Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/3319#discussion_r22010770
--- Diff: mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala
---
@@ -197,6 +300,171 @@ 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) {
+ sRows.append(r)
+ sparseA.append(v)
+ while (c != lastCol) {
+ sCols.append(nnz)
+ lastCol += 1
+ }
+ nnz += 1
+ }
+ i += 1
+ }
+ while (numCols > lastCol) {
+ sCols.append(sparseA.length)
+ lastCol += 1
+ }
+ new SparseMatrix(numRows, numCols, sCols.toArray, sRows.toArray,
sparseA.toArray)
+ }
+
+ /**
+ * Generate a `SparseMatrix` consisting of i.i.d. uniform random numbers.
+ * @param numRows number of rows of the matrix
+ * @param numCols number of columns of the matrix
+ * @param density the desired density for the matrix
+ * @param rng a random number generator
+ * @return `SparseMatrix` with size `numRows` x `numCols` and values in
U(0, 1)
+ */
+ def sprand(numRows: Int, numCols: Int, density: Double, rng: Random):
SparseMatrix = {
+ require(density >= 0.0 && density <= 1.0, "density must be a double in
the range " +
+ s"0.0 <= d <= 1.0. Currently, density: $density")
+ val length = numRows * numCols
+ val rawA = new Array[Double](length)
+ var nnz = 0
+ for (i <- 0 until length) {
--- End diff --
`sprand` is not generated this way, which has `O(m * n)` complexity. Please
check MATLAB's implementation of octave's.
---
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
