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

[LUCENE-4345] - adding kNN score as count / k for the most frequent class in results 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1403798 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Tommaso Teofili 2012-10-30 17:41:32 +00:00
parent 87f549a1f8
commit 010c5f8d98
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
lucene/classification/src/java/org/apache/lucene/classification/KNearestNeighborClassifier.java
View File

@ -32,6 +32,7 @@ import java.util.Map;
/**
* A k-Nearest Neighbor classifier (see <code>http://en.wikipedia.org/wiki/K-nearest_neighbors</code>) based
* on {@link MoreLikeThis}
*
* @lucene.experimental
*/
public class KNearestNeighborClassifier implements Classifier {
@ -44,6 +45,7 @@ public class KNearestNeighborClassifier implements Classifier {
/**
* Create a {@link Classifier} using kNN algorithm
*
* @param k the number of neighbors to analyze as an <code>int</code>
*/
public KNearestNeighborClassifier(int k) {
@ -62,8 +64,7 @@ public class KNearestNeighborClassifier implements Classifier {
Integer count = classCounts.get(cl);
if (count != null) {
classCounts.put(cl, count + 1);
}
else {
} else {
classCounts.put(cl, 1);
}
}
@ -76,7 +77,7 @@ public class KNearestNeighborClassifier implements Classifier {
assignedClass = cl;
}
}
double score = 1; // TODO : derive score from query
double score = classCounts.get(assignedClass) / k;
return new ClassificationResult(assignedClass, score);
}