices, values, false)
- override def hashCode(): Int = toBreeze.hashCode()
+ override def hashCode(): Int = asBreeze.hashCode()
override def equals(o: Any): Boolean = o match {
- case m: Matrix => toBreeze == m.toBreeze
+ case m: Matrix => asBreeze == m.asBreeze
case _ => false
}
- private[ml] def toBreeze: BM[Double] = {
+ private[ml] def asBreeze: BM[Double] = {
if (!isTransposed) {
new BSM[Double](values, numRows, numCols, colPtrs, rowIndices)
} else {
diff --git a/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala b/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala
index 59f9c2adba..909fec1c06 100644
--- a/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala
+++ b/mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala
@@ -92,14 +92,14 @@ sealed trait Vector extends Serializable {
/**
* Converts the instance to a breeze vector.
*/
- private[spark] def toBreeze: BV[Double]
+ private[spark] def asBreeze: BV[Double]
/**
* Gets the value of the ith element.
* @param i index
*/
@Since("2.0.0")
- def apply(i: Int): Double = toBreeze(i)
+ def apply(i: Int): Double = asBreeze(i)
/**
* Makes a deep copy of this vector.
@@ -453,7 +453,7 @@ class DenseVector @Since("2.0.0") ( @Since("2.0.0") val values: Array[Double]) e
override def toArray: Array[Double] = values
- private[spark] override def toBreeze: BV[Double] = new BDV[Double](values)
+ private[spark] override def asBreeze: BV[Double] = new BDV[Double](values)
override def apply(i: Int): Double = values(i)
@@ -584,7 +584,7 @@ class SparseVector @Since("2.0.0") (
new SparseVector(size, indices.clone(), values.clone())
}
- private[spark] override def toBreeze: BV[Double] = new BSV[Double](indices, values, size)
+ private[spark] override def asBreeze: BV[Double] = new BSV[Double](indices, values, size)
override def foreachActive(f: (Int, Double) => Unit): Unit = {
var i = 0
diff --git a/mllib-local/src/main/scala/org/apache/spark/ml/stat/distribution/MultivariateGaussian.scala b/mllib-local/src/main/scala/org/apache/spark/ml/stat/distribution/MultivariateGaussian.scala
index 383d6d96e8..0be28677ef 100644
--- a/mllib-local/src/main/scala/org/apache/spark/ml/stat/distribution/MultivariateGaussian.scala
+++ b/mllib-local/src/main/scala/org/apache/spark/ml/stat/distribution/MultivariateGaussian.scala
@@ -47,7 +47,7 @@ class MultivariateGaussian @Since("2.0.0") (
this(Vectors.fromBreeze(mean), Matrices.fromBreeze(cov))
}
- private val breezeMu = mean.toBreeze.toDenseVector
+ private val breezeMu = mean.asBreeze.toDenseVector
/**
* Compute distribution dependent constants:
@@ -61,7 +61,7 @@ class MultivariateGaussian @Since("2.0.0") (
*/
@Since("2.0.0")
def pdf(x: Vector): Double = {
- pdf(x.toBreeze)
+ pdf(x.asBreeze)
}
/**
@@ -69,7 +69,7 @@ class MultivariateGaussian @Since("2.0.0") (
*/
@Since("2.0.0")
def logpdf(x: Vector): Double = {
- logpdf(x.toBreeze)
+ logpdf(x.asBreeze)
}
/** Returns density of this multivariate Gaussian at given point, x */
@@ -113,7 +113,7 @@ class MultivariateGaussian @Since("2.0.0") (
* relation to the maximum singular value (same tolerance used by, e.g., Octave).
*/
private def calculateCovarianceConstants: (BDM[Double], Double) = {
- val eigSym.EigSym(d, u) = eigSym(cov.toBreeze.toDenseMatrix) // sigma = u * diag(d) * u.t
+ val eigSym.EigSym(d, u) = eigSym(cov.asBreeze.toDenseMatrix) // sigma = u * diag(d) * u.t
// For numerical stability, values are considered to be non-zero only if they exceed tol.
// This prevents any inverted value from exceeding (eps * n * max(d))^-1
diff --git a/mllib-local/src/test/scala/org/apache/spark/ml/linalg/BreezeMatrixConversionSuite.scala b/mllib-local/src/test/scala/org/apache/spark/ml/linalg/BreezeMatrixConversionSuite.scala
index 70a21e41bf..f07ed20cf0 100644
--- a/mllib-local/src/test/scala/org/apache/spark/ml/linalg/BreezeMatrixConversionSuite.scala
+++ b/mllib-local/src/test/scala/org/apache/spark/ml/linalg/BreezeMatrixConversionSuite.scala
@@ -24,7 +24,7 @@ import org.apache.spark.ml.SparkMLFunSuite
class BreezeMatrixConversionSuite extends SparkMLFunSuite {
test("dense matrix to breeze") {
val mat = Matrices.dense(3, 2, Array(0.0, 1.0, 2.0, 3.0, 4.0, 5.0))
- val breeze = mat.toBreeze.asInstanceOf[BDM[Double]]
+ val breeze = mat.asBreeze.asInstanceOf[BDM[Double]]
assert(breeze.rows === mat.numRows)
assert(breeze.cols === mat.numCols)
assert(breeze.data.eq(mat.asInstanceOf[DenseMatrix].values), "should not copy data")
@@ -48,7 +48,7 @@ class BreezeMatrixConversionSuite extends SparkMLFunSuite {
val colPtrs = Array(0, 2, 4)
val rowIndices = Array(1, 2, 1, 2)
val mat = Matrices.sparse(3, 2, colPtrs, rowIndices, values)
- val breeze = mat.toBreeze.asInstanceOf[BSM[Double]]
+ val breeze = mat.asBreeze.asInstanceOf[BSM[Double]]
assert(breeze.rows === mat.numRows)
assert(breeze.cols === mat.numCols)
assert(breeze.data.eq(mat.asInstanceOf[SparseMatrix].values), "should not copy data")
diff --git a/mllib-local/src/test/scala/org/apache/spark/ml/linalg/BreezeVectorConversionSuite.scala b/mllib-local/src/test/scala/org/apache/spark/ml/linalg/BreezeVectorConversionSuite.scala
index 00c9ee79eb..4c9740b6bc 100644
--- a/mllib-local/src/test/scala/org/apache/spark/ml/linalg/BreezeVectorConversionSuite.scala
+++ b/mllib-local/src/test/scala/org/apache/spark/ml/linalg/BreezeVectorConversionSuite.scala
@@ -33,12 +33,12 @@ class BreezeVectorConversionSuite extends SparkMLFunSuite {
test("dense to breeze") {
val vec = Vectors.dense(arr)
- assert(vec.toBreeze === new BDV[Double](arr))
+ assert(vec.asBreeze === new BDV[Double](arr))
}
test("sparse to breeze") {
val vec = Vectors.sparse(n, indices, values)
- assert(vec.toBreeze === new BSV[Double](indices, values, n))
+ assert(vec.asBreeze === new BSV[Double](indices, values, n))
}
test("dense breeze to vector") {
diff --git a/mllib-local/src/test/scala/org/apache/spark/ml/linalg/MatricesSuite.scala b/mllib-local/src/test/scala/org/apache/spark/ml/linalg/MatricesSuite.scala
index 5c69c5ed7b..2796fcf2cb 100644
--- a/mllib-local/src/test/scala/org/apache/spark/ml/linalg/MatricesSuite.scala
+++ b/mllib-local/src/test/scala/org/apache/spark/ml/linalg/MatricesSuite.scala
@@ -61,7 +61,7 @@ class MatricesSuite extends SparkMLFunSuite {
(1, 2, 2.0), (2, 2, 2.0), (1, 2, 2.0), (0, 0, 0.0))
val mat2 = SparseMatrix.fromCOO(m, n, entries)
- assert(mat.toBreeze === mat2.toBreeze)
+ assert(mat.asBreeze === mat2.asBreeze)
assert(mat2.values.length == 4)
}
@@ -174,8 +174,8 @@ class MatricesSuite extends SparkMLFunSuite {
val spMat2 = deMat1.toSparse
val deMat2 = spMat1.toDense
- assert(spMat1.toBreeze === spMat2.toBreeze)
- assert(deMat1.toBreeze === deMat2.toBreeze)
+ assert(spMat1.asBreeze === spMat2.asBreeze)
+ assert(deMat1.asBreeze === deMat2.asBreeze)
}
test("map, update") {
@@ -209,8 +209,8 @@ class MatricesSuite extends SparkMLFunSuite {
val sATexpected =
new SparseMatrix(3, 4, Array(0, 1, 2, 3, 4), Array(1, 0, 1, 2), Array(2.0, 1.0, 1.0, 3.0))
- assert(dAT.toBreeze === dATexpected.toBreeze)
- assert(sAT.toBreeze === sATexpected.toBreeze)
+ assert(dAT.asBreeze === dATexpected.asBreeze)
+ assert(sAT.asBreeze === sATexpected.asBreeze)
assert(dA(1, 0) === dAT(0, 1))
assert(dA(2, 1) === dAT(1, 2))
assert(sA(1, 0) === sAT(0, 1))
@@ -219,8 +219,8 @@ class MatricesSuite extends SparkMLFunSuite {
assert(!dA.toArray.eq(dAT.toArray), "has to have a new array")
assert(dA.values.eq(dAT.transpose.asInstanceOf[DenseMatrix].values), "should not copy array")
- assert(dAT.toSparse.toBreeze === sATexpected.toBreeze)
- assert(sAT.toDense.toBreeze === dATexpected.toBreeze)
+ assert(dAT.toSparse.asBreeze === sATexpected.asBreeze)
+ assert(sAT.toDense.asBreeze === dATexpected.asBreeze)
}
test("foreachActive") {
diff --git a/mllib-local/src/test/scala/org/apache/spark/ml/linalg/VectorsSuite.scala b/mllib-local/src/test/scala/org/apache/spark/ml/linalg/VectorsSuite.scala
index 887814b5e7..614be460a4 100644
--- a/mllib-local/src/test/scala/org/apache/spark/ml/linalg/VectorsSuite.scala
+++ b/mllib-local/src/test/scala/org/apache/spark/ml/linalg/VectorsSuite.scala
@@ -230,7 +230,7 @@ class VectorsSuite extends SparkMLFunSuite {
val denseVector1 = Vectors.dense(sparseVector1.toArray)
val denseVector2 = Vectors.dense(sparseVector2.toArray)
- val squaredDist = breezeSquaredDistance(sparseVector1.toBreeze, sparseVector2.toBreeze)
+ val squaredDist = breezeSquaredDistance(sparseVector1.asBreeze, sparseVector2.asBreeze)
// SparseVector vs. SparseVector
assert(Vectors.sqdist(sparseVector1, sparseVector2) ~== squaredDist relTol 1E-8)