[
https://issues.apache.org/jira/browse/LUCENE-7196?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Tommaso Teofili updated LUCENE-7196:
------------------------------------
Priority: Minor (was: Major)
> DataSplitter should be providing class centric doc sets in all generated
> indexes
> --------------------------------------------------------------------------------
>
> Key: LUCENE-7196
> URL: https://issues.apache.org/jira/browse/LUCENE-7196
> Project: Lucene - Core
> Issue Type: Improvement
> Components: modules/classification
> Reporter: Tommaso Teofili
> Priority: Minor
> Fix For: 6.1
>
>
> {{DataSplitter}} currently creates 3 indexes (train/test/cv) out of an
> _original_ index for evaluation of {{Classifiers}} however "class coverage"
> in such generated indexes is not guaranteed; that means e.g. in _training
> index_ only documents belonging to 50% of the class set could be indexed and
> hence classifiers may not be very effective. In order to provide more
> consistent evaluation the generated index should contain _ split-ratio * |
> docs in c |_ documents for each class _c_.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
