You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@madlib.apache.org by iyerr3 <gi...@git.apache.org> on 2018/03/26 04:55:10 UTC
[GitHub] madlib pull request #249: RF: Use NULL::integer[] when no continuous feature...
GitHub user iyerr3 opened a pull request:
https://github.com/apache/madlib/pull/249
RF: Use NULL::integer[] when no continuous features
JIRA: MADLIB-1219
When variable importance is enabled, to compute importance score,
distribution of the categorical and continuous features are computed.
For continuous features, this function requires initializing a vector of
length = number of continuous features. When there are no continuous
features, this initialization fails.
This commit fixes the issue by inputing a NULL::integer[] vector when
there no continuous features.
Closes #249
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/iyerr3/incubator-madlib bugfix/rf_var_imp_no_continuous
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/madlib/pull/249.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 #249
----
----
---
[GitHub] madlib issue #249: RF: Use NULL::integer[] when no continuous features
Posted by iyerr3 <gi...@git.apache.org>.
Github user iyerr3 commented on the issue:
https://github.com/apache/madlib/pull/249
@kaknikhil Thanks for the suggestion. It makes sense to use that function with integer types excluded (since DT does not treat integer as continuous). I'll add that as a separate commit since it's unrelated to this PR.
---
[GitHub] madlib issue #249: RF: Use NULL::integer[] when no continuous features
Posted by asfgit <gi...@git.apache.org>.
Github user asfgit commented on the issue:
https://github.com/apache/madlib/pull/249
Refer to this link for build results (access rights to CI server needed):
https://builds.apache.org/job/madlib-pr-build/406/
---
[GitHub] madlib issue #249: RF: Use NULL::integer[] when no continuous features
Posted by asfgit <gi...@git.apache.org>.
Github user asfgit commented on the issue:
https://github.com/apache/madlib/pull/249
Refer to this link for build results (access rights to CI server needed):
https://builds.apache.org/job/madlib-pr-build/402/
---
[GitHub] madlib issue #249: RF: Use NULL::integer[] when no continuous features
Posted by fmcquillan99 <gi...@git.apache.org>.
Github user fmcquillan99 commented on the issue:
https://github.com/apache/madlib/pull/249
See https://issues.apache.org/jira/browse/MADLIB-1219 for results from my tests.
LGTM
---
[GitHub] madlib issue #249: RF: Use NULL::integer[] when no continuous features
Posted by asfgit <gi...@git.apache.org>.
Github user asfgit commented on the issue:
https://github.com/apache/madlib/pull/249
Refer to this link for build results (access rights to CI server needed):
https://builds.apache.org/job/madlib-pr-build/403/
---
[GitHub] madlib issue #249: RF: Use NULL::integer[] when no continuous features
Posted by kaknikhil <gi...@git.apache.org>.
Github user kaknikhil commented on the issue:
https://github.com/apache/madlib/pull/249
The changes look good. +1 for adding an install check test.
I noticed that `con_features` is populated by `decision_tree.py:_classify_features` which does something like `con_types = ['real', 'float8', 'double precision', 'numeric']`. Is it better to call the utilities function `is_psql_numeric_type` ?
---
[GitHub] madlib pull request #249: RF: Use NULL::integer[] when no continuous feature...
Posted by asfgit <gi...@git.apache.org>.
Github user asfgit closed the pull request at:
https://github.com/apache/madlib/pull/249
---