Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/4256#discussion_r23739791
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala
---
@@ -182,6 +184,38 @@ class BlockMatrix(
this
}
+ /** Converts to CoordinateMatrix. */
+ def toCoordinateMatrix(): CoordinateMatrix = {
+ val entryRDD = blocks.flatMap { case ((blockRowIndex, blockColIndex),
mat) =>
+ val rowStart = blockRowIndex.toLong * rowsPerBlock
+ val colStart = blockColIndex.toLong * colsPerBlock
+ mat match {
+ case dn: DenseMatrix =>
+ val entryValues = new ArrayBuffer[MatrixEntry](mat.numRows *
mat.numCols)
+ dn.foreachActive { (i, j, v) =>
+ if (v != 0.0) entryValues.append(new MatrixEntry(rowStart + i,
colStart + j, v))
+ }
+ entryValues
+ case sp: SparseMatrix =>
+ val entryValues = new Array[MatrixEntry](sp.values.length)
+ var cnt = 0
+ sp.foreachActive { (i, j, v) =>
+ entryValues(cnt) = new MatrixEntry(rowStart + i, colStart + j,
v)
+ cnt += 1
+ }
+ entryValues
+ }
+ }
+ new CoordinateMatrix(entryRDD, numRows(), numCols())
+ }
+
+ /** Converts to IndexedRowMatrix. The number of columns must be within
the integer range. */
+ def toIndexedRowMatrix(): IndexedRowMatrix = {
+ require(numCols() < Int.MaxValue, "The number of columns must be
within the integer range. " +
+ s"numCols: ${numCols()}")
+ toCoordinateMatrix().toIndexedRowMatrix()
--- End diff --
Add a TODO so we remember to optimize it later.
---
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]
