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 2015/03/20 22:18:23 UTC
spark git commit: [SPARK-6421][MLLIB] _regression_train_wrapper does
not test initialWeights correctly
Repository: spark
Updated Branches:
refs/heads/master 11e025956 -> 257cde7c3
[SPARK-6421][MLLIB] _regression_train_wrapper does not test initialWeights correctly
Weight parameters must be initialized correctly even when numpy array is passed as initial weights.
Author: lewuathe <le...@me.com>
Closes #5101 from Lewuathe/SPARK-6421 and squashes the following commits:
7795201 [lewuathe] Fix lint-python errors
21d4fe3 [lewuathe] Fix init logic of weights
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/257cde7c
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/257cde7c
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/257cde7c
Branch: refs/heads/master
Commit: 257cde7c363efb3317bfb5c13975cca9154894e2
Parents: 11e0259
Author: lewuathe <le...@me.com>
Authored: Fri Mar 20 17:18:18 2015 -0400
Committer: Xiangrui Meng <me...@databricks.com>
Committed: Fri Mar 20 17:18:18 2015 -0400
----------------------------------------------------------------------
python/pyspark/mllib/regression.py | 3 ++-
python/pyspark/mllib/tests.py | 7 +++++++
2 files changed, 9 insertions(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/257cde7c/python/pyspark/mllib/regression.py
----------------------------------------------------------------------
diff --git a/python/pyspark/mllib/regression.py b/python/pyspark/mllib/regression.py
index 015a786..414a0ad 100644
--- a/python/pyspark/mllib/regression.py
+++ b/python/pyspark/mllib/regression.py
@@ -163,7 +163,8 @@ def _regression_train_wrapper(train_func, modelClass, data, initial_weights):
first = data.first()
if not isinstance(first, LabeledPoint):
raise ValueError("data should be an RDD of LabeledPoint, but got %s" % first)
- initial_weights = initial_weights or [0.0] * len(data.first().features)
+ if initial_weights is None:
+ initial_weights = [0.0] * len(data.first().features)
weights, intercept = train_func(data, _convert_to_vector(initial_weights))
return modelClass(weights, intercept)
http://git-wip-us.apache.org/repos/asf/spark/blob/257cde7c/python/pyspark/mllib/tests.py
----------------------------------------------------------------------
diff --git a/python/pyspark/mllib/tests.py b/python/pyspark/mllib/tests.py
index 5328d99..1550196 100644
--- a/python/pyspark/mllib/tests.py
+++ b/python/pyspark/mllib/tests.py
@@ -323,6 +323,13 @@ class ListTests(PySparkTestCase):
self.assertTrue(gbt_model.predict(features[2]) <= 0)
self.assertTrue(gbt_model.predict(features[3]) > 0)
+ try:
+ LinearRegressionWithSGD.train(rdd, initialWeights=array([1.0, 1.0]))
+ LassoWithSGD.train(rdd, initialWeights=array([1.0, 1.0]))
+ RidgeRegressionWithSGD.train(rdd, initialWeights=array([1.0, 1.0]))
+ except ValueError:
+ self.fail()
+
class StatTests(PySparkTestCase):
# SPARK-4023
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org