[SPARK-6421] _regression_train_wrapper does not test initialWeights correctly

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 1.3.0
• Fix Version/s: 1.3.1, 1.4.0
• Component/s: MLlib, PySpark
• Target Version/s: 1.3.1, 1.4.0
• Assignee: Kai
• Reporter: Joseph K. Bradley
• Created: 19/Mar/15 23:08
• Updated: 20/Mar/15 21:18
• Resolved: 20/Mar/15 21:18

Description

There is a bug in this line: https://github.com/apache/spark/blob/f17d43b033d928dbc46aef8e367aa08902e698ad/python/pyspark/mllib/regression.py#L138

You can reproduce this bug as follows:

>>> from numpy import array
>>> a = array([1,2,3])
>>> b = a or [1.0] * 3
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

Issue Links

• links to: [Github] Pull Request #5101 (Lewuathe)