Github user MechCoder commented on a diff in the pull request:
https://github.com/apache/spark/pull/7554#discussion_r35572557
--- Diff: python/pyspark/mllib/linalg.py ---
@@ -1152,9 +1156,385 @@ def sparse(numRows, numCols, colPtrs, rowIndices,
values):
return SparseMatrix(numRows, numCols, colPtrs, rowIndices, values)
+class DistributedMatrix(object):
+ """
+ Represents a distributively stored matrix backed by one or
+ more RDDs.
+
+ """
+ def numRows(self):
+ """Get or compute the number of rows."""
+ raise NotImplementedError
+
+ def numCols(self):
+ """Get or compute the number of cols."""
+ raise NotImplementedError
+
+
+class RowMatrix(DistributedMatrix):
+ """
+ Represents a row-oriented distributed Matrix with no meaningful
+ row indices.
+
+ .. note:: Experimental
+ """
+ def __init__(self, rows, numRows=0, numCols=0):
+ """
+ Create a wrapper over a Java RowMatrix.
+
+ :param rows: An RDD of Vectors.
+ """
+ if not isinstance(rows, RDD):
+ raise TypeError("rows should be an RDD object, got %s" %
type(rows))
+ first = rows.first()
+ if not isinstance(first, Vector):
+ raise TypeError("rows should be an RDD of Vectors, got an RDD
of %s" % type(first))
+
+ javaRowMatrix = callMLlibFunc("createRowMatrix", rows,
long(numRows), int(numCols))
+ self._jrm = JavaModelWrapper(javaRowMatrix)
+ self.rows = rows
+
+ @staticmethod
+ def _from_java(javaRowMatrix):
+ """Create a PySpark RowMatrix from a Java RowMatrix object."""
+ rows = JavaModelWrapper(javaRowMatrix).call("rows")
+ return RowMatrix(rows)
+
+ def numRows(self):
+ """
+ Get or compute the number of rows.
+
+ >>> rows = sc.parallelize([Vectors.dense([1, 2, 3]),
Vectors.dense([4, 5, 6]),
+ ... Vectors.dense([7, 8, 9]),
Vectors.dense([10, 11, 12])])
+ >>> rm = RowMatrix(rows)
+ >>> int(rm.numRows())
+ 4
+
+ >>> rows = sc.parallelize([Vectors.dense([1, 2, 3]),
Vectors.dense([4, 5, 6]),
+ ... Vectors.dense([7, 8, 9]),
Vectors.dense([10, 11, 12])])
+ >>> rm = RowMatrix(rows, 7, 6)
+ >>> int(rm.numRows())
+ 7
+ """
+ return self._jrm.call("numRows")
+
+ def numCols(self):
+ """
+ Get or compute the number of cols.
+
+ >>> rows = sc.parallelize([Vectors.dense([1, 2, 3]),
Vectors.dense([4, 5, 6]),
+ ... Vectors.dense([7, 8, 9]),
Vectors.dense([10, 11, 12])])
+ >>> rm = RowMatrix(rows)
+ >>> int(rm.numCols())
+ 3
+
+ >>> rows = sc.parallelize([Vectors.dense([1, 2, 3]),
Vectors.dense([4, 5, 6]),
+ ... Vectors.dense([7, 8, 9]),
Vectors.dense([10, 11, 12])])
+ >>> rm = RowMatrix(rows, 7, 6)
+ >>> int(rm.numCols())
+ 6
+ """
+ return self._jrm.call("numCols")
+
+
+class IndexedRow(object):
+ """
+ Represents a row of an IndexedRowMatrix.
+
+ Just a wrapper over a (long, Vector) tuple.
+
+ .. note:: Experimental
+ """
+ def __init__(self, index, vector):
+ self.index = long(index)
+ self.vector = _convert_to_vector(vector)
+
+ def __repr__(self):
+ return "IndexedRow(%s, %s)" % (self.index, self.vector)
+
+
+class IndexedRowMatrix(DistributedMatrix):
+ """
+ Represents a row-oriented distributed Matrix with indexed rows.
+
+ .. note:: Experimental
+ """
+ def __init__(self, rows, numRows=0, numCols=0):
+ """
+ Create a wrapper over a Java IndexedRowMatrix.
+
+ :param rows: An RDD of IndexedRows or (long, Vector) tuples.
+ """
+ if not isinstance(rows, RDD):
+ raise TypeError("rows should be an RDD object, got %s" %
type(rows))
+ first = rows.first()
+ if not (isinstance(first, IndexedRow) or
+ (isinstance(first, tuple) and len(first) == 2 and
+ isinstance(first[0], (long, int)) and
isinstance(first[1], Vector))):
+ raise TypeError("rows should be an RDD of IndexedRows or
(long, Vector) tuples, "
+ "got an RDD of %s" % type(first))
+
+ # We use DataFrames for serialization of IndexedRows from
+ # Python, so first convert the RDD to a DataFrame on this side.
+ # This will convert each IndexedRow to a Row containing the
+ # 'index' and 'vector' values, which can both be easily
+ # serialized. We will convert back to IndexedRows on the
+ # Scala side.
+ javaIndexedRowMatrix = callMLlibFunc("createIndexedRowMatrix",
rows.toDF(),
+ long(numRows), int(numCols))
+ self._jirm = JavaModelWrapper(javaIndexedRowMatrix)
+ self.rows = rows
+
+ @staticmethod
+ def _from_java(javaIndexedRowMatrix):
+ """Create a PySpark IndexedRowMatrix from a Java IndexedRowMatrix
object."""
+ # We use DataFrames for serialization of IndexedRows from
+ # Java, so we first convert the RDD of rows to a DataFrame
+ # on the Scala/Java side. Then we map each Row in the
+ # DataFrame back to an IndexedRow on this side.
+ rowsDF = callMLlibFunc("getIndexedRows", javaIndexedRowMatrix)
+ rows = rowsDF.map(lambda row: IndexedRow(row[0], row[1]))
+ return IndexedRowMatrix(rows)
+
+ def numRows(self):
+ """
+ Get or compute the number of rows.
+
+ >>> rows = sc.parallelize([IndexedRow(0, Vectors.dense([1, 2, 3])),
+ ... IndexedRow(1, Vectors.dense([4, 5, 6])),
+ ... IndexedRow(2, Vectors.dense([7, 8, 9])),
+ ... IndexedRow(3, Vectors.dense([10, 11,
12]))])
+ >>> rm = IndexedRowMatrix(rows)
+ >>> int(rm.numRows())
+ 4
+
+ >>> rows = sc.parallelize([IndexedRow(0, Vectors.dense([1, 2, 3])),
+ ... IndexedRow(1, Vectors.dense([4, 5, 6])),
+ ... IndexedRow(2, Vectors.dense([7, 8, 9])),
+ ... IndexedRow(3, Vectors.dense([10, 11,
12]))])
+ >>> rm = IndexedRowMatrix(rows, 7, 6)
+ >>> int(rm.numRows())
+ 7
+ """
+ return self._jirm.call("numRows")
+
+ def numCols(self):
+ """
+ Get or compute the number of cols.
+
+ >>> rows = sc.parallelize([IndexedRow(0, Vectors.dense([1, 2, 3])),
+ ... IndexedRow(1, Vectors.dense([4, 5, 6])),
+ ... IndexedRow(2, Vectors.dense([7, 8, 9])),
+ ... IndexedRow(3, Vectors.dense([10, 11,
12]))])
+ >>> rm = IndexedRowMatrix(rows)
+ >>> int(rm.numCols())
+ 3
+
+ >>> rows = sc.parallelize([IndexedRow(0, Vectors.dense([1, 2, 3])),
+ ... IndexedRow(1, Vectors.dense([4, 5, 6])),
+ ... IndexedRow(2, Vectors.dense([7, 8, 9])),
+ ... IndexedRow(3, Vectors.dense([10, 11,
12]))])
+ >>> rm = IndexedRowMatrix(rows, 7, 6)
+ >>> int(rm.numCols())
+ 6
+ """
+ return self._jirm.call("numCols")
+
+ def toRowMatrix(self):
+ """
+ Convert this matrix to a RowMatrix.
+
+ >>> rows = sc.parallelize([IndexedRow(0, Vectors.dense([1, 2, 3])),
+ ... IndexedRow(6, Vectors.dense([4, 5,
6]))])
+ >>> rm = IndexedRowMatrix(rows).toRowMatrix()
+ >>> rm.rows.collect()
+ [DenseVector([1.0, 2.0, 3.0]), DenseVector([4.0, 5.0, 6.0])]
+ """
+ javaRowMatrix = self._jirm.call("toRowMatrix")
+ return RowMatrix._from_java(javaRowMatrix)
+
+ def toCoordinateMatrix(self):
+ """
+ Convert this matrix to a CoordinateMatrix.
+
+ >>> rows = sc.parallelize([IndexedRow(0, Vectors.dense([1, 0])),
+ ... IndexedRow(6, Vectors.dense([0, 5]))])
+ >>> cm = IndexedRowMatrix(rows).toCoordinateMatrix()
+ >>> cm.entries.take(3)
+ [MatrixEntry(0, 0, 1.0), MatrixEntry(0, 1, 0.0), MatrixEntry(6, 0,
0.0)]
+ """
+ javaCoordinateMatrix = self._jirm.call("toCoordinateMatrix")
+ return CoordinateMatrix._from_java(javaCoordinateMatrix)
+
+
+class MatrixEntry(object):
+ """
+ Represents an entry of a CoordinateMatrix.
+
+ Just a wrapper over a (long, long, float) tuple.
--- End diff --
nit: you could move this over to document i, j and value
---
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]
