Github user brkyvz commented on a diff in the pull request: https://github.com/apache/spark/pull/3319#discussion_r21881678 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala --- @@ -197,6 +295,171 @@ class SparseMatrix( } override def copy = new SparseMatrix(numRows, numCols, colPtrs, rowIndices, values.clone()) + + private[mllib] def map(f: Double => Double) = + new SparseMatrix(numRows, numCols, colPtrs, rowIndices, values.map(f)) + + private[mllib] def update(f: Double => Double): SparseMatrix = { + val len = values.length + var i = 0 + while (i < len) { + values(i) = f(values(i)) + i += 1 + } + this + } +} + +/** + * Factory methods for [[org.apache.spark.mllib.linalg.SparseMatrix]]. + */ +object SparseMatrix { + + /** + * Generate an Identity Matrix in `SparseMatrix` format. + * @param n number of rows and columns of the matrix + * @return `SparseMatrix` with size `n` x `n` and values of ones on the diagonal + */ + def speye(n: Int): SparseMatrix = { + new SparseMatrix(n, n, (0 to n).toArray, (0 until n).toArray, Array.fill(n)(1.0)) + } + + /** Generates a SparseMatrix given an Array[Double] of size numRows * numCols. The number of + * non-zeros in `raw` is provided for efficiency. */ + private def genRand( + numRows: Int, + numCols: Int, + raw: Array[Double], + nonZero: Int): SparseMatrix = { + val sparseA: ArrayBuffer[Double] = new ArrayBuffer(nonZero) + val sCols: ArrayBuffer[Int] = new ArrayBuffer(numCols + 1) + val sRows: ArrayBuffer[Int] = new ArrayBuffer(nonZero) + + var i = 0 + var nnz = 0 + var lastCol = -1 + raw.foreach { v => + val r = i % numRows + val c = (i - r) / numRows + if ( v != 0.0) { --- End diff -- Right now, it's not. Currently users can supply zero values during the construction of SparseMatrix. Two things: 1) Should I add a check in the constructor of SparseMatrix? 2) Should I transform genRand into something like .toSparse() inside DenseMatrix, and add a .toDense() inside SparseMatrix? (I actually had these two methods in my multi model training repo)
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org