spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From sethah <...@git.apache.org>
Subject [GitHub] spark pull request #15628: [SPARK-17471][ML] Add compressed method to ML mat...
Date Thu, 23 Mar 2017 14:52:56 GMT
Github user sethah commented on a diff in the pull request:

    https://github.com/apache/spark/pull/15628#discussion_r107689306
  
    --- Diff: mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala ---
    @@ -291,31 +396,60 @@ class DenseMatrix @Since("2.0.0") (
       override def numActives: Int = values.length
     
       /**
    -   * Generate a `SparseMatrix` from the given `DenseMatrix`. The new matrix will have
isTransposed
    -   * set to false.
    +   * Generate a `SparseMatrix` from the given `DenseMatrix`.
    +   *
    +   * @param colMajor Whether the resulting `SparseMatrix` values will be in column major
order.
        */
    -  @Since("2.0.0")
    -  def toSparse: SparseMatrix = {
    -    val spVals: MArrayBuilder[Double] = new MArrayBuilder.ofDouble
    -    val colPtrs: Array[Int] = new Array[Int](numCols + 1)
    -    val rowIndices: MArrayBuilder[Int] = new MArrayBuilder.ofInt
    -    var nnz = 0
    -    var j = 0
    -    while (j < numCols) {
    -      var i = 0
    -      while (i < numRows) {
    -        val v = values(index(i, j))
    -        if (v != 0.0) {
    -          rowIndices += i
    -          spVals += v
    -          nnz += 1
    +  private[ml] override def toSparseMatrix(colMajor: Boolean): SparseMatrix = {
    +    if (!colMajor) this.transpose.toSparseMatrix(colMajor = true).transpose
    +    else {
    +      val spVals: MArrayBuilder[Double] = new MArrayBuilder.ofDouble
    +      val colPtrs: Array[Int] = new Array[Int](numCols + 1)
    +      val rowIndices: MArrayBuilder[Int] = new MArrayBuilder.ofInt
    +      var nnz = 0
    +      var j = 0
    +      while (j < numCols) {
    +        var i = 0
    +        while (i < numRows) {
    +          val v = values(index(i, j))
    +          if (v != 0.0) {
    +            rowIndices += i
    +            spVals += v
    +            nnz += 1
    +          }
    +          i += 1
             }
    -        i += 1
    +        j += 1
    +        colPtrs(j) = nnz
           }
    -      j += 1
    -      colPtrs(j) = nnz
    +      new SparseMatrix(numRows, numCols, colPtrs, rowIndices.result(), spVals.result())
    +    }
    +  }
    +
    +  /**
    +   * Generate a `DenseMatrix` from this `DenseMatrix`.
    +   *
    +   * @param colMajor Whether the resulting `DenseMatrix` values will be in column major
order.
    +   */
    +  private[ml] override def toDenseMatrix(colMajor: Boolean): DenseMatrix = {
    +    if (!(isTransposed ^ colMajor)) {
    +      val newValues = new Array[Double](numCols * numRows)
    +      var j = 0
    --- End diff --
    
    I don't see how there is an unnecessary copy. `toArray` copies the elements of the current
matrix to a new Array, then uses that as the backing array of a new `DenseMatrix`. We cannot
modify the original matrix values.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message