Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/4274#discussion_r23832172
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala
---
@@ -237,4 +239,88 @@ class BlockMatrix(
val localMat = toLocalMatrix()
new BDM[Double](localMat.numRows, localMat.numCols, localMat.toArray)
}
+
+ /** Adds two block matrices together. The matrices must have the same
size and matching
+ * `rowsPerBlock` and `colsPerBlock` values. */
+ def add(other: BlockMatrix): BlockMatrix = {
+ require(numRows() == other.numRows(), "Both matrices must have the
same number of rows. " +
+ s"A.numRows: ${numRows()}, B.numRows: ${other.numRows()}")
+ require(numCols() == other.numCols(), "Both matrices must have the
same number of columns. " +
+ s"A.numCols: ${numCols()}, B.numCols: ${other.numCols()}")
+ if (checkPartitioning(other, OperationNames.add)) {
+ val addedBlocks = blocks.cogroup(other.blocks, partitioner).
+ map { case ((blockRowIndex, blockColIndex), (a, b)) =>
+ if (a.isEmpty) {
+ new MatrixBlock((blockRowIndex, blockColIndex), b.head)
+ } else if (b.isEmpty) {
+ new MatrixBlock((blockRowIndex, blockColIndex), a.head)
+ } else {
+ val result = a.head.toBreeze + b.head.toBreeze
+ new MatrixBlock((blockRowIndex, blockColIndex),
Matrices.fromBreeze(result))
+ }
+ }
+ new BlockMatrix(addedBlocks, rowsPerBlock, colsPerBlock, numRows(),
numCols())
+ } else {
+ throw new SparkException(
+ "Cannot add matrices with non-matching partitioners")
+ }
+ }
+
+ /** Left multiplies this [[BlockMatrix]] to `other`, another
[[BlockMatrix]]. The `colsPerBlock`
+ * of this matrix must equal the `rowsPerBlock` of `other`. If `other`
contains
+ * [[SparseMatrix]], they will have to be converted to a
+ * [[DenseMatrix]]. This may cause some performance issues until
support for multiplying
+ * two sparse matrices is added.
+ */
+ def multiply(other: BlockMatrix): BlockMatrix = {
+ require(numCols() == other.numRows(), "The number of columns of A and
the number of rows " +
+ s"of B must be equal. A.numCols: ${numCols()}, B.numRows:
${other.numRows()}. If you " +
+ s"think they should be equal, try setting the dimensions of A and B
explicitly while " +
+ s"initializing them.")
+ if (checkPartitioning(other, OperationNames.multiply)) {
--- End diff --
Same here. We can embedded the logic here.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
