madlib-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From iyerr3 <...@git.apache.org>
Subject [GitHub] incubator-madlib pull request #111: Decision Tree: Multiple fixes - pruning,...
Date Wed, 05 Apr 2017 00:20:59 GMT
GitHub user iyerr3 opened a pull request:

    https://github.com/apache/incubator-madlib/pull/111

    Decision Tree: Multiple fixes - pruning, tree_depth, viz

    Commit includes following changes:
    - Pruning is not performed when cp = 0 (default behavior)
    - Integer categorical variable is treated as ordered and hence is not
      re-ordered (using the response variable)
    - Visualization is improved: nodes with categorical feature splits only
      provide the last value in the split, instead of the complete list.
      This is consistent with the visualization in scikit-learn.
    - A particular bug is fixed: User input of max_depth starts from 0 and
      the internal tree_depth starts from 1. This change was not taken into
      account when tree train termination was checked.

You can merge this pull request into a Git repository by running:

    $ git pull https://github.com/iyerr3/incubator-madlib bugfix/dt_accuracy_test

Alternatively you can review and apply these changes as the patch at:

    https://github.com/apache/incubator-madlib/pull/111.patch

To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:

    This closes #111
    
----
commit b29f43c56b772325d70f6c2bdaf7660837c32153
Author: Rahul Iyer <riyer@apache.org>
Date:   2017-04-04T21:55:49Z

    Decision Tree: Multiple fixes - pruning, tree_depth, viz
    
    Commit includes following changes:
    - Pruning is not performed when cp = 0 (default behavior)
    - Integer categorical variable is treated as ordered and hence is not
      re-ordered (using the response variable)
    - Visualization is improved: nodes with categorical feature splits only
      provide the last value in the split, instead of the complete list.
      This is consistent with the visualization in scikit-learn.
    - A particular bug is fixed: User input of max_depth starts from 0 and
      the internal tree_depth starts from 1. This change was not taken into
      account when tree train termination was checked.

----


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message