You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by me...@apache.org on 2015/04/02 02:03:42 UTC
spark git commit: [SPARK-6576] [MLlib] [PySpark] DenseMatrix in
PySpark should support indexing
Repository: spark
Updated Branches:
refs/heads/master ccafd757e -> 2fa3b47db
[SPARK-6576] [MLlib] [PySpark] DenseMatrix in PySpark should support indexing
Support indexing in DenseMatrices in PySpark
Author: MechCoder <ma...@gmail.com>
Closes #5232 from MechCoder/SPARK-6576 and squashes the following commits:
a735078 [MechCoder] Change bounds
a062025 [MechCoder] Matrices are stored in column order
7917bc1 [MechCoder] [SPARK-6576] DenseMatrix in PySpark should support indexing
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/2fa3b47d
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/2fa3b47d
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/2fa3b47d
Branch: refs/heads/master
Commit: 2fa3b47dbf38aae58514473932c69bbd35de4e4c
Parents: ccafd75
Author: MechCoder <ma...@gmail.com>
Authored: Wed Apr 1 17:03:39 2015 -0700
Committer: Xiangrui Meng <me...@databricks.com>
Committed: Wed Apr 1 17:03:39 2015 -0700
----------------------------------------------------------------------
python/pyspark/mllib/linalg.py | 10 ++++++++++
python/pyspark/mllib/tests.py | 7 +++++++
2 files changed, 17 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/2fa3b47d/python/pyspark/mllib/linalg.py
----------------------------------------------------------------------
diff --git a/python/pyspark/mllib/linalg.py b/python/pyspark/mllib/linalg.py
index 8b791ff..51c1490 100644
--- a/python/pyspark/mllib/linalg.py
+++ b/python/pyspark/mllib/linalg.py
@@ -670,6 +670,16 @@ class DenseMatrix(Matrix):
"""
return self.values.reshape((self.numRows, self.numCols), order='F')
+ def __getitem__(self, indices):
+ i, j = indices
+ if i < 0 or i >= self.numRows:
+ raise ValueError("Row index %d is out of range [0, %d)"
+ % (i, self.numRows))
+ if j >= self.numCols or j < 0:
+ raise ValueError("Column index %d is out of range [0, %d)"
+ % (j, self.numCols))
+ return self.values[i + j * self.numRows]
+
def __eq__(self, other):
return (isinstance(other, DenseMatrix) and
self.numRows == other.numRows and
http://git-wip-us.apache.org/repos/asf/spark/blob/2fa3b47d/python/pyspark/mllib/tests.py
----------------------------------------------------------------------
diff --git a/python/pyspark/mllib/tests.py b/python/pyspark/mllib/tests.py
index 3bb0f0c..893fc6f 100644
--- a/python/pyspark/mllib/tests.py
+++ b/python/pyspark/mllib/tests.py
@@ -135,6 +135,13 @@ class VectorTests(PySparkTestCase):
for ind in [4, -5, 7.8]:
self.assertRaises(ValueError, sv.__getitem__, ind)
+ def test_matrix_indexing(self):
+ mat = DenseMatrix(3, 2, [0, 1, 4, 6, 8, 10])
+ expected = [[0, 6], [1, 8], [4, 10]]
+ for i in range(3):
+ for j in range(2):
+ self.assertEquals(mat[i, j], expected[i][j])
+
class ListTests(PySparkTestCase):
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org