[SPARK-16328][ML][MLLIB][PYSPARK] Add 'asML' and 'fromML' conversion methods to PySpark linalg

The move to `ml.linalg` created `asML`/`fromML` utility methods in Scala/Java for converting between representations. These are missing in Python, this PR adds them.

## How was this patch tested?

New doctests.

Author: Nick Pentreath <nickp@za.ibm.com>

Closes #13997 from MLnick/SPARK-16328-python-linalg-convert.

1 files changed, 99 insertions, 0 deletions

diff --git a/python/pyspark/mllib/linalg/__init__.py b/python/pyspark/mllib/linalg/__init__.py
index 3a345b2b56..15dc53a959 100644
--- a/python/pyspark/mllib/linalg/__init__.py
+++ b/python/pyspark/mllib/linalg/__init__.py
@@ -39,6 +39,7 @@ else:
 import numpy as np
 
 from pyspark import since
+from pyspark.ml import linalg as newlinalg
 from pyspark.sql.types import UserDefinedType, StructField, StructType, ArrayType, DoubleType, \
     IntegerType, ByteType, BooleanType
 
@@ -247,6 +248,15 @@ class Vector(object):
         """
         raise NotImplementedError
 
+    def asML(self):
+        """
+        Convert this vector to the new mllib-local representation.
+        This does NOT copy the data; it copies references.
+
+        :return: :py:class:`pyspark.ml.linalg.Vector`
+        """
+        raise NotImplementedError
+
 
 class DenseVector(Vector):
     """
@@ -408,6 +418,17 @@ class DenseVector(Vector):
         """
         return self.array
 
+    def asML(self):
+        """
+        Convert this vector to the new mllib-local representation.
+        This does NOT copy the data; it copies references.
+
+        :return: :py:class:`pyspark.ml.linalg.DenseVector`
+
+        .. versionadded:: 2.0.0
+        """
+        return newlinalg.DenseVector(self.array)
+
     @property
     def values(self):
         """
@@ -737,6 +758,17 @@ class SparseVector(Vector):
         arr[self.indices] = self.values
         return arr
 
+    def asML(self):
+        """
+        Convert this vector to the new mllib-local representation.
+        This does NOT copy the data; it copies references.
+
+        :return: :py:class:`pyspark.ml.linalg.SparseVector`
+
+        .. versionadded:: 2.0.0
+        """
+        return newlinalg.SparseVector(self.size, self.indices, self.values)
+
     def __len__(self):
         return self.size
 
@@ -846,6 +878,24 @@ class Vectors(object):
         return DenseVector(elements)
 
     @staticmethod
+    def fromML(vec):
+        """
+        Convert a vector from the new mllib-local representation.
+        This does NOT copy the data; it copies references.
+
+        :param vec: a :py:class:`pyspark.ml.linalg.Vector`
+        :return: a :py:class:`pyspark.mllib.linalg.Vector`
+
+        .. versionadded:: 2.0.0
+        """
+        if isinstance(vec, newlinalg.DenseVector):
+            return DenseVector(vec.array)
+        elif isinstance(vec, newlinalg.SparseVector):
+            return SparseVector(vec.size, vec.indices, vec.values)
+        else:
+            raise TypeError("Unsupported vector type %s" % type(vec))
+
+    @staticmethod
     def stringify(vector):
         """
         Converts a vector into a string, which can be recognized by
@@ -945,6 +995,13 @@ class Matrix(object):
         """
         raise NotImplementedError
 
+    def asML(self):
+        """
+        Convert this matrix to the new mllib-local representation.
+        This does NOT copy the data; it copies references.
+        """
+        raise NotImplementedError
+
     @staticmethod
     def _convert_to_array(array_like, dtype):
         """
@@ -1044,6 +1101,17 @@ class DenseMatrix(Matrix):
 
         return SparseMatrix(self.numRows, self.numCols, colPtrs, rowIndices, values)
 
+    def asML(self):
+        """
+        Convert this matrix to the new mllib-local representation.
+        This does NOT copy the data; it copies references.
+
+        :return: :py:class:`pyspark.ml.linalg.DenseMatrix`
+
+        .. versionadded:: 2.0.0
+        """
+        return newlinalg.DenseMatrix(self.numRows, self.numCols, self.values, self.isTransposed)
+
     def __getitem__(self, indices):
         i, j = indices
         if i < 0 or i >= self.numRows:
@@ -1216,6 +1284,18 @@ class SparseMatrix(Matrix):
         densevals = np.ravel(self.toArray(), order='F')
         return DenseMatrix(self.numRows, self.numCols, densevals)
 
+    def asML(self):
+        """
+        Convert this matrix to the new mllib-local representation.
+        This does NOT copy the data; it copies references.
+
+        :return: :py:class:`pyspark.ml.linalg.SparseMatrix`
+
+        .. versionadded:: 2.0.0
+        """
+        return newlinalg.SparseMatrix(self.numRows, self.numCols, self.colPtrs, self.rowIndices,
+                                      self.values, self.isTransposed)
+
     # TODO: More efficient implementation:
     def __eq__(self, other):
         return np.all(self.toArray() == other.toArray())
@@ -1236,6 +1316,25 @@ class Matrices(object):
         """
         return SparseMatrix(numRows, numCols, colPtrs, rowIndices, values)
 
+    @staticmethod
+    def fromML(mat):
+        """
+        Convert a matrix from the new mllib-local representation.
+        This does NOT copy the data; it copies references.
+
+        :param mat: a :py:class:`pyspark.ml.linalg.Matrix`
+        :return: a :py:class:`pyspark.mllib.linalg.Matrix`
+
+        .. versionadded:: 2.0.0
+        """
+        if isinstance(mat, newlinalg.DenseMatrix):
+            return DenseMatrix(mat.numRows, mat.numCols, mat.values, mat.isTransposed)
+        elif isinstance(mat, newlinalg.SparseMatrix):
+            return SparseMatrix(mat.numRows, mat.numCols, mat.colPtrs, mat.rowIndices,
+                                mat.values, mat.isTransposed)
+        else:
+            raise TypeError("Unsupported matrix type %s" % type(mat))
+
 
 class QRDecomposition(object):
     """