Repository: spark
Updated Branches:
  refs/heads/branch-1.5 77eeaad98 -> 15d2736af


[SPARK-10959] [PYSPARK] StreamingLogisticRegressionWithSGD does not t…

…rain with given regParam and StreamingLinearRegressionWithSGD intercept 
param is not in correct position.

regParam was being passed into the StreamingLogisticRegressionWithSGD 
constructor, but not transferred to the call for model training. The param is 
added as a named argument to the call.  For StreamingLinearRegressionWithSGC 
the intercept parameter was not in the correct position and was being passed in 
as the regularization value.

Author: Bryan Cutler <[email protected]>

Closes #9087 from BryanCutler/StreamingSGD-convergenceTol-bug-10959-branch-1.5.


Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/15d2736a
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/15d2736a
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/15d2736a

Branch: refs/heads/branch-1.5
Commit: 15d2736af7b521a666ffb4e83cd253db08c4ac96
Parents: 77eeaad
Author: Bryan Cutler <[email protected]>
Authored: Tue Oct 13 15:59:36 2015 -0700
Committer: Xiangrui Meng <[email protected]>
Committed: Tue Oct 13 15:59:36 2015 -0700

----------------------------------------------------------------------
 python/pyspark/mllib/classification.py | 3 ++-
 python/pyspark/mllib/regression.py     | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark/blob/15d2736a/python/pyspark/mllib/classification.py
----------------------------------------------------------------------
diff --git a/python/pyspark/mllib/classification.py 
b/python/pyspark/mllib/classification.py
index 8f27c44..e4500a0 100644
--- a/python/pyspark/mllib/classification.py
+++ b/python/pyspark/mllib/classification.py
@@ -632,7 +632,8 @@ class 
StreamingLogisticRegressionWithSGD(StreamingLinearAlgorithm):
             if not rdd.isEmpty():
                 self._model = LogisticRegressionWithSGD.train(
                     rdd, self.numIterations, self.stepSize,
-                    self.miniBatchFraction, self._model.weights)
+                    self.miniBatchFraction, self._model.weights,
+                    regParam=self.regParam)
 
         dstream.foreachRDD(update)
 

http://git-wip-us.apache.org/repos/asf/spark/blob/15d2736a/python/pyspark/mllib/regression.py
----------------------------------------------------------------------
diff --git a/python/pyspark/mllib/regression.py 
b/python/pyspark/mllib/regression.py
index 41946e3..6bbac02 100644
--- a/python/pyspark/mllib/regression.py
+++ b/python/pyspark/mllib/regression.py
@@ -669,7 +669,7 @@ class 
StreamingLinearRegressionWithSGD(StreamingLinearAlgorithm):
                 self._model = LinearRegressionWithSGD.train(
                     rdd, self.numIterations, self.stepSize,
                     self.miniBatchFraction, self._model.weights,
-                    self._model.intercept)
+                    intercept=self._model.intercept)
 
         dstream.foreachRDD(update)
 


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to