Github user dusenberrymw commented on a diff in the pull request:
https://github.com/apache/spark/pull/7963#discussion_r36552801
--- Diff: python/pyspark/mllib/linalg/distributed.py ---
@@ -151,6 +151,112 @@ def numCols(self):
"""
return self._java_matrix_wrapper.call("numCols")
+ def computeSVD(self, k, computeU=False, rCond=1e-9):
+ """
+ Computes the singular value decomposition of the RowMatrix.
+
+ The given row matrix A of dimension (m X n) is decomposed into U *
s * V'T where
+
+ * U: (m X k) (left singular vectors) is a RowMatrix whose columns
are the
+ eigenvectors of (A X A')
+ * s: DenseVector consisting of square root of the eigenvalues
(singular values)
+ in descending order.
+ * v: (n X k) (right singular vectors) is a Matrix whose columns
are the
+ eigenvectors of (A' X A)
+
+ For more specific details on implementation, please refer the
scala documentation.
+
+ :param k: Set the number of singular values to keep.
+ :param computeU: Whether of not to compute U. If set to be True,
then U is computed
+ by A * V * s^-1
+ :param rCond: Reciprocal condition number. All singular values
smaller than
+ rCond * s[0] are treated as zero, where s[0] is the
largest
+ singular value.
+ :returns: SingularValueDecomposition object
+
+ >>> data = [(3, 1, 1), (-1, 3, 1)]
+ >>> rm = RowMatrix(sc.parallelize(data))
+ >>> svd_model = rm.computeSVD(2, True)
+ >>> svd_model.U.rows.collect()
+ [DenseVector([-0.7071, 0.7071]), DenseVector([-0.7071, -0.7071])]
+ >>> svd_model.s
+ DenseVector([3.4641, 3.1623])
+ >>> svd_model.V
+ DenseMatrix(3, 2, [-0.4082, -0.8165, -0.4082, 0.8944, -0.4472,
0.0], 0)
+ """
+ j_model = self._java_matrix_wrapper.call("computeSVD", int(k),
computeU, float(rCond))
+ return SingularValueDecomposition(j_model)
+
+ def computePrincipalComponents(self, k):
+ """
+ Computes the k principal components of the given row matrix
+
+ :param k: Number of principal components to keep.
+ :returns: DenseMatrix
+
+ >>> data = sc.parallelize([[1, 2, 3], [2, 4, 5], [3, 6, 1]])
+ >>> rm = RowMatrix(data)
+
+ >>> # Returns the two principal components of rm
+ >>> pca = rm.computePrincipalComponents(2)
+ >>> pca
+ DenseMatrix(3, 2, [-0.349, -0.6981, 0.6252, -0.2796, -0.5592,
-0.7805], 0)
+
+ >>> # Transform into new dimensions with the greatest variance.
+ >>> rm.multiply(pca).rows.collect() # doctest:
+NORMALIZE_WHITESPACE
+ [DenseVector([0.1305, -3.7394]), DenseVector([-0.3642, -6.6983]), \
+ DenseVector([-4.6102, -4.9745])]
+ """
+ return
self._java_matrix_wrapper.call("computePrincipalComponents", k)
+
+ def multiply(self, matrix):
+ """
+ Multiplies the given RowMatrix with another matrix.
+
+ :param matrix: Matrix to multiply with.
+ :returns: RowMatrix
+
+ >>> rm = RowMatrix(sc.parallelize([[0, 1], [2, 3]]))
+ >>> rm.multiply(DenseMatrix(2, 2, [0, 2, 1, 3])).rows.collect()
+ [DenseVector([2.0, 3.0]), DenseVector([6.0, 11.0])]
+ """
+ # TODO: Only DenseMatrices are supported on the Scala side.
--- End diff --
Good call, it would definitely be helpful to check that `matrix` is a
`DenseMatrix` 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]
