Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/2378#discussion_r17756431
--- Diff: python/pyspark/mllib/tests.py ---
@@ -198,41 +212,36 @@ def test_serialize(self):
lil[1, 0] = 1
lil[3, 0] = 2
sv = SparseVector(4, {1: 1, 3: 2})
- self.assertEquals(sv, _convert_vector(lil))
- self.assertEquals(sv, _convert_vector(lil.tocsc()))
- self.assertEquals(sv, _convert_vector(lil.tocoo()))
- self.assertEquals(sv, _convert_vector(lil.tocsr()))
- self.assertEquals(sv, _convert_vector(lil.todok()))
- self.assertEquals(sv,
_deserialize_double_vector(_serialize_double_vector(lil)))
- self.assertEquals(sv,
_deserialize_double_vector(_serialize_double_vector(lil.tocsc())))
- self.assertEquals(sv,
_deserialize_double_vector(_serialize_double_vector(lil.tocsr())))
- self.assertEquals(sv,
_deserialize_double_vector(_serialize_double_vector(lil.todok())))
+ self.assertEquals(sv, _convert_to_vector(lil))
+ self.assertEquals(sv, _convert_to_vector(lil.tocsc()))
+ self.assertEquals(sv, _convert_to_vector(lil.tocoo()))
+ self.assertEquals(sv, _convert_to_vector(lil.tocsr()))
+ self.assertEquals(sv, _convert_to_vector(lil.todok()))
+
+ def serialize(l):
+ return ser.loads(ser.dumps(_convert_to_vector(l)))
+ self.assertEquals(sv, serialize(lil))
+ self.assertEquals(sv, serialize(lil.tocsc()))
+ self.assertEquals(sv, serialize(lil.tocsr()))
+ self.assertEquals(sv, serialize(lil.todok()))
def test_dot(self):
from scipy.sparse import lil_matrix
lil = lil_matrix((4, 1))
lil[1, 0] = 1
lil[3, 0] = 2
- dv = array([1., 2., 3., 4.])
- sv = SparseVector(4, {0: 1, 1: 2, 2: 3, 3: 4})
- mat = array([[1., 2., 3., 4.],
- [1., 2., 3., 4.],
- [1., 2., 3., 4.],
- [1., 2., 3., 4.]])
- self.assertEquals(10.0, _dot(lil, dv))
- self.assertTrue(array_equal(array([3., 6., 9., 12.]), _dot(lil,
mat)))
+ dv = DenseVector(array([1., 2., 3., 4.]))
+ self.assertEquals(10.0, dv.dot(lil))
--- End diff --
I guess the assumption in the old code was that one of the arguments of
dot() would be an array represented as a 1-dimensional matrix. Now that I
think about it, that functionality is better left as traditional matrix-vector
multiplication. I revoke my previous comment!
---
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]
