[
https://issues.apache.org/jira/browse/MADLIB-1205?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16537837#comment-16537837
]
ASF GitHub Bot commented on MADLIB-1205:
----------------------------------------
GitHub user orhankislal opened a pull request:
https://github.com/apache/madlib/pull/289
RF: Add impurity variable importance
JIRA: MADLIB-1205
This commit makes the following changes:
- Add impurity variable importance for random forests.
- Rename current cat_var_importance and con_var_importance measurements to
oob_cat_var_importance and oob_con_var_importance.
New impurity measurement is provided as impurity_var_importance, and
supports
grouping. It combines the importance values for both categorical and
continuous features into a single array.
Co-authored-by: Rahul Iyer <[email protected]>
Co-authored-by: Jingyi Mei <[email protected]>
Co-authored-by: Arvind Sridhar <[email protected]>
Co-authored-by: Nandish Jayaram <[email protected]>
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/madlib/madlib rf_gini_importance
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/madlib/pull/289.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 #289
----
commit 622d46a85f4264fdc94bd41dc66a23f1aa2c3ed6
Author: Rahul Iyer <riyer@...>
Date: 2018-07-10T00:34:33Z
RF: Add impurity variable importance
JIRA: MADLIB-1205
This commit makes the following changes:
- Add impurity variable importance for random forests.
- Rename current cat_var_importance and con_var_importance measurements to
oob_cat_var_importance and oob_con_var_importance.
New impurity measurement is provided as impurity_var_importance, and
supports
grouping. It combines the importance values for both categorical and
continuous features into a single array.
Co-authored-by: Rahul Iyer <[email protected]>
Co-authored-by: Jingyi Mei <[email protected]>
Co-authored-by: Arvind Sridhar <[email protected]>
Co-authored-by: Nandish Jayaram <[email protected]>
----
> Add gini importance to DT
> -------------------------
>
> Key: MADLIB-1205
> URL: https://issues.apache.org/jira/browse/MADLIB-1205
> Project: Apache MADlib
> Issue Type: New Feature
> Components: Module: Decision Tree, Module: Random Forest
> Reporter: Rahul Iyer
> Assignee: Rahul Iyer
> Priority: Major
> Fix For: v1.15
>
>
> From the Breiman resource that we use for random forest:
> {quote}Gini importance
> {quote}
> {quote}Every time a split of a node is made on variable m the gini impurity
> criterion for the two descendent nodes is less than the parent node. Adding
> up the gini decreases for each individual variable over all trees in the
> forest gives a fast variable importance that is often very consistent with
> the permutation importance measure.
> {quote}
> We can add a similar measure in our DT code called as
> {{impurity_variable_importance}}.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
