Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/15628#discussion_r107803088
--- Diff:
mllib-local/src/main/scala/org/apache/spark/ml/linalg/Matrices.scala ---
@@ -291,31 +404,49 @@ 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) {
+ new DenseMatrix(numRows, numCols, toArray, isTransposed = false)
+ } else if (!isTransposed && !colMajor) {
+ new DenseMatrix(numRows, numCols, transpose.toArray, isTransposed =
true)
+ } else {
+ this
}
- new SparseMatrix(numRows, numCols, colPtrs, rowIndices.result(),
spVals.result())
}
--- End diff --
I have to say I'm a bit surprised - I thought that's what `toArray` already
did! Yeah, that seems like a good change, but I'd prefer to do it in another pr
because we need to make sure that this doesn't adversely affect other places
that use `toArray` as well as adding unit tests. If that sounds ok, I'll make a
JIRA for it.
---
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
