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 2015/04/06 01:13:28 UTC
spark git commit: [SPARK-6262][MLLIB]Implement missing methods for
MultivariateStatisticalSummary
Repository: spark
Updated Branches:
refs/heads/master f15806a8f -> acffc4345
[SPARK-6262][MLLIB]Implement missing methods for MultivariateStatisticalSummary
Add below methods in pyspark for MultivariateStatisticalSummary
- normL1
- normL2
Author: lewuathe <le...@me.com>
Closes #5359 from Lewuathe/SPARK-6262 and squashes the following commits:
cbe439e [lewuathe] Implement missing methods for MultivariateStatisticalSummary
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/acffc434
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/acffc434
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/acffc434
Branch: refs/heads/master
Commit: acffc43455d7b3e4000be4ff0175b8ea19cd280b
Parents: f15806a
Author: lewuathe <le...@me.com>
Authored: Sun Apr 5 16:13:31 2015 -0700
Committer: Xiangrui Meng <me...@databricks.com>
Committed: Sun Apr 5 16:13:31 2015 -0700
----------------------------------------------------------------------
python/pyspark/mllib/stat/_statistics.py | 6 ++++++
python/pyspark/mllib/tests.py | 6 ++++++
2 files changed, 12 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/acffc434/python/pyspark/mllib/stat/_statistics.py
----------------------------------------------------------------------
diff --git a/python/pyspark/mllib/stat/_statistics.py b/python/pyspark/mllib/stat/_statistics.py
index 218ac14..1d83e9d 100644
--- a/python/pyspark/mllib/stat/_statistics.py
+++ b/python/pyspark/mllib/stat/_statistics.py
@@ -49,6 +49,12 @@ class MultivariateStatisticalSummary(JavaModelWrapper):
def min(self):
return self.call("min").toArray()
+ def normL1(self):
+ return self.call("normL1").toArray()
+
+ def normL2(self):
+ return self.call("normL2").toArray()
+
class Statistics(object):
http://git-wip-us.apache.org/repos/asf/spark/blob/acffc434/python/pyspark/mllib/tests.py
----------------------------------------------------------------------
diff --git a/python/pyspark/mllib/tests.py b/python/pyspark/mllib/tests.py
index dd3b66c..47dad7d 100644
--- a/python/pyspark/mllib/tests.py
+++ b/python/pyspark/mllib/tests.py
@@ -357,6 +357,12 @@ class StatTests(PySparkTestCase):
summary = Statistics.colStats(data)
self.assertEqual(10, summary.count())
+ def test_col_norms(self):
+ data = RandomRDDs.normalVectorRDD(self.sc, 1000, 10, 10)
+ summary = Statistics.colStats(data)
+ self.assertEqual(10, len(summary.normL1()))
+ self.assertEqual(10, len(summary.normL2()))
+
class VectorUDTTests(PySparkTestCase):
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org