Github user Lewuathe commented on a diff in the pull request:
https://github.com/apache/spark/pull/5707#discussion_r30123899
--- Diff: python/pyspark/mllib/tests.py ---
@@ -818,6 +819,40 @@ def test_model_transform(self):
self.assertEqual(model.transform([1.0, 2.0, 3.0]),
DenseVector([1.0, 2.0, 3.0]))
+class MLUtilsTests(MLlibTestCase):
+ def test_append_bias(self):
+ data = [2.0, 2.0, 2.0]
+ ret = MLUtils.appendBias(data)
+ self.assertEqual(ret[3], 1.0)
+ self.assertEqual(type(ret), list)
+
+ def test_append_bias_with_vector(self):
+ data = Vectors.dense([2.0, 2.0, 2.0])
+ ret = MLUtils.appendBias(data)
+ self.assertEqual(ret[3], 1.0)
+ self.assertEqual(type(ret), list)
+
+ def test_load_vectors(self):
+ import shutil
+ data = [
+ [1.0, 2.0, 3.0],
+ [1.0, 2.0, 3.0]
+ ]
+ temp_dir = tempfile.mkdtemp()
+ load_vectors_path = os.path.join(temp_dir, "test_load_vectors")
+ try:
+ self.sc.parallelize(data).saveAsTextFile(load_vectors_path)
+ ret_rdd = MLUtils.loadVectors(self.sc, load_vectors_path)
+ ret = ret_rdd.collect()
+ self.assertEqual(len(ret), 2)
+ self.assertEqual(ret[0], DenseVector([1.0, 2.0, 3.0]))
+ self.assertEqual(ret[1], DenseVector([1.0, 2.0, 3.0]))
+ except:
+ self.fail()
--- End diff --
In order to confirm the existence of vectors exported with
`saveAsTextFile`, it should be removed on each time this test runs.
---
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]
