diff options
| author | Holden Karau <holden@pigscanfly.ca> | 2015-06-22 22:40:19 -0700 |
|---|---|---|
| committer | Joseph K. Bradley <joseph@databricks.com> | 2015-06-22 22:40:19 -0700 |
| commit | 164fe2aa44993da6c77af6de5efdae47a8b3958c (patch) | |
| tree | 938944e023b53542ee306edcecec99a24d66429f /python/pyspark/mllib/tests.py | |
| parent | 44fa7df64daa55bd6eb1f2c219a9701b34e1c2a3 (diff) | |
| download | spark-164fe2aa44993da6c77af6de5efdae47a8b3958c.tar.gz spark-164fe2aa44993da6c77af6de5efdae47a8b3958c.tar.bz2 spark-164fe2aa44993da6c77af6de5efdae47a8b3958c.zip | |
[SPARK-7781] [MLLIB] gradient boosted trees.train regressor missing max bins
Author: Holden Karau <holden@pigscanfly.ca>
Closes #6331 from holdenk/SPARK-7781-GradientBoostedTrees.trainRegressor-missing-max-bins and squashes the following commits:
2894695 [Holden Karau] remove extra blank line
2573e8d [Holden Karau] Update the scala side of the pythonmllibapi and make the test a bit nicer too
3a09170 [Holden Karau] add maxBins to to the train method as well
af7f274 [Holden Karau] Add maxBins to GradientBoostedTrees.trainRegressor and correctly mention the default of 32 in other places where it mentioned 100
Diffstat (limited to 'python/pyspark/mllib/tests.py')
| -rw-r--r-- | python/pyspark/mllib/tests.py | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/python/pyspark/mllib/tests.py b/python/pyspark/mllib/tests.py index b13159e29d..c8d61b9855 100644 --- a/python/pyspark/mllib/tests.py +++ b/python/pyspark/mllib/tests.py @@ -463,6 +463,13 @@ class ListTests(MLlibTestCase): except ValueError: self.fail() + # Verify that maxBins is being passed through + GradientBoostedTrees.trainRegressor( + rdd, categoricalFeaturesInfo=categoricalFeaturesInfo, numIterations=4, maxBins=32) + with self.assertRaises(Exception) as cm: + GradientBoostedTrees.trainRegressor( + rdd, categoricalFeaturesInfo=categoricalFeaturesInfo, numIterations=4, maxBins=1) + class StatTests(MLlibTestCase): # SPARK-4023 |