[
https://issues.apache.org/jira/browse/SOLR-3700?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13444827#comment-13444827
]
Tommaso Teofili commented on SOLR-3700:
---------------------------------------
the suggested snippet for calculating the frequency of terms (from the
'content' field) in docs with a certain class is ok apart that the terms should
be extracted from the text field instead of the class field and the docFreq
should be counted on the class field:
{code}
Terms terms = MultiFields.getTerms(atomicReader, textFieldName);
long numPostings = terms.getSumDocFreq(); // number of term/doc pairs
double avgNumberOfUniqueTerms = numPostings / (double) terms.getDocCount();
// avg # of unique terms per doc
int docsWithC = atomicReader.docFreq(classFieldName, new BytesRef(c));
return avgNumberOfUniqueTerms * docsWithC; // avg # of unique terms in text
field per doc * # docs with c
{code}
comparing the previous (slow) ranked search giving an output of 92 this gives
an estimated output of ~98.6 which seems reasonable.
> Create a Classification component
> ---------------------------------
>
> Key: SOLR-3700
> URL: https://issues.apache.org/jira/browse/SOLR-3700
> Project: Solr
> Issue Type: New Feature
> Reporter: Tommaso Teofili
> Assignee: Tommaso Teofili
> Priority: Minor
> Attachments: SOLR-3700_2.patch, SOLR-3700.patch
>
>
> Lucene/Solr can host huge sets of documents containing lots of information in
> fields so that these can be used as training examples (w/ features) in order
> to very quickly create classifiers algorithms to use on new documents and /
> or to provide an additional service.
> So the idea is to create a contrib module (called 'classification') to host a
> ClassificationComponent that will use already seen data (the indexed
> documents / fields) to classify new documents / text fragments.
> The first version will contain a (simplistic) Lucene based Naive Bayes
> classifier but more implementations should be added in the future.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
