diff options
author | Xiangrui Meng <meng@databricks.com> | 2015-02-17 10:17:45 -0800 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-02-17 10:17:45 -0800 |
commit | c76da36c2163276b5c34e59fbb139eeb34ed0faa (patch) | |
tree | ded3c1ff10a27cd88bc8ba81b4a71b2ae84a8aa7 /python/pyspark/__init__.py | |
parent | 3ce46e94fe77d15f18e916b76b37fa96356ace93 (diff) | |
download | spark-c76da36c2163276b5c34e59fbb139eeb34ed0faa.tar.gz spark-c76da36c2163276b5c34e59fbb139eeb34ed0faa.tar.bz2 spark-c76da36c2163276b5c34e59fbb139eeb34ed0faa.zip |
[SPARK-5858][MLLIB] Remove unnecessary first() call in GLM
`numFeatures` is only used by multinomial logistic regression. Calling `.first()` for every GLM causes performance regression, especially in Python.
Author: Xiangrui Meng <meng@databricks.com>
Closes #4647 from mengxr/SPARK-5858 and squashes the following commits:
036dc7f [Xiangrui Meng] remove unnecessary first() call
12c5548 [Xiangrui Meng] check numFeatures only once
Diffstat (limited to 'python/pyspark/__init__.py')
0 files changed, 0 insertions, 0 deletions