Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[LUCENE-4345] - fixed javadoc for DatasetSplitter 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1415079 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Tommaso Teofili 2012-11-29 08:28:08 +00:00
parent e39fe565ab
commit 0602a9fc16
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
lucene/classification/src/java/org/apache/lucene/classification/utils/DatasetSplitter.java
View File

@ -48,6 +48,16 @@ public class DatasetSplitter {
this.testRatio = testRatio;
}
/**
* Split a given index into 3 indexes for training, test and cross validation tasks respectively
* @param originalIndex an {@link AtomicReader} on the source index
* @param trainingIndex a {@link Directory} used to write the training index
* @param testIndex a {@link Directory} used to write the test index
* @param crossValidationIndex a {@link Directory} used to write the cross validation index
* @param analyzer {@link Analyzer} used to create the new docs
* @param fieldNames names of fields that need to be put in the new indexes or <code>null</code> if all should be used
* @throws IOException if any writing operation fails on any of the indexes
*/
public void split(AtomicReader originalIndex, Directory trainingIndex, Directory testIndex, Directory crossValidationIndex,
Analyzer analyzer, String... fieldNames) throws IOException {